summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2024-01-10 17:45:22 +0100
committerLinus Torvalds <torvalds@linux-foundation.org>2024-01-10 17:45:22 +0100
commit12958e9c4c8e93ef694c10960c78453edf21526e (patch)
tree80e4a3a945358d9a546c3f5cda25bc5ceadcdf7c
parentMerge tag 'fsnotify_for_v6.8-rc1' of git://git.kernel.org/pub/scm/linux/kerne... (diff)
parentxfs: use the op name in trace_xlog_intent_recovery_failed (diff)
downloadlinux-12958e9c4c8e93ef694c10960c78453edf21526e.tar.xz
linux-12958e9c4c8e93ef694c10960c78453edf21526e.zip
Merge tag 'xfs-6.8-merge-3' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux
Pull xfs updates from Chandan Babu: "New features/functionality: - Online repair: - Reserve disk space for online repairs - Fix misinteraction between the AIL and btree bulkloader because of which the bulk load fails to queue a buffer for writeback if it happens to be on the AIL list - Prevent transaction reservation overflows when reaping blocks during online repair - Whenever possible, bulkloader now copies multiple records into a block - Support repairing of 1. Per-AG free space, inode and refcount btrees 2. Ondisk inodes 3. File data and attribute fork mappings - Verify the contents of 1. Inode and data fork of realtime bitmap file 2. Quota files - Introduce MF_MEM_PRE_REMOVE. This will be used to notify tasks about a pmem device being removed Bug fixes: - Fix memory leak of recovered attri intent items - Fix UAF during log intent recovery - Fix realtime geometry integer overflows - Prevent scrub from live locking in xchk_iget - Prevent fs shutdown when removing files during low free disk space - Prevent transaction reservation overflow when extending an RT device - Prevent incorrect warning from being printed when extending a filesystem - Fix an off-by-one error in xreap_agextent_binval - Serialize access to perag radix tree during deletion operation - Fix perag memory leak during growfs - Allow allocation of minlen realtime extent when the maximum sized realtime free extent is minlen in size Cleanups: - Remove duplicate boilerplate code spread across functionality associated with different log items - Cleanup resblks interfaces - Pass defer ops pointer to defer helpers instead of an enum - Initialize di_crc in xfs_log_dinode to prevent KMSAN warnings - Use static_assert() instead of BUILD_BUG_ON_MSG() to validate size of structures and structure member offsets. This is done in order to be able to share the code with userspace - Move XFS documentation under a new directory specific to XFS - Do not invoke deferred ops' ->create_done callback if the deferred operation does not have an intent item associated with it - Remove duplicate inclusion of header files from scrub/health.c - Refactor Realtime code - Cleanup attr code" * tag 'xfs-6.8-merge-3' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux: (123 commits) xfs: use the op name in trace_xlog_intent_recovery_failed xfs: fix a use after free in xfs_defer_finish_recovery xfs: turn the XFS_DA_OP_REPLACE checks in xfs_attr_shortform_addname into asserts xfs: remove xfs_attr_sf_hdr_t xfs: remove struct xfs_attr_shortform xfs: use xfs_attr_sf_findname in xfs_attr_shortform_getvalue xfs: remove xfs_attr_shortform_lookup xfs: simplify xfs_attr_sf_findname xfs: move the xfs_attr_sf_lookup tracepoint xfs: return if_data from xfs_idata_realloc xfs: make if_data a void pointer xfs: fold xfs_rtallocate_extent into xfs_bmap_rtalloc xfs: simplify and optimize the RT allocation fallback cascade xfs: reorder the minlen and prod calculations in xfs_bmap_rtalloc xfs: remove XFS_RTMIN/XFS_RTMAX xfs: remove rt-wrappers from xfs_format.h xfs: factor out a xfs_rtalloc_sumlevel helper xfs: tidy up xfs_rtallocate_extent_exact xfs: merge the calls to xfs_rtallocate_range in xfs_rtallocate_block xfs: reflow the tail end of xfs_rtallocate_extent_block ...
-rw-r--r--Documentation/filesystems/index.rst5
-rw-r--r--Documentation/filesystems/xfs/index.rst14
-rw-r--r--Documentation/filesystems/xfs/xfs-delayed-logging-design.rst (renamed from Documentation/filesystems/xfs-delayed-logging-design.rst)0
-rw-r--r--Documentation/filesystems/xfs/xfs-maintainer-entry-profile.rst (renamed from Documentation/filesystems/xfs-maintainer-entry-profile.rst)0
-rw-r--r--Documentation/filesystems/xfs/xfs-online-fsck-design.rst (renamed from Documentation/filesystems/xfs-online-fsck-design.rst)2
-rw-r--r--Documentation/filesystems/xfs/xfs-self-describing-metadata.rst (renamed from Documentation/filesystems/xfs-self-describing-metadata.rst)0
-rw-r--r--Documentation/maintainer/maintainer-entry-profile.rst2
-rw-r--r--MAINTAINERS4
-rw-r--r--drivers/dax/super.c3
-rw-r--r--fs/xfs/Makefile21
-rw-r--r--fs/xfs/libxfs/xfs_ag.c38
-rw-r--r--fs/xfs/libxfs/xfs_ag.h12
-rw-r--r--fs/xfs/libxfs/xfs_ag_resv.c2
-rw-r--r--fs/xfs/libxfs/xfs_alloc.c116
-rw-r--r--fs/xfs/libxfs/xfs_alloc.h24
-rw-r--r--fs/xfs/libxfs/xfs_alloc_btree.c13
-rw-r--r--fs/xfs/libxfs/xfs_attr.c125
-rw-r--r--fs/xfs/libxfs/xfs_attr_leaf.c238
-rw-r--r--fs/xfs/libxfs/xfs_attr_leaf.h8
-rw-r--r--fs/xfs/libxfs/xfs_attr_sf.h24
-rw-r--r--fs/xfs/libxfs/xfs_bmap.c201
-rw-r--r--fs/xfs/libxfs/xfs_bmap.h9
-rw-r--r--fs/xfs/libxfs/xfs_bmap_btree.c123
-rw-r--r--fs/xfs/libxfs/xfs_bmap_btree.h5
-rw-r--r--fs/xfs/libxfs/xfs_btree.c28
-rw-r--r--fs/xfs/libxfs/xfs_btree.h5
-rw-r--r--fs/xfs/libxfs/xfs_btree_staging.c89
-rw-r--r--fs/xfs/libxfs/xfs_btree_staging.h33
-rw-r--r--fs/xfs/libxfs/xfs_da_btree.c69
-rw-r--r--fs/xfs/libxfs/xfs_da_btree.h2
-rw-r--r--fs/xfs/libxfs/xfs_da_format.h33
-rw-r--r--fs/xfs/libxfs/xfs_defer.c453
-rw-r--r--fs/xfs/libxfs/xfs_defer.h59
-rw-r--r--fs/xfs/libxfs/xfs_dir2.c2
-rw-r--r--fs/xfs/libxfs/xfs_dir2_block.c6
-rw-r--r--fs/xfs/libxfs/xfs_dir2_priv.h3
-rw-r--r--fs/xfs/libxfs/xfs_dir2_sf.c91
-rw-r--r--fs/xfs/libxfs/xfs_format.h19
-rw-r--r--fs/xfs/libxfs/xfs_health.h10
-rw-r--r--fs/xfs/libxfs/xfs_ialloc.c36
-rw-r--r--fs/xfs/libxfs/xfs_ialloc.h3
-rw-r--r--fs/xfs/libxfs/xfs_ialloc_btree.c2
-rw-r--r--fs/xfs/libxfs/xfs_iext_tree.c59
-rw-r--r--fs/xfs/libxfs/xfs_inode_fork.c78
-rw-r--r--fs/xfs/libxfs/xfs_inode_fork.h13
-rw-r--r--fs/xfs/libxfs/xfs_log_recover.h8
-rw-r--r--fs/xfs/libxfs/xfs_ondisk.h (renamed from fs/xfs/xfs_ondisk.h)22
-rw-r--r--fs/xfs/libxfs/xfs_refcount.c57
-rw-r--r--fs/xfs/libxfs/xfs_refcount.h12
-rw-r--r--fs/xfs/libxfs/xfs_refcount_btree.c15
-rw-r--r--fs/xfs/libxfs/xfs_rmap.c2
-rw-r--r--fs/xfs/libxfs/xfs_rtbitmap.c120
-rw-r--r--fs/xfs/libxfs/xfs_rtbitmap.h20
-rw-r--r--fs/xfs/libxfs/xfs_sb.c6
-rw-r--r--fs/xfs/libxfs/xfs_shared.h2
-rw-r--r--fs/xfs/libxfs/xfs_symlink_remote.c12
-rw-r--r--fs/xfs/libxfs/xfs_types.h8
-rw-r--r--fs/xfs/scrub/agb_bitmap.c103
-rw-r--r--fs/xfs/scrub/agb_bitmap.h68
-rw-r--r--fs/xfs/scrub/agheader_repair.c19
-rw-r--r--fs/xfs/scrub/alloc.c52
-rw-r--r--fs/xfs/scrub/alloc_repair.c934
-rw-r--r--fs/xfs/scrub/attr.c17
-rw-r--r--fs/xfs/scrub/bitmap.c467
-rw-r--r--fs/xfs/scrub/bitmap.h111
-rw-r--r--fs/xfs/scrub/bmap.c162
-rw-r--r--fs/xfs/scrub/bmap_repair.c867
-rw-r--r--fs/xfs/scrub/common.c35
-rw-r--r--fs/xfs/scrub/common.h56
-rw-r--r--fs/xfs/scrub/cow_repair.c614
-rw-r--r--fs/xfs/scrub/dir.c42
-rw-r--r--fs/xfs/scrub/dqiterate.c211
-rw-r--r--fs/xfs/scrub/fsb_bitmap.h37
-rw-r--r--fs/xfs/scrub/health.c34
-rw-r--r--fs/xfs/scrub/health.h2
-rw-r--r--fs/xfs/scrub/ialloc.c39
-rw-r--r--fs/xfs/scrub/ialloc_repair.c884
-rw-r--r--fs/xfs/scrub/inode.c20
-rw-r--r--fs/xfs/scrub/inode_repair.c1525
-rw-r--r--fs/xfs/scrub/newbt.c559
-rw-r--r--fs/xfs/scrub/newbt.h68
-rw-r--r--fs/xfs/scrub/off_bitmap.h37
-rw-r--r--fs/xfs/scrub/parent.c17
-rw-r--r--fs/xfs/scrub/quota.c107
-rw-r--r--fs/xfs/scrub/quota.h36
-rw-r--r--fs/xfs/scrub/quota_repair.c575
-rw-r--r--fs/xfs/scrub/readdir.c6
-rw-r--r--fs/xfs/scrub/reap.c168
-rw-r--r--fs/xfs/scrub/reap.h5
-rw-r--r--fs/xfs/scrub/refcount.c2
-rw-r--r--fs/xfs/scrub/refcount_repair.c794
-rw-r--r--fs/xfs/scrub/repair.c391
-rw-r--r--fs/xfs/scrub/repair.h99
-rw-r--r--fs/xfs/scrub/rmap.c1
-rw-r--r--fs/xfs/scrub/rtbitmap.c107
-rw-r--r--fs/xfs/scrub/rtbitmap.h22
-rw-r--r--fs/xfs/scrub/rtbitmap_repair.c202
-rw-r--r--fs/xfs/scrub/rtsummary.c143
-rw-r--r--fs/xfs/scrub/scrub.c62
-rw-r--r--fs/xfs/scrub/scrub.h15
-rw-r--r--fs/xfs/scrub/symlink.c22
-rw-r--r--fs/xfs/scrub/trace.c3
-rw-r--r--fs/xfs/scrub/trace.h488
-rw-r--r--fs/xfs/scrub/xfarray.h22
-rw-r--r--fs/xfs/xfs_attr_item.c295
-rw-r--r--fs/xfs/xfs_attr_list.c13
-rw-r--r--fs/xfs/xfs_bmap_item.c200
-rw-r--r--fs/xfs/xfs_bmap_util.c141
-rw-r--r--fs/xfs/xfs_bmap_util.h2
-rw-r--r--fs/xfs/xfs_buf.c44
-rw-r--r--fs/xfs/xfs_buf.h1
-rw-r--r--fs/xfs/xfs_dir2_readdir.c9
-rw-r--r--fs/xfs/xfs_dquot.c37
-rw-r--r--fs/xfs/xfs_dquot.h8
-rw-r--r--fs/xfs/xfs_extent_busy.c13
-rw-r--r--fs/xfs/xfs_extent_busy.h2
-rw-r--r--fs/xfs/xfs_extfree_item.c332
-rw-r--r--fs/xfs/xfs_fsops.c59
-rw-r--r--fs/xfs/xfs_fsops.h14
-rw-r--r--fs/xfs/xfs_globals.c12
-rw-r--r--fs/xfs/xfs_health.c8
-rw-r--r--fs/xfs/xfs_inode.c65
-rw-r--r--fs/xfs/xfs_inode.h2
-rw-r--r--fs/xfs/xfs_inode_item.c13
-rw-r--r--fs/xfs/xfs_ioctl.c115
-rw-r--r--fs/xfs/xfs_log.c1
-rw-r--r--fs/xfs/xfs_log_priv.h1
-rw-r--r--fs/xfs/xfs_log_recover.c131
-rw-r--r--fs/xfs/xfs_mount.c8
-rw-r--r--fs/xfs/xfs_notify_failure.c108
-rw-r--r--fs/xfs/xfs_quota.h5
-rw-r--r--fs/xfs/xfs_refcount_item.c234
-rw-r--r--fs/xfs/xfs_reflink.c2
-rw-r--r--fs/xfs/xfs_rmap_item.c257
-rw-r--r--fs/xfs/xfs_rtalloc.c659
-rw-r--r--fs/xfs/xfs_rtalloc.h37
-rw-r--r--fs/xfs/xfs_super.c6
-rw-r--r--fs/xfs/xfs_symlink.c7
-rw-r--r--fs/xfs/xfs_sysctl.h2
-rw-r--r--fs/xfs/xfs_sysfs.c63
-rw-r--r--fs/xfs/xfs_trace.h42
-rw-r--r--fs/xfs/xfs_trans.c62
-rw-r--r--fs/xfs/xfs_trans.h16
-rw-r--r--fs/xfs/xfs_xattr.c6
-rw-r--r--include/linux/mm.h1
-rw-r--r--mm/memory-failure.c21
146 files changed, 12727 insertions, 2943 deletions
diff --git a/Documentation/filesystems/index.rst b/Documentation/filesystems/index.rst
index 09cade7eaefc..e18bc5ae3b35 100644
--- a/Documentation/filesystems/index.rst
+++ b/Documentation/filesystems/index.rst
@@ -121,8 +121,5 @@ Documentation for filesystem implementations.
udf
virtiofs
vfat
- xfs-delayed-logging-design
- xfs-maintainer-entry-profile
- xfs-self-describing-metadata
- xfs-online-fsck-design
+ xfs/index
zonefs
diff --git a/Documentation/filesystems/xfs/index.rst b/Documentation/filesystems/xfs/index.rst
new file mode 100644
index 000000000000..ab66c57a5d18
--- /dev/null
+++ b/Documentation/filesystems/xfs/index.rst
@@ -0,0 +1,14 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+============================
+XFS Filesystem Documentation
+============================
+
+.. toctree::
+ :maxdepth: 2
+ :numbered:
+
+ xfs-delayed-logging-design
+ xfs-maintainer-entry-profile
+ xfs-self-describing-metadata
+ xfs-online-fsck-design
diff --git a/Documentation/filesystems/xfs-delayed-logging-design.rst b/Documentation/filesystems/xfs/xfs-delayed-logging-design.rst
index 6402ab8e370c..6402ab8e370c 100644
--- a/Documentation/filesystems/xfs-delayed-logging-design.rst
+++ b/Documentation/filesystems/xfs/xfs-delayed-logging-design.rst
diff --git a/Documentation/filesystems/xfs-maintainer-entry-profile.rst b/Documentation/filesystems/xfs/xfs-maintainer-entry-profile.rst
index 32b6ac4ca9d6..32b6ac4ca9d6 100644
--- a/Documentation/filesystems/xfs-maintainer-entry-profile.rst
+++ b/Documentation/filesystems/xfs/xfs-maintainer-entry-profile.rst
diff --git a/Documentation/filesystems/xfs-online-fsck-design.rst b/Documentation/filesystems/xfs/xfs-online-fsck-design.rst
index a0678101a7d0..352516feef6f 100644
--- a/Documentation/filesystems/xfs-online-fsck-design.rst
+++ b/Documentation/filesystems/xfs/xfs-online-fsck-design.rst
@@ -962,7 +962,7 @@ disk, but these buffer verifiers cannot provide any consistency checking
between metadata structures.
For more information, please see the documentation for
-Documentation/filesystems/xfs-self-describing-metadata.rst
+Documentation/filesystems/xfs/xfs-self-describing-metadata.rst
Reverse Mapping
---------------
diff --git a/Documentation/filesystems/xfs-self-describing-metadata.rst b/Documentation/filesystems/xfs/xfs-self-describing-metadata.rst
index a10c4ae6955e..a10c4ae6955e 100644
--- a/Documentation/filesystems/xfs-self-describing-metadata.rst
+++ b/Documentation/filesystems/xfs/xfs-self-describing-metadata.rst
diff --git a/Documentation/maintainer/maintainer-entry-profile.rst b/Documentation/maintainer/maintainer-entry-profile.rst
index 7ad4bfc2cc03..18cee1edaecb 100644
--- a/Documentation/maintainer/maintainer-entry-profile.rst
+++ b/Documentation/maintainer/maintainer-entry-profile.rst
@@ -105,4 +105,4 @@ to do something different in the near future.
../driver-api/media/maintainer-entry-profile
../driver-api/vfio-pci-device-specific-driver-acceptance
../nvme/feature-and-quirk-policy
- ../filesystems/xfs-maintainer-entry-profile
+ ../filesystems/xfs/xfs-maintainer-entry-profile
diff --git a/MAINTAINERS b/MAINTAINERS
index 40c754b4c39c..83240dcd4065 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -23846,10 +23846,10 @@ S: Supported
W: http://xfs.org/
C: irc://irc.oftc.net/xfs
T: git git://git.kernel.org/pub/scm/fs/xfs/xfs-linux.git
-P: Documentation/filesystems/xfs-maintainer-entry-profile.rst
+P: Documentation/filesystems/xfs/xfs-maintainer-entry-profile.rst
F: Documentation/ABI/testing/sysfs-fs-xfs
F: Documentation/admin-guide/xfs.rst
-F: Documentation/filesystems/xfs-*
+F: Documentation/filesystems/xfs/*
F: fs/xfs/
F: include/uapi/linux/dqblk_xfs.h
F: include/uapi/linux/fsmap.h
diff --git a/drivers/dax/super.c b/drivers/dax/super.c
index 0da9232ea175..f4b635526345 100644
--- a/drivers/dax/super.c
+++ b/drivers/dax/super.c
@@ -326,7 +326,8 @@ void kill_dax(struct dax_device *dax_dev)
return;
if (dax_dev->holder_data != NULL)
- dax_holder_notify_failure(dax_dev, 0, U64_MAX, 0);
+ dax_holder_notify_failure(dax_dev, 0, U64_MAX,
+ MF_MEM_PRE_REMOVE);
clear_bit(DAXDEV_ALIVE, &dax_dev->flags);
synchronize_srcu(&dax_srcu);
diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index 7762c01a85cf..fbe3cdc79036 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -145,6 +145,7 @@ ifeq ($(CONFIG_XFS_ONLINE_SCRUB),y)
xfs-y += $(addprefix scrub/, \
trace.o \
+ agb_bitmap.o \
agheader.o \
alloc.o \
attr.o \
@@ -175,14 +176,32 @@ xfs-$(CONFIG_XFS_RT) += $(addprefix scrub/, \
rtsummary.o \
)
-xfs-$(CONFIG_XFS_QUOTA) += scrub/quota.o
+xfs-$(CONFIG_XFS_QUOTA) += $(addprefix scrub/, \
+ dqiterate.o \
+ quota.o \
+ )
# online repair
ifeq ($(CONFIG_XFS_ONLINE_REPAIR),y)
xfs-y += $(addprefix scrub/, \
agheader_repair.o \
+ alloc_repair.o \
+ bmap_repair.o \
+ cow_repair.o \
+ ialloc_repair.o \
+ inode_repair.o \
+ newbt.o \
reap.o \
+ refcount_repair.o \
repair.o \
)
+
+xfs-$(CONFIG_XFS_RT) += $(addprefix scrub/, \
+ rtbitmap_repair.o \
+ )
+
+xfs-$(CONFIG_XFS_QUOTA) += $(addprefix scrub/, \
+ quota_repair.o \
+ )
endif
endif
diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c
index f9f4d694640d..39d9525270b7 100644
--- a/fs/xfs/libxfs/xfs_ag.c
+++ b/fs/xfs/libxfs/xfs_ag.c
@@ -332,6 +332,31 @@ xfs_agino_range(
return __xfs_agino_range(mp, xfs_ag_block_count(mp, agno), first, last);
}
+/*
+ * Free perag within the specified AG range, it is only used to free unused
+ * perags under the error handling path.
+ */
+void
+xfs_free_unused_perag_range(
+ struct xfs_mount *mp,
+ xfs_agnumber_t agstart,
+ xfs_agnumber_t agend)
+{
+ struct xfs_perag *pag;
+ xfs_agnumber_t index;
+
+ for (index = agstart; index < agend; index++) {
+ spin_lock(&mp->m_perag_lock);
+ pag = radix_tree_delete(&mp->m_perag_tree, index);
+ spin_unlock(&mp->m_perag_lock);
+ if (!pag)
+ break;
+ xfs_buf_hash_destroy(pag);
+ xfs_defer_drain_free(&pag->pag_intents_drain);
+ kmem_free(pag);
+ }
+}
+
int
xfs_initialize_perag(
struct xfs_mount *mp,
@@ -424,19 +449,14 @@ xfs_initialize_perag(
out_remove_pag:
xfs_defer_drain_free(&pag->pag_intents_drain);
+ spin_lock(&mp->m_perag_lock);
radix_tree_delete(&mp->m_perag_tree, index);
+ spin_unlock(&mp->m_perag_lock);
out_free_pag:
kmem_free(pag);
out_unwind_new_pags:
/* unwind any prior newly initialized pags */
- for (index = first_initialised; index < agcount; index++) {
- pag = radix_tree_delete(&mp->m_perag_tree, index);
- if (!pag)
- break;
- xfs_buf_hash_destroy(pag);
- xfs_defer_drain_free(&pag->pag_intents_drain);
- kmem_free(pag);
- }
+ xfs_free_unused_perag_range(mp, first_initialised, agcount);
return error;
}
@@ -984,7 +1004,7 @@ xfs_ag_shrink_space(
if (err2 != -ENOSPC)
goto resv_err;
- err2 = __xfs_free_extent_later(*tpp, args.fsbno, delta, NULL,
+ err2 = xfs_free_extent_later(*tpp, args.fsbno, delta, NULL,
XFS_AG_RESV_NONE, true);
if (err2)
goto resv_err;
diff --git a/fs/xfs/libxfs/xfs_ag.h b/fs/xfs/libxfs/xfs_ag.h
index 2e0aef87d633..4b343c4fac28 100644
--- a/fs/xfs/libxfs/xfs_ag.h
+++ b/fs/xfs/libxfs/xfs_ag.h
@@ -80,6 +80,16 @@ struct xfs_perag {
*/
uint16_t pag_checked;
uint16_t pag_sick;
+
+#ifdef CONFIG_XFS_ONLINE_REPAIR
+ /*
+ * Alternate btree heights so that online repair won't trip the write
+ * verifiers while rebuilding the AG btrees.
+ */
+ uint8_t pagf_repair_levels[XFS_BTNUM_AGF];
+ uint8_t pagf_repair_refcount_level;
+#endif
+
spinlock_t pag_state_lock;
spinlock_t pagb_lock; /* lock for pagb_tree */
@@ -133,6 +143,8 @@ __XFS_AG_OPSTATE(prefers_metadata, PREFERS_METADATA)
__XFS_AG_OPSTATE(allows_inodes, ALLOWS_INODES)
__XFS_AG_OPSTATE(agfl_needs_reset, AGFL_NEEDS_RESET)
+void xfs_free_unused_perag_range(struct xfs_mount *mp, xfs_agnumber_t agstart,
+ xfs_agnumber_t agend);
int xfs_initialize_perag(struct xfs_mount *mp, xfs_agnumber_t agcount,
xfs_rfsblock_t dcount, xfs_agnumber_t *maxagi);
int xfs_initialize_perag_data(struct xfs_mount *mp, xfs_agnumber_t agno);
diff --git a/fs/xfs/libxfs/xfs_ag_resv.c b/fs/xfs/libxfs/xfs_ag_resv.c
index 7fd1fea95552..da1057bd0e60 100644
--- a/fs/xfs/libxfs/xfs_ag_resv.c
+++ b/fs/xfs/libxfs/xfs_ag_resv.c
@@ -411,6 +411,8 @@ xfs_ag_resv_free_extent(
fallthrough;
case XFS_AG_RESV_NONE:
xfs_trans_mod_sb(tp, XFS_TRANS_SB_FDBLOCKS, (int64_t)len);
+ fallthrough;
+ case XFS_AG_RESV_IGNORE:
return;
}
diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index 100ab5931b31..3bd0a33fee0a 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -246,11 +246,9 @@ xfs_alloc_btrec_to_irec(
/* Simple checks for free space records. */
xfs_failaddr_t
xfs_alloc_check_irec(
- struct xfs_btree_cur *cur,
- const struct xfs_alloc_rec_incore *irec)
+ struct xfs_perag *pag,
+ const struct xfs_alloc_rec_incore *irec)
{
- struct xfs_perag *pag = cur->bc_ag.pag;
-
if (irec->ar_blockcount == 0)
return __this_address;
@@ -299,7 +297,7 @@ xfs_alloc_get_rec(
return error;
xfs_alloc_btrec_to_irec(rec, &irec);
- fa = xfs_alloc_check_irec(cur, &irec);
+ fa = xfs_alloc_check_irec(cur->bc_ag.pag, &irec);
if (fa)
return xfs_alloc_complain_bad_rec(cur, fa, &irec);
@@ -2514,7 +2512,7 @@ xfs_defer_agfl_block(
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);
+ xfs_defer_add(tp, &xefi->xefi_list, &xfs_agfl_free_defer_type);
return 0;
}
@@ -2522,14 +2520,15 @@ xfs_defer_agfl_block(
* Add the extent to the list of extents to be free at transaction end.
* The list is maintained sorted (by block number).
*/
-int
-__xfs_free_extent_later(
+static int
+xfs_defer_extent_free(
struct xfs_trans *tp,
xfs_fsblock_t bno,
xfs_filblks_t len,
const struct xfs_owner_info *oinfo,
enum xfs_ag_resv_type type,
- bool skip_discard)
+ bool skip_discard,
+ struct xfs_defer_pending **dfpp)
{
struct xfs_extent_free_item *xefi;
struct xfs_mount *mp = tp->t_mountp;
@@ -2577,10 +2576,105 @@ __xfs_free_extent_later(
XFS_FSB_TO_AGBNO(tp->t_mountp, bno), len);
xfs_extent_free_get_group(mp, xefi);
- xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_FREE, &xefi->xefi_list);
+ *dfpp = xfs_defer_add(tp, &xefi->xefi_list, &xfs_extent_free_defer_type);
return 0;
}
+int
+xfs_free_extent_later(
+ struct xfs_trans *tp,
+ xfs_fsblock_t bno,
+ xfs_filblks_t len,
+ const struct xfs_owner_info *oinfo,
+ enum xfs_ag_resv_type type,
+ bool skip_discard)
+{
+ struct xfs_defer_pending *dontcare = NULL;
+
+ return xfs_defer_extent_free(tp, bno, len, oinfo, type, skip_discard,
+ &dontcare);
+}
+
+/*
+ * Set up automatic freeing of unwritten space in the filesystem.
+ *
+ * This function attached a paused deferred extent free item to the
+ * transaction. Pausing means that the EFI will be logged in the next
+ * transaction commit, but the pending EFI will not be finished until the
+ * pending item is unpaused.
+ *
+ * If the system goes down after the EFI has been persisted to the log but
+ * before the pending item is unpaused, log recovery will find the EFI, fail to
+ * find the EFD, and free the space.
+ *
+ * If the pending item is unpaused, the next transaction commit will log an EFD
+ * without freeing the space.
+ *
+ * Caller must ensure that the tp, fsbno, len, oinfo, and resv flags of the
+ * @args structure are set to the relevant values.
+ */
+int
+xfs_alloc_schedule_autoreap(
+ const struct xfs_alloc_arg *args,
+ bool skip_discard,
+ struct xfs_alloc_autoreap *aarp)
+{
+ int error;
+
+ error = xfs_defer_extent_free(args->tp, args->fsbno, args->len,
+ &args->oinfo, args->resv, skip_discard, &aarp->dfp);
+ if (error)
+ return error;
+
+ xfs_defer_item_pause(args->tp, aarp->dfp);
+ return 0;
+}
+
+/*
+ * Cancel automatic freeing of unwritten space in the filesystem.
+ *
+ * Earlier, we created a paused deferred extent free item and attached it to
+ * this transaction so that we could automatically roll back a new space
+ * allocation if the system went down. Now we want to cancel the paused work
+ * item by marking the EFI stale so we don't actually free the space, unpausing
+ * the pending item and logging an EFD.
+ *
+ * The caller generally should have already mapped the space into the ondisk
+ * filesystem. If the reserved space was partially used, the caller must call
+ * xfs_free_extent_later to create a new EFI to free the unused space.
+ */
+void
+xfs_alloc_cancel_autoreap(
+ struct xfs_trans *tp,
+ struct xfs_alloc_autoreap *aarp)
+{
+ struct xfs_defer_pending *dfp = aarp->dfp;
+ struct xfs_extent_free_item *xefi;
+
+ if (!dfp)
+ return;
+
+ list_for_each_entry(xefi, &dfp->dfp_work, xefi_list)
+ xefi->xefi_flags |= XFS_EFI_CANCELLED;
+
+ xfs_defer_item_unpause(tp, dfp);
+}
+
+/*
+ * Commit automatic freeing of unwritten space in the filesystem.
+ *
+ * This unpauses an earlier _schedule_autoreap and commits to freeing the
+ * allocated space. Call this if none of the reserved space was used.
+ */
+void
+xfs_alloc_commit_autoreap(
+ struct xfs_trans *tp,
+ struct xfs_alloc_autoreap *aarp)
+{
+ if (aarp->dfp)
+ xfs_defer_item_unpause(tp, aarp->dfp);
+}
+
#ifdef DEBUG
/*
* Check if an AGF has a free extent record whose length is equal to
@@ -3848,7 +3942,7 @@ xfs_alloc_query_range_helper(
xfs_failaddr_t fa;
xfs_alloc_btrec_to_irec(rec, &irec);
- fa = xfs_alloc_check_irec(cur, &irec);
+ fa = xfs_alloc_check_irec(cur->bc_ag.pag, &irec);
if (fa)
return xfs_alloc_complain_bad_rec(cur, fa, &irec);
diff --git a/fs/xfs/libxfs/xfs_alloc.h b/fs/xfs/libxfs/xfs_alloc.h
index 6bb8d295c321..0b956f8b9d5a 100644
--- a/fs/xfs/libxfs/xfs_alloc.h
+++ b/fs/xfs/libxfs/xfs_alloc.h
@@ -185,7 +185,7 @@ xfs_alloc_get_rec(
union xfs_btree_rec;
void xfs_alloc_btrec_to_irec(const union xfs_btree_rec *rec,
struct xfs_alloc_rec_incore *irec);
-xfs_failaddr_t xfs_alloc_check_irec(struct xfs_btree_cur *cur,
+xfs_failaddr_t xfs_alloc_check_irec(struct xfs_perag *pag,
const struct xfs_alloc_rec_incore *irec);
int xfs_read_agf(struct xfs_perag *pag, struct xfs_trans *tp, int flags,
@@ -231,7 +231,7 @@ xfs_buf_to_agfl_bno(
return bp->b_addr;
}
-int __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,
enum xfs_ag_resv_type type, bool skip_discard);
@@ -255,18 +255,18 @@ void xfs_extent_free_get_group(struct xfs_mount *mp,
#define XFS_EFI_SKIP_DISCARD (1U << 0) /* don't issue discard */
#define XFS_EFI_ATTR_FORK (1U << 1) /* freeing attr fork block */
#define XFS_EFI_BMBT_BLOCK (1U << 2) /* freeing bmap btree block */
+#define XFS_EFI_CANCELLED (1U << 3) /* dont actually free the space */
-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,
- enum xfs_ag_resv_type type)
-{
- return __xfs_free_extent_later(tp, bno, len, oinfo, type, false);
-}
+struct xfs_alloc_autoreap {
+ struct xfs_defer_pending *dfp;
+};
+int xfs_alloc_schedule_autoreap(const struct xfs_alloc_arg *args,
+ bool skip_discard, struct xfs_alloc_autoreap *aarp);
+void xfs_alloc_cancel_autoreap(struct xfs_trans *tp,
+ struct xfs_alloc_autoreap *aarp);
+void xfs_alloc_commit_autoreap(struct xfs_trans *tp,
+ struct xfs_alloc_autoreap *aarp);
extern struct kmem_cache *xfs_extfree_item_cache;
diff --git a/fs/xfs/libxfs/xfs_alloc_btree.c b/fs/xfs/libxfs/xfs_alloc_btree.c
index c65228efed4a..a7032bf0cd37 100644
--- a/fs/xfs/libxfs/xfs_alloc_btree.c
+++ b/fs/xfs/libxfs/xfs_alloc_btree.c
@@ -323,7 +323,18 @@ xfs_allocbt_verify(
if (bp->b_ops->magic[0] == cpu_to_be32(XFS_ABTC_MAGIC))
btnum = XFS_BTNUM_CNTi;
if (pag && xfs_perag_initialised_agf(pag)) {
- if (level >= pag->pagf_levels[btnum])
+ unsigned int maxlevel = pag->pagf_levels[btnum];
+
+#ifdef CONFIG_XFS_ONLINE_REPAIR
+ /*
+ * Online repair could be rewriting the free space btrees, so
+ * we'll validate against the larger of either tree while this
+ * is going on.
+ */
+ maxlevel = max_t(unsigned int, maxlevel,
+ pag->pagf_repair_levels[btnum]);
+#endif
+ if (level >= maxlevel)
return __this_address;
} else if (level >= mp->m_alloc_maxlevels)
return __this_address;
diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c
index e28d93d232de..9976a00a73f9 100644
--- a/fs/xfs/libxfs/xfs_attr.c
+++ b/fs/xfs/libxfs/xfs_attr.c
@@ -862,8 +862,11 @@ xfs_attr_lookup(
if (!xfs_inode_hasattr(dp))
return -ENOATTR;
- if (dp->i_af.if_format == XFS_DINODE_FMT_LOCAL)
- return xfs_attr_sf_findname(args, NULL, NULL);
+ if (dp->i_af.if_format == XFS_DINODE_FMT_LOCAL) {
+ if (xfs_attr_sf_findname(args))
+ return -EEXIST;
+ return -ENOATTR;
+ }
if (xfs_attr_is_leaf(dp)) {
error = xfs_attr_leaf_hasname(args, &bp);
@@ -880,11 +883,10 @@ xfs_attr_lookup(
return error;
}
-static int
-xfs_attr_intent_init(
+static void
+xfs_attr_defer_add(
struct xfs_da_args *args,
- unsigned int op_flags, /* op flag (set or remove) */
- struct xfs_attr_intent **attr) /* new xfs_attr_intent */
+ unsigned int op_flags)
{
struct xfs_attr_intent *new;
@@ -893,66 +895,22 @@ xfs_attr_intent_init(
new->xattri_op_flags = op_flags;
new->xattri_da_args = args;
- *attr = new;
- return 0;
-}
-
-/* Sets an attribute for an inode as a deferred operation */
-static int
-xfs_attr_defer_add(
- struct xfs_da_args *args)
-{
- struct xfs_attr_intent *new;
- int error = 0;
-
- error = xfs_attr_intent_init(args, XFS_ATTRI_OP_FLAGS_SET, &new);
- if (error)
- return error;
+ switch (op_flags) {
+ case XFS_ATTRI_OP_FLAGS_SET:
+ new->xattri_dela_state = xfs_attr_init_add_state(args);
+ break;
+ case XFS_ATTRI_OP_FLAGS_REPLACE:
+ new->xattri_dela_state = xfs_attr_init_replace_state(args);
+ break;
+ case XFS_ATTRI_OP_FLAGS_REMOVE:
+ new->xattri_dela_state = xfs_attr_init_remove_state(args);
+ break;
+ default:
+ ASSERT(0);
+ }
- new->xattri_dela_state = xfs_attr_init_add_state(args);
- xfs_defer_add(args->trans, XFS_DEFER_OPS_TYPE_ATTR, &new->xattri_list);
+ xfs_defer_add(args->trans, &new->xattri_list, &xfs_attr_defer_type);
trace_xfs_attr_defer_add(new->xattri_dela_state, args->dp);
-
- return 0;
-}
-
-/* Sets an attribute for an inode as a deferred operation */
-static int
-xfs_attr_defer_replace(
- struct xfs_da_args *args)
-{
- struct xfs_attr_intent *new;
- int error = 0;
-
- error = xfs_attr_intent_init(args, XFS_ATTRI_OP_FLAGS_REPLACE, &new);
- if (error)
- return error;
-
- new->xattri_dela_state = xfs_attr_init_replace_state(args);
- xfs_defer_add(args->trans, XFS_DEFER_OPS_TYPE_ATTR, &new->xattri_list);
- trace_xfs_attr_defer_replace(new->xattri_dela_state, args->dp);
-
- return 0;
-}
-
-/* Removes an attribute for an inode as a deferred operation */
-static int
-xfs_attr_defer_remove(
- struct xfs_da_args *args)
-{
-
- struct xfs_attr_intent *new;
- int error;
-
- error = xfs_attr_intent_init(args, XFS_ATTRI_OP_FLAGS_REMOVE, &new);
- if (error)
- return error;
-
- new->xattri_dela_state = xfs_attr_init_remove_state(args);
- xfs_defer_add(args->trans, XFS_DEFER_OPS_TYPE_ATTR, &new->xattri_list);
- trace_xfs_attr_defer_remove(new->xattri_dela_state, args->dp);
-
- return 0;
}
/*
@@ -1038,16 +996,16 @@ xfs_attr_set(
error = xfs_attr_lookup(args);
switch (error) {
case -EEXIST:
- /* if no value, we are performing a remove operation */
if (!args->value) {
- error = xfs_attr_defer_remove(args);
+ /* if no value, we are performing a remove operation */
+ xfs_attr_defer_add(args, XFS_ATTRI_OP_FLAGS_REMOVE);
break;
}
+
/* Pure create fails if the attr already exists */
if (args->attr_flags & XATTR_CREATE)
goto out_trans_cancel;
-
- error = xfs_attr_defer_replace(args);
+ xfs_attr_defer_add(args, XFS_ATTRI_OP_FLAGS_REPLACE);
break;
case -ENOATTR:
/* Can't remove what isn't there. */
@@ -1057,14 +1015,11 @@ xfs_attr_set(
/* Pure replace fails if no existing attr to replace. */
if (args->attr_flags & XATTR_REPLACE)
goto out_trans_cancel;
-
- error = xfs_attr_defer_add(args);
+ xfs_attr_defer_add(args, XFS_ATTRI_OP_FLAGS_SET);
break;
default:
goto out_trans_cancel;
}
- if (error)
- goto out_trans_cancel;
/*
* If this is a synchronous mount, make sure that the
@@ -1097,10 +1052,9 @@ out_trans_cancel:
static inline int xfs_attr_sf_totsize(struct xfs_inode *dp)
{
- struct xfs_attr_shortform *sf;
+ struct xfs_attr_sf_hdr *sf = dp->i_af.if_data;
- sf = (struct xfs_attr_shortform *)dp->i_af.if_u1.if_data;
- return be16_to_cpu(sf->hdr.totsize);
+ return be16_to_cpu(sf->totsize);
}
/*
@@ -1112,19 +1066,13 @@ xfs_attr_shortform_addname(
struct xfs_da_args *args)
{
int newsize, forkoff;
- int error;
trace_xfs_attr_sf_addname(args);
- error = xfs_attr_shortform_lookup(args);
- switch (error) {
- case -ENOATTR:
- if (args->op_flags & XFS_DA_OP_REPLACE)
- return error;
- break;
- case -EEXIST:
- if (!(args->op_flags & XFS_DA_OP_REPLACE))
- return error;
+ if (xfs_attr_sf_findname(args)) {
+ int error;
+
+ ASSERT(args->op_flags & XFS_DA_OP_REPLACE);
error = xfs_attr_sf_removename(args);
if (error)
@@ -1137,11 +1085,8 @@ xfs_attr_shortform_addname(
* around.
*/
args->op_flags &= ~XFS_DA_OP_REPLACE;
- break;
- case 0:
- break;
- default:
- return error;
+ } else {
+ ASSERT(!(args->op_flags & XFS_DA_OP_REPLACE));
}
if (args->namelen >= XFS_ATTR_SF_ENTSIZE_MAX ||
diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c
index 2580ae47209a..6374bf107242 100644
--- a/fs/xfs/libxfs/xfs_attr_leaf.c
+++ b/fs/xfs/libxfs/xfs_attr_leaf.c
@@ -690,56 +690,32 @@ xfs_attr_shortform_create(
ASSERT(ifp->if_bytes == 0);
if (ifp->if_format == XFS_DINODE_FMT_EXTENTS)
ifp->if_format = XFS_DINODE_FMT_LOCAL;
- xfs_idata_realloc(dp, sizeof(*hdr), XFS_ATTR_FORK);
- hdr = (struct xfs_attr_sf_hdr *)ifp->if_u1.if_data;
+
+ hdr = xfs_idata_realloc(dp, sizeof(*hdr), XFS_ATTR_FORK);
memset(hdr, 0, sizeof(*hdr));
hdr->totsize = cpu_to_be16(sizeof(*hdr));
xfs_trans_log_inode(args->trans, dp, XFS_ILOG_CORE | XFS_ILOG_ADATA);
}
/*
- * Return -EEXIST if attr is found, or -ENOATTR if not
- * args: args containing attribute name and namelen
- * sfep: If not null, pointer will be set to the last attr entry found on
- -EEXIST. On -ENOATTR pointer is left at the last entry in the list
- * basep: If not null, pointer is set to the byte offset of the entry in the
- * list on -EEXIST. On -ENOATTR, pointer is left at the byte offset of
- * the last entry in the list
+ * Return the entry if the attr in args is found, or NULL if not.
*/
-int
+struct xfs_attr_sf_entry *
xfs_attr_sf_findname(
- struct xfs_da_args *args,
- struct xfs_attr_sf_entry **sfep,
- unsigned int *basep)
+ struct xfs_da_args *args)
{
- struct xfs_attr_shortform *sf;
- struct xfs_attr_sf_entry *sfe;
- unsigned int base = sizeof(struct xfs_attr_sf_hdr);
- int size = 0;
- int end;
- int i;
+ struct xfs_attr_sf_hdr *sf = args->dp->i_af.if_data;
+ struct xfs_attr_sf_entry *sfe;
- sf = (struct xfs_attr_shortform *)args->dp->i_af.if_u1.if_data;
- sfe = &sf->list[0];
- end = sf->hdr.count;
- for (i = 0; i < end; sfe = xfs_attr_sf_nextentry(sfe),
- base += size, i++) {
- size = xfs_attr_sf_entsize(sfe);
- if (!xfs_attr_match(args, sfe->namelen, sfe->nameval,
- sfe->flags))
- continue;
- break;
+ for (sfe = xfs_attr_sf_firstentry(sf);
+ sfe < xfs_attr_sf_endptr(sf);
+ sfe = xfs_attr_sf_nextentry(sfe)) {
+ if (xfs_attr_match(args, sfe->namelen, sfe->nameval,
+ sfe->flags))
+ return sfe;
}
- if (sfep != NULL)
- *sfep = sfe;
-
- if (basep != NULL)
- *basep = base;
-
- if (i == end)
- return -ENOATTR;
- return -EEXIST;
+ return NULL;
}
/*
@@ -751,38 +727,31 @@ xfs_attr_shortform_add(
struct xfs_da_args *args,
int forkoff)
{
- struct xfs_attr_shortform *sf;
+ struct xfs_inode *dp = args->dp;
+ struct xfs_mount *mp = dp->i_mount;
+ struct xfs_ifork *ifp = &dp->i_af;
+ struct xfs_attr_sf_hdr *sf = ifp->if_data;
struct xfs_attr_sf_entry *sfe;
- int offset, size;
- struct xfs_mount *mp;
- struct xfs_inode *dp;
- struct xfs_ifork *ifp;
+ int size;
trace_xfs_attr_sf_add(args);
- dp = args->dp;
- mp = dp->i_mount;
dp->i_forkoff = forkoff;
- ifp = &dp->i_af;
ASSERT(ifp->if_format == XFS_DINODE_FMT_LOCAL);
- sf = (struct xfs_attr_shortform *)ifp->if_u1.if_data;
- if (xfs_attr_sf_findname(args, &sfe, NULL) == -EEXIST)
- ASSERT(0);
+ ASSERT(!xfs_attr_sf_findname(args));
- offset = (char *)sfe - (char *)sf;
size = xfs_attr_sf_entsize_byname(args->namelen, args->valuelen);
- xfs_idata_realloc(dp, size, XFS_ATTR_FORK);
- sf = (struct xfs_attr_shortform *)ifp->if_u1.if_data;
- sfe = (struct xfs_attr_sf_entry *)((char *)sf + offset);
+ sf = xfs_idata_realloc(dp, size, XFS_ATTR_FORK);
+ sfe = xfs_attr_sf_endptr(sf);
sfe->namelen = args->namelen;
sfe->valuelen = args->valuelen;
sfe->flags = args->attr_filter;
memcpy(sfe->nameval, args->name, args->namelen);
memcpy(&sfe->nameval[args->namelen], args->value, args->valuelen);
- sf->hdr.count++;
- be16_add_cpu(&sf->hdr.totsize, size);
+ sf->count++;
+ be16_add_cpu(&sf->totsize, size);
xfs_trans_log_inode(args->trans, dp, XFS_ILOG_CORE | XFS_ILOG_ADATA);
xfs_sbversion_add_attr2(mp, args->trans);
@@ -811,48 +780,43 @@ int
xfs_attr_sf_removename(
struct xfs_da_args *args)
{
- struct xfs_attr_shortform *sf;
+ struct xfs_inode *dp = args->dp;
+ struct xfs_mount *mp = dp->i_mount;
+ struct xfs_attr_sf_hdr *sf = dp->i_af.if_data;
struct xfs_attr_sf_entry *sfe;
- int size = 0, end, totsize;
- unsigned int base;
- struct xfs_mount *mp;
- struct xfs_inode *dp;
- int error;
+ uint16_t totsize = be16_to_cpu(sf->totsize);
+ void *next, *end;
+ int size = 0;
trace_xfs_attr_sf_remove(args);
- dp = args->dp;
- mp = dp->i_mount;
- sf = (struct xfs_attr_shortform *)dp->i_af.if_u1.if_data;
-
- error = xfs_attr_sf_findname(args, &sfe, &base);
-
- /*
- * If we are recovering an operation, finding nothing to
- * remove is not an error - it just means there was nothing
- * to clean up.
- */
- if (error == -ENOATTR && (args->op_flags & XFS_DA_OP_RECOVERY))
- return 0;
- if (error != -EEXIST)
- return error;
- size = xfs_attr_sf_entsize(sfe);
+ sfe = xfs_attr_sf_findname(args);
+ if (!sfe) {
+ /*
+ * If we are recovering an operation, finding nothing to remove
+ * is not an error, it just means there was nothing to clean up.
+ */
+ if (args->op_flags & XFS_DA_OP_RECOVERY)
+ return 0;
+ return -ENOATTR;
+ }
/*
* Fix up the attribute fork data, covering the hole
*/
- end = base + size;
- totsize = be16_to_cpu(sf->hdr.totsize);
- if (end != totsize)
- memmove(&((char *)sf)[base], &((char *)sf)[end], totsize - end);
- sf->hdr.count--;
- be16_add_cpu(&sf->hdr.totsize, -size);
+ size = xfs_attr_sf_entsize(sfe);
+ next = xfs_attr_sf_nextentry(sfe);
+ end = xfs_attr_sf_endptr(sf);
+ if (next < end)
+ memmove(sfe, next, end - next);
+ sf->count--;
+ totsize -= size;
+ sf->totsize = cpu_to_be16(totsize);
/*
* Fix up the start offset of the attribute fork
*/
- totsize -= size;
- if (totsize == sizeof(xfs_attr_sf_hdr_t) && xfs_has_attr2(mp) &&
+ if (totsize == sizeof(struct xfs_attr_sf_hdr) && xfs_has_attr2(mp) &&
(dp->i_df.if_format != XFS_DINODE_FMT_BTREE) &&
!(args->op_flags & (XFS_DA_OP_ADDNAME | XFS_DA_OP_REPLACE))) {
xfs_attr_fork_remove(dp, args->trans);
@@ -860,7 +824,7 @@ xfs_attr_sf_removename(
xfs_idata_realloc(dp, -size, XFS_ATTR_FORK);
dp->i_forkoff = xfs_attr_shortform_bytesfit(dp, totsize);
ASSERT(dp->i_forkoff);
- ASSERT(totsize > sizeof(xfs_attr_sf_hdr_t) ||
+ ASSERT(totsize > sizeof(struct xfs_attr_sf_hdr) ||
(args->op_flags & XFS_DA_OP_ADDNAME) ||
!xfs_has_attr2(mp) ||
dp->i_df.if_format == XFS_DINODE_FMT_BTREE);
@@ -874,33 +838,6 @@ xfs_attr_sf_removename(
}
/*
- * Look up a name in a shortform attribute list structure.
- */
-/*ARGSUSED*/
-int
-xfs_attr_shortform_lookup(xfs_da_args_t *args)
-{
- struct xfs_attr_shortform *sf;
- struct xfs_attr_sf_entry *sfe;
- int i;
- struct xfs_ifork *ifp;
-
- trace_xfs_attr_sf_lookup(args);
-
- ifp = &args->dp->i_af;
- ASSERT(ifp->if_format == XFS_DINODE_FMT_LOCAL);
- sf = (struct xfs_attr_shortform *)ifp->if_u1.if_data;
- sfe = &sf->list[0];
- for (i = 0; i < sf->hdr.count;
- sfe = xfs_attr_sf_nextentry(sfe), i++) {
- if (xfs_attr_match(args, sfe->namelen, sfe->nameval,
- sfe->flags))
- return -EEXIST;
- }
- return -ENOATTR;
-}
-
-/*
* Retrieve the attribute value and length.
*
* If args->valuelen is zero, only the length needs to be returned. Unlike a
@@ -909,23 +846,19 @@ xfs_attr_shortform_lookup(xfs_da_args_t *args)
*/
int
xfs_attr_shortform_getvalue(
- struct xfs_da_args *args)
+ struct xfs_da_args *args)
{
- struct xfs_attr_shortform *sf;
- struct xfs_attr_sf_entry *sfe;
- int i;
+ struct xfs_attr_sf_entry *sfe;
ASSERT(args->dp->i_af.if_format == XFS_DINODE_FMT_LOCAL);
- sf = (struct xfs_attr_shortform *)args->dp->i_af.if_u1.if_data;
- sfe = &sf->list[0];
- for (i = 0; i < sf->hdr.count;
- sfe = xfs_attr_sf_nextentry(sfe), i++) {
- if (xfs_attr_match(args, sfe->namelen, sfe->nameval,
- sfe->flags))
- return xfs_attr_copy_value(args,
- &sfe->nameval[args->namelen], sfe->valuelen);
- }
- return -ENOATTR;
+
+ trace_xfs_attr_sf_lookup(args);
+
+ sfe = xfs_attr_sf_findname(args);
+ if (!sfe)
+ return -ENOATTR;
+ return xfs_attr_copy_value(args, &sfe->nameval[args->namelen],
+ sfe->valuelen);
}
/* Convert from using the shortform to the leaf format. */
@@ -933,26 +866,23 @@ int
xfs_attr_shortform_to_leaf(
struct xfs_da_args *args)
{
- struct xfs_inode *dp;
- struct xfs_attr_shortform *sf;
+ struct xfs_inode *dp = args->dp;
+ struct xfs_ifork *ifp = &dp->i_af;
+ struct xfs_attr_sf_hdr *sf = ifp->if_data;
struct xfs_attr_sf_entry *sfe;
+ int size = be16_to_cpu(sf->totsize);
struct xfs_da_args nargs;
char *tmpbuffer;
- int error, i, size;
+ int error, i;
xfs_dablk_t blkno;
struct xfs_buf *bp;
- struct xfs_ifork *ifp;
trace_xfs_attr_sf_to_leaf(args);
- dp = args->dp;
- ifp = &dp->i_af;
- sf = (struct xfs_attr_shortform *)ifp->if_u1.if_data;
- size = be16_to_cpu(sf->hdr.totsize);
tmpbuffer = kmem_alloc(size, 0);
ASSERT(tmpbuffer != NULL);
- memcpy(tmpbuffer, ifp->if_u1.if_data, size);
- sf = (struct xfs_attr_shortform *)tmpbuffer;
+ memcpy(tmpbuffer, ifp->if_data, size);
+ sf = (struct xfs_attr_sf_hdr *)tmpbuffer;
xfs_idata_realloc(dp, -size, XFS_ATTR_FORK);
xfs_bmap_local_to_extents_empty(args->trans, dp, XFS_ATTR_FORK);
@@ -975,8 +905,8 @@ xfs_attr_shortform_to_leaf(
nargs.trans = args->trans;
nargs.op_flags = XFS_DA_OP_OKNOENT;
- sfe = &sf->list[0];
- for (i = 0; i < sf->hdr.count; i++) {
+ sfe = xfs_attr_sf_firstentry(sf);
+ for (i = 0; i < sf->count; i++) {
nargs.name = sfe->nameval;
nargs.namelen = sfe->namelen;
nargs.value = &sfe->nameval[nargs.namelen];
@@ -1040,23 +970,16 @@ xfs_attr_shortform_allfit(
return xfs_attr_shortform_bytesfit(dp, bytes);
}
-/* Verify the consistency of an inline attribute fork. */
+/* Verify the consistency of a raw inline attribute fork. */
xfs_failaddr_t
xfs_attr_shortform_verify(
- struct xfs_inode *ip)
+ struct xfs_attr_sf_hdr *sfp,
+ size_t size)
{
- struct xfs_attr_shortform *sfp;
- struct xfs_attr_sf_entry *sfep;
+ struct xfs_attr_sf_entry *sfep = xfs_attr_sf_firstentry(sfp);
struct xfs_attr_sf_entry *next_sfep;
char *endp;
- struct xfs_ifork *ifp;
int i;
- int64_t size;
-
- ASSERT(ip->i_af.if_format == XFS_DINODE_FMT_LOCAL);
- ifp = xfs_ifork_ptr(ip, XFS_ATTR_FORK);
- sfp = (struct xfs_attr_shortform *)ifp->if_u1.if_data;
- size = ifp->if_bytes;
/*
* Give up if the attribute is way too short.
@@ -1067,8 +990,7 @@ xfs_attr_shortform_verify(
endp = (char *)sfp + size;
/* Check all reported entries */
- sfep = &sfp->list[0];
- for (i = 0; i < sfp->hdr.count; i++) {
+ for (i = 0; i < sfp->count; i++) {
/*
* struct xfs_attr_sf_entry has a variable length.
* Check the fixed-offset parts of the structure are
@@ -1244,14 +1166,10 @@ xfs_attr3_leaf_to_node(
if (error)
goto out;
- /* copy leaf to new buffer, update identifiers */
- xfs_trans_buf_set_type(args->trans, bp2, XFS_BLFT_ATTR_LEAF_BUF);
- bp2->b_ops = bp1->b_ops;
- memcpy(bp2->b_addr, bp1->b_addr, args->geo->blksize);
- if (xfs_has_crc(mp)) {
- struct xfs_da3_blkinfo *hdr3 = bp2->b_addr;
- hdr3->blkno = cpu_to_be64(xfs_buf_daddr(bp2));
- }
+ /*
+ * Copy leaf to new buffer and log it.
+ */
+ xfs_da_buf_copy(bp2, bp1, args->geo->blksize);
xfs_trans_log_buf(args->trans, bp2, 0, args->geo->blksize - 1);
/*
diff --git a/fs/xfs/libxfs/xfs_attr_leaf.h b/fs/xfs/libxfs/xfs_attr_leaf.h
index 368f4d9fa1d5..9b9948639c0f 100644
--- a/fs/xfs/libxfs/xfs_attr_leaf.h
+++ b/fs/xfs/libxfs/xfs_attr_leaf.h
@@ -47,16 +47,14 @@ struct xfs_attr3_icleaf_hdr {
*/
void xfs_attr_shortform_create(struct xfs_da_args *args);
void xfs_attr_shortform_add(struct xfs_da_args *args, int forkoff);
-int xfs_attr_shortform_lookup(struct xfs_da_args *args);
int xfs_attr_shortform_getvalue(struct xfs_da_args *args);
int xfs_attr_shortform_to_leaf(struct xfs_da_args *args);
int xfs_attr_sf_removename(struct xfs_da_args *args);
-int xfs_attr_sf_findname(struct xfs_da_args *args,
- struct xfs_attr_sf_entry **sfep,
- unsigned int *basep);
+struct xfs_attr_sf_entry *xfs_attr_sf_findname(struct xfs_da_args *args);
int xfs_attr_shortform_allfit(struct xfs_buf *bp, struct xfs_inode *dp);
int xfs_attr_shortform_bytesfit(struct xfs_inode *dp, int bytes);
-xfs_failaddr_t xfs_attr_shortform_verify(struct xfs_inode *ip);
+xfs_failaddr_t xfs_attr_shortform_verify(struct xfs_attr_sf_hdr *sfp,
+ size_t size);
void xfs_attr_fork_remove(struct xfs_inode *ip, struct xfs_trans *tp);
/*
diff --git a/fs/xfs/libxfs/xfs_attr_sf.h b/fs/xfs/libxfs/xfs_attr_sf.h
index 37578b369d9b..bc4422223024 100644
--- a/fs/xfs/libxfs/xfs_attr_sf.h
+++ b/fs/xfs/libxfs/xfs_attr_sf.h
@@ -7,14 +7,6 @@
#define __XFS_ATTR_SF_H__
/*
- * Attribute storage when stored inside the inode.
- *
- * Small attribute lists are packed as tightly as possible so as
- * to fit into the literal area of the inode.
- */
-typedef struct xfs_attr_sf_hdr xfs_attr_sf_hdr_t;
-
-/*
* We generate this then sort it, attr_list() must return things in hash-order.
*/
typedef struct xfs_attr_sf_sort {
@@ -41,11 +33,25 @@ static inline int xfs_attr_sf_entsize(struct xfs_attr_sf_entry *sfep)
return struct_size(sfep, nameval, sfep->namelen + sfep->valuelen);
}
-/* next entry in struct */
+/* first entry in the SF attr fork */
+static inline struct xfs_attr_sf_entry *
+xfs_attr_sf_firstentry(struct xfs_attr_sf_hdr *hdr)
+{
+ return (struct xfs_attr_sf_entry *)(hdr + 1);
+}
+
+/* next entry after sfep */
static inline struct xfs_attr_sf_entry *
xfs_attr_sf_nextentry(struct xfs_attr_sf_entry *sfep)
{
return (void *)sfep + xfs_attr_sf_entsize(sfep);
}
+/* pointer to the space after the last entry, e.g. for adding a new one */
+static inline struct xfs_attr_sf_entry *
+xfs_attr_sf_endptr(struct xfs_attr_sf_hdr *sf)
+{
+ return (void *)sf + be16_to_cpu(sf->totsize);
+}
+
#endif /* __XFS_ATTR_SF_H__ */
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index be62acffad6c..98aaca933bdd 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -575,7 +575,7 @@ xfs_bmap_btree_to_extents(
xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, whichfork);
error = xfs_free_extent_later(cur->bc_tp, cbno, 1, &oinfo,
- XFS_AG_RESV_NONE);
+ XFS_AG_RESV_NONE, false);
if (error)
return error;
@@ -747,7 +747,7 @@ xfs_bmap_local_to_extents_empty(
ASSERT(ifp->if_nextents == 0);
xfs_bmap_forkoff_reset(ip, whichfork);
- ifp->if_u1.if_root = NULL;
+ ifp->if_data = NULL;
ifp->if_height = 0;
ifp->if_format = XFS_DINODE_FMT_EXTENTS;
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
@@ -832,7 +832,7 @@ xfs_bmap_local_to_extents(
xfs_bmap_local_to_extents_empty(tp, ip, whichfork);
flags |= XFS_ILOG_CORE;
- ifp->if_u1.if_root = NULL;
+ ifp->if_data = NULL;
ifp->if_height = 0;
rec.br_startoff = 0;
@@ -3044,7 +3044,8 @@ xfs_bmap_extsize_align(
#define XFS_ALLOC_GAP_UNITS 4
-void
+/* returns true if ap->blkno was modified */
+bool
xfs_bmap_adjacent(
struct xfs_bmalloca *ap) /* bmap alloc argument struct */
{
@@ -3079,13 +3080,14 @@ xfs_bmap_adjacent(
if (adjust &&
ISVALID(ap->blkno + adjust, ap->prev.br_startblock))
ap->blkno += adjust;
+ return true;
}
/*
* If not at eof, then compare the two neighbor blocks.
* Figure out whether either one gives us a good starting point,
* and pick the better one.
*/
- else if (!ap->eof) {
+ if (!ap->eof) {
xfs_fsblock_t gotbno; /* right side block number */
xfs_fsblock_t gotdiff=0; /* right side difference */
xfs_fsblock_t prevbno; /* left side block number */
@@ -3165,14 +3167,21 @@ xfs_bmap_adjacent(
* If both valid, pick the better one, else the only good
* one, else ap->blkno is already set (to 0 or the inode block).
*/
- if (prevbno != NULLFSBLOCK && gotbno != NULLFSBLOCK)
+ if (prevbno != NULLFSBLOCK && gotbno != NULLFSBLOCK) {
ap->blkno = prevdiff <= gotdiff ? prevbno : gotbno;
- else if (prevbno != NULLFSBLOCK)
+ return true;
+ }
+ if (prevbno != NULLFSBLOCK) {
ap->blkno = prevbno;
- else if (gotbno != NULLFSBLOCK)
+ return true;
+ }
+ if (gotbno != NULLFSBLOCK) {
ap->blkno = gotbno;
+ return true;
+ }
}
#undef ISVALID
+ return false;
}
int
@@ -3263,11 +3272,14 @@ xfs_bmap_btalloc_select_lengths(
}
/* Update all inode and quota accounting for the allocation we just did. */
-static void
-xfs_bmap_btalloc_accounting(
- struct xfs_bmalloca *ap,
- struct xfs_alloc_arg *args)
+void
+xfs_bmap_alloc_account(
+ struct xfs_bmalloca *ap)
{
+ bool isrt = XFS_IS_REALTIME_INODE(ap->ip) &&
+ (ap->flags & XFS_BMAPI_ATTRFORK);
+ uint fld;
+
if (ap->flags & XFS_BMAPI_COWFORK) {
/*
* COW fork blocks are in-core only and thus are treated as
@@ -3279,7 +3291,7 @@ xfs_bmap_btalloc_accounting(
* yet.
*/
if (ap->wasdel) {
- xfs_mod_delalloc(ap->ip->i_mount, -(int64_t)args->len);
+ xfs_mod_delalloc(ap->ip->i_mount, -(int64_t)ap->length);
return;
}
@@ -3291,22 +3303,25 @@ xfs_bmap_btalloc_accounting(
* This essentially transfers the transaction quota reservation
* to that of a delalloc extent.
*/
- ap->ip->i_delayed_blks += args->len;
- xfs_trans_mod_dquot_byino(ap->tp, ap->ip, XFS_TRANS_DQ_RES_BLKS,
- -(long)args->len);
+ ap->ip->i_delayed_blks += ap->length;
+ xfs_trans_mod_dquot_byino(ap->tp, ap->ip, isrt ?
+ XFS_TRANS_DQ_RES_RTBLKS : XFS_TRANS_DQ_RES_BLKS,
+ -(long)ap->length);
return;
}
/* data/attr fork only */
- ap->ip->i_nblocks += args->len;
+ ap->ip->i_nblocks += ap->length;
xfs_trans_log_inode(ap->tp, ap->ip, XFS_ILOG_CORE);
if (ap->wasdel) {
- ap->ip->i_delayed_blks -= args->len;
- xfs_mod_delalloc(ap->ip->i_mount, -(int64_t)args->len);
+ ap->ip->i_delayed_blks -= ap->length;
+ xfs_mod_delalloc(ap->ip->i_mount, -(int64_t)ap->length);
+ fld = isrt ? XFS_TRANS_DQ_DELRTBCOUNT : XFS_TRANS_DQ_DELBCOUNT;
+ } else {
+ fld = isrt ? XFS_TRANS_DQ_RTBCOUNT : XFS_TRANS_DQ_BCOUNT;
}
- xfs_trans_mod_dquot_byino(ap->tp, ap->ip,
- ap->wasdel ? XFS_TRANS_DQ_DELBCOUNT : XFS_TRANS_DQ_BCOUNT,
- args->len);
+
+ xfs_trans_mod_dquot_byino(ap->tp, ap->ip, fld, ap->length);
}
static int
@@ -3380,7 +3395,7 @@ xfs_bmap_process_allocated_extent(
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_alloc_account(ap);
}
#ifdef DEBUG
@@ -5010,7 +5025,6 @@ xfs_bmap_del_extent_real(
xfs_fileoff_t del_endoff; /* first offset past del */
int do_fx; /* free extent at end of routine */
int error; /* error return value */
- int flags = 0;/* inode logging flags */
struct xfs_bmbt_irec got; /* current extent entry */
xfs_fileoff_t got_endoff; /* first offset past got */
int i; /* temp state */
@@ -5023,6 +5037,8 @@ xfs_bmap_del_extent_real(
uint32_t state = xfs_bmap_fork_to_state(whichfork);
struct xfs_bmbt_irec old;
+ *logflagsp = 0;
+
mp = ip->i_mount;
XFS_STATS_INC(mp, xs_del_exlist);
@@ -5035,7 +5051,6 @@ xfs_bmap_del_extent_real(
ASSERT(got_endoff >= del_endoff);
ASSERT(!isnullstartblock(got.br_startblock));
qfield = 0;
- error = 0;
/*
* If it's the case where the directory code is running with no block
@@ -5051,13 +5066,13 @@ xfs_bmap_del_extent_real(
del->br_startoff > got.br_startoff && del_endoff < got_endoff)
return -ENOSPC;
- flags = XFS_ILOG_CORE;
+ *logflagsp = XFS_ILOG_CORE;
if (whichfork == XFS_DATA_FORK && XFS_IS_REALTIME_INODE(ip)) {
if (!(bflags & XFS_BMAPI_REMAP)) {
error = xfs_rtfree_blocks(tp, del->br_startblock,
del->br_blockcount);
if (error)
- goto done;
+ return error;
}
do_fx = 0;
@@ -5072,11 +5087,9 @@ xfs_bmap_del_extent_real(
if (cur) {
error = xfs_bmbt_lookup_eq(cur, &got, &i);
if (error)
- goto done;
- if (XFS_IS_CORRUPT(mp, i != 1)) {
- error = -EFSCORRUPTED;
- goto done;
- }
+ return error;
+ if (XFS_IS_CORRUPT(mp, i != 1))
+ return -EFSCORRUPTED;
}
if (got.br_startoff == del->br_startoff)
@@ -5093,17 +5106,15 @@ xfs_bmap_del_extent_real(
xfs_iext_prev(ifp, icur);
ifp->if_nextents--;
- flags |= XFS_ILOG_CORE;
+ *logflagsp |= XFS_ILOG_CORE;
if (!cur) {
- flags |= xfs_ilog_fext(whichfork);
+ *logflagsp |= xfs_ilog_fext(whichfork);
break;
}
if ((error = xfs_btree_delete(cur, &i)))
- goto done;
- if (XFS_IS_CORRUPT(mp, i != 1)) {
- error = -EFSCORRUPTED;
- goto done;
- }
+ return error;
+ if (XFS_IS_CORRUPT(mp, i != 1))
+ return -EFSCORRUPTED;
break;
case BMAP_LEFT_FILLING:
/*
@@ -5114,12 +5125,12 @@ xfs_bmap_del_extent_real(
got.br_blockcount -= del->br_blockcount;
xfs_iext_update_extent(ip, state, icur, &got);
if (!cur) {
- flags |= xfs_ilog_fext(whichfork);
+ *logflagsp |= xfs_ilog_fext(whichfork);
break;
}
error = xfs_bmbt_update(cur, &got);
if (error)
- goto done;
+ return error;
break;
case BMAP_RIGHT_FILLING:
/*
@@ -5128,12 +5139,12 @@ xfs_bmap_del_extent_real(
got.br_blockcount -= del->br_blockcount;
xfs_iext_update_extent(ip, state, icur, &got);
if (!cur) {
- flags |= xfs_ilog_fext(whichfork);
+ *logflagsp |= xfs_ilog_fext(whichfork);
break;
}
error = xfs_bmbt_update(cur, &got);
if (error)
- goto done;
+ return error;
break;
case 0:
/*
@@ -5150,18 +5161,18 @@ xfs_bmap_del_extent_real(
new.br_state = got.br_state;
new.br_startblock = del_endblock;
- flags |= XFS_ILOG_CORE;
+ *logflagsp |= XFS_ILOG_CORE;
if (cur) {
error = xfs_bmbt_update(cur, &got);
if (error)
- goto done;
+ return error;
error = xfs_btree_increment(cur, 0, &i);
if (error)
- goto done;
+ return error;
cur->bc_rec.b = new;
error = xfs_btree_insert(cur, &i);
if (error && error != -ENOSPC)
- goto done;
+ return error;
/*
* If get no-space back from btree insert, it tried a
* split, and we have a zero block reservation. Fix up
@@ -5174,33 +5185,28 @@ xfs_bmap_del_extent_real(
*/
error = xfs_bmbt_lookup_eq(cur, &got, &i);
if (error)
- goto done;
- if (XFS_IS_CORRUPT(mp, i != 1)) {
- error = -EFSCORRUPTED;
- goto done;
- }
+ return error;
+ if (XFS_IS_CORRUPT(mp, i != 1))
+ return -EFSCORRUPTED;
/*
* Update the btree record back
* to the original value.
*/
error = xfs_bmbt_update(cur, &old);
if (error)
- goto done;
+ return error;
/*
* Reset the extent record back
* to the original value.
*/
xfs_iext_update_extent(ip, state, icur, &old);
- flags = 0;
- error = -ENOSPC;
- goto done;
- }
- if (XFS_IS_CORRUPT(mp, i != 1)) {
- error = -EFSCORRUPTED;
- goto done;
+ *logflagsp = 0;
+ return -ENOSPC;
}
+ if (XFS_IS_CORRUPT(mp, i != 1))
+ return -EFSCORRUPTED;
} else
- flags |= xfs_ilog_fext(whichfork);
+ *logflagsp |= xfs_ilog_fext(whichfork);
ifp->if_nextents++;
xfs_iext_next(ifp, icur);
@@ -5218,13 +5224,13 @@ xfs_bmap_del_extent_real(
if (xfs_is_reflink_inode(ip) && whichfork == XFS_DATA_FORK) {
xfs_refcount_decrease_extent(tp, del);
} else {
- error = __xfs_free_extent_later(tp, del->br_startblock,
+ error = xfs_free_extent_later(tp, del->br_startblock,
del->br_blockcount, NULL,
XFS_AG_RESV_NONE,
((bflags & XFS_BMAPI_NODISCARD) ||
del->br_state == XFS_EXT_UNWRITTEN));
if (error)
- goto done;
+ return error;
}
}
@@ -5239,9 +5245,7 @@ xfs_bmap_del_extent_real(
if (qfield && !(bflags & XFS_BMAPI_REMAP))
xfs_trans_mod_dquot_byino(tp, ip, qfield, (long)-nblks);
-done:
- *logflagsp = flags;
- return error;
+ return 0;
}
/*
@@ -5250,7 +5254,7 @@ done:
* that value. If not all extents in the block range can be removed then
* *done is set.
*/
-int /* error */
+static int
__xfs_bunmapi(
struct xfs_trans *tp, /* transaction pointer */
struct xfs_inode *ip, /* incore inode */
@@ -6102,7 +6106,7 @@ __xfs_bmap_add(
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);
+ xfs_defer_add(tp, &bi->bi_list, &xfs_bmap_update_defer_type);
return 0;
}
@@ -6179,19 +6183,18 @@ xfs_bmap_finish_one(
return error;
}
-/* Check that an inode's extent does not have invalid flags or bad ranges. */
+/* Check that an extent does not have invalid flags or bad ranges. */
xfs_failaddr_t
-xfs_bmap_validate_extent(
- struct xfs_inode *ip,
+xfs_bmap_validate_extent_raw(
+ struct xfs_mount *mp,
+ bool rtfile,
int whichfork,
struct xfs_bmbt_irec *irec)
{
- struct xfs_mount *mp = ip->i_mount;
-
if (!xfs_verify_fileext(mp, irec->br_startoff, irec->br_blockcount))
return __this_address;
- if (XFS_IS_REALTIME_INODE(ip) && whichfork == XFS_DATA_FORK) {
+ if (rtfile && whichfork == XFS_DATA_FORK) {
if (!xfs_verify_rtbext(mp, irec->br_startblock,
irec->br_blockcount))
return __this_address;
@@ -6221,3 +6224,53 @@ xfs_bmap_intent_destroy_cache(void)
kmem_cache_destroy(xfs_bmap_intent_cache);
xfs_bmap_intent_cache = NULL;
}
+
+/* Check that an inode's extent does not have invalid flags or bad ranges. */
+xfs_failaddr_t
+xfs_bmap_validate_extent(
+ struct xfs_inode *ip,
+ int whichfork,
+ struct xfs_bmbt_irec *irec)
+{
+ return xfs_bmap_validate_extent_raw(ip->i_mount,
+ XFS_IS_REALTIME_INODE(ip), whichfork, irec);
+}
+
+/*
+ * Used in xfs_itruncate_extents(). This is the maximum number of extents
+ * freed from a file in a single transaction.
+ */
+#define XFS_ITRUNC_MAX_EXTENTS 2
+
+/*
+ * Unmap every extent in part of an inode's fork. We don't do any higher level
+ * invalidation work at all.
+ */
+int
+xfs_bunmapi_range(
+ struct xfs_trans **tpp,
+ struct xfs_inode *ip,
+ uint32_t flags,
+ xfs_fileoff_t startoff,
+ xfs_fileoff_t endoff)
+{
+ xfs_filblks_t unmap_len = endoff - startoff + 1;
+ int error = 0;
+
+ ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
+
+ while (unmap_len > 0) {
+ ASSERT((*tpp)->t_highest_agno == NULLAGNUMBER);
+ error = __xfs_bunmapi(*tpp, ip, startoff, &unmap_len, flags,
+ XFS_ITRUNC_MAX_EXTENTS);
+ if (error)
+ goto out;
+
+ /* free the just unmapped extents */
+ error = xfs_defer_finish(tpp);
+ if (error)
+ goto out;
+ }
+out:
+ return error;
+}
diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h
index e33470e39728..f6b73f1bad5f 100644
--- a/fs/xfs/libxfs/xfs_bmap.h
+++ b/fs/xfs/libxfs/xfs_bmap.h
@@ -116,6 +116,8 @@ static inline int xfs_bmapi_whichfork(uint32_t bmapi_flags)
return XFS_DATA_FORK;
}
+void xfs_bmap_alloc_account(struct xfs_bmalloca *ap);
+
/*
* Special values for xfs_bmbt_irec_t br_startblock field.
*/
@@ -190,9 +192,6 @@ int xfs_bmapi_read(struct xfs_inode *ip, xfs_fileoff_t bno,
int xfs_bmapi_write(struct xfs_trans *tp, struct xfs_inode *ip,
xfs_fileoff_t bno, xfs_filblks_t len, uint32_t flags,
xfs_extlen_t total, struct xfs_bmbt_irec *mval, int *nmap);
-int __xfs_bunmapi(struct xfs_trans *tp, struct xfs_inode *ip,
- xfs_fileoff_t bno, xfs_filblks_t *rlen, uint32_t flags,
- xfs_extnum_t nexts);
int xfs_bunmapi(struct xfs_trans *tp, struct xfs_inode *ip,
xfs_fileoff_t bno, xfs_filblks_t len, uint32_t flags,
xfs_extnum_t nexts, int *done);
@@ -263,6 +262,8 @@ static inline uint32_t xfs_bmap_fork_to_state(int whichfork)
}
}
+xfs_failaddr_t xfs_bmap_validate_extent_raw(struct xfs_mount *mp, bool rtfile,
+ int whichfork, struct xfs_bmbt_irec *irec);
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,
@@ -271,6 +272,8 @@ int xfs_bmap_complain_bad_rec(struct xfs_inode *ip, int whichfork,
int xfs_bmapi_remap(struct xfs_trans *tp, struct xfs_inode *ip,
xfs_fileoff_t bno, xfs_filblks_t len, xfs_fsblock_t startblock,
uint32_t flags);
+int xfs_bunmapi_range(struct xfs_trans **tpp, struct xfs_inode *ip,
+ uint32_t flags, xfs_fileoff_t startoff, xfs_fileoff_t endoff);
extern struct kmem_cache *xfs_bmap_intent_cache;
diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c
index bf3f1b36fdd2..71f2d50f7823 100644
--- a/fs/xfs/libxfs/xfs_bmap_btree.c
+++ b/fs/xfs/libxfs/xfs_bmap_btree.c
@@ -15,6 +15,7 @@
#include "xfs_trans.h"
#include "xfs_alloc.h"
#include "xfs_btree.h"
+#include "xfs_btree_staging.h"
#include "xfs_bmap_btree.h"
#include "xfs_bmap.h"
#include "xfs_error.h"
@@ -272,7 +273,7 @@ xfs_bmbt_free_block(
xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, cur->bc_ino.whichfork);
error = xfs_free_extent_later(cur->bc_tp, fsbno, 1, &oinfo,
- XFS_AG_RESV_NONE);
+ XFS_AG_RESV_NONE, false);
if (error)
return error;
@@ -288,10 +289,7 @@ xfs_bmbt_get_minrecs(
int level)
{
if (level == cur->bc_nlevels - 1) {
- struct xfs_ifork *ifp;
-
- ifp = xfs_ifork_ptr(cur->bc_ino.ip,
- cur->bc_ino.whichfork);
+ struct xfs_ifork *ifp = xfs_btree_ifork_ptr(cur);
return xfs_bmbt_maxrecs(cur->bc_mp,
ifp->if_broot_bytes, level == 0) / 2;
@@ -306,10 +304,7 @@ xfs_bmbt_get_maxrecs(
int level)
{
if (level == cur->bc_nlevels - 1) {
- struct xfs_ifork *ifp;
-
- ifp = xfs_ifork_ptr(cur->bc_ino.ip,
- cur->bc_ino.whichfork);
+ struct xfs_ifork *ifp = xfs_btree_ifork_ptr(cur);
return xfs_bmbt_maxrecs(cur->bc_mp,
ifp->if_broot_bytes, level == 0);
@@ -543,23 +538,19 @@ static const struct xfs_btree_ops xfs_bmbt_ops = {
.keys_contiguous = xfs_bmbt_keys_contiguous,
};
-/*
- * Allocate a new bmap btree cursor.
- */
-struct xfs_btree_cur * /* new bmap btree cursor */
-xfs_bmbt_init_cursor(
- struct xfs_mount *mp, /* file system mount point */
- struct xfs_trans *tp, /* transaction pointer */
- struct xfs_inode *ip, /* inode owning the btree */
- int whichfork) /* data or attr fork */
+static struct xfs_btree_cur *
+xfs_bmbt_init_common(
+ struct xfs_mount *mp,
+ struct xfs_trans *tp,
+ struct xfs_inode *ip,
+ int whichfork)
{
- struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork);
struct xfs_btree_cur *cur;
+
ASSERT(whichfork != XFS_COW_FORK);
cur = xfs_btree_alloc_cursor(mp, tp, XFS_BTNUM_BMAP,
mp->m_bm_maxlevels[whichfork], xfs_bmbt_cur_cache);
- cur->bc_nlevels = be16_to_cpu(ifp->if_broot->bb_level) + 1;
cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_bmbt_2);
cur->bc_ops = &xfs_bmbt_ops;
@@ -567,10 +558,30 @@ xfs_bmbt_init_cursor(
if (xfs_has_crc(mp))
cur->bc_flags |= XFS_BTREE_CRC_BLOCKS;
- cur->bc_ino.forksize = xfs_inode_fork_size(ip, whichfork);
cur->bc_ino.ip = ip;
cur->bc_ino.allocated = 0;
cur->bc_ino.flags = 0;
+
+ return cur;
+}
+
+/*
+ * Allocate a new bmap btree cursor.
+ */
+struct xfs_btree_cur *
+xfs_bmbt_init_cursor(
+ struct xfs_mount *mp,
+ struct xfs_trans *tp,
+ struct xfs_inode *ip,
+ int whichfork)
+{
+ struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork);
+ struct xfs_btree_cur *cur;
+
+ cur = xfs_bmbt_init_common(mp, tp, ip, whichfork);
+
+ cur->bc_nlevels = be16_to_cpu(ifp->if_broot->bb_level) + 1;
+ cur->bc_ino.forksize = xfs_inode_fork_size(ip, whichfork);
cur->bc_ino.whichfork = whichfork;
return cur;
@@ -588,6 +599,76 @@ xfs_bmbt_block_maxrecs(
}
/*
+ * Allocate a new bmap btree cursor for reloading an inode block mapping data
+ * structure. Note that callers can use the staged cursor to reload extents
+ * format inode forks if they rebuild the iext tree and commit the staged
+ * cursor immediately.
+ */
+struct xfs_btree_cur *
+xfs_bmbt_stage_cursor(
+ struct xfs_mount *mp,
+ struct xfs_inode *ip,
+ struct xbtree_ifakeroot *ifake)
+{
+ struct xfs_btree_cur *cur;
+ struct xfs_btree_ops *ops;
+
+ /* data fork always has larger maxheight */
+ cur = xfs_bmbt_init_common(mp, NULL, ip, XFS_DATA_FORK);
+ cur->bc_nlevels = ifake->if_levels;
+ cur->bc_ino.forksize = ifake->if_fork_size;
+
+ /* Don't let anyone think we're attached to the real fork yet. */
+ cur->bc_ino.whichfork = -1;
+ xfs_btree_stage_ifakeroot(cur, ifake, &ops);
+ ops->update_cursor = NULL;
+ return cur;
+}
+
+/*
+ * Swap in the new inode fork root. Once we pass this point the newly rebuilt
+ * mappings are in place and we have to kill off any old btree blocks.
+ */
+void
+xfs_bmbt_commit_staged_btree(
+ struct xfs_btree_cur *cur,
+ struct xfs_trans *tp,
+ int whichfork)
+{
+ struct xbtree_ifakeroot *ifake = cur->bc_ino.ifake;
+ struct xfs_ifork *ifp;
+ static const short brootflag[2] = {XFS_ILOG_DBROOT, XFS_ILOG_ABROOT};
+ static const short extflag[2] = {XFS_ILOG_DEXT, XFS_ILOG_AEXT};
+ int flags = XFS_ILOG_CORE;
+
+ ASSERT(cur->bc_flags & XFS_BTREE_STAGING);
+ ASSERT(whichfork != XFS_COW_FORK);
+
+ /*
+ * Free any resources hanging off the real fork, then shallow-copy the
+ * staging fork's contents into the real fork to transfer everything
+ * we just built.
+ */
+ ifp = xfs_ifork_ptr(cur->bc_ino.ip, whichfork);
+ xfs_idestroy_fork(ifp);
+ memcpy(ifp, ifake->if_fork, sizeof(struct xfs_ifork));
+
+ switch (ifp->if_format) {
+ case XFS_DINODE_FMT_EXTENTS:
+ flags |= extflag[whichfork];
+ break;
+ case XFS_DINODE_FMT_BTREE:
+ flags |= brootflag[whichfork];
+ break;
+ default:
+ ASSERT(0);
+ break;
+ }
+ xfs_trans_log_inode(tp, cur->bc_ino.ip, flags);
+ xfs_btree_commit_ifakeroot(cur, tp, whichfork, &xfs_bmbt_ops);
+}
+
+/*
* Calculate number of records in a bmap btree block.
*/
int
diff --git a/fs/xfs/libxfs/xfs_bmap_btree.h b/fs/xfs/libxfs/xfs_bmap_btree.h
index 3e7a40a83835..151b8491f60e 100644
--- a/fs/xfs/libxfs/xfs_bmap_btree.h
+++ b/fs/xfs/libxfs/xfs_bmap_btree.h
@@ -11,6 +11,7 @@ struct xfs_btree_block;
struct xfs_mount;
struct xfs_inode;
struct xfs_trans;
+struct xbtree_ifakeroot;
/*
* Btree block header size depends on a superblock flag.
@@ -106,6 +107,10 @@ extern int xfs_bmbt_change_owner(struct xfs_trans *tp, struct xfs_inode *ip,
extern struct xfs_btree_cur *xfs_bmbt_init_cursor(struct xfs_mount *,
struct xfs_trans *, struct xfs_inode *, int);
+struct xfs_btree_cur *xfs_bmbt_stage_cursor(struct xfs_mount *mp,
+ struct xfs_inode *ip, struct xbtree_ifakeroot *ifake);
+void xfs_bmbt_commit_staged_btree(struct xfs_btree_cur *cur,
+ struct xfs_trans *tp, int whichfork);
extern unsigned long long xfs_bmbt_calc_size(struct xfs_mount *mp,
unsigned long long len);
diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c
index 6a6503ab0cd7..ea8d3659df20 100644
--- a/fs/xfs/libxfs/xfs_btree.c
+++ b/fs/xfs/libxfs/xfs_btree.c
@@ -1330,7 +1330,7 @@ xfs_btree_get_buf_block(
* Read in the buffer at the given ptr and return the buffer and
* the block pointer within the buffer.
*/
-STATIC int
+int
xfs_btree_read_buf_block(
struct xfs_btree_cur *cur,
const union xfs_btree_ptr *ptr,
@@ -5212,3 +5212,29 @@ xfs_btree_destroy_cur_caches(void)
xfs_rmapbt_destroy_cur_cache();
xfs_refcountbt_destroy_cur_cache();
}
+
+/* Move the btree cursor before the first record. */
+int
+xfs_btree_goto_left_edge(
+ struct xfs_btree_cur *cur)
+{
+ int stat = 0;
+ int error;
+
+ memset(&cur->bc_rec, 0, sizeof(cur->bc_rec));
+ error = xfs_btree_lookup(cur, XFS_LOOKUP_LE, &stat);
+ if (error)
+ return error;
+ if (!stat)
+ return 0;
+
+ error = xfs_btree_decrement(cur, 0, &stat);
+ if (error)
+ return error;
+ if (stat != 0) {
+ ASSERT(0);
+ return -EFSCORRUPTED;
+ }
+
+ return 0;
+}
diff --git a/fs/xfs/libxfs/xfs_btree.h b/fs/xfs/libxfs/xfs_btree.h
index 4d68a58be160..d906324e25c8 100644
--- a/fs/xfs/libxfs/xfs_btree.h
+++ b/fs/xfs/libxfs/xfs_btree.h
@@ -700,6 +700,9 @@ void xfs_btree_set_ptr_null(struct xfs_btree_cur *cur,
int xfs_btree_get_buf_block(struct xfs_btree_cur *cur,
const union xfs_btree_ptr *ptr, struct xfs_btree_block **block,
struct xfs_buf **bpp);
+int xfs_btree_read_buf_block(struct xfs_btree_cur *cur,
+ const union xfs_btree_ptr *ptr, int flags,
+ struct xfs_btree_block **block, struct xfs_buf **bpp);
void xfs_btree_set_sibling(struct xfs_btree_cur *cur,
struct xfs_btree_block *block, const union xfs_btree_ptr *ptr,
int lr);
@@ -735,4 +738,6 @@ xfs_btree_alloc_cursor(
int __init xfs_btree_init_cur_caches(void);
void xfs_btree_destroy_cur_caches(void);
+int xfs_btree_goto_left_edge(struct xfs_btree_cur *cur);
+
#endif /* __XFS_BTREE_H__ */
diff --git a/fs/xfs/libxfs/xfs_btree_staging.c b/fs/xfs/libxfs/xfs_btree_staging.c
index dd75e208b543..e276eba87cb1 100644
--- a/fs/xfs/libxfs/xfs_btree_staging.c
+++ b/fs/xfs/libxfs/xfs_btree_staging.c
@@ -333,20 +333,41 @@ xfs_btree_commit_ifakeroot(
/*
* Put a btree block that we're loading onto the ordered list and release it.
* The btree blocks will be written to disk when bulk loading is finished.
+ * If we reach the dirty buffer threshold, flush them to disk before
+ * continuing.
*/
-static void
+static int
xfs_btree_bload_drop_buf(
- struct list_head *buffers_list,
- struct xfs_buf **bpp)
+ struct xfs_btree_bload *bbl,
+ struct list_head *buffers_list,
+ struct xfs_buf **bpp)
{
- if (*bpp == NULL)
- return;
+ struct xfs_buf *bp = *bpp;
+ int error;
+
+ if (!bp)
+ return 0;
- if (!xfs_buf_delwri_queue(*bpp, buffers_list))
- ASSERT(0);
+ /*
+ * Mark this buffer XBF_DONE (i.e. uptodate) so that a subsequent
+ * xfs_buf_read will not pointlessly reread the contents from the disk.
+ */
+ bp->b_flags |= XBF_DONE;
- xfs_buf_relse(*bpp);
+ xfs_buf_delwri_queue_here(bp, buffers_list);
+ xfs_buf_relse(bp);
*bpp = NULL;
+ bbl->nr_dirty++;
+
+ if (!bbl->max_dirty || bbl->nr_dirty < bbl->max_dirty)
+ return 0;
+
+ error = xfs_buf_delwri_submit(buffers_list);
+ if (error)
+ return error;
+
+ bbl->nr_dirty = 0;
+ return 0;
}
/*
@@ -384,7 +405,7 @@ xfs_btree_bload_prep_block(
ASSERT(*bpp == NULL);
/* Allocate a new incore btree root block. */
- new_size = bbl->iroot_size(cur, nr_this_block, priv);
+ new_size = bbl->iroot_size(cur, level, nr_this_block, priv);
ifp->if_broot = kmem_zalloc(new_size, 0);
ifp->if_broot_bytes = (int)new_size;
@@ -418,7 +439,10 @@ xfs_btree_bload_prep_block(
*/
if (*blockp)
xfs_btree_set_sibling(cur, *blockp, &new_ptr, XFS_BB_RIGHTSIB);
- xfs_btree_bload_drop_buf(buffers_list, bpp);
+
+ ret = xfs_btree_bload_drop_buf(bbl, buffers_list, bpp);
+ if (ret)
+ return ret;
/* Initialize the new btree block. */
xfs_btree_init_block_cur(cur, new_bp, level, nr_this_block);
@@ -436,22 +460,19 @@ STATIC int
xfs_btree_bload_leaf(
struct xfs_btree_cur *cur,
unsigned int recs_this_block,
- xfs_btree_bload_get_record_fn get_record,
+ xfs_btree_bload_get_records_fn get_records,
struct xfs_btree_block *block,
void *priv)
{
- unsigned int j;
+ unsigned int j = 1;
int ret;
/* Fill the leaf block with records. */
- for (j = 1; j <= recs_this_block; j++) {
- union xfs_btree_rec *block_rec;
-
- ret = get_record(cur, priv);
- if (ret)
+ while (j <= recs_this_block) {
+ ret = get_records(cur, j, block, recs_this_block - j + 1, priv);
+ if (ret < 0)
return ret;
- block_rec = xfs_btree_rec_addr(cur, j, block);
- cur->bc_ops->init_rec_from_cur(cur, block_rec);
+ j += ret;
}
return 0;
@@ -485,7 +506,12 @@ xfs_btree_bload_node(
ASSERT(!xfs_btree_ptr_is_null(cur, child_ptr));
- ret = xfs_btree_get_buf_block(cur, child_ptr, &child_block,
+ /*
+ * Read the lower-level block in case the buffer for it has
+ * been reclaimed. LRU refs will be set on the block, which is
+ * desirable if the new btree commits.
+ */
+ ret = xfs_btree_read_buf_block(cur, child_ptr, 0, &child_block,
&child_bp);
if (ret)
return ret;
@@ -570,7 +596,14 @@ xfs_btree_bload_level_geometry(
unsigned int desired_npb;
unsigned int maxnr;
- maxnr = cur->bc_ops->get_maxrecs(cur, level);
+ /*
+ * Compute the absolute maximum number of records that we can store in
+ * the ondisk block or inode root.
+ */
+ if (cur->bc_ops->get_dmaxrecs)
+ maxnr = cur->bc_ops->get_dmaxrecs(cur, level);
+ else
+ maxnr = cur->bc_ops->get_maxrecs(cur, level);
/*
* Compute the number of blocks we need to fill each block with the
@@ -764,6 +797,7 @@ xfs_btree_bload(
cur->bc_nlevels = bbl->btree_height;
xfs_btree_set_ptr_null(cur, &child_ptr);
xfs_btree_set_ptr_null(cur, &ptr);
+ bbl->nr_dirty = 0;
xfs_btree_bload_level_geometry(cur, bbl, level, nr_this_level,
&avg_per_block, &blocks, &blocks_with_extra);
@@ -789,7 +823,7 @@ xfs_btree_bload(
trace_xfs_btree_bload_block(cur, level, i, blocks, &ptr,
nr_this_block);
- ret = xfs_btree_bload_leaf(cur, nr_this_block, bbl->get_record,
+ ret = xfs_btree_bload_leaf(cur, nr_this_block, bbl->get_records,
block, priv);
if (ret)
goto out;
@@ -802,7 +836,10 @@ xfs_btree_bload(
xfs_btree_copy_ptrs(cur, &child_ptr, &ptr, 1);
}
total_blocks += blocks;
- xfs_btree_bload_drop_buf(&buffers_list, &bp);
+
+ ret = xfs_btree_bload_drop_buf(bbl, &buffers_list, &bp);
+ if (ret)
+ goto out;
/* Populate the internal btree nodes. */
for (level = 1; level < cur->bc_nlevels; level++) {
@@ -844,7 +881,11 @@ xfs_btree_bload(
xfs_btree_copy_ptrs(cur, &first_ptr, &ptr, 1);
}
total_blocks += blocks;
- xfs_btree_bload_drop_buf(&buffers_list, &bp);
+
+ ret = xfs_btree_bload_drop_buf(bbl, &buffers_list, &bp);
+ if (ret)
+ goto out;
+
xfs_btree_copy_ptrs(cur, &child_ptr, &first_ptr, 1);
}
diff --git a/fs/xfs/libxfs/xfs_btree_staging.h b/fs/xfs/libxfs/xfs_btree_staging.h
index f0d2976050ae..055ea43b1e18 100644
--- a/fs/xfs/libxfs/xfs_btree_staging.h
+++ b/fs/xfs/libxfs/xfs_btree_staging.h
@@ -37,12 +37,6 @@ struct xbtree_ifakeroot {
/* Number of bytes available for this fork in the inode. */
unsigned int if_fork_size;
-
- /* Fork format. */
- unsigned int if_format;
-
- /* Number of records. */
- unsigned int if_extents;
};
/* Cursor interactions with fake roots for inode-rooted btrees. */
@@ -53,19 +47,24 @@ void xfs_btree_commit_ifakeroot(struct xfs_btree_cur *cur, struct xfs_trans *tp,
int whichfork, const struct xfs_btree_ops *ops);
/* Bulk loading of staged btrees. */
-typedef int (*xfs_btree_bload_get_record_fn)(struct xfs_btree_cur *cur, void *priv);
+typedef int (*xfs_btree_bload_get_records_fn)(struct xfs_btree_cur *cur,
+ unsigned int idx, struct xfs_btree_block *block,
+ unsigned int nr_wanted, void *priv);
typedef int (*xfs_btree_bload_claim_block_fn)(struct xfs_btree_cur *cur,
union xfs_btree_ptr *ptr, void *priv);
typedef size_t (*xfs_btree_bload_iroot_size_fn)(struct xfs_btree_cur *cur,
- unsigned int nr_this_level, void *priv);
+ unsigned int level, unsigned int nr_this_level, void *priv);
struct xfs_btree_bload {
/*
- * This function will be called nr_records times to load records into
- * the btree. The function does this by setting the cursor's bc_rec
- * field in in-core format. Records must be returned in sort order.
+ * This function will be called to load @nr_wanted records into the
+ * btree. The implementation does this by setting the cursor's bc_rec
+ * field in in-core format and using init_rec_from_cur to set the
+ * records in the btree block. Records must be returned in sort order.
+ * The function must return the number of records loaded or the usual
+ * negative errno.
*/
- xfs_btree_bload_get_record_fn get_record;
+ xfs_btree_bload_get_records_fn get_records;
/*
* This function will be called nr_blocks times to obtain a pointer
@@ -113,6 +112,16 @@ struct xfs_btree_bload {
* height of the new btree.
*/
unsigned int btree_height;
+
+ /*
+ * Flush the new btree block buffer list to disk after this many blocks
+ * have been formatted. Zero prohibits writing any buffers until all
+ * blocks have been formatted.
+ */
+ uint16_t max_dirty;
+
+ /* Number of dirty buffers. */
+ uint16_t nr_dirty;
};
int xfs_btree_bload_compute_geometry(struct xfs_btree_cur *cur,
diff --git a/fs/xfs/libxfs/xfs_da_btree.c b/fs/xfs/libxfs/xfs_da_btree.c
index e576560b46e9..5457188bb4de 100644
--- a/fs/xfs/libxfs/xfs_da_btree.c
+++ b/fs/xfs/libxfs/xfs_da_btree.c
@@ -421,6 +421,25 @@ xfs_da3_node_read_mapped(
return xfs_da3_node_set_type(tp, *bpp);
}
+/*
+ * Copy src directory/attr leaf/node buffer to the dst.
+ * For v5 file systems make sure the right blkno is stamped in.
+ */
+void
+xfs_da_buf_copy(
+ struct xfs_buf *dst,
+ struct xfs_buf *src,
+ size_t size)
+{
+ struct xfs_da3_blkinfo *da3 = dst->b_addr;
+
+ memcpy(dst->b_addr, src->b_addr, size);
+ dst->b_ops = src->b_ops;
+ xfs_trans_buf_copy_type(dst, src);
+ if (xfs_has_crc(dst->b_mount))
+ da3->blkno = cpu_to_be64(xfs_buf_daddr(dst));
+}
+
/*========================================================================
* Routines used for growing the Btree.
*========================================================================*/
@@ -690,12 +709,6 @@ xfs_da3_root_split(
btree = icnodehdr.btree;
size = (int)((char *)&btree[icnodehdr.count] - (char *)oldroot);
level = icnodehdr.level;
-
- /*
- * we are about to copy oldroot to bp, so set up the type
- * of bp while we know exactly what it will be.
- */
- xfs_trans_buf_set_type(tp, bp, XFS_BLFT_DA_NODE_BUF);
} else {
struct xfs_dir3_icleaf_hdr leafhdr;
@@ -707,31 +720,17 @@ xfs_da3_root_split(
size = (int)((char *)&leafhdr.ents[leafhdr.count] -
(char *)leaf);
level = 0;
-
- /*
- * we are about to copy oldroot to bp, so set up the type
- * of bp while we know exactly what it will be.
- */
- xfs_trans_buf_set_type(tp, bp, XFS_BLFT_DIR_LEAFN_BUF);
}
/*
- * we can copy most of the information in the node from one block to
- * another, but for CRC enabled headers we have to make sure that the
- * block specific identifiers are kept intact. We update the buffer
- * directly for this.
+ * Copy old root to new buffer and log it.
*/
- memcpy(node, oldroot, size);
- if (oldroot->hdr.info.magic == cpu_to_be16(XFS_DA3_NODE_MAGIC) ||
- oldroot->hdr.info.magic == cpu_to_be16(XFS_DIR3_LEAFN_MAGIC)) {
- struct xfs_da3_intnode *node3 = (struct xfs_da3_intnode *)node;
-
- node3->hdr.info.blkno = cpu_to_be64(xfs_buf_daddr(bp));
- }
+ xfs_da_buf_copy(bp, blk1->bp, size);
xfs_trans_log_buf(tp, bp, 0, size - 1);
- bp->b_ops = blk1->bp->b_ops;
- xfs_trans_buf_copy_type(bp, blk1->bp);
+ /*
+ * Update blk1 to point to new buffer.
+ */
blk1->bp = bp;
blk1->blkno = blkno;
@@ -1220,21 +1219,14 @@ xfs_da3_root_join(
xfs_da_blkinfo_onlychild_validate(bp->b_addr, oldroothdr.level);
/*
- * This could be copying a leaf back into the root block in the case of
- * there only being a single leaf block left in the tree. Hence we have
- * to update the b_ops pointer as well to match the buffer type change
- * that could occur. For dir3 blocks we also need to update the block
- * number in the buffer header.
+ * Copy child to root buffer and log it.
