summaryrefslogtreecommitdiffstats
path: root/fs/xfs/libxfs
diff options
context:
space:
mode:
Diffstat (limited to '')
-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.c131
-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.c106
-rw-r--r--fs/xfs/libxfs/xfs_rtbitmap.h4
-rw-r--r--fs/xfs/libxfs/xfs_sb.c20
-rw-r--r--fs/xfs/libxfs/xfs_sb.h2
-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.h20
48 files changed, 1477 insertions, 842 deletions
diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c
index f9f4d69464..39d9525270 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 2e0aef87d6..4b343c4fac 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 7fd1fea955..da1057bd0e 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 100ab5931b..3bd0a33fee 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 6bb8d295c3..0b956f8b9d 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 c65228efed..a7032bf0cd 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 e28d93d232..e965a48e7d 100644
--- a/fs/xfs/libxfs/xfs_attr.c
+++ b/fs/xfs/libxfs/xfs_attr.c
@@ -421,10 +421,10 @@ xfs_attr_complete_op(
bool do_replace = args->op_flags & XFS_DA_OP_REPLACE;
args->op_flags &= ~XFS_DA_OP_REPLACE;
- if (do_replace) {
- args->attr_filter &= ~XFS_ATTR_INCOMPLETE;
+ args->attr_filter &= ~XFS_ATTR_INCOMPLETE;
+ if (do_replace)
return replace_state;
- }
+
return XFS_DAS_DONE;
}
@@ -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 2580ae4720..6374bf1072 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 368f4d9fa1..9b9948639c 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 37578b369d..bc44222230 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 be62acffad..f362345467 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 e33470e397..f6b73f1bad 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 bf3f1b36fd..71f2d50f78 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 3e7a40a838..151b8491f6 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 6a6503ab0c..ea8d3659df 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 4d68a58be1..d906324e25 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 dd75e208b5..e276eba87c 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 f0d2976050..055ea43b1e 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 e576560b46..5457188bb4 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 ffa3df5b28..706baf36e1 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 f9015f88ec..24f9d1461f 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 f71679ce23..66a17910d0 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 8788ad5f6a..18a9fb92dd 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 f5462fd582..a766732815 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 00f960a703..3c256d4cc4 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 7404a9ff1a..1db2e60ba8 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 8cd37e6e9d..e1f83fc7b6 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 9a88aba158..382ab1e71c 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 99e796256c..6296993ff8 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 b83e54c709..2361a22035 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 fe824bb04a..f1412183bb 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 9258f01c00..42a5e1f227 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 773cf43494..f4e6b200cd 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 5a2e7ddfa7..f4569e18a8 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 96d307784c..96303249d2 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 a5100a11fa..9fe7a9564b 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 21a7e350b4..81885a6a02 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 646b3fa362..6709a7f8ba 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 783cd89ca1..9b56768a59 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 5c3987d8dc..0d80bd9914 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 fbb0b26374..76bf7f48cb 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 c269d70431..e31663cb7b 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;
diff --git a/fs/xfs/libxfs/xfs_rtbitmap.h b/fs/xfs/libxfs/xfs_rtbitmap.h
index c0637057d6..152a66750a 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,
diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index 1f74d0cd16..5bb6e2bd6d 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");
@@ -1375,3 +1377,17 @@ xfs_validate_stripe_geometry(
}
return true;
}
+
+/*
+ * 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);
+}
diff --git a/fs/xfs/libxfs/xfs_sb.h b/fs/xfs/libxfs/xfs_sb.h
index 19134b23c1..2e8e8d63d4 100644
--- a/fs/xfs/libxfs/xfs_sb.h
+++ b/fs/xfs/libxfs/xfs_sb.h
@@ -38,4 +38,6 @@ extern int xfs_sb_get_secondary(struct xfs_mount *mp,
extern bool xfs_validate_stripe_geometry(struct xfs_mount *mp,
__s64 sunit, __s64 swidth, int sectorsize, bool silent);
+uint8_t xfs_compute_rextslog(xfs_rtbxlen_t rtextents);
+
#endif /* __XFS_SB_H__ */
diff --git a/fs/xfs/libxfs/xfs_shared.h b/fs/xfs/libxfs/xfs_shared.h
index c4381388c0..4220d3584c 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 bdc777b9ec..160aa20aa4 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 533200c4cc..62e02d5380 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. */
@@ -245,4 +251,16 @@ bool xfs_verify_fileoff(struct xfs_mount *mp, xfs_fileoff_t off);
bool xfs_verify_fileext(struct xfs_mount *mp, xfs_fileoff_t off,
xfs_fileoff_t len);
+/* 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;
+}
+
#endif /* __XFS_TYPES_H__ */