*/
- memcpy(root_blk->bp->b_addr, bp->b_addr, args->geo->blksize);
- root_blk->bp->b_ops = bp->b_ops;
- xfs_trans_buf_copy_type(root_blk->bp, bp);
- if (oldroothdr.magic == XFS_DA3_NODE_MAGIC) {
- struct xfs_da3_blkinfo *da3 = root_blk->bp->b_addr;
- da3->blkno = cpu_to_be64(xfs_buf_daddr(root_blk->bp));
- }
+ xfs_da_buf_copy(root_blk->bp, bp, args->geo->blksize);
xfs_trans_log_buf(args->trans, root_blk->bp, 0,
args->geo->blksize - 1);
+ /*
+ * Now we can drop the child buffer.
+ */
error = xfs_da_shrink_inode(args, child, bp);
return error;
}
@@ -2317,9 +2309,10 @@ xfs_da3_swap_lastblock(
/*
* Copy the last block into the dead buffer and log it.
*/
- memcpy(dead_buf->b_addr, last_buf->b_addr, args->geo->blksize);
+ xfs_da_buf_copy(dead_buf, last_buf, args->geo->blksize);
xfs_trans_log_buf(tp, dead_buf, 0, args->geo->blksize - 1);
dead_info = dead_buf->b_addr;
+
/*
* Get values from the moved block.
*/
diff --git a/fs/xfs/libxfs/xfs_da_btree.h b/fs/xfs/libxfs/xfs_da_btree.h
index ffa3df5b2893..706baf36e175 100644
--- a/fs/xfs/libxfs/xfs_da_btree.h
+++ b/fs/xfs/libxfs/xfs_da_btree.h
@@ -219,6 +219,8 @@ int xfs_da_reada_buf(struct xfs_inode *dp, xfs_dablk_t bno,
const struct xfs_buf_ops *ops);
int xfs_da_shrink_inode(xfs_da_args_t *args, xfs_dablk_t dead_blkno,
struct xfs_buf *dead_buf);
+void xfs_da_buf_copy(struct xfs_buf *dst, struct xfs_buf *src,
+ size_t size);
uint xfs_da_hashname(const uint8_t *name_string, int name_length);
enum xfs_dacmp xfs_da_compname(struct xfs_da_args *args,
diff --git a/fs/xfs/libxfs/xfs_da_format.h b/fs/xfs/libxfs/xfs_da_format.h
index f9015f88eca7..24f9d1461f9a 100644
--- a/fs/xfs/libxfs/xfs_da_format.h
+++ b/fs/xfs/libxfs/xfs_da_format.h
@@ -578,20 +578,25 @@ xfs_dir2_block_leaf_p(struct xfs_dir2_block_tail *btp)
#define XFS_ATTR_LEAF_MAPSIZE 3 /* how many freespace slots */
/*
- * Entries are packed toward the top as tight as possible.
- */
-struct xfs_attr_shortform {
- struct xfs_attr_sf_hdr { /* constant-structure header block */
- __be16 totsize; /* total bytes in shortform list */
- __u8 count; /* count of active entries */
- __u8 padding;
- } hdr;
- struct xfs_attr_sf_entry {
- uint8_t namelen; /* actual length of name (no NULL) */
- uint8_t valuelen; /* actual length of value (no NULL) */
- uint8_t flags; /* flags bits (see xfs_attr_leaf.h) */
- uint8_t nameval[]; /* name & value bytes concatenated */
- } list[]; /* variable sized array */
+ * Attribute storage when stored inside the inode.
+ *
+ * Small attribute lists are packed as tightly as possible so as to fit into the
+ * literal area of the inode.
+ *
+ * These "shortform" attribute forks consist of a single xfs_attr_sf_hdr header
+ * followed by zero or more xfs_attr_sf_entry structures.
+ */
+struct xfs_attr_sf_hdr { /* constant-structure header block */
+ __be16 totsize; /* total bytes in shortform list */
+ __u8 count; /* count of active entries */
+ __u8 padding;
+};
+
+struct xfs_attr_sf_entry {
+ __u8 namelen; /* actual length of name (no NULL) */
+ __u8 valuelen; /* actual length of value (no NULL) */
+ __u8 flags; /* flags bits (XFS_ATTR_*) */
+ __u8 nameval[]; /* name & value bytes concatenated */
};
typedef struct xfs_attr_leaf_map { /* RLE map of free bytes */
diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c
index f71679ce23b9..66a17910d021 100644
--- a/fs/xfs/libxfs/xfs_defer.c
+++ b/fs/xfs/libxfs/xfs_defer.c
@@ -26,6 +26,7 @@
#include "xfs_da_format.h"
#include "xfs_da_btree.h"
#include "xfs_attr.h"
+#include "xfs_trans_priv.h"
static struct kmem_cache *xfs_defer_pending_cache;
@@ -181,16 +182,89 @@ static struct kmem_cache *xfs_defer_pending_cache;
* Note that the continuation requested between t2 and t3 is likely to
* reoccur.
*/
+STATIC struct xfs_log_item *
+xfs_defer_barrier_create_intent(
+ struct xfs_trans *tp,
+ struct list_head *items,
+ unsigned int count,
+ bool sort)
+{
+ return NULL;
+}
-static const struct xfs_defer_op_type *defer_op_types[] = {
- [XFS_DEFER_OPS_TYPE_BMAP] = &xfs_bmap_update_defer_type,
- [XFS_DEFER_OPS_TYPE_REFCOUNT] = &xfs_refcount_update_defer_type,
- [XFS_DEFER_OPS_TYPE_RMAP] = &xfs_rmap_update_defer_type,
- [XFS_DEFER_OPS_TYPE_FREE] = &xfs_extent_free_defer_type,
- [XFS_DEFER_OPS_TYPE_AGFL_FREE] = &xfs_agfl_free_defer_type,
- [XFS_DEFER_OPS_TYPE_ATTR] = &xfs_attr_defer_type,
+STATIC void
+xfs_defer_barrier_abort_intent(
+ struct xfs_log_item *intent)
+{
+ /* empty */
+}
+
+STATIC struct xfs_log_item *
+xfs_defer_barrier_create_done(
+ struct xfs_trans *tp,
+ struct xfs_log_item *intent,
+ unsigned int count)
+{
+ return NULL;
+}
+
+STATIC int
+xfs_defer_barrier_finish_item(
+ struct xfs_trans *tp,
+ struct xfs_log_item *done,
+ struct list_head *item,
+ struct xfs_btree_cur **state)
+{
+ ASSERT(0);
+ return -EFSCORRUPTED;
+}
+
+STATIC void
+xfs_defer_barrier_cancel_item(
+ struct list_head *item)
+{
+ ASSERT(0);
+}
+
+static const struct xfs_defer_op_type xfs_barrier_defer_type = {
+ .max_items = 1,
+ .create_intent = xfs_defer_barrier_create_intent,
+ .abort_intent = xfs_defer_barrier_abort_intent,
+ .create_done = xfs_defer_barrier_create_done,
+ .finish_item = xfs_defer_barrier_finish_item,
+ .cancel_item = xfs_defer_barrier_cancel_item,
};
+/* Create a log intent done item for a log intent item. */
+static inline void
+xfs_defer_create_done(
+ struct xfs_trans *tp,
+ struct xfs_defer_pending *dfp)
+{
+ struct xfs_log_item *lip;
+
+ /* If there is no log intent item, there can be no log done item. */
+ if (!dfp->dfp_intent)
+ return;
+
+ /*
+ * Mark the transaction dirty, even on error. This ensures the
+ * transaction is aborted, which:
+ *
+ * 1.) releases the log intent item and frees the log done item
+ * 2.) shuts down the filesystem
+ */
+ tp->t_flags |= XFS_TRANS_DIRTY;
+ lip = dfp->dfp_ops->create_done(tp, dfp->dfp_intent, dfp->dfp_count);
+ if (!lip)
+ return;
+
+ tp->t_flags |= XFS_TRANS_HAS_INTENT_DONE;
+ xfs_trans_add_item(tp, lip);
+ set_bit(XFS_LI_DIRTY, &lip->li_flags);
+ dfp->dfp_done = lip;
+}
+
/*
* Ensure there's a log intent item associated with this deferred work item if
* the operation must be restarted on crash. Returns 1 if there's a log item;
@@ -202,18 +276,21 @@ xfs_defer_create_intent(
struct xfs_defer_pending *dfp,
bool sort)
{
- const struct xfs_defer_op_type *ops = defer_op_types[dfp->dfp_type];
struct xfs_log_item *lip;
if (dfp->dfp_intent)
return 1;
- lip = ops->create_intent(tp, &dfp->dfp_work, dfp->dfp_count, sort);
+ lip = dfp->dfp_ops->create_intent(tp, &dfp->dfp_work, dfp->dfp_count,
+ sort);
if (!lip)
return 0;
if (IS_ERR(lip))
return PTR_ERR(lip);
+ tp->t_flags |= XFS_TRANS_DIRTY;
+ xfs_trans_add_item(tp, lip);
+ set_bit(XFS_LI_DIRTY, &lip->li_flags);
dfp->dfp_intent = lip;
return 1;
}
@@ -245,23 +322,50 @@ xfs_defer_create_intents(
return ret;
}
-STATIC void
+static inline void
xfs_defer_pending_abort(
struct xfs_mount *mp,
+ struct xfs_defer_pending *dfp)
+{
+ trace_xfs_defer_pending_abort(mp, dfp);
+
+ if (dfp->dfp_intent && !dfp->dfp_done) {
+ dfp->dfp_ops->abort_intent(dfp->dfp_intent);
+ dfp->dfp_intent = NULL;
+ }
+}
+
+static inline void
+xfs_defer_pending_cancel_work(
+ struct xfs_mount *mp,
+ struct xfs_defer_pending *dfp)
+{
+ struct list_head *pwi;
+ struct list_head *n;
+
+ trace_xfs_defer_cancel_list(mp, dfp);
+
+ list_del(&dfp->dfp_list);
+ list_for_each_safe(pwi, n, &dfp->dfp_work) {
+ list_del(pwi);
+ dfp->dfp_count--;
+ trace_xfs_defer_cancel_item(mp, dfp, pwi);
+ dfp->dfp_ops->cancel_item(pwi);
+ }
+ ASSERT(dfp->dfp_count == 0);
+ kmem_cache_free(xfs_defer_pending_cache, dfp);
+}
+
+STATIC void
+xfs_defer_pending_abort_list(
+ struct xfs_mount *mp,
struct list_head *dop_list)
{
struct xfs_defer_pending *dfp;
- const struct xfs_defer_op_type *ops;
/* Abort intent items that don't have a done item. */
- list_for_each_entry(dfp, dop_list, dfp_list) {
- ops = defer_op_types[dfp->dfp_type];
- trace_xfs_defer_pending_abort(mp, dfp);
- if (dfp->dfp_intent && !dfp->dfp_done) {
- ops->abort_intent(dfp->dfp_intent);
- dfp->dfp_intent = NULL;
- }
- }
+ list_for_each_entry(dfp, dop_list, dfp_list)
+ xfs_defer_pending_abort(mp, dfp);
}
/* Abort all the intents that were committed. */
@@ -271,7 +375,7 @@ xfs_defer_trans_abort(
struct list_head *dop_pending)
{
trace_xfs_defer_trans_abort(tp, _RET_IP_);
- xfs_defer_pending_abort(tp->t_mountp, dop_pending);
+ xfs_defer_pending_abort_list(tp->t_mountp, dop_pending);
}
/*
@@ -389,27 +493,31 @@ xfs_defer_cancel_list(
{
struct xfs_defer_pending *dfp;
struct xfs_defer_pending *pli;
- struct list_head *pwi;
- struct list_head *n;
- const struct xfs_defer_op_type *ops;
/*
* Free the pending items. Caller should already have arranged
* for the intent items to be released.
*/
- list_for_each_entry_safe(dfp, pli, dop_list, dfp_list) {
- ops = defer_op_types[dfp->dfp_type];
- trace_xfs_defer_cancel_list(mp, dfp);
- list_del(&dfp->dfp_list);
- list_for_each_safe(pwi, n, &dfp->dfp_work) {
- list_del(pwi);
- dfp->dfp_count--;
- trace_xfs_defer_cancel_item(mp, dfp, pwi);
- ops->cancel_item(pwi);
- }
- ASSERT(dfp->dfp_count == 0);
- kmem_cache_free(xfs_defer_pending_cache, dfp);
+ list_for_each_entry_safe(dfp, pli, dop_list, dfp_list)
+ xfs_defer_pending_cancel_work(mp, dfp);
+}
+
+static inline void
+xfs_defer_relog_intent(
+ struct xfs_trans *tp,
+ struct xfs_defer_pending *dfp)
+{
+ struct xfs_log_item *lip;
+
+ xfs_defer_create_done(tp, dfp);
+
+ lip = dfp->dfp_ops->relog_intent(tp, dfp->dfp_intent, dfp->dfp_done);
+ if (lip) {
+ xfs_trans_add_item(tp, lip);
+ set_bit(XFS_LI_DIRTY, &lip->li_flags);
}
+ dfp->dfp_done = NULL;
+ dfp->dfp_intent = lip;
}
/*
@@ -417,7 +525,7 @@ xfs_defer_cancel_list(
* done item to release the intent item; and then log a new intent item.
* The caller should provide a fresh transaction and roll it after we're done.
*/
-static int
+static void
xfs_defer_relog(
struct xfs_trans **tpp,
struct list_head *dfops)
@@ -456,31 +564,28 @@ xfs_defer_relog(
trace_xfs_defer_relog_intent((*tpp)->t_mountp, dfp);
XFS_STATS_INC((*tpp)->t_mountp, defer_relog);
- dfp->dfp_intent = xfs_trans_item_relog(dfp->dfp_intent, *tpp);
- }
- if ((*tpp)->t_flags & XFS_TRANS_DIRTY)
- return xfs_defer_trans_roll(tpp);
- return 0;
+ xfs_defer_relog_intent(*tpp, dfp);
+ }
}
/*
* Log an intent-done item for the first pending intent, and finish the work
* items.
*/
-static int
+int
xfs_defer_finish_one(
struct xfs_trans *tp,
struct xfs_defer_pending *dfp)
{
- const struct xfs_defer_op_type *ops = defer_op_types[dfp->dfp_type];
+ const struct xfs_defer_op_type *ops = dfp->dfp_ops;
struct xfs_btree_cur *state = NULL;
struct list_head *li, *n;
int error;
trace_xfs_defer_pending_finish(tp->t_mountp, dfp);
- dfp->dfp_done = ops->create_done(tp, dfp->dfp_intent, dfp->dfp_count);
+ xfs_defer_create_done(tp, dfp);
list_for_each_safe(li, n, &dfp->dfp_work) {
list_del(li);
dfp->dfp_count--;
@@ -517,6 +622,24 @@ out:
return error;
}
+/* Move all paused deferred work from @tp to @paused_list. */
+static void
+xfs_defer_isolate_paused(
+ struct xfs_trans *tp,
+ struct list_head *paused_list)
+{
+ struct xfs_defer_pending *dfp;
+ struct xfs_defer_pending *pli;
+
+ list_for_each_entry_safe(dfp, pli, &tp->t_dfops, dfp_list) {
+ if (!(dfp->dfp_flags & XFS_DEFER_PAUSED))
+ continue;
+
+ list_move_tail(&dfp->dfp_list, paused_list);
+ trace_xfs_defer_isolate_paused(tp->t_mountp, dfp);
+ }
+}
+
/*
* Finish all the pending work. This involves logging intent items for
* any work items that wandered in since the last transaction roll (if
@@ -532,6 +655,7 @@ xfs_defer_finish_noroll(
struct xfs_defer_pending *dfp = NULL;
int error = 0;
LIST_HEAD(dop_pending);
+ LIST_HEAD(dop_paused);
ASSERT((*tp)->t_flags & XFS_TRANS_PERM_LOG_RES);
@@ -550,6 +674,8 @@ xfs_defer_finish_noroll(
*/
int has_intents = xfs_defer_create_intents(*tp);
+ xfs_defer_isolate_paused(*tp, &dop_paused);
+
list_splice_init(&(*tp)->t_dfops, &dop_pending);
if (has_intents < 0) {
@@ -562,22 +688,33 @@ xfs_defer_finish_noroll(
goto out_shutdown;
/* Relog intent items to keep the log moving. */
- error = xfs_defer_relog(tp, &dop_pending);
- if (error)
- goto out_shutdown;
+ xfs_defer_relog(tp, &dop_pending);
+ xfs_defer_relog(tp, &dop_paused);
+
+ if ((*tp)->t_flags & XFS_TRANS_DIRTY) {
+ error = xfs_defer_trans_roll(tp);
+ if (error)
+ goto out_shutdown;
+ }
}
- dfp = list_first_entry(&dop_pending, struct xfs_defer_pending,
- dfp_list);
+ dfp = list_first_entry_or_null(&dop_pending,
+ struct xfs_defer_pending, dfp_list);
+ if (!dfp)
+ break;
error = xfs_defer_finish_one(*tp, dfp);
if (error && error != -EAGAIN)
goto out_shutdown;
}
+ /* Requeue the paused items in the outgoing transaction. */
+ list_splice_tail_init(&dop_paused, &(*tp)->t_dfops);
+
trace_xfs_defer_finish_done(*tp, _RET_IP_);
return 0;
out_shutdown:
+ list_splice_tail_init(&dop_paused, &dop_pending);
xfs_defer_trans_abort(*tp, &dop_pending);
xfs_force_shutdown((*tp)->t_mountp, SHUTDOWN_CORRUPT_INCORE);
trace_xfs_defer_finish_error(*tp, error);
@@ -590,6 +727,9 @@ int
xfs_defer_finish(
struct xfs_trans **tp)
{
+#ifdef DEBUG
+ struct xfs_defer_pending *dfp;
+#endif
int error;
/*
@@ -609,7 +749,10 @@ xfs_defer_finish(
}
/* Reset LOWMODE now that we've finished all the dfops. */
- ASSERT(list_empty(&(*tp)->t_dfops));
+#ifdef DEBUG
+ list_for_each_entry(dfp, &(*tp)->t_dfops, dfp_list)
+ ASSERT(dfp->dfp_flags & XFS_DEFER_PAUSED);
+#endif
(*tp)->t_flags &= ~XFS_TRANS_LOWMODE;
return 0;
}
@@ -621,48 +764,165 @@ xfs_defer_cancel(
struct xfs_mount *mp = tp->t_mountp;
trace_xfs_defer_cancel(tp, _RET_IP_);
+ xfs_defer_trans_abort(tp, &tp->t_dfops);
xfs_defer_cancel_list(mp, &tp->t_dfops);
}
+/*
+ * Return the last pending work item attached to this transaction if it matches
+ * the deferred op type.
+ */
+static inline struct xfs_defer_pending *
+xfs_defer_find_last(
+ struct xfs_trans *tp,
+ const struct xfs_defer_op_type *ops)
+{
+ struct xfs_defer_pending *dfp = NULL;
+
+ /* No dfops at all? */
+ if (list_empty(&tp->t_dfops))
+ return NULL;
+
+ dfp = list_last_entry(&tp->t_dfops, struct xfs_defer_pending,
+ dfp_list);
+
+ /* Wrong type? */
+ if (dfp->dfp_ops != ops)
+ return NULL;
+ return dfp;
+}
+
+/*
+ * Decide if we can add a deferred work item to the last dfops item attached
+ * to the transaction.
+ */
+static inline bool
+xfs_defer_can_append(
+ struct xfs_defer_pending *dfp,
+ const struct xfs_defer_op_type *ops)
+{
+ /* Already logged? */
+ if (dfp->dfp_intent)
+ return false;
+
+ /* Paused items cannot absorb more work */
+ if (dfp->dfp_flags & XFS_DEFER_PAUSED)
+ return NULL;
+
+ /* Already full? */
+ if (ops->max_items && dfp->dfp_count >= ops->max_items)
+ return false;
+
+ return true;
+}
+
+/* Create a new pending item at the end of the transaction list. */
+static inline struct xfs_defer_pending *
+xfs_defer_alloc(
+ struct xfs_trans *tp,
+ const struct xfs_defer_op_type *ops)
+{
+ struct xfs_defer_pending *dfp;
+
+ dfp = kmem_cache_zalloc(xfs_defer_pending_cache,
+ GFP_NOFS | __GFP_NOFAIL);
+ dfp->dfp_ops = ops;
+ INIT_LIST_HEAD(&dfp->dfp_work);
+ list_add_tail(&dfp->dfp_list, &tp->t_dfops);
+
+ return dfp;
+}
+
/* Add an item for later deferred processing. */
-void
+struct xfs_defer_pending *
xfs_defer_add(
struct xfs_trans *tp,
- enum xfs_defer_ops_type type,
- struct list_head *li)
+ struct list_head *li,
+ const struct xfs_defer_op_type *ops)
{
struct xfs_defer_pending *dfp = NULL;
- const struct xfs_defer_op_type *ops = defer_op_types[type];
ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES);
- BUILD_BUG_ON(ARRAY_SIZE(defer_op_types) != XFS_DEFER_OPS_TYPE_MAX);
- /*
- * Add the item to a pending item at the end of the intake list.
- * If the last pending item has the same type, reuse it. Else,
- * create a new pending item at the end of the intake list.
- */
- if (!list_empty(&tp->t_dfops)) {
- dfp = list_last_entry(&tp->t_dfops,
- struct xfs_defer_pending, dfp_list);
- if (dfp->dfp_type != type ||
- (ops->max_items && dfp->dfp_count >= ops->max_items))
- dfp = NULL;
- }
- if (!dfp) {
- dfp = kmem_cache_zalloc(xfs_defer_pending_cache,
- GFP_NOFS | __GFP_NOFAIL);
- dfp->dfp_type = type;
- dfp->dfp_intent = NULL;
- dfp->dfp_done = NULL;
- dfp->dfp_count = 0;
- INIT_LIST_HEAD(&dfp->dfp_work);
- list_add_tail(&dfp->dfp_list, &tp->t_dfops);
- }
+ dfp = xfs_defer_find_last(tp, ops);
+ if (!dfp || !xfs_defer_can_append(dfp, ops))
+ dfp = xfs_defer_alloc(tp, ops);
- list_add_tail(li, &dfp->dfp_work);
+ xfs_defer_add_item(dfp, li);
trace_xfs_defer_add_item(tp->t_mountp, dfp, li);
- dfp->dfp_count++;
+ return dfp;
+}
+
+/*
+ * Add a defer ops barrier to force two otherwise adjacent deferred work items
+ * to be tracked separately and have separate log items.
+ */
+void
+xfs_defer_add_barrier(
+ struct xfs_trans *tp)
+{
+ struct xfs_defer_pending *dfp;
+
+ ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES);
+
+ /* If the last defer op added was a barrier, we're done. */
+ dfp = xfs_defer_find_last(tp, &xfs_barrier_defer_type);
+ if (dfp)
+ return;
+
+ xfs_defer_alloc(tp, &xfs_barrier_defer_type);
+
+ trace_xfs_defer_add_item(tp->t_mountp, dfp, NULL);
+}
+
+/*
+ * Create a pending deferred work item to replay the recovered intent item
+ * and add it to the list.
+ */
+void
+xfs_defer_start_recovery(
+ struct xfs_log_item *lip,
+ struct list_head *r_dfops,
+ const struct xfs_defer_op_type *ops)
+{
+ struct xfs_defer_pending *dfp;
+
+ dfp = kmem_cache_zalloc(xfs_defer_pending_cache,
+ GFP_NOFS | __GFP_NOFAIL);
+ dfp->dfp_ops = ops;
+ dfp->dfp_intent = lip;
+ INIT_LIST_HEAD(&dfp->dfp_work);
+ list_add_tail(&dfp->dfp_list, r_dfops);
+}
+
+/*
+ * Cancel a deferred work item created to recover a log intent item. @dfp
+ * will be freed after this function returns.
+ */
+void
+xfs_defer_cancel_recovery(
+ struct xfs_mount *mp,
+ struct xfs_defer_pending *dfp)
+{
+ xfs_defer_pending_abort(mp, dfp);
+ xfs_defer_pending_cancel_work(mp, dfp);
+}
+
+/* Replay the deferred work item created from a recovered log intent item. */
+int
+xfs_defer_finish_recovery(
+ struct xfs_mount *mp,
+ struct xfs_defer_pending *dfp,
+ struct list_head *capture_list)
+{
+ const struct xfs_defer_op_type *ops = dfp->dfp_ops;
+ int error;
+
+ /* dfp is freed by recover_work and must not be accessed afterwards */
+ error = ops->recover_work(dfp, capture_list);
+ if (error)
+ trace_xlog_intent_recovery_failed(mp, ops, error);
+ return error;
}
/*
@@ -769,7 +1029,7 @@ xfs_defer_ops_capture_abort(
{
unsigned short i;
- xfs_defer_pending_abort(mp, &dfc->dfc_dfops);
+ xfs_defer_pending_abort_list(mp, &dfc->dfc_dfops);
xfs_defer_cancel_list(mp, &dfc->dfc_dfops);
for (i = 0; i < dfc->dfc_held.dr_bufs; i++)
@@ -938,3 +1198,36 @@ xfs_defer_destroy_item_caches(void)
xfs_rmap_intent_destroy_cache();
xfs_defer_destroy_cache();
}
+
+/*
+ * Mark a deferred work item so that it will be requeued indefinitely without
+ * being finished. Caller must ensure there are no data dependencies on this
+ * work item in the meantime.
+ */
+void
+xfs_defer_item_pause(
+ struct xfs_trans *tp,
+ struct xfs_defer_pending *dfp)
+{
+ ASSERT(!(dfp->dfp_flags & XFS_DEFER_PAUSED));
+
+ dfp->dfp_flags |= XFS_DEFER_PAUSED;
+
+ trace_xfs_defer_item_pause(tp->t_mountp, dfp);
+}
+
+/*
+ * Release a paused deferred work item so that it will be finished during the
+ * next transaction roll.
+ */
+void
+xfs_defer_item_unpause(
+ struct xfs_trans *tp,
+ struct xfs_defer_pending *dfp)
+{
+ ASSERT(dfp->dfp_flags & XFS_DEFER_PAUSED);
+
+ dfp->dfp_flags &= ~XFS_DEFER_PAUSED;
+
+ trace_xfs_defer_item_unpause(tp->t_mountp, dfp);
+}
diff --git a/fs/xfs/libxfs/xfs_defer.h b/fs/xfs/libxfs/xfs_defer.h
index 8788ad5f6a73..18a9fb92dde8 100644
--- a/fs/xfs/libxfs/xfs_defer.h
+++ b/fs/xfs/libxfs/xfs_defer.h
@@ -11,19 +11,6 @@ struct xfs_defer_op_type;
struct xfs_defer_capture;
/*
- * Header for deferred operation list.
- */
-enum xfs_defer_ops_type {
- XFS_DEFER_OPS_TYPE_BMAP,
- XFS_DEFER_OPS_TYPE_REFCOUNT,
- XFS_DEFER_OPS_TYPE_RMAP,
- XFS_DEFER_OPS_TYPE_FREE,
- XFS_DEFER_OPS_TYPE_AGFL_FREE,
- XFS_DEFER_OPS_TYPE_ATTR,
- XFS_DEFER_OPS_TYPE_MAX,
-};
-
-/*
* Save a log intent item and a list of extents, so that we can replay
* whatever action had to happen to the extent list and file the log done
* item.
@@ -33,19 +20,35 @@ struct xfs_defer_pending {
struct list_head dfp_work; /* work items */
struct xfs_log_item *dfp_intent; /* log intent item */
struct xfs_log_item *dfp_done; /* log done item */
+ const struct xfs_defer_op_type *dfp_ops;
unsigned int dfp_count; /* # extent items */
- enum xfs_defer_ops_type dfp_type;
+ unsigned int dfp_flags;
};
-void xfs_defer_add(struct xfs_trans *tp, enum xfs_defer_ops_type type,
- struct list_head *h);
+/*
+ * Create a log intent item for this deferred item, but don't actually finish
+ * the work. Caller must clear this before the final transaction commit.
+ */
+#define XFS_DEFER_PAUSED (1U << 0)
+
+#define XFS_DEFER_PENDING_STRINGS \
+ { XFS_DEFER_PAUSED, "paused" }
+
+void xfs_defer_item_pause(struct xfs_trans *tp, struct xfs_defer_pending *dfp);
+void xfs_defer_item_unpause(struct xfs_trans *tp, struct xfs_defer_pending *dfp);
+
+struct xfs_defer_pending *xfs_defer_add(struct xfs_trans *tp, struct list_head *h,
+ const struct xfs_defer_op_type *ops);
int xfs_defer_finish_noroll(struct xfs_trans **tp);
int xfs_defer_finish(struct xfs_trans **tp);
+int xfs_defer_finish_one(struct xfs_trans *tp, struct xfs_defer_pending *dfp);
void xfs_defer_cancel(struct xfs_trans *);
void xfs_defer_move(struct xfs_trans *dtp, struct xfs_trans *stp);
/* Description of a deferred type. */
struct xfs_defer_op_type {
+ const char *name;
+ unsigned int max_items;
struct xfs_log_item *(*create_intent)(struct xfs_trans *tp,
struct list_head *items, unsigned int count, bool sort);
void (*abort_intent)(struct xfs_log_item *intent);
@@ -56,7 +59,11 @@ struct xfs_defer_op_type {
void (*finish_cleanup)(struct xfs_trans *tp,
struct xfs_btree_cur *state, int error);
void (*cancel_item)(struct list_head *item);
- unsigned int max_items;
+ int (*recover_work)(struct xfs_defer_pending *dfp,
+ struct list_head *capture_list);
+ struct xfs_log_item *(*relog_intent)(struct xfs_trans *tp,
+ struct xfs_log_item *intent,
+ struct xfs_log_item *done_item);
};
extern const struct xfs_defer_op_type xfs_bmap_update_defer_type;
@@ -125,7 +132,25 @@ void xfs_defer_ops_capture_abort(struct xfs_mount *mp,
struct xfs_defer_capture *d);
void xfs_defer_resources_rele(struct xfs_defer_resources *dres);
+void xfs_defer_start_recovery(struct xfs_log_item *lip,
+ struct list_head *r_dfops, const struct xfs_defer_op_type *ops);
+void xfs_defer_cancel_recovery(struct xfs_mount *mp,
+ struct xfs_defer_pending *dfp);
+int xfs_defer_finish_recovery(struct xfs_mount *mp,
+ struct xfs_defer_pending *dfp, struct list_head *capture_list);
+
+static inline void
+xfs_defer_add_item(
+ struct xfs_defer_pending *dfp,
+ struct list_head *work)
+{
+ list_add_tail(work, &dfp->dfp_work);
+ dfp->dfp_count++;
+}
+
int __init xfs_defer_init_item_caches(void);
void xfs_defer_destroy_item_caches(void);
+void xfs_defer_add_barrier(struct xfs_trans *tp);
+
#endif /* __XFS_DEFER_H__ */
diff --git a/fs/xfs/libxfs/xfs_dir2.c b/fs/xfs/libxfs/xfs_dir2.c
index f5462fd582d5..a76673281514 100644
--- a/fs/xfs/libxfs/xfs_dir2.c
+++ b/fs/xfs/libxfs/xfs_dir2.c
@@ -196,7 +196,7 @@ xfs_dir_isempty(
return 1;
if (dp->i_disk_size > xfs_inode_data_fork_size(dp))
return 0;
- sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
+ sfp = dp->i_df.if_data;
return !sfp->count;
}
diff --git a/fs/xfs/libxfs/xfs_dir2_block.c b/fs/xfs/libxfs/xfs_dir2_block.c
index 00f960a703b2..3c256d4cc40b 100644
--- a/fs/xfs/libxfs/xfs_dir2_block.c
+++ b/fs/xfs/libxfs/xfs_dir2_block.c
@@ -1089,7 +1089,7 @@ xfs_dir2_sf_to_block(
int newoffset; /* offset from current entry */
unsigned int offset = geo->data_entry_offset;
xfs_dir2_sf_entry_t *sfep; /* sf entry pointer */
- xfs_dir2_sf_hdr_t *oldsfp; /* old shortform header */
+ struct xfs_dir2_sf_hdr *oldsfp = ifp->if_data;
xfs_dir2_sf_hdr_t *sfp; /* shortform header */
__be16 *tagp; /* end of data entry */
struct xfs_name name;
@@ -1099,10 +1099,8 @@ xfs_dir2_sf_to_block(
ASSERT(ifp->if_format == XFS_DINODE_FMT_LOCAL);
ASSERT(dp->i_disk_size >= offsetof(struct xfs_dir2_sf_hdr, parent));
- oldsfp = (xfs_dir2_sf_hdr_t *)ifp->if_u1.if_data;
-
ASSERT(ifp->if_bytes == dp->i_disk_size);
- ASSERT(ifp->if_u1.if_data != NULL);
+ ASSERT(oldsfp != NULL);
ASSERT(dp->i_disk_size >= xfs_dir2_sf_hdr_size(oldsfp->i8count));
ASSERT(dp->i_df.if_nextents == 0);
diff --git a/fs/xfs/libxfs/xfs_dir2_priv.h b/fs/xfs/libxfs/xfs_dir2_priv.h
index 7404a9ff1a92..1db2e60ba827 100644
--- a/fs/xfs/libxfs/xfs_dir2_priv.h
+++ b/fs/xfs/libxfs/xfs_dir2_priv.h
@@ -175,7 +175,8 @@ extern int xfs_dir2_sf_create(struct xfs_da_args *args, xfs_ino_t pino);
extern int xfs_dir2_sf_lookup(struct xfs_da_args *args);
extern int xfs_dir2_sf_removename(struct xfs_da_args *args);
extern int xfs_dir2_sf_replace(struct xfs_da_args *args);
-extern xfs_failaddr_t xfs_dir2_sf_verify(struct xfs_inode *ip);
+xfs_failaddr_t xfs_dir2_sf_verify(struct xfs_mount *mp,
+ struct xfs_dir2_sf_hdr *sfp, int64_t size);
int xfs_dir2_sf_entsize(struct xfs_mount *mp,
struct xfs_dir2_sf_hdr *hdr, int len);
void xfs_dir2_sf_put_ino(struct xfs_mount *mp, struct xfs_dir2_sf_hdr *hdr,
diff --git a/fs/xfs/libxfs/xfs_dir2_sf.c b/fs/xfs/libxfs/xfs_dir2_sf.c
index 8cd37e6e9d38..e1f83fc7b6ad 100644
--- a/fs/xfs/libxfs/xfs_dir2_sf.c
+++ b/fs/xfs/libxfs/xfs_dir2_sf.c
@@ -364,25 +364,23 @@ int /* error */
xfs_dir2_sf_addname(
xfs_da_args_t *args) /* operation arguments */
{
- xfs_inode_t *dp; /* incore directory inode */
+ struct xfs_inode *dp = args->dp;
+ struct xfs_dir2_sf_hdr *sfp = dp->i_df.if_data;
int error; /* error return value */
int incr_isize; /* total change in size */
int new_isize; /* size after adding name */
int objchange; /* changing to 8-byte inodes */
xfs_dir2_data_aoff_t offset = 0; /* offset for new entry */
int pick; /* which algorithm to use */
- xfs_dir2_sf_hdr_t *sfp; /* shortform structure */
xfs_dir2_sf_entry_t *sfep = NULL; /* shortform entry */
trace_xfs_dir2_sf_addname(args);
ASSERT(xfs_dir2_sf_lookup(args) == -ENOENT);
- dp = args->dp;
ASSERT(dp->i_df.if_format == XFS_DINODE_FMT_LOCAL);
ASSERT(dp->i_disk_size >= offsetof(struct xfs_dir2_sf_hdr, parent));
ASSERT(dp->i_df.if_bytes == dp->i_disk_size);
- ASSERT(dp->i_df.if_u1.if_data != NULL);
- sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
+ ASSERT(sfp != NULL);
ASSERT(dp->i_disk_size >= xfs_dir2_sf_hdr_size(sfp->i8count));
/*
* Compute entry (and change in) size.
@@ -462,20 +460,17 @@ xfs_dir2_sf_addname_easy(
{
struct xfs_inode *dp = args->dp;
struct xfs_mount *mp = dp->i_mount;
- int byteoff; /* byte offset in sf dir */
- xfs_dir2_sf_hdr_t *sfp; /* shortform structure */
+ struct xfs_dir2_sf_hdr *sfp = dp->i_df.if_data;
+ int byteoff = (int)((char *)sfep - (char *)sfp);
- sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
- byteoff = (int)((char *)sfep - (char *)sfp);
/*
* Grow the in-inode space.
*/
- xfs_idata_realloc(dp, xfs_dir2_sf_entsize(mp, sfp, args->namelen),
+ sfp = xfs_idata_realloc(dp, xfs_dir2_sf_entsize(mp, sfp, args->namelen),
XFS_DATA_FORK);
/*
* Need to set up again due to realloc of the inode data.
*/
- sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
sfep = (xfs_dir2_sf_entry_t *)((char *)sfp + byteoff);
/*
* Fill in the new entry.
@@ -528,11 +523,10 @@ xfs_dir2_sf_addname_hard(
/*
* Copy the old directory to the stack buffer.
*/
- sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
old_isize = (int)dp->i_disk_size;
buf = kmem_alloc(old_isize, 0);
oldsfp = (xfs_dir2_sf_hdr_t *)buf;
- memcpy(oldsfp, sfp, old_isize);
+ memcpy(oldsfp, dp->i_df.if_data, old_isize);
/*
* Loop over the old directory finding the place we're going
* to insert the new entry.
@@ -556,11 +550,8 @@ xfs_dir2_sf_addname_hard(
* the data.
*/
xfs_idata_realloc(dp, -old_isize, XFS_DATA_FORK);
- xfs_idata_realloc(dp, new_isize, XFS_DATA_FORK);
- /*
- * Reset the pointer since the buffer was reallocated.
- */
- sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
+ sfp = xfs_idata_realloc(dp, new_isize, XFS_DATA_FORK);
+
/*
* Copy the first part of the directory, including the header.
*/
@@ -610,11 +601,10 @@ xfs_dir2_sf_addname_pick(
int i; /* entry number */
xfs_dir2_data_aoff_t offset; /* data block offset */
xfs_dir2_sf_entry_t *sfep; /* shortform entry */
- xfs_dir2_sf_hdr_t *sfp; /* shortform structure */
+ struct xfs_dir2_sf_hdr *sfp = dp->i_df.if_data;
int size; /* entry's data size */
int used; /* data bytes used */
- sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
size = xfs_dir2_data_entsize(mp, args->namelen);
offset = args->geo->data_first_offset;
sfep = xfs_dir2_sf_firstentry(sfp);
@@ -673,14 +663,13 @@ xfs_dir2_sf_check(
{
struct xfs_inode *dp = args->dp;
struct xfs_mount *mp = dp->i_mount;
+ struct xfs_dir2_sf_hdr *sfp = dp->i_df.if_data;
int i; /* entry number */
int i8count; /* number of big inode#s */
xfs_ino_t ino; /* entry inode number */
int offset; /* data offset */
xfs_dir2_sf_entry_t *sfep; /* shortform dir entry */
- xfs_dir2_sf_hdr_t *sfp; /* shortform structure */
- sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
offset = args->geo->data_first_offset;
ino = xfs_dir2_sf_get_parent_ino(sfp);
i8count = ino > XFS_DIR2_MAX_SHORT_INUM;
@@ -707,11 +696,10 @@ xfs_dir2_sf_check(
/* Verify the consistency of an inline directory. */
xfs_failaddr_t
xfs_dir2_sf_verify(
- struct xfs_inode *ip)
+ struct xfs_mount *mp,
+ struct xfs_dir2_sf_hdr *sfp,
+ int64_t size)
{
- struct xfs_mount *mp = ip->i_mount;
- struct xfs_ifork *ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK);
- struct xfs_dir2_sf_hdr *sfp;
struct xfs_dir2_sf_entry *sfep;
struct xfs_dir2_sf_entry *next_sfep;
char *endp;
@@ -719,15 +707,9 @@ xfs_dir2_sf_verify(
int i;
int i8count;
int offset;
- int64_t size;
int error;
uint8_t filetype;
- ASSERT(ifp->if_format == XFS_DINODE_FMT_LOCAL);
-
- sfp = (struct xfs_dir2_sf_hdr *)ifp->if_u1.if_data;
- size = ifp->if_bytes;
-
/*
* Give up if the directory is way too short.
*/
@@ -834,15 +816,13 @@ xfs_dir2_sf_create(
ASSERT(dp->i_df.if_bytes == 0);
i8count = pino > XFS_DIR2_MAX_SHORT_INUM;
size = xfs_dir2_sf_hdr_size(i8count);
+
/*
- * Make a buffer for the data.
- */
- xfs_idata_realloc(dp, size, XFS_DATA_FORK);
- /*
- * Fill in the header,
+ * Make a buffer for the data and fill in the header.
*/
- sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
+ sfp = xfs_idata_realloc(dp, size, XFS_DATA_FORK);
sfp->i8count = i8count;
+
/*
* Now can put in the inode number, since i8count is set.
*/
@@ -864,9 +844,9 @@ xfs_dir2_sf_lookup(
{
struct xfs_inode *dp = args->dp;
struct xfs_mount *mp = dp->i_mount;
+ struct xfs_dir2_sf_hdr *sfp = dp->i_df.if_data;
int i; /* entry index */
xfs_dir2_sf_entry_t *sfep; /* shortform directory entry */
- xfs_dir2_sf_hdr_t *sfp; /* shortform structure */
enum xfs_dacmp cmp; /* comparison result */
xfs_dir2_sf_entry_t *ci_sfep; /* case-insens. entry */
@@ -877,8 +857,7 @@ xfs_dir2_sf_lookup(
ASSERT(dp->i_df.if_format == XFS_DINODE_FMT_LOCAL);
ASSERT(dp->i_disk_size >= offsetof(struct xfs_dir2_sf_hdr, parent));
ASSERT(dp->i_df.if_bytes == dp->i_disk_size);
- ASSERT(dp->i_df.if_u1.if_data != NULL);
- sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
+ ASSERT(sfp != NULL);
ASSERT(dp->i_disk_size >= xfs_dir2_sf_hdr_size(sfp->i8count));
/*
* Special case for .
@@ -940,13 +919,13 @@ xfs_dir2_sf_removename(
{
struct xfs_inode *dp = args->dp;
struct xfs_mount *mp = dp->i_mount;
+ struct xfs_dir2_sf_hdr *sfp = dp->i_df.if_data;
int byteoff; /* offset of removed entry */
int entsize; /* this entry's size */
int i; /* shortform entry index */
int newsize; /* new inode size */
int oldsize; /* old inode size */
xfs_dir2_sf_entry_t *sfep; /* shortform directory entry */
- xfs_dir2_sf_hdr_t *sfp; /* shortform structure */
trace_xfs_dir2_sf_removename(args);
@@ -954,8 +933,7 @@ xfs_dir2_sf_removename(
oldsize = (int)dp->i_disk_size;
ASSERT(oldsize >= offsetof(struct xfs_dir2_sf_hdr, parent));
ASSERT(dp->i_df.if_bytes == oldsize);
- ASSERT(dp->i_df.if_u1.if_data != NULL);
- sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
+ ASSERT(sfp != NULL);
ASSERT(oldsize >= xfs_dir2_sf_hdr_size(sfp->i8count));
/*
* Loop over the old directory entries.
@@ -992,11 +970,12 @@ xfs_dir2_sf_removename(
*/
sfp->count--;
dp->i_disk_size = newsize;
+
/*
* Reallocate, making it smaller.
*/
- xfs_idata_realloc(dp, newsize - oldsize, XFS_DATA_FORK);
- sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
+ sfp = xfs_idata_realloc(dp, newsize - oldsize, XFS_DATA_FORK);
+
/*
* Are we changing inode number size?
*/
@@ -1019,13 +998,12 @@ xfs_dir2_sf_replace_needblock(
struct xfs_inode *dp,
xfs_ino_t inum)
{
+ struct xfs_dir2_sf_hdr *sfp = dp->i_df.if_data;
int newsize;
- struct xfs_dir2_sf_hdr *sfp;
if (dp->i_df.if_format != XFS_DINODE_FMT_LOCAL)
return false;
- sfp = (struct xfs_dir2_sf_hdr *)dp->i_df.if_u1.if_data;
newsize = dp->i_df.if_bytes + (sfp->count + 1) * XFS_INO64_DIFF;
return inum > XFS_DIR2_MAX_SHORT_INUM &&
@@ -1041,19 +1019,18 @@ xfs_dir2_sf_replace(
{
struct xfs_inode *dp = args->dp;
struct xfs_mount *mp = dp->i_mount;
+ struct xfs_dir2_sf_hdr *sfp = dp->i_df.if_data;
int i; /* entry index */
xfs_ino_t ino=0; /* entry old inode number */
int i8elevated; /* sf_toino8 set i8count=1 */
xfs_dir2_sf_entry_t *sfep; /* shortform directory entry */
- xfs_dir2_sf_hdr_t *sfp; /* shortform structure */
trace_xfs_dir2_sf_replace(args);
ASSERT(dp->i_df.if_format == XFS_DINODE_FMT_LOCAL);
ASSERT(dp->i_disk_size >= offsetof(struct xfs_dir2_sf_hdr, parent));
ASSERT(dp->i_df.if_bytes == dp->i_disk_size);
- ASSERT(dp->i_df.if_u1.if_data != NULL);
- sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
+ ASSERT(sfp != NULL);
ASSERT(dp->i_disk_size >= xfs_dir2_sf_hdr_size(sfp->i8count));
/*
@@ -1076,7 +1053,7 @@ xfs_dir2_sf_replace(
*/
xfs_dir2_sf_toino8(args);
i8elevated = 1;
- sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
+ sfp = dp->i_df.if_data;
} else
i8elevated = 0;
@@ -1157,11 +1134,11 @@ xfs_dir2_sf_toino4(
{
struct xfs_inode *dp = args->dp;
struct xfs_mount *mp = dp->i_mount;
+ struct xfs_dir2_sf_hdr *oldsfp = dp->i_df.if_data;
char *buf; /* old dir's buffer */
int i; /* entry index */
int newsize; /* new inode size */
xfs_dir2_sf_entry_t *oldsfep; /* old sf entry */
- xfs_dir2_sf_hdr_t *oldsfp; /* old sf directory */
int oldsize; /* old inode size */
xfs_dir2_sf_entry_t *sfep; /* new sf entry */
xfs_dir2_sf_hdr_t *sfp; /* new sf directory */
@@ -1175,7 +1152,6 @@ xfs_dir2_sf_toino4(
*/
oldsize = dp->i_df.if_bytes;
buf = kmem_alloc(oldsize, 0);
- oldsfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
ASSERT(oldsfp->i8count == 1);
memcpy(buf, oldsfp, oldsize);
/*
@@ -1188,7 +1164,7 @@ xfs_dir2_sf_toino4(
* Reset our pointers, the data has moved.
*/
oldsfp = (xfs_dir2_sf_hdr_t *)buf;
- sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
+ sfp = dp->i_df.if_data;
/*
* Fill in the new header.
*/
@@ -1230,11 +1206,11 @@ xfs_dir2_sf_toino8(
{
struct xfs_inode *dp = args->dp;
struct xfs_mount *mp = dp->i_mount;
+ struct xfs_dir2_sf_hdr *oldsfp = dp->i_df.if_data;
char *buf; /* old dir's buffer */
int i; /* entry index */
int newsize; /* new inode size */
xfs_dir2_sf_entry_t *oldsfep; /* old sf entry */
- xfs_dir2_sf_hdr_t *oldsfp; /* old sf directory */
int oldsize; /* old inode size */
xfs_dir2_sf_entry_t *sfep; /* new sf entry */
xfs_dir2_sf_hdr_t *sfp; /* new sf directory */
@@ -1248,7 +1224,6 @@ xfs_dir2_sf_toino8(
*/
oldsize = dp->i_df.if_bytes;
buf = kmem_alloc(oldsize, 0);
- oldsfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
ASSERT(oldsfp->i8count == 0);
memcpy(buf, oldsfp, oldsize);
/*
@@ -1261,7 +1236,7 @@ xfs_dir2_sf_toino8(
* Reset our pointers, the data has moved.
*/
oldsfp = (xfs_dir2_sf_hdr_t *)buf;
- sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
+ sfp = dp->i_df.if_data;
/*
* Fill in the new header.
*/
diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h
index 9a88aba1589f..382ab1e71c0b 100644
--- a/fs/xfs/libxfs/xfs_format.h
+++ b/fs/xfs/libxfs/xfs_format.h
@@ -1008,7 +1008,7 @@ enum xfs_dinode_fmt {
* Return pointers to the data or attribute forks.
*/
#define XFS_DFORK_DPTR(dip) \
- ((char *)dip + xfs_dinode_size(dip->di_version))
+ ((void *)dip + xfs_dinode_size(dip->di_version))
#define XFS_DFORK_APTR(dip) \
(XFS_DFORK_DPTR(dip) + XFS_DFORK_BOFF(dip))
#define XFS_DFORK_PTR(dip,w) \
@@ -1156,20 +1156,6 @@ static inline bool xfs_dinode_has_large_extent_counts(
#define XFS_DFL_RTEXTSIZE (64 * 1024) /* 64kB */
#define XFS_MIN_RTEXTSIZE (4 * 1024) /* 4kB */
-#define XFS_BLOCKSIZE(mp) ((mp)->m_sb.sb_blocksize)
-#define XFS_BLOCKMASK(mp) ((mp)->m_blockmask)
-
-/*
- * RT bit manipulation macros.
- */
-#define XFS_RTMIN(a,b) ((a) < (b) ? (a) : (b))
-#define XFS_RTMAX(a,b) ((a) > (b) ? (a) : (b))
-
-#define XFS_RTLOBIT(w) xfs_lowbit32(w)
-#define XFS_RTHIBIT(w) xfs_highbit32(w)
-
-#define XFS_RTBLOCKLOG(b) xfs_highbit64(b)
-
/*
* Dquot and dquot block format definitions
*/
@@ -1272,6 +1258,9 @@ static inline time64_t xfs_dq_bigtime_to_unix(uint32_t ondisk_seconds)
#define XFS_DQ_GRACE_MIN ((int64_t)0)
#define XFS_DQ_GRACE_MAX ((int64_t)U32_MAX)
+/* Maximum id value for a quota record */
+#define XFS_DQ_ID_MAX (U32_MAX)
+
/*
* This is the main portion of the on-disk representation of quota information
* for a user. We pad this with some more expansion room to construct the on
diff --git a/fs/xfs/libxfs/xfs_health.h b/fs/xfs/libxfs/xfs_health.h
index 99e796256c5d..6296993ff8f3 100644
--- a/fs/xfs/libxfs/xfs_health.h
+++ b/fs/xfs/libxfs/xfs_health.h
@@ -68,6 +68,11 @@ struct xfs_fsop_geom;
#define XFS_SICK_INO_SYMLINK (1 << 6) /* symbolic link remote target */
#define XFS_SICK_INO_PARENT (1 << 7) /* parent pointers */
+#define XFS_SICK_INO_BMBTD_ZAPPED (1 << 8) /* data fork erased */
+#define XFS_SICK_INO_BMBTA_ZAPPED (1 << 9) /* attr fork erased */
+#define XFS_SICK_INO_DIR_ZAPPED (1 << 10) /* directory erased */
+#define XFS_SICK_INO_SYMLINK_ZAPPED (1 << 11) /* symlink erased */
+
/* Primary evidence of health problems in a given group. */
#define XFS_SICK_FS_PRIMARY (XFS_SICK_FS_COUNTERS | \
XFS_SICK_FS_UQUOTA | \
@@ -97,6 +102,11 @@ struct xfs_fsop_geom;
XFS_SICK_INO_SYMLINK | \
XFS_SICK_INO_PARENT)
+#define XFS_SICK_INO_ZAPPED (XFS_SICK_INO_BMBTD_ZAPPED | \
+ XFS_SICK_INO_BMBTA_ZAPPED | \
+ XFS_SICK_INO_DIR_ZAPPED | \
+ XFS_SICK_INO_SYMLINK_ZAPPED)
+
/* These functions must be provided by the xfs implementation. */
void xfs_fs_mark_sick(struct xfs_mount *mp, unsigned int mask);
diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
index b83e54c70906..2361a22035b0 100644
--- a/fs/xfs/libxfs/xfs_ialloc.c
+++ b/fs/xfs/libxfs/xfs_ialloc.c
@@ -95,18 +95,28 @@ xfs_inobt_btrec_to_irec(
irec->ir_free = be64_to_cpu(rec->inobt.ir_free);
}
+/* Compute the freecount of an incore inode record. */
+uint8_t
+xfs_inobt_rec_freecount(
+ const struct xfs_inobt_rec_incore *irec)
+{
+ uint64_t realfree = irec->ir_free;
+
+ if (xfs_inobt_issparse(irec->ir_holemask))
+ realfree &= xfs_inobt_irec_to_allocmask(irec);
+ return hweight64(realfree);
+}
+
/* Simple checks for inode records. */
xfs_failaddr_t
xfs_inobt_check_irec(
- struct xfs_btree_cur *cur,
+ struct xfs_perag *pag,
const struct xfs_inobt_rec_incore *irec)
{
- uint64_t realfree;
-
/* Record has to be properly aligned within the AG. */
- if (!xfs_verify_agino(cur->bc_ag.pag, irec->ir_startino))
+ if (!xfs_verify_agino(pag, irec->ir_startino))
return __this_address;
- if (!xfs_verify_agino(cur->bc_ag.pag,
+ if (!xfs_verify_agino(pag,
irec->ir_startino + XFS_INODES_PER_CHUNK - 1))
return __this_address;
if (irec->ir_count < XFS_INODES_PER_HOLEMASK_BIT ||
@@ -115,12 +125,7 @@ xfs_inobt_check_irec(
if (irec->ir_freecount > XFS_INODES_PER_CHUNK)
return __this_address;
- /* if there are no holes, return the first available offset */
- if (!xfs_inobt_issparse(irec->ir_holemask))
- realfree = irec->ir_free;
- else
- realfree = irec->ir_free & xfs_inobt_irec_to_allocmask(irec);
- if (hweight64(realfree) != irec->ir_freecount)
+ if (xfs_inobt_rec_freecount(irec) != irec->ir_freecount)
return __this_address;
return NULL;
@@ -164,7 +169,7 @@ xfs_inobt_get_rec(
return error;
xfs_inobt_btrec_to_irec(mp, rec, irec);
- fa = xfs_inobt_check_irec(cur, irec);
+ fa = xfs_inobt_check_irec(cur->bc_ag.pag, irec);
if (fa)
return xfs_inobt_complain_bad_rec(cur, fa, irec);
@@ -1854,7 +1859,7 @@ xfs_difree_inode_chunk(
return xfs_free_extent_later(tp,
XFS_AGB_TO_FSB(mp, agno, sagbno),
M_IGEO(mp)->ialloc_blks, &XFS_RMAP_OINFO_INODES,
- XFS_AG_RESV_NONE);
+ XFS_AG_RESV_NONE, false);
}
/* holemask is only 16-bits (fits in an unsigned long) */
@@ -1900,7 +1905,8 @@ xfs_difree_inode_chunk(
ASSERT(contigblk % mp->m_sb.sb_spino_align == 0);
error = xfs_free_extent_later(tp,
XFS_AGB_TO_FSB(mp, agno, agbno), contigblk,
- &XFS_RMAP_OINFO_INODES, XFS_AG_RESV_NONE);
+ &XFS_RMAP_OINFO_INODES, XFS_AG_RESV_NONE,
+ false);
if (error)
return error;
@@ -2739,7 +2745,7 @@ xfs_ialloc_count_inodes_rec(
xfs_failaddr_t fa;
xfs_inobt_btrec_to_irec(cur->bc_mp, rec, &irec);
- fa = xfs_inobt_check_irec(cur, &irec);
+ fa = xfs_inobt_check_irec(cur->bc_ag.pag, &irec);
if (fa)
return xfs_inobt_complain_bad_rec(cur, fa, &irec);
diff --git a/fs/xfs/libxfs/xfs_ialloc.h b/fs/xfs/libxfs/xfs_ialloc.h
index fe824bb04a09..f1412183bb44 100644
--- a/fs/xfs/libxfs/xfs_ialloc.h
+++ b/fs/xfs/libxfs/xfs_ialloc.h
@@ -79,6 +79,7 @@ int xfs_inobt_lookup(struct xfs_btree_cur *cur, xfs_agino_t ino,
*/
int xfs_inobt_get_rec(struct xfs_btree_cur *cur,
xfs_inobt_rec_incore_t *rec, int *stat);
+uint8_t xfs_inobt_rec_freecount(const struct xfs_inobt_rec_incore *irec);
/*
* Inode chunk initialisation routine
@@ -93,7 +94,7 @@ union xfs_btree_rec;
void xfs_inobt_btrec_to_irec(struct xfs_mount *mp,
const union xfs_btree_rec *rec,
struct xfs_inobt_rec_incore *irec);
-xfs_failaddr_t xfs_inobt_check_irec(struct xfs_btree_cur *cur,
+xfs_failaddr_t xfs_inobt_check_irec(struct xfs_perag *pag,
const struct xfs_inobt_rec_incore *irec);
int xfs_ialloc_has_inodes_at_extent(struct xfs_btree_cur *cur,
xfs_agblock_t bno, xfs_extlen_t len,
diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c
index 9258f01c0015..42a5e1f227a0 100644
--- a/fs/xfs/libxfs/xfs_ialloc_btree.c
+++ b/fs/xfs/libxfs/xfs_ialloc_btree.c
@@ -161,7 +161,7 @@ __xfs_inobt_free_block(
xfs_inobt_mod_blockcount(cur, -1);
fsbno = XFS_DADDR_TO_FSB(cur->bc_mp, xfs_buf_daddr(bp));
return xfs_free_extent_later(cur->bc_tp, fsbno, 1,
- &XFS_RMAP_OINFO_INOBT, resv);
+ &XFS_RMAP_OINFO_INOBT, resv, false);
}
STATIC int
diff --git a/fs/xfs/libxfs/xfs_iext_tree.c b/fs/xfs/libxfs/xfs_iext_tree.c
index 773cf4349428..f4e6b200cdf8 100644
--- a/fs/xfs/libxfs/xfs_iext_tree.c
+++ b/fs/xfs/libxfs/xfs_iext_tree.c
@@ -158,7 +158,7 @@ static void *
xfs_iext_find_first_leaf(
struct xfs_ifork *ifp)
{
- struct xfs_iext_node *node = ifp->if_u1.if_root;
+ struct xfs_iext_node *node = ifp->if_data;
int height;
if (!ifp->if_height)
@@ -176,7 +176,7 @@ static void *
xfs_iext_find_last_leaf(
struct xfs_ifork *ifp)
{
- struct xfs_iext_node *node = ifp->if_u1.if_root;
+ struct xfs_iext_node *node = ifp->if_data;
int height, i;
if (!ifp->if_height)
@@ -306,7 +306,7 @@ xfs_iext_find_level(
xfs_fileoff_t offset,
int level)
{
- struct xfs_iext_node *node = ifp->if_u1.if_root;
+ struct xfs_iext_node *node = ifp->if_data;
int height, i;
if (!ifp->if_height)
@@ -402,12 +402,12 @@ xfs_iext_grow(
int i;
if (ifp->if_height == 1) {
- struct xfs_iext_leaf *prev = ifp->if_u1.if_root;
+ struct xfs_iext_leaf *prev = ifp->if_data;
node->keys[0] = xfs_iext_leaf_key(prev, 0);
node->ptrs[0] = prev;
} else {
- struct xfs_iext_node *prev = ifp->if_u1.if_root;
+ struct xfs_iext_node *prev = ifp->if_data;
ASSERT(ifp->if_height > 1);
@@ -418,7 +418,7 @@ xfs_iext_grow(
for (i = 1; i < KEYS_PER_NODE; i++)
node->keys[i] = XFS_IEXT_KEY_INVALID;
- ifp->if_u1.if_root = node;
+ ifp->if_data = node;
ifp->if_height++;
}
@@ -430,7 +430,7 @@ xfs_iext_update_node(
int level,
void *ptr)
{
- struct xfs_iext_node *node = ifp->if_u1.if_root;
+ struct xfs_iext_node *node = ifp->if_data;
int height, i;
for (height = ifp->if_height; height > level; height--) {
@@ -583,11 +583,11 @@ xfs_iext_alloc_root(
{
ASSERT(ifp->if_bytes == 0);
- ifp->if_u1.if_root = kmem_zalloc(sizeof(struct xfs_iext_rec), KM_NOFS);
+ ifp->if_data = kmem_zalloc(sizeof(struct xfs_iext_rec), KM_NOFS);
ifp->if_height = 1;
/* now that we have a node step into it */
- cur->leaf = ifp->if_u1.if_root;
+ cur->leaf = ifp->if_data;
cur->pos = 0;
}
@@ -603,9 +603,9 @@ xfs_iext_realloc_root(
if (new_size / sizeof(struct xfs_iext_rec) == RECS_PER_LEAF)
new_size = NODE_SIZE;
- new = krealloc(ifp->if_u1.if_root, new_size, GFP_NOFS | __GFP_NOFAIL);
+ new = krealloc(ifp->if_data, new_size, GFP_NOFS | __GFP_NOFAIL);
memset(new + ifp->if_bytes, 0, new_size - ifp->if_bytes);
- ifp->if_u1.if_root = new;
+ ifp->if_data = new;
cur->leaf = new;
}
@@ -622,13 +622,11 @@ static inline void xfs_iext_inc_seq(struct xfs_ifork *ifp)
}
void
-xfs_iext_insert(
- struct xfs_inode *ip,
+xfs_iext_insert_raw(
+ struct xfs_ifork *ifp,
struct xfs_iext_cursor *cur,
- struct xfs_bmbt_irec *irec,
- int state)
+ struct xfs_bmbt_irec *irec)
{
- struct xfs_ifork *ifp = xfs_iext_state_to_fork(ip, state);
xfs_fileoff_t offset = irec->br_startoff;
struct xfs_iext_leaf *new = NULL;
int nr_entries, i;
@@ -662,12 +660,23 @@ xfs_iext_insert(
xfs_iext_set(cur_rec(cur), irec);
ifp->if_bytes += sizeof(struct xfs_iext_rec);
- trace_xfs_iext_insert(ip, cur, state, _RET_IP_);
-
if (new)
xfs_iext_insert_node(ifp, xfs_iext_leaf_key(new, 0), new, 2);
}
+void
+xfs_iext_insert(
+ struct xfs_inode *ip,
+ struct xfs_iext_cursor *cur,
+ struct xfs_bmbt_irec *irec,
+ int state)
+{
+ struct xfs_ifork *ifp = xfs_iext_state_to_fork(ip, state);
+
+ xfs_iext_insert_raw(ifp, cur, irec);
+ trace_xfs_iext_insert(ip, cur, state, _RET_IP_);
+}
+
static struct xfs_iext_node *
xfs_iext_rebalance_node(
struct xfs_iext_node *parent,
@@ -777,8 +786,8 @@ again:
* If we are at the root and only one entry is left we can just
* free this node and update the root pointer.
*/
- ASSERT(node == ifp->if_u1.if_root);
- ifp->if_u1.if_root = node->ptrs[0];
+ ASSERT(node == ifp->if_data);
+ ifp->if_data = node->ptrs[0];
ifp->if_height--;
kmem_free(node);
}
@@ -854,8 +863,8 @@ xfs_iext_free_last_leaf(
struct xfs_ifork *ifp)
{
ifp->if_height--;
- kmem_free(ifp->if_u1.if_root);
- ifp->if_u1.if_root = NULL;
+ kmem_free(ifp->if_data);
+ ifp->if_data = NULL;
}
void
@@ -872,7 +881,7 @@ xfs_iext_remove(
trace_xfs_iext_remove(ip, cur, state, _RET_IP_);
ASSERT(ifp->if_height > 0);
- ASSERT(ifp->if_u1.if_root != NULL);
+ ASSERT(ifp->if_data != NULL);
ASSERT(xfs_iext_valid(ifp, cur));
xfs_iext_inc_seq(ifp);
@@ -1042,9 +1051,9 @@ void
xfs_iext_destroy(
struct xfs_ifork *ifp)
{
- xfs_iext_destroy_node(ifp->if_u1.if_root, ifp->if_height);
+ xfs_iext_destroy_node(ifp->if_data, ifp->if_height);
ifp->if_bytes = 0;
ifp->if_height = 0;
- ifp->if_u1.if_root = NULL;
+ ifp->if_data = NULL;
}
diff --git a/fs/xfs/libxfs/xfs_inode_fork.c b/fs/xfs/libxfs/xfs_inode_fork.c
index 5a2e7ddfa76d..f4569e18a8d0 100644
--- a/fs/xfs/libxfs/xfs_inode_fork.c
+++ b/fs/xfs/libxfs/xfs_inode_fork.c
@@ -50,12 +50,15 @@ xfs_init_local_fork(
mem_size++;
if (size) {
- ifp->if_u1.if_data = kmem_alloc(mem_size, KM_NOFS);
- memcpy(ifp->if_u1.if_data, data, size);
+ char *new_data = kmem_alloc(mem_size, KM_NOFS);
+
+ memcpy(new_data, data, size);
if (zero_terminate)
- ifp->if_u1.if_data[size] = '\0';
+ new_data[size] = '\0';
+
+ ifp->if_data = new_data;
} else {
- ifp->if_u1.if_data = NULL;
+ ifp->if_data = NULL;
}
ifp->if_bytes = size;
@@ -125,7 +128,7 @@ xfs_iformat_extents(
}
ifp->if_bytes = 0;
- ifp->if_u1.if_root = NULL;
+ ifp->if_data = NULL;
ifp->if_height = 0;
if (size) {
dp = (xfs_bmbt_rec_t *) XFS_DFORK_PTR(dip, whichfork);
@@ -212,7 +215,7 @@ xfs_iformat_btree(
ifp->if_broot, size);
ifp->if_bytes = 0;
- ifp->if_u1.if_root = NULL;
+ ifp->if_data = NULL;
ifp->if_height = 0;
return 0;
}
@@ -276,10 +279,9 @@ static uint16_t
xfs_dfork_attr_shortform_size(
struct xfs_dinode *dip)
{
- struct xfs_attr_shortform *atp =
- (struct xfs_attr_shortform *)XFS_DFORK_APTR(dip);
+ struct xfs_attr_sf_hdr *sf = XFS_DFORK_APTR(dip);
- return be16_to_cpu(atp->hdr.totsize);
+ return be16_to_cpu(sf->totsize);
}
void
@@ -493,7 +495,7 @@ xfs_iroot_realloc(
* byte_diff -- the change in the number of bytes, positive or negative,
* requested for the if_data array.
*/
-void
+void *
xfs_idata_realloc(
struct xfs_inode *ip,
int64_t byte_diff,
@@ -505,21 +507,18 @@ xfs_idata_realloc(
ASSERT(new_size >= 0);
ASSERT(new_size <= xfs_inode_fork_size(ip, whichfork));
- if (byte_diff == 0)
- return;
-
- if (new_size == 0) {
- kmem_free(ifp->if_u1.if_data);
- ifp->if_u1.if_data = NULL;
- ifp->if_bytes = 0;
- return;
+ if (byte_diff) {
+ ifp->if_data = krealloc(ifp->if_data, new_size,
+ GFP_NOFS | __GFP_NOFAIL);
+ if (new_size == 0)
+ ifp->if_data = NULL;
+ ifp->if_bytes = new_size;
}
- ifp->if_u1.if_data = krealloc(ifp->if_u1.if_data, new_size,
- GFP_NOFS | __GFP_NOFAIL);
- ifp->if_bytes = new_size;
+ return ifp->if_data;
}
+/* Free all memory and reset a fork back to its initial state. */
void
xfs_idestroy_fork(
struct xfs_ifork *ifp)
@@ -531,8 +530,8 @@ xfs_idestroy_fork(
switch (ifp->if_format) {
case XFS_DINODE_FMT_LOCAL:
- kmem_free(ifp->if_u1.if_data);
- ifp->if_u1.if_data = NULL;
+ kmem_free(ifp->if_data);
+ ifp->if_data = NULL;
break;
case XFS_DINODE_FMT_EXTENTS:
case XFS_DINODE_FMT_BTREE:
@@ -625,9 +624,9 @@ xfs_iflush_fork(
case XFS_DINODE_FMT_LOCAL:
if ((iip->ili_fields & dataflag[whichfork]) &&
(ifp->if_bytes > 0)) {
- ASSERT(ifp->if_u1.if_data != NULL);
+ ASSERT(ifp->if_data != NULL);
ASSERT(ifp->if_bytes <= xfs_inode_fork_size(ip, whichfork));
- memcpy(cp, ifp->if_u1.if_data, ifp->if_bytes);
+ memcpy(cp, ifp->if_data, ifp->if_bytes);
}
break;
@@ -702,19 +701,27 @@ xfs_ifork_verify_local_data(
xfs_failaddr_t fa = NULL;
switch (VFS_I(ip)->i_mode & S_IFMT) {
- case S_IFDIR:
- fa = xfs_dir2_sf_verify(ip);
+ case S_IFDIR: {
+ struct xfs_mount *mp = ip->i_mount;
+ struct xfs_ifork *ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK);
+ struct xfs_dir2_sf_hdr *sfp = ifp->if_data;
+
+ fa = xfs_dir2_sf_verify(mp, sfp, ifp->if_bytes);
break;
- case S_IFLNK:
- fa = xfs_symlink_shortform_verify(ip);
+ }
+ case S_IFLNK: {
+ struct xfs_ifork *ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK);
+
+ fa = xfs_symlink_shortform_verify(ifp->if_data, ifp->if_bytes);
break;
+ }
default:
break;
}
if (fa) {
xfs_inode_verifier_error(ip, -EFSCORRUPTED, "data fork",
- ip->i_df.if_u1.if_data, ip->i_df.if_bytes, fa);
+ ip->i_df.if_data, ip->i_df.if_bytes, fa);
return -EFSCORRUPTED;
}
@@ -729,14 +736,17 @@ xfs_ifork_verify_local_attr(
struct xfs_ifork *ifp = &ip->i_af;
xfs_failaddr_t fa;
- if (!xfs_inode_has_attr_fork(ip))
+ if (!xfs_inode_has_attr_fork(ip)) {
fa = __this_address;
- else
- fa = xfs_attr_shortform_verify(ip);
+ } else {
+ struct xfs_ifork *ifp = &ip->i_af;
+ ASSERT(ifp->if_format == XFS_DINODE_FMT_LOCAL);
+ fa = xfs_attr_shortform_verify(ifp->if_data, ifp->if_bytes);
+ }
if (fa) {
xfs_inode_verifier_error(ip, -EFSCORRUPTED, "attr fork",
- ifp->if_u1.if_data, ifp->if_bytes, fa);
+ ifp->if_data, ifp->if_bytes, fa);
return -EFSCORRUPTED;
}
diff --git a/fs/xfs/libxfs/xfs_inode_fork.h b/fs/xfs/libxfs/xfs_inode_fork.h
index 96d307784c85..96303249d28a 100644
--- a/fs/xfs/libxfs/xfs_inode_fork.h
+++ b/fs/xfs/libxfs/xfs_inode_fork.h
@@ -13,14 +13,12 @@ struct xfs_dinode;
* File incore extent information, present for each of data & attr forks.
*/
struct xfs_ifork {
- int64_t if_bytes; /* bytes in if_u1 */
+ int64_t if_bytes; /* bytes in if_data */
struct xfs_btree_block *if_broot; /* file's incore btree root */
unsigned int if_seq; /* fork mod counter */
int if_height; /* height of the extent tree */
- union {
- void *if_root; /* extent tree root */
- char *if_data; /* inline file data */
- } if_u1;
+ void *if_data; /* extent tree root or
+ inline data */
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 */
@@ -170,7 +168,7 @@ int xfs_iformat_attr_fork(struct xfs_inode *, struct xfs_dinode *);
void xfs_iflush_fork(struct xfs_inode *, struct xfs_dinode *,
struct xfs_inode_log_item *, int);
void xfs_idestroy_fork(struct xfs_ifork *ifp);
-void xfs_idata_realloc(struct xfs_inode *ip, int64_t byte_diff,
+void * xfs_idata_realloc(struct xfs_inode *ip, int64_t byte_diff,
int whichfork);
void xfs_iroot_realloc(struct xfs_inode *, int, int);
int xfs_iread_extents(struct xfs_trans *, struct xfs_inode *, int);
@@ -180,6 +178,9 @@ void xfs_init_local_fork(struct xfs_inode *ip, int whichfork,
const void *data, int64_t size);
xfs_extnum_t xfs_iext_count(struct xfs_ifork *ifp);
+void xfs_iext_insert_raw(struct xfs_ifork *ifp,
+ struct xfs_iext_cursor *cur,
+ struct xfs_bmbt_irec *irec);
void xfs_iext_insert(struct xfs_inode *, struct xfs_iext_cursor *cur,
struct xfs_bmbt_irec *, int);
void xfs_iext_remove(struct xfs_inode *, struct xfs_iext_cursor *,
diff --git a/fs/xfs/libxfs/xfs_log_recover.h b/fs/xfs/libxfs/xfs_log_recover.h
index a5100a11faf9..9fe7a9564bca 100644
--- a/fs/xfs/libxfs/xfs_log_recover.h
+++ b/fs/xfs/libxfs/xfs_log_recover.h
@@ -11,6 +11,7 @@
* define how recovery should work for that type of log item.
*/
struct xlog_recover_item;
+struct xfs_defer_op_type;
/* Sorting hat for log items as they're read in. */
enum xlog_recover_reorder {
@@ -153,4 +154,11 @@ xlog_recover_resv(const struct xfs_trans_res *r)
return ret;
}
+struct xfs_defer_pending;
+
+void xlog_recover_intent_item(struct xlog *log, struct xfs_log_item *lip,
+ xfs_lsn_t lsn, const struct xfs_defer_op_type *ops);
+int xlog_recover_finish_intent(struct xfs_trans *tp,
+ struct xfs_defer_pending *dfp);
+
#endif /* __XFS_LOG_RECOVER_H__ */
diff --git a/fs/xfs/xfs_ondisk.h b/fs/xfs/libxfs/xfs_ondisk.h
index 21a7e350b4c5..81885a6a028e 100644
--- a/fs/xfs/xfs_ondisk.h
+++ b/fs/xfs/libxfs/xfs_ondisk.h
@@ -7,16 +7,16 @@
#define __XFS_ONDISK_H
#define XFS_CHECK_STRUCT_SIZE(structname, size) \
- BUILD_BUG_ON_MSG(sizeof(structname) != (size), "XFS: sizeof(" \
- #structname ") is wrong, expected " #size)
+ static_assert(sizeof(structname) == (size), \
+ "XFS: sizeof(" #structname ") is wrong, expected " #size)
#define XFS_CHECK_OFFSET(structname, member, off) \
- BUILD_BUG_ON_MSG(offsetof(structname, member) != (off), \
+ static_assert(offsetof(structname, member) == (off), \
"XFS: offsetof(" #structname ", " #member ") is wrong, " \
"expected " #off)
#define XFS_CHECK_VALUE(value, expected) \
- BUILD_BUG_ON_MSG((value) != (expected), \
+ static_assert((value) == (expected), \
"XFS: value of " #value " is wrong, expected " #expected)
static inline void __init
@@ -93,13 +93,13 @@ xfs_check_ondisk_structs(void)
XFS_CHECK_OFFSET(xfs_attr_leaf_name_remote_t, namelen, 8);
XFS_CHECK_OFFSET(xfs_attr_leaf_name_remote_t, name, 9);
XFS_CHECK_STRUCT_SIZE(xfs_attr_leafblock_t, 32);
- XFS_CHECK_STRUCT_SIZE(struct xfs_attr_shortform, 4);
- XFS_CHECK_OFFSET(struct xfs_attr_shortform, hdr.totsize, 0);
- XFS_CHECK_OFFSET(struct xfs_attr_shortform, hdr.count, 2);
- XFS_CHECK_OFFSET(struct xfs_attr_shortform, list[0].namelen, 4);
- XFS_CHECK_OFFSET(struct xfs_attr_shortform, list[0].valuelen, 5);
- XFS_CHECK_OFFSET(struct xfs_attr_shortform, list[0].flags, 6);
- XFS_CHECK_OFFSET(struct xfs_attr_shortform, list[0].nameval, 7);
+ XFS_CHECK_STRUCT_SIZE(struct xfs_attr_sf_hdr, 4);
+ XFS_CHECK_OFFSET(struct xfs_attr_sf_hdr, totsize, 0);
+ XFS_CHECK_OFFSET(struct xfs_attr_sf_hdr, count, 2);
+ XFS_CHECK_OFFSET(struct xfs_attr_sf_entry, namelen, 0);
+ XFS_CHECK_OFFSET(struct xfs_attr_sf_entry, valuelen, 1);
+ XFS_CHECK_OFFSET(struct xfs_attr_sf_entry, flags, 2);
+ XFS_CHECK_OFFSET(struct xfs_attr_sf_entry, nameval, 3);
XFS_CHECK_STRUCT_SIZE(xfs_da_blkinfo_t, 12);
XFS_CHECK_STRUCT_SIZE(xfs_da_intnode_t, 16);
XFS_CHECK_STRUCT_SIZE(xfs_da_node_entry_t, 8);
diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c
index 646b3fa362ad..6709a7f8bad5 100644
--- a/fs/xfs/libxfs/xfs_refcount.c
+++ b/fs/xfs/libxfs/xfs_refcount.c
@@ -123,11 +123,9 @@ xfs_refcount_btrec_to_irec(
/* Simple checks for refcount records. */
xfs_failaddr_t
xfs_refcount_check_irec(
- struct xfs_btree_cur *cur,
+ struct xfs_perag *pag,
const struct xfs_refcount_irec *irec)
{
- struct xfs_perag *pag = cur->bc_ag.pag;
-
if (irec->rc_blockcount == 0 || irec->rc_blockcount > MAXREFCEXTLEN)
return __this_address;
@@ -179,7 +177,7 @@ xfs_refcount_get_rec(
return error;
xfs_refcount_btrec_to_irec(rec, irec);
- fa = xfs_refcount_check_irec(cur, irec);
+ fa = xfs_refcount_check_irec(cur->bc_ag.pag, irec);
if (fa)
return xfs_refcount_complain_bad_rec(cur, fa, irec);
@@ -1153,7 +1151,7 @@ xfs_refcount_adjust_extents(
tmp.rc_startblock);
error = xfs_free_extent_later(cur->bc_tp, fsbno,
tmp.rc_blockcount, NULL,
- XFS_AG_RESV_NONE);
+ XFS_AG_RESV_NONE, false);
if (error)
goto out_error;
}
@@ -1215,7 +1213,7 @@ xfs_refcount_adjust_extents(
ext.rc_startblock);
error = xfs_free_extent_later(cur->bc_tp, fsbno,
ext.rc_blockcount, NULL,
- XFS_AG_RESV_NONE);
+ XFS_AG_RESV_NONE, false);
if (error)
goto out_error;
}
@@ -1458,7 +1456,7 @@ __xfs_refcount_add(
ri->ri_blockcount = blockcount;
xfs_refcount_update_get_group(tp->t_mountp, ri);
- xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_REFCOUNT, &ri->ri_list);
+ xfs_defer_add(tp, &ri->ri_list, &xfs_refcount_update_defer_type);
}
/*
@@ -1899,7 +1897,7 @@ xfs_refcount_recover_extent(
INIT_LIST_HEAD(&rr->rr_list);
xfs_refcount_btrec_to_irec(rec, &rr->rr_rrec);
- if (xfs_refcount_check_irec(cur, &rr->rr_rrec) != NULL ||
+ if (xfs_refcount_check_irec(cur->bc_ag.pag, &rr->rr_rrec) != NULL ||
XFS_IS_CORRUPT(cur->bc_mp,
rr->rr_rrec.rc_domain != XFS_REFC_DOMAIN_COW)) {
kfree(rr);
@@ -1985,7 +1983,7 @@ xfs_refcount_recover_cow_leftovers(
/* Free the block. */
error = xfs_free_extent_later(tp, fsb,
rr->rr_rrec.rc_blockcount, NULL,
- XFS_AG_RESV_NONE);
+ XFS_AG_RESV_NONE, false);
if (error)
goto out_trans;
@@ -2033,6 +2031,47 @@ xfs_refcount_has_records(
return xfs_btree_has_records(cur, &low, &high, NULL, outcome);
}
+struct xfs_refcount_query_range_info {
+ xfs_refcount_query_range_fn fn;
+ void *priv;
+};
+
+/* Format btree record and pass to our callback. */
+STATIC int
+xfs_refcount_query_range_helper(
+ struct xfs_btree_cur *cur,
+ const union xfs_btree_rec *rec,
+ void *priv)
+{
+ struct xfs_refcount_query_range_info *query = priv;
+ struct xfs_refcount_irec irec;
+ xfs_failaddr_t fa;
+
+ xfs_refcount_btrec_to_irec(rec, &irec);
+ fa = xfs_refcount_check_irec(cur->bc_ag.pag, &irec);
+ if (fa)
+ return xfs_refcount_complain_bad_rec(cur, fa, &irec);
+
+ return query->fn(cur, &irec, query->priv);
+}
+
+/* Find all refcount records between two keys. */
+int
+xfs_refcount_query_range(
+ struct xfs_btree_cur *cur,
+ const struct xfs_refcount_irec *low_rec,
+ const struct xfs_refcount_irec *high_rec,
+ xfs_refcount_query_range_fn fn,
+ void *priv)
+{
+ union xfs_btree_irec low_brec = { .rc = *low_rec };
+ union xfs_btree_irec high_brec = { .rc = *high_rec };
+ struct xfs_refcount_query_range_info query = { .priv = priv, .fn = fn };
+
+ return xfs_btree_query_range(cur, &low_brec, &high_brec,
+ xfs_refcount_query_range_helper, &query);
+}
+
int __init
xfs_refcount_intent_init_cache(void)
{
diff --git a/fs/xfs/libxfs/xfs_refcount.h b/fs/xfs/libxfs/xfs_refcount.h
index 783cd89ca195..9b56768a590c 100644
--- a/fs/xfs/libxfs/xfs_refcount.h
+++ b/fs/xfs/libxfs/xfs_refcount.h
@@ -117,7 +117,7 @@ extern int xfs_refcount_has_records(struct xfs_btree_cur *cur,
union xfs_btree_rec;
extern void xfs_refcount_btrec_to_irec(const union xfs_btree_rec *rec,
struct xfs_refcount_irec *irec);
-xfs_failaddr_t xfs_refcount_check_irec(struct xfs_btree_cur *cur,
+xfs_failaddr_t xfs_refcount_check_irec(struct xfs_perag *pag,
const struct xfs_refcount_irec *irec);
extern int xfs_refcount_insert(struct xfs_btree_cur *cur,
struct xfs_refcount_irec *irec, int *stat);
@@ -127,4 +127,14 @@ extern struct kmem_cache *xfs_refcount_intent_cache;
int __init xfs_refcount_intent_init_cache(void);
void xfs_refcount_intent_destroy_cache(void);
+typedef int (*xfs_refcount_query_range_fn)(
+ struct xfs_btree_cur *cur,
+ const struct xfs_refcount_irec *rec,
+ void *priv);
+
+int xfs_refcount_query_range(struct xfs_btree_cur *cur,
+ const struct xfs_refcount_irec *low_rec,
+ const struct xfs_refcount_irec *high_rec,
+ xfs_refcount_query_range_fn fn, void *priv);
+
#endif /* __XFS_REFCOUNT_H__ */
diff --git a/fs/xfs/libxfs/xfs_refcount_btree.c b/fs/xfs/libxfs/xfs_refcount_btree.c
index 5c3987d8dc24..0d80bd99147c 100644
--- a/fs/xfs/libxfs/xfs_refcount_btree.c
+++ b/fs/xfs/libxfs/xfs_refcount_btree.c
@@ -112,7 +112,7 @@ xfs_refcountbt_free_block(
be32_add_cpu(&agf->agf_refcount_blocks, -1);
xfs_alloc_log_agf(cur->bc_tp, agbp, XFS_AGF_REFCOUNT_BLOCKS);
return xfs_free_extent_later(cur->bc_tp, fsbno, 1,
- &XFS_RMAP_OINFO_REFC, XFS_AG_RESV_METADATA);
+ &XFS_RMAP_OINFO_REFC, XFS_AG_RESV_METADATA, false);
}
STATIC int
@@ -226,7 +226,18 @@ xfs_refcountbt_verify(
level = be16_to_cpu(block->bb_level);
if (pag && xfs_perag_initialised_agf(pag)) {
- if (level >= pag->pagf_refcount_level)
+ unsigned int maxlevel = pag->pagf_refcount_level;
+
+#ifdef CONFIG_XFS_ONLINE_REPAIR
+ /*
+ * Online repair could be rewriting the refcount btree, so
+ * we'll validate against the larger of either tree while this
+ * is going on.
+ */
+ maxlevel = max_t(unsigned int, maxlevel,
+ pag->pagf_repair_refcount_level);
+#endif
+ if (level >= maxlevel)
return __this_address;
} else if (level >= mp->m_refc_maxlevels)
return __this_address;
diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c
index fbb0b2637463..76bf7f48cb5a 100644
--- a/fs/xfs/libxfs/xfs_rmap.c
+++ b/fs/xfs/libxfs/xfs_rmap.c
@@ -2567,7 +2567,7 @@ __xfs_rmap_add(
ri->ri_bmap = *bmap;
xfs_rmap_update_get_group(tp->t_mountp, ri);
- xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_RMAP, &ri->ri_list);
+ xfs_defer_add(tp, &ri->ri_list, &xfs_rmap_update_defer_type);
}
/* Map an extent into a file. */
diff --git a/fs/xfs/libxfs/xfs_rtbitmap.c b/fs/xfs/libxfs/xfs_rtbitmap.c
index c269d704314d..31100120b2c5 100644
--- a/fs/xfs/libxfs/xfs_rtbitmap.c
+++ b/fs/xfs/libxfs/xfs_rtbitmap.c
@@ -184,7 +184,7 @@ xfs_rtfind_back(
* Calculate first (leftmost) bit number to look at,
* and mask for all the relevant bits in this word.
*/
- firstbit = XFS_RTMAX((xfs_srtblock_t)(bit - len + 1), 0);
+ firstbit = max_t(xfs_srtblock_t, bit - len + 1, 0);
mask = (((xfs_rtword_t)1 << (bit - firstbit + 1)) - 1) <<
firstbit;
/*
@@ -195,7 +195,7 @@ xfs_rtfind_back(
/*
* Different. Mark where we are and return.
*/
- i = bit - XFS_RTHIBIT(wdiff);
+ i = bit - xfs_highbit32(wdiff);
*rtx = start - i + 1;
return 0;
}
@@ -233,7 +233,7 @@ xfs_rtfind_back(
/*
* Different, mark where we are and return.
*/
- i += XFS_NBWORD - 1 - XFS_RTHIBIT(wdiff);
+ i += XFS_NBWORD - 1 - xfs_highbit32(wdiff);
*rtx = start - i + 1;
return 0;
}
@@ -272,7 +272,7 @@ xfs_rtfind_back(
/*
* Different, mark where we are and return.
*/
- i += XFS_NBWORD - 1 - XFS_RTHIBIT(wdiff);
+ i += XFS_NBWORD - 1 - xfs_highbit32(wdiff);
*rtx = start - i + 1;
return 0;
} else
@@ -338,7 +338,7 @@ xfs_rtfind_forw(
* Calculate last (rightmost) bit number to look at,
* and mask for all the relevant bits in this word.
*/
- lastbit = XFS_RTMIN(bit + len, XFS_NBWORD);
+ lastbit = min(bit + len, XFS_NBWORD);
mask = (((xfs_rtword_t)1 << (lastbit - bit)) - 1) << bit;
/*
* Calculate the difference between the value there
@@ -348,7 +348,7 @@ xfs_rtfind_forw(
/*
* Different. Mark where we are and return.
*/
- i = XFS_RTLOBIT(wdiff) - bit;
+ i = xfs_lowbit32(wdiff) - bit;
*rtx = start + i - 1;
return 0;
}
@@ -386,7 +386,7 @@ xfs_rtfind_forw(
/*
* Different, mark where we are and return.
*/
- i += XFS_RTLOBIT(wdiff);
+ i += xfs_lowbit32(wdiff);
*rtx = start + i - 1;
return 0;
}
@@ -423,7 +423,7 @@ xfs_rtfind_forw(
/*
* Different, mark where we are and return.
*/
- i += XFS_RTLOBIT(wdiff);
+ i += xfs_lowbit32(wdiff);
*rtx = start + i - 1;
return 0;
} else
@@ -452,71 +452,59 @@ xfs_trans_log_rtsummary(
}
/*
- * Read and/or modify the summary information for a given extent size,
- * bitmap block combination.
- * Keeps track of a current summary block, so we don't keep reading
- * it from the buffer cache.
- *
- * Summary information is returned in *sum if specified.
- * If no delta is specified, returns summary only.
+ * Modify the summary information for a given extent size, bitmap block
+ * combination.
*/
int
-xfs_rtmodify_summary_int(
+xfs_rtmodify_summary(
struct xfs_rtalloc_args *args,
int log, /* log2 of extent size */
xfs_fileoff_t bbno, /* bitmap block number */
- int delta, /* change to make to summary info */
- xfs_suminfo_t *sum) /* out: summary info for this block */
+ int delta) /* in/out: summary block number */
{
struct xfs_mount *mp = args->mp;
- int error;
- xfs_fileoff_t sb; /* summary fsblock */
- xfs_rtsumoff_t so; /* index into the summary file */
+ xfs_rtsumoff_t so = xfs_rtsumoffs(mp, log, bbno);
unsigned int infoword;
+ xfs_suminfo_t val;
+ int error;
- /*
- * Compute entry number in the summary file.
- */
- so = xfs_rtsumoffs(mp, log, bbno);
- /*
- * Compute the block number in the summary file.
- */
- sb = xfs_rtsumoffs_to_block(mp, so);
-
- error = xfs_rtsummary_read_buf(args, sb);
+ error = xfs_rtsummary_read_buf(args, xfs_rtsumoffs_to_block(mp, so));
if (error)
return error;
- /*
- * Point to the summary information, modify/log it, and/or copy it out.
- */
infoword = xfs_rtsumoffs_to_infoword(mp, so);
- if (delta) {
- xfs_suminfo_t val = xfs_suminfo_add(args, infoword, delta);
-
- if (mp->m_rsum_cache) {
- if (val == 0 && log + 1 == mp->m_rsum_cache[bbno])
- mp->m_rsum_cache[bbno] = log;
- if (val != 0 && log >= mp->m_rsum_cache[bbno])
- mp->m_rsum_cache[bbno] = log + 1;
- }
- xfs_trans_log_rtsummary(args, infoword);
- if (sum)
- *sum = val;
- } else if (sum) {
- *sum = xfs_suminfo_get(args, infoword);
+ val = xfs_suminfo_add(args, infoword, delta);
+
+ if (mp->m_rsum_cache) {
+ if (val == 0 && log + 1 == mp->m_rsum_cache[bbno])
+ mp->m_rsum_cache[bbno] = log;
+ if (val != 0 && log >= mp->m_rsum_cache[bbno])
+ mp->m_rsum_cache[bbno] = log + 1;
}
+
+ xfs_trans_log_rtsummary(args, infoword);
return 0;
}
+/*
+ * Read and return the summary information for a given extent size, bitmap block
+ * combination.
+ */
int
-xfs_rtmodify_summary(
+xfs_rtget_summary(
struct xfs_rtalloc_args *args,
int log, /* log2 of extent size */
xfs_fileoff_t bbno, /* bitmap block number */
- int delta) /* in/out: summary block number */
+ xfs_suminfo_t *sum) /* out: summary info for this block */
{
- return xfs_rtmodify_summary_int(args, log, bbno, delta, NULL);
+ struct xfs_mount *mp = args->mp;
+ xfs_rtsumoff_t so = xfs_rtsumoffs(mp, log, bbno);
+ int error;
+
+ error = xfs_rtsummary_read_buf(args, xfs_rtsumoffs_to_block(mp, so));
+ if (!error)
+ *sum = xfs_suminfo_get(args, xfs_rtsumoffs_to_infoword(mp, so));
+ return error;
}
/* Log rtbitmap block from the word @from to the byte before @next. */
@@ -585,7 +573,7 @@ xfs_rtmodify_range(
/*
* Compute first bit not changed and mask of relevant bits.
*/
- lastbit = XFS_RTMIN(bit + len, XFS_NBWORD);
+ lastbit = min(bit + len, XFS_NBWORD);
mask = (((xfs_rtword_t)1 << (lastbit - bit)) - 1) << bit;
/*
* Set/clear the active bits.
@@ -720,7 +708,7 @@ xfs_rtfree_range(
*/
if (preblock < start) {
error = xfs_rtmodify_summary(args,
- XFS_RTBLOCKLOG(start - preblock),
+ xfs_highbit64(start - preblock),
xfs_rtx_to_rbmblock(mp, preblock), -1);
if (error) {
return error;
@@ -732,7 +720,7 @@ xfs_rtfree_range(
*/
if (postblock > end) {
error = xfs_rtmodify_summary(args,
- XFS_RTBLOCKLOG(postblock - end),
+ xfs_highbit64(postblock - end),
xfs_rtx_to_rbmblock(mp, end + 1), -1);
if (error) {
return error;
@@ -743,7 +731,7 @@ xfs_rtfree_range(
* (new) free extent.
*/
return xfs_rtmodify_summary(args,
- XFS_RTBLOCKLOG(postblock + 1 - preblock),
+ xfs_highbit64(postblock + 1 - preblock),
xfs_rtx_to_rbmblock(mp, preblock), 1);
}
@@ -799,7 +787,7 @@ xfs_rtcheck_range(
/*
* Compute first bit not examined.
*/
- lastbit = XFS_RTMIN(bit + len, XFS_NBWORD);
+ lastbit = min(bit + len, XFS_NBWORD);
/*
* Mask of relevant bits.
*/
@@ -812,7 +800,7 @@ xfs_rtcheck_range(
/*
* Different, compute first wrong bit and return.
*/
- i = XFS_RTLOBIT(wdiff) - bit;
+ i = xfs_lowbit32(wdiff) - bit;
*new = start + i;
*stat = 0;
return 0;
@@ -851,7 +839,7 @@ xfs_rtcheck_range(
/*
* Different, compute first wrong bit and return.
*/
- i += XFS_RTLOBIT(wdiff);
+ i += xfs_lowbit32(wdiff);
*new = start + i;
*stat = 0;
return 0;
@@ -889,7 +877,7 @@ xfs_rtcheck_range(
/*
* Different, compute first wrong bit and return.
*/
- i += XFS_RTLOBIT(wdiff);
+ i += xfs_lowbit32(wdiff);
*new = start + i;
*stat = 0;
return 0;
@@ -1131,6 +1119,20 @@ xfs_rtbitmap_blockcount(
}
/*
+ * Compute the maximum level number of the realtime summary file, as defined by
+ * mkfs. The historic use of highbit32 on a 64-bit quantity prohibited correct
+ * use of rt volumes with more than 2^32 extents.
+ */
+uint8_t
+xfs_compute_rextslog(
+ xfs_rtbxlen_t rtextents)
+{
+ if (!rtextents)
+ return 0;
+ return xfs_highbit64(rtextents);
+}
+
+/*
* Compute the number of rtbitmap words needed to populate every block of a
* bitmap that is large enough to track the given number of rt extents.
*/
diff --git a/fs/xfs/libxfs/xfs_rtbitmap.h b/fs/xfs/libxfs/xfs_rtbitmap.h
index c0637057d69c..274dc7dae1fa 100644
--- a/fs/xfs/libxfs/xfs_rtbitmap.h
+++ b/fs/xfs/libxfs/xfs_rtbitmap.h
@@ -321,8 +321,8 @@ int xfs_rtfind_forw(struct xfs_rtalloc_args *args, xfs_rtxnum_t start,
xfs_rtxnum_t limit, xfs_rtxnum_t *rtblock);
int xfs_rtmodify_range(struct xfs_rtalloc_args *args, xfs_rtxnum_t start,
xfs_rtxlen_t len, int val);
-int xfs_rtmodify_summary_int(struct xfs_rtalloc_args *args, int log,
- xfs_fileoff_t bbno, int delta, xfs_suminfo_t *sum);
+int xfs_rtget_summary(struct xfs_rtalloc_args *args, int log,
+ xfs_fileoff_t bbno, xfs_suminfo_t *sum);
int xfs_rtmodify_summary(struct xfs_rtalloc_args *args, int log,
xfs_fileoff_t bbno, int delta);
int xfs_rtfree_range(struct xfs_rtalloc_args *args, xfs_rtxnum_t start,
@@ -351,6 +351,20 @@ xfs_rtfree_extent(
int xfs_rtfree_blocks(struct xfs_trans *tp, xfs_fsblock_t rtbno,
xfs_filblks_t rtlen);
+uint8_t xfs_compute_rextslog(xfs_rtbxlen_t rtextents);
+
+/* Do we support an rt volume having this number of rtextents? */
+static inline bool
+xfs_validate_rtextents(
+ xfs_rtbxlen_t rtextents)
+{
+ /* No runt rt volumes */
+ if (rtextents == 0)
+ return false;
+
+ return true;
+}
+
xfs_filblks_t xfs_rtbitmap_blockcount(struct xfs_mount *mp, xfs_rtbxlen_t
rtextents);
unsigned long long xfs_rtbitmap_wordcount(struct xfs_mount *mp,
@@ -369,6 +383,8 @@ unsigned long long xfs_rtsummary_wordcount(struct xfs_mount *mp,
# define xfs_rtsummary_read_buf(a,b) (-ENOSYS)
# define xfs_rtbuf_cache_relse(a) (0)
# define xfs_rtalloc_extent_is_free(m,t,s,l,i) (-ENOSYS)
+# define xfs_compute_rextslog(rtx) (0)
+# define xfs_validate_rtextents(rtx) (false)
static inline xfs_filblks_t
xfs_rtbitmap_blockcount(struct xfs_mount *mp, xfs_rtbxlen_t rtextents)
{
diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index 1f74d0cd1618..4a9e8588f4c9 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -25,6 +25,7 @@
#include "xfs_da_format.h"
#include "xfs_health.h"
#include "xfs_ag.h"
+#include "xfs_rtbitmap.h"
/*
* Physical superblock buffer manipulations. Shared with libxfs in userspace.
@@ -508,8 +509,9 @@ xfs_validate_sb_common(
rbmblocks = howmany_64(sbp->sb_rextents,
NBBY * sbp->sb_blocksize);
- if (sbp->sb_rextents != rexts ||
- sbp->sb_rextslog != xfs_highbit32(sbp->sb_rextents) ||
+ if (!xfs_validate_rtextents(rexts) ||
+ sbp->sb_rextents != rexts ||
+ sbp->sb_rextslog != xfs_compute_rextslog(rexts) ||
sbp->sb_rbmblocks != rbmblocks) {
xfs_notice(mp,
"realtime geometry sanity check failed");
diff --git a/fs/xfs/libxfs/xfs_shared.h b/fs/xfs/libxfs/xfs_shared.h
index c4381388c0c1..4220d3584c1b 100644
--- a/fs/xfs/libxfs/xfs_shared.h
+++ b/fs/xfs/libxfs/xfs_shared.h
@@ -139,7 +139,7 @@ bool xfs_symlink_hdr_ok(xfs_ino_t ino, uint32_t offset,
uint32_t size, struct xfs_buf *bp);
void xfs_symlink_local_to_remote(struct xfs_trans *tp, struct xfs_buf *bp,
struct xfs_inode *ip, struct xfs_ifork *ifp);
-xfs_failaddr_t xfs_symlink_shortform_verify(struct xfs_inode *ip);
+xfs_failaddr_t xfs_symlink_shortform_verify(void *sfp, int64_t size);
/* Computed inode geometry for the filesystem. */
struct xfs_ino_geometry {
diff --git a/fs/xfs/libxfs/xfs_symlink_remote.c b/fs/xfs/libxfs/xfs_symlink_remote.c
index bdc777b9ec4a..160aa20aa441 100644
--- a/fs/xfs/libxfs/xfs_symlink_remote.c
+++ b/fs/xfs/libxfs/xfs_symlink_remote.c
@@ -175,7 +175,7 @@ xfs_symlink_local_to_remote(
if (!xfs_has_crc(mp)) {
bp->b_ops = NULL;
- memcpy(bp->b_addr, ifp->if_u1.if_data, ifp->if_bytes);
+ memcpy(bp->b_addr, ifp->if_data, ifp->if_bytes);
xfs_trans_log_buf(tp, bp, 0, ifp->if_bytes - 1);
return;
}
@@ -191,7 +191,7 @@ xfs_symlink_local_to_remote(
buf = bp->b_addr;
buf += xfs_symlink_hdr_set(mp, ip->i_ino, 0, ifp->if_bytes, bp);
- memcpy(buf, ifp->if_u1.if_data, ifp->if_bytes);
+ memcpy(buf, ifp->if_data, ifp->if_bytes);
xfs_trans_log_buf(tp, bp, 0, sizeof(struct xfs_dsymlink_hdr) +
ifp->if_bytes - 1);
}
@@ -202,15 +202,11 @@ xfs_symlink_local_to_remote(
*/
xfs_failaddr_t
xfs_symlink_shortform_verify(
- struct xfs_inode *ip)
+ void *sfp,
+ int64_t size)
{
- struct xfs_ifork *ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK);
- char *sfp = (char *)ifp->if_u1.if_data;
- int size = ifp->if_bytes;
char *endp = sfp + size;
- ASSERT(ifp->if_format == XFS_DINODE_FMT_LOCAL);
-
/*
* Zero length symlinks should never occur in memory as they are
* never allowed to exist on disk.
diff --git a/fs/xfs/libxfs/xfs_types.h b/fs/xfs/libxfs/xfs_types.h
index 533200c4ccc2..20b5375f2d9c 100644
--- a/fs/xfs/libxfs/xfs_types.h
+++ b/fs/xfs/libxfs/xfs_types.h
@@ -51,7 +51,6 @@ typedef void * xfs_failaddr_t;
#define NULLRFSBLOCK ((xfs_rfsblock_t)-1)
#define NULLRTBLOCK ((xfs_rtblock_t)-1)
#define NULLFILEOFF ((xfs_fileoff_t)-1)
-#define NULLRTEXTNO ((xfs_rtxnum_t)-1)
#define NULLAGBLOCK ((xfs_agblock_t)-1)
#define NULLAGNUMBER ((xfs_agnumber_t)-1)
@@ -208,6 +207,13 @@ enum xfs_ag_resv_type {
XFS_AG_RESV_AGFL,
XFS_AG_RESV_METADATA,
XFS_AG_RESV_RMAPBT,
+
+ /*
+ * Don't increase fdblocks when freeing extent. This is a pony for
+ * the bnobt repair functions to re-free the free space without
+ * altering fdblocks. If you think you need this you're wrong.
+ */
+ XFS_AG_RESV_IGNORE,
};
/* Results of scanning a btree keyspace to check occupancy. */
diff --git a/fs/xfs/scrub/agb_bitmap.c b/fs/xfs/scrub/agb_bitmap.c
new file mode 100644
index 000000000000..573e4e062754
--- /dev/null
+++ b/fs/xfs/scrub/agb_bitmap.c
@@ -0,0 +1,103 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2018-2023 Oracle. All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#include "xfs.h"
+#include "xfs_shared.h"
+#include "xfs_bit.h"
+#include "xfs_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_btree.h"
+#include "bitmap.h"
+#include "scrub/agb_bitmap.h"
+
+/*
+ * Record all btree blocks seen while iterating all records of a btree.
+ *
+ * We know that the btree query_all function starts at the left edge and walks
+ * towards the right edge of the tree. Therefore, we know that we can walk up
+ * the btree cursor towards the root; if the pointer for a given level points
+ * to the first record/key in that block, we haven't seen this block before;
+ * and therefore we need to remember that we saw this block in the btree.
+ *
+ * So if our btree is:
+ *
+ * 4
+ * / | \
+ * 1 2 3
+ *
+ * Pretend for this example that each leaf block has 100 btree records. For
+ * the first btree record, we'll observe that bc_levels[0].ptr == 1, so we
+ * record that we saw block 1. Then we observe that bc_levels[1].ptr == 1, so
+ * we record block 4. The list is [1, 4].
+ *
+ * For the second btree record, we see that bc_levels[0].ptr == 2, so we exit
+ * the loop. The list remains [1, 4].
+ *
+ * For the 101st btree record, we've moved onto leaf block 2. Now
+ * bc_levels[0].ptr == 1 again, so we record that we saw block 2. We see that
+ * bc_levels[1].ptr == 2, so we exit the loop. The list is now [1, 4, 2].
+ *
+ * For the 102nd record, bc_levels[0].ptr == 2, so we continue.
+ *
+ * For the 201st record, we've moved on to leaf block 3.
+ * bc_levels[0].ptr == 1, so we add 3 to the list. Now it is [1, 4, 2, 3].
+ *
+ * For the 300th record we just exit, with the list being [1, 4, 2, 3].
+ */
+
+/* Mark a btree block to the agblock bitmap. */
+STATIC int
+xagb_bitmap_visit_btblock(
+ struct xfs_btree_cur *cur,
+ int level,
+ void *priv)
+{
+ struct xagb_bitmap *bitmap = priv;
+ struct xfs_buf *bp;
+ xfs_fsblock_t fsbno;
+ xfs_agblock_t agbno;
+
+ xfs_btree_get_block(cur, level, &bp);
+ if (!bp)
+ return 0;
+
+ fsbno = XFS_DADDR_TO_FSB(cur->bc_mp, xfs_buf_daddr(bp));
+ agbno = XFS_FSB_TO_AGBNO(cur->bc_mp, fsbno);
+
+ return xagb_bitmap_set(bitmap, agbno, 1);
+}
+
+/* Mark all (per-AG) btree blocks in the agblock bitmap. */
+int
+xagb_bitmap_set_btblocks(
+ struct xagb_bitmap *bitmap,
+ struct xfs_btree_cur *cur)
+{
+ return xfs_btree_visit_blocks(cur, xagb_bitmap_visit_btblock,
+ XFS_BTREE_VISIT_ALL, bitmap);
+}
+
+/*
+ * Record all the buffers pointed to by the btree cursor. Callers already
+ * engaged in a btree walk should call this function to capture the list of
+ * blocks going from the leaf towards the root.
+ */
+int
+xagb_bitmap_set_btcur_path(
+ struct xagb_bitmap *bitmap,
+ struct xfs_btree_cur *cur)
+{
+ int i;
+ int error;
+
+ for (i = 0; i < cur->bc_nlevels && cur->bc_levels[i].ptr == 1; i++) {
+ error = xagb_bitmap_visit_btblock(cur, i, bitmap);
+ if (error)
+ return error;
+ }
+
+ return 0;
+}
diff --git a/fs/xfs/scrub/agb_bitmap.h b/fs/xfs/scrub/agb_bitmap.h
new file mode 100644
index 000000000000..ed08f76ff4f3
--- /dev/null
+++ b/fs/xfs/scrub/agb_bitmap.h
@@ -0,0 +1,68 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2018-2023 Oracle. All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#ifndef __XFS_SCRUB_AGB_BITMAP_H__
+#define __XFS_SCRUB_AGB_BITMAP_H__
+
+/* Bitmaps, but for type-checked for xfs_agblock_t */
+
+struct xagb_bitmap {
+ struct xbitmap32 agbitmap;
+};
+
+static inline void xagb_bitmap_init(struct xagb_bitmap *bitmap)
+{
+ xbitmap32_init(&bitmap->agbitmap);
+}
+
+static inline void xagb_bitmap_destroy(struct xagb_bitmap *bitmap)
+{
+ xbitmap32_destroy(&bitmap->agbitmap);
+}
+
+static inline int xagb_bitmap_clear(struct xagb_bitmap *bitmap,
+ xfs_agblock_t start, xfs_extlen_t len)
+{
+ return xbitmap32_clear(&bitmap->agbitmap, start, len);
+}
+static inline int xagb_bitmap_set(struct xagb_bitmap *bitmap,
+ xfs_agblock_t start, xfs_extlen_t len)
+{
+ return xbitmap32_set(&bitmap->agbitmap, start, len);
+}
+
+static inline bool xagb_bitmap_test(struct xagb_bitmap *bitmap,
+ xfs_agblock_t start, xfs_extlen_t *len)
+{
+ return xbitmap32_test(&bitmap->agbitmap, start, len);
+}
+
+static inline int xagb_bitmap_disunion(struct xagb_bitmap *bitmap,
+ struct xagb_bitmap *sub)
+{
+ return xbitmap32_disunion(&bitmap->agbitmap, &sub->agbitmap);
+}
+
+static inline uint32_t xagb_bitmap_hweight(struct xagb_bitmap *bitmap)
+{
+ return xbitmap32_hweight(&bitmap->agbitmap);
+}
+static inline bool xagb_bitmap_empty(struct xagb_bitmap *bitmap)
+{
+ return xbitmap32_empty(&bitmap->agbitmap);
+}
+
+static inline int xagb_bitmap_walk(struct xagb_bitmap *bitmap,
+ xbitmap32_walk_fn fn, void *priv)
+{
+ return xbitmap32_walk(&bitmap->agbitmap, fn, priv);
+}
+
+int xagb_bitmap_set_btblocks(struct xagb_bitmap *bitmap,
+ struct xfs_btree_cur *cur);
+int xagb_bitmap_set_btcur_path(struct xagb_bitmap *bitmap,
+ struct xfs_btree_cur *cur);
+
+#endif /* __XFS_SCRUB_AGB_BITMAP_H__ */
diff --git a/fs/xfs/scrub/agheader_repair.c b/fs/xfs/scrub/agheader_repair.c
index 876a2f41b063..26bd1ff68f1b 100644
--- a/fs/xfs/scrub/agheader_repair.c
+++ b/fs/xfs/scrub/agheader_repair.c
@@ -26,6 +26,7 @@
#include "scrub/trace.h"
#include "scrub/repair.h"
#include "scrub/bitmap.h"
+#include "scrub/agb_bitmap.h"
#include "scrub/reap.h"
/* Superblock */
@@ -72,7 +73,7 @@ xrep_superblock(
/* Write this to disk. */
xfs_trans_buf_set_type(sc->tp, bp, XFS_BLFT_SB_BUF);
xfs_trans_log_buf(sc->tp, bp, 0, BBTOB(bp->b_length) - 1);
- return error;
+ return 0;
}
/* AGF */
@@ -341,7 +342,7 @@ xrep_agf_commit_new(
pag->pagf_refcount_level = be32_to_cpu(agf->agf_refcount_level);
set_bit(XFS_AGSTATE_AGF_INIT, &pag->pag_opstate);
- return 0;
+ return xrep_roll_ag_trans(sc);
}
/* Repair the AGF. v5 filesystems only. */
@@ -494,12 +495,11 @@ xrep_agfl_walk_rmap(
/* Strike out the blocks that are cross-linked according to the rmapbt. */
STATIC int
xrep_agfl_check_extent(
- uint64_t start,
- uint64_t len,
+ uint32_t agbno,
+ uint32_t len,
void *priv)
{
struct xrep_agfl *ra = priv;
- xfs_agblock_t agbno = start;
xfs_agblock_t last_agbno = agbno + len - 1;
int error;
@@ -647,8 +647,8 @@ struct xrep_agfl_fill {
/* Fill the AGFL with whatever blocks are in this extent. */
static int
xrep_agfl_fill(
- uint64_t start,
- uint64_t len,
+ uint32_t start,
+ uint32_t len,
void *priv)
{
struct xrep_agfl_fill *af = priv;
@@ -789,6 +789,9 @@ xrep_agfl(
/* Dump any AGFL overflow. */
error = xrep_reap_agblocks(sc, &agfl_extents, &XFS_RMAP_OINFO_AG,
XFS_AG_RESV_AGFL);
+ if (error)
+ goto err;
+
err:
xagb_bitmap_destroy(&agfl_extents);
return error;
@@ -962,7 +965,7 @@ xrep_agi_commit_new(
pag->pagi_freecount = be32_to_cpu(agi->agi_freecount);
set_bit(XFS_AGSTATE_AGI_INIT, &pag->pag_opstate);
- return 0;
+ return xrep_roll_ag_trans(sc);
}
/* Repair the AGI. */
diff --git a/fs/xfs/scrub/alloc.c b/fs/xfs/scrub/alloc.c
index 279af72b1671..d1b8a4997dd2 100644
--- a/fs/xfs/scrub/alloc.c
+++ b/fs/xfs/scrub/alloc.c
@@ -9,13 +9,16 @@
#include "xfs_format.h"
#include "xfs_trans_resv.h"
#include "xfs_mount.h"
+#include "xfs_log_format.h"
+#include "xfs_trans.h"
#include "xfs_btree.h"
#include "xfs_alloc.h"
#include "xfs_rmap.h"
+#include "xfs_ag.h"
#include "scrub/scrub.h"
#include "scrub/common.h"
#include "scrub/btree.h"
-#include "xfs_ag.h"
+#include "scrub/repair.h"
/*
* Set us up to scrub free space btrees.
@@ -24,10 +27,19 @@ int
xchk_setup_ag_allocbt(
struct xfs_scrub *sc)
{
+ int error;
+
if (xchk_need_intent_drain(sc))
xchk_fsgates_enable(sc, XCHK_FSGATES_DRAIN);
- return xchk_setup_ag_btree(sc, false);
+ error = xchk_setup_ag_btree(sc, false);
+ if (error)
+ return error;
+
+ if (xchk_could_repair(sc))
+ return xrep_setup_ag_allocbt(sc);
+
+ return 0;
}
/* Free space btree scrubber. */
@@ -127,7 +139,7 @@ xchk_allocbt_rec(
struct xchk_alloc *ca = bs->private;
xfs_alloc_btrec_to_irec(rec, &irec);
- if (xfs_alloc_check_irec(bs->cur, &irec) != NULL) {
+ if (xfs_alloc_check_irec(bs->cur->bc_ag.pag, &irec) != NULL) {
xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
return 0;
}
@@ -138,31 +150,27 @@ xchk_allocbt_rec(
return 0;
}
-/* Scrub the freespace btrees for some AG. */
-STATIC int
+/* Scrub one of the freespace btrees for some AG. */
+int
xchk_allocbt(
- struct xfs_scrub *sc,
- xfs_btnum_t which)
+ struct xfs_scrub *sc)
{
struct xchk_alloc ca = { };
struct xfs_btree_cur *cur;
- cur = which == XFS_BTNUM_BNO ? sc->sa.bno_cur : sc->sa.cnt_cur;
- return xchk_btree(sc, cur, xchk_allocbt_rec, &XFS_RMAP_OINFO_AG, &ca);
-}
-
-int
-xchk_bnobt(
- struct xfs_scrub *sc)
-{
- return xchk_allocbt(sc, XFS_BTNUM_BNO);
-}
+ switch (sc->sm->sm_type) {
+ case XFS_SCRUB_TYPE_BNOBT:
+ cur = sc->sa.bno_cur;
+ break;
+ case XFS_SCRUB_TYPE_CNTBT:
+ cur = sc->sa.cnt_cur;
+ break;
+ default:
+ ASSERT(0);
+ return -EIO;
+ }
-int
-xchk_cntbt(
- struct xfs_scrub *sc)
-{
- return xchk_allocbt(sc, XFS_BTNUM_CNT);
+ return xchk_btree(sc, cur, xchk_allocbt_rec, &XFS_RMAP_OINFO_AG, &ca);
}
/* xref check that the extent is not free */
diff --git a/fs/xfs/scrub/alloc_repair.c b/fs/xfs/scrub/alloc_repair.c
new file mode 100644
index 000000000000..45edda096869
--- /dev/null
+++ b/fs/xfs/scrub/alloc_repair.c
@@ -0,0 +1,934 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2018-2023 Oracle. All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_defer.h"
+#include "xfs_btree.h"
+#include "xfs_btree_staging.h"
+#include "xfs_bit.h"
+#include "xfs_log_format.h"
+#include "xfs_trans.h"
+#include "xfs_sb.h"
+#include "xfs_alloc.h"
+#include "xfs_alloc_btree.h"
+#include "xfs_rmap.h"
+#include "xfs_rmap_btree.h"
+#include "xfs_inode.h"
+#include "xfs_refcount.h"
+#include "xfs_extent_busy.h"
+#include "xfs_health.h"
+#include "xfs_bmap.h"
+#include "xfs_ialloc.h"
+#include "xfs_ag.h"
+#include "scrub/xfs_scrub.h"
+#include "scrub/scrub.h"
+#include "scrub/common.h"
+#include "scrub/btree.h"
+#include "scrub/trace.h"
+#include "scrub/repair.h"
+#include "scrub/bitmap.h"
+#include "scrub/agb_bitmap.h"
+#include "scrub/xfile.h"
+#include "scrub/xfarray.h"
+#include "scrub/newbt.h"
+#include "scrub/reap.h"
+
+/*
+ * Free Space Btree Repair
+ * =======================
+ *
+ * The reverse mappings are supposed to record all space usage for the entire
+ * AG. Therefore, we can recreate the free extent records in an AG by looking
+ * for gaps in the physical extents recorded in the rmapbt. These records are
+ * staged in @free_records. Identifying the gaps is more difficult on a
+ * reflink filesystem because rmap records are allowed to overlap.
+ *
+ * Because the final step of building a new index is to free the space used by
+ * the old index, repair needs to find that space. Unfortunately, all
+ * structures that live in the free space (bnobt, cntbt, rmapbt, agfl) share
+ * the same rmapbt owner code (OWN_AG), so this is not straightforward.
+ *
+ * The scan of the reverse mapping information records the space used by OWN_AG
+ * in @old_allocbt_blocks, which (at this stage) is somewhat misnamed. While
+ * walking the rmapbt records, we create a second bitmap @not_allocbt_blocks to
+ * record all visited rmap btree blocks and all blocks owned by the AGFL.
+ *
+ * After that is where the definitions of old_allocbt_blocks shifts. This
+ * expression identifies possible former bnobt/cntbt blocks:
+ *
+ * (OWN_AG blocks) & ~(rmapbt blocks | agfl blocks);
+ *
+ * Substituting from above definitions, that becomes:
+ *
+ * old_allocbt_blocks & ~not_allocbt_blocks
+ *
+ * The OWN_AG bitmap itself isn't needed after this point, so what we really do
+ * instead is:
+ *
+ * old_allocbt_blocks &= ~not_allocbt_blocks;
+ *
+ * After this point, @old_allocbt_blocks is a bitmap of alleged former
+ * bnobt/cntbt blocks. The xagb_bitmap_disunion operation modifies its first
+ * parameter in place to avoid copying records around.
+ *
+ * Next, some of the space described by @free_records are diverted to the newbt
+ * reservation and used to format new btree blocks. The remaining records are
+ * written to the new btree indices. We reconstruct both bnobt and cntbt at
+ * the same time since we've already done all the work.
+ *
+ * We use the prefix 'xrep_abt' here because we regenerate both free space
+ * allocation btrees at the same time.
+ */
+
+struct xrep_abt {
+ /* Blocks owned by the rmapbt or the agfl. */
+ struct xagb_bitmap not_allocbt_blocks;
+
+ /* All OWN_AG blocks. */
+ struct xagb_bitmap old_allocbt_blocks;
+
+ /*
+ * New bnobt information. All btree block reservations are added to
+ * the reservation list in new_bnobt.
+ */
+ struct xrep_newbt new_bnobt;
+
+ /* new cntbt information */
+ struct xrep_newbt new_cntbt;
+
+ /* Free space extents. */
+ struct xfarray *free_records;
+
+ struct xfs_scrub *sc;
+
+ /* Number of non-null records in @free_records. */
+ uint64_t nr_real_records;
+
+ /* get_records()'s position in the free space record array. */
+ xfarray_idx_t array_cur;
+
+ /*
+ * Next block we anticipate seeing in the rmap records. If the next
+ * rmap record is greater than next_agbno, we have found unused space.
+ */
+ xfs_agblock_t next_agbno;
+
+ /* Number of free blocks in this AG. */
+ xfs_agblock_t nr_blocks;
+
+ /* Longest free extent we found in the AG. */
+ xfs_agblock_t longest;
+};
+
+/* Set up to repair AG free space btrees. */
+int
+xrep_setup_ag_allocbt(
+ struct xfs_scrub *sc)
+{
+ unsigned int busy_gen;
+
+ /*
+ * Make sure the busy extent list is clear because we can't put extents
+ * on there twice.
+ */
+ busy_gen = READ_ONCE(sc->sa.pag->pagb_gen);
+ if (xfs_extent_busy_list_empty(sc->sa.pag))
+ return 0;
+
+ return xfs_extent_busy_flush(sc->tp, sc->sa.pag, busy_gen, 0);
+}
+
+/* Check for any obvious conflicts in the free extent. */
+STATIC int
+xrep_abt_check_free_ext(
+ struct xfs_scrub *sc,
+ const struct xfs_alloc_rec_incore *rec)
+{
+ enum xbtree_recpacking outcome;
+ int error;
+
+ if (xfs_alloc_check_irec(sc->sa.pag, rec) != NULL)
+ return -EFSCORRUPTED;
+
+ /* Must not be an inode chunk. */
+ error = xfs_ialloc_has_inodes_at_extent(sc->sa.ino_cur,
+ rec->ar_startblock, rec->ar_blockcount, &outcome);
+ if (error)
+ return error;
+ if (outcome != XBTREE_RECPACKING_EMPTY)
+ return -EFSCORRUPTED;
+
+ /* Must not be shared or CoW staging. */
+ if (sc->sa.refc_cur) {
+ error = xfs_refcount_has_records(sc->sa.refc_cur,
+ XFS_REFC_DOMAIN_SHARED, rec->ar_startblock,
+ rec->ar_blockcount, &outcome);
+ if (error)
+ return error;
+ if (outcome != XBTREE_RECPACKING_EMPTY)
+ return -EFSCORRUPTED;
+
+ error = xfs_refcount_has_records(sc->sa.refc_cur,
+ XFS_REFC_DOMAIN_COW, rec->ar_startblock,
+ rec->ar_blockcount, &outcome);
+ if (error)
+ return error;
+ if (outcome != XBTREE_RECPACKING_EMPTY)
+ return -EFSCORRUPTED;
+ }
+
+ return 0;
+}
+
+/*
+ * Stash a free space record for all the space since the last bno we found
+ * all the way up to @end.
+ */
+static int
+xrep_abt_stash(
+ struct xrep_abt *ra,
+ xfs_agblock_t end)
+{
+ struct xfs_alloc_rec_incore arec = {
+ .ar_startblock = ra->next_agbno,
+ .ar_blockcount = end - ra->next_agbno,
+ };
+ struct xfs_scrub *sc = ra->sc;
+ int error = 0;
+
+ if (xchk_should_terminate(sc, &error))
+ return error;
+
+ error = xrep_abt_check_free_ext(ra->sc, &arec);
+ if (error)
+ return error;
+
+ trace_xrep_abt_found(sc->mp, sc->sa.pag->pag_agno, &arec);
+
+ error = xfarray_append(ra->free_records, &arec);
+ if (error)
+ return error;
+
+ ra->nr_blocks += arec.ar_blockcount;
+ return 0;
+}
+
+/* Record extents that aren't in use from gaps in the rmap records. */
+STATIC int
+xrep_abt_walk_rmap(
+ struct xfs_btree_cur *cur,
+ const struct xfs_rmap_irec *rec,
+ void *priv)
+{
+ struct xrep_abt *ra = priv;
+ int error;
+
+ /* Record all the OWN_AG blocks... */
+ if (rec->rm_owner == XFS_RMAP_OWN_AG) {
+ error = xagb_bitmap_set(&ra->old_allocbt_blocks,
+ rec->rm_startblock, rec->rm_blockcount);
+ if (error)
+ return error;
+ }
+
+ /* ...and all the rmapbt blocks... */
+ error = xagb_bitmap_set_btcur_path(&ra->not_allocbt_blocks, cur);
+ if (error)
+ return error;
+
+ /* ...and all the free space. */
+ if (rec->rm_startblock > ra->next_agbno) {
+ error = xrep_abt_stash(ra, rec->rm_startblock);
+ if (error)
+ return error;
+ }
+
+ /*
+ * rmap records can overlap on reflink filesystems, so project
+ * next_agbno as far out into the AG space as we currently know about.
+ */
+ ra->next_agbno = max_t(xfs_agblock_t, ra->next_agbno,
+ rec->rm_startblock + rec->rm_blockcount);
+ return 0;
+}
+
+/* Collect an AGFL block for the not-to-release list. */
+static int
+xrep_abt_walk_agfl(
+ struct xfs_mount *mp,
+ xfs_agblock_t agbno,
+ void *priv)
+{
+ struct xrep_abt *ra = priv;
+
+ return xagb_bitmap_set(&ra->not_allocbt_blocks, agbno, 1);
+}
+
+/*
+ * Compare two free space extents by block number. We want to sort in order of
+ * increasing block number.
+ */
+static int
+xrep_bnobt_extent_cmp(
+ const void *a,
+ const void *b)
+{
+ const struct xfs_alloc_rec_incore *ap = a;
+ const struct xfs_alloc_rec_incore *bp = b;
+
+ if (ap->ar_startblock > bp->ar_startblock)
+ return 1;
+ else if (ap->ar_startblock < bp->ar_startblock)
+ return -1;
+ return 0;
+}
+
+/*
+ * Re-sort the free extents by block number so that we can put the records into
+ * the bnobt in the correct order. Make sure the records do not overlap in
+ * physical space.
+ */
+STATIC int
+xrep_bnobt_sort_records(
+ struct xrep_abt *ra)
+{
+ struct xfs_alloc_rec_incore arec;
+ xfarray_idx_t cur = XFARRAY_CURSOR_INIT;
+ xfs_agblock_t next_agbno = 0;
+ int error;
+
+ error = xfarray_sort(ra->free_records, xrep_bnobt_extent_cmp, 0);
+ if (error)
+ return error;
+
+ while ((error = xfarray_iter(ra->free_records, &cur, &arec)) == 1) {
+ if (arec.ar_startblock < next_agbno)
+ return -EFSCORRUPTED;
+
+ next_agbno = arec.ar_startblock + arec.ar_blockcount;
+ }
+
+ return error;
+}
+
+/*
+ * Compare two free space extents by length and then block number. We want
+ * to sort first in order of increasing length and then in order of increasing
+ * block number.
+ */
+static int
+xrep_cntbt_extent_cmp(
+ const void *a,
+ const void *b)
+{
+ const struct xfs_alloc_rec_incore *ap = a;
+ const struct xfs_alloc_rec_incore *bp = b;
+
+ if (ap->ar_blockcount > bp->ar_blockcount)
+ return 1;
+ else if (ap->ar_blockcount < bp->ar_blockcount)
+ return -1;
+ return xrep_bnobt_extent_cmp(a, b);
+}
+
+/*
+ * Sort the free extents by length so so that we can put the records into the
+ * cntbt in the correct order. Don't let userspace kill us if we're resorting
+ * after allocating btree blocks.
+ */
+STATIC int
+xrep_cntbt_sort_records(
+ struct xrep_abt *ra,
+ bool is_resort)
+{
+ return xfarray_sort(ra->free_records, xrep_cntbt_extent_cmp,
+ is_resort ? 0 : XFARRAY_SORT_KILLABLE);
+}
+
+/*
+ * Iterate all reverse mappings to find (1) the gaps between rmap records (all
+ * unowned space), (2) the OWN_AG extents (which encompass the free space
+ * btrees, the rmapbt, and the agfl), (3) the rmapbt blocks, and (4) the AGFL
+ * blocks. The free space is (1) + (2) - (3) - (4).
+ */
+STATIC int
+xrep_abt_find_freespace(
+ struct xrep_abt *ra)
+{
+ struct xfs_scrub *sc = ra->sc;
+ struct xfs_mount *mp = sc->mp;
+ struct xfs_agf *agf = sc->sa.agf_bp->b_addr;
+ struct xfs_buf *agfl_bp;
+ xfs_agblock_t agend;
+ int error;
+
+ xagb_bitmap_init(&ra->not_allocbt_blocks);
+
+ xrep_ag_btcur_init(sc, &sc->sa);
+
+ /*
+ * Iterate all the reverse mappings to find gaps in the physical
+ * mappings, all the OWN_AG blocks, and all the rmapbt extents.
+ */
+ error = xfs_rmap_query_all(sc->sa.rmap_cur, xrep_abt_walk_rmap, ra);
+ if (error)
+ goto err;
+
+ /* Insert a record for space between the last rmap and EOAG. */
+ agend = be32_to_cpu(agf->agf_length);
+ if (ra->next_agbno < agend) {
+ error = xrep_abt_stash(ra, agend);
+ if (error)
+ goto err;
+ }
+
+ /* Collect all the AGFL blocks. */
+ error = xfs_alloc_read_agfl(sc->sa.pag, sc->tp, &agfl_bp);
+ if (error)
+ goto err;
+
+ error = xfs_agfl_walk(mp, agf, agfl_bp, xrep_abt_walk_agfl, ra);
+ if (error)
+ goto err_agfl;
+
+ /* Compute the old bnobt/cntbt blocks. */
+ error = xagb_bitmap_disunion(&ra->old_allocbt_blocks,
+ &ra->not_allocbt_blocks);
+ if (error)
+ goto err_agfl;
+
+ ra->nr_real_records = xfarray_length(ra->free_records);
+err_agfl:
+ xfs_trans_brelse(sc->tp, agfl_bp);
+err:
+ xchk_ag_btcur_free(&sc->sa);
+ xagb_bitmap_destroy(&ra->not_allocbt_blocks);
+ return error;
+}
+
+/*
+ * We're going to use the observed free space records to reserve blocks for the
+ * new free space btrees, so we play an iterative game where we try to converge
+ * on the number of blocks we need:
+ *
+ * 1. Estimate how many blocks we'll need to store the records.
+ * 2. If the first free record has more blocks than we need, we're done.
+ * We will have to re-sort the records prior to building the cntbt.
+ * 3. If that record has exactly the number of blocks we need, null out the
+ * record. We're done.
+ * 4. Otherwise, we still need more blocks. Null out the record, subtract its
+ * length from the number of blocks we need, and go back to step 1.
+ *
+ * Fortunately, we don't have to do any transaction work to play this game, so
+ * we don't have to tear down the staging cursors.
+ */
+STATIC int
+xrep_abt_reserve_space(
+ struct xrep_abt *ra,
+ struct xfs_btree_cur *bno_cur,
+ struct xfs_btree_cur *cnt_cur,
+ bool *needs_resort)
+{
+ struct xfs_scrub *sc = ra->sc;
+ xfarray_idx_t record_nr;
+ unsigned int allocated = 0;
+ int error = 0;
+
+ record_nr = xfarray_length(ra->free_records) - 1;
+ do {
+ struct xfs_alloc_rec_incore arec;
+ uint64_t required;
+ unsigned int desired;
+ unsigned int len;
+
+ /* Compute how many blocks we'll need. */
+ error = xfs_btree_bload_compute_geometry(cnt_cur,
+ &ra->new_cntbt.bload, ra->nr_real_records);
+ if (error)
+ break;
+
+ error = xfs_btree_bload_compute_geometry(bno_cur,
+ &ra->new_bnobt.bload, ra->nr_real_records);
+ if (error)
+ break;
+
+ /* How many btree blocks do we need to store all records? */
+ required = ra->new_bnobt.bload.nr_blocks +
+ ra->new_cntbt.bload.nr_blocks;
+ ASSERT(required < INT_MAX);
+
+ /* If we've reserved enough blocks, we're done. */
+ if (allocated >= required)
+ break;
+
+ desired = required - allocated;
+
+ /* We need space but there's none left; bye! */
+ if (ra->nr_real_records == 0) {
+ error = -ENOSPC;
+ break;
+ }
+
+ /* Grab the first record from the list. */
+ error = xfarray_load(ra->free_records, record_nr, &arec);
+ if (error)
+ break;
+
+ ASSERT(arec.ar_blockcount <= UINT_MAX);
+ len = min_t(unsigned int, arec.ar_blockcount, desired);
+
+ trace_xrep_newbt_alloc_ag_blocks(sc->mp, sc->sa.pag->pag_agno,
+ arec.ar_startblock, len, XFS_RMAP_OWN_AG);
+
+ error = xrep_newbt_add_extent(&ra->new_bnobt, sc->sa.pag,
+ arec.ar_startblock, len);
+ if (error)
+ break;
+ allocated += len;
+ ra->nr_blocks -= len;
+
+ if (arec.ar_blockcount > desired) {
+ /*
+ * Record has more space than we need. The number of
+ * free records doesn't change, so shrink the free
+ * record, inform the caller that the records are no
+ * longer sorted by length, and exit.
+ */
+ arec.ar_startblock += desired;
+ arec.ar_blockcount -= desired;
+ error = xfarray_store(ra->free_records, record_nr,
+ &arec);
+ if (error)
+ break;
+
+ *needs_resort = true;
+ return 0;
+ }
+
+ /*
+ * We're going to use up the entire record, so unset it and
+ * move on to the next one. This changes the number of free
+ * records (but doesn't break the sorting order), so we must
+ * go around the loop once more to re-run _bload_init.
+ */
+ error = xfarray_unset(ra->free_records, record_nr);
+ if (error)
+ break;
+ ra->nr_real_records--;
+ record_nr--;
+ } while (1);
+
+ return error;
+}
+
+STATIC int
+xrep_abt_dispose_one(
+ struct xrep_abt *ra,
+ struct xrep_newbt_resv *resv)
+{
+ struct xfs_scrub *sc = ra->sc;
+ struct xfs_perag *pag = sc->sa.pag;
+ xfs_agblock_t free_agbno = resv->agbno + resv->used;
+ xfs_extlen_t free_aglen = resv->len - resv->used;
+ int error;
+
+ ASSERT(pag == resv->pag);
+
+ /* Add a deferred rmap for each extent we used. */
+ if (resv->used > 0)
+ xfs_rmap_alloc_extent(sc->tp, pag->pag_agno, resv->agbno,
+ resv->used, XFS_RMAP_OWN_AG);
+
+ /*
+ * For each reserved btree block we didn't use, add it to the free
+ * space btree. We didn't touch fdblocks when we reserved them, so
+ * we don't touch it now.
+ */
+ if (free_aglen == 0)
+ return 0;
+
+ trace_xrep_newbt_free_blocks(sc->mp, resv->pag->pag_agno, free_agbno,
+ free_aglen, ra->new_bnobt.oinfo.oi_owner);
+
+ error = __xfs_free_extent(sc->tp, resv->pag, free_agbno, free_aglen,
+ &ra->new_bnobt.oinfo, XFS_AG_RESV_IGNORE, true);
+ if (error)
+ return error;
+
+ return xrep_defer_finish(sc);
+}
+
+/*
+ * Deal with all the space we reserved. Blocks that were allocated for the
+ * free space btrees need to have a (deferred) rmap added for the OWN_AG
+ * allocation, and blocks that didn't get used can be freed via the usual
+ * (deferred) means.
+ */
+STATIC void
+xrep_abt_dispose_reservations(
+ struct xrep_abt *ra,
+ int error)
+{
+ struct xrep_newbt_resv *resv, *n;
+
+ if (error)
+ goto junkit;
+
+ list_for_each_entry_safe(resv, n, &ra->new_bnobt.resv_list, list) {
+ error = xrep_abt_dispose_one(ra, resv);
+ if (error)
+ goto junkit;
+ }
+
+junkit:
+ list_for_each_entry_safe(resv, n, &ra->new_bnobt.resv_list, list) {
+ xfs_perag_put(resv->pag);
+ list_del(&resv->list);
+ kfree(resv);
+ }
+
+ xrep_newbt_cancel(&ra->new_bnobt);
+ xrep_newbt_cancel(&ra->new_cntbt);
+}
+
+/* Retrieve free space data for bulk load. */
+STATIC int
+xrep_abt_get_records(
+ struct xfs_btree_cur *cur,
+ unsigned int idx,
+ struct xfs_btree_block *block,
+ unsigned int nr_wanted,
+ void *priv)
+{
+ struct xfs_alloc_rec_incore *arec = &cur->bc_rec.a;
+ struct xrep_abt *ra = priv;
+ union xfs_btree_rec *block_rec;
+ unsigned int loaded;
+ int error;
+
+ for (loaded = 0; loaded < nr_wanted; loaded++, idx++) {
+ error = xfarray_load_next(ra->free_records, &ra->array_cur,
+ arec);
+ if (error)
+ return error;
+
+ ra->longest = max(ra->longest, arec->ar_blockcount);
+
+ block_rec = xfs_btree_rec_addr(cur, idx, block);
+ cur->bc_ops->init_rec_from_cur(cur, block_rec);
+ }
+
+ return loaded;
+}
+
+/* Feed one of the new btree blocks to the bulk loader. */
+STATIC int
+xrep_abt_claim_block(
+ struct xfs_btree_cur *cur,
+ union xfs_btree_ptr *ptr,
+ void *priv)
+{
+ struct xrep_abt *ra = priv;
+
+ return xrep_newbt_claim_block(cur, &ra->new_bnobt, ptr);
+}
+
+/*
+ * Reset the AGF counters to reflect the free space btrees that we just
+ * rebuilt, then reinitialize the per-AG data.
+ */
+STATIC int
+xrep_abt_reset_counters(
+ struct xrep_abt *ra)
+{
+ struct xfs_scrub *sc = ra->sc;
+ struct xfs_perag *pag = sc->sa.pag;
+ struct xfs_agf *agf = sc->sa.agf_bp->b_addr;
+ unsigned int freesp_btreeblks = 0;
+
+ /*
+ * Compute the contribution to agf_btreeblks for the new free space
+ * btrees. This is the computed btree size minus anything we didn't
+ * use.
+ */
+ freesp_btreeblks += ra->new_bnobt.bload.nr_blocks - 1;
+ freesp_btreeblks += ra->new_cntbt.bload.nr_blocks - 1;
+
+ freesp_btreeblks -= xrep_newbt_unused_blocks(&ra->new_bnobt);
+ freesp_btreeblks -= xrep_newbt_unused_blocks(&ra->new_cntbt);
+
+ /*
+ * The AGF header contains extra information related to the free space
+ * btrees, so we must update those fields here.
+ */
+ agf->agf_btreeblks = cpu_to_be32(freesp_btreeblks +
+ (be32_to_cpu(agf->agf_rmap_blocks) - 1));
+ agf->agf_freeblks = cpu_to_be32(ra->nr_blocks);
+ agf->agf_longest = cpu_to_be32(ra->longest);
+ xfs_alloc_log_agf(sc->tp, sc->sa.agf_bp, XFS_AGF_BTREEBLKS |
+ XFS_AGF_LONGEST |
+ XFS_AGF_FREEBLKS);
+
+ /*
+ * After we commit the new btree to disk, it is possible that the
+ * process to reap the old btree blocks will race with the AIL trying
+ * to checkpoint the old btree blocks into the filesystem. If the new
+ * tree is shorter than the old one, the allocbt write verifier will
+ * fail and the AIL will shut down the filesystem.
+ *
+ * To avoid this, save the old incore btree height values as the alt
+ * height values before re-initializing the perag info from the updated
+ * AGF to capture all the new values.
+ */
+ pag->pagf_repair_levels[XFS_BTNUM_BNOi] = pag->pagf_levels[XFS_BTNUM_BNOi];
+ pag->pagf_repair_levels[XFS_BTNUM_CNTi] = pag->pagf_levels[XFS_BTNUM_CNTi];
+
+ /* Reinitialize with the values we just logged. */
+ return xrep_reinit_pagf(sc);
+}
+
+/*
+ * Use the collected free space information to stage new free space btrees.
+ * If this is successful we'll return with the new btree root
+ * information logged to the repair transaction but not yet committed.
+ */
+STATIC int
+xrep_abt_build_new_trees(
+ struct xrep_abt *ra)
+{
+ struct xfs_scrub *sc = ra->sc;
+ struct xfs_btree_cur *bno_cur;
+ struct xfs_btree_cur *cnt_cur;
+ struct xfs_perag *pag = sc->sa.pag;
+ bool needs_resort = false;
+ int error;
+
+ /*
+ * Sort the free extents by length so that we can set up the free space
+ * btrees in as few extents as possible. This reduces the amount of
+ * deferred rmap / free work we have to do at the end.
+ */
+ error = xrep_cntbt_sort_records(ra, false);
+ if (error)
+ return error;
+
+ /*
+ * Prepare to construct the new btree by reserving disk space for the
+ * new btree and setting up all the accounting information we'll need
+ * to root the new btree while it's under construction and before we
+ * attach it to the AG header.
+ */
+ xrep_newbt_init_bare(&ra->new_bnobt, sc);
+ xrep_newbt_init_bare(&ra->new_cntbt, sc);
+
+ ra->new_bnobt.bload.get_records = xrep_abt_get_records;
+ ra->new_cntbt.bload.get_records = xrep_abt_get_records;
+
+ ra->new_bnobt.bload.claim_block = xrep_abt_claim_block;
+ ra->new_cntbt.bload.claim_block = xrep_abt_claim_block;
+
+ /* Allocate cursors for the staged btrees. */
+ bno_cur = xfs_allocbt_stage_cursor(sc->mp, &ra->new_bnobt.afake,
+ pag, XFS_BTNUM_BNO);
+ cnt_cur = xfs_allocbt_stage_cursor(sc->mp, &ra->new_cntbt.afake,
+ pag, XFS_BTNUM_CNT);
+
+ /* Last chance to abort before we start committing fixes. */
+ if (xchk_should_terminate(sc, &error))
+ goto err_cur;
+
+ /* Reserve the space we'll need for the new btrees. */
+ error = xrep_abt_reserve_space(ra, bno_cur, cnt_cur, &needs_resort);
+ if (error)
+ goto err_cur;
+
+ /*
+ * If we need to re-sort the free extents by length, do so so that we
+ * can put the records into the cntbt in the correct order.
+ */
+ if (needs_resort) {
+ error = xrep_cntbt_sort_records(ra, needs_resort);
+ if (error)
+ goto err_cur;
+ }
+
+ /*
+ * Due to btree slack factors, it's possible for a new btree to be one
+ * level taller than the old btree. Update the alternate incore btree
+ * height so that we don't trip the verifiers when writing the new
+ * btree blocks to disk.
+ */
+ pag->pagf_repair_levels[XFS_BTNUM_BNOi] =
+ ra->new_bnobt.bload.btree_height;
+ pag->pagf_repair_levels[XFS_BTNUM_CNTi] =
+ ra->new_cntbt.bload.btree_height;
+
+ /* Load the free space by length tree. */
+ ra->array_cur = XFARRAY_CURSOR_INIT;
+ ra->longest = 0;
+ error = xfs_btree_bload(cnt_cur, &ra->new_cntbt.bload, ra);
+ if (error)
+ goto err_levels;
+
+ error = xrep_bnobt_sort_records(ra);
+ if (error)
+ return error;
+
+ /* Load the free space by block number tree. */
+ ra->array_cur = XFARRAY_CURSOR_INIT;
+ error = xfs_btree_bload(bno_cur, &ra->new_bnobt.bload, ra);
+ if (error)
+ goto err_levels;
+
+ /*
+ * Install the new btrees in the AG header. After this point the old
+ * btrees are no longer accessible and the new trees are live.
+ */
+ xfs_allocbt_commit_staged_btree(bno_cur, sc->tp, sc->sa.agf_bp);
+ xfs_btree_del_cursor(bno_cur, 0);
+ xfs_allocbt_commit_staged_btree(cnt_cur, sc->tp, sc->sa.agf_bp);
+ xfs_btree_del_cursor(cnt_cur, 0);
+
+ /* Reset the AGF counters now that we've changed the btree shape. */
+ error = xrep_abt_reset_counters(ra);
+ if (error)
+ goto err_newbt;
+
+ /* Dispose of any unused blocks and the accounting information. */
+ xrep_abt_dispose_reservations(ra, error);
+
+ return xrep_roll_ag_trans(sc);
+
+err_levels:
+ pag->pagf_repair_levels[XFS_BTNUM_BNOi] = 0;
+ pag->pagf_repair_levels[XFS_BTNUM_CNTi] = 0;
+err_cur:
+ xfs_btree_del_cursor(cnt_cur, error);
+ xfs_btree_del_cursor(bno_cur, error);
+err_newbt:
+ xrep_abt_dispose_reservations(ra, error);
+ return error;
+}
+
+/*
+ * Now that we've logged the roots of the new btrees, invalidate all of the
+ * old blocks and free them.
+ */
+STATIC int
+xrep_abt_remove_old_trees(
+ struct xrep_abt *ra)
+{
+ struct xfs_perag *pag = ra->sc->sa.pag;
+ int error;
+
+ /* Free the old btree blocks if they're not in use. */
+ error = xrep_reap_agblocks(ra->sc, &ra->old_allocbt_blocks,
+ &XFS_RMAP_OINFO_AG, XFS_AG_RESV_IGNORE);
+ if (error)
+ return error;
+
+ /*
+ * Now that we've zapped all the old allocbt blocks we can turn off
+ * the alternate height mechanism.
+ */
+ pag->pagf_repair_levels[XFS_BTNUM_BNOi] = 0;
+ pag->pagf_repair_levels[XFS_BTNUM_CNTi] = 0;
+ return 0;
+}
+
+/* Repair the freespace btrees for some AG. */
+int
+xrep_allocbt(
+ struct xfs_scrub *sc)
+{
+ struct xrep_abt *ra;
+ struct xfs_mount *mp = sc->mp;
+ char *descr;
+ int error;
+
+ /* We require the rmapbt to rebuild anything. */
+ if (!xfs_has_rmapbt(mp))
+ return -EOPNOTSUPP;
+
+ ra = kzalloc(sizeof(struct xrep_abt), XCHK_GFP_FLAGS);
+ if (!ra)
+ return -ENOMEM;
+ ra->sc = sc;
+
+ /* We rebuild both data structures. */
+ sc->sick_mask = XFS_SICK_AG_BNOBT | XFS_SICK_AG_CNTBT;
+
+ /*
+ * Make sure the busy extent list is clear because we can't put extents
+ * on there twice. In theory we cleared this before we started, but
+ * let's not risk the filesystem.
+ */
+ if (!xfs_extent_busy_list_empty(sc->sa.pag)) {
+ error = -EDEADLOCK;
+ goto out_ra;
+ }
+
+ /* Set up enough storage to handle maximally fragmented free space. */
+ descr = xchk_xfile_ag_descr(sc, "free space records");
+ error = xfarray_create(descr, mp->m_sb.sb_agblocks / 2,
+ sizeof(struct xfs_alloc_rec_incore),
+ &ra->free_records);
+ kfree(descr);
+ if (error)
+ goto out_ra;
+
+ /* Collect the free space data and find the old btree blocks. */
+ xagb_bitmap_init(&ra->old_allocbt_blocks);
+ error = xrep_abt_find_freespace(ra);
+ if (error)
+ goto out_bitmap;
+
+ /* Rebuild the free space information. */
+ error = xrep_abt_build_new_trees(ra);
+ if (error)
+ goto out_bitmap;
+
+ /* Kill the old trees. */
+ error = xrep_abt_remove_old_trees(ra);
+ if (error)
+ goto out_bitmap;
+
+out_bitmap:
+ xagb_bitmap_destroy(&ra->old_allocbt_blocks);
+ xfarray_destroy(ra->free_records);
+out_ra:
+ kfree(ra);
+ return error;
+}
+
+/* Make sure both btrees are ok after we've rebuilt them. */
+int
+xrep_revalidate_allocbt(
+ struct xfs_scrub *sc)
+{
+ __u32 old_type = sc->sm->sm_type;
+ int error;
+
+ /*
+ * We must update sm_type temporarily so that the tree-to-tree cross
+ * reference checks will work in the correct direction, and also so
+ * that tracing will report correctly if there are more errors.
+ */
+ sc->sm->sm_type = XFS_SCRUB_TYPE_BNOBT;
+ error = xchk_allocbt(sc);
+ if (error)
+ goto out;
+
+ sc->sm->sm_type = XFS_SCRUB_TYPE_CNTBT;
+ error = xchk_allocbt(sc);
+out:
+ sc->sm->sm_type = old_type;
+ return error;
+}
diff --git a/fs/xfs/scrub/attr.c b/fs/xfs/scrub/attr.c
index 6c16d9530cca..83c7feb38714 100644
--- a/fs/xfs/scrub/attr.c
+++ b/fs/xfs/scrub/attr.c
@@ -527,28 +527,23 @@ xchk_xattr_check_sf(
struct xfs_scrub *sc)
{
struct xchk_xattr_buf *ab = sc->buf;
- struct xfs_attr_shortform *sf;
- struct xfs_attr_sf_entry *sfe;
+ struct xfs_ifork *ifp = &sc->ip->i_af;
+ struct xfs_attr_sf_hdr *sf = ifp->if_data;
+ struct xfs_attr_sf_entry *sfe = xfs_attr_sf_firstentry(sf);
struct xfs_attr_sf_entry *next;
- struct xfs_ifork *ifp;
- unsigned char *end;
+ unsigned char *end = ifp->if_data + ifp->if_bytes;
int i;
int error = 0;
- ifp = xfs_ifork_ptr(sc->ip, XFS_ATTR_FORK);
-
bitmap_zero(ab->usedmap, ifp->if_bytes);
- sf = (struct xfs_attr_shortform *)sc->ip->i_af.if_u1.if_data;
- end = (unsigned char *)ifp->if_u1.if_data + ifp->if_bytes;
- xchk_xattr_set_map(sc, ab->usedmap, 0, sizeof(sf->hdr));
+ xchk_xattr_set_map(sc, ab->usedmap, 0, sizeof(*sf));
- sfe = &sf->list[0];
if ((unsigned char *)sfe > end) {
xchk_fblock_set_corrupt(sc, XFS_ATTR_FORK, 0);
return 0;
}
- for (i = 0; i < sf->hdr.count; i++) {
+ for (i = 0; i < sf->count; i++) {
unsigned char *name = sfe->nameval;
unsigned char *value = &sfe->nameval[sfe->namelen];
diff --git a/fs/xfs/scrub/bitmap.c b/fs/xfs/scrub/bitmap.c
index e0c89a9a0ca0..1449bb5262d9 100644
--- a/fs/xfs/scrub/bitmap.c
+++ b/fs/xfs/scrub/bitmap.c
@@ -16,7 +16,9 @@
#include <linux/interval_tree_generic.h>
-struct xbitmap_node {
+/* u64 bitmap */
+
+struct xbitmap64_node {
struct rb_node bn_rbnode;
/* First set bit of this interval and subtree. */
@@ -39,72 +41,72 @@ struct xbitmap_node {
* forward-declare them anyway for clarity.
*/
static inline void
-xbitmap_tree_insert(struct xbitmap_node *node, struct rb_root_cached *root);
+xbitmap64_tree_insert(struct xbitmap64_node *node, struct rb_root_cached *root);
static inline void
-xbitmap_tree_remove(struct xbitmap_node *node, struct rb_root_cached *root);
+xbitmap64_tree_remove(struct xbitmap64_node *node, struct rb_root_cached *root);
-static inline struct xbitmap_node *
-xbitmap_tree_iter_first(struct rb_root_cached *root, uint64_t start,
+static inline struct xbitmap64_node *
+xbitmap64_tree_iter_first(struct rb_root_cached *root, uint64_t start,
uint64_t last);
-static inline struct xbitmap_node *
-xbitmap_tree_iter_next(struct xbitmap_node *node, uint64_t start,
+static inline struct xbitmap64_node *
+xbitmap64_tree_iter_next(struct xbitmap64_node *node, uint64_t start,
uint64_t last);
-INTERVAL_TREE_DEFINE(struct xbitmap_node, bn_rbnode, uint64_t,
- __bn_subtree_last, START, LAST, static inline, xbitmap_tree)
+INTERVAL_TREE_DEFINE(struct xbitmap64_node, bn_rbnode, uint64_t,
+ __bn_subtree_last, START, LAST, static inline, xbitmap64_tree)
/* Iterate each interval of a bitmap. Do not change the bitmap. */
-#define for_each_xbitmap_extent(bn, bitmap) \
+#define for_each_xbitmap64_extent(bn, bitmap) \
for ((bn) = rb_entry_safe(rb_first(&(bitmap)->xb_root.rb_root), \
- struct xbitmap_node, bn_rbnode); \
+ struct xbitmap64_node, bn_rbnode); \
(bn) != NULL; \
(bn) = rb_entry_safe(rb_next(&(bn)->bn_rbnode), \
- struct xbitmap_node, bn_rbnode))
+ struct xbitmap64_node, bn_rbnode))
/* Clear a range of this bitmap. */
int
-xbitmap_clear(
- struct xbitmap *bitmap,
+xbitmap64_clear(
+ struct xbitmap64 *bitmap,
uint64_t start,
uint64_t len)
{
- struct xbitmap_node *bn;
- struct xbitmap_node *new_bn;
+ struct xbitmap64_node *bn;
+ struct xbitmap64_node *new_bn;
uint64_t last = start + len - 1;
- while ((bn = xbitmap_tree_iter_first(&bitmap->xb_root, start, last))) {
+ while ((bn = xbitmap64_tree_iter_first(&bitmap->xb_root, start, last))) {
if (bn->bn_start < start && bn->bn_last > last) {
uint64_t old_last = bn->bn_last;
/* overlaps with the entire clearing range */
- xbitmap_tree_remove(bn, &bitmap->xb_root);
+ xbitmap64_tree_remove(bn, &bitmap->xb_root);
bn->bn_last = start - 1;
- xbitmap_tree_insert(bn, &bitmap->xb_root);
+ xbitmap64_tree_insert(bn, &bitmap->xb_root);
/* add an extent */
- new_bn = kmalloc(sizeof(struct xbitmap_node),
+ new_bn = kmalloc(sizeof(struct xbitmap64_node),
XCHK_GFP_FLAGS);
if (!new_bn)
return -ENOMEM;
new_bn->bn_start = last + 1;
new_bn->bn_last = old_last;
- xbitmap_tree_insert(new_bn, &bitmap->xb_root);
+ xbitmap64_tree_insert(new_bn, &bitmap->xb_root);
} else if (bn->bn_start < start) {
/* overlaps with the left side of the clearing range */
- xbitmap_tree_remove(bn, &bitmap->xb_root);
+ xbitmap64_tree_remove(bn, &bitmap->xb_root);
bn->bn_last = start - 1;
- xbitmap_tree_insert(bn, &bitmap->xb_root);
+ xbitmap64_tree_insert(bn, &bitmap->xb_root);
} else if (bn->bn_last > last) {
/* overlaps with the right side of the clearing range */
- xbitmap_tree_remove(bn, &bitmap->xb_root);
+ xbitmap64_tree_remove(bn, &bitmap->xb_root);
bn->bn_start = last + 1;
- xbitmap_tree_insert(bn, &bitmap->xb_root);
+ xbitmap64_tree_insert(bn, &bitmap->xb_root);
break;
} else {
/* in the middle of the clearing range */
- xbitmap_tree_remove(bn, &bitmap->xb_root);
+ xbitmap64_tree_remove(bn, &bitmap->xb_root);
kfree(bn);
}
}
@@ -114,59 +116,59 @@ xbitmap_clear(
/* Set a range of this bitmap. */
int
-xbitmap_set(
- struct xbitmap *bitmap,
+xbitmap64_set(
+ struct xbitmap64 *bitmap,
uint64_t start,
uint64_t len)
{
- struct xbitmap_node *left;
- struct xbitmap_node *right;
+ struct xbitmap64_node *left;
+ struct xbitmap64_node *right;
uint64_t last = start + len - 1;
int error;
/* Is this whole range already set? */
- left = xbitmap_tree_iter_first(&bitmap->xb_root, start, last);
+ left = xbitmap64_tree_iter_first(&bitmap->xb_root, start, last);
if (left && left->bn_start <= start && left->bn_last >= last)
return 0;
/* Clear out everything in the range we want to set. */
- error = xbitmap_clear(bitmap, start, len);
+ error = xbitmap64_clear(bitmap, start, len);
if (error)
return error;
/* Do we have a left-adjacent extent? */
- left = xbitmap_tree_iter_first(&bitmap->xb_root, start - 1, start - 1);
+ left = xbitmap64_tree_iter_first(&bitmap->xb_root, start - 1, start - 1);
ASSERT(!left || left->bn_last + 1 == start);
/* Do we have a right-adjacent extent? */
- right = xbitmap_tree_iter_first(&bitmap->xb_root, last + 1, last + 1);
+ right = xbitmap64_tree_iter_first(&bitmap->xb_root, last + 1, last + 1);
ASSERT(!right || right->bn_start == last + 1);
if (left && right) {
/* combine left and right adjacent extent */
- xbitmap_tree_remove(left, &bitmap->xb_root);
- xbitmap_tree_remove(right, &bitmap->xb_root);
+ xbitmap64_tree_remove(left, &bitmap->xb_root);
+ xbitmap64_tree_remove(right, &bitmap->xb_root);
left->bn_last = right->bn_last;
- xbitmap_tree_insert(left, &bitmap->xb_root);
+ xbitmap64_tree_insert(left, &bitmap->xb_root);
kfree(right);
} else if (left) {
/* combine with left extent */
- xbitmap_tree_remove(left, &bitmap->xb_root);
+ xbitmap64_tree_remove(left, &bitmap->xb_root);
left->bn_last = last;
- xbitmap_tree_insert(left, &bitmap->xb_root);
+ xbitmap64_tree_insert(left, &bitmap->xb_root);
} else if (right) {
/* combine with right extent */
- xbitmap_tree_remove(right, &bitmap->xb_root);
+ xbitmap64_tree_remove(right, &bitmap->xb_root);
right->bn_start = start;
- xbitmap_tree_insert(right, &bitmap->xb_root);
+ xbitmap64_tree_insert(right, &bitmap->xb_root);
} else {
/* add an extent */
- left = kmalloc(sizeof(struct xbitmap_node), XCHK_GFP_FLAGS);
+ left = kmalloc(sizeof(struct xbitmap64_node), XCHK_GFP_FLAGS);
if (!left)
return -ENOMEM;
left->bn_start = start;
left->bn_last = last;
- xbitmap_tree_insert(left, &bitmap->xb_root);
+ xbitmap64_tree_insert(left, &bitmap->xb_root);
}
return 0;
@@ -174,21 +176,21 @@ xbitmap_set(
/* Free everything related to this bitmap. */
void
-xbitmap_destroy(
- struct xbitmap *bitmap)
+xbitmap64_destroy(
+ struct xbitmap64 *bitmap)
{
- struct xbitmap_node *bn;
+ struct xbitmap64_node *bn;
- while ((bn = xbitmap_tree_iter_first(&bitmap->xb_root, 0, -1ULL))) {
- xbitmap_tree_remove(bn, &bitmap->xb_root);
+ while ((bn = xbitmap64_tree_iter_first(&bitmap->xb_root, 0, -1ULL))) {
+ xbitmap64_tree_remove(bn, &bitmap->xb_root);
kfree(bn);
}
}
/* Set up a per-AG block bitmap. */
void
-xbitmap_init(
- struct xbitmap *bitmap)
+xbitmap64_init(
+ struct xbitmap64 *bitmap)
{
bitmap->xb_root = RB_ROOT_CACHED;
}
@@ -208,18 +210,18 @@ xbitmap_init(
* This is the logical equivalent of bitmap &= ~sub.
*/
int
-xbitmap_disunion(
- struct xbitmap *bitmap,
- struct xbitmap *sub)
+xbitmap64_disunion(
+ struct xbitmap64 *bitmap,
+ struct xbitmap64 *sub)
{
- struct xbitmap_node *bn;
+ struct xbitmap64_node *bn;
int error;
- if (xbitmap_empty(bitmap) || xbitmap_empty(sub))
+ if (xbitmap64_empty(bitmap) || xbitmap64_empty(sub))
return 0;
- for_each_xbitmap_extent(bn, sub) {
- error = xbitmap_clear(bitmap, bn->bn_start,
+ for_each_xbitmap64_extent(bn, sub) {
+ error = xbitmap64_clear(bitmap, bn->bn_start,
bn->bn_last - bn->bn_start + 1);
if (error)
return error;
@@ -228,88 +230,273 @@ xbitmap_disunion(
return 0;
}
+/* How many bits are set in this bitmap? */
+uint64_t
+xbitmap64_hweight(
+ struct xbitmap64 *bitmap)
+{
+ struct xbitmap64_node *bn;
+ uint64_t ret = 0;
+
+ for_each_xbitmap64_extent(bn, bitmap)
+ ret += bn->bn_last - bn->bn_start + 1;
+
+ return ret;
+}
+
+/* Call a function for every run of set bits in this bitmap. */
+int
+xbitmap64_walk(
+ struct xbitmap64 *bitmap,
+ xbitmap64_walk_fn fn,
+ void *priv)
+{
+ struct xbitmap64_node *bn;
+ int error = 0;
+
+ for_each_xbitmap64_extent(bn, bitmap) {
+ error = fn(bn->bn_start, bn->bn_last - bn->bn_start + 1, priv);
+ if (error)
+ break;
+ }
+
+ return error;
+}
+
+/* Does this bitmap have no bits set at all? */
+bool
+xbitmap64_empty(
+ struct xbitmap64 *bitmap)
+{
+ return bitmap->xb_root.rb_root.rb_node == NULL;
+}
+
+/* Is the start of the range set or clear? And for how long? */
+bool
+xbitmap64_test(
+ struct xbitmap64 *bitmap,
+ uint64_t start,
+ uint64_t *len)
+{
+ struct xbitmap64_node *bn;
+ uint64_t last = start + *len - 1;
+
+ bn = xbitmap64_tree_iter_first(&bitmap->xb_root, start, last);
+ if (!bn)
+ return false;
+ if (bn->bn_start <= start) {
+ if (bn->bn_last < last)
+ *len = bn->bn_last - start + 1;
+ return true;
+ }
+ *len = bn->bn_start - start;
+ return false;
+}
+
+/* u32 bitmap */
+
+struct xbitmap32_node {
+ struct rb_node bn_rbnode;
+
+ /* First set bit of this interval and subtree. */
+ uint32_t bn_start;
+
+ /* Last set bit of this interval. */
+ uint32_t bn_last;
+
+ /* Last set bit of this subtree. Do not touch this. */
+ uint32_t __bn_subtree_last;
+};
+
+/* Define our own interval tree type with uint32_t parameters. */
+
/*
- * Record all btree blocks seen while iterating all records of a btree.
- *
- * We know that the btree query_all function starts at the left edge and walks
- * towards the right edge of the tree. Therefore, we know that we can walk up
- * the btree cursor towards the root; if the pointer for a given level points
- * to the first record/key in that block, we haven't seen this block before;
- * and therefore we need to remember that we saw this block in the btree.
- *
- * So if our btree is:
- *
- * 4
- * / | \
- * 1 2 3
- *
- * Pretend for this example that each leaf block has 100 btree records. For
- * the first btree record, we'll observe that bc_levels[0].ptr == 1, so we
- * record that we saw block 1. Then we observe that bc_levels[1].ptr == 1, so
- * we record block 4. The list is [1, 4].
- *
- * For the second btree record, we see that bc_levels[0].ptr == 2, so we exit
- * the loop. The list remains [1, 4].
- *
- * For the 101st btree record, we've moved onto leaf block 2. Now
- * bc_levels[0].ptr == 1 again, so we record that we saw block 2. We see that
- * bc_levels[1].ptr == 2, so we exit the loop. The list is now [1, 4, 2].
- *
- * For the 102nd record, bc_levels[0].ptr == 2, so we continue.
- *
- * For the 201st record, we've moved on to leaf block 3.
- * bc_levels[0].ptr == 1, so we add 3 to the list. Now it is [1, 4, 2, 3].
- *
- * For the 300th record we just exit, with the list being [1, 4, 2, 3].
+ * These functions are defined by the INTERVAL_TREE_DEFINE macro, but we'll
+ * forward-declare them anyway for clarity.
*/
+static inline void
+xbitmap32_tree_insert(struct xbitmap32_node *node, struct rb_root_cached *root);
-/* Mark a btree block to the agblock bitmap. */
-STATIC int
-xagb_bitmap_visit_btblock(
- struct xfs_btree_cur *cur,
- int level,
- void *priv)
+static inline void
+xbitmap32_tree_remove(struct xbitmap32_node *node, struct rb_root_cached *root);
+
+static inline struct xbitmap32_node *
+xbitmap32_tree_iter_first(struct rb_root_cached *root, uint32_t start,
+ uint32_t last);
+
+static inline struct xbitmap32_node *
+xbitmap32_tree_iter_next(struct xbitmap32_node *node, uint32_t start,
+ uint32_t last);
+
+INTERVAL_TREE_DEFINE(struct xbitmap32_node, bn_rbnode, uint32_t,
+ __bn_subtree_last, START, LAST, static inline, xbitmap32_tree)
+
+/* Iterate each interval of a bitmap. Do not change the bitmap. */
+#define for_each_xbitmap32_extent(bn, bitmap) \
+ for ((bn) = rb_entry_safe(rb_first(&(bitmap)->xb_root.rb_root), \
+ struct xbitmap32_node, bn_rbnode); \
+ (bn) != NULL; \
+ (bn) = rb_entry_safe(rb_next(&(bn)->bn_rbnode), \
+ struct xbitmap32_node, bn_rbnode))
+
+/* Clear a range of this bitmap. */
+int
+xbitmap32_clear(
+ struct xbitmap32 *bitmap,
+ uint32_t start,
+ uint32_t len)
{
- struct xagb_bitmap *bitmap = priv;
- struct xfs_buf *bp;
- xfs_fsblock_t fsbno;
- xfs_agblock_t agbno;
+ struct xbitmap32_node *bn;
+ struct xbitmap32_node *new_bn;
+ uint32_t last = start + len - 1;
- xfs_btree_get_block(cur, level, &bp);
- if (!bp)
- return 0;
+ while ((bn = xbitmap32_tree_iter_first(&bitmap->xb_root, start, last))) {
+ if (bn->bn_start < start && bn->bn_last > last) {
+ uint32_t old_last = bn->bn_last;
- fsbno = XFS_DADDR_TO_FSB(cur->bc_mp, xfs_buf_daddr(bp));
- agbno = XFS_FSB_TO_AGBNO(cur->bc_mp, fsbno);
+ /* overlaps with the entire clearing range */
+ xbitmap32_tree_remove(bn, &bitmap->xb_root);
+ bn->bn_last = start - 1;
+ xbitmap32_tree_insert(bn, &bitmap->xb_root);
- return xagb_bitmap_set(bitmap, agbno, 1);
+ /* add an extent */
+ new_bn = kmalloc(sizeof(struct xbitmap32_node),
+ XCHK_GFP_FLAGS);
+ if (!new_bn)
+ return -ENOMEM;
+ new_bn->bn_start = last + 1;
+ new_bn->bn_last = old_last;
+ xbitmap32_tree_insert(new_bn, &bitmap->xb_root);
+ } else if (bn->bn_start < start) {
+ /* overlaps with the left side of the clearing range */
+ xbitmap32_tree_remove(bn, &bitmap->xb_root);
+ bn->bn_last = start - 1;
+ xbitmap32_tree_insert(bn, &bitmap->xb_root);
+ } else if (bn->bn_last > last) {
+ /* overlaps with the right side of the clearing range */
+ xbitmap32_tree_remove(bn, &bitmap->xb_root);
+ bn->bn_start = last + 1;
+ xbitmap32_tree_insert(bn, &bitmap->xb_root);
+ break;
+ } else {
+ /* in the middle of the clearing range */
+ xbitmap32_tree_remove(bn, &bitmap->xb_root);
+ kfree(bn);
+ }
+ }
+
+ return 0;
}
-/* Mark all (per-AG) btree blocks in the agblock bitmap. */
+/* Set a range of this bitmap. */
int
-xagb_bitmap_set_btblocks(
- struct xagb_bitmap *bitmap,
- struct xfs_btree_cur *cur)
+xbitmap32_set(
+ struct xbitmap32 *bitmap,
+ uint32_t start,
+ uint32_t len)
{
- return xfs_btree_visit_blocks(cur, xagb_bitmap_visit_btblock,
- XFS_BTREE_VISIT_ALL, bitmap);
+ struct xbitmap32_node *left;
+ struct xbitmap32_node *right;
+ uint32_t last = start + len - 1;
+ int error;
+
+ /* Is this whole range already set? */
+ left = xbitmap32_tree_iter_first(&bitmap->xb_root, start, last);
+ if (left && left->bn_start <= start && left->bn_last >= last)
+ return 0;
+
+ /* Clear out everything in the range we want to set. */
+ error = xbitmap32_clear(bitmap, start, len);
+ if (error)
+ return error;
+
+ /* Do we have a left-adjacent extent? */
+ left = xbitmap32_tree_iter_first(&bitmap->xb_root, start - 1, start - 1);
+ ASSERT(!left || left->bn_last + 1 == start);
+
+ /* Do we have a right-adjacent extent? */
+ right = xbitmap32_tree_iter_first(&bitmap->xb_root, last + 1, last + 1);
+ ASSERT(!right || right->bn_start == last + 1);
+
+ if (left && right) {
+ /* combine left and right adjacent extent */
+ xbitmap32_tree_remove(left, &bitmap->xb_root);
+ xbitmap32_tree_remove(right, &bitmap->xb_root);
+ left->bn_last = right->bn_last;
+ xbitmap32_tree_insert(left, &bitmap->xb_root);
+ kfree(right);
+ } else if (left) {
+ /* combine with left extent */
+ xbitmap32_tree_remove(left, &bitmap->xb_root);
+ left->bn_last = last;
+ xbitmap32_tree_insert(left, &bitmap->xb_root);
+ } else if (right) {
+ /* combine with right extent */
+ xbitmap32_tree_remove(right, &bitmap->xb_root);
+ right->bn_start = start;
+ xbitmap32_tree_insert(right, &bitmap->xb_root);
+ } else {
+ /* add an extent */
+ left = kmalloc(sizeof(struct xbitmap32_node), XCHK_GFP_FLAGS);
+ if (!left)
+ return -ENOMEM;
+ left->bn_start = start;
+ left->bn_last = last;
+ xbitmap32_tree_insert(left, &bitmap->xb_root);
+ }
+
+ return 0;
+}
+
+/* Free everything related to this bitmap. */
+void
+xbitmap32_destroy(
+ struct xbitmap32 *bitmap)
+{
+ struct xbitmap32_node *bn;
+
+ while ((bn = xbitmap32_tree_iter_first(&bitmap->xb_root, 0, -1U))) {
+ xbitmap32_tree_remove(bn, &bitmap->xb_root);
+ kfree(bn);
+ }
+}
+
+/* Set up a per-AG block bitmap. */
+void
+xbitmap32_init(
+ struct xbitmap32 *bitmap)
+{
+ bitmap->xb_root = RB_ROOT_CACHED;
}
/*
- * Record all the buffers pointed to by the btree cursor. Callers already
- * engaged in a btree walk should call this function to capture the list of
- * blocks going from the leaf towards the root.
+ * Remove all the blocks mentioned in @sub from the extents in @bitmap.
+ *
+ * The intent is that callers will iterate the rmapbt for all of its records
+ * for a given owner to generate @bitmap; and iterate all the blocks of the
+ * metadata structures that are not being rebuilt and have the same rmapbt
+ * owner to generate @sub. This routine subtracts all the extents
+ * mentioned in sub from all the extents linked in @bitmap, which leaves
+ * @bitmap as the list of blocks that are not accounted for, which we assume
+ * are the dead blocks of the old metadata structure. The blocks mentioned in
+ * @bitmap can be reaped.
+ *
+ * This is the logical equivalent of bitmap &= ~sub.
*/
int
-xagb_bitmap_set_btcur_path(
- struct xagb_bitmap *bitmap,
- struct xfs_btree_cur *cur)
+xbitmap32_disunion(
+ struct xbitmap32 *bitmap,
+ struct xbitmap32 *sub)
{
- int i;
+ struct xbitmap32_node *bn;
int error;
- for (i = 0; i < cur->bc_nlevels && cur->bc_levels[i].ptr == 1; i++) {
- error = xagb_bitmap_visit_btblock(cur, i, bitmap);
+ if (xbitmap32_empty(bitmap) || xbitmap32_empty(sub))
+ return 0;
+
+ for_each_xbitmap32_extent(bn, sub) {
+ error = xbitmap32_clear(bitmap, bn->bn_start,
+ bn->bn_last - bn->bn_start + 1);
if (error)
return error;
}
@@ -318,14 +505,14 @@ xagb_bitmap_set_btcur_path(
}
/* How many bits are set in this bitmap? */
-uint64_t
-xbitmap_hweight(
- struct xbitmap *bitmap)
+uint32_t
+xbitmap32_hweight(
+ struct xbitmap32 *bitmap)
{
- struct xbitmap_node *bn;
- uint64_t ret = 0;
+ struct xbitmap32_node *bn;
+ uint32_t ret = 0;
- for_each_xbitmap_extent(bn, bitmap)
+ for_each_xbitmap32_extent(bn, bitmap)
ret += bn->bn_last - bn->bn_start + 1;
return ret;
@@ -333,15 +520,15 @@ xbitmap_hweight(
/* Call a function for every run of set bits in this bitmap. */
int
-xbitmap_walk(
- struct xbitmap *bitmap,
- xbitmap_walk_fn fn,
+xbitmap32_walk(
+ struct xbitmap32 *bitmap,
+ xbitmap32_walk_fn fn,
void *priv)
{
- struct xbitmap_node *bn;
+ struct xbitmap32_node *bn;
int error = 0;
- for_each_xbitmap_extent(bn, bitmap) {
+ for_each_xbitmap32_extent(bn, bitmap) {
error = fn(bn->bn_start, bn->bn_last - bn->bn_start + 1, priv);
if (error)
break;
@@ -352,23 +539,23 @@ xbitmap_walk(
/* Does this bitmap have no bits set at all? */
bool
-xbitmap_empty(
- struct xbitmap *bitmap)
+xbitmap32_empty(
+ struct xbitmap32 *bitmap)
{
return bitmap->xb_root.rb_root.rb_node == NULL;
}
/* Is the start of the range set or clear? And for how long? */
bool
-xbitmap_test(
- struct xbitmap *bitmap,
- uint64_t start,
- uint64_t *len)
+xbitmap32_test(
+ struct xbitmap32 *bitmap,
+ uint32_t start,
+ uint32_t *len)
{
- struct xbitmap_node *bn;
- uint64_t last = start + *len - 1;
+ struct xbitmap32_node *bn;
+ uint32_t last = start + *len - 1;
- bn = xbitmap_tree_iter_first(&bitmap->xb_root, start, last);
+ bn = xbitmap32_tree_iter_first(&bitmap->xb_root, start, last);
if (!bn)
return false;
if (bn->bn_start <= start) {
diff --git a/fs/xfs/scrub/bitmap.h b/fs/xfs/scrub/bitmap.h
index 4fe58bad6734..2df8911606d6 100644
--- a/fs/xfs/scrub/bitmap.h
+++ b/fs/xfs/scrub/bitmap.h
@@ -6,17 +6,19 @@
#ifndef __XFS_SCRUB_BITMAP_H__
#define __XFS_SCRUB_BITMAP_H__
-struct xbitmap {
+/* u64 bitmap */
+
+struct xbitmap64 {
struct rb_root_cached xb_root;
};
-void xbitmap_init(struct xbitmap *bitmap);
-void xbitmap_destroy(struct xbitmap *bitmap);
+void xbitmap64_init(struct xbitmap64 *bitmap);
+void xbitmap64_destroy(struct xbitmap64 *bitmap);
-int xbitmap_clear(struct xbitmap *bitmap, uint64_t start, uint64_t len);
-int xbitmap_set(struct xbitmap *bitmap, uint64_t start, uint64_t len);
-int xbitmap_disunion(struct xbitmap *bitmap, struct xbitmap *sub);
-uint64_t xbitmap_hweight(struct xbitmap *bitmap);
+int xbitmap64_clear(struct xbitmap64 *bitmap, uint64_t start, uint64_t len);
+int xbitmap64_set(struct xbitmap64 *bitmap, uint64_t start, uint64_t len);
+int xbitmap64_disunion(struct xbitmap64 *bitmap, struct xbitmap64 *sub);
+uint64_t xbitmap64_hweight(struct xbitmap64 *bitmap);
/*
* Return codes for the bitmap iterator functions are 0 to continue iterating,
@@ -25,84 +27,39 @@ uint64_t xbitmap_hweight(struct xbitmap *bitmap);
* iteration, because neither bitmap iterator ever generates that error code on
* its own. Callers must not modify the bitmap while walking it.
*/
-typedef int (*xbitmap_walk_fn)(uint64_t start, uint64_t len, void *priv);
-int xbitmap_walk(struct xbitmap *bitmap, xbitmap_walk_fn fn,
+typedef int (*xbitmap64_walk_fn)(uint64_t start, uint64_t len, void *priv);
+int xbitmap64_walk(struct xbitmap64 *bitmap, xbitmap64_walk_fn fn,
void *priv);
-bool xbitmap_empty(struct xbitmap *bitmap);
-bool xbitmap_test(struct xbitmap *bitmap, uint64_t start, uint64_t *len);
+bool xbitmap64_empty(struct xbitmap64 *bitmap);
+bool xbitmap64_test(struct xbitmap64 *bitmap, uint64_t start, uint64_t *len);
-/* Bitmaps, but for type-checked for xfs_agblock_t */
+/* u32 bitmap */
-struct xagb_bitmap {
- struct xbitmap agbitmap;
+struct xbitmap32 {
+ struct rb_root_cached xb_root;
};
-static inline void xagb_bitmap_init(struct xagb_bitmap *bitmap)
-{
- xbitmap_init(&bitmap->agbitmap);
-}
-
-static inline void xagb_bitmap_destroy(struct xagb_bitmap *bitmap)
-{
- xbitmap_destroy(&bitmap->agbitmap);
-}
-
-static inline int xagb_bitmap_clear(struct xagb_bitmap *bitmap,
- xfs_agblock_t start, xfs_extlen_t len)
-{
- return xbitmap_clear(&bitmap->agbitmap, start, len);
-}
-static inline int xagb_bitmap_set(struct xagb_bitmap *bitmap,
- xfs_agblock_t start, xfs_extlen_t len)
-{
- return xbitmap_set(&bitmap->agbitmap, start, len);
-}
-
-static inline bool
-xagb_bitmap_test(
- struct xagb_bitmap *bitmap,
- xfs_agblock_t start,
- xfs_extlen_t *len)
-{
- uint64_t biglen = *len;
- bool ret;
-
- ret = xbitmap_test(&bitmap->agbitmap, start, &biglen);
-
- if (start + biglen >= UINT_MAX) {
- ASSERT(0);
- biglen = UINT_MAX - start;
- }
-
- *len = biglen;
- return ret;
-}
-
-static inline int xagb_bitmap_disunion(struct xagb_bitmap *bitmap,
- struct xagb_bitmap *sub)
-{
- return xbitmap_disunion(&bitmap->agbitmap, &sub->agbitmap);
-}
+void xbitmap32_init(struct xbitmap32 *bitmap);
+void xbitmap32_destroy(struct xbitmap32 *bitmap);
-static inline uint32_t xagb_bitmap_hweight(struct xagb_bitmap *bitmap)
-{
- return xbitmap_hweight(&bitmap->agbitmap);
-}
-static inline bool xagb_bitmap_empty(struct xagb_bitmap *bitmap)
-{
- return xbitmap_empty(&bitmap->agbitmap);
-}
+int xbitmap32_clear(struct xbitmap32 *bitmap, uint32_t start, uint32_t len);
+int xbitmap32_set(struct xbitmap32 *bitmap, uint32_t start, uint32_t len);
+int xbitmap32_disunion(struct xbitmap32 *bitmap, struct xbitmap32 *sub);
+uint32_t xbitmap32_hweight(struct xbitmap32 *bitmap);
-static inline int xagb_bitmap_walk(struct xagb_bitmap *bitmap,
- xbitmap_walk_fn fn, void *priv)
-{
- return xbitmap_walk(&bitmap->agbitmap, fn, priv);
-}
+/*
+ * Return codes for the bitmap iterator functions are 0 to continue iterating,
+ * and non-zero to stop iterating. Any non-zero value will be passed up to the
+ * iteration caller. The special value -ECANCELED can be used to stop
+ * iteration, because neither bitmap iterator ever generates that error code on
+ * its own. Callers must not modify the bitmap while walking it.
+ */
+typedef int (*xbitmap32_walk_fn)(uint32_t start, uint32_t len, void *priv);
+int xbitmap32_walk(struct xbitmap32 *bitmap, xbitmap32_walk_fn fn,
+ void *priv);
-int xagb_bitmap_set_btblocks(struct xagb_bitmap *bitmap,
- struct xfs_btree_cur *cur);
-int xagb_bitmap_set_btcur_path(struct xagb_bitmap *bitmap,
- struct xfs_btree_cur *cur);
+bool xbitmap32_empty(struct xbitmap32 *bitmap);
+bool xbitmap32_test(struct xbitmap32 *bitmap, uint32_t start, uint32_t *len);
#endif /* __XFS_SCRUB_BITMAP_H__ */
diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c
index 06d8c1996a33..b169cddde6da 100644
--- a/fs/xfs/scrub/bmap.c
+++ b/fs/xfs/scrub/bmap.c
@@ -19,9 +19,11 @@
#include "xfs_bmap_btree.h"
#include "xfs_rmap.h"
#include "xfs_rmap_btree.h"
+#include "xfs_health.h"
#include "scrub/scrub.h"
#include "scrub/common.h"
#include "scrub/btree.h"
+#include "scrub/health.h"
#include "xfs_ag.h"
/* Set us up with an inode's bmap. */
@@ -48,9 +50,18 @@ xchk_setup_inode_bmap(
if (S_ISREG(VFS_I(sc->ip)->i_mode) &&
sc->sm->sm_type != XFS_SCRUB_TYPE_BMBTA) {
struct address_space *mapping = VFS_I(sc->ip)->i_mapping;
+ bool is_repair = xchk_could_repair(sc);
xchk_ilock(sc, XFS_MMAPLOCK_EXCL);
+ /* Break all our leases, we're going to mess with things. */
+ if (is_repair) {
+ error = xfs_break_layouts(VFS_I(sc->ip),
+ &sc->ilock_flags, BREAK_WRITE);
+ if (error)
+ goto out;
+ }
+
inode_dio_wait(VFS_I(sc->ip));
/*
@@ -71,6 +82,15 @@ xchk_setup_inode_bmap(
error = filemap_fdatawait_keep_errors(mapping);
if (error && (error != -ENOSPC && error != -EIO))
goto out;
+
+ /* Drop the page cache if we're repairing block mappings. */
+ if (is_repair) {
+ error = invalidate_inode_pages2(
+ VFS_I(sc->ip)->i_mapping);
+ if (error)
+ goto out;
+ }
+
}
/* Got the inode, lock it and we're ready to go. */
@@ -78,6 +98,10 @@ xchk_setup_inode_bmap(
if (error)
goto out;
+ error = xchk_ino_dqattach(sc);
+ if (error)
+ goto out;
+
xchk_ilock(sc, XFS_ILOCK_EXCL);
out:
/* scrub teardown will unlock and release the inode */
@@ -633,6 +657,82 @@ xchk_bmap_check_ag_rmaps(
}
/*
+ * Decide if we want to scan the reverse mappings to determine if the attr
+ * fork /really/ has zero space mappings.
+ */
+STATIC bool
+xchk_bmap_check_empty_attrfork(
+ struct xfs_inode *ip)
+{
+ struct xfs_ifork *ifp = &ip->i_af;
+
+ /*
+ * If the dinode repair found a bad attr fork, it will reset the fork
+ * to extents format with zero records and wait for the this scrubber
+ * to reconstruct the block mappings. If the fork is not in this
+ * state, then the fork cannot have been zapped.
+ */
+ if (ifp->if_format != XFS_DINODE_FMT_EXTENTS || ifp->if_nextents != 0)
+ return false;
+
+ /*
+ * Files can have an attr fork in EXTENTS format with zero records for
+ * several reasons:
+ *
+ * a) an attr set created a fork but ran out of space
+ * b) attr replace deleted an old attr but failed during the set step
+ * c) the data fork was in btree format when all attrs were deleted, so
+ * the fork was left in place
+ * d) the inode repair code zapped the fork
+ *
+ * Only in case (d) do we want to scan the rmapbt to see if we need to
+ * rebuild the attr fork. The fork zap code clears all DAC permission
+ * bits and zeroes the uid and gid, so avoid the scan if any of those
+ * three conditions are not met.
+ */
+ if ((VFS_I(ip)->i_mode & 0777) != 0)
+ return false;
+ if (!uid_eq(VFS_I(ip)->i_uid, GLOBAL_ROOT_UID))
+ return false;
+ if (!gid_eq(VFS_I(ip)->i_gid, GLOBAL_ROOT_GID))
+ return false;
+
+ return true;
+}
+
+/*
+ * Decide if we want to scan the reverse mappings to determine if the data
+ * fork /really/ has zero space mappings.
+ */
+STATIC bool
+xchk_bmap_check_empty_datafork(
+ struct xfs_inode *ip)
+{
+ struct xfs_ifork *ifp = &ip->i_df;
+
+ /* Don't support realtime rmap checks yet. */
+ if (XFS_IS_REALTIME_INODE(ip))
+ return false;
+
+ /*
+ * If the dinode repair found a bad data fork, it will reset the fork
+ * to extents format with zero records and wait for the this scrubber
+ * to reconstruct the block mappings. If the fork is not in this
+ * state, then the fork cannot have been zapped.
+ */
+ if (ifp->if_format != XFS_DINODE_FMT_EXTENTS || ifp->if_nextents != 0)
+ return false;
+
+ /*
+ * If we encounter an empty data fork along with evidence that the fork
+ * might not really be empty, we need to scan the reverse mappings to
+ * decide if we're going to rebuild the fork. Data forks with nonzero
+ * file size are scanned.
+ */
+ return i_size_read(VFS_I(ip)) != 0;
+}
+
+/*
* Decide if we want to walk every rmap btree in the fs to make sure that each
* rmap for this file fork has corresponding bmbt entries.
*/
@@ -641,7 +741,6 @@ xchk_bmap_want_check_rmaps(
struct xchk_bmap_info *info)
{
struct xfs_scrub *sc = info->sc;
- struct xfs_ifork *ifp;
if (!xfs_has_rmapbt(sc->mp))
return false;
@@ -650,28 +749,10 @@ xchk_bmap_want_check_rmaps(
if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
return false;
- /* Don't support realtime rmap checks yet. */
- if (info->is_rt)
- return false;
-
- /*
- * The inode repair code zaps broken inode forks by resetting them back
- * to EXTENTS format and zero extent records. If we encounter a fork
- * in this state along with evidence that the fork isn't supposed to be
- * empty, we need to scan the reverse mappings to decide if we're going
- * to rebuild the fork. Data forks with nonzero file size are scanned.
- * xattr forks are never empty of content, so they are always scanned.
- */
- ifp = xfs_ifork_ptr(sc->ip, info->whichfork);
- if (ifp->if_format == XFS_DINODE_FMT_EXTENTS && ifp->if_nextents == 0) {
- if (info->whichfork == XFS_DATA_FORK &&
- i_size_read(VFS_I(sc->ip)) == 0)
- return false;
-
- return true;
- }
+ if (info->whichfork == XFS_ATTR_FORK)
+ return xchk_bmap_check_empty_attrfork(sc->ip);
- return false;
+ return xchk_bmap_check_empty_datafork(sc->ip);
}
/* Make sure each rmap has a corresponding bmbt entry. */
@@ -939,7 +1020,20 @@ int
xchk_bmap_data(
struct xfs_scrub *sc)
{
- return xchk_bmap(sc, XFS_DATA_FORK);
+ int error;
+
+ if (xchk_file_looks_zapped(sc, XFS_SICK_INO_BMBTD_ZAPPED)) {
+ xchk_ino_set_corrupt(sc, sc->ip->i_ino);
+ return 0;
+ }
+
+ error = xchk_bmap(sc, XFS_DATA_FORK);
+ if (error)
+ return error;
+
+ /* If the data fork is clean, it is clearly not zapped. */
+ xchk_mark_healthy_if_clean(sc, XFS_SICK_INO_BMBTD_ZAPPED);
+ return 0;
}
/* Scrub an inode's attr fork. */
@@ -947,7 +1041,27 @@ int
xchk_bmap_attr(
struct xfs_scrub *sc)
{
- return xchk_bmap(sc, XFS_ATTR_FORK);
+ int error;
+
+ /*
+ * If the attr fork has been zapped, it's possible that forkoff was
+ * reset to zero and hence sc->ip->i_afp is NULL. We don't want the
+ * NULL ifp check in xchk_bmap to conclude that the attr fork is ok,
+ * so short circuit that logic by setting the corruption flag and
+ * returning immediately.
+ */
+ if (xchk_file_looks_zapped(sc, XFS_SICK_INO_BMBTA_ZAPPED)) {
+ xchk_ino_set_corrupt(sc, sc->ip->i_ino);
+ return 0;
+ }
+
+ error = xchk_bmap(sc, XFS_ATTR_FORK);
+ if (error)
+ return error;
+
+ /* If the attr fork is clean, it is clearly not zapped. */
+ xchk_mark_healthy_if_clean(sc, XFS_SICK_INO_BMBTA_ZAPPED);
+ return 0;
}
/* Scrub an inode's CoW fork. */
diff --git a/fs/xfs/scrub/bmap_repair.c b/fs/xfs/scrub/bmap_repair.c
new file mode 100644
index 000000000000..a4bb89fdd510
--- /dev/null
+++ b/fs/xfs/scrub/bmap_repair.c
@@ -0,0 +1,867 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2018-2023 Oracle. All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_defer.h"
+#include "xfs_btree.h"
+#include "xfs_btree_staging.h"
+#include "xfs_bit.h"
+#include "xfs_log_format.h"
+#include "xfs_trans.h"
+#include "xfs_sb.h"
+#include "xfs_inode.h"
+#include "xfs_inode_fork.h"
+#include "xfs_alloc.h"
+#include "xfs_rtalloc.h"
+#include "xfs_bmap.h"
+#include "xfs_bmap_util.h"
+#include "xfs_bmap_btree.h"
+#include "xfs_rmap.h"
+#include "xfs_rmap_btree.h"
+#include "xfs_refcount.h"
+#include "xfs_quota.h"
+#include "xfs_ialloc.h"
+#include "xfs_ag.h"
+#include "xfs_reflink.h"
+#include "scrub/xfs_scrub.h"
+#include "scrub/scrub.h"
+#include "scrub/common.h"
+#include "scrub/btree.h"
+#include "scrub/trace.h"
+#include "scrub/repair.h"
+#include "scrub/bitmap.h"
+#include "scrub/fsb_bitmap.h"
+#include "scrub/xfile.h"
+#include "scrub/xfarray.h"
+#include "scrub/newbt.h"
+#include "scrub/reap.h"
+
+/*
+ * Inode Fork Block Mapping (BMBT) Repair
+ * ======================================
+ *
+ * Gather all the rmap records for the inode and fork we're fixing, reset the
+ * incore fork, then recreate the btree.
+ */
+
+enum reflink_scan_state {
+ RLS_IRRELEVANT = -1, /* not applicable to this file */
+ RLS_UNKNOWN, /* shared extent scans required */
+ RLS_SET_IFLAG, /* iflag must be set */
+};
+
+struct xrep_bmap {
+ /* Old bmbt blocks */
+ struct xfsb_bitmap old_bmbt_blocks;
+
+ /* New fork. */
+ struct xrep_newbt new_bmapbt;
+
+ /* List of new bmap records. */
+ struct xfarray *bmap_records;
+
+ struct xfs_scrub *sc;
+
+ /* How many blocks did we find allocated to this file? */
+ xfs_rfsblock_t nblocks;
+
+ /* How many bmbt blocks did we find for this fork? */
+ xfs_rfsblock_t old_bmbt_block_count;
+
+ /* get_records()'s position in the free space record array. */
+ xfarray_idx_t array_cur;
+
+ /* How many real (non-hole, non-delalloc) mappings do we have? */
+ uint64_t real_mappings;
+
+ /* Which fork are we fixing? */
+ int whichfork;
+
+ /* What d the REFLINK flag be set when the repair is over? */
+ enum reflink_scan_state reflink_scan;
+
+ /* Do we allow unwritten extents? */
+ bool allow_unwritten;
+};
+
+/* Is this space extent shared? Flag the inode if it is. */
+STATIC int
+xrep_bmap_discover_shared(
+ struct xrep_bmap *rb,
+ xfs_fsblock_t startblock,
+ xfs_filblks_t blockcount)
+{
+ struct xfs_scrub *sc = rb->sc;
+ xfs_agblock_t agbno;
+ xfs_agblock_t fbno;
+ xfs_extlen_t flen;
+ int error;
+
+ agbno = XFS_FSB_TO_AGBNO(sc->mp, startblock);
+ error = xfs_refcount_find_shared(sc->sa.refc_cur, agbno, blockcount,
+ &fbno, &flen, false);
+ if (error)
+ return error;
+
+ if (fbno != NULLAGBLOCK)
+ rb->reflink_scan = RLS_SET_IFLAG;
+
+ return 0;
+}
+
+/* Remember this reverse-mapping as a series of bmap records. */
+STATIC int
+xrep_bmap_from_rmap(
+ struct xrep_bmap *rb,
+ xfs_fileoff_t startoff,
+ xfs_fsblock_t startblock,
+ xfs_filblks_t blockcount,
+ bool unwritten)
+{
+ struct xfs_bmbt_irec irec = {
+ .br_startoff = startoff,
+ .br_startblock = startblock,
+ .br_state = unwritten ? XFS_EXT_UNWRITTEN : XFS_EXT_NORM,
+ };
+ struct xfs_bmbt_rec rbe;
+ struct xfs_scrub *sc = rb->sc;
+ int error = 0;
+
+ /*
+ * If we're repairing the data fork of a non-reflinked regular file on
+ * a reflink filesystem, we need to figure out if this space extent is
+ * shared.
+ */
+ if (rb->reflink_scan == RLS_UNKNOWN && !unwritten) {
+ error = xrep_bmap_discover_shared(rb, startblock, blockcount);
+ if (error)
+ return error;
+ }
+
+ do {
+ xfs_failaddr_t fa;
+
+ irec.br_blockcount = min_t(xfs_filblks_t, blockcount,
+ XFS_MAX_BMBT_EXTLEN);
+
+ fa = xfs_bmap_validate_extent(sc->ip, rb->whichfork, &irec);
+ if (fa)
+ return -EFSCORRUPTED;
+
+ xfs_bmbt_disk_set_all(&rbe, &irec);
+
+ trace_xrep_bmap_found(sc->ip, rb->whichfork, &irec);
+
+ if (xchk_should_terminate(sc, &error))
+ return error;
+
+ error = xfarray_append(rb->bmap_records, &rbe);
+ if (error)
+ return error;
+
+ rb->real_mappings++;
+
+ irec.br_startblock += irec.br_blockcount;
+ irec.br_startoff += irec.br_blockcount;
+ blockcount -= irec.br_blockcount;
+ } while (blockcount > 0);
+
+ return 0;
+}
+
+/* Check for any obvious errors or conflicts in the file mapping. */
+STATIC int
+xrep_bmap_check_fork_rmap(
+ struct xrep_bmap *rb,
+ struct xfs_btree_cur *cur,
+ const struct xfs_rmap_irec *rec)
+{
+ struct xfs_scrub *sc = rb->sc;
+ enum xbtree_recpacking outcome;
+ int error;
+
+ /*
+ * Data extents for rt files are never stored on the data device, but
+ * everything else (xattrs, bmbt blocks) can be.
+ */
+ if (XFS_IS_REALTIME_INODE(sc->ip) &&
+ !(rec->rm_flags & (XFS_RMAP_ATTR_FORK | XFS_RMAP_BMBT_BLOCK)))
+ return -EFSCORRUPTED;
+
+ /* Check that this is within the AG. */
+ if (!xfs_verify_agbext(cur->bc_ag.pag, rec->rm_startblock,
+ rec->rm_blockcount))
+ return -EFSCORRUPTED;
+
+ /* Check the file offset range. */
+ if (!(rec->rm_flags & XFS_RMAP_BMBT_BLOCK) &&
+ !xfs_verify_fileext(sc->mp, rec->rm_offset, rec->rm_blockcount))
+ return -EFSCORRUPTED;
+
+ /* No contradictory flags. */
+ if ((rec->rm_flags & (XFS_RMAP_ATTR_FORK | XFS_RMAP_BMBT_BLOCK)) &&
+ (rec->rm_flags & XFS_RMAP_UNWRITTEN))
+ return -EFSCORRUPTED;
+
+ /* Make sure this isn't free space. */
+ error = xfs_alloc_has_records(sc->sa.bno_cur, rec->rm_startblock,
+ rec->rm_blockcount, &outcome);
+ if (error)
+ return error;
+ if (outcome != XBTREE_RECPACKING_EMPTY)
+ return -EFSCORRUPTED;
+
+ /* Must not be an inode chunk. */
+ error = xfs_ialloc_has_inodes_at_extent(sc->sa.ino_cur,
+ rec->rm_startblock, rec->rm_blockcount, &outcome);
+ if (error)
+ return error;
+ if (outcome != XBTREE_RECPACKING_EMPTY)
+ return -EFSCORRUPTED;
+
+ return 0;
+}
+
+/* Record extents that belong to this inode's fork. */
+STATIC int
+xrep_bmap_walk_rmap(
+ struct xfs_btree_cur *cur,
+ const struct xfs_rmap_irec *rec,
+ void *priv)
+{
+ struct xrep_bmap *rb = priv;
+ struct xfs_mount *mp = cur->bc_mp;
+ xfs_fsblock_t fsbno;
+ int error = 0;
+
+ if (xchk_should_terminate(rb->sc, &error))
+ return error;
+
+ if (rec->rm_owner != rb->sc->ip->i_ino)
+ return 0;
+
+ error = xrep_bmap_check_fork_rmap(rb, cur, rec);
+ if (error)
+ return error;
+
+ /*
+ * Record all blocks allocated to this file even if the extent isn't
+ * for the fork we're rebuilding so that we can reset di_nblocks later.
+ */
+ rb->nblocks += rec->rm_blockcount;
+
+ /* If this rmap isn't for the fork we want, we're done. */
+ if (rb->whichfork == XFS_DATA_FORK &&
+ (rec->rm_flags & XFS_RMAP_ATTR_FORK))
+ return 0;
+ if (rb->whichfork == XFS_ATTR_FORK &&
+ !(rec->rm_flags & XFS_RMAP_ATTR_FORK))
+ return 0;
+
+ /* Reject unwritten extents if we don't allow those. */
+ if ((rec->rm_flags & XFS_RMAP_UNWRITTEN) && !rb->allow_unwritten)
+ return -EFSCORRUPTED;
+
+ fsbno = XFS_AGB_TO_FSB(mp, cur->bc_ag.pag->pag_agno,
+ rec->rm_startblock);
+
+ if (rec->rm_flags & XFS_RMAP_BMBT_BLOCK) {
+ rb->old_bmbt_block_count += rec->rm_blockcount;
+ return xfsb_bitmap_set(&rb->old_bmbt_blocks, fsbno,
+ rec->rm_blockcount);
+ }
+
+ return xrep_bmap_from_rmap(rb, rec->rm_offset, fsbno,
+ rec->rm_blockcount,
+ rec->rm_flags & XFS_RMAP_UNWRITTEN);
+}
+
+/*
+ * Compare two block mapping records. We want to sort in order of increasing
+ * file offset.
+ */
+static int
+xrep_bmap_extent_cmp(
+ const void *a,
+ const void *b)
+{
+ const struct xfs_bmbt_rec *ba = a;
+ const struct xfs_bmbt_rec *bb = b;
+ xfs_fileoff_t ao = xfs_bmbt_disk_get_startoff(ba);
+ xfs_fileoff_t bo = xfs_bmbt_disk_get_startoff(bb);
+
+ if (ao > bo)
+ return 1;
+ else if (ao < bo)
+ return -1;
+ return 0;
+}
+
+/*
+ * Sort the bmap extents by fork offset or else the records will be in the
+ * wrong order. Ensure there are no overlaps in the file offset ranges.
+ */
+STATIC int
+xrep_bmap_sort_records(
+ struct xrep_bmap *rb)
+{
+ struct xfs_bmbt_irec irec;
+ xfs_fileoff_t next_off = 0;
+ xfarray_idx_t array_cur;
+ int error;
+
+ error = xfarray_sort(rb->bmap_records, xrep_bmap_extent_cmp,
+ XFARRAY_SORT_KILLABLE);
+ if (error)
+ return error;
+
+ foreach_xfarray_idx(rb->bmap_records, array_cur) {
+ struct xfs_bmbt_rec rec;
+
+ if (xchk_should_terminate(rb->sc, &error))
+ return error;
+
+ error = xfarray_load(rb->bmap_records, array_cur, &rec);
+ if (error)
+ return error;
+
+ xfs_bmbt_disk_get_all(&rec, &irec);
+
+ if (irec.br_startoff < next_off)
+ return -EFSCORRUPTED;
+
+ next_off = irec.br_startoff + irec.br_blockcount;
+ }
+
+ return 0;
+}
+
+/* Scan one AG for reverse mappings that we can turn into extent maps. */
+STATIC int
+xrep_bmap_scan_ag(
+ struct xrep_bmap *rb,
+ struct xfs_perag *pag)
+{
+ struct xfs_scrub *sc = rb->sc;
+ int error;
+
+ error = xrep_ag_init(sc, pag, &sc->sa);
+ if (error)
+ return error;
+
+ error = xfs_rmap_query_all(sc->sa.rmap_cur, xrep_bmap_walk_rmap, rb);
+ xchk_ag_free(sc, &sc->sa);
+ return error;
+}
+
+/* Find the delalloc extents from the old incore extent tree. */
+STATIC int
+xrep_bmap_find_delalloc(
+ struct xrep_bmap *rb)
+{
+ struct xfs_bmbt_irec irec;
+ struct xfs_iext_cursor icur;
+ struct xfs_bmbt_rec rbe;
+ struct xfs_inode *ip = rb->sc->ip;
+ struct xfs_ifork *ifp = xfs_ifork_ptr(ip, rb->whichfork);
+ int error = 0;
+
+ /*
+ * Skip this scan if we don't expect to find delayed allocation
+ * reservations in this fork.
+ */
+ if (rb->whichfork == XFS_ATTR_FORK || ip->i_delayed_blks == 0)
+ return 0;
+
+ for_each_xfs_iext(ifp, &icur, &irec) {
+ if (!isnullstartblock(irec.br_startblock))
+ continue;
+
+ xfs_bmbt_disk_set_all(&rbe, &irec);
+
+ trace_xrep_bmap_found(ip, rb->whichfork, &irec);
+
+ if (xchk_should_terminate(rb->sc, &error))
+ return error;
+
+ error = xfarray_append(rb->bmap_records, &rbe);
+ if (error)
+ return error;
+ }
+
+ return 0;
+}
+
+/*
+ * Collect block mappings for this fork of this inode and decide if we have
+ * enough space to rebuild. Caller is responsible for cleaning up the list if
+ * anything goes wrong.
+ */
+STATIC int
+xrep_bmap_find_mappings(
+ struct xrep_bmap *rb)
+{
+ struct xfs_scrub *sc = rb->sc;
+ struct xfs_perag *pag;
+ xfs_agnumber_t agno;
+ int error = 0;
+
+ /* Iterate the rmaps for extents. */
+ for_each_perag(sc->mp, agno, pag) {
+ error = xrep_bmap_scan_ag(rb, pag);
+ if (error) {
+ xfs_perag_rele(pag);
+ return error;
+ }
+ }
+
+ return xrep_bmap_find_delalloc(rb);
+}
+
+/* Retrieve real extent mappings for bulk loading the bmap btree. */
+STATIC int
+xrep_bmap_get_records(
+ struct xfs_btree_cur *cur,
+ unsigned int idx,
+ struct xfs_btree_block *block,
+ unsigned int nr_wanted,
+ void *priv)
+{
+ struct xfs_bmbt_rec rec;
+ struct xfs_bmbt_irec *irec = &cur->bc_rec.b;
+ struct xrep_bmap *rb = priv;
+ union xfs_btree_rec *block_rec;
+ unsigned int loaded;
+ int error;
+
+ for (loaded = 0; loaded < nr_wanted; loaded++, idx++) {
+ do {
+ error = xfarray_load(rb->bmap_records, rb->array_cur++,
+ &rec);
+ if (error)
+ return error;
+
+ xfs_bmbt_disk_get_all(&rec, irec);
+ } while (isnullstartblock(irec->br_startblock));
+
+ block_rec = xfs_btree_rec_addr(cur, idx, block);
+ cur->bc_ops->init_rec_from_cur(cur, block_rec);
+ }
+
+ return loaded;
+}
+
+/* Feed one of the new btree blocks to the bulk loader. */
+STATIC int
+xrep_bmap_claim_block(
+ struct xfs_btree_cur *cur,
+ union xfs_btree_ptr *ptr,
+ void *priv)
+{
+ struct xrep_bmap *rb = priv;
+
+ return xrep_newbt_claim_block(cur, &rb->new_bmapbt, ptr);
+}
+
+/* Figure out how much space we need to create the incore btree root block. */
+STATIC size_t
+xrep_bmap_iroot_size(
+ struct xfs_btree_cur *cur,
+ unsigned int level,
+ unsigned int nr_this_level,
+ void *priv)
+{
+ ASSERT(level > 0);
+
+ return XFS_BMAP_BROOT_SPACE_CALC(cur->bc_mp, nr_this_level);
+}
+
+/* Update the inode counters. */
+STATIC int
+xrep_bmap_reset_counters(
+ struct xrep_bmap *rb)
+{
+ struct xfs_scrub *sc = rb->sc;
+ struct xbtree_ifakeroot *ifake = &rb->new_bmapbt.ifake;
+ int64_t delta;
+
+ if (rb->reflink_scan == RLS_SET_IFLAG)
+ sc->ip->i_diflags2 |= XFS_DIFLAG2_REFLINK;
+
+ /*
+ * Update the inode block counts to reflect the extents we found in the
+ * rmapbt.
+ */
+ delta = ifake->if_blocks - rb->old_bmbt_block_count;
+ sc->ip->i_nblocks = rb->nblocks + delta;
+ xfs_trans_log_inode(sc->tp, sc->ip, XFS_ILOG_CORE);
+
+ /*
+ * Adjust the quota counts by the difference in size between the old
+ * and new bmbt.
+ */
+ xfs_trans_mod_dquot_byino(sc->tp, sc->ip, XFS_TRANS_DQ_BCOUNT, delta);
+ return 0;
+}
+
+/*
+ * Create a new iext tree and load it with block mappings. If the inode is
+ * in extents format, that's all we need to do to commit the new mappings.
+ * If it is in btree format, this takes care of preloading the incore tree.
+ */
+STATIC int
+xrep_bmap_extents_load(
+ struct xrep_bmap *rb)
+{
+ struct xfs_iext_cursor icur;
+ struct xfs_bmbt_irec irec;
+ struct xfs_ifork *ifp = rb->new_bmapbt.ifake.if_fork;
+ xfarray_idx_t array_cur;
+ int error;
+
+ ASSERT(ifp->if_bytes == 0);
+
+ /* Add all the mappings (incl. delalloc) to the incore extent tree. */
+ xfs_iext_first(ifp, &icur);
+ foreach_xfarray_idx(rb->bmap_records, array_cur) {
+ struct xfs_bmbt_rec rec;
+
+ error = xfarray_load(rb->bmap_records, array_cur, &rec);
+ if (error)
+ return error;
+
+ xfs_bmbt_disk_get_all(&rec, &irec);
+
+ xfs_iext_insert_raw(ifp, &icur, &irec);
+ if (!isnullstartblock(irec.br_startblock))
+ ifp->if_nextents++;
+
+ xfs_iext_next(ifp, &icur);
+ }
+
+ return xrep_ino_ensure_extent_count(rb->sc, rb->whichfork,
+ ifp->if_nextents);
+}
+
+/*
+ * Reserve new btree blocks, bulk load the bmap records into the ondisk btree,
+ * and load the incore extent tree.
+ */
+STATIC int
+xrep_bmap_btree_load(
+ struct xrep_bmap *rb,
+ struct xfs_btree_cur *bmap_cur)
+{
+ struct xfs_scrub *sc = rb->sc;
+ int error;
+
+ /* Compute how many blocks we'll need. */
+ error = xfs_btree_bload_compute_geometry(bmap_cur,
+ &rb->new_bmapbt.bload, rb->real_mappings);
+ if (error)
+ return error;
+
+ /* Last chance to abort before we start committing fixes. */
+ if (xchk_should_terminate(sc, &error))
+ return error;
+
+ /*
+ * Guess how many blocks we're going to need to rebuild an entire bmap
+ * from the number of extents we found, and pump up our transaction to
+ * have sufficient block reservation. We're allowed to exceed file
+ * quota to repair inconsistent metadata.
+ */
+ error = xfs_trans_reserve_more_inode(sc->tp, sc->ip,
+ rb->new_bmapbt.bload.nr_blocks, 0, true);
+ if (error)
+ return error;
+
+ /* Reserve the space we'll need for the new btree. */
+ error = xrep_newbt_alloc_blocks(&rb->new_bmapbt,
+ rb->new_bmapbt.bload.nr_blocks);
+ if (error)
+ return error;
+
+ /* Add all observed bmap records. */
+ rb->array_cur = XFARRAY_CURSOR_INIT;
+ error = xfs_btree_bload(bmap_cur, &rb->new_bmapbt.bload, rb);
+ if (error)
+ return error;
+
+ /*
+ * Load the new bmap records into the new incore extent tree to
+ * preserve delalloc reservations for regular files. The directory
+ * code loads the extent tree during xfs_dir_open and assumes
+ * thereafter that it remains loaded, so we must not violate that
+ * assumption.
+ */
+ return xrep_bmap_extents_load(rb);
+}
+
+/*
+ * Use the collected bmap information to stage a new bmap fork. If this is
+ * successful we'll return with the new fork information logged to the repair
+ * transaction but not yet committed. The caller must ensure that the inode
+ * is joined to the transaction; the inode will be joined to a clean
+ * transaction when the function returns.
+ */
+STATIC int
+xrep_bmap_build_new_fork(
+ struct xrep_bmap *rb)
+{
+ struct xfs_owner_info oinfo;
+ struct xfs_scrub *sc = rb->sc;
+ struct xfs_btree_cur *bmap_cur;
+ struct xbtree_ifakeroot *ifake = &rb->new_bmapbt.ifake;
+ int error;
+
+ error = xrep_bmap_sort_records(rb);
+ if (error)
+ return error;
+
+ /*
+ * Prepare to construct the new fork by initializing the new btree
+ * structure and creating a fake ifork in the ifakeroot structure.
+ */
+ xfs_rmap_ino_bmbt_owner(&oinfo, sc->ip->i_ino, rb->whichfork);
+ error = xrep_newbt_init_inode(&rb->new_bmapbt, sc, rb->whichfork,
+ &oinfo);
+ if (error)
+ return error;
+
+ rb->new_bmapbt.bload.get_records = xrep_bmap_get_records;
+ rb->new_bmapbt.bload.claim_block = xrep_bmap_claim_block;
+ rb->new_bmapbt.bload.iroot_size = xrep_bmap_iroot_size;
+ bmap_cur = xfs_bmbt_stage_cursor(sc->mp, sc->ip, ifake);
+
+ /*
+ * Figure out the size and format of the new fork, then fill it with
+ * all the bmap records we've found. Join the inode to the transaction
+ * so that we can roll the transaction while holding the inode locked.
+ */
+ if (rb->real_mappings <= XFS_IFORK_MAXEXT(sc->ip, rb->whichfork)) {
+ ifake->if_fork->if_format = XFS_DINODE_FMT_EXTENTS;
+ error = xrep_bmap_extents_load(rb);
+ } else {
+ ifake->if_fork->if_format = XFS_DINODE_FMT_BTREE;
+ error = xrep_bmap_btree_load(rb, bmap_cur);
+ }
+ if (error)
+ goto err_cur;
+
+ /*
+ * Install the new fork in the inode. After this point the old mapping
+ * data are no longer accessible and the new tree is live. We delete
+ * the cursor immediately after committing the staged root because the
+ * staged fork might be in extents format.
+ */
+ xfs_bmbt_commit_staged_btree(bmap_cur, sc->tp, rb->whichfork);
+ xfs_btree_del_cursor(bmap_cur, 0);
+
+ /* Reset the inode counters now that we've changed the fork. */
+ error = xrep_bmap_reset_counters(rb);
+ if (error)
+ goto err_newbt;
+
+ /* Dispose of any unused blocks and the accounting information. */
+ error = xrep_newbt_commit(&rb->new_bmapbt);
+ if (error)
+ return error;
+
+ return xrep_roll_trans(sc);
+
+err_cur:
+ if (bmap_cur)
+ xfs_btree_del_cursor(bmap_cur, error);
+err_newbt:
+ xrep_newbt_cancel(&rb->new_bmapbt);
+ return error;
+}
+
+/*
+ * Now that we've logged the new inode btree, invalidate all of the old blocks
+ * and free them, if there were any.
+ */
+STATIC int
+xrep_bmap_remove_old_tree(
+ struct xrep_bmap *rb)
+{
+ struct xfs_scrub *sc = rb->sc;
+ struct xfs_owner_info oinfo;
+
+ /* Free the old bmbt blocks if they're not in use. */
+ xfs_rmap_ino_bmbt_owner(&oinfo, sc->ip->i_ino, rb->whichfork);
+ return xrep_reap_fsblocks(sc, &rb->old_bmbt_blocks, &oinfo);
+}
+
+/* Check for garbage inputs. Returns -ECANCELED if there's nothing to do. */
+STATIC int
+xrep_bmap_check_inputs(
+ struct xfs_scrub *sc,
+ int whichfork)
+{
+ struct xfs_ifork *ifp = xfs_ifork_ptr(sc->ip, whichfork);
+
+ ASSERT(whichfork == XFS_DATA_FORK || whichfork == XFS_ATTR_FORK);
+
+ if (!xfs_has_rmapbt(sc->mp))
+ return -EOPNOTSUPP;
+
+ /* No fork means nothing to rebuild. */
+ if (!ifp)
+ return -ECANCELED;
+
+ /*
+ * We only know how to repair extent mappings, which is to say that we
+ * only support extents and btree fork format. Repairs to a local
+ * format fork require a higher level repair function, so we do not
+ * have any work to do here.
+ */
+ switch (ifp->if_format) {
+ case XFS_DINODE_FMT_DEV:
+ case XFS_DINODE_FMT_LOCAL:
+ case XFS_DINODE_FMT_UUID:
+ return -ECANCELED;
+ case XFS_DINODE_FMT_EXTENTS:
+ case XFS_DINODE_FMT_BTREE:
+ break;
+ default:
+ return -EFSCORRUPTED;
+ }
+
+ if (whichfork == XFS_ATTR_FORK)
+ return 0;
+
+ /* Only files, symlinks, and directories get to have data forks. */
+ switch (VFS_I(sc->ip)->i_mode & S_IFMT) {
+ case S_IFREG:
+ case S_IFDIR:
+ case S_IFLNK:
+ /* ok */
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ /* Don't know how to rebuild realtime data forks. */
+ if (XFS_IS_REALTIME_INODE(sc->ip))
+ return -EOPNOTSUPP;
+
+ return 0;
+}
+
+/* Set up the initial state of the reflink scan. */
+static inline enum reflink_scan_state
+xrep_bmap_init_reflink_scan(
+ struct xfs_scrub *sc,
+ int whichfork)
+{
+ /* cannot share on non-reflink filesystem */
+ if (!xfs_has_reflink(sc->mp))
+ return RLS_IRRELEVANT;
+
+ /* preserve flag if it's already set */
+ if (xfs_is_reflink_inode(sc->ip))
+ return RLS_SET_IFLAG;
+
+ /* can only share regular files */
+ if (!S_ISREG(VFS_I(sc->ip)->i_mode))
+ return RLS_IRRELEVANT;
+
+ /* cannot share attr fork extents */
+ if (whichfork != XFS_DATA_FORK)
+ return RLS_IRRELEVANT;
+
+ /* cannot share realtime extents */
+ if (XFS_IS_REALTIME_INODE(sc->ip))
+ return RLS_IRRELEVANT;
+
+ return RLS_UNKNOWN;
+}
+
+/* Repair an inode fork. */
+int
+xrep_bmap(
+ struct xfs_scrub *sc,
+ int whichfork,
+ bool allow_unwritten)
+{
+ struct xrep_bmap *rb;
+ char *descr;
+ unsigned int max_bmbt_recs;
+ bool large_extcount;
+ int error = 0;
+
+ error = xrep_bmap_check_inputs(sc, whichfork);
+ if (error == -ECANCELED)
+ return 0;
+ if (error)
+ return error;
+
+ rb = kzalloc(sizeof(struct xrep_bmap), XCHK_GFP_FLAGS);
+ if (!rb)
+ return -ENOMEM;
+ rb->sc = sc;
+ rb->whichfork = whichfork;
+ rb->reflink_scan = xrep_bmap_init_reflink_scan(sc, whichfork);
+ rb->allow_unwritten = allow_unwritten;
+
+ /* Set up enough storage to handle the max records for this fork. */
+ large_extcount = xfs_has_large_extent_counts(sc->mp);
+ max_bmbt_recs = xfs_iext_max_nextents(large_extcount, whichfork);
+ descr = xchk_xfile_ino_descr(sc, "%s fork mapping records",
+ whichfork == XFS_DATA_FORK ? "data" : "attr");
+ error = xfarray_create(descr, max_bmbt_recs,
+ sizeof(struct xfs_bmbt_rec), &rb->bmap_records);
+ kfree(descr);
+ if (error)
+ goto out_rb;
+
+ /* Collect all reverse mappings for this fork's extents. */
+ xfsb_bitmap_init(&rb->old_bmbt_blocks);
+ error = xrep_bmap_find_mappings(rb);
+ if (error)
+ goto out_bitmap;
+
+ xfs_trans_ijoin(sc->tp, sc->ip, 0);
+
+ /* Rebuild the bmap information. */
+ error = xrep_bmap_build_new_fork(rb);
+ if (error)
+ goto out_bitmap;
+
+ /* Kill the old tree. */
+ error = xrep_bmap_remove_old_tree(rb);
+ if (error)
+ goto out_bitmap;
+
+out_bitmap:
+ xfsb_bitmap_destroy(&rb->old_bmbt_blocks);
+ xfarray_destroy(rb->bmap_records);
+out_rb:
+ kfree(rb);
+ return error;
+}
+
+/* Repair an inode's data fork. */
+int
+xrep_bmap_data(
+ struct xfs_scrub *sc)
+{
+ return xrep_bmap(sc, XFS_DATA_FORK, true);
+}
+
+/* Repair an inode's attr fork. */
+int
+xrep_bmap_attr(
+ struct xfs_scrub *sc)
+{
+ return xrep_bmap(sc, XFS_ATTR_FORK, false);
+}
diff --git a/fs/xfs/scrub/common.c b/fs/xfs/scrub/common.c
index de24532fe083..81f2b96bb5a7 100644
--- a/fs/xfs/scrub/common.c
+++ b/fs/xfs/scrub/common.c
@@ -25,6 +25,7 @@
#include "xfs_trans_priv.h"
#include "xfs_da_format.h"
#include "xfs_da_btree.h"
+#include "xfs_dir2_priv.h"
#include "xfs_attr.h"
#include "xfs_reflink.h"
#include "xfs_ag.h"
@@ -604,6 +605,7 @@ xchk_ag_free(
struct xchk_ag *sa)
{
xchk_ag_btcur_free(sa);
+ xrep_reset_perag_resv(sc);
if (sa->agf_bp) {
xfs_trans_brelse(sc->tp, sa->agf_bp);
sa->agf_bp = NULL;
@@ -733,6 +735,8 @@ xchk_iget(
xfs_ino_t inum,
struct xfs_inode **ipp)
{
+ ASSERT(sc->tp != NULL);
+
return xfs_iget(sc->mp, sc->tp, inum, XFS_IGET_UNTRUSTED, 0, ipp);
}
@@ -816,6 +820,26 @@ again:
return 0;
}
+#ifdef CONFIG_XFS_QUOTA
+/*
+ * Try to attach dquots to this inode if we think we might want to repair it.
+ * Callers must not hold any ILOCKs. If the dquots are broken and cannot be
+ * attached, a quotacheck will be scheduled.
+ */
+int
+xchk_ino_dqattach(
+ struct xfs_scrub *sc)
+{
+ ASSERT(sc->tp != NULL);
+ ASSERT(sc->ip != NULL);
+
+ if (!xchk_could_repair(sc))
+ return 0;
+
+ return xrep_ino_dqattach(sc);
+}
+#endif
+
/* Install an inode that we opened by handle for scrubbing. */
int
xchk_install_handle_inode(
@@ -882,8 +906,8 @@ xchk_iget_for_scrubbing(
if (!xfs_verify_ino(sc->mp, sc->sm->sm_ino))
return -ENOENT;
- /* Try a regular untrusted iget. */
- error = xchk_iget(sc, sc->sm->sm_ino, &ip);
+ /* Try a safe untrusted iget. */
+ error = xchk_iget_safe(sc, sc->sm->sm_ino, &ip);
if (!error)
return xchk_install_handle_inode(sc, ip);
if (error == -ENOENT)
@@ -1027,6 +1051,11 @@ xchk_setup_inode_contents(
error = xchk_trans_alloc(sc, resblks);
if (error)
goto out;
+
+ error = xchk_ino_dqattach(sc);
+ if (error)
+ goto out;
+
xchk_ilock(sc, XFS_ILOCK_EXCL);
out:
/* scrub teardown will unlock and release the inode for us */
@@ -1132,6 +1161,7 @@ xchk_metadata_inode_subtype(
unsigned int scrub_type)
{
__u32 smtype = sc->sm->sm_type;
+ unsigned int sick_mask = sc->sick_mask;
int error;
sc->sm->sm_type = scrub_type;
@@ -1149,6 +1179,7 @@ xchk_metadata_inode_subtype(
break;
}
+ sc->sick_mask = sick_mask;
sc->sm->sm_type = smtype;
return error;
}
diff --git a/fs/xfs/scrub/common.h b/fs/xfs/scrub/common.h
index cabdc0e16838..da09580b454a 100644
--- a/fs/xfs/scrub/common.h
+++ b/fs/xfs/scrub/common.h
@@ -103,9 +103,15 @@ xchk_setup_rtsummary(struct xfs_scrub *sc)
}
#endif
#ifdef CONFIG_XFS_QUOTA
+int xchk_ino_dqattach(struct xfs_scrub *sc);
int xchk_setup_quota(struct xfs_scrub *sc);
#else
static inline int
+xchk_ino_dqattach(struct xfs_scrub *sc)
+{
+ return 0;
+}
+static inline int
xchk_setup_quota(struct xfs_scrub *sc)
{
return -ENOENT;
@@ -151,6 +157,11 @@ void xchk_iunlock(struct xfs_scrub *sc, unsigned int ilock_flags);
void xchk_buffer_recheck(struct xfs_scrub *sc, struct xfs_buf *bp);
+/*
+ * Grab the inode at @inum. The caller must have created a scrub transaction
+ * so that we can confirm the inumber by walking the inobt and not deadlock on
+ * a loop in the inobt.
+ */
int xchk_iget(struct xfs_scrub *sc, xfs_ino_t inum, struct xfs_inode **ipp);
int xchk_iget_agi(struct xfs_scrub *sc, xfs_ino_t inum,
struct xfs_buf **agi_bpp, struct xfs_inode **ipp);
@@ -158,6 +169,26 @@ void xchk_irele(struct xfs_scrub *sc, struct xfs_inode *ip);
int xchk_install_handle_inode(struct xfs_scrub *sc, struct xfs_inode *ip);
/*
+ * Safe version of (untrusted) xchk_iget that uses an empty transaction to
+ * avoid deadlocking on loops in the inobt. This should only be used in a
+ * scrub or repair setup routine, and only prior to grabbing a transaction.
+ */
+static inline int
+xchk_iget_safe(struct xfs_scrub *sc, xfs_ino_t inum, struct xfs_inode **ipp)
+{
+ int error;
+
+ ASSERT(sc->tp == NULL);
+
+ error = xchk_trans_alloc(sc, 0);
+ if (error)
+ return error;
+ error = xchk_iget(sc, inum, ipp);
+ xchk_trans_cancel(sc);
+ return error;
+}
+
+/*
* Don't bother cross-referencing if we already found corruption or cross
* referencing discrepancies.
*/
@@ -167,6 +198,8 @@ static inline bool xchk_skip_xref(struct xfs_scrub_metadata *sm)
XFS_SCRUB_OFLAG_XCORRUPT);
}
+bool xchk_dir_looks_zapped(struct xfs_inode *dp);
+
#ifdef CONFIG_XFS_ONLINE_REPAIR
/* Decide if a repair is required. */
static inline bool xchk_needs_repair(const struct xfs_scrub_metadata *sm)
@@ -175,8 +208,21 @@ static inline bool xchk_needs_repair(const struct xfs_scrub_metadata *sm)
XFS_SCRUB_OFLAG_XCORRUPT |
XFS_SCRUB_OFLAG_PREEN);
}
+
+/*
+ * "Should we prepare for a repair?"
+ *
+ * Return true if the caller permits us to repair metadata and we're not
+ * setting up for a post-repair evaluation.
+ */
+static inline bool xchk_could_repair(const struct xfs_scrub *sc)
+{
+ return (sc->sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR) &&
+ !(sc->flags & XREP_ALREADY_FIXED);
+}
#else
# define xchk_needs_repair(sc) (false)
+# define xchk_could_repair(sc) (false)
#endif /* CONFIG_XFS_ONLINE_REPAIR */
int xchk_metadata_inode_forks(struct xfs_scrub *sc);
@@ -188,6 +234,16 @@ int xchk_metadata_inode_forks(struct xfs_scrub *sc);
#define xchk_xfile_descr(sc, fmt, ...) \
kasprintf(XCHK_GFP_FLAGS, "XFS (%s): " fmt, \
(sc)->mp->m_super->s_id, ##__VA_ARGS__)
+#define xchk_xfile_ag_descr(sc, fmt, ...) \
+ kasprintf(XCHK_GFP_FLAGS, "XFS (%s): AG 0x%x " fmt, \
+ (sc)->mp->m_super->s_id, \
+ (sc)->sa.pag ? (sc)->sa.pag->pag_agno : (sc)->sm->sm_agno, \
+ ##__VA_ARGS__)
+#define xchk_xfile_ino_descr(sc, fmt, ...) \
+ kasprintf(XCHK_GFP_FLAGS, "XFS (%s): inode 0x%llx " fmt, \
+ (sc)->mp->m_super->s_id, \
+ (sc)->ip ? (sc)->ip->i_ino : (sc)->sm->sm_ino, \
+ ##__VA_ARGS__)
/*
* Setting up a hook to wait for intents to drain is costly -- we have to take
diff --git a/fs/xfs/scrub/cow_repair.c b/fs/xfs/scrub/cow_repair.c
new file mode 100644
index 000000000000..1e82c727af8e
--- /dev/null
+++ b/fs/xfs/scrub/cow_repair.c
@@ -0,0 +1,614 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2022-2023 Oracle. All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_defer.h"
+#include "xfs_btree.h"
+#include "xfs_log_format.h"
+#include "xfs_trans.h"
+#include "xfs_inode.h"
+#include "xfs_inode_fork.h"
+#include "xfs_alloc.h"
+#include "xfs_bmap.h"
+#include "xfs_rmap.h"
+#include "xfs_refcount.h"
+#include "xfs_quota.h"
+#include "xfs_ialloc.h"
+#include "xfs_ag.h"
+#include "xfs_error.h"
+#include "xfs_errortag.h"
+#include "xfs_icache.h"
+#include "xfs_refcount_btree.h"
+#include "scrub/xfs_scrub.h"
+#include "scrub/scrub.h"
+#include "scrub/common.h"
+#include "scrub/trace.h"
+#include "scrub/repair.h"
+#include "scrub/bitmap.h"
+#include "scrub/off_bitmap.h"
+#include "scrub/fsb_bitmap.h"
+#include "scrub/reap.h"
+
+/*
+ * CoW Fork Mapping Repair
+ * =======================
+ *
+ * Although CoW staging extents are owned by incore CoW inode forks, on disk
+ * they are owned by the refcount btree. The ondisk metadata does not record
+ * any ownership information, which limits what we can do to repair the
+ * mappings in the CoW fork. At most, we can replace ifork mappings that lack
+ * an entry in the refcount btree or are described by a reverse mapping record
+ * whose owner is not OWN_COW.
+ *
+ * Replacing extents is also tricky -- we can't touch written CoW fork extents
+ * since they are undergoing writeback, and delalloc extents do not require
+ * repair since they only exist incore. Hence the most we can do is find the
+ * bad parts of unwritten mappings, allocate a replacement set of blocks, and
+ * replace the incore mapping. We use the regular reaping process to unmap
+ * or free the discarded blocks, as appropriate.
+ */
+struct xrep_cow {
+ struct xfs_scrub *sc;
+
+ /* Bitmap of file offset ranges that need replacing. */
+ struct xoff_bitmap bad_fileoffs;
+
+ /* Bitmap of fsblocks that were removed from the CoW fork. */
+ struct xfsb_bitmap old_cowfork_fsblocks;
+
+ /* CoW fork mappings used to scan for bad CoW staging extents. */
+ struct xfs_bmbt_irec irec;
+
+ /* refcount btree block number of irec.br_startblock */
+ unsigned int irec_startbno;
+
+ /* refcount btree block number of the next refcount record we expect */
+ unsigned int next_bno;
+};
+
+/* CoW staging extent. */
+struct xrep_cow_extent {
+ xfs_fsblock_t fsbno;
+ xfs_extlen_t len;
+};
+
+/*
+ * Mark the part of the file range that corresponds to the given physical
+ * space. Caller must ensure that the physical range is within xc->irec.
+ */
+STATIC int
+xrep_cow_mark_file_range(
+ struct xrep_cow *xc,
+ xfs_fsblock_t startblock,
+ xfs_filblks_t blockcount)
+{
+ xfs_fileoff_t startoff;
+
+ startoff = xc->irec.br_startoff +
+ (startblock - xc->irec.br_startblock);
+
+ trace_xrep_cow_mark_file_range(xc->sc->ip, startblock, startoff,
+ blockcount);
+
+ return xoff_bitmap_set(&xc->bad_fileoffs, startoff, blockcount);
+}
+
+/*
+ * Trim @src to fit within the CoW fork mapping being examined, and put the
+ * result in @dst.
+ */
+static inline void
+xrep_cow_trim_refcount(
+ struct xrep_cow *xc,
+ struct xfs_refcount_irec *dst,
+ const struct xfs_refcount_irec *src)
+{
+ unsigned int adj;
+
+ memcpy(dst, src, sizeof(*dst));
+
+ if (dst->rc_startblock < xc->irec_startbno) {
+ adj = xc->irec_startbno - dst->rc_startblock;
+ dst->rc_blockcount -= adj;
+ dst->rc_startblock += adj;
+ }
+
+ if (dst->rc_startblock + dst->rc_blockcount >
+ xc->irec_startbno + xc->irec.br_blockcount) {
+ adj = (dst->rc_startblock + dst->rc_blockcount) -
+ (xc->irec_startbno + xc->irec.br_blockcount);
+ dst->rc_blockcount -= adj;
+ }
+}
+
+/* Mark any shared CoW staging extents. */
+STATIC int
+xrep_cow_mark_shared_staging(
+ struct xfs_btree_cur *cur,
+ const struct xfs_refcount_irec *rec,
+ void *priv)
+{
+ struct xrep_cow *xc = priv;
+ struct xfs_refcount_irec rrec;
+ xfs_fsblock_t fsbno;
+
+ if (!xfs_refcount_check_domain(rec) ||
+ rec->rc_domain != XFS_REFC_DOMAIN_SHARED)
+ return -EFSCORRUPTED;
+
+ xrep_cow_trim_refcount(xc, &rrec, rec);
+
+ fsbno = XFS_AGB_TO_FSB(xc->sc->mp, cur->bc_ag.pag->pag_agno,
+ rrec.rc_startblock);
+ return xrep_cow_mark_file_range(xc, fsbno, rrec.rc_blockcount);
+}
+
+/*
+ * Mark any portion of the CoW fork file offset range where there is not a CoW
+ * staging extent record in the refcountbt, and keep a record of where we did
+ * find correct refcountbt records. Staging records are always cleaned out at
+ * mount time, so any two inodes trying to map the same staging area would have
+ * already taken the fs down due to refcount btree verifier errors. Hence this
+ * inode should be the sole creator of the staging extent records ondisk.
+ */
+STATIC int
+xrep_cow_mark_missing_staging(
+ struct xfs_btree_cur *cur,
+ const struct xfs_refcount_irec *rec,
+ void *priv)
+{
+ struct xrep_cow *xc = priv;
+ struct xfs_refcount_irec rrec;
+ int error;
+
+ if (!xfs_refcount_check_domain(rec) ||
+ rec->rc_domain != XFS_REFC_DOMAIN_COW)
+ return -EFSCORRUPTED;
+
+ xrep_cow_trim_refcount(xc, &rrec, rec);
+
+ if (xc->next_bno >= rrec.rc_startblock)
+ goto next;
+
+ error = xrep_cow_mark_file_range(xc,
+ XFS_AGB_TO_FSB(xc->sc->mp, cur->bc_ag.pag->pag_agno,
+ xc->next_bno),
+ rrec.rc_startblock - xc->next_bno);
+ if (error)
+ return error;
+
+next:
+ xc->next_bno = rrec.rc_startblock + rrec.rc_blockcount;
+ return 0;
+}
+
+/*
+ * Mark any area that does not correspond to a CoW staging rmap. These are
+ * cross-linked areas that must be avoided.
+ */
+STATIC int
+xrep_cow_mark_missing_staging_rmap(
+ struct xfs_btree_cur *cur,
+ const struct xfs_rmap_irec *rec,
+ void *priv)
+{
+ struct xrep_cow *xc = priv;
+ xfs_fsblock_t fsbno;
+ xfs_agblock_t rec_bno;
+ xfs_extlen_t rec_len;
+ unsigned int adj;
+
+ if (rec->rm_owner == XFS_RMAP_OWN_COW)
+ return 0;
+
+ rec_bno = rec->rm_startblock;
+ rec_len = rec->rm_blockcount;
+ if (rec_bno < xc->irec_startbno) {
+ adj = xc->irec_startbno - rec_bno;
+ rec_len -= adj;
+ rec_bno += adj;
+ }
+
+ if (rec_bno + rec_len > xc->irec_startbno + xc->irec.br_blockcount) {
+ adj = (rec_bno + rec_len) -
+ (xc->irec_startbno + xc->irec.br_blockcount);
+ rec_len -= adj;
+ }
+
+ fsbno = XFS_AGB_TO_FSB(xc->sc->mp, cur->bc_ag.pag->pag_agno, rec_bno);
+ return xrep_cow_mark_file_range(xc, fsbno, rec_len);
+}
+
+/*
+ * Find any part of the CoW fork mapping that isn't a single-owner CoW staging
+ * extent and mark the corresponding part of the file range in the bitmap.
+ */
+STATIC int
+xrep_cow_find_bad(
+ struct xrep_cow *xc)
+{
+ struct xfs_refcount_irec rc_low = { 0 };
+ struct xfs_refcount_irec rc_high = { 0 };
+ struct xfs_rmap_irec rm_low = { 0 };
+ struct xfs_rmap_irec rm_high = { 0 };
+ struct xfs_perag *pag;
+ struct xfs_scrub *sc = xc->sc;
+ xfs_agnumber_t agno;
+ int error;
+
+ agno = XFS_FSB_TO_AGNO(sc->mp, xc->irec.br_startblock);
+ xc->irec_startbno = XFS_FSB_TO_AGBNO(sc->mp, xc->irec.br_startblock);
+
+ pag = xfs_perag_get(sc->mp, agno);
+ if (!pag)
+ return -EFSCORRUPTED;
+
+ error = xrep_ag_init(sc, pag, &sc->sa);
+ if (error)
+ goto out_pag;
+
+ /* Mark any CoW fork extents that are shared. */
+ rc_low.rc_startblock = xc->irec_startbno;
+ rc_high.rc_startblock = xc->irec_startbno + xc->irec.br_blockcount - 1;
+ rc_low.rc_domain = rc_high.rc_domain = XFS_REFC_DOMAIN_SHARED;
+ error = xfs_refcount_query_range(sc->sa.refc_cur, &rc_low, &rc_high,
+ xrep_cow_mark_shared_staging, xc);
+ if (error)
+ goto out_sa;
+
+ /* Make sure there are CoW staging extents for the whole mapping. */
+ rc_low.rc_startblock = xc->irec_startbno;
+ rc_high.rc_startblock = xc->irec_startbno + xc->irec.br_blockcount - 1;
+ rc_low.rc_domain = rc_high.rc_domain = XFS_REFC_DOMAIN_COW;
+ xc->next_bno = xc->irec_startbno;
+ error = xfs_refcount_query_range(sc->sa.refc_cur, &rc_low, &rc_high,
+ xrep_cow_mark_missing_staging, xc);
+ if (error)
+ goto out_sa;
+
+ if (xc->next_bno < xc->irec_startbno + xc->irec.br_blockcount) {
+ error = xrep_cow_mark_file_range(xc,
+ XFS_AGB_TO_FSB(sc->mp, pag->pag_agno,
+ xc->next_bno),
+ xc->irec_startbno + xc->irec.br_blockcount -
+ xc->next_bno);
+ if (error)
+ goto out_sa;
+ }
+
+ /* Mark any area has an rmap that isn't a COW staging extent. */
+ rm_low.rm_startblock = xc->irec_startbno;
+ memset(&rm_high, 0xFF, sizeof(rm_high));
+ rm_high.rm_startblock = xc->irec_startbno + xc->irec.br_blockcount - 1;
+ error = xfs_rmap_query_range(sc->sa.rmap_cur, &rm_low, &rm_high,
+ xrep_cow_mark_missing_staging_rmap, xc);
+ if (error)
+ goto out_sa;
+
+ /*
+ * If userspace is forcing us to rebuild the CoW fork or someone turned
+ * on the debugging knob, replace everything in the CoW fork.
+ */
+ if ((sc->sm->sm_flags & XFS_SCRUB_IFLAG_FORCE_REBUILD) ||
+ XFS_TEST_ERROR(false, sc->mp, XFS_ERRTAG_FORCE_SCRUB_REPAIR)) {
+ error = xrep_cow_mark_file_range(xc, xc->irec.br_startblock,
+ xc->irec.br_blockcount);
+ if (error)
+ return error;
+ }
+
+out_sa:
+ xchk_ag_free(sc, &sc->sa);
+out_pag:
+ xfs_perag_put(pag);
+ return 0;
+}
+
+/*
+ * Allocate a replacement CoW staging extent of up to the given number of
+ * blocks, and fill out the mapping.
+ */
+STATIC int
+xrep_cow_alloc(
+ struct xfs_scrub *sc,
+ xfs_extlen_t maxlen,
+ struct xrep_cow_extent *repl)
+{
+ struct xfs_alloc_arg args = {
+ .tp = sc->tp,
+ .mp = sc->mp,
+ .oinfo = XFS_RMAP_OINFO_SKIP_UPDATE,
+ .minlen = 1,
+ .maxlen = maxlen,
+ .prod = 1,
+ .resv = XFS_AG_RESV_NONE,
+ .datatype = XFS_ALLOC_USERDATA,
+ };
+ int error;
+
+ error = xfs_trans_reserve_more(sc->tp, maxlen, 0);
+ if (error)
+ return error;
+
+ error = xfs_alloc_vextent_start_ag(&args,
+ XFS_INO_TO_FSB(sc->mp, sc->ip->i_ino));
+ if (error)
+ return error;
+ if (args.fsbno == NULLFSBLOCK)
+ return -ENOSPC;
+
+ xfs_refcount_alloc_cow_extent(sc->tp, args.fsbno, args.len);
+
+ repl->fsbno = args.fsbno;
+ repl->len = args.len;
+ return 0;
+}
+
+/*
+ * Look up the current CoW fork mapping so that we only allocate enough to
+ * replace a single mapping. If we don't find a mapping that covers the start
+ * of the file range, or we find a delalloc or written extent, something is
+ * seriously wrong, since we didn't drop the ILOCK.
+ */
+static inline int
+xrep_cow_find_mapping(
+ struct xrep_cow *xc,
+ struct xfs_iext_cursor *icur,
+ xfs_fileoff_t startoff,
+ struct xfs_bmbt_irec *got)
+{
+ struct xfs_inode *ip = xc->sc->ip;
+ struct xfs_ifork *ifp = xfs_ifork_ptr(ip, XFS_COW_FORK);
+
+ if (!xfs_iext_lookup_extent(ip, ifp, startoff, icur, got))
+ goto bad;
+
+ if (got->br_startoff > startoff)
+ goto bad;
+
+ if (got->br_blockcount == 0)
+ goto bad;
+
+ if (isnullstartblock(got->br_startblock))
+ goto bad;
+
+ if (xfs_bmap_is_written_extent(got))
+ goto bad;
+
+ return 0;
+bad:
+ ASSERT(0);
+ return -EFSCORRUPTED;
+}
+
+#define REPLACE_LEFT_SIDE (1U << 0)
+#define REPLACE_RIGHT_SIDE (1U << 1)
+
+/*
+ * Given a CoW fork mapping @got and a replacement mapping @repl, remap the
+ * beginning of @got with the space described by @rep.
+ */
+static inline void
+xrep_cow_replace_mapping(
+ struct xfs_inode *ip,
+ struct xfs_iext_cursor *icur,
+ const struct xfs_bmbt_irec *got,
+ const struct xrep_cow_extent *repl)
+{
+ struct xfs_bmbt_irec new = *got; /* struct copy */
+
+ ASSERT(repl->len > 0);
+ ASSERT(!isnullstartblock(got->br_startblock));
+
+ trace_xrep_cow_replace_mapping(ip, got, repl->fsbno, repl->len);
+
+ if (got->br_blockcount == repl->len) {
+ /*
+ * The new extent is a complete replacement for the existing
+ * extent. Update the COW fork record.
+ */
+ new.br_startblock = repl->fsbno;
+ xfs_iext_update_extent(ip, BMAP_COWFORK, icur, &new);
+ return;
+ }
+
+ /*
+ * The new extent can replace the beginning of the COW fork record.
+ * Move the left side of @got upwards, then insert the new record.
+ */
+ new.br_startoff += repl->len;
+ new.br_startblock += repl->len;
+ new.br_blockcount -= repl->len;
+ xfs_iext_update_extent(ip, BMAP_COWFORK, icur, &new);
+
+ new.br_startoff = got->br_startoff;
+ new.br_startblock = repl->fsbno;
+ new.br_blockcount = repl->len;
+ xfs_iext_insert(ip, icur, &new, BMAP_COWFORK);
+}
+
+/*
+ * Replace the unwritten CoW staging extent backing the given file range with a
+ * new space extent that isn't as problematic.
+ */
+STATIC int
+xrep_cow_replace_range(
+ struct xrep_cow *xc,
+ xfs_fileoff_t startoff,
+ xfs_extlen_t *blockcount)
+{
+ struct xfs_iext_cursor icur;
+ struct xrep_cow_extent repl;
+ struct xfs_bmbt_irec got;
+ struct xfs_scrub *sc = xc->sc;
+ xfs_fileoff_t nextoff;
+ xfs_extlen_t alloc_len;
+ int error;
+
+ /*
+ * Put the existing CoW fork mapping in @got. If @got ends before
+ * @rep, truncate @rep so we only replace one extent mapping at a time.
+ */
+ error = xrep_cow_find_mapping(xc, &icur, startoff, &got);
+ if (error)
+ return error;
+ nextoff = min(startoff + *blockcount,
+ got.br_startoff + got.br_blockcount);
+
+ /*
+ * Allocate a replacement extent. If we don't fill all the blocks,
+ * shorten the quantity that will be deleted in this step.
+ */
+ alloc_len = min_t(xfs_fileoff_t, XFS_MAX_BMBT_EXTLEN,
+ nextoff - startoff);
+ error = xrep_cow_alloc(sc, alloc_len, &repl);
+ if (error)
+ return error;
+
+ /*
+ * Replace the old mapping with the new one, and commit the metadata
+ * changes made so far.
+ */
+ xrep_cow_replace_mapping(sc->ip, &icur, &got, &repl);
+
+ xfs_inode_set_cowblocks_tag(sc->ip);
+ error = xfs_defer_finish(&sc->tp);
+ if (error)
+ return error;
+
+ /* Note the old CoW staging extents; we'll reap them all later. */
+ error = xfsb_bitmap_set(&xc->old_cowfork_fsblocks, got.br_startblock,
+ repl.len);
+ if (error)
+ return error;
+
+ *blockcount = repl.len;
+ return 0;
+}
+
+/*
+ * Replace a bad part of an unwritten CoW staging extent with a fresh delalloc
+ * reservation.
+ */
+STATIC int
+xrep_cow_replace(
+ uint64_t startoff,
+ uint64_t blockcount,
+ void *priv)
+{
+ struct xrep_cow *xc = priv;
+ int error = 0;
+
+ while (blockcount > 0) {
+ xfs_extlen_t len = min_t(xfs_filblks_t, blockcount,
+ XFS_MAX_BMBT_EXTLEN);
+
+ error = xrep_cow_replace_range(xc, startoff, &len);
+ if (error)
+ break;
+
+ blockcount -= len;
+ startoff += len;
+ }
+
+ return error;
+}
+
+/*
+ * Repair an inode's CoW fork. The CoW fork is an in-core structure, so
+ * there's no btree to rebuid. Instead, we replace any mappings that are
+ * cross-linked or lack ondisk CoW fork records in the refcount btree.
+ */
+int
+xrep_bmap_cow(
+ struct xfs_scrub *sc)
+{
+ struct xrep_cow *xc;
+ struct xfs_iext_cursor icur;
+ struct xfs_ifork *ifp = xfs_ifork_ptr(sc->ip, XFS_COW_FORK);
+ int error;
+
+ if (!xfs_has_rmapbt(sc->mp) || !xfs_has_reflink(sc->mp))
+ return -EOPNOTSUPP;
+
+ if (!ifp)
+ return 0;
+
+ /* realtime files aren't supported yet */
+ if (XFS_IS_REALTIME_INODE(sc->ip))
+ return -EOPNOTSUPP;
+
+ /*
+ * If we're somehow not in extents format, then reinitialize it to
+ * an empty extent mapping fork and exit.
+ */
+ if (ifp->if_format != XFS_DINODE_FMT_EXTENTS) {
+ ifp->if_format = XFS_DINODE_FMT_EXTENTS;
+ ifp->if_nextents = 0;
+ return 0;
+ }
+
+ xc = kzalloc(sizeof(struct xrep_cow), XCHK_GFP_FLAGS);
+ if (!xc)
+ return -ENOMEM;
+
+ xfs_trans_ijoin(sc->tp, sc->ip, 0);
+
+ xc->sc = sc;
+ xoff_bitmap_init(&xc->bad_fileoffs);
+ xfsb_bitmap_init(&xc->old_cowfork_fsblocks);
+
+ for_each_xfs_iext(ifp, &icur, &xc->irec) {
+ if (xchk_should_terminate(sc, &error))
+ goto out_bitmap;
+
+ /*
+ * delalloc reservations only exist incore, so there is no
+ * ondisk metadata that we can examine. Hence we leave them
+ * alone.
+ */
+ if (isnullstartblock(xc->irec.br_startblock))
+ continue;
+
+ /*
+ * COW fork extents are only in the written state if writeback
+ * is actively writing to disk. We cannot restart the write
+ * at a different disk address since we've already issued the
+ * IO, so we leave these alone and hope for the best.
+ */
+ if (xfs_bmap_is_written_extent(&xc->irec))
+ continue;
+
+ error = xrep_cow_find_bad(xc);
+ if (error)
+ goto out_bitmap;
+ }
+
+ /* Replace any bad unwritten mappings with fresh reservations. */
+ error = xoff_bitmap_walk(&xc->bad_fileoffs, xrep_cow_replace, xc);
+ if (error)
+ goto out_bitmap;
+
+ /*
+ * Reap as many of the old CoW blocks as we can. They are owned ondisk
+ * by the refcount btree, not the inode, so it is correct to treat them
+ * like inode metadata.
+ */
+ error = xrep_reap_fsblocks(sc, &xc->old_cowfork_fsblocks,
+ &XFS_RMAP_OINFO_COW);
+ if (error)
+ goto out_bitmap;
+
+out_bitmap:
+ xfsb_bitmap_destroy(&xc->old_cowfork_fsblocks);
+ xoff_bitmap_destroy(&xc->bad_fileoffs);
+ kmem_free(xc);
+ return error;
+}
diff --git a/fs/xfs/scrub/dir.c b/fs/xfs/scrub/dir.c
index 0b491784b759..d86ab51af928 100644
--- a/fs/xfs/scrub/dir.c
+++ b/fs/xfs/scrub/dir.c
@@ -15,10 +15,12 @@
#include "xfs_icache.h"
#include "xfs_dir2.h"
#include "xfs_dir2_priv.h"
+#include "xfs_health.h"
#include "scrub/scrub.h"
#include "scrub/common.h"
#include "scrub/dabtree.h"
#include "scrub/readdir.h"
+#include "scrub/health.h"
/* Set us up to scrub directories. */
int
@@ -760,6 +762,11 @@ xchk_directory(
if (!S_ISDIR(VFS_I(sc->ip)->i_mode))
return -ENOENT;
+ if (xchk_file_looks_zapped(sc, XFS_SICK_INO_DIR_ZAPPED)) {
+ xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
+ return 0;
+ }
+
/* Plausible size? */
if (sc->ip->i_disk_size < xfs_dir2_sf_hdr_size(0)) {
xchk_ino_set_corrupt(sc, sc->ip->i_ino);
@@ -784,7 +791,36 @@ xchk_directory(
/* Look up every name in this directory by hash. */
error = xchk_dir_walk(sc, sc->ip, xchk_dir_actor, NULL);
- if (error == -ECANCELED)
- error = 0;
- return error;
+ if (error && error != -ECANCELED)
+ return error;
+
+ /* If the dir is clean, it is clearly not zapped. */
+ xchk_mark_healthy_if_clean(sc, XFS_SICK_INO_DIR_ZAPPED);
+ return 0;
+}
+
+/*
+ * Decide if this directory has been zapped to satisfy the inode and ifork
+ * verifiers. Checking and repairing should be postponed until the directory
+ * is fixed.
+ */
+bool
+xchk_dir_looks_zapped(
+ struct xfs_inode *dp)
+{
+ /* Repair zapped this dir's data fork a short time ago */
+ if (xfs_ifork_zapped(dp, XFS_DATA_FORK))
+ return true;
+
+ /*
+ * If the dinode repair found a bad data fork, it will reset the fork
+ * to extents format with zero records and wait for the bmapbtd
+ * scrubber to reconstruct the block mappings. Directories always
+ * contain some content, so this is a clear sign of a zapped directory.
+ * The state checked by xfs_ifork_zapped is not persisted, so this is
+ * the secondary strategy if repairs are interrupted by a crash or an
+ * unmount.
+ */
+ return dp->i_df.if_format == XFS_DINODE_FMT_EXTENTS &&
+ dp->i_df.if_nextents == 0;
}
diff --git a/fs/xfs/scrub/dqiterate.c b/fs/xfs/scrub/dqiterate.c
new file mode 100644
index 000000000000..20c4daedd48d
--- /dev/null
+++ b/fs/xfs/scrub/dqiterate.c
@@ -0,0 +1,211 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2023 Oracle. All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_bit.h"
+#include "xfs_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_log_format.h"
+#include "xfs_trans.h"
+#include "xfs_inode.h"
+#include "xfs_quota.h"
+#include "xfs_qm.h"
+#include "xfs_bmap.h"
+#include "scrub/scrub.h"
+#include "scrub/common.h"
+#include "scrub/quota.h"
+#include "scrub/trace.h"
+
+/* Initialize a dquot iteration cursor. */
+void
+xchk_dqiter_init(
+ struct xchk_dqiter *cursor,
+ struct xfs_scrub *sc,
+ xfs_dqtype_t dqtype)
+{
+ cursor->sc = sc;
+ cursor->bmap.br_startoff = NULLFILEOFF;
+ cursor->dqtype = dqtype & XFS_DQTYPE_REC_MASK;
+ cursor->quota_ip = xfs_quota_inode(sc->mp, cursor->dqtype);
+ cursor->id = 0;
+}
+
+/*
+ * Ensure that the cached data fork mapping for the dqiter cursor is fresh and
+ * covers the dquot pointed to by the scan cursor.
+ */
+STATIC int
+xchk_dquot_iter_revalidate_bmap(
+ struct xchk_dqiter *cursor)
+{
+ struct xfs_quotainfo *qi = cursor->sc->mp->m_quotainfo;
+ struct xfs_ifork *ifp = xfs_ifork_ptr(cursor->quota_ip,
+ XFS_DATA_FORK);
+ xfs_fileoff_t fileoff;
+ xfs_dqid_t this_id = cursor->id;
+ int nmaps = 1;
+ int error;
+
+ fileoff = this_id / qi->qi_dqperchunk;
+
+ /*
+ * If we have a mapping for cursor->id and it's still fresh, there's
+ * no need to reread the bmbt.
+ */
+ if (cursor->bmap.br_startoff != NULLFILEOFF &&
+ cursor->if_seq == ifp->if_seq &&
+ cursor->bmap.br_startoff + cursor->bmap.br_blockcount > fileoff)
+ return 0;
+
+ /* Look up the data fork mapping for the dquot id of interest. */
+ error = xfs_bmapi_read(cursor->quota_ip, fileoff,
+ XFS_MAX_FILEOFF - fileoff, &cursor->bmap, &nmaps, 0);
+ if (error)
+ return error;
+ if (!nmaps) {
+ ASSERT(nmaps > 0);
+ return -EFSCORRUPTED;
+ }
+ if (cursor->bmap.br_startoff > fileoff) {
+ ASSERT(cursor->bmap.br_startoff == fileoff);
+ return -EFSCORRUPTED;
+ }
+
+ cursor->if_seq = ifp->if_seq;
+ trace_xchk_dquot_iter_revalidate_bmap(cursor, cursor->id);
+ return 0;
+}
+
+/* Advance the dqiter cursor to the next non-sparse region of the quota file. */
+STATIC int
+xchk_dquot_iter_advance_bmap(
+ struct xchk_dqiter *cursor,
+ uint64_t *next_ondisk_id)
+{
+ struct xfs_quotainfo *qi = cursor->sc->mp->m_quotainfo;
+ struct xfs_ifork *ifp = xfs_ifork_ptr(cursor->quota_ip,
+ XFS_DATA_FORK);
+ xfs_fileoff_t fileoff;
+ uint64_t next_id;
+ int nmaps = 1;
+ int error;
+
+ /* Find the dquot id for the next non-hole mapping. */
+ do {
+ fileoff = cursor->bmap.br_startoff + cursor->bmap.br_blockcount;
+ if (fileoff > XFS_DQ_ID_MAX / qi->qi_dqperchunk) {
+ /* The hole goes beyond the max dquot id, we're done */
+ *next_ondisk_id = -1ULL;
+ return 0;
+ }
+
+ error = xfs_bmapi_read(cursor->quota_ip, fileoff,
+ XFS_MAX_FILEOFF - fileoff, &cursor->bmap,
+ &nmaps, 0);
+ if (error)
+ return error;
+ if (!nmaps) {
+ /* Must have reached the end of the mappings. */
+ *next_ondisk_id = -1ULL;
+ return 0;
+ }
+ if (cursor->bmap.br_startoff > fileoff) {
+ ASSERT(cursor->bmap.br_startoff == fileoff);
+ return -EFSCORRUPTED;
+ }
+ } while (!xfs_bmap_is_real_extent(&cursor->bmap));
+
+ next_id = cursor->bmap.br_startoff * qi->qi_dqperchunk;
+ if (next_id > XFS_DQ_ID_MAX) {
+ /* The hole goes beyond the max dquot id, we're done */
+ *next_ondisk_id = -1ULL;
+ return 0;
+ }
+
+ /* Propose jumping forward to the dquot in the next allocated block. */
+ *next_ondisk_id = next_id;
+ cursor->if_seq = ifp->if_seq;
+ trace_xchk_dquot_iter_advance_bmap(cursor, *next_ondisk_id);
+ return 0;
+}
+
+/*
+ * Find the id of the next highest incore dquot. Normally this will correspond
+ * exactly with the quota file block mappings, but repair might have erased a
+ * mapping because it was crosslinked; in that case, we need to re-allocate the
+ * space so that we can reset q_blkno.
+ */
+STATIC void
+xchk_dquot_iter_advance_incore(
+ struct xchk_dqiter *cursor,
+ uint64_t *next_incore_id)
+{
+ struct xfs_quotainfo *qi = cursor->sc->mp->m_quotainfo;
+ struct radix_tree_root *tree = xfs_dquot_tree(qi, cursor->dqtype);
+ struct xfs_dquot *dq;
+ unsigned int nr_found;
+
+ *next_incore_id = -1ULL;
+
+ mutex_lock(&qi->qi_tree_lock);
+ nr_found = radix_tree_gang_lookup(tree, (void **)&dq, cursor->id, 1);
+ if (nr_found)
+ *next_incore_id = dq->q_id;
+ mutex_unlock(&qi->qi_tree_lock);
+
+ trace_xchk_dquot_iter_advance_incore(cursor, *next_incore_id);
+}
+
+/*
+ * Walk all incore dquots of this filesystem. Caller must set *@cursorp to
+ * zero before the first call, and must not hold the quota file ILOCK.
+ * Returns 1 and a valid *@dqpp; 0 and *@dqpp == NULL when there are no more
+ * dquots to iterate; or a negative errno.
+ */
+int
+xchk_dquot_iter(
+ struct xchk_dqiter *cursor,
+ struct xfs_dquot **dqpp)
+{
+ struct xfs_mount *mp = cursor->sc->mp;
+ struct xfs_dquot *dq = NULL;
+ uint64_t next_ondisk, next_incore = -1ULL;
+ unsigned int lock_mode;
+ int error = 0;
+
+ if (cursor->id > XFS_DQ_ID_MAX)
+ return 0;
+ next_ondisk = cursor->id;
+
+ /* Revalidate and/or advance the cursor. */
+ lock_mode = xfs_ilock_data_map_shared(cursor->quota_ip);
+ error = xchk_dquot_iter_revalidate_bmap(cursor);
+ if (!error && !xfs_bmap_is_real_extent(&cursor->bmap))
+ error = xchk_dquot_iter_advance_bmap(cursor, &next_ondisk);
+ xfs_iunlock(cursor->quota_ip, lock_mode);
+ if (error)
+ return error;
+
+ if (next_ondisk > cursor->id)
+ xchk_dquot_iter_advance_incore(cursor, &next_incore);
+
+ /* Pick the next dquot in the sequence and return it. */
+ cursor->id = min(next_ondisk, next_incore);
+ if (cursor->id > XFS_DQ_ID_MAX)
+ return 0;
+
+ trace_xchk_dquot_iter(cursor, cursor->id);
+
+ error = xfs_qm_dqget(mp, cursor->id, cursor->dqtype, false, &dq);
+ if (error)
+ return error;
+
+ cursor->id = dq->q_id + 1;
+ *dqpp = dq;
+ return 1;
+}
diff --git a/fs/xfs/scrub/fsb_bitmap.h b/fs/xfs/scrub/fsb_bitmap.h
new file mode 100644
index 000000000000..40b462c1dd0d
--- /dev/null
+++ b/fs/xfs/scrub/fsb_bitmap.h
@@ -0,0 +1,37 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2018-2023 Oracle. All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#ifndef __XFS_SCRUB_FSB_BITMAP_H__
+#define __XFS_SCRUB_FSB_BITMAP_H__
+
+/* Bitmaps, but for type-checked for xfs_fsblock_t */
+
+struct xfsb_bitmap {
+ struct xbitmap64 fsbitmap;
+};
+
+static inline void xfsb_bitmap_init(struct xfsb_bitmap *bitmap)
+{
+ xbitmap64_init(&bitmap->fsbitmap);
+}
+
+static inline void xfsb_bitmap_destroy(struct xfsb_bitmap *bitmap)
+{
+ xbitmap64_destroy(&bitmap->fsbitmap);
+}
+
+static inline int xfsb_bitmap_set(struct xfsb_bitmap *bitmap,
+ xfs_fsblock_t start, xfs_filblks_t len)
+{
+ return xbitmap64_set(&bitmap->fsbitmap, start, len);
+}
+
+static inline int xfsb_bitmap_walk(struct xfsb_bitmap *bitmap,
+ xbitmap64_walk_fn fn, void *priv)
+{
+ return xbitmap64_walk(&bitmap->fsbitmap, fn, priv);
+}
+
+#endif /* __XFS_SCRUB_FSB_BITMAP_H__ */
diff --git a/fs/xfs/scrub/health.c b/fs/xfs/scrub/health.c
index 5e2b09ed6e29..531006910ca9 100644
--- a/fs/xfs/scrub/health.c
+++ b/fs/xfs/scrub/health.c
@@ -10,8 +10,6 @@
#include "xfs_trans_resv.h"
#include "xfs_mount.h"
#include "xfs_btree.h"
-#include "xfs_trans_resv.h"
-#include "xfs_mount.h"
#include "xfs_ag.h"
#include "xfs_health.h"
#include "scrub/scrub.h"
@@ -118,6 +116,38 @@ xchk_health_mask_for_scrub_type(
}
/*
+ * If the scrub state is clean, add @mask to the scrub sick mask to clear
+ * additional sick flags from the metadata object's sick state.
+ */
+void
+xchk_mark_healthy_if_clean(
+ struct xfs_scrub *sc,
+ unsigned int mask)
+{
+ if (!(sc->sm->sm_flags & (XFS_SCRUB_OFLAG_CORRUPT |
+ XFS_SCRUB_OFLAG_XCORRUPT)))
+ sc->sick_mask |= mask;
+}
+
+/*
+ * If we're scrubbing a piece of file metadata for the first time, does it look
+ * like it has been zapped? Skip the check if we just repaired the metadata
+ * and are revalidating it.
+ */
+bool
+xchk_file_looks_zapped(
+ struct xfs_scrub *sc,
+ unsigned int mask)
+{
+ ASSERT((mask & ~XFS_SICK_INO_ZAPPED) == 0);
+
+ if (sc->flags & XREP_ALREADY_FIXED)
+ return false;
+
+ return xfs_inode_has_sickness(sc->ip, mask);
+}
+
+/*
* Update filesystem health assessments based on what we found and did.
*
* If the scrubber finds errors, we mark sick whatever's mentioned in
diff --git a/fs/xfs/scrub/health.h b/fs/xfs/scrub/health.h
index 66a273f8585b..a731b2467399 100644
--- a/fs/xfs/scrub/health.h
+++ b/fs/xfs/scrub/health.h
@@ -10,5 +10,7 @@ unsigned int xchk_health_mask_for_scrub_type(__u32 scrub_type);
void xchk_update_health(struct xfs_scrub *sc);
bool xchk_ag_btree_healthy_enough(struct xfs_scrub *sc, struct xfs_perag *pag,
xfs_btnum_t btnum);
+void xchk_mark_healthy_if_clean(struct xfs_scrub *sc, unsigned int mask);
+bool xchk_file_looks_zapped(struct xfs_scrub *sc, unsigned int mask);
#endif /* __XFS_SCRUB_HEALTH_H__ */
diff --git a/fs/xfs/scrub/ialloc.c b/fs/xfs/scrub/ialloc.c
index fb7bbf47ae5d..a720fc62262a 100644
--- a/fs/xfs/scrub/ialloc.c
+++ b/fs/xfs/scrub/ialloc.c
@@ -585,7 +585,7 @@ xchk_iallocbt_rec(
uint16_t holemask;
xfs_inobt_btrec_to_irec(mp, rec, &irec);
- if (xfs_inobt_check_irec(bs->cur, &irec) != NULL) {
+ if (xfs_inobt_check_irec(bs->cur->bc_ag.pag, &irec) != NULL) {
xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
return 0;
}
@@ -708,11 +708,10 @@ xchk_iallocbt_xref_rmap_inodes(
xchk_btree_xref_set_corrupt(sc, sc->sa.rmap_cur, 0);
}
-/* Scrub the inode btrees for some AG. */
-STATIC int
+/* Scrub one of the inode btrees for some AG. */
+int
xchk_iallocbt(
- struct xfs_scrub *sc,
- xfs_btnum_t which)
+ struct xfs_scrub *sc)
{
struct xfs_btree_cur *cur;
struct xchk_iallocbt iabt = {
@@ -720,9 +719,23 @@ xchk_iallocbt(
.next_startino = NULLAGINO,
.next_cluster_ino = NULLAGINO,
};
+ xfs_btnum_t which;
int error;
- cur = which == XFS_BTNUM_INO ? sc->sa.ino_cur : sc->sa.fino_cur;
+ switch (sc->sm->sm_type) {
+ case XFS_SCRUB_TYPE_INOBT:
+ cur = sc->sa.ino_cur;
+ which = XFS_BTNUM_INO;
+ break;
+ case XFS_SCRUB_TYPE_FINOBT:
+ cur = sc->sa.fino_cur;
+ which = XFS_BTNUM_FINO;
+ break;
+ default:
+ ASSERT(0);
+ return -EIO;
+ }
+
error = xchk_btree(sc, cur, xchk_iallocbt_rec, &XFS_RMAP_OINFO_INOBT,
&iabt);
if (error)
@@ -743,20 +756,6 @@ xchk_iallocbt(
return error;
}
-int
-xchk_inobt(
- struct xfs_scrub *sc)
-{
- return xchk_iallocbt(sc, XFS_BTNUM_INO);
-}
-
-int
-xchk_finobt(
- struct xfs_scrub *sc)
-{
- return xchk_iallocbt(sc, XFS_BTNUM_FINO);
-}
-
/* See if an inode btree has (or doesn't have) an inode chunk record. */
static inline void
xchk_xref_inode_check(
diff --git a/fs/xfs/scrub/ialloc_repair.c b/fs/xfs/scrub/ialloc_repair.c
new file mode 100644
index 000000000000..b3f7182dd2f5
--- /dev/null
+++ b/fs/xfs/scrub/ialloc_repair.c
@@ -0,0 +1,884 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2018-2023 Oracle. All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_defer.h"
+#include "xfs_btree.h"
+#include "xfs_btree_staging.h"
+#include "xfs_bit.h"
+#include "xfs_log_format.h"
+#include "xfs_trans.h"
+#include "xfs_sb.h"
+#include "xfs_inode.h"
+#include "xfs_alloc.h"
+#include "xfs_ialloc.h"
+#include "xfs_ialloc_btree.h"
+#include "xfs_icache.h"
+#include "xfs_rmap.h"
+#include "xfs_rmap_btree.h"
+#include "xfs_log.h"
+#include "xfs_trans_priv.h"
+#include "xfs_error.h"
+#include "xfs_health.h"
+#include "xfs_ag.h"
+#include "scrub/xfs_scrub.h"
+#include "scrub/scrub.h"
+#include "scrub/common.h"
+#include "scrub/btree.h"
+#include "scrub/trace.h"
+#include "scrub/repair.h"
+#include "scrub/bitmap.h"
+#include "scrub/agb_bitmap.h"
+#include "scrub/xfile.h"
+#include "scrub/xfarray.h"
+#include "scrub/newbt.h"
+#include "scrub/reap.h"
+
+/*
+ * Inode Btree Repair
+ * ==================
+ *
+ * A quick refresher of inode btrees on a v5 filesystem:
+ *
+ * - Inode records are read into memory in units of 'inode clusters'. However
+ * many inodes fit in a cluster buffer is the smallest number of inodes that
+ * can be allocated or freed. Clusters are never smaller than one fs block
+ * though they can span multiple blocks. The size (in fs blocks) is
+ * computed with xfs_icluster_size_fsb(). The fs block alignment of a
+ * cluster is computed with xfs_ialloc_cluster_alignment().
+ *
+ * - Each inode btree record can describe a single 'inode chunk'. The chunk
+ * size is defined to be 64 inodes. If sparse inodes are enabled, every
+ * inobt record must be aligned to the chunk size; if not, every record must
+ * be aligned to the start of a cluster. It is possible to construct an XFS
+ * geometry where one inobt record maps to multiple inode clusters; it is
+ * also possible to construct a geometry where multiple inobt records map to
+ * different parts of one inode cluster.
+ *
+ * - If sparse inodes are not enabled, the smallest unit of allocation for
+ * inode records is enough to contain one inode chunk's worth of inodes.
+ *
+ * - If sparse inodes are enabled, the holemask field will be active. Each
+ * bit of the holemask represents 4 potential inodes; if set, the
+ * corresponding space does *not* contain inodes and must be left alone.
+ * Clusters cannot be smaller than 4 inodes. The smallest unit of allocation
+ * of inode records is one inode cluster.
+ *
+ * So what's the rebuild algorithm?
+ *
+ * Iterate the reverse mapping records looking for OWN_INODES and OWN_INOBT
+ * records. The OWN_INOBT records are the old inode btree blocks and will be
+ * cleared out after we've rebuilt the tree. Each possible inode cluster
+ * within an OWN_INODES record will be read in; for each possible inobt record
+ * associated with that cluster, compute the freemask calculated from the
+ * i_mode data in the inode chunk. For sparse inodes the holemask will be
+ * calculated by creating the properly aligned inobt record and punching out
+ * any chunk that's missing. Inode allocations and frees grab the AGI first,
+ * so repair protects itself from concurrent access by locking the AGI.
+ *
+ * Once we've reconstructed all the inode records, we can create new inode
+ * btree roots and reload the btrees. We rebuild both inode trees at the same
+ * time because they have the same rmap owner and it would be more complex to
+ * figure out if the other tree isn't in need of a rebuild and which OWN_INOBT
+ * blocks it owns. We have all the data we need to build both, so dump
+ * everything and start over.
+ *
+ * We use the prefix 'xrep_ibt' because we rebuild both inode btrees at once.
+ */
+
+struct xrep_ibt {
+ /* Record under construction. */
+ struct xfs_inobt_rec_incore rie;
+
+ /* new inobt information */
+ struct xrep_newbt new_inobt;
+
+ /* new finobt information */
+ struct xrep_newbt new_finobt;
+
+ /* Old inode btree blocks we found in the rmap. */
+ struct xagb_bitmap old_iallocbt_blocks;
+
+ /* Reconstructed inode records. */
+ struct xfarray *inode_records;
+
+ struct xfs_scrub *sc;
+
+ /* Number of inodes assigned disk space. */
+ unsigned int icount;
+
+ /* Number of inodes in use. */
+ unsigned int iused;
+
+ /* Number of finobt records needed. */
+ unsigned int finobt_recs;
+
+ /* get_records()'s position in the inode record array. */
+ xfarray_idx_t array_cur;
+};
+
+/*
+ * Is this inode in use? If the inode is in memory we can tell from i_mode,
+ * otherwise we have to check di_mode in the on-disk buffer. We only care
+ * that the high (i.e. non-permission) bits of _mode are zero. This should be
+ * safe because repair keeps all AG headers locked until the end, and process
+ * trying to perform an inode allocation/free must lock the AGI.
+ *
+ * @cluster_ag_base is the inode offset of the cluster within the AG.
+ * @cluster_bp is the cluster buffer.
+ * @cluster_index is the inode offset within the inode cluster.
+ */
+STATIC int
+xrep_ibt_check_ifree(
+ struct xrep_ibt *ri,
+ xfs_agino_t cluster_ag_base,
+ struct xfs_buf *cluster_bp,
+ unsigned int cluster_index,
+ bool *inuse)
+{
+ struct xfs_scrub *sc = ri->sc;
+ struct xfs_mount *mp = sc->mp;
+ struct xfs_dinode *dip;
+ xfs_ino_t fsino;
+ xfs_agino_t agino;
+ xfs_agnumber_t agno = ri->sc->sa.pag->pag_agno;
+ unsigned int cluster_buf_base;
+ unsigned int offset;
+ int error;
+
+ agino = cluster_ag_base + cluster_index;
+ fsino = XFS_AGINO_TO_INO(mp, agno, agino);
+
+ /* Inode uncached or half assembled, read disk buffer */
+ cluster_buf_base = XFS_INO_TO_OFFSET(mp, cluster_ag_base);
+ offset = (cluster_buf_base + cluster_index) * mp->m_sb.sb_inodesize;
+ if (offset >= BBTOB(cluster_bp->b_length))
+ return -EFSCORRUPTED;
+ dip = xfs_buf_offset(cluster_bp, offset);
+ if (be16_to_cpu(dip->di_magic) != XFS_DINODE_MAGIC)
+ return -EFSCORRUPTED;
+
+ if (dip->di_version >= 3 && be64_to_cpu(dip->di_ino) != fsino)
+ return -EFSCORRUPTED;
+
+ /* Will the in-core inode tell us if it's in use? */
+ error = xchk_inode_is_allocated(sc, agino, inuse);
+ if (!error)
+ return 0;
+
+ *inuse = dip->di_mode != 0;
+ return 0;
+}
+
+/* Stash the accumulated inobt record for rebuilding. */
+STATIC int
+xrep_ibt_stash(
+ struct xrep_ibt *ri)
+{
+ int error = 0;
+
+ if (xchk_should_terminate(ri->sc, &error))
+ return error;
+
+ ri->rie.ir_freecount = xfs_inobt_rec_freecount(&ri->rie);
+ if (xfs_inobt_check_irec(ri->sc->sa.pag, &ri->rie) != NULL)
+ return -EFSCORRUPTED;
+
+ if (ri->rie.ir_freecount > 0)
+ ri->finobt_recs++;
+
+ trace_xrep_ibt_found(ri->sc->mp, ri->sc->sa.pag->pag_agno, &ri->rie);
+
+ error = xfarray_append(ri->inode_records, &ri->rie);
+ if (error)
+ return error;
+
+ ri->rie.ir_startino = NULLAGINO;
+ return 0;
+}
+
+/*
+ * Given an extent of inodes and an inode cluster buffer, calculate the
+ * location of the corresponding inobt record (creating it if necessary),
+ * then update the parts of the holemask and freemask of that record that
+ * correspond to the inode extent we were given.
+ *
+ * @cluster_ir_startino is the AG inode number of an inobt record that we're
+ * proposing to create for this inode cluster. If sparse inodes are enabled,
+ * we must round down to a chunk boundary to find the actual sparse record.
+ * @cluster_bp is the buffer of the inode cluster.
+ * @nr_inodes is the number of inodes to check from the cluster.
+ */
+STATIC int
+xrep_ibt_cluster_record(
+ struct xrep_ibt *ri,
+ xfs_agino_t cluster_ir_startino,
+ struct xfs_buf *cluster_bp,
+ unsigned int nr_inodes)
+{
+ struct xfs_scrub *sc = ri->sc;
+ struct xfs_mount *mp = sc->mp;
+ xfs_agino_t ir_startino;
+ unsigned int cluster_base;
+ unsigned int cluster_index;
+ int error = 0;
+
+ ir_startino = cluster_ir_startino;
+ if (xfs_has_sparseinodes(mp))
+ ir_startino = rounddown(ir_startino, XFS_INODES_PER_CHUNK);
+ cluster_base = cluster_ir_startino - ir_startino;
+
+ /*
+ * If the accumulated inobt record doesn't map this cluster, add it to
+ * the list and reset it.
+ */
+ if (ri->rie.ir_startino != NULLAGINO &&
+ ri->rie.ir_startino + XFS_INODES_PER_CHUNK <= ir_startino) {
+ error = xrep_ibt_stash(ri);
+ if (error)
+ return error;
+ }
+
+ if (ri->rie.ir_startino == NULLAGINO) {
+ ri->rie.ir_startino = ir_startino;
+ ri->rie.ir_free = XFS_INOBT_ALL_FREE;
+ ri->rie.ir_holemask = 0xFFFF;
+ ri->rie.ir_count = 0;
+ }
+
+ /* Record the whole cluster. */
+ ri->icount += nr_inodes;
+ ri->rie.ir_count += nr_inodes;
+ ri->rie.ir_holemask &= ~xfs_inobt_maskn(
+ cluster_base / XFS_INODES_PER_HOLEMASK_BIT,
+ nr_inodes / XFS_INODES_PER_HOLEMASK_BIT);
+
+ /* Which inodes within this cluster are free? */
+ for (cluster_index = 0; cluster_index < nr_inodes; cluster_index++) {
+ bool inuse = false;
+
+ error = xrep_ibt_check_ifree(ri, cluster_ir_startino,
+ cluster_bp, cluster_index, &inuse);
+ if (error)
+ return error;
+ if (!inuse)
+ continue;
+ ri->iused++;
+ ri->rie.ir_free &= ~XFS_INOBT_MASK(cluster_base +
+ cluster_index);
+ }
+ return 0;
+}
+
+/*
+ * For each inode cluster covering the physical extent recorded by the rmapbt,
+ * we must calculate the properly aligned startino of that cluster, then
+ * iterate each cluster to fill in used and filled masks appropriately. We
+ * then use the (startino, used, filled) information to construct the
+ * appropriate inode records.
+ */
+STATIC int
+xrep_ibt_process_cluster(
+ struct xrep_ibt *ri,
+ xfs_agblock_t cluster_bno)
+{
+ struct xfs_imap imap;
+ struct xfs_buf *cluster_bp;
+ struct xfs_scrub *sc = ri->sc;
+ struct xfs_mount *mp = sc->mp;
+ struct xfs_ino_geometry *igeo = M_IGEO(mp);
+ xfs_agino_t cluster_ag_base;
+ xfs_agino_t irec_index;
+ unsigned int nr_inodes;
+ int error;
+
+ nr_inodes = min_t(unsigned int, igeo->inodes_per_cluster,
+ XFS_INODES_PER_CHUNK);
+
+ /*
+ * Grab the inode cluster buffer. This is safe to do with a broken
+ * inobt because imap_to_bp directly maps the buffer without touching
+ * either inode btree.
+ */
+ imap.im_blkno = XFS_AGB_TO_DADDR(mp, sc->sa.pag->pag_agno, cluster_bno);
+ imap.im_len = XFS_FSB_TO_BB(mp, igeo->blocks_per_cluster);
+ imap.im_boffset = 0;
+ error = xfs_imap_to_bp(mp, sc->tp, &imap, &cluster_bp);
+ if (error)
+ return error;
+
+ /*
+ * Record the contents of each possible inobt record mapping this
+ * cluster.
+ */
+ cluster_ag_base = XFS_AGB_TO_AGINO(mp, cluster_bno);
+ for (irec_index = 0;
+ irec_index < igeo->inodes_per_cluster;
+ irec_index += XFS_INODES_PER_CHUNK) {
+ error = xrep_ibt_cluster_record(ri,
+ cluster_ag_base + irec_index, cluster_bp,
+ nr_inodes);
+ if (error)
+ break;
+
+ }
+
+ xfs_trans_brelse(sc->tp, cluster_bp);
+ return error;
+}
+
+/* Check for any obvious conflicts in the inode chunk extent. */
+STATIC int
+xrep_ibt_check_inode_ext(
+ struct xfs_scrub *sc,
+ xfs_agblock_t agbno,
+ xfs_extlen_t len)
+{
+ struct xfs_mount *mp = sc->mp;
+ struct xfs_ino_geometry *igeo = M_IGEO(mp);
+ xfs_agino_t agino;
+ enum xbtree_recpacking outcome;
+ int error;
+
+ /* Inode records must be within the AG. */
+ if (!xfs_verify_agbext(sc->sa.pag, agbno, len))
+ return -EFSCORRUPTED;
+
+ /* The entire record must align to the inode cluster size. */
+ if (!IS_ALIGNED(agbno, igeo->blocks_per_cluster) ||
+ !IS_ALIGNED(agbno + len, igeo->blocks_per_cluster))
+ return -EFSCORRUPTED;
+
+ /*
+ * The entire record must also adhere to the inode cluster alignment
+ * size if sparse inodes are not enabled.
+ */
+ if (!xfs_has_sparseinodes(mp) &&
+ (!IS_ALIGNED(agbno, igeo->cluster_align) ||
+ !IS_ALIGNED(agbno + len, igeo->cluster_align)))
+ return -EFSCORRUPTED;
+
+ /*
+ * On a sparse inode fs, this cluster could be part of a sparse chunk.
+ * Sparse clusters must be aligned to sparse chunk alignment.
+ */
+ if (xfs_has_sparseinodes(mp) &&
+ (!IS_ALIGNED(agbno, mp->m_sb.sb_spino_align) ||
+ !IS_ALIGNED(agbno + len, mp->m_sb.sb_spino_align)))
+ return -EFSCORRUPTED;
+
+ /* Make sure the entire range of blocks are valid AG inodes. */
+ agino = XFS_AGB_TO_AGINO(mp, agbno);
+ if (!xfs_verify_agino(sc->sa.pag, agino))
+ return -EFSCORRUPTED;
+
+ agino = XFS_AGB_TO_AGINO(mp, agbno + len) - 1;
+ if (!xfs_verify_agino(sc->sa.pag, agino))
+ return -EFSCORRUPTED;
+
+ /* Make sure this isn't free space. */
+ error = xfs_alloc_has_records(sc->sa.bno_cur, agbno, len, &outcome);
+ if (error)
+ return error;
+ if (outcome != XBTREE_RECPACKING_EMPTY)
+ return -EFSCORRUPTED;
+
+ return 0;
+}
+
+/* Found a fragment of the old inode btrees; dispose of them later. */
+STATIC int
+xrep_ibt_record_old_btree_blocks(
+ struct xrep_ibt *ri,
+ const struct xfs_rmap_irec *rec)
+{
+ if (!xfs_verify_agbext(ri->sc->sa.pag, rec->rm_startblock,
+ rec->rm_blockcount))
+ return -EFSCORRUPTED;
+
+ return xagb_bitmap_set(&ri->old_iallocbt_blocks, rec->rm_startblock,
+ rec->rm_blockcount);
+}
+
+/* Record extents that belong to inode cluster blocks. */
+STATIC int
+xrep_ibt_record_inode_blocks(
+ struct xrep_ibt *ri,
+ const struct xfs_rmap_irec *rec)
+{
+ struct xfs_mount *mp = ri->sc->mp;
+ struct xfs_ino_geometry *igeo = M_IGEO(mp);
+ xfs_agblock_t cluster_base;
+ int error;
+
+ error = xrep_ibt_check_inode_ext(ri->sc, rec->rm_startblock,
+ rec->rm_blockcount);
+ if (error)
+ return error;
+
+ trace_xrep_ibt_walk_rmap(mp, ri->sc->sa.pag->pag_agno,
+ rec->rm_startblock, rec->rm_blockcount, rec->rm_owner,
+ rec->rm_offset, rec->rm_flags);
+
+ /*
+ * Record the free/hole masks for each inode cluster that could be
+ * mapped by this rmap record.
+ */
+ for (cluster_base = 0;
+ cluster_base < rec->rm_blockcount;
+ cluster_base += igeo->blocks_per_cluster) {
+ error = xrep_ibt_process_cluster(ri,
+ rec->rm_startblock + cluster_base);
+ if (error)
+ return error;
+ }
+
+ return 0;
+}
+
+STATIC int
+xrep_ibt_walk_rmap(
+ struct xfs_btree_cur *cur,
+ const struct xfs_rmap_irec *rec,
+ void *priv)
+{
+ struct xrep_ibt *ri = priv;
+ int error = 0;
+
+ if (xchk_should_terminate(ri->sc, &error))
+ return error;
+
+ switch (rec->rm_owner) {
+ case XFS_RMAP_OWN_INOBT:
+ return xrep_ibt_record_old_btree_blocks(ri, rec);
+ case XFS_RMAP_OWN_INODES:
+ return xrep_ibt_record_inode_blocks(ri, rec);
+ }
+ return 0;
+}
+
+/*
+ * Iterate all reverse mappings to find the inodes (OWN_INODES) and the inode
+ * btrees (OWN_INOBT). Figure out if we have enough free space to reconstruct
+ * the inode btrees. The caller must clean up the lists if anything goes
+ * wrong.
+ */
+STATIC int
+xrep_ibt_find_inodes(
+ struct xrep_ibt *ri)
+{
+ struct xfs_scrub *sc = ri->sc;
+ int error;
+
+ ri->rie.ir_startino = NULLAGINO;
+
+ /* Collect all reverse mappings for inode blocks. */
+ xrep_ag_btcur_init(sc, &sc->sa);
+ error = xfs_rmap_query_all(sc->sa.rmap_cur, xrep_ibt_walk_rmap, ri);
+ xchk_ag_btcur_free(&sc->sa);
+ if (error)
+ return error;
+
+ /* If we have a record ready to go, add it to the array. */
+ if (ri->rie.ir_startino != NULLAGINO)
+ return xrep_ibt_stash(ri);
+
+ return 0;
+}
+
+/* Update the AGI counters. */
+STATIC int
+xrep_ibt_reset_counters(
+ struct xrep_ibt *ri)
+{
+ struct xfs_scrub *sc = ri->sc;
+ struct xfs_agi *agi = sc->sa.agi_bp->b_addr;
+ unsigned int freecount = ri->icount - ri->iused;
+
+ /* Trigger inode count recalculation */
+ xfs_force_summary_recalc(sc->mp);
+
+ /*
+ * The AGI header contains extra information related to the inode
+ * btrees, so we must update those fields here.
+ */
+ agi->agi_count = cpu_to_be32(ri->icount);
+ agi->agi_freecount = cpu_to_be32(freecount);
+ xfs_ialloc_log_agi(sc->tp, sc->sa.agi_bp,
+ XFS_AGI_COUNT | XFS_AGI_FREECOUNT);
+
+ /* Reinitialize with the values we just logged. */
+ return xrep_reinit_pagi(sc);
+}
+
+/* Retrieve finobt data for bulk load. */
+STATIC int
+xrep_fibt_get_records(
+ struct xfs_btree_cur *cur,
+ unsigned int idx,
+ struct xfs_btree_block *block,
+ unsigned int nr_wanted,
+ void *priv)
+{
+ struct xfs_inobt_rec_incore *irec = &cur->bc_rec.i;
+ struct xrep_ibt *ri = priv;
+ union xfs_btree_rec *block_rec;
+ unsigned int loaded;
+ int error;
+
+ for (loaded = 0; loaded < nr_wanted; loaded++, idx++) {
+ do {
+ error = xfarray_load(ri->inode_records,
+ ri->array_cur++, irec);
+ } while (error == 0 && xfs_inobt_rec_freecount(irec) == 0);
+ if (error)
+ return error;
+
+ block_rec = xfs_btree_rec_addr(cur, idx, block);
+ cur->bc_ops->init_rec_from_cur(cur, block_rec);
+ }
+
+ return loaded;
+}
+
+/* Retrieve inobt data for bulk load. */
+STATIC int
+xrep_ibt_get_records(
+ struct xfs_btree_cur *cur,
+ unsigned int idx,
+ struct xfs_btree_block *block,
+ unsigned int nr_wanted,
+ void *priv)
+{
+ struct xfs_inobt_rec_incore *irec = &cur->bc_rec.i;
+ struct xrep_ibt *ri = priv;
+ union xfs_btree_rec *block_rec;
+ unsigned int loaded;
+ int error;
+
+ for (loaded = 0; loaded < nr_wanted; loaded++, idx++) {
+ error = xfarray_load(ri->inode_records, ri->array_cur++, irec);
+ if (error)
+ return error;
+
+ block_rec = xfs_btree_rec_addr(cur, idx, block);
+ cur->bc_ops->init_rec_from_cur(cur, block_rec);
+ }
+
+ return loaded;
+}
+
+/* Feed one of the new inobt blocks to the bulk loader. */
+STATIC int
+xrep_ibt_claim_block(
+ struct xfs_btree_cur *cur,
+ union xfs_btree_ptr *ptr,
+ void *priv)
+{
+ struct xrep_ibt *ri = priv;
+
+ return xrep_newbt_claim_block(cur, &ri->new_inobt, ptr);
+}
+
+/* Feed one of the new finobt blocks to the bulk loader. */
+STATIC int
+xrep_fibt_claim_block(
+ struct xfs_btree_cur *cur,
+ union xfs_btree_ptr *ptr,
+ void *priv)
+{
+ struct xrep_ibt *ri = priv;
+
+ return xrep_newbt_claim_block(cur, &ri->new_finobt, ptr);
+}
+
+/* Make sure the records do not overlap in inumber address space. */
+STATIC int
+xrep_ibt_check_overlap(
+ struct xrep_ibt *ri)
+{
+ struct xfs_inobt_rec_incore irec;
+ xfarray_idx_t cur;
+ xfs_agino_t next_agino = 0;
+ int error = 0;
+
+ foreach_xfarray_idx(ri->inode_records, cur) {
+ if (xchk_should_terminate(ri->sc, &error))
+ return error;
+
+ error = xfarray_load(ri->inode_records, cur, &irec);
+ if (error)
+ return error;
+
+ if (irec.ir_startino < next_agino)
+ return -EFSCORRUPTED;
+
+ next_agino = irec.ir_startino + XFS_INODES_PER_CHUNK;
+ }
+
+ return error;
+}
+
+/* Build new inode btrees and dispose of the old one. */
+STATIC int
+xrep_ibt_build_new_trees(
+ struct xrep_ibt *ri)
+{
+ struct xfs_scrub *sc = ri->sc;
+ struct xfs_btree_cur *ino_cur;
+ struct xfs_btree_cur *fino_cur = NULL;
+ xfs_fsblock_t fsbno;
+ bool need_finobt;
+ int error;
+
+ need_finobt = xfs_has_finobt(sc->mp);
+
+ /*
+ * Create new btrees for staging all the inobt records we collected
+ * earlier. The records were collected in order of increasing agino,
+ * so we do not have to sort them. Ensure there are no overlapping
+ * records.
+ */
+ error = xrep_ibt_check_overlap(ri);
+ if (error)
+ return error;
+
+ /*
+ * The new inode btrees will not be rooted in the AGI until we've
+ * successfully rebuilt the tree.
+ *
+ * Start by setting up the inobt staging cursor.
+ */
+ fsbno = XFS_AGB_TO_FSB(sc->mp, sc->sa.pag->pag_agno,
+ XFS_IBT_BLOCK(sc->mp)),
+ xrep_newbt_init_ag(&ri->new_inobt, sc, &XFS_RMAP_OINFO_INOBT, fsbno,
+ XFS_AG_RESV_NONE);
+ ri->new_inobt.bload.claim_block = xrep_ibt_claim_block;
+ ri->new_inobt.bload.get_records = xrep_ibt_get_records;
+
+ ino_cur = xfs_inobt_stage_cursor(sc->sa.pag, &ri->new_inobt.afake,
+ XFS_BTNUM_INO);
+ error = xfs_btree_bload_compute_geometry(ino_cur, &ri->new_inobt.bload,
+ xfarray_length(ri->inode_records));
+ if (error)
+ goto err_inocur;
+
+ /* Set up finobt staging cursor. */
+ if (need_finobt) {
+ enum xfs_ag_resv_type resv = XFS_AG_RESV_METADATA;
+
+ if (sc->mp->m_finobt_nores)
+ resv = XFS_AG_RESV_NONE;
+
+ fsbno = XFS_AGB_TO_FSB(sc->mp, sc->sa.pag->pag_agno,
+ XFS_FIBT_BLOCK(sc->mp)),
+ xrep_newbt_init_ag(&ri->new_finobt, sc, &XFS_RMAP_OINFO_INOBT,
+ fsbno, resv);
+ ri->new_finobt.bload.claim_block = xrep_fibt_claim_block;
+ ri->new_finobt.bload.get_records = xrep_fibt_get_records;
+
+ fino_cur = xfs_inobt_stage_cursor(sc->sa.pag,
+ &ri->new_finobt.afake, XFS_BTNUM_FINO);
+ error = xfs_btree_bload_compute_geometry(fino_cur,
+ &ri->new_finobt.bload, ri->finobt_recs);
+ if (error)
+ goto err_finocur;
+ }
+
+ /* Last chance to abort before we start committing fixes. */
+ if (xchk_should_terminate(sc, &error))
+ goto err_finocur;
+
+ /* Reserve all the space we need to build the new btrees. */
+ error = xrep_newbt_alloc_blocks(&ri->new_inobt,
+ ri->new_inobt.bload.nr_blocks);
+ if (error)
+ goto err_finocur;
+
+ if (need_finobt) {
+ error = xrep_newbt_alloc_blocks(&ri->new_finobt,
+ ri->new_finobt.bload.nr_blocks);
+ if (error)
+ goto err_finocur;
+ }
+
+ /* Add all inobt records. */
+ ri->array_cur = XFARRAY_CURSOR_INIT;
+ error = xfs_btree_bload(ino_cur, &ri->new_inobt.bload, ri);
+ if (error)
+ goto err_finocur;
+
+ /* Add all finobt records. */
+ if (need_finobt) {
+ ri->array_cur = XFARRAY_CURSOR_INIT;
+ error = xfs_btree_bload(fino_cur, &ri->new_finobt.bload, ri);
+ if (error)
+ goto err_finocur;
+ }
+
+ /*
+ * Install the new btrees in the AG header. After this point the old
+ * btrees are no longer accessible and the new trees are live.
+ */
+ xfs_inobt_commit_staged_btree(ino_cur, sc->tp, sc->sa.agi_bp);
+ xfs_btree_del_cursor(ino_cur, 0);
+
+ if (fino_cur) {
+ xfs_inobt_commit_staged_btree(fino_cur, sc->tp, sc->sa.agi_bp);
+ xfs_btree_del_cursor(fino_cur, 0);
+ }
+
+ /* Reset the AGI counters now that we've changed the inode roots. */
+ error = xrep_ibt_reset_counters(ri);
+ if (error)
+ goto err_finobt;
+
+ /* Free unused blocks and bitmap. */
+ if (need_finobt) {
+ error = xrep_newbt_commit(&ri->new_finobt);
+ if (error)
+ goto err_inobt;
+ }
+ error = xrep_newbt_commit(&ri->new_inobt);
+ if (error)
+ return error;
+
+ return xrep_roll_ag_trans(sc);
+
+err_finocur:
+ if (need_finobt)
+ xfs_btree_del_cursor(fino_cur, error);
+err_inocur:
+ xfs_btree_del_cursor(ino_cur, error);
+err_finobt:
+ if (need_finobt)
+ xrep_newbt_cancel(&ri->new_finobt);
+err_inobt:
+ xrep_newbt_cancel(&ri->new_inobt);
+ return error;
+}
+
+/*
+ * Now that we've logged the roots of the new btrees, invalidate all of the
+ * old blocks and free them.
+ */
+STATIC int
+xrep_ibt_remove_old_trees(
+ struct xrep_ibt *ri)
+{
+ struct xfs_scrub *sc = ri->sc;
+ int error;
+
+ /*
+ * Free the old inode btree blocks if they're not in use. It's ok to
+ * reap with XFS_AG_RESV_NONE even if the finobt had a per-AG
+ * reservation because we reset the reservation before releasing the
+ * AGI and AGF header buffer locks.
+ */
+ error = xrep_reap_agblocks(sc, &ri->old_iallocbt_blocks,
+ &XFS_RMAP_OINFO_INOBT, XFS_AG_RESV_NONE);
+ if (error)
+ return error;
+
+ /*
+ * If the finobt is enabled and has a per-AG reservation, make sure we
+ * reinitialize the per-AG reservations.
+ */
+ if (xfs_has_finobt(sc->mp) && !sc->mp->m_finobt_nores)
+ sc->flags |= XREP_RESET_PERAG_RESV;
+
+ return 0;
+}
+
+/* Repair both inode btrees. */
+int
+xrep_iallocbt(
+ struct xfs_scrub *sc)
+{
+ struct xrep_ibt *ri;
+ struct xfs_mount *mp = sc->mp;
+ char *descr;
+ xfs_agino_t first_agino, last_agino;
+ int error = 0;
+
+ /* We require the rmapbt to rebuild anything. */
+ if (!xfs_has_rmapbt(mp))
+ return -EOPNOTSUPP;
+
+ ri = kzalloc(sizeof(struct xrep_ibt), XCHK_GFP_FLAGS);
+ if (!ri)
+ return -ENOMEM;
+ ri->sc = sc;
+
+ /* We rebuild both inode btrees. */
+ sc->sick_mask = XFS_SICK_AG_INOBT | XFS_SICK_AG_FINOBT;
+
+ /* Set up enough storage to handle an AG with nothing but inodes. */
+ xfs_agino_range(mp, sc->sa.pag->pag_agno, &first_agino, &last_agino);
+ last_agino /= XFS_INODES_PER_CHUNK;
+ descr = xchk_xfile_ag_descr(sc, "inode index records");
+ error = xfarray_create(descr, last_agino,
+ sizeof(struct xfs_inobt_rec_incore),
+ &ri->inode_records);
+ kfree(descr);
+ if (error)
+ goto out_ri;
+
+ /* Collect the inode data and find the old btree blocks. */
+ xagb_bitmap_init(&ri->old_iallocbt_blocks);
+ error = xrep_ibt_find_inodes(ri);
+ if (error)
+ goto out_bitmap;
+
+ /* Rebuild the inode indexes. */
+ error = xrep_ibt_build_new_trees(ri);
+ if (error)
+ goto out_bitmap;
+
+ /* Kill the old tree. */
+ error = xrep_ibt_remove_old_trees(ri);
+ if (error)
+ goto out_bitmap;
+
+out_bitmap:
+ xagb_bitmap_destroy(&ri->old_iallocbt_blocks);
+ xfarray_destroy(ri->inode_records);
+out_ri:
+ kfree(ri);
+ return error;
+}
+
+/* Make sure both btrees are ok after we've rebuilt them. */
+int
+xrep_revalidate_iallocbt(
+ struct xfs_scrub *sc)
+{
+ __u32 old_type = sc->sm->sm_type;
+ int error;
+
+ /*
+ * We must update sm_type temporarily so that the tree-to-tree cross
+ * reference checks will work in the correct direction, and also so
+ * that tracing will report correctly if there are more errors.
+ */
+ sc->sm->sm_type = XFS_SCRUB_TYPE_INOBT;
+ error = xchk_iallocbt(sc);
+ if (error)
+ goto out;
+
+ if (xfs_has_finobt(sc->mp)) {
+ sc->sm->sm_type = XFS_SCRUB_TYPE_FINOBT;
+ error = xchk_iallocbt(sc);
+ }
+
+out:
+ sc->sm->sm_type = old_type;
+ return error;
+}
diff --git a/fs/xfs/scrub/inode.c b/fs/xfs/scrub/inode.c
index 889f556bc98f..6e2fe2d6250b 100644
--- a/fs/xfs/scrub/inode.c
+++ b/fs/xfs/scrub/inode.c
@@ -25,6 +25,7 @@
#include "scrub/common.h"
#include "scrub/btree.h"
#include "scrub/trace.h"
+#include "scrub/repair.h"
/* Prepare the attached inode for scrubbing. */
static inline int
@@ -39,6 +40,10 @@ xchk_prepare_iscrub(
if (error)
return error;
+ error = xchk_ino_dqattach(sc);
+ if (error)
+ return error;
+
xchk_ilock(sc, XFS_ILOCK_EXCL);
return 0;
}
@@ -95,8 +100,8 @@ xchk_setup_inode(
if (!xfs_verify_ino(sc->mp, sc->sm->sm_ino))
return -ENOENT;
- /* Try a regular untrusted iget. */
- error = xchk_iget(sc, sc->sm->sm_ino, &ip);
+ /* Try a safe untrusted iget. */
+ error = xchk_iget_safe(sc, sc->sm->sm_ino, &ip);
if (!error)
return xchk_install_handle_iscrub(sc, ip);
if (error == -ENOENT)
@@ -181,8 +186,11 @@ xchk_setup_inode(
* saying the inode is allocated and the icache being unable to load
* the inode until we can flag the corruption in xchk_inode. The
* scrub function has to note the corruption, since we're not really
- * supposed to do that from the setup function.
+ * supposed to do that from the setup function. Save the mapping to
+ * make repairs to the ondisk inode buffer.
*/
+ if (xchk_could_repair(sc))
+ xrep_setup_inode(sc, &imap);
return 0;
out_cancel:
@@ -338,6 +346,10 @@ xchk_inode_flags2(
if (xfs_dinode_has_bigtime(dip) && !xfs_has_bigtime(mp))
goto bad;
+ /* no large extent counts without the filesystem feature */
+ if ((flags2 & XFS_DIFLAG2_NREXT64) && !xfs_has_large_extent_counts(mp))
+ goto bad;
+
return;
bad:
xchk_ino_set_corrupt(sc, ino);
@@ -548,7 +560,7 @@ xchk_dinode(
}
/* di_forkoff */
- if (XFS_DFORK_APTR(dip) >= (char *)dip + mp->m_sb.sb_inodesize)
+ if (XFS_DFORK_BOFF(dip) >= mp->m_sb.sb_inodesize)
xchk_ino_set_corrupt(sc, ino);
if (naextents != 0 && dip->di_forkoff == 0)
xchk_ino_set_corrupt(sc, ino);
diff --git a/fs/xfs/scrub/inode_repair.c b/fs/xfs/scrub/inode_repair.c
new file mode 100644
index 000000000000..0ca62d59f84a
--- /dev/null
+++ b/fs/xfs/scrub/inode_repair.c
@@ -0,0 +1,1525 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2018-2023 Oracle. All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_defer.h"
+#include "xfs_btree.h"
+#include "xfs_bit.h"
+#include "xfs_log_format.h"
+#include "xfs_trans.h"
+#include "xfs_sb.h"
+#include "xfs_inode.h"
+#include "xfs_icache.h"
+#include "xfs_inode_buf.h"
+#include "xfs_inode_fork.h"
+#include "xfs_ialloc.h"
+#include "xfs_da_format.h"
+#include "xfs_reflink.h"
+#include "xfs_alloc.h"
+#include "xfs_rmap.h"
+#include "xfs_rmap_btree.h"
+#include "xfs_bmap.h"
+#include "xfs_bmap_btree.h"
+#include "xfs_bmap_util.h"
+#include "xfs_dir2.h"
+#include "xfs_dir2_priv.h"
+#include "xfs_quota_defs.h"
+#include "xfs_quota.h"
+#include "xfs_ag.h"
+#include "xfs_rtbitmap.h"
+#include "xfs_attr_leaf.h"
+#include "xfs_log_priv.h"
+#include "xfs_health.h"
+#include "scrub/xfs_scrub.h"
+#include "scrub/scrub.h"
+#include "scrub/common.h"
+#include "scrub/btree.h"
+#include "scrub/trace.h"
+#include "scrub/repair.h"
+
+/*
+ * Inode Record Repair
+ * ===================
+ *
+ * Roughly speaking, inode problems can be classified based on whether or not
+ * they trip the dinode verifiers. If those trip, then we won't be able to
+ * xfs_iget ourselves the inode.
+ *
+ * Therefore, the xrep_dinode_* functions fix anything that will cause the
+ * inode buffer verifier or the dinode verifier. The xrep_inode_* functions
+ * fix things on live incore inodes. The inode repair functions make decisions
+ * with security and usability implications when reviving a file:
+ *
+ * - Files with zero di_mode or a garbage di_mode are converted to regular file
+ * that only root can read. This file may not actually contain user data,
+ * if the file was not previously a regular file. Setuid and setgid bits
+ * are cleared.
+ *
+ * - Zero-size directories can be truncated to look empty. It is necessary to
+ * run the bmapbtd and directory repair functions to fully rebuild the
+ * directory.
+ *
+ * - Zero-size symbolic link targets can be truncated to '?'. It is necessary
+ * to run the bmapbtd and symlink repair functions to salvage the symlink.
+ *
+ * - Invalid extent size hints will be removed.
+ *
+ * - Quotacheck will be scheduled if we repaired an inode that was so badly
+ * damaged that the ondisk inode had to be rebuilt.
+ *
+ * - Invalid user, group, or project IDs (aka -1U) will be reset to zero.
+ * Setuid and setgid bits are cleared.
+ *
+ * - Data and attr forks are reset to extents format with zero extents if the
+ * fork data is inconsistent. It is necessary to run the bmapbtd or bmapbta
+ * repair functions to recover the space mapping.
+ *
+ * - ACLs will not be recovered if the attr fork is zapped or the extended
+ * attribute structure itself requires salvaging.
+ *
+ * - If the attr fork is zapped, the user and group ids are reset to root and
+ * the setuid and setgid bits are removed.
+ */
+
+/*
+ * All the information we need to repair the ondisk inode if we can't iget the
+ * incore inode. We don't allocate this buffer unless we're going to perform
+ * a repair to the ondisk inode cluster buffer.
+ */
+struct xrep_inode {
+ /* Inode mapping that we saved from the initial lookup attempt. */
+ struct xfs_imap imap;
+
+ struct xfs_scrub *sc;
+
+ /* Blocks in use on the data device by data extents or bmbt blocks. */
+ xfs_rfsblock_t data_blocks;
+
+ /* Blocks in use on the rt device. */
+ xfs_rfsblock_t rt_blocks;
+
+ /* Blocks in use by the attr fork. */
+ xfs_rfsblock_t attr_blocks;
+
+ /* Number of data device extents for the data fork. */
+ xfs_extnum_t data_extents;
+
+ /*
+ * Number of realtime device extents for the data fork. If
+ * data_extents and rt_extents indicate that the data fork has extents
+ * on both devices, we'll just back away slowly.
+ */
+ xfs_extnum_t rt_extents;
+
+ /* Number of (data device) extents for the attr fork. */
+ xfs_aextnum_t attr_extents;
+
+ /* Sick state to set after zapping parts of the inode. */
+ unsigned int ino_sick_mask;
+
+ /* Must we remove all access from this file? */
+ bool zap_acls;
+};
+
+/*
+ * Setup function for inode repair. @imap contains the ondisk inode mapping
+ * information so that we can correct the ondisk inode cluster buffer if
+ * necessary to make iget work.
+ */
+int
+xrep_setup_inode(
+ struct xfs_scrub *sc,
+ const struct xfs_imap *imap)
+{
+ struct xrep_inode *ri;
+
+ sc->buf = kzalloc(sizeof(struct xrep_inode), XCHK_GFP_FLAGS);
+ if (!sc->buf)
+ return -ENOMEM;
+
+ ri = sc->buf;
+ memcpy(&ri->imap, imap, sizeof(struct xfs_imap));
+ ri->sc = sc;
+ return 0;
+}
+
+/*
+ * Make sure this ondisk inode can pass the inode buffer verifier. This is
+ * not the same as the dinode verifier.
+ */
+STATIC void
+xrep_dinode_buf_core(
+ struct xfs_scrub *sc,
+ struct xfs_buf *bp,
+ unsigned int ioffset)
+{
+ struct xfs_dinode *dip = xfs_buf_offset(bp, ioffset);
+ struct xfs_trans *tp = sc->tp;
+ struct xfs_mount *mp = sc->mp;
+ xfs_agino_t agino;
+ bool crc_ok = false;
+ bool magic_ok = false;
+ bool unlinked_ok = false;
+
+ agino = be32_to_cpu(dip->di_next_unlinked);
+
+ if (xfs_verify_agino_or_null(bp->b_pag, agino))
+ unlinked_ok = true;
+
+ if (dip->di_magic == cpu_to_be16(XFS_DINODE_MAGIC) &&
+ xfs_dinode_good_version(mp, dip->di_version))
+ magic_ok = true;
+
+ if (xfs_verify_cksum((char *)dip, mp->m_sb.sb_inodesize,
+ XFS_DINODE_CRC_OFF))
+ crc_ok = true;
+
+ if (magic_ok && unlinked_ok && crc_ok)
+ return;
+
+ if (!magic_ok) {
+ dip->di_magic = cpu_to_be16(XFS_DINODE_MAGIC);
+ dip->di_version = 3;
+ }
+ if (!unlinked_ok)
+ dip->di_next_unlinked = cpu_to_be32(NULLAGINO);
+ xfs_dinode_calc_crc(mp, dip);
+ xfs_trans_buf_set_type(tp, bp, XFS_BLFT_DINO_BUF);
+ xfs_trans_log_buf(tp, bp, ioffset,
+ ioffset + sizeof(struct xfs_dinode) - 1);
+}
+
+/* Make sure this inode cluster buffer can pass the inode buffer verifier. */
+STATIC void
+xrep_dinode_buf(
+ struct xfs_scrub *sc,
+ struct xfs_buf *bp)
+{
+ struct xfs_mount *mp = sc->mp;
+ int i;
+ int ni;
+
+ ni = XFS_BB_TO_FSB(mp, bp->b_length) * mp->m_sb.sb_inopblock;
+ for (i = 0; i < ni; i++)
+ xrep_dinode_buf_core(sc, bp, i << mp->m_sb.sb_inodelog);
+}
+
+/* Reinitialize things that never change in an inode. */
+STATIC void
+xrep_dinode_header(
+ struct xfs_scrub *sc,
+ struct xfs_dinode *dip)
+{
+ trace_xrep_dinode_header(sc, dip);
+
+ dip->di_magic = cpu_to_be16(XFS_DINODE_MAGIC);
+ if (!xfs_dinode_good_version(sc->mp, dip->di_version))
+ dip->di_version = 3;
+ dip->di_ino = cpu_to_be64(sc->sm->sm_ino);
+ uuid_copy(&dip->di_uuid, &sc->mp->m_sb.sb_meta_uuid);
+ dip->di_gen = cpu_to_be32(sc->sm->sm_gen);
+}
+
+/* Turn di_mode into /something/ recognizable. */
+STATIC void
+xrep_dinode_mode(
+ struct xrep_inode *ri,
+ struct xfs_dinode *dip)
+{
+ struct xfs_scrub *sc = ri->sc;
+ uint16_t mode = be16_to_cpu(dip->di_mode);
+
+ trace_xrep_dinode_mode(sc, dip);
+
+ if (mode == 0 || xfs_mode_to_ftype(mode) != XFS_DIR3_FT_UNKNOWN)
+ return;
+
+ /* bad mode, so we set it to a file that only root can read */
+ mode = S_IFREG;
+ dip->di_mode = cpu_to_be16(mode);
+ dip->di_uid = 0;
+ dip->di_gid = 0;
+ ri->zap_acls = true;
+}
+
+/* Fix any conflicting flags that the verifiers complain about. */
+STATIC void
+xrep_dinode_flags(
+ struct xfs_scrub *sc,
+ struct xfs_dinode *dip,
+ bool isrt)
+{
+ struct xfs_mount *mp = sc->mp;
+ uint64_t flags2 = be64_to_cpu(dip->di_flags2);
+ uint16_t flags = be16_to_cpu(dip->di_flags);
+ uint16_t mode = be16_to_cpu(dip->di_mode);
+
+ trace_xrep_dinode_flags(sc, dip);
+
+ if (isrt)
+ flags |= XFS_DIFLAG_REALTIME;
+ else
+ flags &= ~XFS_DIFLAG_REALTIME;
+
+ /*
+ * For regular files on a reflink filesystem, set the REFLINK flag to
+ * protect shared extents. A later stage will actually check those
+ * extents and clear the flag if possible.
+ */
+ if (xfs_has_reflink(mp) && S_ISREG(mode))
+ flags2 |= XFS_DIFLAG2_REFLINK;
+ else
+ flags2 &= ~(XFS_DIFLAG2_REFLINK | XFS_DIFLAG2_COWEXTSIZE);
+ if (flags & XFS_DIFLAG_REALTIME)
+ flags2 &= ~XFS_DIFLAG2_REFLINK;
+ if (!xfs_has_bigtime(mp))
+ flags2 &= ~XFS_DIFLAG2_BIGTIME;
+ if (!xfs_has_large_extent_counts(mp))
+ flags2 &= ~XFS_DIFLAG2_NREXT64;
+ if (flags2 & XFS_DIFLAG2_NREXT64)
+ dip->di_nrext64_pad = 0;
+ else if (dip->di_version >= 3)
+ dip->di_v3_pad = 0;
+ dip->di_flags = cpu_to_be16(flags);
+ dip->di_flags2 = cpu_to_be64(flags2);
+}
+
+/*
+ * Blow out symlink; now it points nowhere. We don't have to worry about
+ * incore state because this inode is failing the verifiers.
+ */
+STATIC void
+xrep_dinode_zap_symlink(
+ struct xrep_inode *ri,
+ struct xfs_dinode *dip)
+{
+ struct xfs_scrub *sc = ri->sc;
+ char *p;
+
+ trace_xrep_dinode_zap_symlink(sc, dip);
+
+ dip->di_format = XFS_DINODE_FMT_LOCAL;
+ dip->di_size = cpu_to_be64(1);
+ p = XFS_DFORK_PTR(dip, XFS_DATA_FORK);
+ *p = '?';
+ ri->ino_sick_mask |= XFS_SICK_INO_SYMLINK_ZAPPED;
+}
+
+/*
+ * Blow out dir, make the parent point to the root. In the future repair will
+ * reconstruct this directory for us. Note that there's no in-core directory
+ * inode because the sf verifier tripped, so we don't have to worry about the
+ * dentry cache.
+ */
+STATIC void
+xrep_dinode_zap_dir(
+ struct xrep_inode *ri,
+ struct xfs_dinode *dip)
+{
+ struct xfs_scrub *sc = ri->sc;
+ struct xfs_mount *mp = sc->mp;
+ struct xfs_dir2_sf_hdr *sfp;
+ int i8count;
+
+ trace_xrep_dinode_zap_dir(sc, dip);
+
+ dip->di_format = XFS_DINODE_FMT_LOCAL;
+ i8count = mp->m_sb.sb_rootino > XFS_DIR2_MAX_SHORT_INUM;
+ sfp = XFS_DFORK_PTR(dip, XFS_DATA_FORK);
+ sfp->count = 0;
+ sfp->i8count = i8count;
+ xfs_dir2_sf_put_parent_ino(sfp, mp->m_sb.sb_rootino);
+ dip->di_size = cpu_to_be64(xfs_dir2_sf_hdr_size(i8count));
+ ri->ino_sick_mask |= XFS_SICK_INO_DIR_ZAPPED;
+}
+
+/* Make sure we don't have a garbage file size. */
+STATIC void
+xrep_dinode_size(
+ struct xrep_inode *ri,
+ struct xfs_dinode *dip)
+{
+ struct xfs_scrub *sc = ri->sc;
+ uint64_t size = be64_to_cpu(dip->di_size);
+ uint16_t mode = be16_to_cpu(dip->di_mode);
+
+ trace_xrep_dinode_size(sc, dip);
+
+ switch (mode & S_IFMT) {
+ case S_IFIFO:
+ case S_IFCHR:
+ case S_IFBLK:
+ case S_IFSOCK:
+ /* di_size can't be nonzero for special files */
+ dip->di_size = 0;
+ break;
+ case S_IFREG:
+ /* Regular files can't be larger than 2^63-1 bytes. */
+ dip->di_size = cpu_to_be64(size & ~(1ULL << 63));
+ break;
+ case S_IFLNK:
+ /*
+ * Truncate ridiculously oversized symlinks. If the size is
+ * zero, reset it to point to the current directory. Both of
+ * these conditions trigger dinode verifier errors, so there
+ * is no in-core state to reset.
+ */
+ if (size > XFS_SYMLINK_MAXLEN)
+ dip->di_size = cpu_to_be64(XFS_SYMLINK_MAXLEN);
+ else if (size == 0)
+ xrep_dinode_zap_symlink(ri, dip);
+ break;
+ case S_IFDIR:
+ /*
+ * Directories can't have a size larger than 32G. If the size
+ * is zero, reset it to an empty directory. Both of these
+ * conditions trigger dinode verifier errors, so there is no
+ * in-core state to reset.
+ */
+ if (size > XFS_DIR2_SPACE_SIZE)
+ dip->di_size = cpu_to_be64(XFS_DIR2_SPACE_SIZE);
+ else if (size == 0)
+ xrep_dinode_zap_dir(ri, dip);
+ break;
+ }
+}
+
+/* Fix extent size hints. */
+STATIC void
+xrep_dinode_extsize_hints(
+ struct xfs_scrub *sc,
+ struct xfs_dinode *dip)
+{
+ struct xfs_mount *mp = sc->mp;
+ uint64_t flags2 = be64_to_cpu(dip->di_flags2);
+ uint16_t flags = be16_to_cpu(dip->di_flags);
+ uint16_t mode = be16_to_cpu(dip->di_mode);
+
+ xfs_failaddr_t fa;
+
+ trace_xrep_dinode_extsize_hints(sc, dip);
+
+ fa = xfs_inode_validate_extsize(mp, be32_to_cpu(dip->di_extsize),
+ mode, flags);
+ if (fa) {
+ dip->di_extsize = 0;
+ dip->di_flags &= ~cpu_to_be16(XFS_DIFLAG_EXTSIZE |
+ XFS_DIFLAG_EXTSZINHERIT);
+ }
+
+ if (dip->di_version < 3)
+ return;
+
+ fa = xfs_inode_validate_cowextsize(mp, be32_to_cpu(dip->di_cowextsize),
+ mode, flags, flags2);
+ if (fa) {
+ dip->di_cowextsize = 0;
+ dip->di_flags2 &= ~cpu_to_be64(XFS_DIFLAG2_COWEXTSIZE);
+ }
+}
+
+/* Count extents and blocks for an inode given an rmap. */
+STATIC int
+xrep_dinode_walk_rmap(
+ struct xfs_btree_cur *cur,
+ const struct xfs_rmap_irec *rec,
+ void *priv)
+{
+ struct xrep_inode *ri = priv;
+ int error = 0;
+
+ if (xchk_should_terminate(ri->sc, &error))
+ return error;
+
+ /* We only care about this inode. */
+ if (rec->rm_owner != ri->sc->sm->sm_ino)
+ return 0;
+
+ if (rec->rm_flags & XFS_RMAP_ATTR_FORK) {
+ ri->attr_blocks += rec->rm_blockcount;
+ if (!(rec->rm_flags & XFS_RMAP_BMBT_BLOCK))
+ ri->attr_extents++;
+
+ return 0;
+ }
+
+ ri->data_blocks += rec->rm_blockcount;
+ if (!(rec->rm_flags & XFS_RMAP_BMBT_BLOCK))
+ ri->data_extents++;
+
+ return 0;
+}
+
+/* Count extents and blocks for an inode from all AG rmap data. */
+STATIC int
+xrep_dinode_count_ag_rmaps(
+ struct xrep_inode *ri,
+ struct xfs_perag *pag)
+{
+ struct xfs_btree_cur *cur;
+ struct xfs_buf *agf;
+ int error;
+
+ error = xfs_alloc_read_agf(pag, ri->sc->tp, 0, &agf);
+ if (error)
+ return error;
+
+ cur = xfs_rmapbt_init_cursor(ri->sc->mp, ri->sc->tp, agf, pag);
+ error = xfs_rmap_query_all(cur, xrep_dinode_walk_rmap, ri);
+ xfs_btree_del_cursor(cur, error);
+ xfs_trans_brelse(ri->sc->tp, agf);
+ return error;
+}
+
+/* Count extents and blocks for a given inode from all rmap data. */
+STATIC int
+xrep_dinode_count_rmaps(
+ struct xrep_inode *ri)
+{
+ struct xfs_perag *pag;
+ xfs_agnumber_t agno;
+ int error;
+
+ if (!xfs_has_rmapbt(ri->sc->mp) || xfs_has_realtime(ri->sc->mp))
+ return -EOPNOTSUPP;
+
+ for_each_perag(ri->sc->mp, agno, pag) {
+ error = xrep_dinode_count_ag_rmaps(ri, pag);
+ if (error) {
+ xfs_perag_rele(pag);
+ return error;
+ }
+ }
+
+ /* Can't have extents on both the rt and the data device. */
+ if (ri->data_extents && ri->rt_extents)
+ return -EFSCORRUPTED;
+
+ trace_xrep_dinode_count_rmaps(ri->sc,
+ ri->data_blocks, ri->rt_blocks, ri->attr_blocks,
+ ri->data_extents, ri->rt_extents, ri->attr_extents);
+ return 0;
+}
+
+/* Return true if this extents-format ifork looks like garbage. */
+STATIC bool
+xrep_dinode_bad_extents_fork(
+ struct xfs_scrub *sc,
+ struct xfs_dinode *dip,
+ unsigned int dfork_size,
+ int whichfork)
+{
+ struct xfs_bmbt_irec new;
+ struct xfs_bmbt_rec *dp;
+ xfs_extnum_t nex;
+ bool isrt;
+ unsigned int i;
+
+ nex = xfs_dfork_nextents(dip, whichfork);
+ if (nex > dfork_size / sizeof(struct xfs_bmbt_rec))
+ return true;
+
+ dp = XFS_DFORK_PTR(dip, whichfork);
+
+ isrt = dip->di_flags & cpu_to_be16(XFS_DIFLAG_REALTIME);
+ for (i = 0; i < nex; i++, dp++) {
+ xfs_failaddr_t fa;
+
+ xfs_bmbt_disk_get_all(dp, &new);
+ fa = xfs_bmap_validate_extent_raw(sc->mp, isrt, whichfork,
+ &new);
+ if (fa)
+ return true;
+ }
+
+ return false;
+}
+
+/* Return true if this btree-format ifork looks like garbage. */
+STATIC bool
+xrep_dinode_bad_bmbt_fork(
+ struct xfs_scrub *sc,
+ struct xfs_dinode *dip,
+ unsigned int dfork_size,
+ int whichfork)
+{
+ struct xfs_bmdr_block *dfp;
+ xfs_extnum_t nex;
+ unsigned int i;
+ unsigned int dmxr;
+ unsigned int nrecs;
+ unsigned int level;
+
+ nex = xfs_dfork_nextents(dip, whichfork);
+ if (nex <= dfork_size / sizeof(struct xfs_bmbt_rec))
+ return true;
+
+ if (dfork_size < sizeof(struct xfs_bmdr_block))
+ return true;
+
+ dfp = XFS_DFORK_PTR(dip, whichfork);
+ nrecs = be16_to_cpu(dfp->bb_numrecs);
+ level = be16_to_cpu(dfp->bb_level);
+
+ if (nrecs == 0 || XFS_BMDR_SPACE_CALC(nrecs) > dfork_size)
+ return true;
+ if (level == 0 || level >= XFS_BM_MAXLEVELS(sc->mp, whichfork))
+ return true;
+
+ dmxr = xfs_bmdr_maxrecs(dfork_size, 0);
+ for (i = 1; i <= nrecs; i++) {
+ struct xfs_bmbt_key *fkp;
+ xfs_bmbt_ptr_t *fpp;
+ xfs_fileoff_t fileoff;
+ xfs_fsblock_t fsbno;
+
+ fkp = XFS_BMDR_KEY_ADDR(dfp, i);
+ fileoff = be64_to_cpu(fkp->br_startoff);
+ if (!xfs_verify_fileoff(sc->mp, fileoff))
+ return true;
+
+ fpp = XFS_BMDR_PTR_ADDR(dfp, i, dmxr);
+ fsbno = be64_to_cpu(*fpp);
+ if (!xfs_verify_fsbno(sc->mp, fsbno))
+ return true;
+ }
+
+ return false;
+}
+
+/*
+ * Check the data fork for things that will fail the ifork verifiers or the
+ * ifork formatters.
+ */
+STATIC bool
+xrep_dinode_check_dfork(
+ struct xfs_scrub *sc,
+ struct xfs_dinode *dip,
+ uint16_t mode)
+{
+ void *dfork_ptr;
+ int64_t data_size;
+ unsigned int fmt;
+ unsigned int dfork_size;
+
+ /*
+ * Verifier functions take signed int64_t, so check for bogus negative
+ * values first.
+ */
+ data_size = be64_to_cpu(dip->di_size);
+ if (data_size < 0)
+ return true;
+
+ fmt = XFS_DFORK_FORMAT(dip, XFS_DATA_FORK);
+ switch (mode & S_IFMT) {
+ case S_IFIFO:
+ case S_IFCHR:
+ case S_IFBLK:
+ case S_IFSOCK:
+ if (fmt != XFS_DINODE_FMT_DEV)
+ return true;
+ break;
+ case S_IFREG:
+ if (fmt == XFS_DINODE_FMT_LOCAL)
+ return true;
+ fallthrough;
+ case S_IFLNK:
+ case S_IFDIR:
+ switch (fmt) {
+ case XFS_DINODE_FMT_LOCAL:
+ case XFS_DINODE_FMT_EXTENTS:
+ case XFS_DINODE_FMT_BTREE:
+ break;
+ default:
+ return true;
+ }
+ break;
+ default:
+ return true;
+ }
+
+ dfork_size = XFS_DFORK_SIZE(dip, sc->mp, XFS_DATA_FORK);
+ dfork_ptr = XFS_DFORK_PTR(dip, XFS_DATA_FORK);
+
+ switch (fmt) {
+ case XFS_DINODE_FMT_DEV:
+ break;
+ case XFS_DINODE_FMT_LOCAL:
+ /* dir/symlink structure cannot be larger than the fork */
+ if (data_size > dfork_size)
+ return true;
+ /* directory structure must pass verification. */
+ if (S_ISDIR(mode) &&
+ xfs_dir2_sf_verify(sc->mp, dfork_ptr, data_size) != NULL)
+ return true;
+ /* symlink structure must pass verification. */
+ if (S_ISLNK(mode) &&
+ xfs_symlink_shortform_verify(dfork_ptr, data_size) != NULL)
+ return true;
+ break;
+ case XFS_DINODE_FMT_EXTENTS:
+ if (xrep_dinode_bad_extents_fork(sc, dip, dfork_size,
+ XFS_DATA_FORK))
+ return true;
+ break;
+ case XFS_DINODE_FMT_BTREE:
+ if (xrep_dinode_bad_bmbt_fork(sc, dip, dfork_size,
+ XFS_DATA_FORK))
+ return true;
+ break;
+ default:
+ return true;
+ }
+
+ return false;
+}
+
+static void
+xrep_dinode_set_data_nextents(
+ struct xfs_dinode *dip,
+ xfs_extnum_t nextents)
+{
+ if (xfs_dinode_has_large_extent_counts(dip))
+ dip->di_big_nextents = cpu_to_be64(nextents);
+ else
+ dip->di_nextents = cpu_to_be32(nextents);
+}
+
+static void
+xrep_dinode_set_attr_nextents(
+ struct xfs_dinode *dip,
+ xfs_extnum_t nextents)
+{
+ if (xfs_dinode_has_large_extent_counts(dip))
+ dip->di_big_anextents = cpu_to_be32(nextents);
+ else
+ dip->di_anextents = cpu_to_be16(nextents);
+}
+
+/* Reset the data fork to something sane. */
+STATIC void
+xrep_dinode_zap_dfork(
+ struct xrep_inode *ri,
+ struct xfs_dinode *dip,
+ uint16_t mode)
+{
+ struct xfs_scrub *sc = ri->sc;
+
+ trace_xrep_dinode_zap_dfork(sc, dip);
+
+ ri->ino_sick_mask |= XFS_SICK_INO_BMBTD_ZAPPED;
+
+ xrep_dinode_set_data_nextents(dip, 0);
+ ri->data_blocks = 0;
+ ri->rt_blocks = 0;
+
+ /* Special files always get reset to DEV */
+ switch (mode & S_IFMT) {
+ case S_IFIFO:
+ case S_IFCHR:
+ case S_IFBLK:
+ case S_IFSOCK:
+ dip->di_format = XFS_DINODE_FMT_DEV;
+ dip->di_size = 0;
+ return;
+ }
+
+ /*
+ * If we have data extents, reset to an empty map and hope the user
+ * will run the bmapbtd checker next.
+ */
+ if (ri->data_extents || ri->rt_extents || S_ISREG(mode)) {
+ dip->di_format = XFS_DINODE_FMT_EXTENTS;
+ return;
+ }
+
+ /* Otherwise, reset the local format to the minimum. */
+ switch (mode & S_IFMT) {
+ case S_IFLNK:
+ xrep_dinode_zap_symlink(ri, dip);
+ break;
+ case S_IFDIR:
+ xrep_dinode_zap_dir(ri, dip);
+ break;
+ }
+}
+
+/*
+ * Check the attr fork for things that will fail the ifork verifiers or the
+ * ifork formatters.
+ */
+STATIC bool
+xrep_dinode_check_afork(
+ struct xfs_scrub *sc,
+ struct xfs_dinode *dip)
+{
+ struct xfs_attr_sf_hdr *afork_ptr;
+ size_t attr_size;
+ unsigned int afork_size;
+
+ if (XFS_DFORK_BOFF(dip) == 0)
+ return dip->di_aformat != XFS_DINODE_FMT_EXTENTS ||
+ xfs_dfork_attr_extents(dip) != 0;
+
+ afork_size = XFS_DFORK_SIZE(dip, sc->mp, XFS_ATTR_FORK);
+ afork_ptr = XFS_DFORK_PTR(dip, XFS_ATTR_FORK);
+
+ switch (XFS_DFORK_FORMAT(dip, XFS_ATTR_FORK)) {
+ case XFS_DINODE_FMT_LOCAL:
+ /* Fork has to be large enough to extract the xattr size. */
+ if (afork_size < sizeof(struct xfs_attr_sf_hdr))
+ return true;
+
+ /* xattr structure cannot be larger than the fork */
+ attr_size = be16_to_cpu(afork_ptr->totsize);
+ if (attr_size > afork_size)
+ return true;
+
+ /* xattr structure must pass verification. */
+ return xfs_attr_shortform_verify(afork_ptr, attr_size) != NULL;
+ case XFS_DINODE_FMT_EXTENTS:
+ if (xrep_dinode_bad_extents_fork(sc, dip, afork_size,
+ XFS_ATTR_FORK))
+ return true;
+ break;
+ case XFS_DINODE_FMT_BTREE:
+ if (xrep_dinode_bad_bmbt_fork(sc, dip, afork_size,
+ XFS_ATTR_FORK))
+ return true;
+ break;
+ default:
+ return true;
+ }
+
+ return false;
+}
+
+/*
+ * Reset the attr fork to empty. Since the attr fork could have contained
+ * ACLs, make the file readable only by root.
+ */
+STATIC void
+xrep_dinode_zap_afork(
+ struct xrep_inode *ri,
+ struct xfs_dinode *dip,
+ uint16_t mode)
+{
+ struct xfs_scrub *sc = ri->sc;
+
+ trace_xrep_dinode_zap_afork(sc, dip);
+
+ ri->ino_sick_mask |= XFS_SICK_INO_BMBTA_ZAPPED;
+
+ dip->di_aformat = XFS_DINODE_FMT_EXTENTS;
+ xrep_dinode_set_attr_nextents(dip, 0);
+ ri->attr_blocks = 0;
+
+ /*
+ * If the data fork is in btree format, removing the attr fork entirely
+ * might cause verifier failures if the next level down in the bmbt
+ * could now fit in the data fork area.
+ */
+ if (dip->di_format != XFS_DINODE_FMT_BTREE)
+ dip->di_forkoff = 0;
+ dip->di_mode = cpu_to_be16(mode & ~0777);
+ dip->di_uid = 0;
+ dip->di_gid = 0;
+}
+
+/* Make sure the fork offset is a sensible value. */
+STATIC void
+xrep_dinode_ensure_forkoff(
+ struct xrep_inode *ri,
+ struct xfs_dinode *dip,
+ uint16_t mode)
+{
+ struct xfs_bmdr_block *bmdr;
+ struct xfs_scrub *sc = ri->sc;
+ xfs_extnum_t attr_extents, data_extents;
+ size_t bmdr_minsz = XFS_BMDR_SPACE_CALC(1);
+ unsigned int lit_sz = XFS_LITINO(sc->mp);
+ unsigned int afork_min, dfork_min;
+
+ trace_xrep_dinode_ensure_forkoff(sc, dip);
+
+ /*
+ * Before calling this function, xrep_dinode_core ensured that both
+ * forks actually fit inside their respective literal areas. If this
+ * was not the case, the fork was reset to FMT_EXTENTS with zero
+ * records. If the rmapbt scan found attr or data fork blocks, this
+ * will be noted in the dinode_stats, and we must leave enough room
+ * for the bmap repair code to reconstruct the mapping structure.
+ *
+ * First, compute the minimum space required for the attr fork.
+ */
+ switch (dip->di_aformat) {
+ case XFS_DINODE_FMT_LOCAL:
+ /*
+ * If we still have a shortform xattr structure at all, that
+ * means the attr fork area was exactly large enough to fit
+ * the sf structure.
+ */
+ afork_min = XFS_DFORK_SIZE(dip, sc->mp, XFS_ATTR_FORK);
+ break;
+ case XFS_DINODE_FMT_EXTENTS:
+ attr_extents = xfs_dfork_attr_extents(dip);
+ if (attr_extents) {
+ /*
+ * We must maintain sufficient space to hold the entire
+ * extent map array in the data fork. Note that we
+ * previously zapped the fork if it had no chance of
+ * fitting in the inode.
+ */
+ afork_min = sizeof(struct xfs_bmbt_rec) * attr_extents;
+ } else if (ri->attr_extents > 0) {
+ /*
+ * The attr fork thinks it has zero extents, but we
+ * found some xattr extents. We need to leave enough
+ * empty space here so that the incore attr fork will
+ * get created (and hence trigger the attr fork bmap
+ * repairer).
+ */
+ afork_min = bmdr_minsz;
+ } else {
+ /* No extents on disk or found in rmapbt. */
+ afork_min = 0;
+ }
+ break;
+ case XFS_DINODE_FMT_BTREE:
+ /* Must have space for btree header and key/pointers. */
+ bmdr = XFS_DFORK_PTR(dip, XFS_ATTR_FORK);
+ afork_min = XFS_BMAP_BROOT_SPACE(sc->mp, bmdr);
+ break;
+ default:
+ /* We should never see any other formats. */
+ afork_min = 0;
+ break;
+ }
+
+ /* Compute the minimum space required for the data fork. */
+ switch (dip->di_format) {
+ case XFS_DINODE_FMT_DEV:
+ dfork_min = sizeof(__be32);
+ break;
+ case XFS_DINODE_FMT_UUID:
+ dfork_min = sizeof(uuid_t);
+ break;
+ case XFS_DINODE_FMT_LOCAL:
+ /*
+ * If we still have a shortform data fork at all, that means
+ * the data fork area was large enough to fit whatever was in
+ * there.
+ */
+ dfork_min = be64_to_cpu(dip->di_size);
+ break;
+ case XFS_DINODE_FMT_EXTENTS:
+ data_extents = xfs_dfork_data_extents(dip);
+ if (data_extents) {
+ /*
+ * We must maintain sufficient space to hold the entire
+ * extent map array in the data fork. Note that we
+ * previously zapped the fork if it had no chance of
+ * fitting in the inode.
+ */
+ dfork_min = sizeof(struct xfs_bmbt_rec) * data_extents;
+ } else if (ri->data_extents > 0 || ri->rt_extents > 0) {
+ /*
+ * The data fork thinks it has zero extents, but we
+ * found some data extents. We need to leave enough
+ * empty space here so that the data fork bmap repair
+ * will recover the mappings.
+ */
+ dfork_min = bmdr_minsz;
+ } else {
+ /* No extents on disk or found in rmapbt. */
+ dfork_min = 0;
+ }
+ break;
+ case XFS_DINODE_FMT_BTREE:
+ /* Must have space for btree header and key/pointers. */
+ bmdr = XFS_DFORK_PTR(dip, XFS_DATA_FORK);
+ dfork_min = XFS_BMAP_BROOT_SPACE(sc->mp, bmdr);
+ break;
+ default:
+ dfork_min = 0;
+ break;
+ }
+
+ /*
+ * Round all values up to the nearest 8 bytes, because that is the
+ * precision of di_forkoff.
+ */
+ afork_min = roundup(afork_min, 8);
+ dfork_min = roundup(dfork_min, 8);
+ bmdr_minsz = roundup(bmdr_minsz, 8);
+
+ ASSERT(dfork_min <= lit_sz);
+ ASSERT(afork_min <= lit_sz);
+
+ /*
+ * If the data fork was zapped and we don't have enough space for the
+ * recovery fork, move the attr fork up.
+ */
+ if (dip->di_format == XFS_DINODE_FMT_EXTENTS &&
+ xfs_dfork_data_extents(dip) == 0 &&
+ (ri->data_extents > 0 || ri->rt_extents > 0) &&
+ bmdr_minsz > XFS_DFORK_DSIZE(dip, sc->mp)) {
+ if (bmdr_minsz + afork_min > lit_sz) {
+ /*
+ * The attr for and the stub fork we need to recover
+ * the data fork won't both fit. Zap the attr fork.
+ */
+ xrep_dinode_zap_afork(ri, dip, mode);
+ afork_min = bmdr_minsz;
+ } else {
+ void *before, *after;
+
+ /* Otherwise, just slide the attr fork up. */
+ before = XFS_DFORK_APTR(dip);
+ dip->di_forkoff = bmdr_minsz >> 3;
+ after = XFS_DFORK_APTR(dip);
+ memmove(after, before, XFS_DFORK_ASIZE(dip, sc->mp));
+ }
+ }
+
+ /*
+ * If the attr fork was zapped and we don't have enough space for the
+ * recovery fork, move the attr fork down.
+ */
+ if (dip->di_aformat == XFS_DINODE_FMT_EXTENTS &&
+ xfs_dfork_attr_extents(dip) == 0 &&
+ ri->attr_extents > 0 &&
+ bmdr_minsz > XFS_DFORK_ASIZE(dip, sc->mp)) {
+ if (dip->di_format == XFS_DINODE_FMT_BTREE) {
+ /*
+ * If the data fork is in btree format then we can't
+ * adjust forkoff because that runs the risk of
+ * violating the extents/btree format transition rules.
+ */
+ } else if (bmdr_minsz + dfork_min > lit_sz) {
+ /*
+ * If we can't move the attr fork, too bad, we lose the
+ * attr fork and leak its blocks.
+ */
+ xrep_dinode_zap_afork(ri, dip, mode);
+ } else {
+ /*
+ * Otherwise, just slide the attr fork down. The attr
+ * fork is empty, so we don't have any old contents to
+ * move here.
+ */
+ dip->di_forkoff = (lit_sz - bmdr_minsz) >> 3;
+ }
+ }
+}
+
+/*
+ * Zap the data/attr forks if we spot anything that isn't going to pass the
+ * ifork verifiers or the ifork formatters, because we need to get the inode
+ * into good enough shape that the higher level repair functions can run.
+ */
+STATIC void
+xrep_dinode_zap_forks(
+ struct xrep_inode *ri,
+ struct xfs_dinode *dip)
+{
+ struct xfs_scrub *sc = ri->sc;
+ xfs_extnum_t data_extents;
+ xfs_extnum_t attr_extents;
+ xfs_filblks_t nblocks;
+ uint16_t mode;
+ bool zap_datafork = false;
+ bool zap_attrfork = ri->zap_acls;
+
+ trace_xrep_dinode_zap_forks(sc, dip);
+
+ mode = be16_to_cpu(dip->di_mode);
+
+ data_extents = xfs_dfork_data_extents(dip);
+ attr_extents = xfs_dfork_attr_extents(dip);
+ nblocks = be64_to_cpu(dip->di_nblocks);
+
+ /* Inode counters don't make sense? */
+ if (data_extents > nblocks)
+ zap_datafork = true;
+ if (attr_extents > nblocks)
+ zap_attrfork = true;
+ if (data_extents + attr_extents > nblocks)
+ zap_datafork = zap_attrfork = true;
+
+ if (!zap_datafork)
+ zap_datafork = xrep_dinode_check_dfork(sc, dip, mode);
+ if (!zap_attrfork)
+ zap_attrfork = xrep_dinode_check_afork(sc, dip);
+
+ /* Zap whatever's bad. */
+ if (zap_attrfork)
+ xrep_dinode_zap_afork(ri, dip, mode);
+ if (zap_datafork)
+ xrep_dinode_zap_dfork(ri, dip, mode);
+ xrep_dinode_ensure_forkoff(ri, dip, mode);
+
+ /*
+ * Zero di_nblocks if we don't have any extents at all to satisfy the
+ * buffer verifier.
+ */
+ data_extents = xfs_dfork_data_extents(dip);
+ attr_extents = xfs_dfork_attr_extents(dip);
+ if (data_extents + attr_extents == 0)
+ dip->di_nblocks = 0;
+}
+
+/* Inode didn't pass dinode verifiers, so fix the raw buffer and retry iget. */
+STATIC int
+xrep_dinode_core(
+ struct xrep_inode *ri)
+{
+ struct xfs_scrub *sc = ri->sc;
+ struct xfs_buf *bp;
+ struct xfs_dinode *dip;
+ xfs_ino_t ino = sc->sm->sm_ino;
+ int error;
+ int iget_error;
+
+ /* Figure out what this inode had mapped in both forks. */
+ error = xrep_dinode_count_rmaps(ri);
+ if (error)
+ return error;
+
+ /* Read the inode cluster buffer. */
+ error = xfs_trans_read_buf(sc->mp, sc->tp, sc->mp->m_ddev_targp,
+ ri->imap.im_blkno, ri->imap.im_len, XBF_UNMAPPED, &bp,
+ NULL);
+ if (error)
+ return error;
+
+ /* Make sure we can pass the inode buffer verifier. */
+ xrep_dinode_buf(sc, bp);
+ bp->b_ops = &xfs_inode_buf_ops;
+
+ /* Fix everything the verifier will complain about. */
+ dip = xfs_buf_offset(bp, ri->imap.im_boffset);
+ xrep_dinode_header(sc, dip);
+ xrep_dinode_mode(ri, dip);
+ xrep_dinode_flags(sc, dip, ri->rt_extents > 0);
+ xrep_dinode_size(ri, dip);
+ xrep_dinode_extsize_hints(sc, dip);
+ xrep_dinode_zap_forks(ri, dip);
+
+ /* Write out the inode. */
+ trace_xrep_dinode_fixed(sc, dip);
+ xfs_dinode_calc_crc(sc->mp, dip);
+ xfs_trans_buf_set_type(sc->tp, bp, XFS_BLFT_DINO_BUF);
+ xfs_trans_log_buf(sc->tp, bp, ri->imap.im_boffset,
+ ri->imap.im_boffset + sc->mp->m_sb.sb_inodesize - 1);
+
+ /*
+ * In theory, we've fixed the ondisk inode record enough that we should
+ * be able to load the inode into the cache. Try to iget that inode
+ * now while we hold the AGI and the inode cluster buffer and take the
+ * IOLOCK so that we can continue with repairs without anyone else
+ * accessing the inode. If iget fails, we still need to commit the
+ * changes.
+ */
+ iget_error = xchk_iget(sc, ino, &sc->ip);
+ if (!iget_error)
+ xchk_ilock(sc, XFS_IOLOCK_EXCL);
+
+ /*
+ * Commit the inode cluster buffer updates and drop the AGI buffer that
+ * we've been holding since scrub setup. From here on out, repairs
+ * deal only with the cached inode.
+ */
+ error = xrep_trans_commit(sc);
+ if (error)
+ return error;
+
+ if (iget_error)
+ return iget_error;
+
+ error = xchk_trans_alloc(sc, 0);
+ if (error)
+ return error;
+
+ error = xrep_ino_dqattach(sc);
+ if (error)
+ return error;
+
+ xchk_ilock(sc, XFS_ILOCK_EXCL);
+ if (ri->ino_sick_mask)
+ xfs_inode_mark_sick(sc->ip, ri->ino_sick_mask);
+ return 0;
+}
+
+/* Fix everything xfs_dinode_verify cares about. */
+STATIC int
+xrep_dinode_problems(
+ struct xrep_inode *ri)
+{
+ struct xfs_scrub *sc = ri->sc;
+ int error;
+
+ error = xrep_dinode_core(ri);
+ if (error)
+ return error;
+
+ /* We had to fix a totally busted inode, schedule quotacheck. */
+ if (XFS_IS_UQUOTA_ON(sc->mp))
+ xrep_force_quotacheck(sc, XFS_DQTYPE_USER);
+ if (XFS_IS_GQUOTA_ON(sc->mp))
+ xrep_force_quotacheck(sc, XFS_DQTYPE_GROUP);
+ if (XFS_IS_PQUOTA_ON(sc->mp))
+ xrep_force_quotacheck(sc, XFS_DQTYPE_PROJ);
+
+ return 0;
+}
+
+/*
+ * Fix problems that the verifiers don't care about. In general these are
+ * errors that don't cause problems elsewhere in the kernel that we can easily
+ * detect, so we don't check them all that rigorously.
+ */
+
+/* Make sure block and extent counts are ok. */
+STATIC int
+xrep_inode_blockcounts(
+ struct xfs_scrub *sc)
+{
+ struct xfs_ifork *ifp;
+ xfs_filblks_t count;
+ xfs_filblks_t acount;
+ xfs_extnum_t nextents;
+ int error;
+
+ trace_xrep_inode_blockcounts(sc);
+
+ /* Set data fork counters from the data fork mappings. */
+ error = xfs_bmap_count_blocks(sc->tp, sc->ip, XFS_DATA_FORK,
+ &nextents, &count);
+ if (error)
+ return error;
+ if (xfs_is_reflink_inode(sc->ip)) {
+ /*
+ * data fork blockcount can exceed physical storage if a user
+ * reflinks the same block over and over again.
+ */
+ ;
+ } else if (XFS_IS_REALTIME_INODE(sc->ip)) {
+ if (count >= sc->mp->m_sb.sb_rblocks)
+ return -EFSCORRUPTED;
+ } else {
+ if (count >= sc->mp->m_sb.sb_dblocks)
+ return -EFSCORRUPTED;
+ }
+ error = xrep_ino_ensure_extent_count(sc, XFS_DATA_FORK, nextents);
+ if (error)
+ return error;
+ sc->ip->i_df.if_nextents = nextents;
+
+ /* Set attr fork counters from the attr fork mappings. */
+ ifp = xfs_ifork_ptr(sc->ip, XFS_ATTR_FORK);
+ if (ifp) {
+ error = xfs_bmap_count_blocks(sc->tp, sc->ip, XFS_ATTR_FORK,
+ &nextents, &acount);
+ if (error)
+ return error;
+ if (count >= sc->mp->m_sb.sb_dblocks)
+ return -EFSCORRUPTED;
+ error = xrep_ino_ensure_extent_count(sc, XFS_ATTR_FORK,
+ nextents);
+ if (error)
+ return error;
+ ifp->if_nextents = nextents;
+ } else {
+ acount = 0;
+ }
+
+ sc->ip->i_nblocks = count + acount;
+ return 0;
+}
+
+/* Check for invalid uid/gid/prid. */
+STATIC void
+xrep_inode_ids(
+ struct xfs_scrub *sc)
+{
+ bool dirty = false;
+
+ trace_xrep_inode_ids(sc);
+
+ if (!uid_valid(VFS_I(sc->ip)->i_uid)) {
+ i_uid_write(VFS_I(sc->ip), 0);
+ dirty = true;
+ if (XFS_IS_UQUOTA_ON(sc->mp))
+ xrep_force_quotacheck(sc, XFS_DQTYPE_USER);
+ }
+
+ if (!gid_valid(VFS_I(sc->ip)->i_gid)) {
+ i_gid_write(VFS_I(sc->ip), 0);
+ dirty = true;
+ if (XFS_IS_GQUOTA_ON(sc->mp))
+ xrep_force_quotacheck(sc, XFS_DQTYPE_GROUP);
+ }
+
+ if (sc->ip->i_projid == -1U) {
+ sc->ip->i_projid = 0;
+ dirty = true;
+ if (XFS_IS_PQUOTA_ON(sc->mp))
+ xrep_force_quotacheck(sc, XFS_DQTYPE_PROJ);
+ }
+
+ /* strip setuid/setgid if we touched any of the ids */
+ if (dirty)
+ VFS_I(sc->ip)->i_mode &= ~(S_ISUID | S_ISGID);
+}
+
+static inline void
+xrep_clamp_timestamp(
+ struct xfs_inode *ip,
+ struct timespec64 *ts)
+{
+ ts->tv_nsec = clamp_t(long, ts->tv_nsec, 0, NSEC_PER_SEC);
+ *ts = timestamp_truncate(*ts, VFS_I(ip));
+}
+
+/* Nanosecond counters can't have more than 1 billion. */
+STATIC void
+xrep_inode_timestamps(
+ struct xfs_inode *ip)
+{
+ struct timespec64 tstamp;
+ struct inode *inode = VFS_I(ip);
+
+ tstamp = inode_get_atime(inode);
+ xrep_clamp_timestamp(ip, &tstamp);
+ inode_set_atime_to_ts(inode, tstamp);
+
+ tstamp = inode_get_mtime(inode);
+ xrep_clamp_timestamp(ip, &tstamp);
+ inode_set_mtime_to_ts(inode, tstamp);
+
+ tstamp = inode_get_ctime(inode);
+ xrep_clamp_timestamp(ip, &tstamp);
+ inode_set_ctime_to_ts(inode, tstamp);
+
+ xrep_clamp_timestamp(ip, &ip->i_crtime);
+}
+
+/* Fix inode flags that don't make sense together. */
+STATIC void
+xrep_inode_flags(
+ struct xfs_scrub *sc)
+{
+ uint16_t mode;
+
+ trace_xrep_inode_flags(sc);
+
+ mode = VFS_I(sc->ip)->i_mode;
+
+ /* Clear junk flags */
+ if (sc->ip->i_diflags & ~XFS_DIFLAG_ANY)
+ sc->ip->i_diflags &= ~XFS_DIFLAG_ANY;
+
+ /* NEWRTBM only applies to realtime bitmaps */
+ if (sc->ip->i_ino == sc->mp->m_sb.sb_rbmino)
+ sc->ip->i_diflags |= XFS_DIFLAG_NEWRTBM;
+ else
+ sc->ip->i_diflags &= ~XFS_DIFLAG_NEWRTBM;
+
+ /* These only make sense for directories. */
+ if (!S_ISDIR(mode))
+ sc->ip->i_diflags &= ~(XFS_DIFLAG_RTINHERIT |
+ XFS_DIFLAG_EXTSZINHERIT |
+ XFS_DIFLAG_PROJINHERIT |
+ XFS_DIFLAG_NOSYMLINKS);
+
+ /* These only make sense for files. */
+ if (!S_ISREG(mode))
+ sc->ip->i_diflags &= ~(XFS_DIFLAG_REALTIME |
+ XFS_DIFLAG_EXTSIZE);
+
+ /* These only make sense for non-rt files. */
+ if (sc->ip->i_diflags & XFS_DIFLAG_REALTIME)
+ sc->ip->i_diflags &= ~XFS_DIFLAG_FILESTREAM;
+
+ /* Immutable and append only? Drop the append. */
+ if ((sc->ip->i_diflags & XFS_DIFLAG_IMMUTABLE) &&
+ (sc->ip->i_diflags & XFS_DIFLAG_APPEND))
+ sc->ip->i_diflags &= ~XFS_DIFLAG_APPEND;
+
+ /* Clear junk flags. */
+ if (sc->ip->i_diflags2 & ~XFS_DIFLAG2_ANY)
+ sc->ip->i_diflags2 &= ~XFS_DIFLAG2_ANY;
+
+ /* No reflink flag unless we support it and it's a file. */
+ if (!xfs_has_reflink(sc->mp) || !S_ISREG(mode))
+ sc->ip->i_diflags2 &= ~XFS_DIFLAG2_REFLINK;
+
+ /* DAX only applies to files and dirs. */
+ if (!(S_ISREG(mode) || S_ISDIR(mode)))
+ sc->ip->i_diflags2 &= ~XFS_DIFLAG2_DAX;
+
+ /* No reflink files on the realtime device. */
+ if (sc->ip->i_diflags & XFS_DIFLAG_REALTIME)
+ sc->ip->i_diflags2 &= ~XFS_DIFLAG2_REFLINK;
+}
+
+/*
+ * Fix size problems with block/node format directories. If we fail to find
+ * the extent list, just bail out and let the bmapbtd repair functions clean
+ * up that mess.
+ */
+STATIC void
+xrep_inode_blockdir_size(
+ struct xfs_scrub *sc)
+{
+ struct xfs_iext_cursor icur;
+ struct xfs_bmbt_irec got;
+ struct xfs_ifork *ifp;
+ xfs_fileoff_t off;
+ int error;
+
+ trace_xrep_inode_blockdir_size(sc);
+
+ error = xfs_iread_extents(sc->tp, sc->ip, XFS_DATA_FORK);
+ if (error)
+ return;
+
+ /* Find the last block before 32G; this is the dir size. */
+ ifp = xfs_ifork_ptr(sc->ip, XFS_DATA_FORK);
+ off = XFS_B_TO_FSB(sc->mp, XFS_DIR2_SPACE_SIZE);
+ if (!xfs_iext_lookup_extent_before(sc->ip, ifp, &off, &icur, &got)) {
+ /* zero-extents directory? */
+ return;
+ }
+
+ off = got.br_startoff + got.br_blockcount;
+ sc->ip->i_disk_size = min_t(loff_t, XFS_DIR2_SPACE_SIZE,
+ XFS_FSB_TO_B(sc->mp, off));
+}
+
+/* Fix size problems with short format directories. */
+STATIC void
+xrep_inode_sfdir_size(
+ struct xfs_scrub *sc)
+{
+ struct xfs_ifork *ifp;
+
+ trace_xrep_inode_sfdir_size(sc);
+
+ ifp = xfs_ifork_ptr(sc->ip, XFS_DATA_FORK);
+ sc->ip->i_disk_size = ifp->if_bytes;
+}
+
+/*
+ * Fix any irregularities in a directory inode's size now that we can iterate
+ * extent maps and access other regular inode data.
+ */
+STATIC void
+xrep_inode_dir_size(
+ struct xfs_scrub *sc)
+{
+ trace_xrep_inode_dir_size(sc);
+
+ switch (sc->ip->i_df.if_format) {
+ case XFS_DINODE_FMT_EXTENTS:
+ case XFS_DINODE_FMT_BTREE:
+ xrep_inode_blockdir_size(sc);
+ break;
+ case XFS_DINODE_FMT_LOCAL:
+ xrep_inode_sfdir_size(sc);
+ break;
+ }
+}
+
+/* Fix extent size hint problems. */
+STATIC void
+xrep_inode_extsize(
+ struct xfs_scrub *sc)
+{
+ /* Fix misaligned extent size hints on a directory. */
+ if ((sc->ip->i_diflags & XFS_DIFLAG_RTINHERIT) &&
+ (sc->ip->i_diflags & XFS_DIFLAG_EXTSZINHERIT) &&
+ xfs_extlen_to_rtxmod(sc->mp, sc->ip->i_extsize) > 0) {
+ sc->ip->i_extsize = 0;
+ sc->ip->i_diflags &= ~XFS_DIFLAG_EXTSZINHERIT;
+ }
+}
+
+/* Fix any irregularities in an inode that the verifiers don't catch. */
+STATIC int
+xrep_inode_problems(
+ struct xfs_scrub *sc)
+{
+ int error;
+
+ error = xrep_inode_blockcounts(sc);
+ if (error)
+ return error;
+ xrep_inode_timestamps(sc->ip);
+ xrep_inode_flags(sc);
+ xrep_inode_ids(sc);
+ /*
+ * We can now do a better job fixing the size of a directory now that
+ * we can scan the data fork extents than we could in xrep_dinode_size.
+ */
+ if (S_ISDIR(VFS_I(sc->ip)->i_mode))
+ xrep_inode_dir_size(sc);
+ xrep_inode_extsize(sc);
+
+ trace_xrep_inode_fixed(sc);
+ xfs_trans_log_inode(sc->tp, sc->ip, XFS_ILOG_CORE);
+ return xrep_roll_trans(sc);
+}
+
+/* Repair an inode's fields. */
+int
+xrep_inode(
+ struct xfs_scrub *sc)
+{
+ int error = 0;
+
+ /*
+ * No inode? That means we failed the _iget verifiers. Repair all
+ * the things that the inode verifiers care about, then retry _iget.
+ */
+ if (!sc->ip) {
+ struct xrep_inode *ri = sc->buf;
+
+ ASSERT(ri != NULL);
+
+ error = xrep_dinode_problems(ri);
+ if (error)
+ return error;
+
+ /* By this point we had better have a working incore inode. */
+ if (!sc->ip)
+ return -EFSCORRUPTED;
+ }
+
+ xfs_trans_ijoin(sc->tp, sc->ip, 0);
+
+ /* If we found corruption of any kind, try to fix it. */
+ if ((sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT) ||
+ (sc->sm->sm_flags & XFS_SCRUB_OFLAG_XCORRUPT)) {
+ error = xrep_inode_problems(sc);
+ if (error)
+ return error;
+ }
+
+ /* See if we can clear the reflink flag. */
+ if (xfs_is_reflink_inode(sc->ip)) {
+ error = xfs_reflink_clear_inode_flag(sc->ip, &sc->tp);
+ if (error)
+ return error;
+ }
+
+ return xrep_defer_finish(sc);
+}
diff --git a/fs/xfs/scrub/newbt.c b/fs/xfs/scrub/newbt.c
new file mode 100644
index 000000000000..bb6d980b4fcd
--- /dev/null
+++ b/fs/xfs/scrub/newbt.c
@@ -0,0 +1,559 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2022-2023 Oracle. All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_btree.h"
+#include "xfs_btree_staging.h"
+#include "xfs_log_format.h"
+#include "xfs_trans.h"
+#include "xfs_sb.h"
+#include "xfs_inode.h"
+#include "xfs_alloc.h"
+#include "xfs_rmap.h"
+#include "xfs_ag.h"
+#include "xfs_defer.h"
+#include "scrub/scrub.h"
+#include "scrub/common.h"
+#include "scrub/trace.h"
+#include "scrub/repair.h"
+#include "scrub/newbt.h"
+
+/*
+ * Estimate proper slack values for a btree that's being reloaded.
+ *
+ * Under most circumstances, we'll take whatever default loading value the
+ * btree bulk loading code calculates for us. However, there are some
+ * exceptions to this rule:
+ *
+ * (0) If someone turned one of the debug knobs.
+ * (1) If this is a per-AG btree and the AG has less than 10% space free.
+ * (2) If this is an inode btree and the FS has less than 10% space free.
+
+ * In either case, format the new btree blocks almost completely full to
+ * minimize space usage.
+ */
+static void
+xrep_newbt_estimate_slack(
+ struct xrep_newbt *xnr)
+{
+ struct xfs_scrub *sc = xnr->sc;
+ struct xfs_btree_bload *bload = &xnr->bload;
+ uint64_t free;
+ uint64_t sz;
+
+ /*
+ * The xfs_globals values are set to -1 (i.e. take the bload defaults)
+ * unless someone has set them otherwise, so we just pull the values
+ * here.
+ */
+ bload->leaf_slack = xfs_globals.bload_leaf_slack;
+ bload->node_slack = xfs_globals.bload_node_slack;
+
+ if (sc->ops->type == ST_PERAG) {
+ free = sc->sa.pag->pagf_freeblks;
+ sz = xfs_ag_block_count(sc->mp, sc->sa.pag->pag_agno);
+ } else {
+ free = percpu_counter_sum(&sc->mp->m_fdblocks);
+ sz = sc->mp->m_sb.sb_dblocks;
+ }
+
+ /* No further changes if there's more than 10% free space left. */
+ if (free >= div_u64(sz, 10))
+ return;
+
+ /*
+ * We're low on space; load the btrees as tightly as possible. Leave
+ * a couple of open slots in each btree block so that we don't end up
+ * splitting the btrees like crazy after a mount.
+ */
+ if (bload->leaf_slack < 0)
+ bload->leaf_slack = 2;
+ if (bload->node_slack < 0)
+ bload->node_slack = 2;
+}
+
+/* Initialize accounting resources for staging a new AG btree. */
+void
+xrep_newbt_init_ag(
+ struct xrep_newbt *xnr,
+ struct xfs_scrub *sc,
+ const struct xfs_owner_info *oinfo,
+ xfs_fsblock_t alloc_hint,
+ enum xfs_ag_resv_type resv)
+{
+ memset(xnr, 0, sizeof(struct xrep_newbt));
+ xnr->sc = sc;
+ xnr->oinfo = *oinfo; /* structure copy */
+ xnr->alloc_hint = alloc_hint;
+ xnr->resv = resv;
+ INIT_LIST_HEAD(&xnr->resv_list);
+ xnr->bload.max_dirty = XFS_B_TO_FSBT(sc->mp, 256U << 10); /* 256K */
+ xrep_newbt_estimate_slack(xnr);
+}
+
+/* Initialize accounting resources for staging a new inode fork btree. */
+int
+xrep_newbt_init_inode(
+ struct xrep_newbt *xnr,
+ struct xfs_scrub *sc,
+ int whichfork,
+ const struct xfs_owner_info *oinfo)
+{
+ struct xfs_ifork *ifp;
+
+ ifp = kmem_cache_zalloc(xfs_ifork_cache, XCHK_GFP_FLAGS);
+ if (!ifp)
+ return -ENOMEM;
+
+ xrep_newbt_init_ag(xnr, sc, oinfo,
+ XFS_INO_TO_FSB(sc->mp, sc->ip->i_ino),
+ XFS_AG_RESV_NONE);
+ xnr->ifake.if_fork = ifp;
+ xnr->ifake.if_fork_size = xfs_inode_fork_size(sc->ip, whichfork);
+ return 0;
+}
+
+/*
+ * Initialize accounting resources for staging a new btree. Callers are
+ * expected to add their own reservations (and clean them up) manually.
+ */
+void
+xrep_newbt_init_bare(
+ struct xrep_newbt *xnr,
+ struct xfs_scrub *sc)
+{
+ xrep_newbt_init_ag(xnr, sc, &XFS_RMAP_OINFO_ANY_OWNER, NULLFSBLOCK,
+ XFS_AG_RESV_NONE);
+}
+
+/*
+ * Designate specific blocks to be used to build our new btree. @pag must be
+ * a passive reference.
+ */
+STATIC int
+xrep_newbt_add_blocks(
+ struct xrep_newbt *xnr,
+ struct xfs_perag *pag,
+ const struct xfs_alloc_arg *args)
+{
+ struct xfs_mount *mp = xnr->sc->mp;
+ struct xrep_newbt_resv *resv;
+ int error;
+
+ resv = kmalloc(sizeof(struct xrep_newbt_resv), XCHK_GFP_FLAGS);
+ if (!resv)
+ return -ENOMEM;
+
+ INIT_LIST_HEAD(&resv->list);
+ resv->agbno = XFS_FSB_TO_AGBNO(mp, args->fsbno);
+ resv->len = args->len;
+ resv->used = 0;
+ resv->pag = xfs_perag_hold(pag);
+
+ if (args->tp) {
+ ASSERT(xnr->oinfo.oi_offset == 0);
+
+ error = xfs_alloc_schedule_autoreap(args, true, &resv->autoreap);
+ if (error)
+ goto out_pag;
+ }
+
+ list_add_tail(&resv->list, &xnr->resv_list);
+ return 0;
+out_pag:
+ xfs_perag_put(resv->pag);
+ kfree(resv);
+ return error;
+}
+
+/*
+ * Add an extent to the new btree reservation pool. Callers are required to
+ * reap this reservation manually if the repair is cancelled. @pag must be a
+ * passive reference.
+ */
+int
+xrep_newbt_add_extent(
+ struct xrep_newbt *xnr,
+ struct xfs_perag *pag,
+ xfs_agblock_t agbno,
+ xfs_extlen_t len)
+{
+ struct xfs_mount *mp = xnr->sc->mp;
+ struct xfs_alloc_arg args = {
+ .tp = NULL, /* no autoreap */
+ .oinfo = xnr->oinfo,
+ .fsbno = XFS_AGB_TO_FSB(mp, pag->pag_agno, agbno),
+ .len = len,
+ .resv = xnr->resv,
+ };
+
+ return xrep_newbt_add_blocks(xnr, pag, &args);
+}
+
+/* Don't let our allocation hint take us beyond this AG */
+static inline void
+xrep_newbt_validate_ag_alloc_hint(
+ struct xrep_newbt *xnr)
+{
+ struct xfs_scrub *sc = xnr->sc;
+ xfs_agnumber_t agno = XFS_FSB_TO_AGNO(sc->mp, xnr->alloc_hint);
+
+ if (agno == sc->sa.pag->pag_agno &&
+ xfs_verify_fsbno(sc->mp, xnr->alloc_hint))
+ return;
+
+ xnr->alloc_hint = XFS_AGB_TO_FSB(sc->mp, sc->sa.pag->pag_agno,
+ XFS_AGFL_BLOCK(sc->mp) + 1);
+}
+
+/* Allocate disk space for a new per-AG btree. */
+STATIC int
+xrep_newbt_alloc_ag_blocks(
+ struct xrep_newbt *xnr,
+ uint64_t nr_blocks)
+{
+ struct xfs_scrub *sc = xnr->sc;
+ struct xfs_mount *mp = sc->mp;
+ int error = 0;
+
+ ASSERT(sc->sa.pag != NULL);
+
+ while (nr_blocks > 0) {
+ struct xfs_alloc_arg args = {
+ .tp = sc->tp,
+ .mp = mp,
+ .oinfo = xnr->oinfo,
+ .minlen = 1,
+ .maxlen = nr_blocks,
+ .prod = 1,
+ .resv = xnr->resv,
+ };
+ xfs_agnumber_t agno;
+
+ xrep_newbt_validate_ag_alloc_hint(xnr);
+
+ error = xfs_alloc_vextent_near_bno(&args, xnr->alloc_hint);
+ if (error)
+ return error;
+ if (args.fsbno == NULLFSBLOCK)
+ return -ENOSPC;
+
+ agno = XFS_FSB_TO_AGNO(mp, args.fsbno);
+
+ trace_xrep_newbt_alloc_ag_blocks(mp, agno,
+ XFS_FSB_TO_AGBNO(mp, args.fsbno), args.len,
+ xnr->oinfo.oi_owner);
+
+ if (agno != sc->sa.pag->pag_agno) {
+ ASSERT(agno == sc->sa.pag->pag_agno);
+ return -EFSCORRUPTED;
+ }
+
+ error = xrep_newbt_add_blocks(xnr, sc->sa.pag, &args);
+ if (error)
+ return error;
+
+ nr_blocks -= args.len;
+ xnr->alloc_hint = args.fsbno + args.len;
+
+ error = xrep_defer_finish(sc);
+ if (error)
+ return error;
+ }
+
+ return 0;
+}
+
+/* Don't let our allocation hint take us beyond EOFS */
+static inline void
+xrep_newbt_validate_file_alloc_hint(
+ struct xrep_newbt *xnr)
+{
+ struct xfs_scrub *sc = xnr->sc;
+
+ if (xfs_verify_fsbno(sc->mp, xnr->alloc_hint))
+ return;
+
+ xnr->alloc_hint = XFS_AGB_TO_FSB(sc->mp, 0, XFS_AGFL_BLOCK(sc->mp) + 1);
+}
+
+/* Allocate disk space for our new file-based btree. */
+STATIC int
+xrep_newbt_alloc_file_blocks(
+ struct xrep_newbt *xnr,
+ uint64_t nr_blocks)
+{
+ struct xfs_scrub *sc = xnr->sc;
+ struct xfs_mount *mp = sc->mp;
+ int error = 0;
+
+ while (nr_blocks > 0) {
+ struct xfs_alloc_arg args = {
+ .tp = sc->tp,
+ .mp = mp,
+ .oinfo = xnr->oinfo,
+ .minlen = 1,
+ .maxlen = nr_blocks,
+ .prod = 1,
+ .resv = xnr->resv,
+ };
+ struct xfs_perag *pag;
+ xfs_agnumber_t agno;
+
+ xrep_newbt_validate_file_alloc_hint(xnr);
+
+ error = xfs_alloc_vextent_start_ag(&args, xnr->alloc_hint);
+ if (error)
+ return error;
+ if (args.fsbno == NULLFSBLOCK)
+ return -ENOSPC;
+
+ agno = XFS_FSB_TO_AGNO(mp, args.fsbno);
+
+ trace_xrep_newbt_alloc_file_blocks(mp, agno,
+ XFS_FSB_TO_AGBNO(mp, args.fsbno), args.len,
+ xnr->oinfo.oi_owner);
+
+ pag = xfs_perag_get(mp, agno);
+ if (!pag) {
+ ASSERT(0);
+ return -EFSCORRUPTED;
+ }
+
+ error = xrep_newbt_add_blocks(xnr, pag, &args);
+ xfs_perag_put(pag);
+ if (error)
+ return error;
+
+ nr_blocks -= args.len;
+ xnr->alloc_hint = args.fsbno + args.len;
+
+ error = xrep_defer_finish(sc);
+ if (error)
+ return error;
+ }
+
+ return 0;
+}
+
+/* Allocate disk space for our new btree. */
+int
+xrep_newbt_alloc_blocks(
+ struct xrep_newbt *xnr,
+ uint64_t nr_blocks)
+{
+ if (xnr->sc->ip)
+ return xrep_newbt_alloc_file_blocks(xnr, nr_blocks);
+ return xrep_newbt_alloc_ag_blocks(xnr, nr_blocks);
+}
+
+/*
+ * Free the unused part of a space extent that was reserved for a new ondisk
+ * structure. Returns the number of EFIs logged or a negative errno.
+ */
+STATIC int
+xrep_newbt_free_extent(
+ struct xrep_newbt *xnr,
+ struct xrep_newbt_resv *resv,
+ bool btree_committed)
+{
+ struct xfs_scrub *sc = xnr->sc;
+ xfs_agblock_t free_agbno = resv->agbno;
+ xfs_extlen_t free_aglen = resv->len;
+ xfs_fsblock_t fsbno;
+ int error;
+
+ if (!btree_committed || resv->used == 0) {
+ /*
+ * If we're not committing a new btree or we didn't use the
+ * space reservation, let the existing EFI free the entire
+ * space extent.
+ */
+ trace_xrep_newbt_free_blocks(sc->mp, resv->pag->pag_agno,
+ free_agbno, free_aglen, xnr->oinfo.oi_owner);
+ xfs_alloc_commit_autoreap(sc->tp, &resv->autoreap);
+ return 1;
+ }
+
+ /*
+ * We used space and committed the btree. Cancel the autoreap, remove
+ * the written blocks from the reservation, and possibly log a new EFI
+ * to free any unused reservation space.
+ */
+ xfs_alloc_cancel_autoreap(sc->tp, &resv->autoreap);
+ free_agbno += resv->used;
+ free_aglen -= resv->used;
+
+ if (free_aglen == 0)
+ return 0;
+
+ trace_xrep_newbt_free_blocks(sc->mp, resv->pag->pag_agno, free_agbno,
+ free_aglen, xnr->oinfo.oi_owner);
+
+ ASSERT(xnr->resv != XFS_AG_RESV_AGFL);
+ ASSERT(xnr->resv != XFS_AG_RESV_IGNORE);
+
+ /*
+ * Use EFIs to free the reservations. This reduces the chance
+ * that we leak blocks if the system goes down.
+ */
+ fsbno = XFS_AGB_TO_FSB(sc->mp, resv->pag->pag_agno, free_agbno);
+ error = xfs_free_extent_later(sc->tp, fsbno, free_aglen, &xnr->oinfo,
+ xnr->resv, true);
+ if (error)
+ return error;
+
+ return 1;
+}
+
+/* Free all the accounting info and disk space we reserved for a new btree. */
+STATIC int
+xrep_newbt_free(
+ struct xrep_newbt *xnr,
+ bool btree_committed)
+{
+ struct xfs_scrub *sc = xnr->sc;
+ struct xrep_newbt_resv *resv, *n;
+ unsigned int freed = 0;
+ int error = 0;
+
+ /*
+ * If the filesystem already went down, we can't free the blocks. Skip
+ * ahead to freeing the incore metadata because we can't fix anything.
+ */
+ if (xfs_is_shutdown(sc->mp))
+ goto junkit;
+
+ list_for_each_entry_safe(resv, n, &xnr->resv_list, list) {
+ int ret;
+
+ ret = xrep_newbt_free_extent(xnr, resv, btree_committed);
+ list_del(&resv->list);
+ xfs_perag_put(resv->pag);
+ kfree(resv);
+ if (ret < 0) {
+ error = ret;
+ goto junkit;
+ }
+
+ freed += ret;
+ if (freed >= XREP_MAX_ITRUNCATE_EFIS) {
+ error = xrep_defer_finish(sc);
+ if (error)
+ goto junkit;
+ freed = 0;
+ }
+ }
+
+ if (freed)
+ error = xrep_defer_finish(sc);
+
+junkit:
+ /*
+ * If we still have reservations attached to @newbt, cleanup must have
+ * failed and the filesystem is about to go down. Clean up the incore
+ * reservations and try to commit to freeing the space we used.
+ */
+ list_for_each_entry_safe(resv, n, &xnr->resv_list, list) {
+ xfs_alloc_commit_autoreap(sc->tp, &resv->autoreap);
+ list_del(&resv->list);
+ xfs_perag_put(resv->pag);
+ kfree(resv);
+ }
+
+ if (sc->ip) {
+ kmem_cache_free(xfs_ifork_cache, xnr->ifake.if_fork);
+ xnr->ifake.if_fork = NULL;
+ }
+
+ return error;
+}
+
+/*
+ * Free all the accounting info and unused disk space allocations after
+ * committing a new btree.
+ */
+int
+xrep_newbt_commit(
+ struct xrep_newbt *xnr)
+{
+ return xrep_newbt_free(xnr, true);
+}
+
+/*
+ * Free all the accounting info and all of the disk space we reserved for a new
+ * btree that we're not going to commit. We want to try to roll things back
+ * cleanly for things like ENOSPC midway through allocation.
+ */
+void
+xrep_newbt_cancel(
+ struct xrep_newbt *xnr)
+{
+ xrep_newbt_free(xnr, false);
+}
+
+/* Feed one of the reserved btree blocks to the bulk loader. */
+int
+xrep_newbt_claim_block(
+ struct xfs_btree_cur *cur,
+ struct xrep_newbt *xnr,
+ union xfs_btree_ptr *ptr)
+{
+ struct xrep_newbt_resv *resv;
+ struct xfs_mount *mp = cur->bc_mp;
+ xfs_agblock_t agbno;
+
+ /*
+ * The first item in the list should always have a free block unless
+ * we're completely out.
+ */
+ resv = list_first_entry(&xnr->resv_list, struct xrep_newbt_resv, list);
+ if (resv->used == resv->len)
+ return -ENOSPC;
+
+ /*
+ * Peel off a block from the start of the reservation. We allocate
+ * blocks in order to place blocks on disk in increasing record or key
+ * order. The block reservations tend to end up on the list in
+ * decreasing order, which hopefully results in leaf blocks ending up
+ * together.
+ */
+ agbno = resv->agbno + resv->used;
+ resv->used++;
+
+ /* If we used all the blocks in this reservation, move it to the end. */
+ if (resv->used == resv->len)
+ list_move_tail(&resv->list, &xnr->resv_list);
+
+ trace_xrep_newbt_claim_block(mp, resv->pag->pag_agno, agbno, 1,
+ xnr->oinfo.oi_owner);
+
+ if (cur->bc_flags & XFS_BTREE_LONG_PTRS)
+ ptr->l = cpu_to_be64(XFS_AGB_TO_FSB(mp, resv->pag->pag_agno,
+ agbno));
+ else
+ ptr->s = cpu_to_be32(agbno);
+
+ /* Relog all the EFIs. */
+ return xrep_defer_finish(xnr->sc);
+}
+
+/* How many reserved blocks are unused? */
+unsigned int
+xrep_newbt_unused_blocks(
+ struct xrep_newbt *xnr)
+{
+ struct xrep_newbt_resv *resv;
+ unsigned int unused = 0;
+
+ list_for_each_entry(resv, &xnr->resv_list, list)
+ unused += resv->len - resv->used;
+ return unused;
+}
diff --git a/fs/xfs/scrub/newbt.h b/fs/xfs/scrub/newbt.h
new file mode 100644
index 000000000000..89f8e3970b1f
--- /dev/null
+++ b/fs/xfs/scrub/newbt.h
@@ -0,0 +1,68 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2022-2023 Oracle. All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#ifndef __XFS_SCRUB_NEWBT_H__
+#define __XFS_SCRUB_NEWBT_H__
+
+struct xrep_newbt_resv {
+ /* Link to list of extents that we've reserved. */
+ struct list_head list;
+
+ struct xfs_perag *pag;
+
+ /* Auto-freeing this reservation if we don't commit. */
+ struct xfs_alloc_autoreap autoreap;
+
+ /* AG block of the extent we reserved. */
+ xfs_agblock_t agbno;
+
+ /* Length of the reservation. */
+ xfs_extlen_t len;
+
+ /* How much of this reservation has been used. */
+ xfs_extlen_t used;
+};
+
+struct xrep_newbt {
+ struct xfs_scrub *sc;
+
+ /* List of extents that we've reserved. */
+ struct list_head resv_list;
+
+ /* Fake root for new btree. */
+ union {
+ struct xbtree_afakeroot afake;
+ struct xbtree_ifakeroot ifake;
+ };
+
+ /* rmap owner of these blocks */
+ struct xfs_owner_info oinfo;
+
+ /* btree geometry for the bulk loader */
+ struct xfs_btree_bload bload;
+
+ /* Allocation hint */
+ xfs_fsblock_t alloc_hint;
+
+ /* per-ag reservation type */
+ enum xfs_ag_resv_type resv;
+};
+
+void xrep_newbt_init_bare(struct xrep_newbt *xnr, struct xfs_scrub *sc);
+void xrep_newbt_init_ag(struct xrep_newbt *xnr, struct xfs_scrub *sc,
+ const struct xfs_owner_info *oinfo, xfs_fsblock_t alloc_hint,
+ enum xfs_ag_resv_type resv);
+int xrep_newbt_init_inode(struct xrep_newbt *xnr, struct xfs_scrub *sc,
+ int whichfork, const struct xfs_owner_info *oinfo);
+int xrep_newbt_alloc_blocks(struct xrep_newbt *xnr, uint64_t nr_blocks);
+int xrep_newbt_add_extent(struct xrep_newbt *xnr, struct xfs_perag *pag,
+ xfs_agblock_t agbno, xfs_extlen_t len);
+void xrep_newbt_cancel(struct xrep_newbt *xnr);
+int xrep_newbt_commit(struct xrep_newbt *xnr);
+int xrep_newbt_claim_block(struct xfs_btree_cur *cur, struct xrep_newbt *xnr,
+ union xfs_btree_ptr *ptr);
+unsigned int xrep_newbt_unused_blocks(struct xrep_newbt *xnr);
+
+#endif /* __XFS_SCRUB_NEWBT_H__ */
diff --git a/fs/xfs/scrub/off_bitmap.h b/fs/xfs/scrub/off_bitmap.h
new file mode 100644
index 000000000000..0d3f9e6c1aad
--- /dev/null
+++ b/fs/xfs/scrub/off_bitmap.h
@@ -0,0 +1,37 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2022-2023 Oracle. All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#ifndef __XFS_SCRUB_OFF_BITMAP_H__
+#define __XFS_SCRUB_OFF_BITMAP_H__
+
+/* Bitmaps, but for type-checked for xfs_fileoff_t */
+
+struct xoff_bitmap {
+ struct xbitmap64 offbitmap;
+};
+
+static inline void xoff_bitmap_init(struct xoff_bitmap *bitmap)
+{
+ xbitmap64_init(&bitmap->offbitmap);
+}
+
+static inline void xoff_bitmap_destroy(struct xoff_bitmap *bitmap)
+{
+ xbitmap64_destroy(&bitmap->offbitmap);
+}
+
+static inline int xoff_bitmap_set(struct xoff_bitmap *bitmap,
+ xfs_fileoff_t off, xfs_filblks_t len)
+{
+ return xbitmap64_set(&bitmap->offbitmap, off, len);
+}
+
+static inline int xoff_bitmap_walk(struct xoff_bitmap *bitmap,
+ xbitmap64_walk_fn fn, void *priv)
+{
+ return xbitmap64_walk(&bitmap->offbitmap, fn, priv);
+}
+
+#endif /* __XFS_SCRUB_OFF_BITMAP_H__ */
diff --git a/fs/xfs/scrub/parent.c b/fs/xfs/scrub/parent.c
index e6155d86f791..7db873672146 100644
--- a/fs/xfs/scrub/parent.c
+++ b/fs/xfs/scrub/parent.c
@@ -156,6 +156,16 @@ xchk_parent_validate(
goto out_rele;
}
+ /*
+ * We cannot yet validate this parent pointer if the directory looks as
+ * though it has been zapped by the inode record repair code.
+ */
+ if (xchk_dir_looks_zapped(dp)) {
+ error = -EBUSY;
+ xchk_set_incomplete(sc);
+ goto out_unlock;
+ }
+
/* Look for a directory entry in the parent pointing to the child. */
error = xchk_dir_walk(sc, dp, xchk_parent_actor, &spc);
if (!xchk_fblock_xref_process_error(sc, XFS_DATA_FORK, 0, &error))
@@ -217,6 +227,13 @@ xchk_parent(
*/
error = xchk_parent_validate(sc, parent_ino);
} while (error == -EAGAIN);
+ if (error == -EBUSY) {
+ /*
+ * We could not scan a directory, so we marked the check
+ * incomplete. No further error return is necessary.
+ */
+ return 0;
+ }
return error;
}
diff --git a/fs/xfs/scrub/quota.c b/fs/xfs/scrub/quota.c
index 5671c8153433..183d531875ea 100644
--- a/fs/xfs/scrub/quota.c
+++ b/fs/xfs/scrub/quota.c
@@ -6,6 +6,7 @@
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_shared.h"
+#include "xfs_bit.h"
#include "xfs_format.h"
#include "xfs_trans_resv.h"
#include "xfs_mount.h"
@@ -17,9 +18,10 @@
#include "xfs_bmap.h"
#include "scrub/scrub.h"
#include "scrub/common.h"
+#include "scrub/quota.h"
/* Convert a scrub type code to a DQ flag, or return 0 if error. */
-static inline xfs_dqtype_t
+xfs_dqtype_t
xchk_quota_to_dqtype(
struct xfs_scrub *sc)
{
@@ -75,14 +77,70 @@ struct xchk_quota_info {
xfs_dqid_t last_id;
};
+/* There's a written block backing this dquot, right? */
+STATIC int
+xchk_quota_item_bmap(
+ struct xfs_scrub *sc,
+ struct xfs_dquot *dq,
+ xfs_fileoff_t offset)
+{
+ struct xfs_bmbt_irec irec;
+ struct xfs_mount *mp = sc->mp;
+ int nmaps = 1;
+ int error;
+
+ if (!xfs_verify_fileoff(mp, offset)) {
+ xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
+ return 0;
+ }
+
+ if (dq->q_fileoffset != offset) {
+ xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
+ return 0;
+ }
+
+ error = xfs_bmapi_read(sc->ip, offset, 1, &irec, &nmaps, 0);
+ if (error)
+ return error;
+
+ if (nmaps != 1) {
+ xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
+ return 0;
+ }
+
+ if (!xfs_verify_fsbno(mp, irec.br_startblock))
+ xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
+ if (XFS_FSB_TO_DADDR(mp, irec.br_startblock) != dq->q_blkno)
+ xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
+ if (!xfs_bmap_is_written_extent(&irec))
+ xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
+
+ return 0;
+}
+
+/* Complain if a quota timer is incorrectly set. */
+static inline void
+xchk_quota_item_timer(
+ struct xfs_scrub *sc,
+ xfs_fileoff_t offset,
+ const struct xfs_dquot_res *res)
+{
+ if ((res->softlimit && res->count > res->softlimit) ||
+ (res->hardlimit && res->count > res->hardlimit)) {
+ if (!res->timer)
+ xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
+ } else {
+ if (res->timer)
+ xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
+ }
+}
+
/* Scrub the fields in an individual quota item. */
STATIC int
xchk_quota_item(
- struct xfs_dquot *dq,
- xfs_dqtype_t dqtype,
- void *priv)
+ struct xchk_quota_info *sqi,
+ struct xfs_dquot *dq)
{
- struct xchk_quota_info *sqi = priv;
struct xfs_scrub *sc = sqi->sc;
struct xfs_mount *mp = sc->mp;
struct xfs_quotainfo *qi = mp->m_quotainfo;
@@ -94,6 +152,17 @@ xchk_quota_item(
return error;
/*
+ * We want to validate the bmap record for the storage backing this
+ * dquot, so we need to lock the dquot and the quota file. For quota
+ * operations, the locking order is first the ILOCK and then the dquot.
+ * However, dqiterate gave us a locked dquot, so drop the dquot lock to
+ * get the ILOCK.
+ */
+ xfs_dqunlock(dq);
+ xchk_ilock(sc, XFS_ILOCK_SHARED);
+ xfs_dqlock(dq);
+
+ /*
* Except for the root dquot, the actual dquot we got must either have
* the same or higher id as we saw before.
*/
@@ -103,6 +172,11 @@ xchk_quota_item(
sqi->last_id = dq->q_id;
+ error = xchk_quota_item_bmap(sc, dq, offset);
+ xchk_iunlock(sc, XFS_ILOCK_SHARED);
+ if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, offset, &error))
+ return error;
+
/*
* Warn if the hard limits are larger than the fs.
* Administrators can do this, though in production this seems
@@ -166,6 +240,10 @@ xchk_quota_item(
dq->q_rtb.count > dq->q_rtb.hardlimit)
xchk_fblock_set_warning(sc, XFS_DATA_FORK, offset);
+ xchk_quota_item_timer(sc, offset, &dq->q_blk);
+ xchk_quota_item_timer(sc, offset, &dq->q_ino);
+ xchk_quota_item_timer(sc, offset, &dq->q_rtb);
+
out:
if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
return -ECANCELED;
@@ -191,7 +269,7 @@ xchk_quota_data_fork(
return error;
/* Check for data fork problems that apply only to quota files. */
- max_dqid_off = ((xfs_dqid_t)-1) / qi->qi_dqperchunk;
+ max_dqid_off = XFS_DQ_ID_MAX / qi->qi_dqperchunk;
ifp = xfs_ifork_ptr(sc->ip, XFS_DATA_FORK);
for_each_xfs_iext(ifp, &icur, &irec) {
if (xchk_should_terminate(sc, &error))
@@ -218,9 +296,11 @@ int
xchk_quota(
struct xfs_scrub *sc)
{
- struct xchk_quota_info sqi;
+ struct xchk_dqiter cursor = { };
+ struct xchk_quota_info sqi = { .sc = sc };
struct xfs_mount *mp = sc->mp;
struct xfs_quotainfo *qi = mp->m_quotainfo;
+ struct xfs_dquot *dq;
xfs_dqtype_t dqtype;
int error = 0;
@@ -239,10 +319,15 @@ xchk_quota(
* functions.
*/
xchk_iunlock(sc, sc->ilock_flags);
- sqi.sc = sc;
- sqi.last_id = 0;
- error = xfs_qm_dqiterate(mp, dqtype, xchk_quota_item, &sqi);
- xchk_ilock(sc, XFS_ILOCK_EXCL);
+
+ /* Now look for things that the quota verifiers won't complain about. */
+ xchk_dqiter_init(&cursor, sc, dqtype);
+ while ((error = xchk_dquot_iter(&cursor, &dq)) == 1) {
+ error = xchk_quota_item(&sqi, dq);
+ xfs_qm_dqput(dq);
+ if (error)
+ break;
+ }
if (error == -ECANCELED)
error = 0;
if (!xchk_fblock_process_error(sc, XFS_DATA_FORK,
diff --git a/fs/xfs/scrub/quota.h b/fs/xfs/scrub/quota.h
new file mode 100644
index 000000000000..6c7134ce2385
--- /dev/null
+++ b/fs/xfs/scrub/quota.h
@@ -0,0 +1,36 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2018-2023 Oracle. All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#ifndef __XFS_SCRUB_QUOTA_H__
+#define __XFS_SCRUB_QUOTA_H__
+
+xfs_dqtype_t xchk_quota_to_dqtype(struct xfs_scrub *sc);
+
+/* dquot iteration code */
+
+struct xchk_dqiter {
+ struct xfs_scrub *sc;
+
+ /* Quota file that we're walking. */
+ struct xfs_inode *quota_ip;
+
+ /* Cached data fork mapping for the dquot. */
+ struct xfs_bmbt_irec bmap;
+
+ /* The next dquot to scan. */
+ uint64_t id;
+
+ /* Quota type (user/group/project). */
+ xfs_dqtype_t dqtype;
+
+ /* Data fork sequence number to detect stale mappings. */
+ unsigned int if_seq;
+};
+
+void xchk_dqiter_init(struct xchk_dqiter *cursor, struct xfs_scrub *sc,
+ xfs_dqtype_t dqtype);
+int xchk_dquot_iter(struct xchk_dqiter *cursor, struct xfs_dquot **dqpp);
+
+#endif /* __XFS_SCRUB_QUOTA_H__ */
diff --git a/fs/xfs/scrub/quota_repair.c b/fs/xfs/scrub/quota_repair.c
new file mode 100644
index 000000000000..0bab4c30cb85
--- /dev/null
+++ b/fs/xfs/scrub/quota_repair.c
@@ -0,0 +1,575 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2018-2023 Oracle. All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_defer.h"
+#include "xfs_btree.h"
+#include "xfs_bit.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans.h"
+#include "xfs_sb.h"
+#include "xfs_inode.h"
+#include "xfs_inode_fork.h"
+#include "xfs_alloc.h"
+#include "xfs_bmap.h"
+#include "xfs_quota.h"
+#include "xfs_qm.h"
+#include "xfs_dquot.h"
+#include "xfs_dquot_item.h"
+#include "xfs_reflink.h"
+#include "xfs_bmap_btree.h"
+#include "xfs_trans_space.h"
+#include "scrub/xfs_scrub.h"
+#include "scrub/scrub.h"
+#include "scrub/common.h"
+#include "scrub/quota.h"
+#include "scrub/trace.h"
+#include "scrub/repair.h"
+
+/*
+ * Quota Repair
+ * ============
+ *
+ * Quota repairs are fairly simplistic; we fix everything that the dquot
+ * verifiers complain about, cap any counters or limits that make no sense,
+ * and schedule a quotacheck if we had to fix anything. We also repair any
+ * data fork extent records that don't apply to metadata files.
+ */
+
+struct xrep_quota_info {
+ struct xfs_scrub *sc;
+ bool need_quotacheck;
+};
+
+/*
+ * Allocate a new block into a sparse hole in the quota file backing this
+ * dquot, initialize the block, and commit the whole mess.
+ */
+STATIC int
+xrep_quota_item_fill_bmap_hole(
+ struct xfs_scrub *sc,
+ struct xfs_dquot *dq,
+ struct xfs_bmbt_irec *irec)
+{
+ struct xfs_buf *bp;
+ struct xfs_mount *mp = sc->mp;
+ int nmaps = 1;
+ int error;
+
+ xfs_trans_ijoin(sc->tp, sc->ip, 0);
+
+ /* Map a block into the file. */
+ error = xfs_trans_reserve_more(sc->tp, XFS_QM_DQALLOC_SPACE_RES(mp),
+ 0);
+ if (error)
+ return error;
+
+ error = xfs_bmapi_write(sc->tp, sc->ip, dq->q_fileoffset,
+ XFS_DQUOT_CLUSTER_SIZE_FSB, XFS_BMAPI_METADATA, 0,
+ irec, &nmaps);
+ if (error)
+ return error;
+ if (nmaps != 1)
+ return -ENOSPC;
+
+ dq->q_blkno = XFS_FSB_TO_DADDR(mp, irec->br_startblock);
+
+ trace_xrep_dquot_item_fill_bmap_hole(sc->mp, dq->q_type, dq->q_id);
+
+ /* Initialize the new block. */
+ error = xfs_trans_get_buf(sc->tp, mp->m_ddev_targp, dq->q_blkno,
+ mp->m_quotainfo->qi_dqchunklen, 0, &bp);
+ if (error)
+ return error;
+ bp->b_ops = &xfs_dquot_buf_ops;
+
+ xfs_qm_init_dquot_blk(sc->tp, dq->q_id, dq->q_type, bp);
+ xfs_buf_set_ref(bp, XFS_DQUOT_REF);
+
+ /*
+ * Finish the mapping transactions and roll one more time to
+ * disconnect sc->ip from sc->tp.
+ */
+ error = xrep_defer_finish(sc);
+ if (error)
+ return error;
+ return xfs_trans_roll(&sc->tp);
+}
+
+/* Make sure there's a written block backing this dquot */
+STATIC int
+xrep_quota_item_bmap(
+ struct xfs_scrub *sc,
+ struct xfs_dquot *dq,
+ bool *dirty)
+{
+ struct xfs_bmbt_irec irec;
+ struct xfs_mount *mp = sc->mp;
+ struct xfs_quotainfo *qi = mp->m_quotainfo;
+ xfs_fileoff_t offset = dq->q_id / qi->qi_dqperchunk;
+ int nmaps = 1;
+ int error;
+
+ /* The computed file offset should always be valid. */
+ if (!xfs_verify_fileoff(mp, offset)) {
+ ASSERT(xfs_verify_fileoff(mp, offset));
+ return -EFSCORRUPTED;
+ }
+ dq->q_fileoffset = offset;
+
+ error = xfs_bmapi_read(sc->ip, offset, 1, &irec, &nmaps, 0);
+ if (error)
+ return error;
+
+ if (nmaps < 1 || !xfs_bmap_is_real_extent(&irec)) {
+ /* Hole/delalloc extent; allocate a real block. */
+ error = xrep_quota_item_fill_bmap_hole(sc, dq, &irec);
+ if (error)
+ return error;
+ } else if (irec.br_state != XFS_EXT_NORM) {
+ /* Unwritten extent, which we already took care of? */
+ ASSERT(irec.br_state == XFS_EXT_NORM);
+ return -EFSCORRUPTED;
+ } else if (dq->q_blkno != XFS_FSB_TO_DADDR(mp, irec.br_startblock)) {
+ /*
+ * If the cached daddr is incorrect, repair probably punched a
+ * hole out of the quota file and filled it back in with a new
+ * block. Update the block mapping in the dquot.
+ */
+ dq->q_blkno = XFS_FSB_TO_DADDR(mp, irec.br_startblock);
+ }
+
+ *dirty = true;
+ return 0;
+}
+
+/* Reset quota timers if incorrectly set. */
+static inline void
+xrep_quota_item_timer(
+ struct xfs_scrub *sc,
+ const struct xfs_dquot_res *res,
+ bool *dirty)
+{
+ if ((res->softlimit && res->count > res->softlimit) ||
+ (res->hardlimit && res->count > res->hardlimit)) {
+ if (!res->timer)
+ *dirty = true;
+ } else {
+ if (res->timer)
+ *dirty = true;
+ }
+}
+
+/* Scrub the fields in an individual quota item. */
+STATIC int
+xrep_quota_item(
+ struct xrep_quota_info *rqi,
+ struct xfs_dquot *dq)
+{
+ struct xfs_scrub *sc = rqi->sc;
+ struct xfs_mount *mp = sc->mp;
+ xfs_ino_t fs_icount;
+ bool dirty = false;
+ int error = 0;
+
+ /* Last chance to abort before we start committing fixes. */
+ if (xchk_should_terminate(sc, &error))
+ return error;
+
+ /*
+ * We might need to fix holes in the bmap record for the storage
+ * backing this dquot, so we need to lock the dquot and the quota file.
+ * dqiterate gave us a locked dquot, so drop the dquot lock to get the
+ * ILOCK_EXCL.
+ */
+ xfs_dqunlock(dq);
+ xchk_ilock(sc, XFS_ILOCK_EXCL);
+ xfs_dqlock(dq);
+
+ error = xrep_quota_item_bmap(sc, dq, &dirty);
+ xchk_iunlock(sc, XFS_ILOCK_EXCL);
+ if (error)
+ return error;
+
+ /* Check the limits. */
+ if (dq->q_blk.softlimit > dq->q_blk.hardlimit) {
+ dq->q_blk.softlimit = dq->q_blk.hardlimit;
+ dirty = true;
+ }
+
+ if (dq->q_ino.softlimit > dq->q_ino.hardlimit) {
+ dq->q_ino.softlimit = dq->q_ino.hardlimit;
+ dirty = true;
+ }
+
+ if (dq->q_rtb.softlimit > dq->q_rtb.hardlimit) {
+ dq->q_rtb.softlimit = dq->q_rtb.hardlimit;
+ dirty = true;
+ }
+
+ /*
+ * Check that usage doesn't exceed physical limits. However, on
+ * a reflink filesystem we're allowed to exceed physical space
+ * if there are no quota limits. We don't know what the real number
+ * is, but we can make quotacheck find out for us.
+ */
+ if (!xfs_has_reflink(mp) && dq->q_blk.count > mp->m_sb.sb_dblocks) {
+ dq->q_blk.reserved -= dq->q_blk.count;
+ dq->q_blk.reserved += mp->m_sb.sb_dblocks;
+ dq->q_blk.count = mp->m_sb.sb_dblocks;
+ rqi->need_quotacheck = true;
+ dirty = true;
+ }
+ fs_icount = percpu_counter_sum(&mp->m_icount);
+ if (dq->q_ino.count > fs_icount) {
+ dq->q_ino.reserved -= dq->q_ino.count;
+ dq->q_ino.reserved += fs_icount;
+ dq->q_ino.count = fs_icount;
+ rqi->need_quotacheck = true;
+ dirty = true;
+ }
+ if (dq->q_rtb.count > mp->m_sb.sb_rblocks) {
+ dq->q_rtb.reserved -= dq->q_rtb.count;
+ dq->q_rtb.reserved += mp->m_sb.sb_rblocks;
+ dq->q_rtb.count = mp->m_sb.sb_rblocks;
+ rqi->need_quotacheck = true;
+ dirty = true;
+ }
+
+ xrep_quota_item_timer(sc, &dq->q_blk, &dirty);
+ xrep_quota_item_timer(sc, &dq->q_ino, &dirty);
+ xrep_quota_item_timer(sc, &dq->q_rtb, &dirty);
+
+ if (!dirty)
+ return 0;
+
+ trace_xrep_dquot_item(sc->mp, dq->q_type, dq->q_id);
+
+ dq->q_flags |= XFS_DQFLAG_DIRTY;
+ xfs_trans_dqjoin(sc->tp, dq);
+ if (dq->q_id) {
+ xfs_qm_adjust_dqlimits(dq);
+ xfs_qm_adjust_dqtimers(dq);
+ }
+ xfs_trans_log_dquot(sc->tp, dq);
+ error = xfs_trans_roll(&sc->tp);
+ xfs_dqlock(dq);
+ return error;
+}
+
+/* Fix a quota timer so that we can pass the verifier. */
+STATIC void
+xrep_quota_fix_timer(
+ struct xfs_mount *mp,
+ const struct xfs_disk_dquot *ddq,
+ __be64 softlimit,
+ __be64 countnow,
+ __be32 *timer,
+ time64_t timelimit)
+{
+ uint64_t soft = be64_to_cpu(softlimit);
+ uint64_t count = be64_to_cpu(countnow);
+ time64_t new_timer;
+ uint32_t t;
+
+ if (!soft || count <= soft || *timer != 0)
+ return;
+
+ new_timer = xfs_dquot_set_timeout(mp,
+ ktime_get_real_seconds() + timelimit);
+ if (ddq->d_type & XFS_DQTYPE_BIGTIME)
+ t = xfs_dq_unix_to_bigtime(new_timer);
+ else
+ t = new_timer;
+
+ *timer = cpu_to_be32(t);
+}
+
+/* Fix anything the verifiers complain about. */
+STATIC int
+xrep_quota_block(
+ struct xfs_scrub *sc,
+ xfs_daddr_t daddr,
+ xfs_dqtype_t dqtype,
+ xfs_dqid_t id)
+{
+ struct xfs_dqblk *dqblk;
+ struct xfs_disk_dquot *ddq;
+ struct xfs_quotainfo *qi = sc->mp->m_quotainfo;
+ struct xfs_def_quota *defq = xfs_get_defquota(qi, dqtype);
+ struct xfs_buf *bp = NULL;
+ enum xfs_blft buftype = 0;
+ int i;
+ int error;
+
+ error = xfs_trans_read_buf(sc->mp, sc->tp, sc->mp->m_ddev_targp, daddr,
+ qi->qi_dqchunklen, 0, &bp, &xfs_dquot_buf_ops);
+ switch (error) {
+ case -EFSBADCRC:
+ case -EFSCORRUPTED:
+ /* Failed verifier, retry read with no ops. */
+ error = xfs_trans_read_buf(sc->mp, sc->tp,
+ sc->mp->m_ddev_targp, daddr, qi->qi_dqchunklen,
+ 0, &bp, NULL);
+ if (error)
+ return error;
+ break;
+ case 0:
+ dqblk = bp->b_addr;
+ ddq = &dqblk[0].dd_diskdq;
+
+ /*
+ * If there's nothing that would impede a dqiterate, we're
+ * done.
+ */
+ if ((ddq->d_type & XFS_DQTYPE_REC_MASK) != dqtype ||
+ id == be32_to_cpu(ddq->d_id)) {
+ xfs_trans_brelse(sc->tp, bp);
+ return 0;
+ }
+ break;
+ default:
+ return error;
+ }
+
+ /* Something's wrong with the block, fix the whole thing. */
+ dqblk = bp->b_addr;
+ bp->b_ops = &xfs_dquot_buf_ops;
+ for (i = 0; i < qi->qi_dqperchunk; i++, dqblk++) {
+ ddq = &dqblk->dd_diskdq;
+
+ trace_xrep_disk_dquot(sc->mp, dqtype, id + i);
+
+ ddq->d_magic = cpu_to_be16(XFS_DQUOT_MAGIC);
+ ddq->d_version = XFS_DQUOT_VERSION;
+ ddq->d_type = dqtype;
+ ddq->d_id = cpu_to_be32(id + i);
+
+ if (xfs_has_bigtime(sc->mp) && ddq->d_id)
+ ddq->d_type |= XFS_DQTYPE_BIGTIME;
+
+ xrep_quota_fix_timer(sc->mp, ddq, ddq->d_blk_softlimit,
+ ddq->d_bcount, &ddq->d_btimer,
+ defq->blk.time);
+
+ xrep_quota_fix_timer(sc->mp, ddq, ddq->d_ino_softlimit,
+ ddq->d_icount, &ddq->d_itimer,
+ defq->ino.time);
+
+ xrep_quota_fix_timer(sc->mp, ddq, ddq->d_rtb_softlimit,
+ ddq->d_rtbcount, &ddq->d_rtbtimer,
+ defq->rtb.time);
+
+ /* We only support v5 filesystems so always set these. */
+ uuid_copy(&dqblk->dd_uuid, &sc->mp->m_sb.sb_meta_uuid);
+ xfs_update_cksum((char *)dqblk, sizeof(struct xfs_dqblk),
+ XFS_DQUOT_CRC_OFF);
+ dqblk->dd_lsn = 0;
+ }
+ switch (dqtype) {
+ case XFS_DQTYPE_USER:
+ buftype = XFS_BLFT_UDQUOT_BUF;
+ break;
+ case XFS_DQTYPE_GROUP:
+ buftype = XFS_BLFT_GDQUOT_BUF;
+ break;
+ case XFS_DQTYPE_PROJ:
+ buftype = XFS_BLFT_PDQUOT_BUF;
+ break;
+ }
+ xfs_trans_buf_set_type(sc->tp, bp, buftype);
+ xfs_trans_log_buf(sc->tp, bp, 0, BBTOB(bp->b_length) - 1);
+ return xrep_roll_trans(sc);
+}
+
+/*
+ * Repair a quota file's data fork. The function returns with the inode
+ * joined.
+ */
+STATIC int
+xrep_quota_data_fork(
+ struct xfs_scrub *sc,
+ xfs_dqtype_t dqtype)
+{
+ struct xfs_bmbt_irec irec = { 0 };
+ struct xfs_iext_cursor icur;
+ struct xfs_quotainfo *qi = sc->mp->m_quotainfo;
+ struct xfs_ifork *ifp;
+ xfs_fileoff_t max_dqid_off;
+ xfs_fileoff_t off;
+ xfs_fsblock_t fsbno;
+ bool truncate = false;
+ bool joined = false;
+ int error = 0;
+
+ error = xrep_metadata_inode_forks(sc);
+ if (error)
+ goto out;
+
+ /* Check for data fork problems that apply only to quota files. */
+ max_dqid_off = XFS_DQ_ID_MAX / qi->qi_dqperchunk;
+ ifp = xfs_ifork_ptr(sc->ip, XFS_DATA_FORK);
+ for_each_xfs_iext(ifp, &icur, &irec) {
+ if (isnullstartblock(irec.br_startblock)) {
+ error = -EFSCORRUPTED;
+ goto out;
+ }
+
+ if (irec.br_startoff > max_dqid_off ||
+ irec.br_startoff + irec.br_blockcount - 1 > max_dqid_off) {
+ truncate = true;
+ break;
+ }
+
+ /* Convert unwritten extents to real ones. */
+ if (irec.br_state == XFS_EXT_UNWRITTEN) {
+ struct xfs_bmbt_irec nrec;
+ int nmap = 1;
+
+ if (!joined) {
+ xfs_trans_ijoin(sc->tp, sc->ip, 0);
+ joined = true;
+ }
+
+ error = xfs_bmapi_write(sc->tp, sc->ip,
+ irec.br_startoff, irec.br_blockcount,
+ XFS_BMAPI_CONVERT, 0, &nrec, &nmap);
+ if (error)
+ goto out;
+ if (nmap != 1) {
+ error = -ENOSPC;
+ goto out;
+ }
+ ASSERT(nrec.br_startoff == irec.br_startoff);
+ ASSERT(nrec.br_blockcount == irec.br_blockcount);
+
+ error = xfs_defer_finish(&sc->tp);
+ if (error)
+ goto out;
+ }
+ }
+
+ if (!joined) {
+ xfs_trans_ijoin(sc->tp, sc->ip, 0);
+ joined = true;
+ }
+
+ if (truncate) {
+ /* Erase everything after the block containing the max dquot */
+ error = xfs_bunmapi_range(&sc->tp, sc->ip, 0,
+ max_dqid_off * sc->mp->m_sb.sb_blocksize,
+ XFS_MAX_FILEOFF);
+ if (error)
+ goto out;
+
+ /* Remove all CoW reservations. */
+ error = xfs_reflink_cancel_cow_blocks(sc->ip, &sc->tp, 0,
+ XFS_MAX_FILEOFF, true);
+ if (error)
+ goto out;
+ sc->ip->i_diflags2 &= ~XFS_DIFLAG2_REFLINK;
+
+ /*
+ * Always re-log the inode so that our permanent transaction
+ * can keep on rolling it forward in the log.
+ */
+ xfs_trans_log_inode(sc->tp, sc->ip, XFS_ILOG_CORE);
+ }
+
+ /* Now go fix anything that fails the verifiers. */
+ for_each_xfs_iext(ifp, &icur, &irec) {
+ for (fsbno = irec.br_startblock, off = irec.br_startoff;
+ fsbno < irec.br_startblock + irec.br_blockcount;
+ fsbno += XFS_DQUOT_CLUSTER_SIZE_FSB,
+ off += XFS_DQUOT_CLUSTER_SIZE_FSB) {
+ error = xrep_quota_block(sc,
+ XFS_FSB_TO_DADDR(sc->mp, fsbno),
+ dqtype, off * qi->qi_dqperchunk);
+ if (error)
+ goto out;
+ }
+ }
+
+out:
+ return error;
+}
+
+/*
+ * Go fix anything in the quota items that we could have been mad about. Now
+ * that we've checked the quota inode data fork we have to drop ILOCK_EXCL to
+ * use the regular dquot functions.
+ */
+STATIC int
+xrep_quota_problems(
+ struct xfs_scrub *sc,
+ xfs_dqtype_t dqtype)
+{
+ struct xchk_dqiter cursor = { };
+ struct xrep_quota_info rqi = { .sc = sc };
+ struct xfs_dquot *dq;
+ int error;
+
+ xchk_dqiter_init(&cursor, sc, dqtype);
+ while ((error = xchk_dquot_iter(&cursor, &dq)) == 1) {
+ error = xrep_quota_item(&rqi, dq);
+ xfs_qm_dqput(dq);
+ if (error)
+ break;
+ }
+ if (error)
+ return error;
+
+ /* Make a quotacheck happen. */
+ if (rqi.need_quotacheck)
+ xrep_force_quotacheck(sc, dqtype);
+ return 0;
+}
+
+/* Repair all of a quota type's items. */
+int
+xrep_quota(
+ struct xfs_scrub *sc)
+{
+ xfs_dqtype_t dqtype;
+ int error;
+
+ dqtype = xchk_quota_to_dqtype(sc);
+
+ /*
+ * Re-take the ILOCK so that we can fix any problems that we found
+ * with the data fork mappings, or with the dquot bufs themselves.
+ */
+ if (!(sc->ilock_flags & XFS_ILOCK_EXCL))
+ xchk_ilock(sc, XFS_ILOCK_EXCL);
+ error = xrep_quota_data_fork(sc, dqtype);
+ if (error)
+ return error;
+
+ /*
+ * Finish deferred items and roll the transaction to unjoin the quota
+ * inode from transaction so that we can unlock the quota inode; we
+ * play only with dquots from now on.
+ */
+ error = xrep_defer_finish(sc);
+ if (error)
+ return error;
+ error = xfs_trans_roll(&sc->tp);
+ if (error)
+ return error;
+ xchk_iunlock(sc, sc->ilock_flags);
+
+ /* Fix anything the dquot verifiers don't complain about. */
+ error = xrep_quota_problems(sc, dqtype);
+ if (error)
+ return error;
+
+ return xrep_trans_commit(sc);
+}
diff --git a/fs/xfs/scrub/readdir.c b/fs/xfs/scrub/readdir.c
index e51c1544be63..16462332c897 100644
--- a/fs/xfs/scrub/readdir.c
+++ b/fs/xfs/scrub/readdir.c
@@ -36,16 +36,14 @@ xchk_dir_walk_sf(
struct xfs_mount *mp = dp->i_mount;
struct xfs_da_geometry *geo = mp->m_dir_geo;
struct xfs_dir2_sf_entry *sfep;
- struct xfs_dir2_sf_hdr *sfp;
+ struct xfs_dir2_sf_hdr *sfp = dp->i_df.if_data;
xfs_ino_t ino;
xfs_dir2_dataptr_t dapos;
unsigned int i;
int error;
ASSERT(dp->i_df.if_bytes == dp->i_disk_size);
- ASSERT(dp->i_df.if_u1.if_data != NULL);
-
- sfp = (struct xfs_dir2_sf_hdr *)dp->i_df.if_u1.if_data;
+ ASSERT(sfp != NULL);
/* dot entry */
dapos = xfs_dir2_db_off_to_dataptr(geo, geo->datablk,
diff --git a/fs/xfs/scrub/reap.c b/fs/xfs/scrub/reap.c
index 86a62420e02c..f99eca799809 100644
--- a/fs/xfs/scrub/reap.c
+++ b/fs/xfs/scrub/reap.c
@@ -20,6 +20,7 @@
#include "xfs_ialloc_btree.h"
#include "xfs_rmap.h"
#include "xfs_rmap_btree.h"
+#include "xfs_refcount.h"
#include "xfs_refcount_btree.h"
#include "xfs_extent_busy.h"
#include "xfs_ag.h"
@@ -31,11 +32,14 @@
#include "xfs_da_btree.h"
#include "xfs_attr.h"
#include "xfs_attr_remote.h"
+#include "xfs_defer.h"
#include "scrub/scrub.h"
#include "scrub/common.h"
#include "scrub/trace.h"
#include "scrub/repair.h"
#include "scrub/bitmap.h"
+#include "scrub/agb_bitmap.h"
+#include "scrub/fsb_bitmap.h"
#include "scrub/reap.h"
/*
@@ -73,10 +77,10 @@
* with only the same rmap owner but the block is not owned by something with
* the same rmap owner, the block will be freed.
*
- * The caller is responsible for locking the AG headers for the entire rebuild
- * operation so that nothing else can sneak in and change the AG state while
- * we're not looking. We must also invalidate any buffers associated with
- * @bitmap.
+ * The caller is responsible for locking the AG headers/inode for the entire
+ * rebuild operation so that nothing else can sneak in and change the incore
+ * state while we're not looking. We must also invalidate any buffers
+ * associated with @bitmap.
*/
/* Information about reaping extents after a repair. */
@@ -247,7 +251,7 @@ xreap_agextent_binval(
max_fsbs = min_t(xfs_agblock_t, agbno_next - bno,
xfs_attr3_rmt_blocks(mp, XFS_XATTR_SIZE_MAX));
- for (fsbcount = 1; fsbcount < max_fsbs; fsbcount++) {
+ for (fsbcount = 1; fsbcount <= max_fsbs; fsbcount++) {
struct xfs_buf *bp = NULL;
xfs_daddr_t daddr;
int error;
@@ -377,6 +381,17 @@ xreap_agextent_iter(
trace_xreap_dispose_unmap_extent(sc->sa.pag, agbno, *aglenp);
rs->force_roll = true;
+
+ if (rs->oinfo == &XFS_RMAP_OINFO_COW) {
+ /*
+ * If we're unmapping CoW staging extents, remove the
+ * records from the refcountbt, which will remove the
+ * rmap record as well.
+ */
+ xfs_refcount_free_cow_extent(sc->tp, fsbno, *aglenp);
+ return 0;
+ }
+
return xfs_rmap_free(sc->tp, sc->sa.agf_bp, sc->sa.pag, agbno,
*aglenp, rs->oinfo);
}
@@ -395,6 +410,26 @@ xreap_agextent_iter(
return 0;
}
+ /*
+ * If we're getting rid of CoW staging extents, use deferred work items
+ * to remove the refcountbt records (which removes the rmap records)
+ * and free the extent. We're not worried about the system going down
+ * here because log recovery walks the refcount btree to clean out the
+ * CoW staging extents.
+ */
+ if (rs->oinfo == &XFS_RMAP_OINFO_COW) {
+ ASSERT(rs->resv == XFS_AG_RESV_NONE);
+
+ xfs_refcount_free_cow_extent(sc->tp, fsbno, *aglenp);
+ error = xfs_free_extent_later(sc->tp, fsbno, *aglenp, NULL,
+ rs->resv, true);
+ if (error)
+ return error;
+
+ rs->force_roll = true;
+ return 0;
+ }
+
/* Put blocks back on the AGFL one at a time. */
if (rs->resv == XFS_AG_RESV_AGFL) {
ASSERT(*aglenp == 1);
@@ -409,13 +444,17 @@ xreap_agextent_iter(
/*
* Use deferred frees to get rid of the old btree blocks to try to
* minimize the window in which we could crash and lose the old blocks.
+ * Add a defer ops barrier every other extent to avoid stressing the
+ * system with large EFIs.
*/
- error = __xfs_free_extent_later(sc->tp, fsbno, *aglenp, rs->oinfo,
+ error = xfs_free_extent_later(sc->tp, fsbno, *aglenp, rs->oinfo,
rs->resv, true);
if (error)
return error;
rs->deferred++;
+ if (rs->deferred % 2 == 0)
+ xfs_defer_add_barrier(sc->tp);
return 0;
}
@@ -425,13 +464,12 @@ xreap_agextent_iter(
*/
STATIC int
xreap_agmeta_extent(
- uint64_t fsbno,
- uint64_t len,
+ uint32_t agbno,
+ uint32_t len,
void *priv)
{
struct xreap_state *rs = priv;
struct xfs_scrub *sc = rs->sc;
- xfs_agblock_t agbno = fsbno;
xfs_agblock_t agbno_next = agbno + len;
int error = 0;
@@ -496,3 +534,115 @@ xrep_reap_agblocks(
return 0;
}
+
+/*
+ * Break a file metadata extent into sub-extents by fate (crosslinked, not
+ * crosslinked), and dispose of each sub-extent separately. The extent must
+ * not cross an AG boundary.
+ */
+STATIC int
+xreap_fsmeta_extent(
+ uint64_t fsbno,
+ uint64_t len,
+ void *priv)
+{
+ struct xreap_state *rs = priv;
+ struct xfs_scrub *sc = rs->sc;
+ xfs_agnumber_t agno = XFS_FSB_TO_AGNO(sc->mp, fsbno);
+ xfs_agblock_t agbno = XFS_FSB_TO_AGBNO(sc->mp, fsbno);
+ xfs_agblock_t agbno_next = agbno + len;
+ int error = 0;
+
+ ASSERT(len <= XFS_MAX_BMBT_EXTLEN);
+ ASSERT(sc->ip != NULL);
+ ASSERT(!sc->sa.pag);
+
+ /*
+ * We're reaping blocks after repairing file metadata, which means that
+ * we have to init the xchk_ag structure ourselves.
+ */
+ sc->sa.pag = xfs_perag_get(sc->mp, agno);
+ if (!sc->sa.pag)
+ return -EFSCORRUPTED;
+
+ error = xfs_alloc_read_agf(sc->sa.pag, sc->tp, 0, &sc->sa.agf_bp);
+ if (error)
+ goto out_pag;
+
+ while (agbno < agbno_next) {
+ xfs_extlen_t aglen;
+ bool crosslinked;
+
+ error = xreap_agextent_select(rs, agbno, agbno_next,
+ &crosslinked, &aglen);
+ if (error)
+ goto out_agf;
+
+ error = xreap_agextent_iter(rs, agbno, &aglen, crosslinked);
+ if (error)
+ goto out_agf;
+
+ if (xreap_want_defer_finish(rs)) {
+ /*
+ * Holds the AGF buffer across the deferred chain
+ * processing.
+ */
+ error = xrep_defer_finish(sc);
+ if (error)
+ goto out_agf;
+ xreap_defer_finish_reset(rs);
+ } else if (xreap_want_roll(rs)) {
+ /*
+ * Hold the AGF buffer across the transaction roll so
+ * that we don't have to reattach it to the scrub
+ * context.
+ */
+ xfs_trans_bhold(sc->tp, sc->sa.agf_bp);
+ error = xfs_trans_roll_inode(&sc->tp, sc->ip);
+ xfs_trans_bjoin(sc->tp, sc->sa.agf_bp);
+ if (error)
+ goto out_agf;
+ xreap_reset(rs);
+ }
+
+ agbno += aglen;
+ }
+
+out_agf:
+ xfs_trans_brelse(sc->tp, sc->sa.agf_bp);
+ sc->sa.agf_bp = NULL;
+out_pag:
+ xfs_perag_put(sc->sa.pag);
+ sc->sa.pag = NULL;
+ return error;
+}
+
+/*
+ * Dispose of every block of every fs metadata extent in the bitmap.
+ * Do not use this to dispose of the mappings in an ondisk inode fork.
+ */
+int
+xrep_reap_fsblocks(
+ struct xfs_scrub *sc,
+ struct xfsb_bitmap *bitmap,
+ const struct xfs_owner_info *oinfo)
+{
+ struct xreap_state rs = {
+ .sc = sc,
+ .oinfo = oinfo,
+ .resv = XFS_AG_RESV_NONE,
+ };
+ int error;
+
+ ASSERT(xfs_has_rmapbt(sc->mp));
+ ASSERT(sc->ip != NULL);
+
+ error = xfsb_bitmap_walk(bitmap, xreap_fsmeta_extent, &rs);
+ if (error)
+ return error;
+
+ if (xreap_dirty(&rs))
+ return xrep_defer_finish(sc);
+
+ return 0;
+}
diff --git a/fs/xfs/scrub/reap.h b/fs/xfs/scrub/reap.h
index fe24626af164..0b69f16dd98f 100644
--- a/fs/xfs/scrub/reap.h
+++ b/fs/xfs/scrub/reap.h
@@ -6,7 +6,12 @@
#ifndef __XFS_SCRUB_REAP_H__
#define __XFS_SCRUB_REAP_H__
+struct xagb_bitmap;
+struct xfsb_bitmap;
+
int xrep_reap_agblocks(struct xfs_scrub *sc, struct xagb_bitmap *bitmap,
const struct xfs_owner_info *oinfo, enum xfs_ag_resv_type type);
+int xrep_reap_fsblocks(struct xfs_scrub *sc, struct xfsb_bitmap *bitmap,
+ const struct xfs_owner_info *oinfo);
#endif /* __XFS_SCRUB_REAP_H__ */
diff --git a/fs/xfs/scrub/refcount.c b/fs/xfs/scrub/refcount.c
index 304ea1e1bfb0..bf22f245bbfa 100644
--- a/fs/xfs/scrub/refcount.c
+++ b/fs/xfs/scrub/refcount.c
@@ -441,7 +441,7 @@ xchk_refcountbt_rec(
struct xchk_refcbt_records *rrc = bs->private;
xfs_refcount_btrec_to_irec(rec, &irec);
- if (xfs_refcount_check_irec(bs->cur, &irec) != NULL) {
+ if (xfs_refcount_check_irec(bs->cur->bc_ag.pag, &irec) != NULL) {
xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
return 0;
}
diff --git a/fs/xfs/scrub/refcount_repair.c b/fs/xfs/scrub/refcount_repair.c
new file mode 100644
index 000000000000..f38fccc42a20
--- /dev/null
+++ b/fs/xfs/scrub/refcount_repair.c
@@ -0,0 +1,794 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2018-2023 Oracle. All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_defer.h"
+#include "xfs_btree.h"
+#include "xfs_btree_staging.h"
+#include "xfs_inode.h"
+#include "xfs_bit.h"
+#include "xfs_log_format.h"
+#include "xfs_trans.h"
+#include "xfs_sb.h"
+#include "xfs_alloc.h"
+#include "xfs_ialloc.h"
+#include "xfs_rmap.h"
+#include "xfs_rmap_btree.h"
+#include "xfs_refcount.h"
+#include "xfs_refcount_btree.h"
+#include "xfs_error.h"
+#include "xfs_ag.h"
+#include "scrub/xfs_scrub.h"
+#include "scrub/scrub.h"
+#include "scrub/common.h"
+#include "scrub/btree.h"
+#include "scrub/trace.h"
+#include "scrub/repair.h"
+#include "scrub/bitmap.h"
+#include "scrub/agb_bitmap.h"
+#include "scrub/xfile.h"
+#include "scrub/xfarray.h"
+#include "scrub/newbt.h"
+#include "scrub/reap.h"
+
+/*
+ * Rebuilding the Reference Count Btree
+ * ====================================
+ *
+ * This algorithm is "borrowed" from xfs_repair. Imagine the rmap
+ * entries as rectangles representing extents of physical blocks, and
+ * that the rectangles can be laid down to allow them to overlap each
+ * other; then we know that we must emit a refcnt btree entry wherever
+ * the amount of overlap changes, i.e. the emission stimulus is
+ * level-triggered:
+ *
+ * - ---
+ * -- ----- ---- --- ------
+ * -- ---- ----------- ---- ---------
+ * -------------------------------- -----------
+ * ^ ^ ^^ ^^ ^ ^^ ^^^ ^^^^ ^ ^^ ^ ^ ^
+ * 2 1 23 21 3 43 234 2123 1 01 2 3 0
+ *
+ * For our purposes, a rmap is a tuple (startblock, len, fileoff, owner).
+ *
+ * Note that in the actual refcnt btree we don't store the refcount < 2
+ * cases because the bnobt tells us which blocks are free; single-use
+ * blocks aren't recorded in the bnobt or the refcntbt. If the rmapbt
+ * supports storing multiple entries covering a given block we could
+ * theoretically dispense with the refcntbt and simply count rmaps, but
+ * that's inefficient in the (hot) write path, so we'll take the cost of
+ * the extra tree to save time. Also there's no guarantee that rmap
+ * will be enabled.
+ *
+ * Given an array of rmaps sorted by physical block number, a starting
+ * physical block (sp), a bag to hold rmaps that cover sp, and the next
+ * physical block where the level changes (np), we can reconstruct the
+ * refcount btree as follows:
+ *
+ * While there are still unprocessed rmaps in the array,
+ * - Set sp to the physical block (pblk) of the next unprocessed rmap.
+ * - Add to the bag all rmaps in the array where startblock == sp.
+ * - Set np to the physical block where the bag size will change. This
+ * is the minimum of (the pblk of the next unprocessed rmap) and
+ * (startblock + len of each rmap in the bag).
+ * - Record the bag size as old_bag_size.
+ *
+ * - While the bag isn't empty,
+ * - Remove from the bag all rmaps where startblock + len == np.
+ * - Add to the bag all rmaps in the array where startblock == np.
+ * - If the bag size isn't old_bag_size, store the refcount entry
+ * (sp, np - sp, bag_size) in the refcnt btree.
+ * - If the bag is empty, break out of the inner loop.
+ * - Set old_bag_size to the bag size
+ * - Set sp = np.
+ * - Set np to the physical block where the bag size will change.
+ * This is the minimum of (the pblk of the next unprocessed rmap)
+ * and (startblock + len of each rmap in the bag).
+ *
+ * Like all the other repairers, we make a list of all the refcount
+ * records we need, then reinitialize the refcount btree root and
+ * insert all the records.
+ */
+
+/* The only parts of the rmap that we care about for computing refcounts. */
+struct xrep_refc_rmap {
+ xfs_agblock_t startblock;
+ xfs_extlen_t blockcount;
+} __packed;
+
+struct xrep_refc {
+ /* refcount extents */
+ struct xfarray *refcount_records;
+
+ /* new refcountbt information */
+ struct xrep_newbt new_btree;
+
+ /* old refcountbt blocks */
+ struct xagb_bitmap old_refcountbt_blocks;
+
+ struct xfs_scrub *sc;
+
+ /* get_records()'s position in the refcount record array. */
+ xfarray_idx_t array_cur;
+
+ /* # of refcountbt blocks */
+ xfs_extlen_t btblocks;
+};
+
+/* Check for any obvious conflicts with this shared/CoW staging extent. */
+STATIC int
+xrep_refc_check_ext(
+ struct xfs_scrub *sc,
+ const struct xfs_refcount_irec *rec)
+{
+ enum xbtree_recpacking outcome;
+ int error;
+
+ if (xfs_refcount_check_irec(sc->sa.pag, rec) != NULL)
+ return -EFSCORRUPTED;
+
+ /* Make sure this isn't free space. */
+ error = xfs_alloc_has_records(sc->sa.bno_cur, rec->rc_startblock,
+ rec->rc_blockcount, &outcome);
+ if (error)
+ return error;
+ if (outcome != XBTREE_RECPACKING_EMPTY)
+ return -EFSCORRUPTED;
+
+ /* Must not be an inode chunk. */
+ error = xfs_ialloc_has_inodes_at_extent(sc->sa.ino_cur,
+ rec->rc_startblock, rec->rc_blockcount, &outcome);
+ if (error)
+ return error;
+ if (outcome != XBTREE_RECPACKING_EMPTY)
+ return -EFSCORRUPTED;
+
+ return 0;
+}
+
+/* Record a reference count extent. */
+STATIC int
+xrep_refc_stash(
+ struct xrep_refc *rr,
+ enum xfs_refc_domain domain,
+ xfs_agblock_t agbno,
+ xfs_extlen_t len,
+ uint64_t refcount)
+{
+ struct xfs_refcount_irec irec = {
+ .rc_startblock = agbno,
+ .rc_blockcount = len,
+ .rc_domain = domain,
+ };
+ struct xfs_scrub *sc = rr->sc;
+ int error = 0;
+
+ if (xchk_should_terminate(sc, &error))
+ return error;
+
+ irec.rc_refcount = min_t(uint64_t, MAXREFCOUNT, refcount);
+
+ error = xrep_refc_check_ext(rr->sc, &irec);
+ if (error)
+ return error;
+
+ trace_xrep_refc_found(sc->sa.pag, &irec);
+
+ return xfarray_append(rr->refcount_records, &irec);
+}
+
+/* Record a CoW staging extent. */
+STATIC int
+xrep_refc_stash_cow(
+ struct xrep_refc *rr,
+ xfs_agblock_t agbno,
+ xfs_extlen_t len)
+{
+ return xrep_refc_stash(rr, XFS_REFC_DOMAIN_COW, agbno, len, 1);
+}
+
+/* Decide if an rmap could describe a shared extent. */
+static inline bool
+xrep_refc_rmap_shareable(
+ struct xfs_mount *mp,
+ const struct xfs_rmap_irec *rmap)
+{
+ /* AG metadata are never sharable */
+ if (XFS_RMAP_NON_INODE_OWNER(rmap->rm_owner))
+ return false;
+
+ /* Metadata in files are never shareable */
+ if (xfs_internal_inum(mp, rmap->rm_owner))
+ return false;
+
+ /* Metadata and unwritten file blocks are not shareable. */
+ if (rmap->rm_flags & (XFS_RMAP_ATTR_FORK | XFS_RMAP_BMBT_BLOCK |
+ XFS_RMAP_UNWRITTEN))
+ return false;
+
+ return true;
+}
+
+/*
+ * Walk along the reverse mapping records until we find one that could describe
+ * a shared extent.
+ */
+STATIC int
+xrep_refc_walk_rmaps(
+ struct xrep_refc *rr,
+ struct xrep_refc_rmap *rrm,
+ bool *have_rec)
+{
+ struct xfs_rmap_irec rmap;
+ struct xfs_btree_cur *cur = rr->sc->sa.rmap_cur;
+ struct xfs_mount *mp = cur->bc_mp;
+ int have_gt;
+ int error = 0;
+
+ *have_rec = false;
+
+ /*
+ * Loop through the remaining rmaps. Remember CoW staging
+ * extents and the refcountbt blocks from the old tree for later
+ * disposal. We can only share written data fork extents, so
+ * keep looping until we find an rmap for one.
+ */
+ do {
+ if (xchk_should_terminate(rr->sc, &error))
+ return error;
+
+ error = xfs_btree_increment(cur, 0, &have_gt);
+ if (error)
+ return error;
+ if (!have_gt)
+ return 0;
+
+ error = xfs_rmap_get_rec(cur, &rmap, &have_gt);
+ if (error)
+ return error;
+ if (XFS_IS_CORRUPT(mp, !have_gt))
+ return -EFSCORRUPTED;
+
+ if (rmap.rm_owner == XFS_RMAP_OWN_COW) {
+ error = xrep_refc_stash_cow(rr, rmap.rm_startblock,
+ rmap.rm_blockcount);
+ if (error)
+ return error;
+ } else if (rmap.rm_owner == XFS_RMAP_OWN_REFC) {
+ /* refcountbt block, dump it when we're done. */
+ rr->btblocks += rmap.rm_blockcount;
+ error = xagb_bitmap_set(&rr->old_refcountbt_blocks,
+ rmap.rm_startblock, rmap.rm_blockcount);
+ if (error)
+ return error;
+ }
+ } while (!xrep_refc_rmap_shareable(mp, &rmap));
+
+ rrm->startblock = rmap.rm_startblock;
+ rrm->blockcount = rmap.rm_blockcount;
+ *have_rec = true;
+ return 0;
+}
+
+static inline uint32_t
+xrep_refc_encode_startblock(
+ const struct xfs_refcount_irec *irec)
+{
+ uint32_t start;
+
+ start = irec->rc_startblock & ~XFS_REFC_COWFLAG;
+ if (irec->rc_domain == XFS_REFC_DOMAIN_COW)
+ start |= XFS_REFC_COWFLAG;
+
+ return start;
+}
+
+/* Sort in the same order as the ondisk records. */
+static int
+xrep_refc_extent_cmp(
+ const void *a,
+ const void *b)
+{
+ const struct xfs_refcount_irec *ap = a;
+ const struct xfs_refcount_irec *bp = b;
+ uint32_t sa, sb;
+
+ sa = xrep_refc_encode_startblock(ap);
+ sb = xrep_refc_encode_startblock(bp);
+
+ if (sa > sb)
+ return 1;
+ if (sa < sb)
+ return -1;
+ return 0;
+}
+
+/*
+ * Sort the refcount extents by startblock or else the btree records will be in
+ * the wrong order. Make sure the records do not overlap in physical space.
+ */
+STATIC int
+xrep_refc_sort_records(
+ struct xrep_refc *rr)
+{
+ struct xfs_refcount_irec irec;
+ xfarray_idx_t cur;
+ enum xfs_refc_domain dom = XFS_REFC_DOMAIN_SHARED;
+ xfs_agblock_t next_agbno = 0;
+ int error;
+
+ error = xfarray_sort(rr->refcount_records, xrep_refc_extent_cmp,
+ XFARRAY_SORT_KILLABLE);
+ if (error)
+ return error;
+
+ foreach_xfarray_idx(rr->refcount_records, cur) {
+ if (xchk_should_terminate(rr->sc, &error))
+ return error;
+
+ error = xfarray_load(rr->refcount_records, cur, &irec);
+ if (error)
+ return error;
+
+ if (dom == XFS_REFC_DOMAIN_SHARED &&
+ irec.rc_domain == XFS_REFC_DOMAIN_COW) {
+ dom = irec.rc_domain;
+ next_agbno = 0;
+ }
+
+ if (dom != irec.rc_domain)
+ return -EFSCORRUPTED;
+ if (irec.rc_startblock < next_agbno)
+ return -EFSCORRUPTED;
+
+ next_agbno = irec.rc_startblock + irec.rc_blockcount;
+ }
+
+ return error;
+}
+
+#define RRM_NEXT(r) ((r).startblock + (r).blockcount)
+/*
+ * Find the next block where the refcount changes, given the next rmap we
+ * looked at and the ones we're already tracking.
+ */
+static inline int
+xrep_refc_next_edge(
+ struct xfarray *rmap_bag,
+ struct xrep_refc_rmap *next_rrm,
+ bool next_valid,
+ xfs_agblock_t *nbnop)
+{
+ struct xrep_refc_rmap rrm;
+ xfarray_idx_t array_cur = XFARRAY_CURSOR_INIT;
+ xfs_agblock_t nbno = NULLAGBLOCK;
+ int error;
+
+ if (next_valid)
+ nbno = next_rrm->startblock;
+
+ while ((error = xfarray_iter(rmap_bag, &array_cur, &rrm)) == 1)
+ nbno = min_t(xfs_agblock_t, nbno, RRM_NEXT(rrm));
+
+ if (error)
+ return error;
+
+ /*
+ * We should have found /something/ because either next_rrm is the next
+ * interesting rmap to look at after emitting this refcount extent, or
+ * there are other rmaps in rmap_bag contributing to the current
+ * sharing count. But if something is seriously wrong, bail out.
+ */
+ if (nbno == NULLAGBLOCK)
+ return -EFSCORRUPTED;
+
+ *nbnop = nbno;
+ return 0;
+}
+
+/*
+ * Walk forward through the rmap btree to collect all rmaps starting at
+ * @bno in @rmap_bag. These represent the file(s) that share ownership of
+ * the current block. Upon return, the rmap cursor points to the last record
+ * satisfying the startblock constraint.
+ */
+static int
+xrep_refc_push_rmaps_at(
+ struct xrep_refc *rr,
+ struct xfarray *rmap_bag,
+ xfs_agblock_t bno,
+ struct xrep_refc_rmap *rrm,
+ bool *have,
+ uint64_t *stack_sz)
+{
+ struct xfs_scrub *sc = rr->sc;
+ int have_gt;
+ int error;
+
+ while (*have && rrm->startblock == bno) {
+ error = xfarray_store_anywhere(rmap_bag, rrm);
+ if (error)
+ return error;
+ (*stack_sz)++;
+ error = xrep_refc_walk_rmaps(rr, rrm, have);
+ if (error)
+ return error;
+ }
+
+ error = xfs_btree_decrement(sc->sa.rmap_cur, 0, &have_gt);
+ if (error)
+ return error;
+ if (XFS_IS_CORRUPT(sc->mp, !have_gt))
+ return -EFSCORRUPTED;
+
+ return 0;
+}
+
+/* Iterate all the rmap records to generate reference count data. */
+STATIC int
+xrep_refc_find_refcounts(
+ struct xrep_refc *rr)
+{
+ struct xrep_refc_rmap rrm;
+ struct xfs_scrub *sc = rr->sc;
+ struct xfarray *rmap_bag;
+ char *descr;
+ uint64_t old_stack_sz;
+ uint64_t stack_sz = 0;
+ xfs_agblock_t sbno;
+ xfs_agblock_t cbno;
+ xfs_agblock_t nbno;
+ bool have;
+ int error;
+
+ xrep_ag_btcur_init(sc, &sc->sa);
+
+ /*
+ * Set up a sparse array to store all the rmap records that we're
+ * tracking to generate a reference count record. If this exceeds
+ * MAXREFCOUNT, we clamp rc_refcount.
+ */
+ descr = xchk_xfile_ag_descr(sc, "rmap record bag");
+ error = xfarray_create(descr, 0, sizeof(struct xrep_refc_rmap),
+ &rmap_bag);
+ kfree(descr);
+ if (error)
+ goto out_cur;
+
+ /* Start the rmapbt cursor to the left of all records. */
+ error = xfs_btree_goto_left_edge(sc->sa.rmap_cur);
+ if (error)
+ goto out_bag;
+
+ /* Process reverse mappings into refcount data. */
+ while (xfs_btree_has_more_records(sc->sa.rmap_cur)) {
+ /* Push all rmaps with pblk == sbno onto the stack */
+ error = xrep_refc_walk_rmaps(rr, &rrm, &have);
+ if (error)
+ goto out_bag;
+ if (!have)
+ break;
+ sbno = cbno = rrm.startblock;
+ error = xrep_refc_push_rmaps_at(rr, rmap_bag, sbno,
+ &rrm, &have, &stack_sz);
+ if (error)
+ goto out_bag;
+
+ /* Set nbno to the bno of the next refcount change */
+ error = xrep_refc_next_edge(rmap_bag, &rrm, have, &nbno);
+ if (error)
+ goto out_bag;
+
+ ASSERT(nbno > sbno);
+ old_stack_sz = stack_sz;
+
+ /* While stack isn't empty... */
+ while (stack_sz) {
+ xfarray_idx_t array_cur = XFARRAY_CURSOR_INIT;
+
+ /* Pop all rmaps that end at nbno */
+ while ((error = xfarray_iter(rmap_bag, &array_cur,
+ &rrm)) == 1) {
+ if (RRM_NEXT(rrm) != nbno)
+ continue;
+ error = xfarray_unset(rmap_bag, array_cur - 1);
+ if (error)
+ goto out_bag;
+ stack_sz--;
+ }
+ if (error)
+ goto out_bag;
+
+ /* Push array items that start at nbno */
+ error = xrep_refc_walk_rmaps(rr, &rrm, &have);
+ if (error)
+ goto out_bag;
+ if (have) {
+ error = xrep_refc_push_rmaps_at(rr, rmap_bag,
+ nbno, &rrm, &have, &stack_sz);
+ if (error)
+ goto out_bag;
+ }
+
+ /* Emit refcount if necessary */
+ ASSERT(nbno > cbno);
+ if (stack_sz != old_stack_sz) {
+ if (old_stack_sz > 1) {
+ error = xrep_refc_stash(rr,
+ XFS_REFC_DOMAIN_SHARED,
+ cbno, nbno - cbno,
+ old_stack_sz);
+ if (error)
+ goto out_bag;
+ }
+ cbno = nbno;
+ }
+
+ /* Stack empty, go find the next rmap */
+ if (stack_sz == 0)
+ break;
+ old_stack_sz = stack_sz;
+ sbno = nbno;
+
+ /* Set nbno to the bno of the next refcount change */
+ error = xrep_refc_next_edge(rmap_bag, &rrm, have,
+ &nbno);
+ if (error)
+ goto out_bag;
+
+ ASSERT(nbno > sbno);
+ }
+ }
+
+ ASSERT(stack_sz == 0);
+out_bag:
+ xfarray_destroy(rmap_bag);
+out_cur:
+ xchk_ag_btcur_free(&sc->sa);
+ return error;
+}
+#undef RRM_NEXT
+
+/* Retrieve refcountbt data for bulk load. */
+STATIC int
+xrep_refc_get_records(
+ struct xfs_btree_cur *cur,
+ unsigned int idx,
+ struct xfs_btree_block *block,
+ unsigned int nr_wanted,
+ void *priv)
+{
+ struct xfs_refcount_irec *irec = &cur->bc_rec.rc;
+ struct xrep_refc *rr = priv;
+ union xfs_btree_rec *block_rec;
+ unsigned int loaded;
+ int error;
+
+ for (loaded = 0; loaded < nr_wanted; loaded++, idx++) {
+ error = xfarray_load(rr->refcount_records, rr->array_cur++,
+ irec);
+ if (error)
+ return error;
+
+ block_rec = xfs_btree_rec_addr(cur, idx, block);
+ cur->bc_ops->init_rec_from_cur(cur, block_rec);
+ }
+
+ return loaded;
+}
+
+/* Feed one of the new btree blocks to the bulk loader. */
+STATIC int
+xrep_refc_claim_block(
+ struct xfs_btree_cur *cur,
+ union xfs_btree_ptr *ptr,
+ void *priv)
+{
+ struct xrep_refc *rr = priv;
+
+ return xrep_newbt_claim_block(cur, &rr->new_btree, ptr);
+}
+
+/* Update the AGF counters. */
+STATIC int
+xrep_refc_reset_counters(
+ struct xrep_refc *rr)
+{
+ struct xfs_scrub *sc = rr->sc;
+ struct xfs_perag *pag = sc->sa.pag;
+
+ /*
+ * After we commit the new btree to disk, it is possible that the
+ * process to reap the old btree blocks will race with the AIL trying
+ * to checkpoint the old btree blocks into the filesystem. If the new
+ * tree is shorter than the old one, the refcountbt write verifier will
+ * fail and the AIL will shut down the filesystem.
+ *
+ * To avoid this, save the old incore btree height values as the alt
+ * height values before re-initializing the perag info from the updated
+ * AGF to capture all the new values.
+ */
+ pag->pagf_repair_refcount_level = pag->pagf_refcount_level;
+
+ /* Reinitialize with the values we just logged. */
+ return xrep_reinit_pagf(sc);
+}
+
+/*
+ * Use the collected refcount information to stage a new refcount btree. If
+ * this is successful we'll return with the new btree root information logged
+ * to the repair transaction but not yet committed.
+ */
+STATIC int
+xrep_refc_build_new_tree(
+ struct xrep_refc *rr)
+{
+ struct xfs_scrub *sc = rr->sc;
+ struct xfs_btree_cur *refc_cur;
+ struct xfs_perag *pag = sc->sa.pag;
+ xfs_fsblock_t fsbno;
+ int error;
+
+ error = xrep_refc_sort_records(rr);
+ if (error)
+ return error;
+
+ /*
+ * Prepare to construct the new btree by reserving disk space for the
+ * new btree and setting up all the accounting information we'll need
+ * to root the new btree while it's under construction and before we
+ * attach it to the AG header.
+ */
+ fsbno = XFS_AGB_TO_FSB(sc->mp, pag->pag_agno, xfs_refc_block(sc->mp));
+ xrep_newbt_init_ag(&rr->new_btree, sc, &XFS_RMAP_OINFO_REFC, fsbno,
+ XFS_AG_RESV_METADATA);
+ rr->new_btree.bload.get_records = xrep_refc_get_records;
+ rr->new_btree.bload.claim_block = xrep_refc_claim_block;
+
+ /* Compute how many blocks we'll need. */
+ refc_cur = xfs_refcountbt_stage_cursor(sc->mp, &rr->new_btree.afake,
+ pag);
+ error = xfs_btree_bload_compute_geometry(refc_cur,
+ &rr->new_btree.bload,
+ xfarray_length(rr->refcount_records));
+ if (error)
+ goto err_cur;
+
+ /* Last chance to abort before we start committing fixes. */
+ if (xchk_should_terminate(sc, &error))
+ goto err_cur;
+
+ /* Reserve the space we'll need for the new btree. */
+ error = xrep_newbt_alloc_blocks(&rr->new_btree,
+ rr->new_btree.bload.nr_blocks);
+ if (error)
+ goto err_cur;
+
+ /*
+ * Due to btree slack factors, it's possible for a new btree to be one
+ * level taller than the old btree. Update the incore btree height so
+ * that we don't trip the verifiers when writing the new btree blocks
+ * to disk.
+ */
+ pag->pagf_repair_refcount_level = rr->new_btree.bload.btree_height;
+
+ /* Add all observed refcount records. */
+ rr->array_cur = XFARRAY_CURSOR_INIT;
+ error = xfs_btree_bload(refc_cur, &rr->new_btree.bload, rr);
+ if (error)
+ goto err_level;
+
+ /*
+ * Install the new btree in the AG header. After this point the old
+ * btree is no longer accessible and the new tree is live.
+ */
+ xfs_refcountbt_commit_staged_btree(refc_cur, sc->tp, sc->sa.agf_bp);
+ xfs_btree_del_cursor(refc_cur, 0);
+
+ /* Reset the AGF counters now that we've changed the btree shape. */
+ error = xrep_refc_reset_counters(rr);
+ if (error)
+ goto err_newbt;
+
+ /* Dispose of any unused blocks and the accounting information. */
+ error = xrep_newbt_commit(&rr->new_btree);
+ if (error)
+ return error;
+
+ return xrep_roll_ag_trans(sc);
+
+err_level:
+ pag->pagf_repair_refcount_level = 0;
+err_cur:
+ xfs_btree_del_cursor(refc_cur, error);
+err_newbt:
+ xrep_newbt_cancel(&rr->new_btree);
+ return error;
+}
+
+/*
+ * Now that we've logged the roots of the new btrees, invalidate all of the
+ * old blocks and free them.
+ */
+STATIC int
+xrep_refc_remove_old_tree(
+ struct xrep_refc *rr)
+{
+ struct xfs_scrub *sc = rr->sc;
+ struct xfs_perag *pag = sc->sa.pag;
+ int error;
+
+ /* Free the old refcountbt blocks if they're not in use. */
+ error = xrep_reap_agblocks(sc, &rr->old_refcountbt_blocks,
+ &XFS_RMAP_OINFO_REFC, XFS_AG_RESV_METADATA);
+ if (error)
+ return error;
+
+ /*
+ * Now that we've zapped all the old refcountbt blocks we can turn off
+ * the alternate height mechanism and reset the per-AG space
+ * reservations.
+ */
+ pag->pagf_repair_refcount_level = 0;
+ sc->flags |= XREP_RESET_PERAG_RESV;
+ return 0;
+}
+
+/* Rebuild the refcount btree. */
+int
+xrep_refcountbt(
+ struct xfs_scrub *sc)
+{
+ struct xrep_refc *rr;
+ struct xfs_mount *mp = sc->mp;
+ char *descr;
+ int error;
+
+ /* We require the rmapbt to rebuild anything. */
+ if (!xfs_has_rmapbt(mp))
+ return -EOPNOTSUPP;
+
+ rr = kzalloc(sizeof(struct xrep_refc), XCHK_GFP_FLAGS);
+ if (!rr)
+ return -ENOMEM;
+ rr->sc = sc;
+
+ /* Set up enough storage to handle one refcount record per block. */
+ descr = xchk_xfile_ag_descr(sc, "reference count records");
+ error = xfarray_create(descr, mp->m_sb.sb_agblocks,
+ sizeof(struct xfs_refcount_irec),
+ &rr->refcount_records);
+ kfree(descr);
+ if (error)
+ goto out_rr;
+
+ /* Collect all reference counts. */
+ xagb_bitmap_init(&rr->old_refcountbt_blocks);
+ error = xrep_refc_find_refcounts(rr);
+ if (error)
+ goto out_bitmap;
+
+ /* Rebuild the refcount information. */
+ error = xrep_refc_build_new_tree(rr);
+ if (error)
+ goto out_bitmap;
+
+ /* Kill the old tree. */
+ error = xrep_refc_remove_old_tree(rr);
+ if (error)
+ goto out_bitmap;
+
+out_bitmap:
+ xagb_bitmap_destroy(&rr->old_refcountbt_blocks);
+ xfarray_destroy(rr->refcount_records);
+out_rr:
+ kfree(rr);
+ return error;
+}
diff --git a/fs/xfs/scrub/repair.c b/fs/xfs/scrub/repair.c
index 1b8b5439f2d7..745d5b8f405a 100644
--- a/fs/xfs/scrub/repair.c
+++ b/fs/xfs/scrub/repair.c
@@ -27,6 +27,9 @@
#include "xfs_quota.h"
#include "xfs_qm.h"
#include "xfs_defer.h"
+#include "xfs_errortag.h"
+#include "xfs_error.h"
+#include "xfs_reflink.h"
#include "scrub/scrub.h"
#include "scrub/common.h"
#include "scrub/trace.h"
@@ -176,6 +179,16 @@ xrep_roll_ag_trans(
return 0;
}
+/* Roll the scrub transaction, holding the primary metadata locked. */
+int
+xrep_roll_trans(
+ struct xfs_scrub *sc)
+{
+ if (!sc->ip)
+ return xrep_roll_ag_trans(sc);
+ return xfs_trans_roll_inode(&sc->tp, sc->ip);
+}
+
/* Finish all deferred work attached to the repair transaction. */
int
xrep_defer_finish(
@@ -673,6 +686,7 @@ xrep_find_ag_btree_roots(
return error;
}
+#ifdef CONFIG_XFS_QUOTA
/* Force a quotacheck the next time we mount. */
void
xrep_force_quotacheck(
@@ -699,10 +713,10 @@ xrep_force_quotacheck(
*
* This function ensures that the appropriate dquots are attached to an inode.
* We cannot allow the dquot code to allocate an on-disk dquot block here
- * because we're already in transaction context with the inode locked. The
- * on-disk dquot should already exist anyway. If the quota code signals
- * corruption or missing quota information, schedule quotacheck, which will
- * repair corruptions in the quota metadata.
+ * because we're already in transaction context. The on-disk dquot should
+ * already exist anyway. If the quota code signals corruption or missing quota
+ * information, schedule quotacheck, which will repair corruptions in the quota
+ * metadata.
*/
int
xrep_ino_dqattach(
@@ -710,7 +724,10 @@ xrep_ino_dqattach(
{
int error;
- error = xfs_qm_dqattach_locked(sc->ip, false);
+ ASSERT(sc->tp != NULL);
+ ASSERT(sc->ip != NULL);
+
+ error = xfs_qm_dqattach(sc->ip);
switch (error) {
case -EFSBADCRC:
case -EFSCORRUPTED:
@@ -734,3 +751,367 @@ xrep_ino_dqattach(
return error;
}
+#endif /* CONFIG_XFS_QUOTA */
+
+/*
+ * Ensure that the inode being repaired is ready to handle a certain number of
+ * extents, or return EFSCORRUPTED. Caller must hold the ILOCK of the inode
+ * being repaired and have joined it to the scrub transaction.
+ */
+int
+xrep_ino_ensure_extent_count(
+ struct xfs_scrub *sc,
+ int whichfork,
+ xfs_extnum_t nextents)
+{
+ xfs_extnum_t max_extents;
+ bool inode_has_nrext64;
+
+ inode_has_nrext64 = xfs_inode_has_large_extent_counts(sc->ip);
+ max_extents = xfs_iext_max_nextents(inode_has_nrext64, whichfork);
+ if (nextents <= max_extents)
+ return 0;
+ if (inode_has_nrext64)
+ return -EFSCORRUPTED;
+ if (!xfs_has_large_extent_counts(sc->mp))
+ return -EFSCORRUPTED;
+
+ max_extents = xfs_iext_max_nextents(true, whichfork);
+ if (nextents > max_extents)
+ return -EFSCORRUPTED;
+
+ sc->ip->i_diflags2 |= XFS_DIFLAG2_NREXT64;
+ xfs_trans_log_inode(sc->tp, sc->ip, XFS_ILOG_CORE);
+ return 0;
+}
+
+/*
+ * Initialize all the btree cursors for an AG repair except for the btree that
+ * we're rebuilding.
+ */
+void
+xrep_ag_btcur_init(
+ struct xfs_scrub *sc,
+ struct xchk_ag *sa)
+{
+ struct xfs_mount *mp = sc->mp;
+
+ /* Set up a bnobt cursor for cross-referencing. */
+ if (sc->sm->sm_type != XFS_SCRUB_TYPE_BNOBT &&
+ sc->sm->sm_type != XFS_SCRUB_TYPE_CNTBT) {
+ sa->bno_cur = xfs_allocbt_init_cursor(mp, sc->tp, sa->agf_bp,
+ sc->sa.pag, XFS_BTNUM_BNO);
+ sa->cnt_cur = xfs_allocbt_init_cursor(mp, sc->tp, sa->agf_bp,
+ sc->sa.pag, XFS_BTNUM_CNT);
+ }
+
+ /* Set up a inobt cursor for cross-referencing. */
+ if (sc->sm->sm_type != XFS_SCRUB_TYPE_INOBT &&
+ sc->sm->sm_type != XFS_SCRUB_TYPE_FINOBT) {
+ sa->ino_cur = xfs_inobt_init_cursor(sc->sa.pag, sc->tp,
+ sa->agi_bp, XFS_BTNUM_INO);
+ if (xfs_has_finobt(mp))
+ sa->fino_cur = xfs_inobt_init_cursor(sc->sa.pag,
+ sc->tp, sa->agi_bp, XFS_BTNUM_FINO);
+ }
+
+ /* Set up a rmapbt cursor for cross-referencing. */
+ if (sc->sm->sm_type != XFS_SCRUB_TYPE_RMAPBT &&
+ xfs_has_rmapbt(mp))
+ sa->rmap_cur = xfs_rmapbt_init_cursor(mp, sc->tp, sa->agf_bp,
+ sc->sa.pag);
+
+ /* Set up a refcountbt cursor for cross-referencing. */
+ if (sc->sm->sm_type != XFS_SCRUB_TYPE_REFCNTBT &&
+ xfs_has_reflink(mp))
+ sa->refc_cur = xfs_refcountbt_init_cursor(mp, sc->tp,
+ sa->agf_bp, sc->sa.pag);
+}
+
+/*
+ * Reinitialize the in-core AG state after a repair by rereading the AGF
+ * buffer. We had better get the same AGF buffer as the one that's attached
+ * to the scrub context.
+ */
+int
+xrep_reinit_pagf(
+ struct xfs_scrub *sc)
+{
+ struct xfs_perag *pag = sc->sa.pag;
+ struct xfs_buf *bp;
+ int error;
+
+ ASSERT(pag);
+ ASSERT(xfs_perag_initialised_agf(pag));
+
+ clear_bit(XFS_AGSTATE_AGF_INIT, &pag->pag_opstate);
+ error = xfs_alloc_read_agf(pag, sc->tp, 0, &bp);
+ if (error)
+ return error;
+
+ if (bp != sc->sa.agf_bp) {
+ ASSERT(bp == sc->sa.agf_bp);
+ return -EFSCORRUPTED;
+ }
+
+ return 0;
+}
+
+/*
+ * Reinitialize the in-core AG state after a repair by rereading the AGI
+ * buffer. We had better get the same AGI buffer as the one that's attached
+ * to the scrub context.
+ */
+int
+xrep_reinit_pagi(
+ struct xfs_scrub *sc)
+{
+ struct xfs_perag *pag = sc->sa.pag;
+ struct xfs_buf *bp;
+ int error;
+
+ ASSERT(pag);
+ ASSERT(xfs_perag_initialised_agi(pag));
+
+ clear_bit(XFS_AGSTATE_AGI_INIT, &pag->pag_opstate);
+ error = xfs_ialloc_read_agi(pag, sc->tp, &bp);
+ if (error)
+ return error;
+
+ if (bp != sc->sa.agi_bp) {
+ ASSERT(bp == sc->sa.agi_bp);
+ return -EFSCORRUPTED;
+ }
+
+ return 0;
+}
+
+/*
+ * Given an active reference to a perag structure, load AG headers and cursors.
+ * This should only be called to scan an AG while repairing file-based metadata.
+ */
+int
+xrep_ag_init(
+ struct xfs_scrub *sc,
+ struct xfs_perag *pag,
+ struct xchk_ag *sa)
+{
+ int error;
+
+ ASSERT(!sa->pag);
+
+ error = xfs_ialloc_read_agi(pag, sc->tp, &sa->agi_bp);
+ if (error)
+ return error;
+
+ error = xfs_alloc_read_agf(pag, sc->tp, 0, &sa->agf_bp);
+ if (error)
+ return error;
+
+ /* Grab our own passive reference from the caller's ref. */
+ sa->pag = xfs_perag_hold(pag);
+ xrep_ag_btcur_init(sc, sa);
+ return 0;
+}
+
+/* Reinitialize the per-AG block reservation for the AG we just fixed. */
+int
+xrep_reset_perag_resv(
+ struct xfs_scrub *sc)
+{
+ int error;
+
+ if (!(sc->flags & XREP_RESET_PERAG_RESV))
+ return 0;
+
+ ASSERT(sc->sa.pag != NULL);
+ ASSERT(sc->ops->type == ST_PERAG);
+ ASSERT(sc->tp);
+
+ sc->flags &= ~XREP_RESET_PERAG_RESV;
+ error = xfs_ag_resv_free(sc->sa.pag);
+ if (error)
+ goto out;
+ error = xfs_ag_resv_init(sc->sa.pag, sc->tp);
+ if (error == -ENOSPC) {
+ xfs_err(sc->mp,
+"Insufficient free space to reset per-AG reservation for AG %u after repair.",
+ sc->sa.pag->pag_agno);
+ error = 0;
+ }
+
+out:
+ return error;
+}
+
+/* Decide if we are going to call the repair function for a scrub type. */
+bool
+xrep_will_attempt(
+ struct xfs_scrub *sc)
+{
+ /* Userspace asked us to rebuild the structure regardless. */
+ if (sc->sm->sm_flags & XFS_SCRUB_IFLAG_FORCE_REBUILD)
+ return true;
+
+ /* Let debug users force us into the repair routines. */
+ if (XFS_TEST_ERROR(false, sc->mp, XFS_ERRTAG_FORCE_SCRUB_REPAIR))
+ return true;
+
+ /* Metadata is corrupt or failed cross-referencing. */
+ if (xchk_needs_repair(sc->sm))
+ return true;
+
+ return false;
+}
+
+/* Try to fix some part of a metadata inode by calling another scrubber. */
+STATIC int
+xrep_metadata_inode_subtype(
+ struct xfs_scrub *sc,
+ unsigned int scrub_type)
+{
+ __u32 smtype = sc->sm->sm_type;
+ __u32 smflags = sc->sm->sm_flags;
+ unsigned int sick_mask = sc->sick_mask;
+ int error;
+
+ /*
+ * Let's see if the inode needs repair. We're going to open-code calls
+ * to the scrub and repair functions so that we can hang on to the
+ * resources that we already acquired instead of using the standard
+ * setup/teardown routines.
+ */
+ sc->sm->sm_flags &= ~XFS_SCRUB_FLAGS_OUT;
+ sc->sm->sm_type = scrub_type;
+
+ switch (scrub_type) {
+ case XFS_SCRUB_TYPE_INODE:
+ error = xchk_inode(sc);
+ break;
+ case XFS_SCRUB_TYPE_BMBTD:
+ error = xchk_bmap_data(sc);
+ break;
+ case XFS_SCRUB_TYPE_BMBTA:
+ error = xchk_bmap_attr(sc);
+ break;
+ default:
+ ASSERT(0);
+ error = -EFSCORRUPTED;
+ }
+ if (error)
+ goto out;
+
+ if (!xrep_will_attempt(sc))
+ goto out;
+
+ /*
+ * Repair some part of the inode. This will potentially join the inode
+ * to the transaction.
+ */
+ switch (scrub_type) {
+ case XFS_SCRUB_TYPE_INODE:
+ error = xrep_inode(sc);
+ break;
+ case XFS_SCRUB_TYPE_BMBTD:
+ error = xrep_bmap(sc, XFS_DATA_FORK, false);
+ break;
+ case XFS_SCRUB_TYPE_BMBTA:
+ error = xrep_bmap(sc, XFS_ATTR_FORK, false);
+ break;
+ }
+ if (error)
+ goto out;
+
+ /*
+ * Finish all deferred intent items and then roll the transaction so
+ * that the inode will not be joined to the transaction when we exit
+ * the function.
+ */
+ error = xfs_defer_finish(&sc->tp);
+ if (error)
+ goto out;
+ error = xfs_trans_roll(&sc->tp);
+ if (error)
+ goto out;
+
+ /*
+ * Clear the corruption flags and re-check the metadata that we just
+ * repaired.
+ */
+ sc->sm->sm_flags &= ~XFS_SCRUB_FLAGS_OUT;
+
+ switch (scrub_type) {
+ case XFS_SCRUB_TYPE_INODE:
+ error = xchk_inode(sc);
+ break;
+ case XFS_SCRUB_TYPE_BMBTD:
+ error = xchk_bmap_data(sc);
+ break;
+ case XFS_SCRUB_TYPE_BMBTA:
+ error = xchk_bmap_attr(sc);
+ break;
+ }
+ if (error)
+ goto out;
+
+ /* If corruption persists, the repair has failed. */
+ if (xchk_needs_repair(sc->sm)) {
+ error = -EFSCORRUPTED;
+ goto out;
+ }
+out:
+ sc->sick_mask = sick_mask;
+ sc->sm->sm_type = smtype;
+ sc->sm->sm_flags = smflags;
+ return error;
+}
+
+/*
+ * Repair the ondisk forks of a metadata inode. The caller must ensure that
+ * sc->ip points to the metadata inode and the ILOCK is held on that inode.
+ * The inode must not be joined to the transaction before the call, and will
+ * not be afterwards.
+ */
+int
+xrep_metadata_inode_forks(
+ struct xfs_scrub *sc)
+{
+ bool dirty = false;
+ int error;
+
+ /* Repair the inode record and the data fork. */
+ error = xrep_metadata_inode_subtype(sc, XFS_SCRUB_TYPE_INODE);
+ if (error)
+ return error;
+
+ error = xrep_metadata_inode_subtype(sc, XFS_SCRUB_TYPE_BMBTD);
+ if (error)
+ return error;
+
+ /* Make sure the attr fork looks ok before we delete it. */
+ error = xrep_metadata_inode_subtype(sc, XFS_SCRUB_TYPE_BMBTA);
+ if (error)
+ return error;
+
+ /* Clear the reflink flag since metadata never shares. */
+ if (xfs_is_reflink_inode(sc->ip)) {
+ dirty = true;
+ xfs_trans_ijoin(sc->tp, sc->ip, 0);
+ error = xfs_reflink_clear_inode_flag(sc->ip, &sc->tp);
+ if (error)
+ return error;
+ }
+
+ /*
+ * If we modified the inode, roll the transaction but don't rejoin the
+ * inode to the new transaction because xrep_bmap_data can do that.
+ */
+ if (dirty) {
+ error = xfs_trans_roll(&sc->tp);
+ if (error)
+ return error;
+ dirty = false;
+ }
+
+ return 0;
+}
diff --git a/fs/xfs/scrub/repair.h b/fs/xfs/scrub/repair.h
index 60d2a9ae5f2e..17114327e6fa 100644
--- a/fs/xfs/scrub/repair.h
+++ b/fs/xfs/scrub/repair.h
@@ -28,15 +28,28 @@ static inline int xrep_notsupported(struct xfs_scrub *sc)
/* Repair helpers */
int xrep_attempt(struct xfs_scrub *sc, struct xchk_stats_run *run);
+bool xrep_will_attempt(struct xfs_scrub *sc);
void xrep_failure(struct xfs_mount *mp);
int xrep_roll_ag_trans(struct xfs_scrub *sc);
+int xrep_roll_trans(struct xfs_scrub *sc);
int xrep_defer_finish(struct xfs_scrub *sc);
bool xrep_ag_has_space(struct xfs_perag *pag, xfs_extlen_t nr_blocks,
enum xfs_ag_resv_type type);
xfs_extlen_t xrep_calc_ag_resblks(struct xfs_scrub *sc);
+static inline int
+xrep_trans_commit(
+ struct xfs_scrub *sc)
+{
+ int error = xfs_trans_commit(sc->tp);
+
+ sc->tp = NULL;
+ return error;
+}
+
struct xbitmap;
struct xagb_bitmap;
+struct xfsb_bitmap;
int xrep_fix_freelist(struct xfs_scrub *sc, bool can_shrink);
@@ -57,8 +70,35 @@ struct xrep_find_ag_btree {
int xrep_find_ag_btree_roots(struct xfs_scrub *sc, struct xfs_buf *agf_bp,
struct xrep_find_ag_btree *btree_info, struct xfs_buf *agfl_bp);
+
+#ifdef CONFIG_XFS_QUOTA
void xrep_force_quotacheck(struct xfs_scrub *sc, xfs_dqtype_t type);
int xrep_ino_dqattach(struct xfs_scrub *sc);
+#else
+# define xrep_force_quotacheck(sc, type) ((void)0)
+# define xrep_ino_dqattach(sc) (0)
+#endif /* CONFIG_XFS_QUOTA */
+
+int xrep_ino_ensure_extent_count(struct xfs_scrub *sc, int whichfork,
+ xfs_extnum_t nextents);
+int xrep_reset_perag_resv(struct xfs_scrub *sc);
+int xrep_bmap(struct xfs_scrub *sc, int whichfork, bool allow_unwritten);
+int xrep_metadata_inode_forks(struct xfs_scrub *sc);
+
+/* Repair setup functions */
+int xrep_setup_ag_allocbt(struct xfs_scrub *sc);
+
+struct xfs_imap;
+int xrep_setup_inode(struct xfs_scrub *sc, const struct xfs_imap *imap);
+
+void xrep_ag_btcur_init(struct xfs_scrub *sc, struct xchk_ag *sa);
+int xrep_ag_init(struct xfs_scrub *sc, struct xfs_perag *pag,
+ struct xchk_ag *sa);
+
+/* Metadata revalidators */
+
+int xrep_revalidate_allocbt(struct xfs_scrub *sc);
+int xrep_revalidate_iallocbt(struct xfs_scrub *sc);
/* Metadata repairers */
@@ -67,9 +107,34 @@ int xrep_superblock(struct xfs_scrub *sc);
int xrep_agf(struct xfs_scrub *sc);
int xrep_agfl(struct xfs_scrub *sc);
int xrep_agi(struct xfs_scrub *sc);
+int xrep_allocbt(struct xfs_scrub *sc);
+int xrep_iallocbt(struct xfs_scrub *sc);
+int xrep_refcountbt(struct xfs_scrub *sc);
+int xrep_inode(struct xfs_scrub *sc);
+int xrep_bmap_data(struct xfs_scrub *sc);
+int xrep_bmap_attr(struct xfs_scrub *sc);
+int xrep_bmap_cow(struct xfs_scrub *sc);
+
+#ifdef CONFIG_XFS_RT
+int xrep_rtbitmap(struct xfs_scrub *sc);
+#else
+# define xrep_rtbitmap xrep_notsupported
+#endif /* CONFIG_XFS_RT */
+
+#ifdef CONFIG_XFS_QUOTA
+int xrep_quota(struct xfs_scrub *sc);
+#else
+# define xrep_quota xrep_notsupported
+#endif /* CONFIG_XFS_QUOTA */
+
+int xrep_reinit_pagf(struct xfs_scrub *sc);
+int xrep_reinit_pagi(struct xfs_scrub *sc);
#else
+#define xrep_ino_dqattach(sc) (0)
+#define xrep_will_attempt(sc) (false)
+
static inline int
xrep_attempt(
struct xfs_scrub *sc,
@@ -87,11 +152,45 @@ xrep_calc_ag_resblks(
return 0;
}
+static inline int
+xrep_reset_perag_resv(
+ struct xfs_scrub *sc)
+{
+ if (!(sc->flags & XREP_RESET_PERAG_RESV))
+ return 0;
+
+ ASSERT(0);
+ return -EOPNOTSUPP;
+}
+
+/* repair setup functions for no-repair */
+static inline int
+xrep_setup_nothing(
+ struct xfs_scrub *sc)
+{
+ return 0;
+}
+#define xrep_setup_ag_allocbt xrep_setup_nothing
+
+#define xrep_setup_inode(sc, imap) ((void)0)
+
+#define xrep_revalidate_allocbt (NULL)
+#define xrep_revalidate_iallocbt (NULL)
+
#define xrep_probe xrep_notsupported
#define xrep_superblock xrep_notsupported
#define xrep_agf xrep_notsupported
#define xrep_agfl xrep_notsupported
#define xrep_agi xrep_notsupported
+#define xrep_allocbt xrep_notsupported
+#define xrep_iallocbt xrep_notsupported
+#define xrep_refcountbt xrep_notsupported
+#define xrep_inode xrep_notsupported
+#define xrep_bmap_data xrep_notsupported
+#define xrep_bmap_attr xrep_notsupported
+#define xrep_bmap_cow xrep_notsupported
+#define xrep_rtbitmap xrep_notsupported
+#define xrep_quota xrep_notsupported
#endif /* CONFIG_XFS_ONLINE_REPAIR */
diff --git a/fs/xfs/scrub/rmap.c b/fs/xfs/scrub/rmap.c
index d29a26ecddd6..c99d1714f283 100644
--- a/fs/xfs/scrub/rmap.c
+++ b/fs/xfs/scrub/rmap.c
@@ -24,6 +24,7 @@
#include "scrub/common.h"
#include "scrub/btree.h"
#include "scrub/bitmap.h"
+#include "scrub/agb_bitmap.h"
/*
* Set us up to scrub reverse mapping btrees.
diff --git a/fs/xfs/scrub/rtbitmap.c b/fs/xfs/scrub/rtbitmap.c
index 41a1d89ae8e6..441ca9977652 100644
--- a/fs/xfs/scrub/rtbitmap.c
+++ b/fs/xfs/scrub/rtbitmap.c
@@ -14,17 +14,33 @@
#include "xfs_rtbitmap.h"
#include "xfs_inode.h"
#include "xfs_bmap.h"
+#include "xfs_bit.h"
#include "scrub/scrub.h"
#include "scrub/common.h"
+#include "scrub/repair.h"
+#include "scrub/rtbitmap.h"
/* Set us up with the realtime metadata locked. */
int
xchk_setup_rtbitmap(
struct xfs_scrub *sc)
{
+ struct xfs_mount *mp = sc->mp;
+ struct xchk_rtbitmap *rtb;
int error;
- error = xchk_trans_alloc(sc, 0);
+ rtb = kzalloc(sizeof(struct xchk_rtbitmap), XCHK_GFP_FLAGS);
+ if (!rtb)
+ return -ENOMEM;
+ sc->buf = rtb;
+
+ if (xchk_could_repair(sc)) {
+ error = xrep_setup_rtbitmap(sc, rtb);
+ if (error)
+ return error;
+ }
+
+ error = xchk_trans_alloc(sc, rtb->resblks);
if (error)
return error;
@@ -32,7 +48,22 @@ xchk_setup_rtbitmap(
if (error)
return error;
+ error = xchk_ino_dqattach(sc);
+ if (error)
+ return error;
+
xchk_ilock(sc, XFS_ILOCK_EXCL | XFS_ILOCK_RTBITMAP);
+
+ /*
+ * Now that we've locked the rtbitmap, we can't race with growfsrt
+ * trying to expand the bitmap or change the size of the rt volume.
+ * Hence it is safe to compute and check the geometry values.
+ */
+ if (mp->m_sb.sb_rblocks) {
+ rtb->rextents = xfs_rtb_to_rtx(mp, mp->m_sb.sb_rblocks);
+ rtb->rextslog = xfs_compute_rextslog(rtb->rextents);
+ rtb->rbmblocks = xfs_rtbitmap_blockcount(mp, rtb->rextents);
+ }
return 0;
}
@@ -63,21 +94,30 @@ STATIC int
xchk_rtbitmap_check_extents(
struct xfs_scrub *sc)
{
- struct xfs_mount *mp = sc->mp;
struct xfs_bmbt_irec map;
- xfs_rtblock_t off;
- int nmap;
+ struct xfs_iext_cursor icur;
+ struct xfs_mount *mp = sc->mp;
+ struct xfs_inode *ip = sc->ip;
+ xfs_fileoff_t off = 0;
+ xfs_fileoff_t endoff;
int error = 0;
- for (off = 0; off < mp->m_sb.sb_rbmblocks;) {
+ /* Mappings may not cross or lie beyond EOF. */
+ endoff = XFS_B_TO_FSB(mp, ip->i_disk_size);
+ if (xfs_iext_lookup_extent(ip, &ip->i_df, endoff, &icur, &map)) {
+ xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, endoff);
+ return 0;
+ }
+
+ while (off < endoff) {
+ int nmap = 1;
+
if (xchk_should_terminate(sc, &error) ||
(sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT))
break;
/* Make sure we have a written extent. */
- nmap = 1;
- error = xfs_bmapi_read(mp->m_rbmip, off,
- mp->m_sb.sb_rbmblocks - off, &map, &nmap,
+ error = xfs_bmapi_read(ip, off, endoff - off, &map, &nmap,
XFS_DATA_FORK);
if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, off, &error))
break;
@@ -98,12 +138,48 @@ int
xchk_rtbitmap(
struct xfs_scrub *sc)
{
+ struct xfs_mount *mp = sc->mp;
+ struct xchk_rtbitmap *rtb = sc->buf;
int error;
- /* Is the size of the rtbitmap correct? */
- if (sc->mp->m_rbmip->i_disk_size !=
- XFS_FSB_TO_B(sc->mp, sc->mp->m_sb.sb_rbmblocks)) {
- xchk_ino_set_corrupt(sc, sc->mp->m_rbmip->i_ino);
+ /* Is sb_rextents correct? */
+ if (mp->m_sb.sb_rextents != rtb->rextents) {
+ xchk_ino_set_corrupt(sc, mp->m_rbmip->i_ino);
+ return 0;
+ }
+
+ /* Is sb_rextslog correct? */
+ if (mp->m_sb.sb_rextslog != rtb->rextslog) {
+ xchk_ino_set_corrupt(sc, mp->m_rbmip->i_ino);
+ return 0;
+ }
+
+ /*
+ * Is sb_rbmblocks large enough to handle the current rt volume? In no
+ * case can we exceed 4bn bitmap blocks since the super field is a u32.
+ */
+ if (rtb->rbmblocks > U32_MAX) {
+ xchk_ino_set_corrupt(sc, mp->m_rbmip->i_ino);
+ return 0;
+ }
+ if (mp->m_sb.sb_rbmblocks != rtb->rbmblocks) {
+ xchk_ino_set_corrupt(sc, mp->m_rbmip->i_ino);
+ return 0;
+ }
+
+ /* The bitmap file length must be aligned to an fsblock. */
+ if (mp->m_rbmip->i_disk_size & mp->m_blockmask) {
+ xchk_ino_set_corrupt(sc, mp->m_rbmip->i_ino);
+ return 0;
+ }
+
+ /*
+ * Is the bitmap file itself large enough to handle the rt volume?
+ * growfsrt expands the bitmap file before updating sb_rextents, so the
+ * file can be larger than sb_rbmblocks.
+ */
+ if (mp->m_rbmip->i_disk_size < XFS_FSB_TO_B(mp, rtb->rbmblocks)) {
+ xchk_ino_set_corrupt(sc, mp->m_rbmip->i_ino);
return 0;
}
@@ -116,12 +192,11 @@ xchk_rtbitmap(
if (error || (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT))
return error;
- error = xfs_rtalloc_query_all(sc->mp, sc->tp, xchk_rtbitmap_rec, sc);
+ error = xfs_rtalloc_query_all(mp, sc->tp, xchk_rtbitmap_rec, sc);
if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, 0, &error))
- goto out;
+ return error;
-out:
- return error;
+ return 0;
}
/* xref check that the extent is not free in the rtbitmap */
diff --git a/fs/xfs/scrub/rtbitmap.h b/fs/xfs/scrub/rtbitmap.h
new file mode 100644
index 000000000000..85304ff019e1
--- /dev/null
+++ b/fs/xfs/scrub/rtbitmap.h
@@ -0,0 +1,22 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2023 Oracle. All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#ifndef __XFS_SCRUB_RTBITMAP_H__
+#define __XFS_SCRUB_RTBITMAP_H__
+
+struct xchk_rtbitmap {
+ uint64_t rextents;
+ uint64_t rbmblocks;
+ unsigned int rextslog;
+ unsigned int resblks;
+};
+
+#ifdef CONFIG_XFS_ONLINE_REPAIR
+int xrep_setup_rtbitmap(struct xfs_scrub *sc, struct xchk_rtbitmap *rtb);
+#else
+# define xrep_setup_rtbitmap(sc, rtb) (0)
+#endif /* CONFIG_XFS_ONLINE_REPAIR */
+
+#endif /* __XFS_SCRUB_RTBITMAP_H__ */
diff --git a/fs/xfs/scrub/rtbitmap_repair.c b/fs/xfs/scrub/rtbitmap_repair.c
new file mode 100644
index 000000000000..46f5d5f605c9
--- /dev/null
+++ b/fs/xfs/scrub/rtbitmap_repair.c
@@ -0,0 +1,202 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2020-2023 Oracle. All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_btree.h"
+#include "xfs_log_format.h"
+#include "xfs_trans.h"
+#include "xfs_inode.h"
+#include "xfs_bit.h"
+#include "xfs_bmap.h"
+#include "xfs_bmap_btree.h"
+#include "scrub/scrub.h"
+#include "scrub/common.h"
+#include "scrub/trace.h"
+#include "scrub/repair.h"
+#include "scrub/xfile.h"
+#include "scrub/rtbitmap.h"
+
+/* Set up to repair the realtime bitmap file metadata. */
+int
+xrep_setup_rtbitmap(
+ struct xfs_scrub *sc,
+ struct xchk_rtbitmap *rtb)
+{
+ struct xfs_mount *mp = sc->mp;
+ unsigned long long blocks = 0;
+
+ /*
+ * Reserve enough blocks to write out a completely new bmbt for a
+ * maximally fragmented bitmap file. We do not hold the rtbitmap
+ * ILOCK yet, so this is entirely speculative.
+ */
+ blocks = xfs_bmbt_calc_size(mp, mp->m_sb.sb_rbmblocks);
+ if (blocks > UINT_MAX)
+ return -EOPNOTSUPP;
+
+ rtb->resblks += blocks;
+ return 0;
+}
+
+/*
+ * Make sure that the given range of the data fork of the realtime file is
+ * mapped to written blocks. The caller must ensure that the inode is joined
+ * to the transaction.
+ */
+STATIC int
+xrep_rtbitmap_data_mappings(
+ struct xfs_scrub *sc,
+ xfs_filblks_t len)
+{
+ struct xfs_bmbt_irec map;
+ xfs_fileoff_t off = 0;
+ int error;
+
+ ASSERT(sc->ip != NULL);
+
+ while (off < len) {
+ int nmaps = 1;
+
+ /*
+ * If we have a real extent mapping this block then we're
+ * in ok shape.
+ */
+ error = xfs_bmapi_read(sc->ip, off, len - off, &map, &nmaps,
+ XFS_DATA_FORK);
+ if (error)
+ return error;
+ if (nmaps == 0) {
+ ASSERT(nmaps != 0);
+ return -EFSCORRUPTED;
+ }
+
+ /*
+ * Written extents are ok. Holes are not filled because we
+ * do not know the freespace information.
+ */
+ if (xfs_bmap_is_written_extent(&map) ||
+ map.br_startblock == HOLESTARTBLOCK) {
+ off = map.br_startoff + map.br_blockcount;
+ continue;
+ }
+
+ /*
+ * If we find a delalloc reservation then something is very
+ * very wrong. Bail out.
+ */
+ if (map.br_startblock == DELAYSTARTBLOCK)
+ return -EFSCORRUPTED;
+
+ /* Make sure we're really converting an unwritten extent. */
+ if (map.br_state != XFS_EXT_UNWRITTEN) {
+ ASSERT(map.br_state == XFS_EXT_UNWRITTEN);
+ return -EFSCORRUPTED;
+ }
+
+ /* Make sure this block has a real zeroed extent mapped. */
+ nmaps = 1;
+ error = xfs_bmapi_write(sc->tp, sc->ip, map.br_startoff,
+ map.br_blockcount,
+ XFS_BMAPI_CONVERT | XFS_BMAPI_ZERO,
+ 0, &map, &nmaps);
+ if (error)
+ return error;
+ if (nmaps != 1)
+ return -EFSCORRUPTED;
+
+ /* Commit new extent and all deferred work. */
+ error = xrep_defer_finish(sc);
+ if (error)
+ return error;
+
+ off = map.br_startoff + map.br_blockcount;
+ }
+
+ return 0;
+}
+
+/* Fix broken rt volume geometry. */
+STATIC int
+xrep_rtbitmap_geometry(
+ struct xfs_scrub *sc,
+ struct xchk_rtbitmap *rtb)
+{
+ struct xfs_mount *mp = sc->mp;
+ struct xfs_trans *tp = sc->tp;
+
+ /* Superblock fields */
+ if (mp->m_sb.sb_rextents != rtb->rextents)
+ xfs_trans_mod_sb(sc->tp, XFS_TRANS_SB_REXTENTS,
+ rtb->rextents - mp->m_sb.sb_rextents);
+
+ if (mp->m_sb.sb_rbmblocks != rtb->rbmblocks)
+ xfs_trans_mod_sb(tp, XFS_TRANS_SB_RBMBLOCKS,
+ rtb->rbmblocks - mp->m_sb.sb_rbmblocks);
+
+ if (mp->m_sb.sb_rextslog != rtb->rextslog)
+ xfs_trans_mod_sb(tp, XFS_TRANS_SB_REXTSLOG,
+ rtb->rextslog - mp->m_sb.sb_rextslog);
+
+ /* Fix broken isize */
+ sc->ip->i_disk_size = roundup_64(sc->ip->i_disk_size,
+ mp->m_sb.sb_blocksize);
+
+ if (sc->ip->i_disk_size < XFS_FSB_TO_B(mp, rtb->rbmblocks))
+ sc->ip->i_disk_size = XFS_FSB_TO_B(mp, rtb->rbmblocks);
+
+ xfs_trans_log_inode(sc->tp, sc->ip, XFS_ILOG_CORE);
+ return xrep_roll_trans(sc);
+}
+
+/* Repair the realtime bitmap file metadata. */
+int
+xrep_rtbitmap(
+ struct xfs_scrub *sc)
+{
+ struct xchk_rtbitmap *rtb = sc->buf;
+ struct xfs_mount *mp = sc->mp;
+ unsigned long long blocks = 0;
+ int error;
+
+ /* Impossibly large rtbitmap means we can't touch the filesystem. */
+ if (rtb->rbmblocks > U32_MAX)
+ return 0;
+
+ /*
+ * If the size of the rt bitmap file is larger than what we reserved,
+ * figure out if we need to adjust the block reservation in the
+ * transaction.
+ */
+ blocks = xfs_bmbt_calc_size(mp, rtb->rbmblocks);
+ if (blocks > UINT_MAX)
+ return -EOPNOTSUPP;
+ if (blocks > rtb->resblks) {
+ error = xfs_trans_reserve_more(sc->tp, blocks, 0);
+ if (error)
+ return error;
+
+ rtb->resblks += blocks;
+ }
+
+ /* Fix inode core and forks. */
+ error = xrep_metadata_inode_forks(sc);
+ if (error)
+ return error;
+
+ xfs_trans_ijoin(sc->tp, sc->ip, 0);
+
+ /* Ensure no unwritten extents. */
+ error = xrep_rtbitmap_data_mappings(sc, rtb->rbmblocks);
+ if (error)
+ return error;
+
+ /* Fix inconsistent bitmap geometry */
+ return xrep_rtbitmap_geometry(sc, rtb);
+}
diff --git a/fs/xfs/scrub/rtsummary.c b/fs/xfs/scrub/rtsummary.c
index 8b15c47408d0..fabd0ed9dfa6 100644
--- a/fs/xfs/scrub/rtsummary.c
+++ b/fs/xfs/scrub/rtsummary.c
@@ -31,6 +31,18 @@
* (potentially large) amount of data in pageable memory.
*/
+struct xchk_rtsummary {
+ struct xfs_rtalloc_args args;
+
+ uint64_t rextents;
+ uint64_t rbmblocks;
+ uint64_t rsumsize;
+ unsigned int rsumlevels;
+
+ /* Memory buffer for the summary comparison. */
+ union xfs_suminfo_raw words[];
+};
+
/* Set us up to check the rtsummary file. */
int
xchk_setup_rtsummary(
@@ -38,8 +50,15 @@ xchk_setup_rtsummary(
{
struct xfs_mount *mp = sc->mp;
char *descr;
+ struct xchk_rtsummary *rts;
int error;
+ rts = kvzalloc(struct_size(rts, words, mp->m_blockwsize),
+ XCHK_GFP_FLAGS);
+ if (!rts)
+ return -ENOMEM;
+ sc->buf = rts;
+
/*
* Create an xfile to construct a new rtsummary file. The xfile allows
* us to avoid pinning kernel memory for this purpose.
@@ -54,15 +73,14 @@ xchk_setup_rtsummary(
if (error)
return error;
- /* Allocate a memory buffer for the summary comparison. */
- sc->buf = kvmalloc(mp->m_sb.sb_blocksize, XCHK_GFP_FLAGS);
- if (!sc->buf)
- return -ENOMEM;
-
error = xchk_install_live_inode(sc, mp->m_rsumip);
if (error)
return error;
+ error = xchk_ino_dqattach(sc);
+ if (error)
+ return error;
+
/*
* Locking order requires us to take the rtbitmap first. We must be
* careful to unlock it ourselves when we are done with the rtbitmap
@@ -71,13 +89,29 @@ xchk_setup_rtsummary(
*/
xfs_ilock(mp->m_rbmip, XFS_ILOCK_SHARED | XFS_ILOCK_RTBITMAP);
xchk_ilock(sc, XFS_ILOCK_EXCL | XFS_ILOCK_RTSUM);
+
+ /*
+ * Now that we've locked the rtbitmap and rtsummary, we can't race with
+ * growfsrt trying to expand the summary or change the size of the rt
+ * volume. Hence it is safe to compute and check the geometry values.
+ */
+ if (mp->m_sb.sb_rblocks) {
+ xfs_filblks_t rsumblocks;
+ int rextslog;
+
+ rts->rextents = xfs_rtb_to_rtx(mp, mp->m_sb.sb_rblocks);
+ rextslog = xfs_compute_rextslog(rts->rextents);
+ rts->rsumlevels = rextslog + 1;
+ rts->rbmblocks = xfs_rtbitmap_blockcount(mp, rts->rextents);
+ rsumblocks = xfs_rtsummary_blockcount(mp, rts->rsumlevels,
+ rts->rbmblocks);
+ rts->rsumsize = XFS_FSB_TO_B(mp, rsumblocks);
+ }
return 0;
}
/* Helper functions to record suminfo words in an xfile. */
-typedef unsigned int xchk_rtsumoff_t;
-
static inline int
xfsum_load(
struct xfs_scrub *sc,
@@ -143,7 +177,7 @@ xchk_rtsum_record_free(
/* Compute the relevant location in the rtsum file. */
rbmoff = xfs_rtx_to_rbmblock(mp, rec->ar_startext);
- lenlog = XFS_RTBLOCKLOG(rec->ar_extcount);
+ lenlog = xfs_highbit64(rec->ar_extcount);
offs = xfs_rtsumoffs(mp, lenlog, rbmoff);
rtbno = xfs_rtx_to_rtb(mp, rec->ar_startext);
@@ -188,19 +222,29 @@ STATIC int
xchk_rtsum_compare(
struct xfs_scrub *sc)
{
- struct xfs_rtalloc_args args = {
- .mp = sc->mp,
- .tp = sc->tp,
- };
- struct xfs_mount *mp = sc->mp;
struct xfs_bmbt_irec map;
- xfs_fileoff_t off;
- xchk_rtsumoff_t sumoff = 0;
- int nmap;
+ struct xfs_iext_cursor icur;
+
+ struct xfs_mount *mp = sc->mp;
+ struct xfs_inode *ip = sc->ip;
+ struct xchk_rtsummary *rts = sc->buf;
+ xfs_fileoff_t off = 0;
+ xfs_fileoff_t endoff;
+ xfs_rtsumoff_t sumoff = 0;
+ int error = 0;
+
+ rts->args.mp = sc->mp;
+ rts->args.tp = sc->tp;
+
+ /* Mappings may not cross or lie beyond EOF. */
+ endoff = XFS_B_TO_FSB(mp, ip->i_disk_size);
+ if (xfs_iext_lookup_extent(ip, &ip->i_df, endoff, &icur, &map)) {
+ xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, endoff);
+ return 0;
+ }
- for (off = 0; off < XFS_B_TO_FSB(mp, mp->m_rsumsize); off++) {
- union xfs_suminfo_raw *ondisk_info;
- int error = 0;
+ while (off < endoff) {
+ int nmap = 1;
if (xchk_should_terminate(sc, &error))
return error;
@@ -208,8 +252,7 @@ xchk_rtsum_compare(
return 0;
/* Make sure we have a written extent. */
- nmap = 1;
- error = xfs_bmapi_read(mp->m_rsumip, off, 1, &map, &nmap,
+ error = xfs_bmapi_read(ip, off, endoff - off, &map, &nmap,
XFS_DATA_FORK);
if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, off, &error))
return error;
@@ -219,24 +262,33 @@ xchk_rtsum_compare(
return 0;
}
+ off += map.br_blockcount;
+ }
+
+ for (off = 0; off < endoff; off++) {
+ union xfs_suminfo_raw *ondisk_info;
+
/* Read a block's worth of ondisk rtsummary file. */
- error = xfs_rtsummary_read_buf(&args, off);
+ error = xfs_rtsummary_read_buf(&rts->args, off);
if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, off, &error))
return error;
/* Read a block's worth of computed rtsummary file. */
- error = xfsum_copyout(sc, sumoff, sc->buf, mp->m_blockwsize);
+ error = xfsum_copyout(sc, sumoff, rts->words, mp->m_blockwsize);
if (error) {
- xfs_rtbuf_cache_relse(&args);
+ xfs_rtbuf_cache_relse(&rts->args);
return error;
}
- ondisk_info = xfs_rsumblock_infoptr(&args, 0);
- if (memcmp(ondisk_info, sc->buf,
- mp->m_blockwsize << XFS_WORDLOG) != 0)
+ ondisk_info = xfs_rsumblock_infoptr(&rts->args, 0);
+ if (memcmp(ondisk_info, rts->words,
+ mp->m_blockwsize << XFS_WORDLOG) != 0) {
xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, off);
+ xfs_rtbuf_cache_relse(&rts->args);
+ return error;
+ }
- xfs_rtbuf_cache_relse(&args);
+ xfs_rtbuf_cache_relse(&rts->args);
sumoff += mp->m_blockwsize;
}
@@ -249,8 +301,43 @@ xchk_rtsummary(
struct xfs_scrub *sc)
{
struct xfs_mount *mp = sc->mp;
+ struct xchk_rtsummary *rts = sc->buf;
int error = 0;
+ /* Is sb_rextents correct? */
+ if (mp->m_sb.sb_rextents != rts->rextents) {
+ xchk_ino_set_corrupt(sc, mp->m_rbmip->i_ino);
+ goto out_rbm;
+ }
+
+ /* Is m_rsumlevels correct? */
+ if (mp->m_rsumlevels != rts->rsumlevels) {
+ xchk_ino_set_corrupt(sc, mp->m_rsumip->i_ino);
+ goto out_rbm;
+ }
+
+ /* Is m_rsumsize correct? */
+ if (mp->m_rsumsize != rts->rsumsize) {
+ xchk_ino_set_corrupt(sc, mp->m_rsumip->i_ino);
+ goto out_rbm;
+ }
+
+ /* The summary file length must be aligned to an fsblock. */
+ if (mp->m_rsumip->i_disk_size & mp->m_blockmask) {
+ xchk_ino_set_corrupt(sc, mp->m_rsumip->i_ino);
+ goto out_rbm;
+ }
+
+ /*
+ * Is the summary file itself large enough to handle the rt volume?
+ * growfsrt expands the summary file before updating sb_rextents, so
+ * the file can be larger than rsumsize.
+ */
+ if (mp->m_rsumip->i_disk_size < rts->rsumsize) {
+ xchk_ino_set_corrupt(sc, mp->m_rsumip->i_ino);
+ goto out_rbm;
+ }
+
/* Invoke the fork scrubber. */
error = xchk_metadata_inode_forks(sc);
if (error || (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT))
diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c
index 4849efcaa33a..caf324c2b991 100644
--- a/fs/xfs/scrub/scrub.c
+++ b/fs/xfs/scrub/scrub.c
@@ -14,8 +14,6 @@
#include "xfs_inode.h"
#include "xfs_quota.h"
#include "xfs_qm.h"
-#include "xfs_errortag.h"
-#include "xfs_error.h"
#include "xfs_scrub.h"
#include "scrub/scrub.h"
#include "scrub/common.h"
@@ -238,27 +236,31 @@ static const struct xchk_meta_ops meta_scrub_ops[] = {
[XFS_SCRUB_TYPE_BNOBT] = { /* bnobt */
.type = ST_PERAG,
.setup = xchk_setup_ag_allocbt,
- .scrub = xchk_bnobt,
- .repair = xrep_notsupported,
+ .scrub = xchk_allocbt,
+ .repair = xrep_allocbt,
+ .repair_eval = xrep_revalidate_allocbt,
},
[XFS_SCRUB_TYPE_CNTBT] = { /* cntbt */
.type = ST_PERAG,
.setup = xchk_setup_ag_allocbt,
- .scrub = xchk_cntbt,
- .repair = xrep_notsupported,
+ .scrub = xchk_allocbt,
+ .repair = xrep_allocbt,
+ .repair_eval = xrep_revalidate_allocbt,
},
[XFS_SCRUB_TYPE_INOBT] = { /* inobt */
.type = ST_PERAG,
.setup = xchk_setup_ag_iallocbt,
- .scrub = xchk_inobt,
- .repair = xrep_notsupported,
+ .scrub = xchk_iallocbt,
+ .repair = xrep_iallocbt,
+ .repair_eval = xrep_revalidate_iallocbt,
},
[XFS_SCRUB_TYPE_FINOBT] = { /* finobt */
.type = ST_PERAG,
.setup = xchk_setup_ag_iallocbt,
- .scrub = xchk_finobt,
+ .scrub = xchk_iallocbt,
.has = xfs_has_finobt,
- .repair = xrep_notsupported,
+ .repair = xrep_iallocbt,
+ .repair_eval = xrep_revalidate_iallocbt,
},
[XFS_SCRUB_TYPE_RMAPBT] = { /* rmapbt */
.type = ST_PERAG,
@@ -272,31 +274,31 @@ static const struct xchk_meta_ops meta_scrub_ops[] = {
.setup = xchk_setup_ag_refcountbt,
.scrub = xchk_refcountbt,
.has = xfs_has_reflink,
- .repair = xrep_notsupported,
+ .repair = xrep_refcountbt,
},
[XFS_SCRUB_TYPE_INODE] = { /* inode record */
.type = ST_INODE,
.setup = xchk_setup_inode,
.scrub = xchk_inode,
- .repair = xrep_notsupported,
+ .repair = xrep_inode,
},
[XFS_SCRUB_TYPE_BMBTD] = { /* inode data fork */
.type = ST_INODE,
.setup = xchk_setup_inode_bmap,
.scrub = xchk_bmap_data,
- .repair = xrep_notsupported,
+ .repair = xrep_bmap_data,
},
[XFS_SCRUB_TYPE_BMBTA] = { /* inode attr fork */
.type = ST_INODE,
.setup = xchk_setup_inode_bmap,
.scrub = xchk_bmap_attr,
- .repair = xrep_notsupported,
+ .repair = xrep_bmap_attr,
},
[XFS_SCRUB_TYPE_BMBTC] = { /* inode CoW fork */
.type = ST_INODE,
.setup = xchk_setup_inode_bmap,
.scrub = xchk_bmap_cow,
- .repair = xrep_notsupported,
+ .repair = xrep_bmap_cow,
},
[XFS_SCRUB_TYPE_DIR] = { /* directory */
.type = ST_INODE,
@@ -326,33 +328,31 @@ static const struct xchk_meta_ops meta_scrub_ops[] = {
.type = ST_FS,
.setup = xchk_setup_rtbitmap,
.scrub = xchk_rtbitmap,
- .has = xfs_has_realtime,
- .repair = xrep_notsupported,
+ .repair = xrep_rtbitmap,
},
[XFS_SCRUB_TYPE_RTSUM] = { /* realtime summary */
.type = ST_FS,
.setup = xchk_setup_rtsummary,
.scrub = xchk_rtsummary,
- .has = xfs_has_realtime,
.repair = xrep_notsupported,
},
[XFS_SCRUB_TYPE_UQUOTA] = { /* user quota */
.type = ST_FS,
.setup = xchk_setup_quota,
.scrub = xchk_quota,
- .repair = xrep_notsupported,
+ .repair = xrep_quota,
},
[XFS_SCRUB_TYPE_GQUOTA] = { /* group quota */
.type = ST_FS,
.setup = xchk_setup_quota,
.scrub = xchk_quota,
- .repair = xrep_notsupported,
+ .repair = xrep_quota,
},
[XFS_SCRUB_TYPE_PQUOTA] = { /* project quota */
.type = ST_FS,
.setup = xchk_setup_quota,
.scrub = xchk_quota,
- .repair = xrep_notsupported,
+ .repair = xrep_quota,
},
[XFS_SCRUB_TYPE_FSCOUNTERS] = { /* fs summary counters */
.type = ST_FS,
@@ -531,7 +531,10 @@ retry_op:
/* Scrub for errors. */
check_start = xchk_stats_now();
- error = sc->ops->scrub(sc);
+ if ((sc->flags & XREP_ALREADY_FIXED) && sc->ops->repair_eval != NULL)
+ error = sc->ops->repair_eval(sc);
+ else
+ error = sc->ops->scrub(sc);
run.scrub_ns += xchk_stats_elapsed_ns(check_start);
if (error == -EDEADLOCK && !(sc->flags & XCHK_TRY_HARDER))
goto try_harder;
@@ -542,23 +545,12 @@ retry_op:
xchk_update_health(sc);
- if ((sc->sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR) &&
- !(sc->flags & XREP_ALREADY_FIXED)) {
- bool needs_fix = xchk_needs_repair(sc->sm);
-
- /* Userspace asked us to rebuild the structure regardless. */
- if (sc->sm->sm_flags & XFS_SCRUB_IFLAG_FORCE_REBUILD)
- needs_fix = true;
-
- /* Let debug users force us into the repair routines. */
- if (XFS_TEST_ERROR(needs_fix, mp, XFS_ERRTAG_FORCE_SCRUB_REPAIR))
- needs_fix = true;
-
+ if (xchk_could_repair(sc)) {
/*
* If userspace asked for a repair but it wasn't necessary,
* report that back to userspace.
*/
- if (!needs_fix) {
+ if (!xrep_will_attempt(sc)) {
sc->sm->sm_flags |= XFS_SCRUB_OFLAG_NO_REPAIR_NEEDED;
goto out_nofix;
}
diff --git a/fs/xfs/scrub/scrub.h b/fs/xfs/scrub/scrub.h
index 1ef9c6b4842a..7fc50654c4fe 100644
--- a/fs/xfs/scrub/scrub.h
+++ b/fs/xfs/scrub/scrub.h
@@ -35,6 +35,14 @@ struct xchk_meta_ops {
/* Repair or optimize the metadata. */
int (*repair)(struct xfs_scrub *);
+ /*
+ * Re-scrub the metadata we repaired, in case there's extra work that
+ * we need to do to check our repair work. If this is NULL, we'll use
+ * the ->scrub function pointer, assuming that the regular scrub is
+ * sufficient.
+ */
+ int (*repair_eval)(struct xfs_scrub *sc);
+
/* Decide if we even have this piece of metadata. */
bool (*has)(struct xfs_mount *);
@@ -113,6 +121,7 @@ struct xfs_scrub {
#define XCHK_HAVE_FREEZE_PROT (1U << 1) /* do we have freeze protection? */
#define XCHK_FSGATES_DRAIN (1U << 2) /* defer ops draining enabled */
#define XCHK_NEED_DRAIN (1U << 3) /* scrub needs to drain defer ops */
+#define XREP_RESET_PERAG_RESV (1U << 30) /* must reset AG space reservation */
#define XREP_ALREADY_FIXED (1U << 31) /* checking our repair work */
/*
@@ -129,10 +138,8 @@ int xchk_superblock(struct xfs_scrub *sc);
int xchk_agf(struct xfs_scrub *sc);
int xchk_agfl(struct xfs_scrub *sc);
int xchk_agi(struct xfs_scrub *sc);
-int xchk_bnobt(struct xfs_scrub *sc);
-int xchk_cntbt(struct xfs_scrub *sc);
-int xchk_inobt(struct xfs_scrub *sc);
-int xchk_finobt(struct xfs_scrub *sc);
+int xchk_allocbt(struct xfs_scrub *sc);
+int xchk_iallocbt(struct xfs_scrub *sc);
int xchk_rmapbt(struct xfs_scrub *sc);
int xchk_refcountbt(struct xfs_scrub *sc);
int xchk_inode(struct xfs_scrub *sc);
diff --git a/fs/xfs/scrub/symlink.c b/fs/xfs/scrub/symlink.c
index 38708fb9a5d7..ddff86713df3 100644
--- a/fs/xfs/scrub/symlink.c
+++ b/fs/xfs/scrub/symlink.c
@@ -12,8 +12,10 @@
#include "xfs_log_format.h"
#include "xfs_inode.h"
#include "xfs_symlink.h"
+#include "xfs_health.h"
#include "scrub/scrub.h"
#include "scrub/common.h"
+#include "scrub/health.h"
/* Set us up to scrub a symbolic link. */
int
@@ -41,29 +43,37 @@ xchk_symlink(
if (!S_ISLNK(VFS_I(ip)->i_mode))
return -ENOENT;
+
+ if (xchk_file_looks_zapped(sc, XFS_SICK_INO_SYMLINK_ZAPPED)) {
+ xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
+ return 0;
+ }
+
ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK);
len = ip->i_disk_size;
/* Plausible size? */
if (len > XFS_SYMLINK_MAXLEN || len <= 0) {
xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
- goto out;
+ return 0;
}
/* Inline symlink? */
if (ifp->if_format == XFS_DINODE_FMT_LOCAL) {
if (len > xfs_inode_data_fork_size(ip) ||
- len > strnlen(ifp->if_u1.if_data, xfs_inode_data_fork_size(ip)))
+ len > strnlen(ifp->if_data, xfs_inode_data_fork_size(ip)))
xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
- goto out;
+ return 0;
}
/* Remote symlink; must read the contents. */
error = xfs_readlink_bmap_ilocked(sc->ip, sc->buf);
if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, 0, &error))
- goto out;
+ return error;
if (strnlen(sc->buf, XFS_SYMLINK_MAXLEN) < len)
xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
-out:
- return error;
+
+ /* If a remote symlink is clean, it is clearly not zapped. */
+ xchk_mark_healthy_if_clean(sc, XFS_SICK_INO_SYMLINK_ZAPPED);
+ return 0;
}
diff --git a/fs/xfs/scrub/trace.c b/fs/xfs/scrub/trace.c
index 29afa4851235..d0e24ffaf754 100644
--- a/fs/xfs/scrub/trace.c
+++ b/fs/xfs/scrub/trace.c
@@ -14,9 +14,12 @@
#include "xfs_btree.h"
#include "xfs_ag.h"
#include "xfs_rtbitmap.h"
+#include "xfs_quota.h"
+#include "xfs_quota_defs.h"
#include "scrub/scrub.h"
#include "scrub/xfile.h"
#include "scrub/xfarray.h"
+#include "scrub/quota.h"
/* Figure out which block the btree cursor was pointing to. */
static inline xfs_fsblock_t
diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index 4a8bc6f3c8f2..6bbb4e8639dc 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -19,6 +19,7 @@
struct xfile;
struct xfarray;
struct xfarray_sortinfo;
+struct xchk_dqiter;
/*
* ftrace's __print_symbolic requires that all enum values be wrapped in the
@@ -106,6 +107,7 @@ TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_FSCOUNTERS);
{ XCHK_HAVE_FREEZE_PROT, "nofreeze" }, \
{ XCHK_FSGATES_DRAIN, "fsgates_drain" }, \
{ XCHK_NEED_DRAIN, "need_drain" }, \
+ { XREP_RESET_PERAG_RESV, "reset_perag_resv" }, \
{ XREP_ALREADY_FIXED, "already_fixed" }
DECLARE_EVENT_CLASS(xchk_class,
@@ -347,6 +349,54 @@ DEFINE_EVENT(xchk_fblock_error_class, name, \
DEFINE_SCRUB_FBLOCK_ERROR_EVENT(xchk_fblock_error);
DEFINE_SCRUB_FBLOCK_ERROR_EVENT(xchk_fblock_warning);
+#ifdef CONFIG_XFS_QUOTA
+DECLARE_EVENT_CLASS(xchk_dqiter_class,
+ TP_PROTO(struct xchk_dqiter *cursor, uint64_t id),
+ TP_ARGS(cursor, id),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_dqtype_t, dqtype)
+ __field(xfs_ino_t, ino)
+ __field(unsigned long long, cur_id)
+ __field(unsigned long long, id)
+ __field(xfs_fileoff_t, startoff)
+ __field(xfs_fsblock_t, startblock)
+ __field(xfs_filblks_t, blockcount)
+ __field(xfs_exntst_t, state)
+ ),
+ TP_fast_assign(
+ __entry->dev = cursor->sc->ip->i_mount->m_super->s_dev;
+ __entry->dqtype = cursor->dqtype;
+ __entry->ino = cursor->quota_ip->i_ino;
+ __entry->cur_id = cursor->id;
+ __entry->startoff = cursor->bmap.br_startoff;
+ __entry->startblock = cursor->bmap.br_startblock;
+ __entry->blockcount = cursor->bmap.br_blockcount;
+ __entry->state = cursor->bmap.br_state;
+ __entry->id = id;
+ ),
+ TP_printk("dev %d:%d dquot type %s ino 0x%llx cursor_id 0x%llx startoff 0x%llx startblock 0x%llx blockcount 0x%llx state %u id 0x%llx",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __print_symbolic(__entry->dqtype, XFS_DQTYPE_STRINGS),
+ __entry->ino,
+ __entry->cur_id,
+ __entry->startoff,
+ __entry->startblock,
+ __entry->blockcount,
+ __entry->state,
+ __entry->id)
+);
+
+#define DEFINE_SCRUB_DQITER_EVENT(name) \
+DEFINE_EVENT(xchk_dqiter_class, name, \
+ TP_PROTO(struct xchk_dqiter *cursor, uint64_t id), \
+ TP_ARGS(cursor, id))
+DEFINE_SCRUB_DQITER_EVENT(xchk_dquot_iter_revalidate_bmap);
+DEFINE_SCRUB_DQITER_EVENT(xchk_dquot_iter_advance_bmap);
+DEFINE_SCRUB_DQITER_EVENT(xchk_dquot_iter_advance_incore);
+DEFINE_SCRUB_DQITER_EVENT(xchk_dquot_iter);
+#endif /* CONFIG_XFS_QUOTA */
+
TRACE_EVENT(xchk_incomplete,
TP_PROTO(struct xfs_scrub *sc, void *ret_ip),
TP_ARGS(sc, ret_ip),
@@ -1172,37 +1222,125 @@ DEFINE_EVENT(xrep_rmap_class, name, \
xfs_agblock_t agbno, xfs_extlen_t len, \
uint64_t owner, uint64_t offset, unsigned int flags), \
TP_ARGS(mp, agno, agbno, len, owner, offset, flags))
-DEFINE_REPAIR_RMAP_EVENT(xrep_alloc_extent_fn);
-DEFINE_REPAIR_RMAP_EVENT(xrep_ialloc_extent_fn);
+DEFINE_REPAIR_RMAP_EVENT(xrep_ibt_walk_rmap);
DEFINE_REPAIR_RMAP_EVENT(xrep_rmap_extent_fn);
-DEFINE_REPAIR_RMAP_EVENT(xrep_bmap_extent_fn);
+DEFINE_REPAIR_RMAP_EVENT(xrep_bmap_walk_rmap);
-TRACE_EVENT(xrep_refcount_extent_fn,
+TRACE_EVENT(xrep_abt_found,
TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
- struct xfs_refcount_irec *irec),
- TP_ARGS(mp, agno, irec),
+ const struct xfs_alloc_rec_incore *rec),
+ TP_ARGS(mp, agno, rec),
TP_STRUCT__entry(
__field(dev_t, dev)
__field(xfs_agnumber_t, agno)
__field(xfs_agblock_t, startblock)
__field(xfs_extlen_t, blockcount)
- __field(xfs_nlink_t, refcount)
),
TP_fast_assign(
__entry->dev = mp->m_super->s_dev;
__entry->agno = agno;
- __entry->startblock = irec->rc_startblock;
- __entry->blockcount = irec->rc_blockcount;
- __entry->refcount = irec->rc_refcount;
+ __entry->startblock = rec->ar_startblock;
+ __entry->blockcount = rec->ar_blockcount;
+ ),
+ TP_printk("dev %d:%d agno 0x%x agbno 0x%x fsbcount 0x%x",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->agno,
+ __entry->startblock,
+ __entry->blockcount)
+)
+
+TRACE_EVENT(xrep_ibt_found,
+ TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
+ const struct xfs_inobt_rec_incore *rec),
+ TP_ARGS(mp, agno, rec),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_agnumber_t, agno)
+ __field(xfs_agino_t, startino)
+ __field(uint16_t, holemask)
+ __field(uint8_t, count)
+ __field(uint8_t, freecount)
+ __field(uint64_t, freemask)
+ ),
+ TP_fast_assign(
+ __entry->dev = mp->m_super->s_dev;
+ __entry->agno = agno;
+ __entry->startino = rec->ir_startino;
+ __entry->holemask = rec->ir_holemask;
+ __entry->count = rec->ir_count;
+ __entry->freecount = rec->ir_freecount;
+ __entry->freemask = rec->ir_free;
+ ),
+ TP_printk("dev %d:%d agno 0x%x agino 0x%x holemask 0x%x count 0x%x freecount 0x%x freemask 0x%llx",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->agno,
+ __entry->startino,
+ __entry->holemask,
+ __entry->count,
+ __entry->freecount,
+ __entry->freemask)
+)
+
+TRACE_EVENT(xrep_refc_found,
+ TP_PROTO(struct xfs_perag *pag, const struct xfs_refcount_irec *rec),
+ TP_ARGS(pag, rec),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_agnumber_t, agno)
+ __field(enum xfs_refc_domain, domain)
+ __field(xfs_agblock_t, startblock)
+ __field(xfs_extlen_t, blockcount)
+ __field(xfs_nlink_t, refcount)
+ ),
+ TP_fast_assign(
+ __entry->dev = pag->pag_mount->m_super->s_dev;
+ __entry->agno = pag->pag_agno;
+ __entry->domain = rec->rc_domain;
+ __entry->startblock = rec->rc_startblock;
+ __entry->blockcount = rec->rc_blockcount;
+ __entry->refcount = rec->rc_refcount;
),
- TP_printk("dev %d:%d agno 0x%x agbno 0x%x fsbcount 0x%x refcount %u",
+ TP_printk("dev %d:%d agno 0x%x dom %s agbno 0x%x fsbcount 0x%x refcount %u",
MAJOR(__entry->dev), MINOR(__entry->dev),
__entry->agno,
+ __print_symbolic(__entry->domain, XFS_REFC_DOMAIN_STRINGS),
__entry->startblock,
__entry->blockcount,
__entry->refcount)
)
+TRACE_EVENT(xrep_bmap_found,
+ TP_PROTO(struct xfs_inode *ip, int whichfork,
+ struct xfs_bmbt_irec *irec),
+ TP_ARGS(ip, whichfork, irec),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_ino_t, ino)
+ __field(int, whichfork)
+ __field(xfs_fileoff_t, lblk)
+ __field(xfs_filblks_t, len)
+ __field(xfs_fsblock_t, pblk)
+ __field(int, state)
+ ),
+ TP_fast_assign(
+ __entry->dev = VFS_I(ip)->i_sb->s_dev;
+ __entry->ino = ip->i_ino;
+ __entry->whichfork = whichfork;
+ __entry->lblk = irec->br_startoff;
+ __entry->len = irec->br_blockcount;
+ __entry->pblk = irec->br_startblock;
+ __entry->state = irec->br_state;
+ ),
+ TP_printk("dev %d:%d ino 0x%llx whichfork %s fileoff 0x%llx fsbcount 0x%llx startblock 0x%llx state %d",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->ino,
+ __print_symbolic(__entry->whichfork, XFS_WHICHFORK_STRINGS),
+ __entry->lblk,
+ __entry->len,
+ __entry->pblk,
+ __entry->state)
+);
+
TRACE_EVENT(xrep_findroot_block,
TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, xfs_agblock_t agbno,
uint32_t magic, uint16_t level),
@@ -1299,39 +1437,327 @@ TRACE_EVENT(xrep_reset_counters,
MAJOR(__entry->dev), MINOR(__entry->dev))
)
-TRACE_EVENT(xrep_ialloc_insert,
+DECLARE_EVENT_CLASS(xrep_newbt_extent_class,
TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
- xfs_agino_t startino, uint16_t holemask, uint8_t count,
- uint8_t freecount, uint64_t freemask),
- TP_ARGS(mp, agno, startino, holemask, count, freecount, freemask),
+ xfs_agblock_t agbno, xfs_extlen_t len,
+ int64_t owner),
+ TP_ARGS(mp, agno, agbno, len, owner),
TP_STRUCT__entry(
__field(dev_t, dev)
__field(xfs_agnumber_t, agno)
- __field(xfs_agino_t, startino)
- __field(uint16_t, holemask)
- __field(uint8_t, count)
- __field(uint8_t, freecount)
- __field(uint64_t, freemask)
+ __field(xfs_agblock_t, agbno)
+ __field(xfs_extlen_t, len)
+ __field(int64_t, owner)
),
TP_fast_assign(
__entry->dev = mp->m_super->s_dev;
__entry->agno = agno;
- __entry->startino = startino;
- __entry->holemask = holemask;
- __entry->count = count;
- __entry->freecount = freecount;
- __entry->freemask = freemask;
+ __entry->agbno = agbno;
+ __entry->len = len;
+ __entry->owner = owner;
),
- TP_printk("dev %d:%d agno 0x%x startino 0x%x holemask 0x%x count %u freecount %u freemask 0x%llx",
+ TP_printk("dev %d:%d agno 0x%x agbno 0x%x fsbcount 0x%x owner 0x%llx",
MAJOR(__entry->dev), MINOR(__entry->dev),
__entry->agno,
- __entry->startino,
- __entry->holemask,
- __entry->count,
- __entry->freecount,
- __entry->freemask)
+ __entry->agbno,
+ __entry->len,
+ __entry->owner)
+);
+#define DEFINE_NEWBT_EXTENT_EVENT(name) \
+DEFINE_EVENT(xrep_newbt_extent_class, name, \
+ TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, \
+ xfs_agblock_t agbno, xfs_extlen_t len, \
+ int64_t owner), \
+ TP_ARGS(mp, agno, agbno, len, owner))
+DEFINE_NEWBT_EXTENT_EVENT(xrep_newbt_alloc_ag_blocks);
+DEFINE_NEWBT_EXTENT_EVENT(xrep_newbt_alloc_file_blocks);
+DEFINE_NEWBT_EXTENT_EVENT(xrep_newbt_free_blocks);
+DEFINE_NEWBT_EXTENT_EVENT(xrep_newbt_claim_block);
+
+DECLARE_EVENT_CLASS(xrep_dinode_class,
+ TP_PROTO(struct xfs_scrub *sc, struct xfs_dinode *dip),
+ TP_ARGS(sc, dip),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_ino_t, ino)
+ __field(uint16_t, mode)
+ __field(uint8_t, version)
+ __field(uint8_t, format)
+ __field(uint32_t, uid)
+ __field(uint32_t, gid)
+ __field(uint64_t, size)
+ __field(uint64_t, nblocks)
+ __field(uint32_t, extsize)
+ __field(uint32_t, nextents)
+ __field(uint16_t, anextents)
+ __field(uint8_t, forkoff)
+ __field(uint8_t, aformat)
+ __field(uint16_t, flags)
+ __field(uint32_t, gen)
+ __field(uint64_t, flags2)
+ __field(uint32_t, cowextsize)
+ ),
+ TP_fast_assign(
+ __entry->dev = sc->mp->m_super->s_dev;
+ __entry->ino = sc->sm->sm_ino;
+ __entry->mode = be16_to_cpu(dip->di_mode);
+ __entry->version = dip->di_version;
+ __entry->format = dip->di_format;
+ __entry->uid = be32_to_cpu(dip->di_uid);
+ __entry->gid = be32_to_cpu(dip->di_gid);
+ __entry->size = be64_to_cpu(dip->di_size);
+ __entry->nblocks = be64_to_cpu(dip->di_nblocks);
+ __entry->extsize = be32_to_cpu(dip->di_extsize);
+ __entry->nextents = be32_to_cpu(dip->di_nextents);
+ __entry->anextents = be16_to_cpu(dip->di_anextents);
+ __entry->forkoff = dip->di_forkoff;
+ __entry->aformat = dip->di_aformat;
+ __entry->flags = be16_to_cpu(dip->di_flags);
+ __entry->gen = be32_to_cpu(dip->di_gen);
+ __entry->flags2 = be64_to_cpu(dip->di_flags2);
+ __entry->cowextsize = be32_to_cpu(dip->di_cowextsize);
+ ),
+ TP_printk("dev %d:%d ino 0x%llx mode 0x%x version %u format %u uid %u gid %u disize 0x%llx nblocks 0x%llx extsize %u nextents %u anextents %u forkoff 0x%x aformat %u flags 0x%x gen 0x%x flags2 0x%llx cowextsize %u",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->ino,
+ __entry->mode,
+ __entry->version,
+ __entry->format,
+ __entry->uid,
+ __entry->gid,
+ __entry->size,
+ __entry->nblocks,
+ __entry->extsize,
+ __entry->nextents,
+ __entry->anextents,
+ __entry->forkoff,
+ __entry->aformat,
+ __entry->flags,
+ __entry->gen,
+ __entry->flags2,
+ __entry->cowextsize)
)
+#define DEFINE_REPAIR_DINODE_EVENT(name) \
+DEFINE_EVENT(xrep_dinode_class, name, \
+ TP_PROTO(struct xfs_scrub *sc, struct xfs_dinode *dip), \
+ TP_ARGS(sc, dip))
+DEFINE_REPAIR_DINODE_EVENT(xrep_dinode_header);
+DEFINE_REPAIR_DINODE_EVENT(xrep_dinode_mode);
+DEFINE_REPAIR_DINODE_EVENT(xrep_dinode_flags);
+DEFINE_REPAIR_DINODE_EVENT(xrep_dinode_size);
+DEFINE_REPAIR_DINODE_EVENT(xrep_dinode_extsize_hints);
+DEFINE_REPAIR_DINODE_EVENT(xrep_dinode_zap_symlink);
+DEFINE_REPAIR_DINODE_EVENT(xrep_dinode_zap_dir);
+DEFINE_REPAIR_DINODE_EVENT(xrep_dinode_fixed);
+DEFINE_REPAIR_DINODE_EVENT(xrep_dinode_zap_forks);
+DEFINE_REPAIR_DINODE_EVENT(xrep_dinode_zap_dfork);
+DEFINE_REPAIR_DINODE_EVENT(xrep_dinode_zap_afork);
+DEFINE_REPAIR_DINODE_EVENT(xrep_dinode_ensure_forkoff);
+
+DECLARE_EVENT_CLASS(xrep_inode_class,
+ TP_PROTO(struct xfs_scrub *sc),
+ TP_ARGS(sc),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_ino_t, ino)
+ __field(xfs_fsize_t, size)
+ __field(xfs_rfsblock_t, nblocks)
+ __field(uint16_t, flags)
+ __field(uint64_t, flags2)
+ __field(uint32_t, nextents)
+ __field(uint8_t, format)
+ __field(uint32_t, anextents)
+ __field(uint8_t, aformat)
+ ),
+ TP_fast_assign(
+ __entry->dev = sc->mp->m_super->s_dev;
+ __entry->ino = sc->sm->sm_ino;
+ __entry->size = sc->ip->i_disk_size;
+ __entry->nblocks = sc->ip->i_nblocks;
+ __entry->flags = sc->ip->i_diflags;
+ __entry->flags2 = sc->ip->i_diflags2;
+ __entry->nextents = sc->ip->i_df.if_nextents;
+ __entry->format = sc->ip->i_df.if_format;
+ __entry->anextents = sc->ip->i_af.if_nextents;
+ __entry->aformat = sc->ip->i_af.if_format;
+ ),
+ TP_printk("dev %d:%d ino 0x%llx disize 0x%llx nblocks 0x%llx flags 0x%x flags2 0x%llx nextents %u format %u anextents %u aformat %u",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->ino,
+ __entry->size,
+ __entry->nblocks,
+ __entry->flags,
+ __entry->flags2,
+ __entry->nextents,
+ __entry->format,
+ __entry->anextents,
+ __entry->aformat)
+)
+
+#define DEFINE_REPAIR_INODE_EVENT(name) \
+DEFINE_EVENT(xrep_inode_class, name, \
+ TP_PROTO(struct xfs_scrub *sc), \
+ TP_ARGS(sc))
+DEFINE_REPAIR_INODE_EVENT(xrep_inode_blockcounts);
+DEFINE_REPAIR_INODE_EVENT(xrep_inode_ids);
+DEFINE_REPAIR_INODE_EVENT(xrep_inode_flags);
+DEFINE_REPAIR_INODE_EVENT(xrep_inode_blockdir_size);
+DEFINE_REPAIR_INODE_EVENT(xrep_inode_sfdir_size);
+DEFINE_REPAIR_INODE_EVENT(xrep_inode_dir_size);
+DEFINE_REPAIR_INODE_EVENT(xrep_inode_fixed);
+
+TRACE_EVENT(xrep_dinode_count_rmaps,
+ TP_PROTO(struct xfs_scrub *sc, xfs_rfsblock_t data_blocks,
+ xfs_rfsblock_t rt_blocks, xfs_rfsblock_t attr_blocks,
+ xfs_extnum_t data_extents, xfs_extnum_t rt_extents,
+ xfs_aextnum_t attr_extents),
+ TP_ARGS(sc, data_blocks, rt_blocks, attr_blocks, data_extents,
+ rt_extents, attr_extents),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_ino_t, ino)
+ __field(xfs_rfsblock_t, data_blocks)
+ __field(xfs_rfsblock_t, rt_blocks)
+ __field(xfs_rfsblock_t, attr_blocks)
+ __field(xfs_extnum_t, data_extents)
+ __field(xfs_extnum_t, rt_extents)
+ __field(xfs_aextnum_t, attr_extents)
+ ),
+ TP_fast_assign(
+ __entry->dev = sc->mp->m_super->s_dev;
+ __entry->ino = sc->sm->sm_ino;
+ __entry->data_blocks = data_blocks;
+ __entry->rt_blocks = rt_blocks;
+ __entry->attr_blocks = attr_blocks;
+ __entry->data_extents = data_extents;
+ __entry->rt_extents = rt_extents;
+ __entry->attr_extents = attr_extents;
+ ),
+ TP_printk("dev %d:%d ino 0x%llx dblocks 0x%llx rtblocks 0x%llx ablocks 0x%llx dextents %llu rtextents %llu aextents %u",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->ino,
+ __entry->data_blocks,
+ __entry->rt_blocks,
+ __entry->attr_blocks,
+ __entry->data_extents,
+ __entry->rt_extents,
+ __entry->attr_extents)
+);
+
+TRACE_EVENT(xrep_cow_mark_file_range,
+ TP_PROTO(struct xfs_inode *ip, xfs_fsblock_t startblock,
+ xfs_fileoff_t startoff, xfs_filblks_t blockcount),
+ TP_ARGS(ip, startblock, startoff, blockcount),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_ino_t, ino)
+ __field(xfs_fsblock_t, startblock)
+ __field(xfs_fileoff_t, startoff)
+ __field(xfs_filblks_t, blockcount)
+ ),
+ TP_fast_assign(
+ __entry->dev = ip->i_mount->m_super->s_dev;
+ __entry->ino = ip->i_ino;
+ __entry->startoff = startoff;
+ __entry->startblock = startblock;
+ __entry->blockcount = blockcount;
+ ),
+ TP_printk("dev %d:%d ino 0x%llx fileoff 0x%llx startblock 0x%llx fsbcount 0x%llx",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->ino,
+ __entry->startoff,
+ __entry->startblock,
+ __entry->blockcount)
+);
+
+TRACE_EVENT(xrep_cow_replace_mapping,
+ TP_PROTO(struct xfs_inode *ip, const struct xfs_bmbt_irec *irec,
+ xfs_fsblock_t new_startblock, xfs_extlen_t new_blockcount),
+ TP_ARGS(ip, irec, new_startblock, new_blockcount),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_ino_t, ino)
+ __field(xfs_fsblock_t, startblock)
+ __field(xfs_fileoff_t, startoff)
+ __field(xfs_filblks_t, blockcount)
+ __field(xfs_exntst_t, state)
+ __field(xfs_fsblock_t, new_startblock)
+ __field(xfs_extlen_t, new_blockcount)
+ ),
+ TP_fast_assign(
+ __entry->dev = ip->i_mount->m_super->s_dev;
+ __entry->ino = ip->i_ino;
+ __entry->startoff = irec->br_startoff;
+ __entry->startblock = irec->br_startblock;
+ __entry->blockcount = irec->br_blockcount;
+ __entry->state = irec->br_state;
+ __entry->new_startblock = new_startblock;
+ __entry->new_blockcount = new_blockcount;
+ ),
+ TP_printk("dev %d:%d ino 0x%llx startoff 0x%llx startblock 0x%llx fsbcount 0x%llx state 0x%x new_startblock 0x%llx new_fsbcount 0x%x",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->ino,
+ __entry->startoff,
+ __entry->startblock,
+ __entry->blockcount,
+ __entry->state,
+ __entry->new_startblock,
+ __entry->new_blockcount)
+);
+
+TRACE_EVENT(xrep_cow_free_staging,
+ TP_PROTO(struct xfs_perag *pag, xfs_agblock_t agbno,
+ xfs_extlen_t blockcount),
+ TP_ARGS(pag, agbno, blockcount),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_agnumber_t, agno)
+ __field(xfs_agblock_t, agbno)
+ __field(xfs_extlen_t, blockcount)
+ ),
+ TP_fast_assign(
+ __entry->dev = pag->pag_mount->m_super->s_dev;
+ __entry->agno = pag->pag_agno;
+ __entry->agbno = agbno;
+ __entry->blockcount = blockcount;
+ ),
+ TP_printk("dev %d:%d agno 0x%x agbno 0x%x fsbcount 0x%x",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->agno,
+ __entry->agbno,
+ __entry->blockcount)
+);
+
+#ifdef CONFIG_XFS_QUOTA
+DECLARE_EVENT_CLASS(xrep_dquot_class,
+ TP_PROTO(struct xfs_mount *mp, uint8_t type, uint32_t id),
+ TP_ARGS(mp, type, id),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(uint8_t, type)
+ __field(uint32_t, id)
+ ),
+ TP_fast_assign(
+ __entry->dev = mp->m_super->s_dev;
+ __entry->id = id;
+ __entry->type = type;
+ ),
+ TP_printk("dev %d:%d type %s id 0x%x",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __print_flags(__entry->type, "|", XFS_DQTYPE_STRINGS),
+ __entry->id)
+);
+
+#define DEFINE_XREP_DQUOT_EVENT(name) \
+DEFINE_EVENT(xrep_dquot_class, name, \
+ TP_PROTO(struct xfs_mount *mp, uint8_t type, uint32_t id), \
+ TP_ARGS(mp, type, id))
+DEFINE_XREP_DQUOT_EVENT(xrep_dquot_item);
+DEFINE_XREP_DQUOT_EVENT(xrep_disk_dquot);
+DEFINE_XREP_DQUOT_EVENT(xrep_dquot_item_fill_bmap_hole);
+#endif /* CONFIG_XFS_QUOTA */
+
#endif /* IS_ENABLED(CONFIG_XFS_ONLINE_REPAIR) */
#endif /* _TRACE_XFS_SCRUB_TRACE_H */
diff --git a/fs/xfs/scrub/xfarray.h b/fs/xfs/scrub/xfarray.h
index 4ecac01363d9..62b9c506fdd1 100644
--- a/fs/xfs/scrub/xfarray.h
+++ b/fs/xfs/scrub/xfarray.h
@@ -54,6 +54,28 @@ static inline int xfarray_append(struct xfarray *array, const void *ptr)
uint64_t xfarray_length(struct xfarray *array);
int xfarray_load_next(struct xfarray *array, xfarray_idx_t *idx, void *rec);
+/*
+ * Iterate the non-null elements in a sparse xfarray. Callers should
+ * initialize *idx to XFARRAY_CURSOR_INIT before the first call; on return, it
+ * will be set to one more than the index of the record that was retrieved.
+ * Returns 1 if a record was retrieved, 0 if there weren't any more records, or
+ * a negative errno.
+ */
+static inline int
+xfarray_iter(
+ struct xfarray *array,
+ xfarray_idx_t *idx,
+ void *rec)
+{
+ int ret = xfarray_load_next(array, idx, rec);
+
+ if (ret == -ENODATA)
+ return 0;
+ if (ret == 0)
+ return 1;
+ return ret;
+}
+
/* Declarations for xfile array sort functionality. */
typedef cmp_func_t xfarray_cmp_fn;
diff --git a/fs/xfs/xfs_attr_item.c b/fs/xfs/xfs_attr_item.c
index 36fe2abb16e6..9e02111bd890 100644
--- a/fs/xfs/xfs_attr_item.c
+++ b/fs/xfs/xfs_attr_item.c
@@ -33,8 +33,6 @@ struct kmem_cache *xfs_attrd_cache;
static const struct xfs_item_ops xfs_attri_item_ops;
static const struct xfs_item_ops xfs_attrd_item_ops;
-static struct xfs_attrd_log_item *xfs_trans_get_attrd(struct xfs_trans *tp,
- struct xfs_attri_log_item *attrip);
static inline struct xfs_attri_log_item *ATTRI_ITEM(struct xfs_log_item *lip)
{
@@ -310,47 +308,6 @@ xfs_attrd_item_intent(
return &ATTRD_ITEM(lip)->attrd_attrip->attri_item;
}
-/*
- * Performs one step of an attribute update intent and marks the attrd item
- * dirty.. An attr operation may be a set or a remove. Note that the
- * transaction is marked dirty regardless of whether the operation succeeds or
- * fails to support the ATTRI/ATTRD lifecycle rules.
- */
-STATIC int
-xfs_xattri_finish_update(
- struct xfs_attr_intent *attr,
- struct xfs_attrd_log_item *attrdp)
-{
- struct xfs_da_args *args = attr->xattri_da_args;
- int error;
-
- if (XFS_TEST_ERROR(false, args->dp->i_mount, XFS_ERRTAG_LARP)) {
- error = -EIO;
- goto out;
- }
-
- error = xfs_attr_set_iter(attr);
- if (!error && attr->xattri_dela_state != XFS_DAS_DONE)
- error = -EAGAIN;
-out:
- /*
- * Mark the transaction dirty, even on error. This ensures the
- * transaction is aborted, which:
- *
- * 1.) releases the ATTRI and frees the ATTRD
- * 2.) shuts down the filesystem
- */
- args->trans->t_flags |= XFS_TRANS_DIRTY | XFS_TRANS_HAS_INTENT_DONE;
-
- /*
- * attr intent/done items are null when logged attributes are disabled
- */
- if (attrdp)
- set_bit(XFS_LI_DIRTY, &attrdp->attrd_item.li_flags);
-
- return error;
-}
-
/* Log an attr to the intent item. */
STATIC void
xfs_attr_log_item(
@@ -360,9 +317,6 @@ xfs_attr_log_item(
{
struct xfs_attri_log_format *attrp;
- tp->t_flags |= XFS_TRANS_DIRTY;
- set_bit(XFS_LI_DIRTY, &attrip->attri_item.li_flags);
-
/*
* At this point the xfs_attr_intent has been constructed, and we've
* created the log intent. Fill in the attri log item and log format
@@ -419,7 +373,6 @@ xfs_attr_create_intent(
}
attrip = xfs_attri_init(mp, attr->xattri_nameval);
- xfs_trans_add_item(tp, &attrip->attri_item);
xfs_attr_log_item(tp, attrip, attr);
return &attrip->attri_item;
@@ -447,23 +400,33 @@ xfs_attr_finish_item(
struct xfs_btree_cur **state)
{
struct xfs_attr_intent *attr;
- struct xfs_attrd_log_item *done_item = NULL;
+ struct xfs_da_args *args;
int error;
attr = container_of(item, struct xfs_attr_intent, xattri_list);
- if (done)
- done_item = ATTRD_ITEM(done);
+ args = attr->xattri_da_args;
- /*
- * Always reset trans after EAGAIN cycle
- * since the transaction is new
- */
- attr->xattri_da_args->trans = tp;
+ /* Reset trans after EAGAIN cycle since the transaction is new */
+ args->trans = tp;
- error = xfs_xattri_finish_update(attr, done_item);
- if (error != -EAGAIN)
- xfs_attr_free_item(attr);
+ if (XFS_TEST_ERROR(false, args->dp->i_mount, XFS_ERRTAG_LARP)) {
+ error = -EIO;
+ goto out;
+ }
+ /* If an attr removal is trivially complete, we're done. */
+ if (attr->xattri_op_flags == XFS_ATTRI_OP_FLAGS_REMOVE &&
+ !xfs_inode_hasattr(args->dp)) {
+ error = 0;
+ goto out;
+ }
+
+ error = xfs_attr_set_iter(attr);
+ if (!error && attr->xattri_dela_state != XFS_DAS_DONE)
+ return -EAGAIN;
+
+out:
+ xfs_attr_free_item(attr);
return error;
}
@@ -532,41 +495,22 @@ xfs_attri_validate(
return xfs_verify_ino(mp, attrp->alfi_ino);
}
-/*
- * Process an attr intent item that was recovered from the log. We need to
- * delete the attr that it describes.
- */
-STATIC int
-xfs_attri_item_recover(
- struct xfs_log_item *lip,
- struct list_head *capture_list)
+static inline struct xfs_attr_intent *
+xfs_attri_recover_work(
+ struct xfs_mount *mp,
+ struct xfs_defer_pending *dfp,
+ struct xfs_attri_log_format *attrp,
+ struct xfs_inode **ipp,
+ struct xfs_attri_log_nameval *nv)
{
- struct xfs_attri_log_item *attrip = ATTRI_ITEM(lip);
struct xfs_attr_intent *attr;
- struct xfs_mount *mp = lip->li_log->l_mp;
- struct xfs_inode *ip;
struct xfs_da_args *args;
- struct xfs_trans *tp;
- struct xfs_trans_res resv;
- struct xfs_attri_log_format *attrp;
- struct xfs_attri_log_nameval *nv = attrip->attri_nameval;
- int error;
- int total;
int local;
- struct xfs_attrd_log_item *done_item = NULL;
-
- /*
- * First check the validity of the attr described by the ATTRI. If any
- * are bad, then assume that all are bad and just toss the ATTRI.
- */
- attrp = &attrip->attri_format;
- if (!xfs_attri_validate(mp, attrp) ||
- !xfs_attr_namecheck(nv->name.i_addr, nv->name.i_len))
- return -EFSCORRUPTED;
+ int error;
- error = xlog_recover_iget(mp, attrp->alfi_ino, &ip);
+ error = xlog_recover_iget(mp, attrp->alfi_ino, ipp);
if (error)
- return error;
+ return ERR_PTR(error);
attr = kmem_zalloc(sizeof(struct xfs_attr_intent) +
sizeof(struct xfs_da_args), KM_NOFS);
@@ -584,7 +528,7 @@ xfs_attri_item_recover(
attr->xattri_nameval = xfs_attri_log_nameval_get(nv);
ASSERT(attr->xattri_nameval);
- args->dp = ip;
+ args->dp = *ipp;
args->geo = mp->m_attr_geo;
args->whichfork = XFS_ATTR_FORK;
args->name = nv->name.i_addr;
@@ -608,43 +552,65 @@ xfs_attri_item_recover(
attr->xattri_dela_state = xfs_attr_init_add_state(args);
break;
case XFS_ATTRI_OP_FLAGS_REMOVE:
- if (!xfs_inode_hasattr(args->dp))
- goto out;
attr->xattri_dela_state = xfs_attr_init_remove_state(args);
break;
- default:
- ASSERT(0);
- error = -EFSCORRUPTED;
- goto out;
}
+ xfs_defer_add_item(dfp, &attr->xattri_list);
+ return attr;
+}
+
+/*
+ * Process an attr intent item that was recovered from the log. We need to
+ * delete the attr that it describes.
+ */
+STATIC int
+xfs_attr_recover_work(
+ struct xfs_defer_pending *dfp,
+ struct list_head *capture_list)
+{
+ struct xfs_log_item *lip = dfp->dfp_intent;
+ struct xfs_attri_log_item *attrip = ATTRI_ITEM(lip);
+ struct xfs_attr_intent *attr;
+ struct xfs_mount *mp = lip->li_log->l_mp;
+ struct xfs_inode *ip;
+ struct xfs_da_args *args;
+ struct xfs_trans *tp;
+ struct xfs_trans_res resv;
+ struct xfs_attri_log_format *attrp;
+ struct xfs_attri_log_nameval *nv = attrip->attri_nameval;
+ int error;
+ int total;
+
+ /*
+ * First check the validity of the attr described by the ATTRI. If any
+ * are bad, then assume that all are bad and just toss the ATTRI.
+ */
+ attrp = &attrip->attri_format;
+ if (!xfs_attri_validate(mp, attrp) ||
+ !xfs_attr_namecheck(nv->name.i_addr, nv->name.i_len))
+ return -EFSCORRUPTED;
+
+ attr = xfs_attri_recover_work(mp, dfp, attrp, &ip, nv);
+ if (IS_ERR(attr))
+ return PTR_ERR(attr);
+ args = attr->xattri_da_args;
+
xfs_init_attr_trans(args, &resv, &total);
resv = xlog_recover_resv(&resv);
error = xfs_trans_alloc(mp, &resv, total, 0, XFS_TRANS_RESERVE, &tp);
if (error)
- goto out;
-
+ return error;
args->trans = tp;
- done_item = xfs_trans_get_attrd(tp, attrip);
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_trans_ijoin(tp, ip, 0);
- error = xfs_xattri_finish_update(attr, done_item);
- if (error == -EAGAIN) {
- /*
- * There's more work to do, so add the intent item to this
- * transaction so that we can continue it later.
- */
- xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_ATTR, &attr->xattri_list);
- error = xfs_defer_ops_capture_and_commit(tp, capture_list);
- if (error)
- goto out_unlock;
-
- xfs_iunlock(ip, XFS_ILOCK_EXCL);
- xfs_irele(ip);
- return 0;
- }
+ error = xlog_recover_finish_intent(tp, dfp);
+ if (error == -EFSCORRUPTED)
+ XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
+ &attrip->attri_format,
+ sizeof(attrip->attri_format));
if (error) {
xfs_trans_cancel(tp);
goto out_unlock;
@@ -654,18 +620,16 @@ xfs_attri_item_recover(
out_unlock:
xfs_iunlock(ip, XFS_ILOCK_EXCL);
xfs_irele(ip);
-out:
- xfs_attr_free_item(attr);
return error;
}
/* Re-log an intent item to push the log tail forward. */
static struct xfs_log_item *
-xfs_attri_item_relog(
+xfs_attr_relog_intent(
+ struct xfs_trans *tp,
struct xfs_log_item *intent,
- struct xfs_trans *tp)
+ struct xfs_log_item *done_item)
{
- struct xfs_attrd_log_item *attrdp;
struct xfs_attri_log_item *old_attrip;
struct xfs_attri_log_item *new_attrip;
struct xfs_attri_log_format *new_attrp;
@@ -674,10 +638,6 @@ xfs_attri_item_relog(
old_attrip = ATTRI_ITEM(intent);
old_attrp = &old_attrip->attri_format;
- tp->t_flags |= XFS_TRANS_DIRTY;
- attrdp = xfs_trans_get_attrd(tp, old_attrip);
- set_bit(XFS_LI_DIRTY, &attrdp->attrd_item.li_flags);
-
/*
* Create a new log item that shares the same name/value buffer as the
* old log item.
@@ -691,12 +651,43 @@ xfs_attri_item_relog(
new_attrp->alfi_name_len = old_attrp->alfi_name_len;
new_attrp->alfi_attr_filter = old_attrp->alfi_attr_filter;
- xfs_trans_add_item(tp, &new_attrip->attri_item);
- set_bit(XFS_LI_DIRTY, &new_attrip->attri_item.li_flags);
-
return &new_attrip->attri_item;
}
+/* Get an ATTRD so we can process all the attrs. */
+static struct xfs_log_item *
+xfs_attr_create_done(
+ struct xfs_trans *tp,
+ struct xfs_log_item *intent,
+ unsigned int count)
+{
+ struct xfs_attri_log_item *attrip;
+ struct xfs_attrd_log_item *attrdp;
+
+ attrip = ATTRI_ITEM(intent);
+
+ attrdp = kmem_cache_zalloc(xfs_attrd_cache, GFP_NOFS | __GFP_NOFAIL);
+
+ xfs_log_item_init(tp->t_mountp, &attrdp->attrd_item, XFS_LI_ATTRD,
+ &xfs_attrd_item_ops);
+ attrdp->attrd_attrip = attrip;
+ attrdp->attrd_format.alfd_alf_id = attrip->attri_format.alfi_id;
+
+ return &attrdp->attrd_item;
+}
+
+const struct xfs_defer_op_type xfs_attr_defer_type = {
+ .name = "attr",
+ .max_items = 1,
+ .create_intent = xfs_attr_create_intent,
+ .abort_intent = xfs_attr_abort_intent,
+ .create_done = xfs_attr_create_done,
+ .finish_item = xfs_attr_finish_item,
+ .cancel_item = xfs_attr_cancel_item,
+ .recover_work = xfs_attr_recover_work,
+ .relog_intent = xfs_attr_relog_intent,
+};
+
STATIC int
xlog_recover_attri_commit_pass2(
struct xlog *log,
@@ -767,63 +758,13 @@ xlog_recover_attri_commit_pass2(
attrip = xfs_attri_init(mp, nv);
memcpy(&attrip->attri_format, attri_formatp, len);
- /*
- * The ATTRI has two references. One for the ATTRD and one for ATTRI to
- * ensure it makes it into the AIL. Insert the ATTRI into the AIL
- * directly and drop the ATTRI reference. Note that
- * xfs_trans_ail_update() drops the AIL lock.
- */
- xfs_trans_ail_insert(log->l_ailp, &attrip->attri_item, lsn);
- xfs_attri_release(attrip);
+ xlog_recover_intent_item(log, &attrip->attri_item, lsn,
+ &xfs_attr_defer_type);
xfs_attri_log_nameval_put(nv);
return 0;
}
/*
- * This routine is called to allocate an "attr free done" log item.
- */
-static struct xfs_attrd_log_item *
-xfs_trans_get_attrd(struct xfs_trans *tp,
- struct xfs_attri_log_item *attrip)
-{
- struct xfs_attrd_log_item *attrdp;
-
- ASSERT(tp != NULL);
-
- attrdp = kmem_cache_zalloc(xfs_attrd_cache, GFP_NOFS | __GFP_NOFAIL);
-
- xfs_log_item_init(tp->t_mountp, &attrdp->attrd_item, XFS_LI_ATTRD,
- &xfs_attrd_item_ops);
- attrdp->attrd_attrip = attrip;
- attrdp->attrd_format.alfd_alf_id = attrip->attri_format.alfi_id;
-
- xfs_trans_add_item(tp, &attrdp->attrd_item);
- return attrdp;
-}
-
-/* Get an ATTRD so we can process all the attrs. */
-static struct xfs_log_item *
-xfs_attr_create_done(
- struct xfs_trans *tp,
- struct xfs_log_item *intent,
- unsigned int count)
-{
- if (!intent)
- return NULL;
-
- return &xfs_trans_get_attrd(tp, ATTRI_ITEM(intent))->attrd_item;
-}
-
-const struct xfs_defer_op_type xfs_attr_defer_type = {
- .max_items = 1,
- .create_intent = xfs_attr_create_intent,
- .abort_intent = xfs_attr_abort_intent,
- .create_done = xfs_attr_create_done,
- .finish_item = xfs_attr_finish_item,
- .cancel_item = xfs_attr_cancel_item,
-};
-
-/*
* This routine is called when an ATTRD format structure is found in a committed
* transaction in the log. Its purpose is to cancel the corresponding ATTRI if
* it was still in the log. To do this it searches the AIL for the ATTRI with
@@ -857,9 +798,7 @@ static const struct xfs_item_ops xfs_attri_item_ops = {
.iop_format = xfs_attri_item_format,
.iop_unpin = xfs_attri_item_unpin,
.iop_release = xfs_attri_item_release,
- .iop_recover = xfs_attri_item_recover,
.iop_match = xfs_attri_item_match,
- .iop_relog = xfs_attri_item_relog,
};
const struct xlog_recover_item_ops xlog_attri_item_ops = {
diff --git a/fs/xfs/xfs_attr_list.c b/fs/xfs/xfs_attr_list.c
index 99bbbe1a0e44..e368ad671e26 100644
--- a/fs/xfs/xfs_attr_list.c
+++ b/fs/xfs/xfs_attr_list.c
@@ -56,14 +56,13 @@ xfs_attr_shortform_list(
struct xfs_attrlist_cursor_kern *cursor = &context->cursor;
struct xfs_inode *dp = context->dp;
struct xfs_attr_sf_sort *sbuf, *sbp;
- struct xfs_attr_shortform *sf;
+ struct xfs_attr_sf_hdr *sf = dp->i_af.if_data;
struct xfs_attr_sf_entry *sfe;
int sbsize, nsbuf, count, i;
int error = 0;
- sf = (struct xfs_attr_shortform *)dp->i_af.if_u1.if_data;
ASSERT(sf != NULL);
- if (!sf->hdr.count)
+ if (!sf->count)
return 0;
trace_xfs_attr_list_sf(context);
@@ -79,8 +78,8 @@ xfs_attr_shortform_list(
*/
if (context->bufsize == 0 ||
(XFS_ISRESET_CURSOR(cursor) &&
- (dp->i_af.if_bytes + sf->hdr.count * 16) < context->bufsize)) {
- for (i = 0, sfe = &sf->list[0]; i < sf->hdr.count; i++) {
+ (dp->i_af.if_bytes + sf->count * 16) < context->bufsize)) {
+ for (i = 0, sfe = xfs_attr_sf_firstentry(sf); i < sf->count; i++) {
if (XFS_IS_CORRUPT(context->dp->i_mount,
!xfs_attr_namecheck(sfe->nameval,
sfe->namelen)))
@@ -109,7 +108,7 @@ xfs_attr_shortform_list(
/*
* It didn't all fit, so we have to sort everything on hashval.
*/
- sbsize = sf->hdr.count * sizeof(*sbuf);
+ sbsize = sf->count * sizeof(*sbuf);
sbp = sbuf = kmem_alloc(sbsize, KM_NOFS);
/*
@@ -117,7 +116,7 @@ xfs_attr_shortform_list(
* the relevant info from only those that match into a buffer.
*/
nsbuf = 0;
- for (i = 0, sfe = &sf->list[0]; i < sf->hdr.count; i++) {
+ for (i = 0, sfe = xfs_attr_sf_firstentry(sf); i < sf->count; i++) {
if (unlikely(
((char *)sfe < (char *)sf) ||
((char *)sfe >= ((char *)sf + dp->i_af.if_bytes)))) {
diff --git a/fs/xfs/xfs_bmap_item.c b/fs/xfs/xfs_bmap_item.c
index e736a0844c89..52fb8a148b7d 100644
--- a/fs/xfs/xfs_bmap_item.c
+++ b/fs/xfs/xfs_bmap_item.c
@@ -221,51 +221,6 @@ static const struct xfs_item_ops xfs_bud_item_ops = {
.iop_intent = xfs_bud_item_intent,
};
-static struct xfs_bud_log_item *
-xfs_trans_get_bud(
- struct xfs_trans *tp,
- struct xfs_bui_log_item *buip)
-{
- struct xfs_bud_log_item *budp;
-
- budp = kmem_cache_zalloc(xfs_bud_cache, GFP_KERNEL | __GFP_NOFAIL);
- xfs_log_item_init(tp->t_mountp, &budp->bud_item, XFS_LI_BUD,
- &xfs_bud_item_ops);
- budp->bud_buip = buip;
- budp->bud_format.bud_bui_id = buip->bui_format.bui_id;
-
- xfs_trans_add_item(tp, &budp->bud_item);
- return budp;
-}
-
-/*
- * Finish an bmap update and log it to the BUD. Note that the
- * transaction is marked dirty regardless of whether the bmap update
- * succeeds or fails to support the BUI/BUD lifecycle rules.
- */
-static int
-xfs_trans_log_finish_bmap_update(
- struct xfs_trans *tp,
- struct xfs_bud_log_item *budp,
- struct xfs_bmap_intent *bi)
-{
- int error;
-
- error = xfs_bmap_finish_one(tp, bi);
-
- /*
- * Mark the transaction dirty, even on error. This ensures the
- * transaction is aborted, which:
- *
- * 1.) releases the BUI and frees the BUD
- * 2.) shuts down the filesystem
- */
- tp->t_flags |= XFS_TRANS_DIRTY | XFS_TRANS_HAS_INTENT_DONE;
- set_bit(XFS_LI_DIRTY, &budp->bud_item.li_flags);
-
- return error;
-}
-
/* Sort bmap intents by inode. */
static int
xfs_bmap_update_diff_items(
@@ -314,9 +269,6 @@ xfs_bmap_update_log_item(
uint next_extent;
struct xfs_map_extent *map;
- tp->t_flags |= XFS_TRANS_DIRTY;
- set_bit(XFS_LI_DIRTY, &buip->bui_item.li_flags);
-
/*
* atomic_inc_return gives us the value after the increment;
* we want to use it as an array index so we need to subtract 1 from
@@ -346,7 +298,6 @@ xfs_bmap_update_create_intent(
ASSERT(count == XFS_BUI_MAX_FAST_EXTENTS);
- xfs_trans_add_item(tp, &buip->bui_item);
if (sort)
list_sort(mp, items, xfs_bmap_update_diff_items);
list_for_each_entry(bi, items, bi_list)
@@ -354,14 +305,23 @@ xfs_bmap_update_create_intent(
return &buip->bui_item;
}
-/* Get an BUD so we can process all the deferred rmap updates. */
+/* Get an BUD so we can process all the deferred bmap updates. */
static struct xfs_log_item *
xfs_bmap_update_create_done(
struct xfs_trans *tp,
struct xfs_log_item *intent,
unsigned int count)
{
- return &xfs_trans_get_bud(tp, BUI_ITEM(intent))->bud_item;
+ struct xfs_bui_log_item *buip = BUI_ITEM(intent);
+ struct xfs_bud_log_item *budp;
+
+ budp = kmem_cache_zalloc(xfs_bud_cache, GFP_KERNEL | __GFP_NOFAIL);
+ xfs_log_item_init(tp->t_mountp, &budp->bud_item, XFS_LI_BUD,
+ &xfs_bud_item_ops);
+ budp->bud_buip = buip;
+ budp->bud_format.bud_bui_id = buip->bui_format.bui_id;
+
+ return &budp->bud_item;
}
/* Take a passive ref to the AG containing the space we're mapping. */
@@ -392,7 +352,7 @@ xfs_bmap_update_put_group(
xfs_perag_intent_put(bi->bi_pag);
}
-/* Process a deferred rmap update. */
+/* Process a deferred bmap update. */
STATIC int
xfs_bmap_update_finish_item(
struct xfs_trans *tp,
@@ -405,7 +365,7 @@ xfs_bmap_update_finish_item(
bi = container_of(item, struct xfs_bmap_intent, bi_list);
- error = xfs_trans_log_finish_bmap_update(tp, BUD_ITEM(done), bi);
+ error = xfs_bmap_finish_one(tp, bi);
if (!error && bi->bi_bmap.br_blockcount > 0) {
ASSERT(bi->bi_type == XFS_BMAP_UNMAP);
return -EAGAIN;
@@ -437,15 +397,6 @@ xfs_bmap_update_cancel_item(
kmem_cache_free(xfs_bmap_intent_cache, bi);
}
-const struct xfs_defer_op_type xfs_bmap_update_defer_type = {
- .max_items = XFS_BUI_MAX_FAST_EXTENTS,
- .create_intent = xfs_bmap_update_create_intent,
- .abort_intent = xfs_bmap_update_abort_intent,
- .create_done = xfs_bmap_update_create_done,
- .finish_item = xfs_bmap_update_finish_item,
- .cancel_item = xfs_bmap_update_cancel_item,
-};
-
/* Is this recovered BUI ok? */
static inline bool
xfs_bui_validate(
@@ -480,23 +431,53 @@ xfs_bui_validate(
return xfs_verify_fsbext(mp, map->me_startblock, map->me_len);
}
+static inline struct xfs_bmap_intent *
+xfs_bui_recover_work(
+ struct xfs_mount *mp,
+ struct xfs_defer_pending *dfp,
+ struct xfs_inode **ipp,
+ struct xfs_map_extent *map)
+{
+ struct xfs_bmap_intent *bi;
+ int error;
+
+ error = xlog_recover_iget(mp, map->me_owner, ipp);
+ if (error)
+ return ERR_PTR(error);
+
+ bi = kmem_cache_zalloc(xfs_bmap_intent_cache, GFP_NOFS | __GFP_NOFAIL);
+ bi->bi_whichfork = (map->me_flags & XFS_BMAP_EXTENT_ATTR_FORK) ?
+ XFS_ATTR_FORK : XFS_DATA_FORK;
+ bi->bi_type = map->me_flags & XFS_BMAP_EXTENT_TYPE_MASK;
+ bi->bi_bmap.br_startblock = map->me_startblock;
+ bi->bi_bmap.br_startoff = map->me_startoff;
+ bi->bi_bmap.br_blockcount = map->me_len;
+ bi->bi_bmap.br_state = (map->me_flags & XFS_BMAP_EXTENT_UNWRITTEN) ?
+ XFS_EXT_UNWRITTEN : XFS_EXT_NORM;
+ bi->bi_owner = *ipp;
+ xfs_bmap_update_get_group(mp, bi);
+
+ xfs_defer_add_item(dfp, &bi->bi_list);
+ return bi;
+}
+
/*
* Process a bmap update intent item that was recovered from the log.
* We need to update some inode's bmbt.
*/
STATIC int
-xfs_bui_item_recover(
- struct xfs_log_item *lip,
+xfs_bmap_recover_work(
+ struct xfs_defer_pending *dfp,
struct list_head *capture_list)
{
- struct xfs_bmap_intent fake = { };
struct xfs_trans_res resv;
+ struct xfs_log_item *lip = dfp->dfp_intent;
struct xfs_bui_log_item *buip = BUI_ITEM(lip);
struct xfs_trans *tp;
struct xfs_inode *ip = NULL;
struct xfs_mount *mp = lip->li_log->l_mp;
struct xfs_map_extent *map;
- struct xfs_bud_log_item *budp;
+ struct xfs_bmap_intent *work;
int iext_delta;
int error = 0;
@@ -507,13 +488,9 @@ xfs_bui_item_recover(
}
map = &buip->bui_format.bui_extents[0];
- fake.bi_whichfork = (map->me_flags & XFS_BMAP_EXTENT_ATTR_FORK) ?
- XFS_ATTR_FORK : XFS_DATA_FORK;
- fake.bi_type = map->me_flags & XFS_BMAP_EXTENT_TYPE_MASK;
-
- error = xlog_recover_iget(mp, map->me_owner, &ip);
- if (error)
- return error;
+ work = xfs_bui_recover_work(mp, dfp, &ip, map);
+ if (IS_ERR(work))
+ return PTR_ERR(work);
/* Allocate transaction and do the work. */
resv = xlog_recover_resv(&M_RES(mp)->tr_itruncate);
@@ -522,42 +499,27 @@ xfs_bui_item_recover(
if (error)
goto err_rele;
- budp = xfs_trans_get_bud(tp, buip);
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_trans_ijoin(tp, ip, 0);
- if (fake.bi_type == XFS_BMAP_MAP)
+ if (work->bi_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, fake.bi_whichfork, iext_delta);
+ error = xfs_iext_count_may_overflow(ip, work->bi_whichfork, iext_delta);
if (error == -EFBIG)
error = xfs_iext_count_upgrade(tp, ip, iext_delta);
if (error)
goto err_cancel;
- fake.bi_owner = ip;
- fake.bi_bmap.br_startblock = map->me_startblock;
- fake.bi_bmap.br_startoff = map->me_startoff;
- fake.bi_bmap.br_blockcount = map->me_len;
- fake.bi_bmap.br_state = (map->me_flags & XFS_BMAP_EXTENT_UNWRITTEN) ?
- XFS_EXT_UNWRITTEN : XFS_EXT_NORM;
-
- xfs_bmap_update_get_group(mp, &fake);
- error = xfs_trans_log_finish_bmap_update(tp, budp, &fake);
+ error = xlog_recover_finish_intent(tp, dfp);
if (error == -EFSCORRUPTED)
- XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, map,
- sizeof(*map));
- xfs_bmap_update_put_group(&fake);
+ XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
+ &buip->bui_format, sizeof(buip->bui_format));
if (error)
goto err_cancel;
- if (fake.bi_bmap.br_blockcount > 0) {
- ASSERT(fake.bi_type == XFS_BMAP_UNMAP);
- xfs_bmap_unmap_extent(tp, ip, &fake.bi_bmap);
- }
-
/*
* Commit transaction, which frees the transaction and saves the inode
* for later replay activities.
@@ -579,21 +541,13 @@ err_rele:
return error;
}
-STATIC bool
-xfs_bui_item_match(
- struct xfs_log_item *lip,
- uint64_t intent_id)
-{
- return BUI_ITEM(lip)->bui_format.bui_id == intent_id;
-}
-
/* Relog an intent item to push the log tail forward. */
static struct xfs_log_item *
-xfs_bui_item_relog(
+xfs_bmap_relog_intent(
+ struct xfs_trans *tp,
struct xfs_log_item *intent,
- struct xfs_trans *tp)
+ struct xfs_log_item *done_item)
{
- struct xfs_bud_log_item *budp;
struct xfs_bui_log_item *buip;
struct xfs_map_extent *map;
unsigned int count;
@@ -601,27 +555,40 @@ xfs_bui_item_relog(
count = BUI_ITEM(intent)->bui_format.bui_nextents;
map = BUI_ITEM(intent)->bui_format.bui_extents;
- tp->t_flags |= XFS_TRANS_DIRTY;
- budp = xfs_trans_get_bud(tp, BUI_ITEM(intent));
- set_bit(XFS_LI_DIRTY, &budp->bud_item.li_flags);
-
buip = xfs_bui_init(tp->t_mountp);
memcpy(buip->bui_format.bui_extents, map, count * sizeof(*map));
atomic_set(&buip->bui_next_extent, count);
- xfs_trans_add_item(tp, &buip->bui_item);
- set_bit(XFS_LI_DIRTY, &buip->bui_item.li_flags);
+
return &buip->bui_item;
}
+const struct xfs_defer_op_type xfs_bmap_update_defer_type = {
+ .name = "bmap",
+ .max_items = XFS_BUI_MAX_FAST_EXTENTS,
+ .create_intent = xfs_bmap_update_create_intent,
+ .abort_intent = xfs_bmap_update_abort_intent,
+ .create_done = xfs_bmap_update_create_done,
+ .finish_item = xfs_bmap_update_finish_item,
+ .cancel_item = xfs_bmap_update_cancel_item,
+ .recover_work = xfs_bmap_recover_work,
+ .relog_intent = xfs_bmap_relog_intent,
+};
+
+STATIC bool
+xfs_bui_item_match(
+ struct xfs_log_item *lip,
+ uint64_t intent_id)
+{
+ return BUI_ITEM(lip)->bui_format.bui_id == intent_id;
+}
+
static const struct xfs_item_ops xfs_bui_item_ops = {
.flags = XFS_ITEM_INTENT,
.iop_size = xfs_bui_item_size,
.iop_format = xfs_bui_item_format,
.iop_unpin = xfs_bui_item_unpin,
.iop_release = xfs_bui_item_release,
- .iop_recover = xfs_bui_item_recover,
.iop_match = xfs_bui_item_match,
- .iop_relog = xfs_bui_item_relog,
};
static inline void
@@ -681,12 +648,9 @@ xlog_recover_bui_commit_pass2(
buip = xfs_bui_init(mp);
xfs_bui_copy_format(&buip->bui_format, bui_formatp);
atomic_set(&buip->bui_next_extent, bui_formatp->bui_nextents);
- /*
- * Insert the intent into the AIL directly and drop one reference so
- * that finishing or canceling the work will drop the other.
- */
- xfs_trans_ail_insert(log->l_ailp, &buip->bui_item, lsn);
- xfs_bui_release(buip);
+
+ xlog_recover_intent_item(log, &buip->bui_item, lsn,
+ &xfs_bmap_update_defer_type);
return 0;
}
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 731260a5af6d..c2531c28905c 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -69,147 +69,6 @@ xfs_zero_extent(
GFP_NOFS, 0);
}
-#ifdef CONFIG_XFS_RT
-int
-xfs_bmap_rtalloc(
- struct xfs_bmalloca *ap)
-{
- struct xfs_mount *mp = ap->ip->i_mount;
- xfs_fileoff_t orig_offset = ap->offset;
- xfs_rtxnum_t rtx;
- xfs_rtxlen_t prod = 0; /* product factor for allocators */
- xfs_extlen_t mod = 0; /* product factor for allocators */
- xfs_rtxlen_t ralen = 0; /* realtime allocation length */
- xfs_extlen_t align; /* minimum allocation alignment */
- xfs_extlen_t orig_length = ap->length;
- xfs_extlen_t minlen = mp->m_sb.sb_rextsize;
- xfs_rtxlen_t raminlen;
- bool rtlocked = false;
- bool ignore_locality = false;
- int error;
-
- align = xfs_get_extsz_hint(ap->ip);
-retry:
- prod = xfs_extlen_to_rtxlen(mp, align);
- error = xfs_bmap_extsize_align(mp, &ap->got, &ap->prev,
- align, 1, ap->eof, 0,
- ap->conv, &ap->offset, &ap->length);
- if (error)
- return error;
- ASSERT(ap->length);
- ASSERT(xfs_extlen_to_rtxmod(mp, ap->length) == 0);
-
- /*
- * If we shifted the file offset downward to satisfy an extent size
- * hint, increase minlen by that amount so that the allocator won't
- * give us an allocation that's too short to cover at least one of the
- * blocks that the caller asked for.
- */
- if (ap->offset != orig_offset)
- minlen += orig_offset - ap->offset;
-
- /*
- * If the offset & length are not perfectly aligned
- * then kill prod, it will just get us in trouble.
- */
- div_u64_rem(ap->offset, align, &mod);
- if (mod || ap->length % align)
- prod = 1;
- /*
- * Set ralen to be the actual requested length in rtextents.
- *
- * If the old value was close enough to XFS_BMBT_MAX_EXTLEN that
- * we rounded up to it, cut it back so it's valid again.
- * Note that if it's a really large request (bigger than
- * XFS_BMBT_MAX_EXTLEN), we don't hear about that number, and can't
- * adjust the starting point to match it.
- */
- ralen = xfs_extlen_to_rtxlen(mp, min(ap->length, XFS_MAX_BMBT_EXTLEN));
-
- /*
- * Lock out modifications to both the RT bitmap and summary inodes
- */
- if (!rtlocked) {
- xfs_ilock(mp->m_rbmip, XFS_ILOCK_EXCL|XFS_ILOCK_RTBITMAP);
- xfs_trans_ijoin(ap->tp, mp->m_rbmip, XFS_ILOCK_EXCL);
- xfs_ilock(mp->m_rsumip, XFS_ILOCK_EXCL|XFS_ILOCK_RTSUM);
- xfs_trans_ijoin(ap->tp, mp->m_rsumip, XFS_ILOCK_EXCL);
- rtlocked = true;
- }
-
- /*
- * If it's an allocation to an empty file at offset 0,
- * pick an extent that will space things out in the rt area.
- */
- if (ap->eof && ap->offset == 0) {
- error = xfs_rtpick_extent(mp, ap->tp, ralen, &rtx);
- if (error)
- return error;
- ap->blkno = xfs_rtx_to_rtb(mp, rtx);
- } else {
- ap->blkno = 0;
- }
-
- xfs_bmap_adjacent(ap);
-
- /*
- * Realtime allocation, done through xfs_rtallocate_extent.
- */
- if (ignore_locality)
- rtx = 0;
- else
- rtx = xfs_rtb_to_rtx(mp, ap->blkno);
- raminlen = max_t(xfs_rtxlen_t, 1, xfs_extlen_to_rtxlen(mp, minlen));
- error = xfs_rtallocate_extent(ap->tp, rtx, raminlen, ralen, &ralen,
- ap->wasdel, prod, &rtx);
- if (error)
- return error;
-
- if (rtx != NULLRTEXTNO) {
- ap->blkno = xfs_rtx_to_rtb(mp, rtx);
- ap->length = xfs_rtxlen_to_extlen(mp, ralen);
- ap->ip->i_nblocks += ap->length;
- xfs_trans_log_inode(ap->tp, ap->ip, XFS_ILOG_CORE);
- if (ap->wasdel)
- ap->ip->i_delayed_blks -= ap->length;
- /*
- * Adjust the disk quota also. This was reserved
- * earlier.
- */
- xfs_trans_mod_dquot_byino(ap->tp, ap->ip,
- ap->wasdel ? XFS_TRANS_DQ_DELRTBCOUNT :
- XFS_TRANS_DQ_RTBCOUNT, ap->length);
- return 0;
- }
-
- if (align > mp->m_sb.sb_rextsize) {
- /*
- * We previously enlarged the request length to try to satisfy
- * an extent size hint. The allocator didn't return anything,
- * so reset the parameters to the original values and try again
- * without alignment criteria.
- */
- ap->offset = orig_offset;
- ap->length = orig_length;
- minlen = align = mp->m_sb.sb_rextsize;
- goto retry;
- }
-
- if (!ignore_locality && ap->blkno != 0) {
- /*
- * If we can't allocate near a specific rt extent, try again
- * without locality criteria.
- */
- ignore_locality = true;
- goto retry;
- }
-
- ap->blkno = NULLFSBLOCK;
- ap->length = 0;
- return 0;
-}
-#endif /* CONFIG_XFS_RT */
-
/*
* Extent tree block counting routines.
*/
diff --git a/fs/xfs/xfs_bmap_util.h b/fs/xfs/xfs_bmap_util.h
index 6888078f5c31..77ecbb753ef2 100644
--- a/fs/xfs/xfs_bmap_util.h
+++ b/fs/xfs/xfs_bmap_util.h
@@ -47,7 +47,7 @@ int xfs_bmap_extsize_align(struct xfs_mount *mp, struct xfs_bmbt_irec *gotp,
struct xfs_bmbt_irec *prevp, xfs_extlen_t extsz,
int rt, int eof, int delay, int convert,
xfs_fileoff_t *offp, xfs_extlen_t *lenp);
-void xfs_bmap_adjacent(struct xfs_bmalloca *ap);
+bool xfs_bmap_adjacent(struct xfs_bmalloca *ap);
int xfs_bmap_last_extent(struct xfs_trans *tp, struct xfs_inode *ip,
int whichfork, struct xfs_bmbt_irec *rec,
int *is_empty);
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 669332849680..8e5bd50d29fe 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -2049,6 +2049,14 @@ error_free:
return NULL;
}
+static inline void
+xfs_buf_list_del(
+ struct xfs_buf *bp)
+{
+ list_del_init(&bp->b_list);
+ wake_up_var(&bp->b_list);
+}
+
/*
* Cancel a delayed write list.
*
@@ -2066,7 +2074,7 @@ xfs_buf_delwri_cancel(
xfs_buf_lock(bp);
bp->b_flags &= ~_XBF_DELWRI_Q;
- list_del_init(&bp->b_list);
+ xfs_buf_list_del(bp);
xfs_buf_relse(bp);
}
}
@@ -2120,6 +2128,34 @@ xfs_buf_delwri_queue(
}
/*
+ * Queue a buffer to this delwri list as part of a data integrity operation.
+ * If the buffer is on any other delwri list, we'll wait for that to clear
+ * so that the caller can submit the buffer for IO and wait for the result.
+ * Callers must ensure the buffer is not already on the list.
+ */
+void
+xfs_buf_delwri_queue_here(
+ struct xfs_buf *bp,
+ struct list_head *buffer_list)
+{
+ /*
+ * We need this buffer to end up on the /caller's/ delwri list, not any
+ * old list. This can happen if the buffer is marked stale (which
+ * clears DELWRI_Q) after the AIL queues the buffer to its list but
+ * before the AIL has a chance to submit the list.
+ */
+ while (!list_empty(&bp->b_list)) {
+ xfs_buf_unlock(bp);
+ wait_var_event(&bp->b_list, list_empty(&bp->b_list));
+ xfs_buf_lock(bp);
+ }
+
+ ASSERT(!(bp->b_flags & _XBF_DELWRI_Q));
+
+ xfs_buf_delwri_queue(bp, buffer_list);
+}
+
+/*
* Compare function is more complex than it needs to be because
* the return value is only 32 bits and we are doing comparisons
* on 64 bit values
@@ -2181,7 +2217,7 @@ xfs_buf_delwri_submit_buffers(
* reference and remove it from the list here.
*/
if (!(bp->b_flags & _XBF_DELWRI_Q)) {
- list_del_init(&bp->b_list);
+ xfs_buf_list_del(bp);
xfs_buf_relse(bp);
continue;
}
@@ -2201,7 +2237,7 @@ xfs_buf_delwri_submit_buffers(
list_move_tail(&bp->b_list, wait_list);
} else {
bp->b_flags |= XBF_ASYNC;
- list_del_init(&bp->b_list);
+ xfs_buf_list_del(bp);
}
__xfs_buf_submit(bp, false);
}
@@ -2255,7 +2291,7 @@ xfs_buf_delwri_submit(
while (!list_empty(&wait_list)) {
bp = list_first_entry(&wait_list, struct xfs_buf, b_list);
- list_del_init(&bp->b_list);
+ xfs_buf_list_del(bp);
/*
* Wait on the locked buffer, check for errors and unlock and
diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h
index c86e16419656..b470de08a46c 100644
--- a/fs/xfs/xfs_buf.h
+++ b/fs/xfs/xfs_buf.h
@@ -319,6 +319,7 @@ extern void xfs_buf_stale(struct xfs_buf *bp);
/* Delayed Write Buffer Routines */
extern void xfs_buf_delwri_cancel(struct list_head *);
extern bool xfs_buf_delwri_queue(struct xfs_buf *, struct list_head *);
+void xfs_buf_delwri_queue_here(struct xfs_buf *bp, struct list_head *bl);
extern int xfs_buf_delwri_submit(struct list_head *);
extern int xfs_buf_delwri_submit_nowait(struct list_head *);
extern int xfs_buf_delwri_pushbuf(struct xfs_buf *, struct list_head *);
diff --git a/fs/xfs/xfs_dir2_readdir.c b/fs/xfs/xfs_dir2_readdir.c
index 9f3ceb461515..cc6dc56f455d 100644
--- a/fs/xfs/xfs_dir2_readdir.c
+++ b/fs/xfs/xfs_dir2_readdir.c
@@ -18,6 +18,7 @@
#include "xfs_bmap.h"
#include "xfs_trans.h"
#include "xfs_error.h"
+#include "xfs_health.h"
/*
* Directory file type support functions
@@ -51,7 +52,7 @@ xfs_dir2_sf_getdents(
struct xfs_mount *mp = dp->i_mount;
xfs_dir2_dataptr_t off; /* current entry's offset */
xfs_dir2_sf_entry_t *sfep; /* shortform directory entry */
- xfs_dir2_sf_hdr_t *sfp; /* shortform structure */
+ struct xfs_dir2_sf_hdr *sfp = dp->i_df.if_data;
xfs_dir2_dataptr_t dot_offset;
xfs_dir2_dataptr_t dotdot_offset;
xfs_ino_t ino;
@@ -59,9 +60,7 @@ xfs_dir2_sf_getdents(
ASSERT(dp->i_df.if_format == XFS_DINODE_FMT_LOCAL);
ASSERT(dp->i_df.if_bytes == dp->i_disk_size);
- ASSERT(dp->i_df.if_u1.if_data != NULL);
-
- sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
+ ASSERT(sfp != NULL);
/*
* If the block number in the offset is out of range, we're done.
@@ -519,6 +518,8 @@ xfs_readdir(
if (xfs_is_shutdown(dp->i_mount))
return -EIO;
+ if (xfs_ifork_zapped(dp, XFS_DATA_FORK))
+ return -EIO;
ASSERT(S_ISDIR(VFS_I(dp)->i_mode));
ASSERT(xfs_isilocked(dp, XFS_IOLOCK_SHARED | XFS_IOLOCK_EXCL));
diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c
index 61a45a86ffe8..b4f20d9c8f98 100644
--- a/fs/xfs/xfs_dquot.c
+++ b/fs/xfs/xfs_dquot.c
@@ -172,14 +172,14 @@ xfs_qm_adjust_dqtimers(
/*
* initialize a buffer full of dquots and log the whole thing
*/
-STATIC void
+void
xfs_qm_init_dquot_blk(
struct xfs_trans *tp,
- struct xfs_mount *mp,
xfs_dqid_t id,
xfs_dqtype_t type,
struct xfs_buf *bp)
{
+ struct xfs_mount *mp = tp->t_mountp;
struct xfs_quotainfo *q = mp->m_quotainfo;
struct xfs_dqblk *d;
xfs_dqid_t curid;
@@ -353,7 +353,7 @@ xfs_dquot_disk_alloc(
* Make a chunk of dquots out of this buffer and log
* the entire thing.
*/
- xfs_qm_init_dquot_blk(tp, mp, dqp->q_id, qtype, bp);
+ xfs_qm_init_dquot_blk(tp, dqp->q_id, qtype, bp);
xfs_buf_set_ref(bp, XFS_DQUOT_REF);
/*
@@ -1362,34 +1362,3 @@ xfs_qm_exit(void)
kmem_cache_destroy(xfs_dqtrx_cache);
kmem_cache_destroy(xfs_dquot_cache);
}
-
-/*
- * Iterate every dquot of a particular type. The caller must ensure that the
- * particular quota type is active. iter_fn can return negative error codes,
- * or -ECANCELED to indicate that it wants to stop iterating.
- */
-int
-xfs_qm_dqiterate(
- struct xfs_mount *mp,
- xfs_dqtype_t type,
- xfs_qm_dqiterate_fn iter_fn,
- void *priv)
-{
- struct xfs_dquot *dq;
- xfs_dqid_t id = 0;
- int error;
-
- do {
- error = xfs_qm_dqget_next(mp, id, type, &dq);
- if (error == -ENOENT)
- return 0;
- if (error)
- return error;
-
- error = iter_fn(dq, type, priv);
- id = dq->q_id + 1;
- xfs_qm_dqput(dq);
- } while (error == 0 && id != 0);
-
- return error;
-}
diff --git a/fs/xfs/xfs_dquot.h b/fs/xfs/xfs_dquot.h
index 80c8f851a2f3..956272d9b302 100644
--- a/fs/xfs/xfs_dquot.h
+++ b/fs/xfs/xfs_dquot.h
@@ -234,12 +234,10 @@ static inline struct xfs_dquot *xfs_qm_dqhold(struct xfs_dquot *dqp)
return dqp;
}
-typedef int (*xfs_qm_dqiterate_fn)(struct xfs_dquot *dq,
- xfs_dqtype_t type, void *priv);
-int xfs_qm_dqiterate(struct xfs_mount *mp, xfs_dqtype_t type,
- xfs_qm_dqiterate_fn iter_fn, void *priv);
-
time64_t xfs_dquot_set_timeout(struct xfs_mount *mp, time64_t timeout);
time64_t xfs_dquot_set_grace_period(time64_t grace);
+void xfs_qm_init_dquot_blk(struct xfs_trans *tp, xfs_dqid_t id, xfs_dqtype_t
+ type, struct xfs_buf *bp);
+
#endif /* __XFS_DQUOT_H__ */
diff --git a/fs/xfs/xfs_extent_busy.c b/fs/xfs/xfs_extent_busy.c
index 9ecfdcdc752f..2ccde32c9a9e 100644
--- a/fs/xfs/xfs_extent_busy.c
+++ b/fs/xfs/xfs_extent_busy.c
@@ -678,3 +678,16 @@ xfs_extent_busy_ag_cmp(
diff = b1->bno - b2->bno;
return diff;
}
+
+/* Are there any busy extents in this AG? */
+bool
+xfs_extent_busy_list_empty(
+ struct xfs_perag *pag)
+{
+ bool res;
+
+ spin_lock(&pag->pagb_lock);
+ res = RB_EMPTY_ROOT(&pag->pagb_tree);
+ spin_unlock(&pag->pagb_lock);
+ return res;
+}
diff --git a/fs/xfs/xfs_extent_busy.h b/fs/xfs/xfs_extent_busy.h
index 0639aab336f3..470032de3139 100644
--- a/fs/xfs/xfs_extent_busy.h
+++ b/fs/xfs/xfs_extent_busy.h
@@ -85,4 +85,6 @@ static inline void xfs_extent_busy_sort(struct list_head *list)
list_sort(NULL, list, xfs_extent_busy_ag_cmp);
}
+bool xfs_extent_busy_list_empty(struct xfs_perag *pag);
+
#endif /* __XFS_EXTENT_BUSY_H__ */
diff --git a/fs/xfs/xfs_extfree_item.c b/fs/xfs/xfs_extfree_item.c
index 3fa8789820ad..1d1185fca6a5 100644
--- a/fs/xfs/xfs_extfree_item.c
+++ b/fs/xfs/xfs_extfree_item.c
@@ -304,39 +304,6 @@ static const struct xfs_item_ops xfs_efd_item_ops = {
};
/*
- * Allocate an "extent free done" log item that will hold nextents worth of
- * extents. The caller must use all nextents extents, because we are not
- * flexible about this at all.
- */
-static struct xfs_efd_log_item *
-xfs_trans_get_efd(
- struct xfs_trans *tp,
- struct xfs_efi_log_item *efip,
- unsigned int nextents)
-{
- struct xfs_efd_log_item *efdp;
-
- ASSERT(nextents > 0);
-
- if (nextents > XFS_EFD_MAX_FAST_EXTENTS) {
- efdp = kzalloc(xfs_efd_log_item_sizeof(nextents),
- GFP_KERNEL | __GFP_NOFAIL);
- } else {
- efdp = kmem_cache_zalloc(xfs_efd_cache,
- GFP_KERNEL | __GFP_NOFAIL);
- }
-
- xfs_log_item_init(tp->t_mountp, &efdp->efd_item, XFS_LI_EFD,
- &xfs_efd_item_ops);
- efdp->efd_efip = efip;
- efdp->efd_format.efd_nextents = nextents;
- efdp->efd_format.efd_efi_id = efip->efi_format.efi_id;
-
- xfs_trans_add_item(tp, &efdp->efd_item);
- return efdp;
-}
-
-/*
* Fill the EFD with all extents from the EFI when we need to roll the
* transaction and continue with a new EFI.
*
@@ -364,69 +331,6 @@ xfs_efd_from_efi(
efdp->efd_next_extent = efip->efi_format.efi_nextents;
}
-/*
- * Free an extent and log it to the EFD. Note that the transaction is marked
- * dirty regardless of whether the extent free succeeds or fails to support the
- * EFI/EFD lifecycle rules.
- */
-static int
-xfs_trans_free_extent(
- struct xfs_trans *tp,
- struct xfs_efd_log_item *efdp,
- struct xfs_extent_free_item *xefi)
-{
- struct xfs_owner_info oinfo = { };
- struct xfs_mount *mp = tp->t_mountp;
- struct xfs_extent *extp;
- uint next_extent;
- xfs_agblock_t agbno = XFS_FSB_TO_AGBNO(mp,
- xefi->xefi_startblock);
- int error;
-
- oinfo.oi_owner = xefi->xefi_owner;
- if (xefi->xefi_flags & XFS_EFI_ATTR_FORK)
- oinfo.oi_flags |= XFS_OWNER_INFO_ATTR_FORK;
- if (xefi->xefi_flags & XFS_EFI_BMBT_BLOCK)
- oinfo.oi_flags |= XFS_OWNER_INFO_BMBT_BLOCK;
-
- trace_xfs_bmap_free_deferred(tp->t_mountp, xefi->xefi_pag->pag_agno, 0,
- agbno, xefi->xefi_blockcount);
-
- error = __xfs_free_extent(tp, xefi->xefi_pag, agbno,
- xefi->xefi_blockcount, &oinfo, xefi->xefi_agresv,
- xefi->xefi_flags & XFS_EFI_SKIP_DISCARD);
-
- /*
- * Mark the transaction dirty, even on error. This ensures the
- * transaction is aborted, which:
- *
- * 1.) releases the EFI and frees the EFD
- * 2.) shuts down the filesystem
- */
- tp->t_flags |= XFS_TRANS_DIRTY | XFS_TRANS_HAS_INTENT_DONE;
- set_bit(XFS_LI_DIRTY, &efdp->efd_item.li_flags);
-
- /*
- * If we need a new transaction to make progress, the caller will log a
- * new EFI with the current contents. It will also log an EFD to cancel
- * the existing EFI, and so we need to copy all the unprocessed extents
- * in this EFI to the EFD so this works correctly.
- */
- if (error == -EAGAIN) {
- xfs_efd_from_efi(efdp);
- return error;
- }
-
- next_extent = efdp->efd_next_extent;
- ASSERT(next_extent < efdp->efd_format.efd_nextents);
- extp = &(efdp->efd_format.efd_extents[next_extent]);
- extp->ext_start = xefi->xefi_startblock;
- extp->ext_len = xefi->xefi_blockcount;
- efdp->efd_next_extent++;
-
- return error;
-}
-
/* Sort bmap items by AG. */
static int
xfs_extent_free_diff_items(
@@ -453,9 +357,6 @@ xfs_extent_free_log_item(
uint next_extent;
struct xfs_extent *extp;
- tp->t_flags |= XFS_TRANS_DIRTY;
- set_bit(XFS_LI_DIRTY, &efip->efi_item.li_flags);
-
/*
* atomic_inc_return gives us the value after the increment;
* we want to use it as an array index so we need to subtract 1 from
@@ -481,7 +382,6 @@ xfs_extent_free_create_intent(
ASSERT(count > 0);
- xfs_trans_add_item(tp, &efip->efi_item);
if (sort)
list_sort(mp, items, xfs_extent_free_diff_items);
list_for_each_entry(xefi, items, xefi_list)
@@ -496,7 +396,26 @@ xfs_extent_free_create_done(
struct xfs_log_item *intent,
unsigned int count)
{
- return &xfs_trans_get_efd(tp, EFI_ITEM(intent), count)->efd_item;
+ struct xfs_efi_log_item *efip = EFI_ITEM(intent);
+ struct xfs_efd_log_item *efdp;
+
+ ASSERT(count > 0);
+
+ if (count > XFS_EFD_MAX_FAST_EXTENTS) {
+ efdp = kzalloc(xfs_efd_log_item_sizeof(count),
+ GFP_KERNEL | __GFP_NOFAIL);
+ } else {
+ efdp = kmem_cache_zalloc(xfs_efd_cache,
+ GFP_KERNEL | __GFP_NOFAIL);
+ }
+
+ xfs_log_item_init(tp->t_mountp, &efdp->efd_item, XFS_LI_EFD,
+ &xfs_efd_item_ops);
+ efdp->efd_efip = efip;
+ efdp->efd_format.efd_nextents = count;
+ efdp->efd_format.efd_efi_id = efip->efi_format.efi_id;
+
+ return &efdp->efd_item;
}
/* Take a passive ref to the AG containing the space we're freeing. */
@@ -527,19 +446,49 @@ xfs_extent_free_finish_item(
struct list_head *item,
struct xfs_btree_cur **state)
{
+ struct xfs_owner_info oinfo = { };
struct xfs_extent_free_item *xefi;
- int error;
+ struct xfs_efd_log_item *efdp = EFD_ITEM(done);
+ struct xfs_mount *mp = tp->t_mountp;
+ struct xfs_extent *extp;
+ uint next_extent;
+ xfs_agblock_t agbno;
+ int error = 0;
xefi = container_of(item, struct xfs_extent_free_item, xefi_list);
+ agbno = XFS_FSB_TO_AGBNO(mp, xefi->xefi_startblock);
+
+ oinfo.oi_owner = xefi->xefi_owner;
+ if (xefi->xefi_flags & XFS_EFI_ATTR_FORK)
+ oinfo.oi_flags |= XFS_OWNER_INFO_ATTR_FORK;
+ if (xefi->xefi_flags & XFS_EFI_BMBT_BLOCK)
+ oinfo.oi_flags |= XFS_OWNER_INFO_BMBT_BLOCK;
- error = xfs_trans_free_extent(tp, EFD_ITEM(done), xefi);
+ trace_xfs_bmap_free_deferred(tp->t_mountp, xefi->xefi_pag->pag_agno, 0,
+ agbno, xefi->xefi_blockcount);
/*
- * Don't free the XEFI if we need a new transaction to complete
- * processing of it.
+ * If we need a new transaction to make progress, the caller will log a
+ * new EFI with the current contents. It will also log an EFD to cancel
+ * the existing EFI, and so we need to copy all the unprocessed extents
+ * in this EFI to the EFD so this works correctly.
*/
- if (error == -EAGAIN)
+ if (!(xefi->xefi_flags & XFS_EFI_CANCELLED))
+ error = __xfs_free_extent(tp, xefi->xefi_pag, agbno,
+ xefi->xefi_blockcount, &oinfo, xefi->xefi_agresv,
+ xefi->xefi_flags & XFS_EFI_SKIP_DISCARD);
+ if (error == -EAGAIN) {
+ xfs_efd_from_efi(efdp);
return error;
+ }
+
+ /* Add the work we finished to the EFD, even though nobody uses that */
+ next_extent = efdp->efd_next_extent;
+ ASSERT(next_extent < efdp->efd_format.efd_nextents);
+ extp = &(efdp->efd_format.efd_extents[next_extent]);
+ extp->ext_start = xefi->xefi_startblock;
+ extp->ext_len = xefi->xefi_blockcount;
+ efdp->efd_next_extent++;
xfs_extent_free_put_group(xefi);
kmem_cache_free(xfs_extfree_item_cache, xefi);
@@ -567,15 +516,6 @@ xfs_extent_free_cancel_item(
kmem_cache_free(xfs_extfree_item_cache, xefi);
}
-const struct xfs_defer_op_type xfs_extent_free_defer_type = {
- .max_items = XFS_EFI_MAX_FAST_EXTENTS,
- .create_intent = xfs_extent_free_create_intent,
- .abort_intent = xfs_extent_free_abort_intent,
- .create_done = xfs_extent_free_create_done,
- .finish_item = xfs_extent_free_finish_item,
- .cancel_item = xfs_extent_free_cancel_item,
-};
-
/*
* AGFL blocks are accounted differently in the reserve pools and are not
* inserted into the busy extent list.
@@ -610,16 +550,6 @@ xfs_agfl_free_finish_item(
error = xfs_free_agfl_block(tp, xefi->xefi_pag->pag_agno,
agbno, agbp, &oinfo);
- /*
- * Mark the transaction dirty, even on error. This ensures the
- * transaction is aborted, which:
- *
- * 1.) releases the EFI and frees the EFD
- * 2.) shuts down the filesystem
- */
- tp->t_flags |= XFS_TRANS_DIRTY;
- set_bit(XFS_LI_DIRTY, &efdp->efd_item.li_flags);
-
next_extent = efdp->efd_next_extent;
ASSERT(next_extent < efdp->efd_format.efd_nextents);
extp = &(efdp->efd_format.efd_extents[next_extent]);
@@ -632,16 +562,6 @@ xfs_agfl_free_finish_item(
return error;
}
-/* sub-type with special handling for AGFL deferred frees */
-const struct xfs_defer_op_type xfs_agfl_free_defer_type = {
- .max_items = XFS_EFI_MAX_FAST_EXTENTS,
- .create_intent = xfs_extent_free_create_intent,
- .abort_intent = xfs_extent_free_abort_intent,
- .create_done = xfs_extent_free_create_done,
- .finish_item = xfs_agfl_free_finish_item,
- .cancel_item = xfs_extent_free_cancel_item,
-};
-
/* Is this recovered EFI ok? */
static inline bool
xfs_efi_validate_ext(
@@ -651,23 +571,41 @@ xfs_efi_validate_ext(
return xfs_verify_fsbext(mp, extp->ext_start, extp->ext_len);
}
+static inline void
+xfs_efi_recover_work(
+ struct xfs_mount *mp,
+ struct xfs_defer_pending *dfp,
+ struct xfs_extent *extp)
+{
+ struct xfs_extent_free_item *xefi;
+
+ xefi = kmem_cache_zalloc(xfs_extfree_item_cache,
+ GFP_KERNEL | __GFP_NOFAIL);
+ xefi->xefi_startblock = extp->ext_start;
+ xefi->xefi_blockcount = extp->ext_len;
+ xefi->xefi_agresv = XFS_AG_RESV_NONE;
+ xefi->xefi_owner = XFS_RMAP_OWN_UNKNOWN;
+ xfs_extent_free_get_group(mp, xefi);
+
+ xfs_defer_add_item(dfp, &xefi->xefi_list);
+}
+
/*
* Process an extent free intent item that was recovered from
* the log. We need to free the extents that it describes.
*/
STATIC int
-xfs_efi_item_recover(
- struct xfs_log_item *lip,
+xfs_extent_free_recover_work(
+ struct xfs_defer_pending *dfp,
struct list_head *capture_list)
{
struct xfs_trans_res resv;
+ struct xfs_log_item *lip = dfp->dfp_intent;
struct xfs_efi_log_item *efip = EFI_ITEM(lip);
struct xfs_mount *mp = lip->li_log->l_mp;
- struct xfs_efd_log_item *efdp;
struct xfs_trans *tp;
int i;
int error = 0;
- bool requeue_only = false;
/*
* First check the validity of the extents described by the
@@ -682,55 +620,22 @@ xfs_efi_item_recover(
sizeof(efip->efi_format));
return -EFSCORRUPTED;
}
+
+ xfs_efi_recover_work(mp, dfp, &efip->efi_format.efi_extents[i]);
}
resv = xlog_recover_resv(&M_RES(mp)->tr_itruncate);
error = xfs_trans_alloc(mp, &resv, 0, 0, 0, &tp);
if (error)
return error;
- efdp = xfs_trans_get_efd(tp, efip, efip->efi_format.efi_nextents);
-
- for (i = 0; i < efip->efi_format.efi_nextents; i++) {
- struct xfs_extent_free_item fake = {
- .xefi_owner = XFS_RMAP_OWN_UNKNOWN,
- .xefi_agresv = XFS_AG_RESV_NONE,
- };
- struct xfs_extent *extp;
- extp = &efip->efi_format.efi_extents[i];
-
- fake.xefi_startblock = extp->ext_start;
- fake.xefi_blockcount = extp->ext_len;
-
- if (!requeue_only) {
- xfs_extent_free_get_group(mp, &fake);
- error = xfs_trans_free_extent(tp, efdp, &fake);
- xfs_extent_free_put_group(&fake);
- }
-
- /*
- * If we can't free the extent without potentially deadlocking,
- * requeue the rest of the extents to a new so that they get
- * run again later with a new transaction context.
- */
- if (error == -EAGAIN || requeue_only) {
- error = xfs_free_extent_later(tp, fake.xefi_startblock,
- fake.xefi_blockcount,
- &XFS_RMAP_OINFO_ANY_OWNER,
- fake.xefi_agresv);
- if (!error) {
- requeue_only = true;
- continue;
- }
- }
-
- if (error == -EFSCORRUPTED)
- XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
- extp, sizeof(*extp));
- if (error)
- goto abort_error;
-
- }
+ error = xlog_recover_finish_intent(tp, dfp);
+ if (error == -EFSCORRUPTED)
+ XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
+ &efip->efi_format,
+ sizeof(efip->efi_format));
+ if (error)
+ goto abort_error;
return xfs_defer_ops_capture_and_commit(tp, capture_list);
@@ -739,21 +644,14 @@ abort_error:
return error;
}
-STATIC bool
-xfs_efi_item_match(
- struct xfs_log_item *lip,
- uint64_t intent_id)
-{
- return EFI_ITEM(lip)->efi_format.efi_id == intent_id;
-}
-
/* Relog an intent item to push the log tail forward. */
static struct xfs_log_item *
-xfs_efi_item_relog(
+xfs_extent_free_relog_intent(
+ struct xfs_trans *tp,
struct xfs_log_item *intent,
- struct xfs_trans *tp)
+ struct xfs_log_item *done_item)
{
- struct xfs_efd_log_item *efdp;
+ struct xfs_efd_log_item *efdp = EFD_ITEM(done_item);
struct xfs_efi_log_item *efip;
struct xfs_extent *extp;
unsigned int count;
@@ -761,29 +659,56 @@ xfs_efi_item_relog(
count = EFI_ITEM(intent)->efi_format.efi_nextents;
extp = EFI_ITEM(intent)->efi_format.efi_extents;
- tp->t_flags |= XFS_TRANS_DIRTY;
- efdp = xfs_trans_get_efd(tp, EFI_ITEM(intent), count);
efdp->efd_next_extent = count;
memcpy(efdp->efd_format.efd_extents, extp, count * sizeof(*extp));
- set_bit(XFS_LI_DIRTY, &efdp->efd_item.li_flags);
efip = xfs_efi_init(tp->t_mountp, count);
memcpy(efip->efi_format.efi_extents, extp, count * sizeof(*extp));
atomic_set(&efip->efi_next_extent, count);
- xfs_trans_add_item(tp, &efip->efi_item);
- set_bit(XFS_LI_DIRTY, &efip->efi_item.li_flags);
+
return &efip->efi_item;
}
+const struct xfs_defer_op_type xfs_extent_free_defer_type = {
+ .name = "extent_free",
+ .max_items = XFS_EFI_MAX_FAST_EXTENTS,
+ .create_intent = xfs_extent_free_create_intent,
+ .abort_intent = xfs_extent_free_abort_intent,
+ .create_done = xfs_extent_free_create_done,
+ .finish_item = xfs_extent_free_finish_item,
+ .cancel_item = xfs_extent_free_cancel_item,
+ .recover_work = xfs_extent_free_recover_work,
+ .relog_intent = xfs_extent_free_relog_intent,
+};
+
+/* sub-type with special handling for AGFL deferred frees */
+const struct xfs_defer_op_type xfs_agfl_free_defer_type = {
+ .name = "agfl_free",
+ .max_items = XFS_EFI_MAX_FAST_EXTENTS,
+ .create_intent = xfs_extent_free_create_intent,
+ .abort_intent = xfs_extent_free_abort_intent,
+ .create_done = xfs_extent_free_create_done,
+ .finish_item = xfs_agfl_free_finish_item,
+ .cancel_item = xfs_extent_free_cancel_item,
+ .recover_work = xfs_extent_free_recover_work,
+ .relog_intent = xfs_extent_free_relog_intent,
+};
+
+STATIC bool
+xfs_efi_item_match(
+ struct xfs_log_item *lip,
+ uint64_t intent_id)
+{
+ return EFI_ITEM(lip)->efi_format.efi_id == intent_id;
+}
+
static const struct xfs_item_ops xfs_efi_item_ops = {
.flags = XFS_ITEM_INTENT,
.iop_size = xfs_efi_item_size,
.iop_format = xfs_efi_item_format,
.iop_unpin = xfs_efi_item_unpin,
.iop_release = xfs_efi_item_release,
- .iop_recover = xfs_efi_item_recover,
.iop_match = xfs_efi_item_match,
- .iop_relog = xfs_efi_item_relog,
};
/*
@@ -820,12 +745,9 @@ xlog_recover_efi_commit_pass2(
return error;
}
atomic_set(&efip->efi_next_extent, efi_formatp->efi_nextents);
- /*
- * Insert the intent into the AIL directly and drop one reference so
- * that finishing or canceling the work will drop the other.
- */
- xfs_trans_ail_insert(log->l_ailp, &efip->efi_item, lsn);
- xfs_efi_release(efip);
+
+ xlog_recover_intent_item(log, &efip->efi_item, lsn,
+ &xfs_extent_free_defer_type);
return 0;
}
diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index 57076a25f17d..83f708f62ed9 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -134,6 +134,10 @@ xfs_growfs_data_private(
if (delta < 0 && nagcount < 2)
return -EINVAL;
+ /* No work to do */
+ if (delta == 0)
+ return 0;
+
oagcount = mp->m_sb.sb_agcount;
/* allocate the new per-ag structures */
if (nagcount > oagcount) {
@@ -153,7 +157,7 @@ xfs_growfs_data_private(
error = xfs_trans_alloc(mp, &M_RES(mp)->tr_growdata, -delta, 0,
0, &tp);
if (error)
- return error;
+ goto out_free_unused_perag;
last_pag = xfs_perag_get(mp, oagcount - 1);
if (delta > 0) {
@@ -227,6 +231,9 @@ xfs_growfs_data_private(
out_trans_cancel:
xfs_trans_cancel(tp);
+out_free_unused_perag:
+ if (nagcount > oagcount)
+ xfs_free_unused_perag_range(mp, oagcount, nagcount);
return error;
}
@@ -344,59 +351,20 @@ xfs_growfs_log(
}
/*
- * exported through ioctl XFS_IOC_FSCOUNTS
- */
-
-void
-xfs_fs_counts(
- xfs_mount_t *mp,
- xfs_fsop_counts_t *cnt)
-{
- cnt->allocino = percpu_counter_read_positive(&mp->m_icount);
- cnt->freeino = percpu_counter_read_positive(&mp->m_ifree);
- cnt->freedata = percpu_counter_read_positive(&mp->m_fdblocks) -
- xfs_fdblocks_unavailable(mp);
- cnt->freertx = percpu_counter_read_positive(&mp->m_frextents);
-}
-
-/*
- * exported through ioctl XFS_IOC_SET_RESBLKS & XFS_IOC_GET_RESBLKS
- *
- * xfs_reserve_blocks is called to set m_resblks
- * in the in-core mount table. The number of unused reserved blocks
- * is kept in m_resblks_avail.
- *
* Reserve the requested number of blocks if available. Otherwise return
* as many as possible to satisfy the request. The actual number
- * reserved are returned in outval
- *
- * A null inval pointer indicates that only the current reserved blocks
- * available should be returned no settings are changed.
+ * reserved are returned in outval.
*/
-
int
xfs_reserve_blocks(
- xfs_mount_t *mp,
- uint64_t *inval,
- xfs_fsop_resblks_t *outval)
+ struct xfs_mount *mp,
+ uint64_t request)
{
int64_t lcounter, delta;
int64_t fdblks_delta = 0;
- uint64_t request;
int64_t free;
int error = 0;
- /* If inval is null, report current values and return */
- if (inval == (uint64_t *)NULL) {
- if (!outval)
- return -EINVAL;
- outval->resblks = mp->m_resblks;
- outval->resblks_avail = mp->m_resblks_avail;
- return 0;
- }
-
- request = *inval;
-
/*
* With per-cpu counters, this becomes an interesting problem. we need
* to work out if we are freeing or allocation blocks first, then we can
@@ -466,11 +434,6 @@ xfs_reserve_blocks(
spin_lock(&mp->m_sb_lock);
}
out:
- if (outval) {
- outval->resblks = mp->m_resblks;
- outval->resblks_avail = mp->m_resblks_avail;
- }
-
spin_unlock(&mp->m_sb_lock);
return error;
}
diff --git a/fs/xfs/xfs_fsops.h b/fs/xfs/xfs_fsops.h
index 2cffe51a31e8..44457b0a0593 100644
--- a/fs/xfs/xfs_fsops.h
+++ b/fs/xfs/xfs_fsops.h
@@ -6,14 +6,12 @@
#ifndef __XFS_FSOPS_H__
#define __XFS_FSOPS_H__
-extern int xfs_growfs_data(struct xfs_mount *mp, struct xfs_growfs_data *in);
-extern int xfs_growfs_log(struct xfs_mount *mp, struct xfs_growfs_log *in);
-extern void xfs_fs_counts(xfs_mount_t *mp, xfs_fsop_counts_t *cnt);
-extern int xfs_reserve_blocks(xfs_mount_t *mp, uint64_t *inval,
- xfs_fsop_resblks_t *outval);
-extern int xfs_fs_goingdown(xfs_mount_t *mp, uint32_t inflags);
+int xfs_growfs_data(struct xfs_mount *mp, struct xfs_growfs_data *in);
+int xfs_growfs_log(struct xfs_mount *mp, struct xfs_growfs_log *in);
+int xfs_reserve_blocks(struct xfs_mount *mp, uint64_t request);
+int xfs_fs_goingdown(struct xfs_mount *mp, uint32_t inflags);
-extern int xfs_fs_reserve_ag_blocks(struct xfs_mount *mp);
-extern int xfs_fs_unreserve_ag_blocks(struct xfs_mount *mp);
+int xfs_fs_reserve_ag_blocks(struct xfs_mount *mp);
+int xfs_fs_unreserve_ag_blocks(struct xfs_mount *mp);
#endif /* __XFS_FSOPS_H__ */
diff --git a/fs/xfs/xfs_globals.c b/fs/xfs/xfs_globals.c
index 9edc1f2bc939..f18fec0adf66 100644
--- a/fs/xfs/xfs_globals.c
+++ b/fs/xfs/xfs_globals.c
@@ -44,4 +44,16 @@ struct xfs_globals xfs_globals = {
.pwork_threads = -1, /* automatic thread detection */
.larp = false, /* log attribute replay */
#endif
+
+ /*
+ * Leave this many record slots empty when bulk loading btrees. By
+ * default we load new btree leaf blocks 75% full.
+ */
+ .bload_leaf_slack = -1,
+
+ /*
+ * Leave this many key/ptr slots empty when bulk loading btrees. By
+ * default we load new btree node blocks 75% full.
+ */
+ .bload_node_slack = -1,
};
diff --git a/fs/xfs/xfs_health.c b/fs/xfs/xfs_health.c
index 72a075bb2c10..9a57afee9338 100644
--- a/fs/xfs/xfs_health.c
+++ b/fs/xfs/xfs_health.c
@@ -222,7 +222,7 @@ xfs_inode_mark_sick(
struct xfs_inode *ip,
unsigned int mask)
{
- ASSERT(!(mask & ~XFS_SICK_INO_PRIMARY));
+ ASSERT(!(mask & ~(XFS_SICK_INO_PRIMARY | XFS_SICK_INO_ZAPPED)));
trace_xfs_inode_mark_sick(ip, mask);
spin_lock(&ip->i_flags_lock);
@@ -246,7 +246,7 @@ xfs_inode_mark_healthy(
struct xfs_inode *ip,
unsigned int mask)
{
- ASSERT(!(mask & ~XFS_SICK_INO_PRIMARY));
+ ASSERT(!(mask & ~(XFS_SICK_INO_PRIMARY | XFS_SICK_INO_ZAPPED)));
trace_xfs_inode_mark_healthy(ip, mask);
spin_lock(&ip->i_flags_lock);
@@ -369,6 +369,10 @@ static const struct ioctl_sick_map ino_map[] = {
{ XFS_SICK_INO_XATTR, XFS_BS_SICK_XATTR },
{ XFS_SICK_INO_SYMLINK, XFS_BS_SICK_SYMLINK },
{ XFS_SICK_INO_PARENT, XFS_BS_SICK_PARENT },
+ { XFS_SICK_INO_BMBTD_ZAPPED, XFS_BS_SICK_BMBTD },
+ { XFS_SICK_INO_BMBTA_ZAPPED, XFS_BS_SICK_BMBTA },
+ { XFS_SICK_INO_DIR_ZAPPED, XFS_BS_SICK_DIR },
+ { XFS_SICK_INO_SYMLINK_ZAPPED, XFS_BS_SICK_SYMLINK },
{ 0, 0 },
};
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index c0f1c89786c2..1fd94958aa97 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -37,15 +37,10 @@
#include "xfs_reflink.h"
#include "xfs_ag.h"
#include "xfs_log_priv.h"
+#include "xfs_health.h"
struct kmem_cache *xfs_inode_cache;
-/*
- * Used in xfs_itruncate_extents(). This is the maximum number of extents
- * freed from a file in a single transaction.
- */
-#define XFS_ITRUNC_MAX_EXTENTS 2
-
STATIC int xfs_iunlink(struct xfs_trans *, struct xfs_inode *);
STATIC int xfs_iunlink_remove(struct xfs_trans *tp, struct xfs_perag *pag,
struct xfs_inode *);
@@ -661,6 +656,8 @@ xfs_lookup(
if (xfs_is_shutdown(dp->i_mount))
return -EIO;
+ if (xfs_ifork_zapped(dp, XFS_DATA_FORK))
+ return -EIO;
error = xfs_dir_lookup(NULL, dp, name, &inum, ci_name);
if (error)
@@ -875,7 +872,7 @@ xfs_init_new_inode(
case S_IFLNK:
ip->i_df.if_format = XFS_DINODE_FMT_EXTENTS;
ip->i_df.if_bytes = 0;
- ip->i_df.if_u1.if_root = NULL;
+ ip->i_df.if_data = NULL;
break;
default:
ASSERT(0);
@@ -978,6 +975,8 @@ xfs_create(
if (xfs_is_shutdown(mp))
return -EIO;
+ if (xfs_ifork_zapped(dp, XFS_DATA_FORK))
+ return -EIO;
prid = xfs_get_initial_prid(dp);
@@ -1217,6 +1216,8 @@ xfs_link(
if (xfs_is_shutdown(mp))
return -EIO;
+ if (xfs_ifork_zapped(tdp, XFS_DATA_FORK))
+ return -EIO;
error = xfs_qm_dqattach(sip);
if (error)
@@ -1339,7 +1340,6 @@ xfs_itruncate_extents_flags(
struct xfs_mount *mp = ip->i_mount;
struct xfs_trans *tp = *tpp;
xfs_fileoff_t first_unmap_block;
- xfs_filblks_t unmap_len;
int error = 0;
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
@@ -1371,19 +1371,10 @@ xfs_itruncate_extents_flags(
return 0;
}
- unmap_len = XFS_MAX_FILEOFF - first_unmap_block + 1;
- while (unmap_len > 0) {
- ASSERT(tp->t_highest_agno == NULLAGNUMBER);
- error = __xfs_bunmapi(tp, ip, first_unmap_block, &unmap_len,
- flags, XFS_ITRUNC_MAX_EXTENTS);
- if (error)
- goto out;
-
- /* free the just unmapped extents */
- error = xfs_defer_finish(&tp);
- if (error)
- goto out;
- }
+ error = xfs_bunmapi_range(&tp, ip, flags, first_unmap_block,
+ XFS_MAX_FILEOFF);
+ if (error)
+ goto out;
if (whichfork == XFS_DATA_FORK) {
/* Remove all pending CoW reservations. */
@@ -2387,8 +2378,8 @@ xfs_ifree(
* already been freed by xfs_attr_inactive.
*/
if (ip->i_df.if_format == XFS_DINODE_FMT_LOCAL) {
- kmem_free(ip->i_df.if_u1.if_data);
- ip->i_df.if_u1.if_data = NULL;
+ kmem_free(ip->i_df.if_data);
+ ip->i_df.if_data = NULL;
ip->i_df.if_bytes = 0;
}
@@ -2506,6 +2497,8 @@ xfs_remove(
if (xfs_is_shutdown(mp))
return -EIO;
+ if (xfs_ifork_zapped(dp, XFS_DATA_FORK))
+ return -EIO;
error = xfs_qm_dqattach(dp);
if (error)
@@ -3758,3 +3751,29 @@ xfs_inode_reload_unlinked(
return error;
}
+
+/* Has this inode fork been zapped by repair? */
+bool
+xfs_ifork_zapped(
+ const struct xfs_inode *ip,
+ int whichfork)
+{
+ unsigned int datamask = 0;
+
+ switch (whichfork) {
+ case XFS_DATA_FORK:
+ switch (ip->i_vnode.i_mode & S_IFMT) {
+ case S_IFDIR:
+ datamask = XFS_SICK_INO_DIR_ZAPPED;
+ break;
+ case S_IFLNK:
+ datamask = XFS_SICK_INO_SYMLINK_ZAPPED;
+ break;
+ }
+ return ip->i_sick & (XFS_SICK_INO_BMBTD_ZAPPED | datamask);
+ case XFS_ATTR_FORK:
+ return ip->i_sick & XFS_SICK_INO_BMBTA_ZAPPED;
+ default:
+ return false;
+ }
+}
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 3beb470f1892..97f63bacd4c2 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -622,4 +622,6 @@ xfs_inode_unlinked_incomplete(
int xfs_inode_reload_unlinked_bucket(struct xfs_trans *tp, struct xfs_inode *ip);
int xfs_inode_reload_unlinked(struct xfs_inode *ip);
+bool xfs_ifork_zapped(const struct xfs_inode *ip, int whichfork);
+
#endif /* __XFS_INODE_H__ */
diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c
index cd7803fda8b1..0aee97ba0be8 100644
--- a/fs/xfs/xfs_inode_item.c
+++ b/fs/xfs/xfs_inode_item.c
@@ -352,11 +352,10 @@ xfs_inode_item_format_data_fork(
~(XFS_ILOG_DEXT | XFS_ILOG_DBROOT | XFS_ILOG_DEV);
if ((iip->ili_fields & XFS_ILOG_DDATA) &&
ip->i_df.if_bytes > 0) {
- ASSERT(ip->i_df.if_u1.if_data != NULL);
+ ASSERT(ip->i_df.if_data != NULL);
ASSERT(ip->i_disk_size > 0);
xlog_copy_iovec(lv, vecp, XLOG_REG_TYPE_ILOCAL,
- ip->i_df.if_u1.if_data,
- ip->i_df.if_bytes);
+ ip->i_df.if_data, ip->i_df.if_bytes);
ilf->ilf_dsize = (unsigned)ip->i_df.if_bytes;
ilf->ilf_size++;
} else {
@@ -431,10 +430,9 @@ xfs_inode_item_format_attr_fork(
if ((iip->ili_fields & XFS_ILOG_ADATA) &&
ip->i_af.if_bytes > 0) {
- ASSERT(ip->i_af.if_u1.if_data != NULL);
+ ASSERT(ip->i_af.if_data != NULL);
xlog_copy_iovec(lv, vecp, XLOG_REG_TYPE_IATTR_LOCAL,
- ip->i_af.if_u1.if_data,
- ip->i_af.if_bytes);
+ ip->i_af.if_data, ip->i_af.if_bytes);
ilf->ilf_asize = (unsigned)ip->i_af.if_bytes;
ilf->ilf_size++;
} else {
@@ -557,6 +555,9 @@ xfs_inode_to_log_dinode(
memset(to->di_pad2, 0, sizeof(to->di_pad2));
uuid_copy(&to->di_uuid, &ip->i_mount->m_sb.sb_meta_uuid);
to->di_v3_pad = 0;
+
+ /* dummy value for initialisation */
+ to->di_crc = 0;
} else {
to->di_version = 2;
to->di_flushiter = ip->i_flushiter;
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index 6c3919687ea6..f02b6e558af5 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -1872,6 +1872,63 @@ xfs_fs_eofblocks_from_user(
return 0;
}
+static int
+xfs_ioctl_getset_resblocks(
+ struct file *filp,
+ unsigned int cmd,
+ void __user *arg)
+{
+ struct xfs_mount *mp = XFS_I(file_inode(filp))->i_mount;
+ struct xfs_fsop_resblks fsop = { };
+ int error;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ if (cmd == XFS_IOC_SET_RESBLKS) {
+ if (xfs_is_readonly(mp))
+ return -EROFS;
+
+ if (copy_from_user(&fsop, arg, sizeof(fsop)))
+ return -EFAULT;
+
+ error = mnt_want_write_file(filp);
+ if (error)
+ return error;
+ error = xfs_reserve_blocks(mp, fsop.resblks);
+ mnt_drop_write_file(filp);
+ if (error)
+ return error;
+ }
+
+ spin_lock(&mp->m_sb_lock);
+ fsop.resblks = mp->m_resblks;
+ fsop.resblks_avail = mp->m_resblks_avail;
+ spin_unlock(&mp->m_sb_lock);
+
+ if (copy_to_user(arg, &fsop, sizeof(fsop)))
+ return -EFAULT;
+ return 0;
+}
+
+static int
+xfs_ioctl_fs_counts(
+ struct xfs_mount *mp,
+ struct xfs_fsop_counts __user *uarg)
+{
+ struct xfs_fsop_counts out = {
+ .allocino = percpu_counter_read_positive(&mp->m_icount),
+ .freeino = percpu_counter_read_positive(&mp->m_ifree),
+ .freedata = percpu_counter_read_positive(&mp->m_fdblocks) -
+ xfs_fdblocks_unavailable(mp),
+ .freertx = percpu_counter_read_positive(&mp->m_frextents),
+ };
+
+ if (copy_to_user(uarg, &out, sizeof(out)))
+ return -EFAULT;
+ return 0;
+}
+
/*
* These long-unused ioctls were removed from the official ioctl API in 5.17,
* but retain these definitions so that we can log warnings about them.
@@ -2008,60 +2065,12 @@ xfs_file_ioctl(
return error;
}
- case XFS_IOC_FSCOUNTS: {
- xfs_fsop_counts_t out;
+ case XFS_IOC_FSCOUNTS:
+ return xfs_ioctl_fs_counts(mp, arg);
- xfs_fs_counts(mp, &out);
-
- if (copy_to_user(arg, &out, sizeof(out)))
- return -EFAULT;
- return 0;
- }
-
- case XFS_IOC_SET_RESBLKS: {
- xfs_fsop_resblks_t inout;
- uint64_t in;
-
- if (!capable(CAP_SYS_ADMIN))
- return -EPERM;
-
- if (xfs_is_readonly(mp))
- return -EROFS;
-
- if (copy_from_user(&inout, arg, sizeof(inout)))
- return -EFAULT;
-
- error = mnt_want_write_file(filp);
- if (error)
- return error;
-
- /* input parameter is passed in resblks field of structure */
- in = inout.resblks;
- error = xfs_reserve_blocks(mp, &in, &inout);
- mnt_drop_write_file(filp);
- if (error)
- return error;
-
- if (copy_to_user(arg, &inout, sizeof(inout)))
- return -EFAULT;
- return 0;
- }
-
- case XFS_IOC_GET_RESBLKS: {
- xfs_fsop_resblks_t out;
-
- if (!capable(CAP_SYS_ADMIN))
- return -EPERM;
-
- error = xfs_reserve_blocks(mp, NULL, &out);
- if (error)
- return error;
-
- if (copy_to_user(arg, &out, sizeof(out)))
- return -EFAULT;
-
- return 0;
- }
+ case XFS_IOC_SET_RESBLKS:
+ case XFS_IOC_GET_RESBLKS:
+ return xfs_ioctl_getset_resblocks(filp, cmd, arg);
case XFS_IOC_FSGROWFSDATA: {
struct xfs_growfs_data in;
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index ee206facf0dc..a1650fc81382 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -1542,6 +1542,7 @@ xlog_alloc_log(
log->l_covered_state = XLOG_STATE_COVER_IDLE;
set_bit(XLOG_ACTIVE_RECOVERY, &log->l_opstate);
INIT_DELAYED_WORK(&log->l_work, xfs_log_worker);
+ INIT_LIST_HEAD(&log->r_dfops);
log->l_prev_block = -1;
/* log->l_tail_lsn = 0x100000000LL; cycle = 1; current block = 0 */
diff --git a/fs/xfs/xfs_log_priv.h b/fs/xfs/xfs_log_priv.h
index fa3ad1d7b31c..e30c06ec20e3 100644
--- a/fs/xfs/xfs_log_priv.h
+++ b/fs/xfs/xfs_log_priv.h
@@ -407,6 +407,7 @@ struct xlog {
long l_opstate; /* operational state */
uint l_quotaoffs_flag; /* XFS_DQ_*, for QUOTAOFFs */
struct list_head *l_buf_cancel_table;
+ struct list_head r_dfops; /* recovered log intent items */
int l_iclog_hsize; /* size of iclog header */
int l_iclog_heads; /* # of iclog header sectors */
uint l_sectBBsize; /* sector size in BBs (2^n) */
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index a1e18b24971a..1251c81e55f9 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -1723,30 +1723,24 @@ xlog_clear_stale_blocks(
*/
void
xlog_recover_release_intent(
- struct xlog *log,
- unsigned short intent_type,
- uint64_t intent_id)
+ struct xlog *log,
+ unsigned short intent_type,
+ uint64_t intent_id)
{
- struct xfs_ail_cursor cur;
- struct xfs_log_item *lip;
- struct xfs_ail *ailp = log->l_ailp;
+ struct xfs_defer_pending *dfp, *n;
+
+ list_for_each_entry_safe(dfp, n, &log->r_dfops, dfp_list) {
+ struct xfs_log_item *lip = dfp->dfp_intent;
- spin_lock(&ailp->ail_lock);
- for (lip = xfs_trans_ail_cursor_first(ailp, &cur, 0); lip != NULL;
- lip = xfs_trans_ail_cursor_next(ailp, &cur)) {
if (lip->li_type != intent_type)
continue;
if (!lip->li_ops->iop_match(lip, intent_id))
continue;
- spin_unlock(&ailp->ail_lock);
- lip->li_ops->iop_release(lip);
- spin_lock(&ailp->ail_lock);
- break;
- }
+ ASSERT(xlog_item_is_intent(lip));
- xfs_trans_ail_cursor_done(&cur);
- spin_unlock(&ailp->ail_lock);
+ xfs_defer_cancel_recovery(log->l_mp, dfp);
+ }
}
int
@@ -1939,6 +1933,29 @@ xlog_buf_readahead(
xfs_buf_readahead(log->l_mp->m_ddev_targp, blkno, len, ops);
}
+/*
+ * Create a deferred work structure for resuming and tracking the progress of a
+ * log intent item that was found during recovery.
+ */
+void
+xlog_recover_intent_item(
+ struct xlog *log,
+ struct xfs_log_item *lip,
+ xfs_lsn_t lsn,
+ const struct xfs_defer_op_type *ops)
+{
+ ASSERT(xlog_item_is_intent(lip));
+
+ xfs_defer_start_recovery(lip, &log->r_dfops, ops);
+
+ /*
+ * Insert the intent into the AIL directly and drop one reference so
+ * that finishing or canceling the work will drop the other.
+ */
+ xfs_trans_ail_insert(log->l_ailp, lip, lsn);
+ lip->li_ops->iop_unpin(lip, 0);
+}
+
STATIC int
xlog_recover_items_pass2(
struct xlog *log,
@@ -2533,36 +2550,26 @@ xlog_abort_defer_ops(
*/
STATIC int
xlog_recover_process_intents(
- struct xlog *log)
+ struct xlog *log)
{
LIST_HEAD(capture_list);
- struct xfs_ail_cursor cur;
- struct xfs_log_item *lip;
- struct xfs_ail *ailp;
- int error = 0;
+ struct xfs_defer_pending *dfp, *n;
+ int error = 0;
#if defined(DEBUG) || defined(XFS_WARN)
- xfs_lsn_t last_lsn;
-#endif
+ xfs_lsn_t last_lsn;
- ailp = log->l_ailp;
- spin_lock(&ailp->ail_lock);
-#if defined(DEBUG) || defined(XFS_WARN)
last_lsn = xlog_assign_lsn(log->l_curr_cycle, log->l_curr_block);
#endif
- for (lip = xfs_trans_ail_cursor_first(ailp, &cur, 0);
- lip != NULL;
- lip = xfs_trans_ail_cursor_next(ailp, &cur)) {
- const struct xfs_item_ops *ops;
- if (!xlog_item_is_intent(lip))
- break;
+ list_for_each_entry_safe(dfp, n, &log->r_dfops, dfp_list) {
+ ASSERT(xlog_item_is_intent(dfp->dfp_intent));
/*
* We should never see a redo item with a LSN higher than
* the last transaction we found in the log at the start
* of recovery.
*/
- ASSERT(XFS_LSN_CMP(last_lsn, lip->li_lsn) >= 0);
+ ASSERT(XFS_LSN_CMP(last_lsn, dfp->dfp_intent->li_lsn) >= 0);
/*
* NOTE: If your intent processing routine can create more
@@ -2571,21 +2578,14 @@ xlog_recover_process_intents(
* replayed in the wrong order!
*
* The recovery function can free the log item, so we must not
- * access lip after it returns.
+ * access dfp->dfp_intent after it returns. It must dispose of
+ * @dfp if it returns 0.
*/
- spin_unlock(&ailp->ail_lock);
- ops = lip->li_ops;
- error = ops->iop_recover(lip, &capture_list);
- spin_lock(&ailp->ail_lock);
- if (error) {
- trace_xlog_intent_recovery_failed(log->l_mp, error,
- ops->iop_recover);
+ error = xfs_defer_finish_recovery(log->l_mp, dfp,
+ &capture_list);
+ if (error)
break;
- }
}
-
- xfs_trans_ail_cursor_done(&cur);
- spin_unlock(&ailp->ail_lock);
if (error)
goto err;
@@ -2606,27 +2606,34 @@ err:
*/
STATIC void
xlog_recover_cancel_intents(
- struct xlog *log)
+ struct xlog *log)
{
- struct xfs_log_item *lip;
- struct xfs_ail_cursor cur;
- struct xfs_ail *ailp;
-
- ailp = log->l_ailp;
- spin_lock(&ailp->ail_lock);
- lip = xfs_trans_ail_cursor_first(ailp, &cur, 0);
- while (lip != NULL) {
- if (!xlog_item_is_intent(lip))
- break;
+ struct xfs_defer_pending *dfp, *n;
- spin_unlock(&ailp->ail_lock);
- lip->li_ops->iop_release(lip);
- spin_lock(&ailp->ail_lock);
- lip = xfs_trans_ail_cursor_next(ailp, &cur);
+ list_for_each_entry_safe(dfp, n, &log->r_dfops, dfp_list) {
+ ASSERT(xlog_item_is_intent(dfp->dfp_intent));
+
+ xfs_defer_cancel_recovery(log->l_mp, dfp);
}
+}
- xfs_trans_ail_cursor_done(&cur);
- spin_unlock(&ailp->ail_lock);
+/*
+ * Transfer ownership of the recovered pending work to the recovery transaction
+ * and try to finish the work. If there is more work to be done, the dfp will
+ * remain attached to the transaction. If not, the dfp is freed.
+ */
+int
+xlog_recover_finish_intent(
+ struct xfs_trans *tp,
+ struct xfs_defer_pending *dfp)
+{
+ int error;
+
+ list_move(&dfp->dfp_list, &tp->t_dfops);
+ error = xfs_defer_finish_one(tp, dfp);
+ if (error == -EAGAIN)
+ return 0;
+ return error;
}
/*
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index aed5be5508fe..aabb25dc3efa 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -637,7 +637,6 @@ xfs_mountfs(
struct xfs_sb *sbp = &(mp->m_sb);
struct xfs_inode *rip;
struct xfs_ino_geometry *igeo = M_IGEO(mp);
- uint64_t resblks;
uint quotamount = 0;
uint quotaflags = 0;
int error = 0;
@@ -974,8 +973,7 @@ xfs_mountfs(
* we were already there on the last unmount. Warn if this occurs.
*/
if (!xfs_is_readonly(mp)) {
- resblks = xfs_default_resblks(mp);
- error = xfs_reserve_blocks(mp, &resblks, NULL);
+ error = xfs_reserve_blocks(mp, xfs_default_resblks(mp));
if (error)
xfs_warn(mp,
"Unable to allocate reserve blocks. Continuing without reserve pool.");
@@ -1053,7 +1051,6 @@ void
xfs_unmountfs(
struct xfs_mount *mp)
{
- uint64_t resblks;
int error;
/*
@@ -1090,8 +1087,7 @@ xfs_unmountfs(
* we only every apply deltas to the superblock and hence the incore
* value does not matter....
*/
- resblks = 0;
- error = xfs_reserve_blocks(mp, &resblks, NULL);
+ error = xfs_reserve_blocks(mp, 0);
if (error)
xfs_warn(mp, "Unable to free reserved block pool. "
"Freespace may not be correct on next mount.");
diff --git a/fs/xfs/xfs_notify_failure.c b/fs/xfs/xfs_notify_failure.c
index a7daa522e00f..fa50e5308292 100644
--- a/fs/xfs/xfs_notify_failure.c
+++ b/fs/xfs/xfs_notify_failure.c
@@ -22,6 +22,7 @@
#include <linux/mm.h>
#include <linux/dax.h>
+#include <linux/fs.h>
struct xfs_failure_info {
xfs_agblock_t startblock;
@@ -73,10 +74,16 @@ xfs_dax_failure_fn(
struct xfs_mount *mp = cur->bc_mp;
struct xfs_inode *ip;
struct xfs_failure_info *notify = data;
+ struct address_space *mapping;
+ pgoff_t pgoff;
+ unsigned long pgcnt;
int error = 0;
if (XFS_RMAP_NON_INODE_OWNER(rec->rm_owner) ||
(rec->rm_flags & (XFS_RMAP_ATTR_FORK | XFS_RMAP_BMBT_BLOCK))) {
+ /* Continue the query because this isn't a failure. */
+ if (notify->mf_flags & MF_MEM_PRE_REMOVE)
+ return 0;
notify->want_shutdown = true;
return 0;
}
@@ -92,15 +99,61 @@ xfs_dax_failure_fn(
return 0;
}
- error = mf_dax_kill_procs(VFS_I(ip)->i_mapping,
- xfs_failure_pgoff(mp, rec, notify),
- xfs_failure_pgcnt(mp, rec, notify),
- notify->mf_flags);
+ mapping = VFS_I(ip)->i_mapping;
+ pgoff = xfs_failure_pgoff(mp, rec, notify);
+ pgcnt = xfs_failure_pgcnt(mp, rec, notify);
+
+ /* Continue the rmap query if the inode isn't a dax file. */
+ if (dax_mapping(mapping))
+ error = mf_dax_kill_procs(mapping, pgoff, pgcnt,
+ notify->mf_flags);
+
+ /* Invalidate the cache in dax pages. */
+ if (notify->mf_flags & MF_MEM_PRE_REMOVE)
+ invalidate_inode_pages2_range(mapping, pgoff,
+ pgoff + pgcnt - 1);
+
xfs_irele(ip);
return error;
}
static int
+xfs_dax_notify_failure_freeze(
+ struct xfs_mount *mp)
+{
+ struct super_block *sb = mp->m_super;
+ int error;
+
+ error = freeze_super(sb, FREEZE_HOLDER_KERNEL);
+ if (error)
+ xfs_emerg(mp, "already frozen by kernel, err=%d", error);
+
+ return error;
+}
+
+static void
+xfs_dax_notify_failure_thaw(
+ struct xfs_mount *mp,
+ bool kernel_frozen)
+{
+ struct super_block *sb = mp->m_super;
+ int error;
+
+ if (kernel_frozen) {
+ error = thaw_super(sb, FREEZE_HOLDER_KERNEL);
+ if (error)
+ xfs_emerg(mp, "still frozen after notify failure, err=%d",
+ error);
+ }
+
+ /*
+ * Also thaw userspace call anyway because the device is about to be
+ * removed immediately.
+ */
+ thaw_super(sb, FREEZE_HOLDER_USERSPACE);
+}
+
+static int
xfs_dax_notify_ddev_failure(
struct xfs_mount *mp,
xfs_daddr_t daddr,
@@ -112,15 +165,29 @@ xfs_dax_notify_ddev_failure(
struct xfs_btree_cur *cur = NULL;
struct xfs_buf *agf_bp = NULL;
int error = 0;
+ bool kernel_frozen = false;
xfs_fsblock_t fsbno = XFS_DADDR_TO_FSB(mp, daddr);
xfs_agnumber_t agno = XFS_FSB_TO_AGNO(mp, fsbno);
xfs_fsblock_t end_fsbno = XFS_DADDR_TO_FSB(mp,
daddr + bblen - 1);
xfs_agnumber_t end_agno = XFS_FSB_TO_AGNO(mp, end_fsbno);
+ if (mf_flags & MF_MEM_PRE_REMOVE) {
+ xfs_info(mp, "Device is about to be removed!");
+ /*
+ * Freeze fs to prevent new mappings from being created.
+ * - Keep going on if others already hold the kernel forzen.
+ * - Keep going on if other errors too because this device is
+ * starting to fail.
+ * - If kernel frozen state is hold successfully here, thaw it
+ * here as well at the end.
+ */
+ kernel_frozen = xfs_dax_notify_failure_freeze(mp) == 0;
+ }
+
error = xfs_trans_alloc_empty(mp, &tp);
if (error)
- return error;
+ goto out;
for (; agno <= end_agno; agno++) {
struct xfs_rmap_irec ri_low = { };
@@ -165,11 +232,26 @@ xfs_dax_notify_ddev_failure(
}
xfs_trans_cancel(tp);
- if (error || notify.want_shutdown) {
+
+ /*
+ * Shutdown fs from a force umount in pre-remove case which won't fail,
+ * so errors can be ignored. Otherwise, shutdown the filesystem with
+ * CORRUPT flag if error occured or notify.want_shutdown was set during
+ * RMAP querying.
+ */
+ if (mf_flags & MF_MEM_PRE_REMOVE)
+ xfs_force_shutdown(mp, SHUTDOWN_FORCE_UMOUNT);
+ else if (error || notify.want_shutdown) {
xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_ONDISK);
if (!error)
error = -EFSCORRUPTED;
}
+
+out:
+ /* Thaw the fs if it has been frozen before. */
+ if (mf_flags & MF_MEM_PRE_REMOVE)
+ xfs_dax_notify_failure_thaw(mp, kernel_frozen);
+
return error;
}
@@ -197,6 +279,14 @@ xfs_dax_notify_failure(
if (mp->m_logdev_targp && mp->m_logdev_targp->bt_daxdev == dax_dev &&
mp->m_logdev_targp != mp->m_ddev_targp) {
+ /*
+ * In the pre-remove case the failure notification is attempting
+ * to trigger a force unmount. The expectation is that the
+ * device is still present, but its removal is in progress and
+ * can not be cancelled, proceed with accessing the log device.
+ */
+ if (mf_flags & MF_MEM_PRE_REMOVE)
+ return 0;
xfs_err(mp, "ondisk log corrupt, shutting down fs!");
xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_ONDISK);
return -EFSCORRUPTED;
@@ -210,6 +300,12 @@ xfs_dax_notify_failure(
ddev_start = mp->m_ddev_targp->bt_dax_part_off;
ddev_end = ddev_start + bdev_nr_bytes(mp->m_ddev_targp->bt_bdev) - 1;
+ /* Notify failure on the whole device. */
+ if (offset == 0 && len == U64_MAX) {
+ offset = ddev_start;
+ len = bdev_nr_bytes(mp->m_ddev_targp->bt_bdev);
+ }
+
/* Ignore the range out of filesystem area */
if (offset + len - 1 < ddev_start)
return -ENXIO;
diff --git a/fs/xfs/xfs_quota.h b/fs/xfs/xfs_quota.h
index dcc785fdd345..e0d56489f3b2 100644
--- a/fs/xfs/xfs_quota.h
+++ b/fs/xfs/xfs_quota.h
@@ -127,7 +127,10 @@ xfs_qm_vop_dqalloc(struct xfs_inode *ip, kuid_t kuid, kgid_t kgid,
}
#define xfs_trans_dup_dqinfo(tp, tp2)
#define xfs_trans_free_dqinfo(tp)
-#define xfs_trans_mod_dquot_byino(tp, ip, fields, delta) do { } while (0)
+static inline void xfs_trans_mod_dquot_byino(struct xfs_trans *tp,
+ struct xfs_inode *ip, uint field, int64_t delta)
+{
+}
#define xfs_trans_apply_dquot_deltas(tp)
#define xfs_trans_unreserve_and_mod_dquots(tp)
static inline int xfs_trans_reserve_quota_nblks(struct xfs_trans *tp,
diff --git a/fs/xfs/xfs_refcount_item.c b/fs/xfs/xfs_refcount_item.c
index 2d4444d61e98..20ad8086da60 100644
--- a/fs/xfs/xfs_refcount_item.c
+++ b/fs/xfs/xfs_refcount_item.c
@@ -227,52 +227,6 @@ static const struct xfs_item_ops xfs_cud_item_ops = {
.iop_intent = xfs_cud_item_intent,
};
-static struct xfs_cud_log_item *
-xfs_trans_get_cud(
- struct xfs_trans *tp,
- struct xfs_cui_log_item *cuip)
-{
- struct xfs_cud_log_item *cudp;
-
- cudp = kmem_cache_zalloc(xfs_cud_cache, GFP_KERNEL | __GFP_NOFAIL);
- xfs_log_item_init(tp->t_mountp, &cudp->cud_item, XFS_LI_CUD,
- &xfs_cud_item_ops);
- cudp->cud_cuip = cuip;
- cudp->cud_format.cud_cui_id = cuip->cui_format.cui_id;
-
- xfs_trans_add_item(tp, &cudp->cud_item);
- return cudp;
-}
-
-/*
- * Finish an refcount update and log it to the CUD. Note that the
- * transaction is marked dirty regardless of whether the refcount
- * update succeeds or fails to support the CUI/CUD lifecycle rules.
- */
-static int
-xfs_trans_log_finish_refcount_update(
- struct xfs_trans *tp,
- struct xfs_cud_log_item *cudp,
- struct xfs_refcount_intent *ri,
- struct xfs_btree_cur **pcur)
-{
- int error;
-
- error = xfs_refcount_finish_one(tp, ri, pcur);
-
- /*
- * Mark the transaction dirty, even on error. This ensures the
- * transaction is aborted, which:
- *
- * 1.) releases the CUI and frees the CUD
- * 2.) shuts down the filesystem
- */
- tp->t_flags |= XFS_TRANS_DIRTY | XFS_TRANS_HAS_INTENT_DONE;
- set_bit(XFS_LI_DIRTY, &cudp->cud_item.li_flags);
-
- return error;
-}
-
/* Sort refcount intents by AG. */
static int
xfs_refcount_update_diff_items(
@@ -318,9 +272,6 @@ xfs_refcount_update_log_item(
uint next_extent;
struct xfs_phys_extent *pmap;
- tp->t_flags |= XFS_TRANS_DIRTY;
- set_bit(XFS_LI_DIRTY, &cuip->cui_item.li_flags);
-
/*
* atomic_inc_return gives us the value after the increment;
* we want to use it as an array index so we need to subtract 1 from
@@ -347,7 +298,6 @@ xfs_refcount_update_create_intent(
ASSERT(count > 0);
- xfs_trans_add_item(tp, &cuip->cui_item);
if (sort)
list_sort(mp, items, xfs_refcount_update_diff_items);
list_for_each_entry(ri, items, ri_list)
@@ -362,7 +312,16 @@ xfs_refcount_update_create_done(
struct xfs_log_item *intent,
unsigned int count)
{
- return &xfs_trans_get_cud(tp, CUI_ITEM(intent))->cud_item;
+ struct xfs_cui_log_item *cuip = CUI_ITEM(intent);
+ struct xfs_cud_log_item *cudp;
+
+ cudp = kmem_cache_zalloc(xfs_cud_cache, GFP_KERNEL | __GFP_NOFAIL);
+ xfs_log_item_init(tp->t_mountp, &cudp->cud_item, XFS_LI_CUD,
+ &xfs_cud_item_ops);
+ cudp->cud_cuip = cuip;
+ cudp->cud_format.cud_cui_id = cuip->cui_format.cui_id;
+
+ return &cudp->cud_item;
}
/* Take a passive ref to the AG containing the space we're refcounting. */
@@ -397,10 +356,9 @@ xfs_refcount_update_finish_item(
int error;
ri = container_of(item, struct xfs_refcount_intent, ri_list);
- error = xfs_trans_log_finish_refcount_update(tp, CUD_ITEM(done), ri,
- state);
/* Did we run out of reservation? Requeue what we didn't finish. */
+ error = xfs_refcount_finish_one(tp, ri, state);
if (!error && ri->ri_blockcount > 0) {
ASSERT(ri->ri_type == XFS_REFCOUNT_INCREASE ||
ri->ri_type == XFS_REFCOUNT_DECREASE);
@@ -433,16 +391,6 @@ xfs_refcount_update_cancel_item(
kmem_cache_free(xfs_refcount_intent_cache, ri);
}
-const struct xfs_defer_op_type xfs_refcount_update_defer_type = {
- .max_items = XFS_CUI_MAX_FAST_EXTENTS,
- .create_intent = xfs_refcount_update_create_intent,
- .abort_intent = xfs_refcount_update_abort_intent,
- .create_done = xfs_refcount_update_create_done,
- .finish_item = xfs_refcount_update_finish_item,
- .finish_cleanup = xfs_refcount_finish_one_cleanup,
- .cancel_item = xfs_refcount_update_cancel_item,
-};
-
/* Is this recovered CUI ok? */
static inline bool
xfs_cui_validate_phys(
@@ -468,23 +416,38 @@ xfs_cui_validate_phys(
return xfs_verify_fsbext(mp, pmap->pe_startblock, pmap->pe_len);
}
+static inline void
+xfs_cui_recover_work(
+ struct xfs_mount *mp,
+ struct xfs_defer_pending *dfp,
+ struct xfs_phys_extent *pmap)
+{
+ struct xfs_refcount_intent *ri;
+
+ ri = kmem_cache_alloc(xfs_refcount_intent_cache,
+ GFP_NOFS | __GFP_NOFAIL);
+ ri->ri_type = pmap->pe_flags & XFS_REFCOUNT_EXTENT_TYPE_MASK;
+ ri->ri_startblock = pmap->pe_startblock;
+ ri->ri_blockcount = pmap->pe_len;
+ xfs_refcount_update_get_group(mp, ri);
+
+ xfs_defer_add_item(dfp, &ri->ri_list);
+}
+
/*
* Process a refcount update intent item that was recovered from the log.
* We need to update the refcountbt.
*/
STATIC int
-xfs_cui_item_recover(
- struct xfs_log_item *lip,
+xfs_refcount_recover_work(
+ struct xfs_defer_pending *dfp,
struct list_head *capture_list)
{
struct xfs_trans_res resv;
+ struct xfs_log_item *lip = dfp->dfp_intent;
struct xfs_cui_log_item *cuip = CUI_ITEM(lip);
- struct xfs_cud_log_item *cudp;
struct xfs_trans *tp;
- struct xfs_btree_cur *rcur = NULL;
struct xfs_mount *mp = lip->li_log->l_mp;
- unsigned int refc_type;
- bool requeue_only = false;
int i;
int error = 0;
@@ -501,6 +464,8 @@ xfs_cui_item_recover(
sizeof(cuip->cui_format));
return -EFSCORRUPTED;
}
+
+ xfs_cui_recover_work(mp, dfp, &cuip->cui_format.cui_extents[i]);
}
/*
@@ -521,100 +486,28 @@ xfs_cui_item_recover(
if (error)
return error;
- cudp = xfs_trans_get_cud(tp, cuip);
-
- for (i = 0; i < cuip->cui_format.cui_nextents; i++) {
- struct xfs_refcount_intent fake = { };
- struct xfs_phys_extent *pmap;
-
- pmap = &cuip->cui_format.cui_extents[i];
- refc_type = pmap->pe_flags & XFS_REFCOUNT_EXTENT_TYPE_MASK;
- switch (refc_type) {
- case XFS_REFCOUNT_INCREASE:
- case XFS_REFCOUNT_DECREASE:
- case XFS_REFCOUNT_ALLOC_COW:
- case XFS_REFCOUNT_FREE_COW:
- fake.ri_type = refc_type;
- break;
- default:
- XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
- &cuip->cui_format,
- sizeof(cuip->cui_format));
- error = -EFSCORRUPTED;
- goto abort_error;
- }
-
- fake.ri_startblock = pmap->pe_startblock;
- fake.ri_blockcount = pmap->pe_len;
-
- if (!requeue_only) {
- xfs_refcount_update_get_group(mp, &fake);
- error = xfs_trans_log_finish_refcount_update(tp, cudp,
- &fake, &rcur);
- xfs_refcount_update_put_group(&fake);
- }
- if (error == -EFSCORRUPTED)
- XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
- &cuip->cui_format,
- sizeof(cuip->cui_format));
- if (error)
- goto abort_error;
-
- /* Requeue what we didn't finish. */
- if (fake.ri_blockcount > 0) {
- struct xfs_bmbt_irec irec = {
- .br_startblock = fake.ri_startblock,
- .br_blockcount = fake.ri_blockcount,
- };
-
- switch (fake.ri_type) {
- case XFS_REFCOUNT_INCREASE:
- xfs_refcount_increase_extent(tp, &irec);
- break;
- case XFS_REFCOUNT_DECREASE:
- xfs_refcount_decrease_extent(tp, &irec);
- break;
- case XFS_REFCOUNT_ALLOC_COW:
- xfs_refcount_alloc_cow_extent(tp,
- irec.br_startblock,
- irec.br_blockcount);
- break;
- case XFS_REFCOUNT_FREE_COW:
- xfs_refcount_free_cow_extent(tp,
- irec.br_startblock,
- irec.br_blockcount);
- break;
- default:
- ASSERT(0);
- }
- requeue_only = true;
- }
- }
+ error = xlog_recover_finish_intent(tp, dfp);
+ if (error == -EFSCORRUPTED)
+ XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
+ &cuip->cui_format,
+ sizeof(cuip->cui_format));
+ if (error)
+ goto abort_error;
- xfs_refcount_finish_one_cleanup(tp, rcur, error);
return xfs_defer_ops_capture_and_commit(tp, capture_list);
abort_error:
- xfs_refcount_finish_one_cleanup(tp, rcur, error);
xfs_trans_cancel(tp);
return error;
}
-STATIC bool
-xfs_cui_item_match(
- struct xfs_log_item *lip,
- uint64_t intent_id)
-{
- return CUI_ITEM(lip)->cui_format.cui_id == intent_id;
-}
-
/* Relog an intent item to push the log tail forward. */
static struct xfs_log_item *
-xfs_cui_item_relog(
+xfs_refcount_relog_intent(
+ struct xfs_trans *tp,
struct xfs_log_item *intent,
- struct xfs_trans *tp)
+ struct xfs_log_item *done_item)
{
- struct xfs_cud_log_item *cudp;
struct xfs_cui_log_item *cuip;
struct xfs_phys_extent *pmap;
unsigned int count;
@@ -622,27 +515,41 @@ xfs_cui_item_relog(
count = CUI_ITEM(intent)->cui_format.cui_nextents;
pmap = CUI_ITEM(intent)->cui_format.cui_extents;
- tp->t_flags |= XFS_TRANS_DIRTY;
- cudp = xfs_trans_get_cud(tp, CUI_ITEM(intent));
- set_bit(XFS_LI_DIRTY, &cudp->cud_item.li_flags);
-
cuip = xfs_cui_init(tp->t_mountp, count);
memcpy(cuip->cui_format.cui_extents, pmap, count * sizeof(*pmap));
atomic_set(&cuip->cui_next_extent, count);
- xfs_trans_add_item(tp, &cuip->cui_item);
- set_bit(XFS_LI_DIRTY, &cuip->cui_item.li_flags);
+
return &cuip->cui_item;
}
+const struct xfs_defer_op_type xfs_refcount_update_defer_type = {
+ .name = "refcount",
+ .max_items = XFS_CUI_MAX_FAST_EXTENTS,
+ .create_intent = xfs_refcount_update_create_intent,
+ .abort_intent = xfs_refcount_update_abort_intent,
+ .create_done = xfs_refcount_update_create_done,
+ .finish_item = xfs_refcount_update_finish_item,
+ .finish_cleanup = xfs_refcount_finish_one_cleanup,
+ .cancel_item = xfs_refcount_update_cancel_item,
+ .recover_work = xfs_refcount_recover_work,
+ .relog_intent = xfs_refcount_relog_intent,
+};
+
+STATIC bool
+xfs_cui_item_match(
+ struct xfs_log_item *lip,
+ uint64_t intent_id)
+{
+ return CUI_ITEM(lip)->cui_format.cui_id == intent_id;
+}
+
static const struct xfs_item_ops xfs_cui_item_ops = {
.flags = XFS_ITEM_INTENT,
.iop_size = xfs_cui_item_size,
.iop_format = xfs_cui_item_format,
.iop_unpin = xfs_cui_item_unpin,
.iop_release = xfs_cui_item_release,
- .iop_recover = xfs_cui_item_recover,
.iop_match = xfs_cui_item_match,
- .iop_relog = xfs_cui_item_relog,
};
static inline void
@@ -696,12 +603,9 @@ xlog_recover_cui_commit_pass2(
cuip = xfs_cui_init(mp, cui_formatp->cui_nextents);
xfs_cui_copy_format(&cuip->cui_format, cui_formatp);
atomic_set(&cuip->cui_next_extent, cui_formatp->cui_nextents);
- /*
- * Insert the intent into the AIL directly and drop one reference so
- * that finishing or canceling the work will drop the other.
- */
- xfs_trans_ail_insert(log->l_ailp, &cuip->cui_item, lsn);
- xfs_cui_release(cuip);
+
+ xlog_recover_intent_item(log, &cuip->cui_item, lsn,
+ &xfs_refcount_update_defer_type);
return 0;
}
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index e5b62dc28466..d5ca8bcae65b 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -618,7 +618,7 @@ xfs_reflink_cancel_cow_blocks(
error = xfs_free_extent_later(*tpp, del.br_startblock,
del.br_blockcount, NULL,
- XFS_AG_RESV_NONE);
+ XFS_AG_RESV_NONE, false);
if (error)
break;
diff --git a/fs/xfs/xfs_rmap_item.c b/fs/xfs/xfs_rmap_item.c
index 0e0e747028da..79ad0087aeca 100644
--- a/fs/xfs/xfs_rmap_item.c
+++ b/fs/xfs/xfs_rmap_item.c
@@ -225,23 +225,6 @@ static const struct xfs_item_ops xfs_rud_item_ops = {
.iop_intent = xfs_rud_item_intent,
};
-static struct xfs_rud_log_item *
-xfs_trans_get_rud(
- struct xfs_trans *tp,
- struct xfs_rui_log_item *ruip)
-{
- struct xfs_rud_log_item *rudp;
-
- rudp = kmem_cache_zalloc(xfs_rud_cache, GFP_KERNEL | __GFP_NOFAIL);
- xfs_log_item_init(tp->t_mountp, &rudp->rud_item, XFS_LI_RUD,
- &xfs_rud_item_ops);
- rudp->rud_ruip = ruip;
- rudp->rud_format.rud_rui_id = ruip->rui_format.rui_id;
-
- xfs_trans_add_item(tp, &rudp->rud_item);
- return rudp;
-}
-
/* Set the map extent flags for this reverse mapping. */
static void
xfs_trans_set_rmap_flags(
@@ -285,35 +268,6 @@ xfs_trans_set_rmap_flags(
}
}
-/*
- * Finish an rmap update and log it to the RUD. Note that the transaction is
- * marked dirty regardless of whether the rmap update succeeds or fails to
- * support the RUI/RUD lifecycle rules.
- */
-static int
-xfs_trans_log_finish_rmap_update(
- struct xfs_trans *tp,
- struct xfs_rud_log_item *rudp,
- struct xfs_rmap_intent *ri,
- struct xfs_btree_cur **pcur)
-{
- int error;
-
- error = xfs_rmap_finish_one(tp, ri, pcur);
-
- /*
- * Mark the transaction dirty, even on error. This ensures the
- * transaction is aborted, which:
- *
- * 1.) releases the RUI and frees the RUD
- * 2.) shuts down the filesystem
- */
- tp->t_flags |= XFS_TRANS_DIRTY | XFS_TRANS_HAS_INTENT_DONE;
- set_bit(XFS_LI_DIRTY, &rudp->rud_item.li_flags);
-
- return error;
-}
-
/* Sort rmap intents by AG. */
static int
xfs_rmap_update_diff_items(
@@ -340,9 +294,6 @@ xfs_rmap_update_log_item(
uint next_extent;
struct xfs_map_extent *map;
- tp->t_flags |= XFS_TRANS_DIRTY;
- set_bit(XFS_LI_DIRTY, &ruip->rui_item.li_flags);
-
/*
* atomic_inc_return gives us the value after the increment;
* we want to use it as an array index so we need to subtract 1 from
@@ -372,7 +323,6 @@ xfs_rmap_update_create_intent(
ASSERT(count > 0);
- xfs_trans_add_item(tp, &ruip->rui_item);
if (sort)
list_sort(mp, items, xfs_rmap_update_diff_items);
list_for_each_entry(ri, items, ri_list)
@@ -387,7 +337,16 @@ xfs_rmap_update_create_done(
struct xfs_log_item *intent,
unsigned int count)
{
- return &xfs_trans_get_rud(tp, RUI_ITEM(intent))->rud_item;
+ struct xfs_rui_log_item *ruip = RUI_ITEM(intent);
+ struct xfs_rud_log_item *rudp;
+
+ rudp = kmem_cache_zalloc(xfs_rud_cache, GFP_KERNEL | __GFP_NOFAIL);
+ xfs_log_item_init(tp->t_mountp, &rudp->rud_item, XFS_LI_RUD,
+ &xfs_rud_item_ops);
+ rudp->rud_ruip = ruip;
+ rudp->rud_format.rud_rui_id = ruip->rui_format.rui_id;
+
+ return &rudp->rud_item;
}
/* Take a passive ref to the AG containing the space we're rmapping. */
@@ -423,8 +382,7 @@ xfs_rmap_update_finish_item(
ri = container_of(item, struct xfs_rmap_intent, ri_list);
- error = xfs_trans_log_finish_rmap_update(tp, RUD_ITEM(done), ri,
- state);
+ error = xfs_rmap_finish_one(tp, ri, state);
xfs_rmap_update_put_group(ri);
kmem_cache_free(xfs_rmap_intent_cache, ri);
@@ -452,16 +410,6 @@ xfs_rmap_update_cancel_item(
kmem_cache_free(xfs_rmap_intent_cache, ri);
}
-const struct xfs_defer_op_type xfs_rmap_update_defer_type = {
- .max_items = XFS_RUI_MAX_FAST_EXTENTS,
- .create_intent = xfs_rmap_update_create_intent,
- .abort_intent = xfs_rmap_update_abort_intent,
- .create_done = xfs_rmap_update_create_done,
- .finish_item = xfs_rmap_update_finish_item,
- .finish_cleanup = xfs_rmap_finish_one_cleanup,
- .cancel_item = xfs_rmap_update_cancel_item,
-};
-
/* Is this recovered RUI ok? */
static inline bool
xfs_rui_validate_map(
@@ -498,20 +446,72 @@ xfs_rui_validate_map(
return xfs_verify_fsbext(mp, map->me_startblock, map->me_len);
}
+static inline void
+xfs_rui_recover_work(
+ struct xfs_mount *mp,
+ struct xfs_defer_pending *dfp,
+ const struct xfs_map_extent *map)
+{
+ struct xfs_rmap_intent *ri;
+
+ ri = kmem_cache_alloc(xfs_rmap_intent_cache, GFP_NOFS | __GFP_NOFAIL);
+
+ switch (map->me_flags & XFS_RMAP_EXTENT_TYPE_MASK) {
+ case XFS_RMAP_EXTENT_MAP:
+ ri->ri_type = XFS_RMAP_MAP;
+ break;
+ case XFS_RMAP_EXTENT_MAP_SHARED:
+ ri->ri_type = XFS_RMAP_MAP_SHARED;
+ break;
+ case XFS_RMAP_EXTENT_UNMAP:
+ ri->ri_type = XFS_RMAP_UNMAP;
+ break;
+ case XFS_RMAP_EXTENT_UNMAP_SHARED:
+ ri->ri_type = XFS_RMAP_UNMAP_SHARED;
+ break;
+ case XFS_RMAP_EXTENT_CONVERT:
+ ri->ri_type = XFS_RMAP_CONVERT;
+ break;
+ case XFS_RMAP_EXTENT_CONVERT_SHARED:
+ ri->ri_type = XFS_RMAP_CONVERT_SHARED;
+ break;
+ case XFS_RMAP_EXTENT_ALLOC:
+ ri->ri_type = XFS_RMAP_ALLOC;
+ break;
+ case XFS_RMAP_EXTENT_FREE:
+ ri->ri_type = XFS_RMAP_FREE;
+ break;
+ default:
+ ASSERT(0);
+ return;
+ }
+
+ ri->ri_owner = map->me_owner;
+ ri->ri_whichfork = (map->me_flags & XFS_RMAP_EXTENT_ATTR_FORK) ?
+ XFS_ATTR_FORK : XFS_DATA_FORK;
+ ri->ri_bmap.br_startblock = map->me_startblock;
+ ri->ri_bmap.br_startoff = map->me_startoff;
+ ri->ri_bmap.br_blockcount = map->me_len;
+ ri->ri_bmap.br_state = (map->me_flags & XFS_RMAP_EXTENT_UNWRITTEN) ?
+ XFS_EXT_UNWRITTEN : XFS_EXT_NORM;
+ xfs_rmap_update_get_group(mp, ri);
+
+ xfs_defer_add_item(dfp, &ri->ri_list);
+}
+
/*
* Process an rmap update intent item that was recovered from the log.
* We need to update the rmapbt.
*/
STATIC int
-xfs_rui_item_recover(
- struct xfs_log_item *lip,
+xfs_rmap_recover_work(
+ struct xfs_defer_pending *dfp,
struct list_head *capture_list)
{
struct xfs_trans_res resv;
+ struct xfs_log_item *lip = dfp->dfp_intent;
struct xfs_rui_log_item *ruip = RUI_ITEM(lip);
- struct xfs_rud_log_item *rudp;
struct xfs_trans *tp;
- struct xfs_btree_cur *rcur = NULL;
struct xfs_mount *mp = lip->li_log->l_mp;
int i;
int error = 0;
@@ -529,6 +529,8 @@ xfs_rui_item_recover(
sizeof(ruip->rui_format));
return -EFSCORRUPTED;
}
+
+ xfs_rui_recover_work(mp, dfp, &ruip->rui_format.rui_extents[i]);
}
resv = xlog_recover_resv(&M_RES(mp)->tr_itruncate);
@@ -536,91 +538,29 @@ xfs_rui_item_recover(
XFS_TRANS_RESERVE, &tp);
if (error)
return error;
- rudp = xfs_trans_get_rud(tp, ruip);
- for (i = 0; i < ruip->rui_format.rui_nextents; i++) {
- struct xfs_rmap_intent fake = { };
- struct xfs_map_extent *map;
-
- map = &ruip->rui_format.rui_extents[i];
- switch (map->me_flags & XFS_RMAP_EXTENT_TYPE_MASK) {
- case XFS_RMAP_EXTENT_MAP:
- fake.ri_type = XFS_RMAP_MAP;
- break;
- case XFS_RMAP_EXTENT_MAP_SHARED:
- fake.ri_type = XFS_RMAP_MAP_SHARED;
- break;
- case XFS_RMAP_EXTENT_UNMAP:
- fake.ri_type = XFS_RMAP_UNMAP;
- break;
- case XFS_RMAP_EXTENT_UNMAP_SHARED:
- fake.ri_type = XFS_RMAP_UNMAP_SHARED;
- break;
- case XFS_RMAP_EXTENT_CONVERT:
- fake.ri_type = XFS_RMAP_CONVERT;
- break;
- case XFS_RMAP_EXTENT_CONVERT_SHARED:
- fake.ri_type = XFS_RMAP_CONVERT_SHARED;
- break;
- case XFS_RMAP_EXTENT_ALLOC:
- fake.ri_type = XFS_RMAP_ALLOC;
- break;
- case XFS_RMAP_EXTENT_FREE:
- fake.ri_type = XFS_RMAP_FREE;
- break;
- default:
- XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
- &ruip->rui_format,
- sizeof(ruip->rui_format));
- error = -EFSCORRUPTED;
- goto abort_error;
- }
-
- fake.ri_owner = map->me_owner;
- fake.ri_whichfork = (map->me_flags & XFS_RMAP_EXTENT_ATTR_FORK) ?
- XFS_ATTR_FORK : XFS_DATA_FORK;
- fake.ri_bmap.br_startblock = map->me_startblock;
- fake.ri_bmap.br_startoff = map->me_startoff;
- fake.ri_bmap.br_blockcount = map->me_len;
- fake.ri_bmap.br_state = (map->me_flags & XFS_RMAP_EXTENT_UNWRITTEN) ?
- XFS_EXT_UNWRITTEN : XFS_EXT_NORM;
-
- xfs_rmap_update_get_group(mp, &fake);
- error = xfs_trans_log_finish_rmap_update(tp, rudp, &fake,
- &rcur);
- if (error == -EFSCORRUPTED)
- XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
- map, sizeof(*map));
- xfs_rmap_update_put_group(&fake);
- if (error)
- goto abort_error;
-
- }
+ error = xlog_recover_finish_intent(tp, dfp);
+ if (error == -EFSCORRUPTED)
+ XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
+ &ruip->rui_format,
+ sizeof(ruip->rui_format));
+ if (error)
+ goto abort_error;
- xfs_rmap_finish_one_cleanup(tp, rcur, error);
return xfs_defer_ops_capture_and_commit(tp, capture_list);
abort_error:
- xfs_rmap_finish_one_cleanup(tp, rcur, error);
xfs_trans_cancel(tp);
return error;
}
-STATIC bool
-xfs_rui_item_match(
- struct xfs_log_item *lip,
- uint64_t intent_id)
-{
- return RUI_ITEM(lip)->rui_format.rui_id == intent_id;
-}
-
/* Relog an intent item to push the log tail forward. */
static struct xfs_log_item *
-xfs_rui_item_relog(
+xfs_rmap_relog_intent(
+ struct xfs_trans *tp,
struct xfs_log_item *intent,
- struct xfs_trans *tp)
+ struct xfs_log_item *done_item)
{
- struct xfs_rud_log_item *rudp;
struct xfs_rui_log_item *ruip;
struct xfs_map_extent *map;
unsigned int count;
@@ -628,27 +568,41 @@ xfs_rui_item_relog(
count = RUI_ITEM(intent)->rui_format.rui_nextents;
map = RUI_ITEM(intent)->rui_format.rui_extents;
- tp->t_flags |= XFS_TRANS_DIRTY;
- rudp = xfs_trans_get_rud(tp, RUI_ITEM(intent));
- set_bit(XFS_LI_DIRTY, &rudp->rud_item.li_flags);
-
ruip = xfs_rui_init(tp->t_mountp, count);
memcpy(ruip->rui_format.rui_extents, map, count * sizeof(*map));
atomic_set(&ruip->rui_next_extent, count);
- xfs_trans_add_item(tp, &ruip->rui_item);
- set_bit(XFS_LI_DIRTY, &ruip->rui_item.li_flags);
+
return &ruip->rui_item;
}
+const struct xfs_defer_op_type xfs_rmap_update_defer_type = {
+ .name = "rmap",
+ .max_items = XFS_RUI_MAX_FAST_EXTENTS,
+ .create_intent = xfs_rmap_update_create_intent,
+ .abort_intent = xfs_rmap_update_abort_intent,
+ .create_done = xfs_rmap_update_create_done,
+ .finish_item = xfs_rmap_update_finish_item,
+ .finish_cleanup = xfs_rmap_finish_one_cleanup,
+ .cancel_item = xfs_rmap_update_cancel_item,
+ .recover_work = xfs_rmap_recover_work,
+ .relog_intent = xfs_rmap_relog_intent,
+};
+
+STATIC bool
+xfs_rui_item_match(
+ struct xfs_log_item *lip,
+ uint64_t intent_id)
+{
+ return RUI_ITEM(lip)->rui_format.rui_id == intent_id;
+}
+
static const struct xfs_item_ops xfs_rui_item_ops = {
.flags = XFS_ITEM_INTENT,
.iop_size = xfs_rui_item_size,
.iop_format = xfs_rui_item_format,
.iop_unpin = xfs_rui_item_unpin,
.iop_release = xfs_rui_item_release,
- .iop_recover = xfs_rui_item_recover,
.iop_match = xfs_rui_item_match,
- .iop_relog = xfs_rui_item_relog,
};
static inline void
@@ -702,12 +656,9 @@ xlog_recover_rui_commit_pass2(
ruip = xfs_rui_init(mp, rui_formatp->rui_nextents);
xfs_rui_copy_format(&ruip->rui_format, rui_formatp);
atomic_set(&ruip->rui_next_extent, rui_formatp->rui_nextents);
- /*
- * Insert the intent into the AIL directly and drop one reference so
- * that finishing or canceling the work will drop the other.
- */
- xfs_trans_ail_insert(log->l_ailp, &ruip->rui_item, lsn);
- xfs_rui_release(ruip);
+
+ xlog_recover_intent_item(log, &ruip->rui_item, lsn,
+ &xfs_rmap_update_defer_type);
return 0;
}
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index 88c48de5c9c8..8649d981a097 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -14,28 +14,14 @@
#include "xfs_inode.h"
#include "xfs_bmap.h"
#include "xfs_bmap_btree.h"
+#include "xfs_bmap_util.h"
#include "xfs_trans.h"
#include "xfs_trans_space.h"
#include "xfs_icache.h"
#include "xfs_rtalloc.h"
#include "xfs_sb.h"
#include "xfs_rtbitmap.h"
-
-/*
- * Read and return the summary information for a given extent size,
- * bitmap block combination.
- * Keeps track of a current summary block, so we don't keep reading
- * it from the buffer cache.
- */
-static int
-xfs_rtget_summary(
- struct xfs_rtalloc_args *args,
- int log, /* log2 of extent size */
- xfs_fileoff_t bbno, /* bitmap block number */
- xfs_suminfo_t *sum) /* out: summary info for this block */
-{
- return xfs_rtmodify_summary_int(args, log, bbno, 0, sum);
-}
+#include "xfs_quota.h"
/*
* Return whether there are any free extents in the size range given
@@ -154,56 +140,55 @@ xfs_rtallocate_range(
* properly update the summary.
*/
error = xfs_rtfind_back(args, start, 0, &preblock);
- if (error) {
+ if (error)
return error;
- }
+
/*
* Find the next allocated block (end of free extent).
*/
error = xfs_rtfind_forw(args, end, mp->m_sb.sb_rextents - 1,
&postblock);
- if (error) {
+ if (error)
return error;
- }
+
/*
* Decrement the summary information corresponding to the entire
* (old) free extent.
*/
error = xfs_rtmodify_summary(args,
- XFS_RTBLOCKLOG(postblock + 1 - preblock),
+ xfs_highbit64(postblock + 1 - preblock),
xfs_rtx_to_rbmblock(mp, preblock), -1);
- if (error) {
+ if (error)
return error;
- }
+
/*
* If there are blocks not being allocated at the front of the
* old extent, add summary data for them to be free.
*/
if (preblock < start) {
error = xfs_rtmodify_summary(args,
- XFS_RTBLOCKLOG(start - preblock),
+ xfs_highbit64(start - preblock),
xfs_rtx_to_rbmblock(mp, preblock), 1);
- if (error) {
+ if (error)
return error;
- }
}
+
/*
* If there are blocks not being allocated at the end of the
* old extent, add summary data for them to be free.
*/
if (postblock > end) {
error = xfs_rtmodify_summary(args,
- XFS_RTBLOCKLOG(postblock - end),
+ xfs_highbit64(postblock - end),
xfs_rtx_to_rbmblock(mp, end + 1), 1);
- if (error) {
+ if (error)
return error;
- }
}
+
/*
* Modify the bitmap to mark this extent allocated.
*/
- error = xfs_rtmodify_range(args, start, len, 0);
- return error;
+ return xfs_rtmodify_range(args, start, len, 0);
}
/*
@@ -265,21 +250,17 @@ xfs_rtallocate_extent_block(
* If it's not so then next will contain the first non-free.
*/
error = xfs_rtcheck_range(args, i, maxlen, 1, &next, &stat);
- if (error) {
+ if (error)
return error;
- }
if (stat) {
/*
* i for maxlen is all free, allocate and return that.
*/
- error = xfs_rtallocate_range(args, i, maxlen);
- if (error) {
- return error;
- }
- *len = maxlen;
- *rtx = i;
- return 0;
+ bestlen = maxlen;
+ besti = i;
+ goto allocate;
}
+
/*
* In the case where we have a variable-sized allocation
* request, figure out how big this free piece is,
@@ -298,45 +279,44 @@ xfs_rtallocate_extent_block(
/*
* If not done yet, find the start of the next free space.
*/
- if (next < end) {
- error = xfs_rtfind_forw(args, next, end, &i);
- if (error) {
- return error;
- }
- } else
+ if (next >= end)
break;
+ error = xfs_rtfind_forw(args, next, end, &i);
+ if (error)
+ return error;
}
+
/*
* Searched the whole thing & didn't find a maxlen free extent.
*/
- if (minlen < maxlen && besti != -1) {
- xfs_rtxlen_t p; /* amount to trim length by */
-
+ if (minlen > maxlen || besti == -1) {
/*
- * If size should be a multiple of prod, make that so.
+ * Allocation failed. Set *nextp to the next block to try.
*/
- if (prod > 1) {
- div_u64_rem(bestlen, prod, &p);
- if (p)
- bestlen -= p;
- }
+ *nextp = next;
+ return -ENOSPC;
+ }
- /*
- * Allocate besti for bestlen & return that.
- */
- error = xfs_rtallocate_range(args, besti, bestlen);
- if (error) {
- return error;
- }
- *len = bestlen;
- *rtx = besti;
- return 0;
+ /*
+ * If size should be a multiple of prod, make that so.
+ */
+ if (prod > 1) {
+ xfs_rtxlen_t p; /* amount to trim length by */
+
+ div_u64_rem(bestlen, prod, &p);
+ if (p)
+ bestlen -= p;
}
+
/*
- * Allocation failed. Set *nextp to the next block to try.
+ * Allocate besti for bestlen & return that.
*/
- *nextp = next;
- *rtx = NULLRTEXTNO;
+allocate:
+ error = xfs_rtallocate_range(args, besti, bestlen);
+ if (error)
+ return error;
+ *len = bestlen;
+ *rtx = besti;
return 0;
}
@@ -367,52 +347,33 @@ xfs_rtallocate_extent_exact(
* Check if the range in question (for maxlen) is free.
*/
error = xfs_rtcheck_range(args, start, maxlen, 1, &next, &isfree);
- if (error) {
+ if (error)
return error;
- }
- if (isfree) {
+
+ if (!isfree) {
/*
- * If it is, allocate it and return success.
+ * If not, allocate what there is, if it's at least minlen.
*/
- error = xfs_rtallocate_range(args, start, maxlen);
- if (error) {
- return error;
- }
- *len = maxlen;
- *rtx = start;
- return 0;
- }
- /*
- * If not, allocate what there is, if it's at least minlen.
- */
- maxlen = next - start;
- if (maxlen < minlen) {
+ maxlen = next - start;
+ if (maxlen < minlen)
+ return -ENOSPC;
+
/*
- * Failed, return failure status.
+ * Trim off tail of extent, if prod is specified.
*/
- *rtx = NULLRTEXTNO;
- return 0;
- }
- /*
- * Trim off tail of extent, if prod is specified.
- */
- if (prod > 1 && (i = maxlen % prod)) {
- maxlen -= i;
- if (maxlen < minlen) {
- /*
- * Now we can't do it, return failure status.
- */
- *rtx = NULLRTEXTNO;
- return 0;
+ if (prod > 1 && (i = maxlen % prod)) {
+ maxlen -= i;
+ if (maxlen < minlen)
+ return -ENOSPC;
}
}
+
/*
* Allocate what we can and return it.
*/
error = xfs_rtallocate_range(args, start, maxlen);
- if (error) {
+ if (error)
return error;
- }
*len = maxlen;
*rtx = start;
return 0;
@@ -441,7 +402,6 @@ xfs_rtallocate_extent_near(
int j; /* secondary loop control */
int log2len; /* log2 of minlen */
xfs_rtxnum_t n; /* next rtext to try */
- xfs_rtxnum_t r; /* result rtext */
ASSERT(minlen % prod == 0);
ASSERT(maxlen % prod == 0);
@@ -455,26 +415,18 @@ xfs_rtallocate_extent_near(
/* Make sure we don't run off the end of the rt volume. */
maxlen = xfs_rtallocate_clamp_len(mp, start, maxlen, prod);
- if (maxlen < minlen) {
- *rtx = NULLRTEXTNO;
- return 0;
- }
+ if (maxlen < minlen)
+ return -ENOSPC;
/*
* Try the exact allocation first.
*/
error = xfs_rtallocate_extent_exact(args, start, minlen, maxlen, len,
- prod, &r);
- if (error) {
+ prod, rtx);
+ if (error != -ENOSPC)
return error;
- }
- /*
- * If the exact allocation worked, return that.
- */
- if (r != NULLRTEXTNO) {
- *rtx = r;
- return 0;
- }
+
+
bbno = xfs_rtx_to_rbmblock(mp, start);
i = 0;
j = -1;
@@ -490,9 +442,9 @@ xfs_rtallocate_extent_near(
*/
error = xfs_rtany_summary(args, log2len, mp->m_rsumlevels - 1,
bbno + i, &maxlog);
- if (error) {
+ if (error)
return error;
- }
+
/*
* If there are any useful extents starting here, try
* allocating one.
@@ -511,17 +463,9 @@ xfs_rtallocate_extent_near(
*/
error = xfs_rtallocate_extent_block(args,
bbno + i, minlen, maxavail, len,
- &n, prod, &r);
- if (error) {
+ &n, prod, rtx);
+ if (error != -ENOSPC)
return error;
- }
- /*
- * If it worked, return it.
- */
- if (r != NULLRTEXTNO) {
- *rtx = r;
- return 0;
- }
}
/*
* On the negative side of the starting location.
@@ -555,17 +499,9 @@ xfs_rtallocate_extent_near(
error = xfs_rtallocate_extent_block(args,
bbno + j, minlen,
maxavail, len, &n, prod,
- &r);
- if (error) {
+ rtx);
+ if (error != -ENOSPC)
return error;
- }
- /*
- * If it works, return the extent.
- */
- if (r != NULLRTEXTNO) {
- *rtx = r;
- return 0;
- }
}
}
}
@@ -599,8 +535,53 @@ xfs_rtallocate_extent_near(
else
break;
}
- *rtx = NULLRTEXTNO;
- return 0;
+ return -ENOSPC;
+}
+
+static int
+xfs_rtalloc_sumlevel(
+ struct xfs_rtalloc_args *args,
+ int l, /* level number */
+ xfs_rtxlen_t minlen, /* minimum length to allocate */
+ xfs_rtxlen_t maxlen, /* maximum length to allocate */
+ xfs_rtxlen_t prod, /* extent product factor */
+ xfs_rtxlen_t *len, /* out: actual length allocated */
+ xfs_rtxnum_t *rtx) /* out: start rtext allocated */
+{
+ xfs_fileoff_t i; /* bitmap block number */
+
+ for (i = 0; i < args->mp->m_sb.sb_rbmblocks; i++) {
+ xfs_suminfo_t sum; /* summary information for extents */
+ xfs_rtxnum_t n; /* next rtext to be tried */
+ int error;
+
+ error = xfs_rtget_summary(args, l, i, &sum);
+ if (error)
+ return error;
+
+ /*
+ * Nothing there, on to the next block.
+ */
+ if (!sum)
+ continue;
+
+ /*
+ * Try allocating the extent.
+ */
+ error = xfs_rtallocate_extent_block(args, i, minlen, maxlen,
+ len, &n, prod, rtx);
+ if (error != -ENOSPC)
+ return error;
+
+ /*
+ * If the "next block to try" returned from the allocator is
+ * beyond the next bitmap block, skip to that bitmap block.
+ */
+ if (xfs_rtx_to_rbmblock(args->mp, n) > i + 1)
+ i = xfs_rtx_to_rbmblock(args->mp, n) - 1;
+ }
+
+ return -ENOSPC;
}
/*
@@ -617,13 +598,8 @@ xfs_rtallocate_extent_size(
xfs_rtxlen_t prod, /* extent product factor */
xfs_rtxnum_t *rtx) /* out: start rtext allocated */
{
- struct xfs_mount *mp = args->mp;
int error;
- xfs_fileoff_t i; /* bitmap block number */
int l; /* level number (loop control) */
- xfs_rtxnum_t n; /* next rtext to be tried */
- xfs_rtxnum_t r; /* result rtext number */
- xfs_suminfo_t sum; /* summary information for extents */
ASSERT(minlen % prod == 0);
ASSERT(maxlen % prod == 0);
@@ -631,119 +607,46 @@ xfs_rtallocate_extent_size(
/*
* Loop over all the levels starting with maxlen.
- * At each level, look at all the bitmap blocks, to see if there
- * are extents starting there that are long enough (>= maxlen).
- * Note, only on the initial level can the allocation fail if
- * the summary says there's an extent.
+ *
+ * At each level, look at all the bitmap blocks, to see if there are
+ * extents starting there that are long enough (>= maxlen).
+ *
+ * Note, only on the initial level can the allocation fail if the
+ * summary says there's an extent.
*/
- for (l = xfs_highbit32(maxlen); l < mp->m_rsumlevels; l++) {
- /*
- * Loop over all the bitmap blocks.
- */
- for (i = 0; i < mp->m_sb.sb_rbmblocks; i++) {
- /*
- * Get the summary for this level/block.
- */
- error = xfs_rtget_summary(args, l, i, &sum);
- if (error) {
- return error;
- }
- /*
- * Nothing there, on to the next block.
- */
- if (!sum)
- continue;
- /*
- * Try allocating the extent.
- */
- error = xfs_rtallocate_extent_block(args, i, maxlen,
- maxlen, len, &n, prod, &r);
- if (error) {
- return error;
- }
- /*
- * If it worked, return that.
- */
- if (r != NULLRTEXTNO) {
- *rtx = r;
- return 0;
- }
- /*
- * If the "next block to try" returned from the
- * allocator is beyond the next bitmap block,
- * skip to that bitmap block.
- */
- if (xfs_rtx_to_rbmblock(mp, n) > i + 1)
- i = xfs_rtx_to_rbmblock(mp, n) - 1;
- }
+ for (l = xfs_highbit32(maxlen); l < args->mp->m_rsumlevels; l++) {
+ error = xfs_rtalloc_sumlevel(args, l, minlen, maxlen, prod, len,
+ rtx);
+ if (error != -ENOSPC)
+ return error;
}
+
/*
- * Didn't find any maxlen blocks. Try smaller ones, unless
- * we're asking for a fixed size extent.
+ * Didn't find any maxlen blocks. Try smaller ones, unless we are
+ * looking for a fixed size extent.
*/
- if (minlen > --maxlen) {
- *rtx = NULLRTEXTNO;
- return 0;
- }
+ if (minlen > --maxlen)
+ return -ENOSPC;
ASSERT(minlen != 0);
ASSERT(maxlen != 0);
/*
* Loop over sizes, from maxlen down to minlen.
- * This time, when we do the allocations, allow smaller ones
- * to succeed.
+ *
+ * This time, when we do the allocations, allow smaller ones to succeed,
+ * but make sure the specified minlen/maxlen are in the possible range
+ * for this summary level.
*/
for (l = xfs_highbit32(maxlen); l >= xfs_highbit32(minlen); l--) {
- /*
- * Loop over all the bitmap blocks, try an allocation
- * starting in that block.
- */
- for (i = 0; i < mp->m_sb.sb_rbmblocks; i++) {
- /*
- * Get the summary information for this level/block.
- */
- error = xfs_rtget_summary(args, l, i, &sum);
- if (error) {
- return error;
- }
- /*
- * If nothing there, go on to next.
- */
- if (!sum)
- continue;
- /*
- * Try the allocation. Make sure the specified
- * minlen/maxlen are in the possible range for
- * this summary level.
- */
- error = xfs_rtallocate_extent_block(args, i,
- XFS_RTMAX(minlen, 1 << l),
- XFS_RTMIN(maxlen, (1 << (l + 1)) - 1),
- len, &n, prod, &r);
- if (error) {
- return error;
- }
- /*
- * If it worked, return that extent.
- */
- if (r != NULLRTEXTNO) {
- *rtx = r;
- return 0;
- }
- /*
- * If the "next block to try" returned from the
- * allocator is beyond the next bitmap block,
- * skip to that bitmap block.
- */
- if (xfs_rtx_to_rbmblock(mp, n) > i + 1)
- i = xfs_rtx_to_rbmblock(mp, n) - 1;
- }
+ error = xfs_rtalloc_sumlevel(args, l,
+ max_t(xfs_rtxlen_t, minlen, 1 << l),
+ min_t(xfs_rtxlen_t, maxlen, (1 << (l + 1)) - 1),
+ prod, len, rtx);
+ if (error != -ENOSPC)
+ return error;
}
- /*
- * Got nothing, return failure.
- */
- *rtx = NULLRTEXTNO;
- return 0;
+
+ return -ENOSPC;
}
/*
@@ -963,8 +866,10 @@ xfs_growfs_rt(
*/
nrextents = nrblocks;
do_div(nrextents, in->extsize);
+ if (!xfs_validate_rtextents(nrextents))
+ return -EINVAL;
nrbmblocks = xfs_rtbitmap_blockcount(mp, nrextents);
- nrextslog = xfs_highbit32(nrextents);
+ nrextslog = xfs_compute_rextslog(nrextents);
nrsumlevels = nrextslog + 1;
nrsumblocks = xfs_rtsummary_blockcount(mp, nrsumlevels, nrbmblocks);
nrsumsize = XFS_FSB_TO_B(mp, nrsumblocks);
@@ -1031,11 +936,14 @@ xfs_growfs_rt(
nsbp->sb_rblocks = min(nrblocks, nrblocks_step);
nsbp->sb_rextents = xfs_rtb_to_rtx(nmp, nsbp->sb_rblocks);
ASSERT(nsbp->sb_rextents != 0);
- nsbp->sb_rextslog = xfs_highbit32(nsbp->sb_rextents);
+ nsbp->sb_rextslog = xfs_compute_rextslog(nsbp->sb_rextents);
nrsumlevels = nmp->m_rsumlevels = nsbp->sb_rextslog + 1;
nrsumblocks = xfs_rtsummary_blockcount(mp, nrsumlevels,
nsbp->sb_rbmblocks);
nmp->m_rsumsize = nrsumsize = XFS_FSB_TO_B(mp, nrsumblocks);
+ /* recompute growfsrt reservation from new rsumsize */
+ xfs_trans_resv_calc(nmp, &nmp->m_resv);
+
/*
* Start a transaction, get the log reservation.
*/
@@ -1122,6 +1030,8 @@ error_cancel:
*/
mp->m_rsumlevels = nrsumlevels;
mp->m_rsumsize = nrsumsize;
+ /* recompute growfsrt reservation from new rsumsize */
+ xfs_trans_resv_calc(mp, &mp->m_resv);
error = xfs_trans_commit(tp);
if (error)
@@ -1160,81 +1070,6 @@ out_free:
}
/*
- * Allocate an extent in the realtime subvolume, with the usual allocation
- * parameters. The length units are all in realtime extents, as is the
- * result block number.
- */
-int
-xfs_rtallocate_extent(
- struct xfs_trans *tp,
- xfs_rtxnum_t start, /* starting rtext number to allocate */
- xfs_rtxlen_t minlen, /* minimum length to allocate */
- xfs_rtxlen_t maxlen, /* maximum length to allocate */
- xfs_rtxlen_t *len, /* out: actual length allocated */
- int wasdel, /* was a delayed allocation extent */
- xfs_rtxlen_t prod, /* extent product factor */
- xfs_rtxnum_t *rtblock) /* out: start rtext allocated */
-{
- struct xfs_rtalloc_args args = {
- .mp = tp->t_mountp,
- .tp = tp,
- };
- int error; /* error value */
- xfs_rtxnum_t r; /* result allocated rtext */
-
- ASSERT(xfs_isilocked(args.mp->m_rbmip, XFS_ILOCK_EXCL));
- ASSERT(minlen > 0 && minlen <= maxlen);
-
- /*
- * If prod is set then figure out what to do to minlen and maxlen.
- */
- if (prod > 1) {
- xfs_rtxlen_t i;
-
- if ((i = maxlen % prod))
- maxlen -= i;
- if ((i = minlen % prod))
- minlen += prod - i;
- if (maxlen < minlen) {
- *rtblock = NULLRTEXTNO;
- return 0;
- }
- }
-
-retry:
- if (start == 0) {
- error = xfs_rtallocate_extent_size(&args, minlen,
- maxlen, len, prod, &r);
- } else {
- error = xfs_rtallocate_extent_near(&args, start, minlen,
- maxlen, len, prod, &r);
- }
-
- xfs_rtbuf_cache_relse(&args);
- if (error)
- return error;
-
- /*
- * If it worked, update the superblock.
- */
- if (r != NULLRTEXTNO) {
- long slen = (long)*len;
-
- ASSERT(*len >= minlen && *len <= maxlen);
- if (wasdel)
- xfs_trans_mod_sb(tp, XFS_TRANS_SB_RES_FREXTENTS, -slen);
- else
- xfs_trans_mod_sb(tp, XFS_TRANS_SB_FREXTENTS, -slen);
- } else if (prod > 1) {
- prod = 1;
- goto retry;
- }
-
- *rtblock = r;
- return 0;
-}
-
-/*
* Initialize realtime fields in the mount structure.
*/
int /* error */
@@ -1412,7 +1247,7 @@ xfs_rtunmount_inodes(
* of rtextents and the fraction.
* The fraction sequence is 0, 1/2, 1/4, 3/4, 1/8, ..., 7/8, 1/16, ...
*/
-int /* error */
+static int
xfs_rtpick_extent(
xfs_mount_t *mp, /* file system mount point */
xfs_trans_t *tp, /* transaction pointer */
@@ -1451,3 +1286,177 @@ xfs_rtpick_extent(
*pick = b;
return 0;
}
+
+static void
+xfs_rtalloc_align_minmax(
+ xfs_rtxlen_t *raminlen,
+ xfs_rtxlen_t *ramaxlen,
+ xfs_rtxlen_t *prod)
+{
+ xfs_rtxlen_t newmaxlen = *ramaxlen;
+ xfs_rtxlen_t newminlen = *raminlen;
+ xfs_rtxlen_t slack;
+
+ slack = newmaxlen % *prod;
+ if (slack)
+ newmaxlen -= slack;
+ slack = newminlen % *prod;
+ if (slack)
+ newminlen += *prod - slack;
+
+ /*
+ * If adjusting for extent size hint alignment produces an invalid
+ * min/max len combination, go ahead without it.
+ */
+ if (newmaxlen < newminlen) {
+ *prod = 1;
+ return;
+ }
+ *ramaxlen = newmaxlen;
+ *raminlen = newminlen;
+}
+
+int
+xfs_bmap_rtalloc(
+ struct xfs_bmalloca *ap)
+{
+ struct xfs_mount *mp = ap->ip->i_mount;
+ xfs_fileoff_t orig_offset = ap->offset;
+ xfs_rtxnum_t start; /* allocation hint rtextent no */
+ xfs_rtxnum_t rtx; /* actually allocated rtextent no */
+ xfs_rtxlen_t prod = 0; /* product factor for allocators */
+ xfs_extlen_t mod = 0; /* product factor for allocators */
+ xfs_rtxlen_t ralen = 0; /* realtime allocation length */
+ xfs_extlen_t align; /* minimum allocation alignment */
+ xfs_extlen_t orig_length = ap->length;
+ xfs_extlen_t minlen = mp->m_sb.sb_rextsize;
+ xfs_rtxlen_t raminlen;
+ bool rtlocked = false;
+ bool ignore_locality = false;
+ struct xfs_rtalloc_args args = {
+ .mp = mp,
+ .tp = ap->tp,
+ };
+ int error;
+
+ align = xfs_get_extsz_hint(ap->ip);
+retry:
+ error = xfs_bmap_extsize_align(mp, &ap->got, &ap->prev,
+ align, 1, ap->eof, 0,
+ ap->conv, &ap->offset, &ap->length);
+ if (error)
+ return error;
+ ASSERT(ap->length);
+ ASSERT(xfs_extlen_to_rtxmod(mp, ap->length) == 0);
+
+ /*
+ * If we shifted the file offset downward to satisfy an extent size
+ * hint, increase minlen by that amount so that the allocator won't
+ * give us an allocation that's too short to cover at least one of the
+ * blocks that the caller asked for.
+ */
+ if (ap->offset != orig_offset)
+ minlen += orig_offset - ap->offset;
+
+ /*
+ * Set ralen to be the actual requested length in rtextents.
+ *
+ * If the old value was close enough to XFS_BMBT_MAX_EXTLEN that
+ * we rounded up to it, cut it back so it's valid again.
+ * Note that if it's a really large request (bigger than
+ * XFS_BMBT_MAX_EXTLEN), we don't hear about that number, and can't
+ * adjust the starting point to match it.
+ */
+ ralen = xfs_extlen_to_rtxlen(mp, min(ap->length, XFS_MAX_BMBT_EXTLEN));
+ raminlen = max_t(xfs_rtxlen_t, 1, xfs_extlen_to_rtxlen(mp, minlen));
+ ASSERT(raminlen > 0);
+ ASSERT(raminlen <= ralen);
+
+ /*
+ * Lock out modifications to both the RT bitmap and summary inodes
+ */
+ if (!rtlocked) {
+ xfs_ilock(mp->m_rbmip, XFS_ILOCK_EXCL|XFS_ILOCK_RTBITMAP);
+ xfs_trans_ijoin(ap->tp, mp->m_rbmip, XFS_ILOCK_EXCL);
+ xfs_ilock(mp->m_rsumip, XFS_ILOCK_EXCL|XFS_ILOCK_RTSUM);
+ xfs_trans_ijoin(ap->tp, mp->m_rsumip, XFS_ILOCK_EXCL);
+ rtlocked = true;
+ }
+
+ if (ignore_locality) {
+ start = 0;
+ } else if (xfs_bmap_adjacent(ap)) {
+ start = xfs_rtb_to_rtx(mp, ap->blkno);
+ } else if (ap->eof && ap->offset == 0) {
+ /*
+ * If it's an allocation to an empty file at offset 0, pick an
+ * extent that will space things out in the rt area.
+ */
+ error = xfs_rtpick_extent(mp, ap->tp, ralen, &start);
+ if (error)
+ return error;
+ } else {
+ start = 0;
+ }
+
+ /*
+ * Only bother calculating a real prod factor if offset & length are
+ * perfectly aligned, otherwise it will just get us in trouble.
+ */
+ div_u64_rem(ap->offset, align, &mod);
+ if (mod || ap->length % align) {
+ prod = 1;
+ } else {
+ prod = xfs_extlen_to_rtxlen(mp, align);
+ if (prod > 1)
+ xfs_rtalloc_align_minmax(&raminlen, &ralen, &prod);
+ }
+
+ if (start) {
+ error = xfs_rtallocate_extent_near(&args, start, raminlen,
+ ralen, &ralen, prod, &rtx);
+ } else {
+ error = xfs_rtallocate_extent_size(&args, raminlen,
+ ralen, &ralen, prod, &rtx);
+ }
+ xfs_rtbuf_cache_relse(&args);
+
+ if (error == -ENOSPC) {
+ if (align > mp->m_sb.sb_rextsize) {
+ /*
+ * We previously enlarged the request length to try to
+ * satisfy an extent size hint. The allocator didn't
+ * return anything, so reset the parameters to the
+ * original values and try again without alignment
+ * criteria.
+ */
+ ap->offset = orig_offset;
+ ap->length = orig_length;
+ minlen = align = mp->m_sb.sb_rextsize;
+ goto retry;
+ }
+
+ if (!ignore_locality && start != 0) {
+ /*
+ * If we can't allocate near a specific rt extent, try
+ * again without locality criteria.
+ */
+ ignore_locality = true;
+ goto retry;
+ }
+
+ ap->blkno = NULLFSBLOCK;
+ ap->length = 0;
+ return 0;
+ }
+ if (error)
+ return error;
+
+ xfs_trans_mod_sb(ap->tp, ap->wasdel ?
+ XFS_TRANS_SB_RES_FREXTENTS : XFS_TRANS_SB_FREXTENTS,
+ -(long)ralen);
+ ap->blkno = xfs_rtx_to_rtb(mp, rtx);
+ ap->length = xfs_rtxlen_to_extlen(mp, ralen);
+ xfs_bmap_alloc_account(ap);
+ return 0;
+}
diff --git a/fs/xfs/xfs_rtalloc.h b/fs/xfs/xfs_rtalloc.h
index f7cb9ffe51ca..a6836da9bebe 100644
--- a/fs/xfs/xfs_rtalloc.h
+++ b/fs/xfs/xfs_rtalloc.h
@@ -13,27 +13,6 @@ struct xfs_trans;
#ifdef CONFIG_XFS_RT
/*
- * Function prototypes for exported functions.
- */
-
-/*
- * Allocate an extent in the realtime subvolume, with the usual allocation
- * parameters. The length units are all in realtime extents, as is the
- * result block number.
- */
-int /* error */
-xfs_rtallocate_extent(
- struct xfs_trans *tp, /* transaction pointer */
- xfs_rtxnum_t start, /* starting rtext number to allocate */
- xfs_rtxlen_t minlen, /* minimum length to allocate */
- xfs_rtxlen_t maxlen, /* maximum length to allocate */
- xfs_rtxlen_t *len, /* out: actual length allocated */
- int wasdel, /* was a delayed allocation extent */
- xfs_rtxlen_t prod, /* extent product factor */
- xfs_rtxnum_t *rtblock); /* out: start rtext allocated */
-
-
-/*
* Initialize realtime fields in the mount structure.
*/
int /* error */
@@ -52,20 +31,6 @@ xfs_rtmount_inodes(
struct xfs_mount *mp); /* file system mount structure */
/*
- * Pick an extent for allocation at the start of a new realtime file.
- * Use the sequence number stored in the atime field of the bitmap inode.
- * Translate this to a fraction of the rtextents, and return the product
- * of rtextents and the fraction.
- * The fraction sequence is 0, 1/2, 1/4, 3/4, 1/8, ..., 7/8, 1/16, ...
- */
-int /* error */
-xfs_rtpick_extent(
- struct xfs_mount *mp, /* file system mount point */
- struct xfs_trans *tp, /* transaction pointer */
- xfs_rtxlen_t len, /* allocation length (rtextents) */
- xfs_rtxnum_t *pick); /* result rt extent */
-
-/*
* Grow the realtime area of the filesystem.
*/
int
@@ -75,8 +40,6 @@ xfs_growfs_rt(
int xfs_rtalloc_reinit_frextents(struct xfs_mount *mp);
#else
-# define xfs_rtallocate_extent(t,b,min,max,l,f,p,rb) (-ENOSYS)
-# define xfs_rtpick_extent(m,t,l,rb) (-ENOSYS)
# define xfs_growfs_rt(mp,in) (-ENOSYS)
# define xfs_rtalloc_reinit_frextents(m) (0)
static inline int /* error */
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 07857d967ee8..aff20ddd4a9f 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -894,10 +894,8 @@ xfs_fs_statfs(
STATIC void
xfs_save_resvblks(struct xfs_mount *mp)
{
- uint64_t resblks = 0;
-
mp->m_resblks_save = mp->m_resblks;
- xfs_reserve_blocks(mp, &resblks, NULL);
+ xfs_reserve_blocks(mp, 0);
}
STATIC void
@@ -911,7 +909,7 @@ xfs_restore_resvblks(struct xfs_mount *mp)
} else
resblks = xfs_default_resblks(mp);
- xfs_reserve_blocks(mp, &resblks, NULL);
+ xfs_reserve_blocks(mp, resblks);
}
/*
diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c
index 85e433df6a3f..92974a4414c8 100644
--- a/fs/xfs/xfs_symlink.c
+++ b/fs/xfs/xfs_symlink.c
@@ -23,6 +23,7 @@
#include "xfs_trans.h"
#include "xfs_ialloc.h"
#include "xfs_error.h"
+#include "xfs_health.h"
/* ----- Kernel only functions below ----- */
int
@@ -108,6 +109,8 @@ xfs_readlink(
if (xfs_is_shutdown(mp))
return -EIO;
+ if (xfs_ifork_zapped(ip, XFS_DATA_FORK))
+ return -EIO;
xfs_ilock(ip, XFS_ILOCK_SHARED);
@@ -128,10 +131,10 @@ xfs_readlink(
* The VFS crashes on a NULL pointer, so return -EFSCORRUPTED
* if if_data is junk.
*/
- if (XFS_IS_CORRUPT(ip->i_mount, !ip->i_df.if_u1.if_data))
+ if (XFS_IS_CORRUPT(ip->i_mount, !ip->i_df.if_data))
goto out;
- memcpy(link, ip->i_df.if_u1.if_data, pathlen + 1);
+ memcpy(link, ip->i_df.if_data, pathlen + 1);
error = 0;
} else {
error = xfs_readlink_bmap_ilocked(ip, link);
diff --git a/fs/xfs/xfs_sysctl.h b/fs/xfs/xfs_sysctl.h
index f78ad6b10ea5..276696a07040 100644
--- a/fs/xfs/xfs_sysctl.h
+++ b/fs/xfs/xfs_sysctl.h
@@ -85,6 +85,8 @@ struct xfs_globals {
int pwork_threads; /* parallel workqueue threads */
bool larp; /* log attribute replay */
#endif
+ int bload_leaf_slack; /* btree bulk load leaf slack */
+ int bload_node_slack; /* btree bulk load node slack */
int log_recovery_delay; /* log recovery delay (secs) */
int mount_delay; /* mount setup delay (secs) */
bool bug_on_assert; /* BUG() the kernel on assert failure */
diff --git a/fs/xfs/xfs_sysfs.c b/fs/xfs/xfs_sysfs.c
index a3c6b1548723..17485666b672 100644
--- a/fs/xfs/xfs_sysfs.c
+++ b/fs/xfs/xfs_sysfs.c
@@ -229,6 +229,15 @@ pwork_threads_show(
}
XFS_SYSFS_ATTR_RW(pwork_threads);
+/*
+ * The "LARP" (Logged extended Attribute Recovery Persistence) debugging knob
+ * sets the XFS_DA_OP_LOGGED flag on all xfs_attr_set operations performed on
+ * V5 filesystems. As a result, the intermediate progress of all setxattr and
+ * removexattr operations are tracked via the log and can be restarted during
+ * recovery. This is useful for testing xattr recovery prior to merging of the
+ * parent pointer feature which requires it to maintain consistency, and may be
+ * enabled for userspace xattrs in the future.
+ */
static ssize_t
larp_store(
struct kobject *kobject,
@@ -253,6 +262,58 @@ larp_show(
XFS_SYSFS_ATTR_RW(larp);
#endif /* DEBUG */
+STATIC ssize_t
+bload_leaf_slack_store(
+ struct kobject *kobject,
+ const char *buf,
+ size_t count)
+{
+ int ret;
+ int val;
+
+ ret = kstrtoint(buf, 0, &val);
+ if (ret)
+ return ret;
+
+ xfs_globals.bload_leaf_slack = val;
+ return count;
+}
+
+STATIC ssize_t
+bload_leaf_slack_show(
+ struct kobject *kobject,
+ char *buf)
+{
+ return snprintf(buf, PAGE_SIZE, "%d\n", xfs_globals.bload_leaf_slack);
+}
+XFS_SYSFS_ATTR_RW(bload_leaf_slack);
+
+STATIC ssize_t
+bload_node_slack_store(
+ struct kobject *kobject,
+ const char *buf,
+ size_t count)
+{
+ int ret;
+ int val;
+
+ ret = kstrtoint(buf, 0, &val);
+ if (ret)
+ return ret;
+
+ xfs_globals.bload_node_slack = val;
+ return count;
+}
+
+STATIC ssize_t
+bload_node_slack_show(
+ struct kobject *kobject,
+ char *buf)
+{
+ return snprintf(buf, PAGE_SIZE, "%d\n", xfs_globals.bload_node_slack);
+}
+XFS_SYSFS_ATTR_RW(bload_node_slack);
+
static struct attribute *xfs_dbg_attrs[] = {
ATTR_LIST(bug_on_assert),
ATTR_LIST(log_recovery_delay),
@@ -262,6 +323,8 @@ static struct attribute *xfs_dbg_attrs[] = {
ATTR_LIST(pwork_threads),
ATTR_LIST(larp),
#endif
+ ATTR_LIST(bload_leaf_slack),
+ ATTR_LIST(bload_node_slack),
NULL,
};
ATTRIBUTE_GROUPS(xfs_dbg);
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 3926cf7f2a6e..0984a1c884c7 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -67,6 +67,7 @@ struct xfs_buf_log_format;
struct xfs_inode_log_format;
struct xfs_bmbt_irec;
struct xfs_btree_cur;
+struct xfs_defer_op_type;
struct xfs_refcount_irec;
struct xfs_fsmap;
struct xfs_rmap_irec;
@@ -145,21 +146,23 @@ DEFINE_ATTR_LIST_EVENT(xfs_attr_leaf_list);
DEFINE_ATTR_LIST_EVENT(xfs_attr_node_list);
TRACE_EVENT(xlog_intent_recovery_failed,
- TP_PROTO(struct xfs_mount *mp, int error, void *function),
- TP_ARGS(mp, error, function),
+ TP_PROTO(struct xfs_mount *mp, const struct xfs_defer_op_type *ops,
+ int error),
+ TP_ARGS(mp, ops, error),
TP_STRUCT__entry(
__field(dev_t, dev)
+ __string(name, ops->name)
__field(int, error)
- __field(void *, function)
),
TP_fast_assign(
__entry->dev = mp->m_super->s_dev;
+ __assign_str(name, ops->name);
__entry->error = error;
- __entry->function = function;
),
- TP_printk("dev %d:%d error %d function %pS",
+ TP_printk("dev %d:%d optype %s error %d",
MAJOR(__entry->dev), MINOR(__entry->dev),
- __entry->error, __entry->function)
+ __get_str(name),
+ __entry->error)
);
DECLARE_EVENT_CLASS(xfs_perag_class,
@@ -2549,22 +2552,25 @@ DECLARE_EVENT_CLASS(xfs_defer_pending_class,
TP_ARGS(mp, dfp),
TP_STRUCT__entry(
__field(dev_t, dev)
- __field(int, type)
+ __string(name, dfp->dfp_ops->name)
__field(void *, intent)
+ __field(unsigned int, flags)
__field(char, committed)
__field(int, nr)
),
TP_fast_assign(
__entry->dev = mp ? mp->m_super->s_dev : 0;
- __entry->type = dfp->dfp_type;
+ __assign_str(name, dfp->dfp_ops->name);
__entry->intent = dfp->dfp_intent;
+ __entry->flags = dfp->dfp_flags;
__entry->committed = dfp->dfp_done != NULL;
__entry->nr = dfp->dfp_count;
),
- TP_printk("dev %d:%d optype %d intent %p committed %d nr %d",
+ TP_printk("dev %d:%d optype %s intent %p flags %s committed %d nr %d",
MAJOR(__entry->dev), MINOR(__entry->dev),
- __entry->type,
+ __get_str(name),
__entry->intent,
+ __print_flags(__entry->flags, "|", XFS_DEFER_PENDING_STRINGS),
__entry->committed,
__entry->nr)
)
@@ -2675,6 +2681,9 @@ DEFINE_DEFER_PENDING_EVENT(xfs_defer_cancel_list);
DEFINE_DEFER_PENDING_EVENT(xfs_defer_pending_finish);
DEFINE_DEFER_PENDING_EVENT(xfs_defer_pending_abort);
DEFINE_DEFER_PENDING_EVENT(xfs_defer_relog_intent);
+DEFINE_DEFER_PENDING_EVENT(xfs_defer_isolate_paused);
+DEFINE_DEFER_PENDING_EVENT(xfs_defer_item_pause);
+DEFINE_DEFER_PENDING_EVENT(xfs_defer_item_unpause);
#define DEFINE_BMAP_FREE_DEFERRED_EVENT DEFINE_PHYS_EXTENT_DEFERRED_EVENT
DEFINE_BMAP_FREE_DEFERRED_EVENT(xfs_bmap_free_defer);
@@ -2688,25 +2697,28 @@ DECLARE_EVENT_CLASS(xfs_defer_pending_item_class,
TP_ARGS(mp, dfp, item),
TP_STRUCT__entry(
__field(dev_t, dev)
- __field(int, type)
+ __string(name, dfp->dfp_ops->name)
__field(void *, intent)
__field(void *, item)
__field(char, committed)
+ __field(unsigned int, flags)
__field(int, nr)
),
TP_fast_assign(
__entry->dev = mp ? mp->m_super->s_dev : 0;
- __entry->type = dfp->dfp_type;
+ __assign_str(name, dfp->dfp_ops->name);
__entry->intent = dfp->dfp_intent;
__entry->item = item;
__entry->committed = dfp->dfp_done != NULL;
+ __entry->flags = dfp->dfp_flags;
__entry->nr = dfp->dfp_count;
),
- TP_printk("dev %d:%d optype %d intent %p item %p committed %d nr %d",
+ TP_printk("dev %d:%d optype %s intent %p item %p flags %s committed %d nr %d",
MAJOR(__entry->dev), MINOR(__entry->dev),
- __entry->type,
+ __get_str(name),
__entry->intent,
__entry->item,
+ __print_flags(__entry->flags, "|", XFS_DEFER_PENDING_STRINGS),
__entry->committed,
__entry->nr)
)
@@ -4399,8 +4411,6 @@ DEFINE_DAS_STATE_EVENT(xfs_attr_remove_iter_return);
DEFINE_DAS_STATE_EVENT(xfs_attr_rmtval_alloc);
DEFINE_DAS_STATE_EVENT(xfs_attr_rmtval_remove_return);
DEFINE_DAS_STATE_EVENT(xfs_attr_defer_add);
-DEFINE_DAS_STATE_EVENT(xfs_attr_defer_replace);
-DEFINE_DAS_STATE_EVENT(xfs_attr_defer_remove);
TRACE_EVENT(xfs_force_shutdown,
diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index 305c9d07bf1b..12d45e93f07d 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -1237,6 +1237,68 @@ out_cancel:
}
/*
+ * Try to reserve more blocks for a transaction.
+ *
+ * This is for callers that need to attach resources to a transaction, scan
+ * those resources to determine the space reservation requirements, and then
+ * modify the attached resources. In other words, online repair. This can
+ * fail due to ENOSPC, so the caller must be able to cancel the transaction
+ * without shutting down the fs.
+ */
+int
+xfs_trans_reserve_more(
+ struct xfs_trans *tp,
+ unsigned int blocks,
+ unsigned int rtextents)
+{
+ struct xfs_trans_res resv = { };
+
+ return xfs_trans_reserve(tp, &resv, blocks, rtextents);
+}
+
+/*
+ * Try to reserve more blocks and file quota for a transaction. Same
+ * conditions of usage as xfs_trans_reserve_more.
+ */
+int
+xfs_trans_reserve_more_inode(
+ struct xfs_trans *tp,
+ struct xfs_inode *ip,
+ unsigned int dblocks,
+ unsigned int rblocks,
+ bool force_quota)
+{
+ struct xfs_trans_res resv = { };
+ struct xfs_mount *mp = ip->i_mount;
+ unsigned int rtx = xfs_extlen_to_rtxlen(mp, rblocks);
+ int error;
+
+ ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
+
+ error = xfs_trans_reserve(tp, &resv, dblocks, rtx);
+ if (error)
+ return error;
+
+ if (!XFS_IS_QUOTA_ON(mp) || xfs_is_quota_inode(&mp->m_sb, ip->i_ino))
+ return 0;
+
+ if (tp->t_flags & XFS_TRANS_RESERVE)
+ force_quota = true;
+
+ error = xfs_trans_reserve_quota_nblks(tp, ip, dblocks, rblocks,
+ force_quota);
+ if (!error)
+ return 0;
+
+ /* Quota failed, give back the new reservation. */
+ xfs_mod_fdblocks(mp, dblocks, tp->t_flags & XFS_TRANS_RESERVE);
+ tp->t_blk_res -= dblocks;
+ xfs_mod_frextents(mp, rtx);
+ tp->t_rtx_res -= rtx;
+ return error;
+}
+
+/*
* Allocate an transaction in preparation for inode creation by reserving quota
* against the given dquots. Callers are not required to hold any inode locks.
*/
diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h
index 6e3646d524ce..08ce757c7454 100644
--- a/fs/xfs/xfs_trans.h
+++ b/fs/xfs/xfs_trans.h
@@ -78,11 +78,7 @@ struct xfs_item_ops {
xfs_lsn_t (*iop_committed)(struct xfs_log_item *, xfs_lsn_t);
uint (*iop_push)(struct xfs_log_item *, struct list_head *);
void (*iop_release)(struct xfs_log_item *);
- int (*iop_recover)(struct xfs_log_item *lip,
- struct list_head *capture_list);
bool (*iop_match)(struct xfs_log_item *item, uint64_t id);
- struct xfs_log_item *(*iop_relog)(struct xfs_log_item *intent,
- struct xfs_trans *tp);
struct xfs_log_item *(*iop_intent)(struct xfs_log_item *intent_done);
};
@@ -168,6 +164,8 @@ typedef struct xfs_trans {
int xfs_trans_alloc(struct xfs_mount *mp, struct xfs_trans_res *resp,
uint blocks, uint rtextents, uint flags,
struct xfs_trans **tpp);
+int xfs_trans_reserve_more(struct xfs_trans *tp,
+ unsigned int blocks, unsigned int rtextents);
int xfs_trans_alloc_empty(struct xfs_mount *mp,
struct xfs_trans **tpp);
void xfs_trans_mod_sb(xfs_trans_t *, uint, int64_t);
@@ -247,19 +245,13 @@ void xfs_trans_buf_copy_type(struct xfs_buf *dst_bp,
extern struct kmem_cache *xfs_trans_cache;
-static inline struct xfs_log_item *
-xfs_trans_item_relog(
- struct xfs_log_item *lip,
- struct xfs_trans *tp)
-{
- return lip->li_ops->iop_relog(lip, tp);
-}
-
struct xfs_dquot;
int xfs_trans_alloc_inode(struct xfs_inode *ip, struct xfs_trans_res *resv,
unsigned int dblocks, unsigned int rblocks, bool force,
struct xfs_trans **tpp);
+int xfs_trans_reserve_more_inode(struct xfs_trans *tp, struct xfs_inode *ip,
+ unsigned int dblocks, unsigned int rblocks, bool force_quota);
int xfs_trans_alloc_icreate(struct xfs_mount *mp, struct xfs_trans_res *resv,
struct xfs_dquot *udqp, struct xfs_dquot *gdqp,
struct xfs_dquot *pdqp, unsigned int dblocks,
diff --git a/fs/xfs/xfs_xattr.c b/fs/xfs/xfs_xattr.c
index 987843f84d03..364104e1b38a 100644
--- a/fs/xfs/xfs_xattr.c
+++ b/fs/xfs/xfs_xattr.c
@@ -136,6 +136,9 @@ xfs_xattr_get(const struct xattr_handler *handler, struct dentry *unused,
};
int error;
+ if (xfs_ifork_zapped(XFS_I(inode), XFS_ATTR_FORK))
+ return -EIO;
+
error = xfs_attr_get(&args);
if (error)
return error;
@@ -294,6 +297,9 @@ xfs_vn_listxattr(
struct inode *inode = d_inode(dentry);
int error;
+ if (xfs_ifork_zapped(XFS_I(inode), XFS_ATTR_FORK))
+ return -EIO;
+
/*
* First read the regular on-disk attributes.
*/
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 896c0079f64f..f5a97dec5169 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -3942,6 +3942,7 @@ enum mf_flags {
MF_UNPOISON = 1 << 4,
MF_SW_SIMULATED = 1 << 5,
MF_NO_RETRY = 1 << 6,
+ MF_MEM_PRE_REMOVE = 1 << 7,
};
int mf_dax_kill_procs(struct address_space *mapping, pgoff_t index,
unsigned long count, int mf_flags);
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index a0d9b4ac7d54..4f9b61f4a668 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -678,7 +678,7 @@ static void add_to_kill_fsdax(struct task_struct *tsk, struct page *p,
*/
static void collect_procs_fsdax(struct page *page,
struct address_space *mapping, pgoff_t pgoff,
- struct list_head *to_kill)
+ struct list_head *to_kill, bool pre_remove)
{
struct vm_area_struct *vma;
struct task_struct *tsk;
@@ -686,8 +686,15 @@ static void collect_procs_fsdax(struct page *page,
i_mmap_lock_read(mapping);
rcu_read_lock();
for_each_process(tsk) {
- struct task_struct *t = task_early_kill(tsk, true);
+ struct task_struct *t = tsk;
+ /*
+ * Search for all tasks while MF_MEM_PRE_REMOVE is set, because
+ * the current may not be the one accessing the fsdax page.
+ * Otherwise, search for the current task.
+ */
+ if (!pre_remove)
+ t = task_early_kill(tsk, true);
if (!t)
continue;
vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) {
@@ -1793,6 +1800,7 @@ int mf_dax_kill_procs(struct address_space *mapping, pgoff_t index,
dax_entry_t cookie;
struct page *page;
size_t end = index + count;
+ bool pre_remove = mf_flags & MF_MEM_PRE_REMOVE;
mf_flags |= MF_ACTION_REQUIRED | MF_MUST_KILL;
@@ -1804,9 +1812,14 @@ int mf_dax_kill_procs(struct address_space *mapping, pgoff_t index,
if (!page)
goto unlock;
- SetPageHWPoison(page);
+ if (!pre_remove)
+ SetPageHWPoison(page);
- collect_procs_fsdax(page, mapping, index, &to_kill);
+ /*
+ * The pre_remove case is revoking access, the memory is still
+ * good and could theoretically be put back into service.
+ */
+ collect_procs_fsdax(page, mapping, index, &to_kill, pre_remove);
unmap_and_kill(&to_kill, page_to_pfn(page), mapping,
index, mf_flags);
unlock: