summaryrefslogtreecommitdiffstats
path: root/fs/xfs/libxfs
diff options
context:
space:
mode:
Diffstat (limited to 'fs/xfs/libxfs')
-rw-r--r--fs/xfs/libxfs/xfs_ag.c12
-rw-r--r--fs/xfs/libxfs/xfs_ag_resv.c24
-rw-r--r--fs/xfs/libxfs/xfs_ag_resv.h2
-rw-r--r--fs/xfs/libxfs/xfs_alloc.c10
-rw-r--r--fs/xfs/libxfs/xfs_attr.c273
-rw-r--r--fs/xfs/libxfs/xfs_attr.h49
-rw-r--r--fs/xfs/libxfs/xfs_attr_leaf.c154
-rw-r--r--fs/xfs/libxfs/xfs_attr_leaf.h4
-rw-r--r--fs/xfs/libxfs/xfs_attr_remote.c102
-rw-r--r--fs/xfs/libxfs/xfs_attr_remote.h8
-rw-r--r--fs/xfs/libxfs/xfs_attr_sf.h1
-rw-r--r--fs/xfs/libxfs/xfs_bmap.c409
-rw-r--r--fs/xfs/libxfs/xfs_bmap.h13
-rw-r--r--fs/xfs/libxfs/xfs_da_btree.c189
-rw-r--r--fs/xfs/libxfs/xfs_da_btree.h34
-rw-r--r--fs/xfs/libxfs/xfs_da_format.h37
-rw-r--r--fs/xfs/libxfs/xfs_defer.c12
-rw-r--r--fs/xfs/libxfs/xfs_defer.h10
-rw-r--r--fs/xfs/libxfs/xfs_dir2.c281
-rw-r--r--fs/xfs/libxfs/xfs_dir2.h23
-rw-r--r--fs/xfs/libxfs/xfs_dir2_block.c42
-rw-r--r--fs/xfs/libxfs/xfs_dir2_data.c18
-rw-r--r--fs/xfs/libxfs/xfs_dir2_leaf.c100
-rw-r--r--fs/xfs/libxfs/xfs_dir2_node.c44
-rw-r--r--fs/xfs/libxfs/xfs_dir2_priv.h15
-rw-r--r--fs/xfs/libxfs/xfs_errortag.h4
-rw-r--r--fs/xfs/libxfs/xfs_exchmaps.c1235
-rw-r--r--fs/xfs/libxfs/xfs_exchmaps.h124
-rw-r--r--fs/xfs/libxfs/xfs_format.h34
-rw-r--r--fs/xfs/libxfs/xfs_fs.h158
-rw-r--r--fs/xfs/libxfs/xfs_health.h4
-rw-r--r--fs/xfs/libxfs/xfs_ialloc.c56
-rw-r--r--fs/xfs/libxfs/xfs_ialloc.h5
-rw-r--r--fs/xfs/libxfs/xfs_ialloc_btree.c4
-rw-r--r--fs/xfs/libxfs/xfs_inode_buf.c55
-rw-r--r--fs/xfs/libxfs/xfs_inode_fork.c57
-rw-r--r--fs/xfs/libxfs/xfs_inode_fork.h6
-rw-r--r--fs/xfs/libxfs/xfs_log_format.h89
-rw-r--r--fs/xfs/libxfs/xfs_log_recover.h4
-rw-r--r--fs/xfs/libxfs/xfs_log_rlimit.c46
-rw-r--r--fs/xfs/libxfs/xfs_ondisk.h6
-rw-r--r--fs/xfs/libxfs/xfs_parent.c379
-rw-r--r--fs/xfs/libxfs/xfs_parent.h110
-rw-r--r--fs/xfs/libxfs/xfs_rtbitmap.c57
-rw-r--r--fs/xfs/libxfs/xfs_rtbitmap.h17
-rw-r--r--fs/xfs/libxfs/xfs_sb.c16
-rw-r--r--fs/xfs/libxfs/xfs_shared.h6
-rw-r--r--fs/xfs/libxfs/xfs_symlink_remote.c54
-rw-r--r--fs/xfs/libxfs/xfs_symlink_remote.h8
-rw-r--r--fs/xfs/libxfs/xfs_trans_resv.c326
-rw-r--r--fs/xfs/libxfs/xfs_trans_space.c121
-rw-r--r--fs/xfs/libxfs/xfs_trans_space.h29
52 files changed, 4060 insertions, 816 deletions
diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c
index dc1873f76b..240e079cb3 100644
--- a/fs/xfs/libxfs/xfs_ag.c
+++ b/fs/xfs/libxfs/xfs_ag.c
@@ -194,7 +194,7 @@ xfs_initialize_perag_data(
pag = xfs_perag_get(mp, index);
error = xfs_alloc_read_agf(pag, NULL, 0, NULL);
if (!error)
- error = xfs_ialloc_read_agi(pag, NULL, NULL);
+ error = xfs_ialloc_read_agi(pag, NULL, 0, NULL);
if (error) {
xfs_perag_put(pag);
return error;
@@ -931,7 +931,7 @@ xfs_ag_shrink_space(
int error, err2;
ASSERT(pag->pag_agno == mp->m_sb.sb_agcount - 1);
- error = xfs_ialloc_read_agi(pag, *tpp, &agibp);
+ error = xfs_ialloc_read_agi(pag, *tpp, 0, &agibp);
if (error)
return error;
@@ -963,9 +963,7 @@ xfs_ag_shrink_space(
* Disable perag reservations so it doesn't cause the allocation request
* to fail. We'll reestablish reservation before we return.
*/
- error = xfs_ag_resv_free(pag);
- if (error)
- return error;
+ xfs_ag_resv_free(pag);
/* internal log shouldn't also show up in the free space btrees */
error = xfs_alloc_vextent_exact_bno(&args,
@@ -1062,7 +1060,7 @@ xfs_ag_extend_space(
ASSERT(pag->pag_agno == pag->pag_mount->m_sb.sb_agcount - 1);
- error = xfs_ialloc_read_agi(pag, tp, &bp);
+ error = xfs_ialloc_read_agi(pag, tp, 0, &bp);
if (error)
return error;
@@ -1119,7 +1117,7 @@ xfs_ag_get_geometry(
int error;
/* Lock the AG headers. */
- error = xfs_ialloc_read_agi(pag, NULL, &agi_bp);
+ error = xfs_ialloc_read_agi(pag, NULL, 0, &agi_bp);
if (error)
return error;
error = xfs_alloc_read_agf(pag, NULL, 0, &agf_bp);
diff --git a/fs/xfs/libxfs/xfs_ag_resv.c b/fs/xfs/libxfs/xfs_ag_resv.c
index da1057bd0e..216423df93 100644
--- a/fs/xfs/libxfs/xfs_ag_resv.c
+++ b/fs/xfs/libxfs/xfs_ag_resv.c
@@ -126,14 +126,13 @@ xfs_ag_resv_needed(
}
/* Clean out a reservation */
-static int
+static void
__xfs_ag_resv_free(
struct xfs_perag *pag,
enum xfs_ag_resv_type type)
{
struct xfs_ag_resv *resv;
xfs_extlen_t oldresv;
- int error;
trace_xfs_ag_resv_free(pag, type, 0);
@@ -149,30 +148,19 @@ __xfs_ag_resv_free(
oldresv = resv->ar_orig_reserved;
else
oldresv = resv->ar_reserved;
- error = xfs_mod_fdblocks(pag->pag_mount, oldresv, true);
+ xfs_add_fdblocks(pag->pag_mount, oldresv);
resv->ar_reserved = 0;
resv->ar_asked = 0;
resv->ar_orig_reserved = 0;
-
- if (error)
- trace_xfs_ag_resv_free_error(pag->pag_mount, pag->pag_agno,
- error, _RET_IP_);
- return error;
}
/* Free a per-AG reservation. */
-int
+void
xfs_ag_resv_free(
struct xfs_perag *pag)
{
- int error;
- int err2;
-
- error = __xfs_ag_resv_free(pag, XFS_AG_RESV_RMAPBT);
- err2 = __xfs_ag_resv_free(pag, XFS_AG_RESV_METADATA);
- if (err2 && !error)
- error = err2;
- return error;
+ __xfs_ag_resv_free(pag, XFS_AG_RESV_RMAPBT);
+ __xfs_ag_resv_free(pag, XFS_AG_RESV_METADATA);
}
static int
@@ -216,7 +204,7 @@ __xfs_ag_resv_init(
if (XFS_TEST_ERROR(false, mp, XFS_ERRTAG_AG_RESV_FAIL))
error = -ENOSPC;
else
- error = xfs_mod_fdblocks(mp, -(int64_t)hidden_space, true);
+ error = xfs_dec_fdblocks(mp, hidden_space, true);
if (error) {
trace_xfs_ag_resv_init_error(pag->pag_mount, pag->pag_agno,
error, _RET_IP_);
diff --git a/fs/xfs/libxfs/xfs_ag_resv.h b/fs/xfs/libxfs/xfs_ag_resv.h
index b74b210008..ff20ed93de 100644
--- a/fs/xfs/libxfs/xfs_ag_resv.h
+++ b/fs/xfs/libxfs/xfs_ag_resv.h
@@ -6,7 +6,7 @@
#ifndef __XFS_AG_RESV_H__
#define __XFS_AG_RESV_H__
-int xfs_ag_resv_free(struct xfs_perag *pag);
+void xfs_ag_resv_free(struct xfs_perag *pag);
int xfs_ag_resv_init(struct xfs_perag *pag, struct xfs_trans *tp);
bool xfs_ag_resv_critical(struct xfs_perag *pag, enum xfs_ag_resv_type type);
diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index 9da52e9217..6c55a6e88e 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -79,7 +79,7 @@ xfs_prealloc_blocks(
}
/*
- * The number of blocks per AG that we withhold from xfs_mod_fdblocks to
+ * The number of blocks per AG that we withhold from xfs_dec_fdblocks to
* guarantee that we can refill the AGFL prior to allocating space in a nearly
* full AG. Although the space described by the free space btrees, the
* blocks used by the freesp btrees themselves, and the blocks owned by the
@@ -89,7 +89,7 @@ xfs_prealloc_blocks(
* until the fs goes down, we subtract this many AG blocks from the incore
* fdblocks to ensure user allocation does not overcommit the space the
* filesystem needs for the AGFLs. The rmap btree uses a per-AG reservation to
- * withhold space from xfs_mod_fdblocks, so we do not account for that here.
+ * withhold space from xfs_dec_fdblocks, so we do not account for that here.
*/
#define XFS_ALLOCBT_AGFL_RESERVE 4
@@ -1008,13 +1008,12 @@ xfs_alloc_cur_finish(
struct xfs_alloc_arg *args,
struct xfs_alloc_cur *acur)
{
- struct xfs_agf __maybe_unused *agf = args->agbp->b_addr;
int error;
ASSERT(acur->cnt && acur->bnolt);
ASSERT(acur->bno >= acur->rec_bno);
ASSERT(acur->bno + acur->len <= acur->rec_bno + acur->rec_len);
- ASSERT(acur->rec_bno + acur->rec_len <= be32_to_cpu(agf->agf_length));
+ ASSERT(xfs_verify_agbext(args->pag, acur->rec_bno, acur->rec_len));
error = xfs_alloc_fixup_trees(acur->cnt, acur->bnolt, acur->rec_bno,
acur->rec_len, acur->bno, acur->len, 0);
@@ -1217,7 +1216,6 @@ STATIC int /* error */
xfs_alloc_ag_vextent_exact(
xfs_alloc_arg_t *args) /* allocation argument structure */
{
- struct xfs_agf __maybe_unused *agf = args->agbp->b_addr;
struct xfs_btree_cur *bno_cur;/* by block-number btree cursor */
struct xfs_btree_cur *cnt_cur;/* by count btree cursor */
int error;
@@ -1297,7 +1295,7 @@ xfs_alloc_ag_vextent_exact(
*/
cnt_cur = xfs_cntbt_init_cursor(args->mp, args->tp, args->agbp,
args->pag);
- ASSERT(args->agbno + args->len <= be32_to_cpu(agf->agf_length));
+ ASSERT(xfs_verify_agbext(args->pag, args->agbno, args->len));
error = xfs_alloc_fixup_trees(cnt_cur, bno_cur, fbno, flen, args->agbno,
args->len, XFSA_FIXUP_BNO_OK);
if (error) {
diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c
index 673a4b6d2e..f30bcc6410 100644
--- a/fs/xfs/libxfs/xfs_attr.c
+++ b/fs/xfs/libxfs/xfs_attr.c
@@ -26,6 +26,7 @@
#include "xfs_trace.h"
#include "xfs_attr_item.h"
#include "xfs_xattr.h"
+#include "xfs_parent.h"
struct kmem_cache *xfs_attr_intent_cache;
@@ -87,6 +88,8 @@ xfs_attr_is_leaf(
struct xfs_iext_cursor icur;
struct xfs_bmbt_irec imap;
+ ASSERT(!xfs_need_iread_extents(ifp));
+
if (ifp->if_nextents != 1 || ifp->if_format != XFS_DINODE_FMT_EXTENTS)
return false;
@@ -224,11 +227,21 @@ int
xfs_attr_get_ilocked(
struct xfs_da_args *args)
{
+ int error;
+
xfs_assert_ilocked(args->dp, XFS_ILOCK_SHARED | XFS_ILOCK_EXCL);
if (!xfs_inode_hasattr(args->dp))
return -ENOATTR;
+ /*
+ * The incore attr fork iext tree must be loaded for xfs_attr_is_leaf
+ * to work correctly.
+ */
+ error = xfs_iread_extents(args->trans, args->dp, XFS_ATTR_FORK);
+ if (error)
+ return error;
+
if (args->dp->i_af.if_format == XFS_DINODE_FMT_LOCAL)
return xfs_attr_shortform_getvalue(args);
if (xfs_attr_is_leaf(args->dp))
@@ -264,9 +277,11 @@ xfs_attr_get(
if (xfs_is_shutdown(args->dp->i_mount))
return -EIO;
+ if (!args->owner)
+ args->owner = args->dp->i_ino;
args->geo = args->dp->i_mount->m_attr_geo;
args->whichfork = XFS_ATTR_FORK;
- args->hashval = xfs_da_hashname(args->name, args->namelen);
+ xfs_attr_sethash(args);
/* Entirely possible to look up a name which doesn't exist */
args->op_flags = XFS_DA_OP_OKNOENT;
@@ -314,26 +329,20 @@ xfs_attr_calc_size(
return nblks;
}
-/* Initialize transaction reservation for attr operations */
-void
-xfs_init_attr_trans(
- struct xfs_da_args *args,
- struct xfs_trans_res *tres,
- unsigned int *total)
+/* Initialize transaction reservation for an xattr set/replace/upsert */
+inline struct xfs_trans_res
+xfs_attr_set_resv(
+ const struct xfs_da_args *args)
{
- struct xfs_mount *mp = args->dp->i_mount;
-
- if (args->value) {
- tres->tr_logres = M_RES(mp)->tr_attrsetm.tr_logres +
- M_RES(mp)->tr_attrsetrt.tr_logres *
- args->total;
- tres->tr_logcount = XFS_ATTRSET_LOG_COUNT;
- tres->tr_logflags = XFS_TRANS_PERM_LOG_RES;
- *total = args->total;
- } else {
- *tres = M_RES(mp)->tr_attrrm;
- *total = XFS_ATTRRM_SPACE_RES(mp);
- }
+ struct xfs_mount *mp = args->dp->i_mount;
+ struct xfs_trans_res ret = {
+ .tr_logres = M_RES(mp)->tr_attrsetm.tr_logres +
+ M_RES(mp)->tr_attrsetrt.tr_logres * args->total,
+ .tr_logcount = XFS_ATTRSET_LOG_COUNT,
+ .tr_logflags = XFS_TRANS_PERM_LOG_RES,
+ };
+
+ return ret;
}
/*
@@ -363,7 +372,7 @@ xfs_attr_try_sf_addname(
* Commit the shortform mods, and we're done.
* NOTE: this is also the error path (EEXIST, etc).
*/
- if (!error && !(args->op_flags & XFS_DA_OP_NOTIME))
+ if (!error)
xfs_trans_ichgtime(args->trans, dp, XFS_ICHGTIME_CHG);
if (xfs_has_wsync(dp->i_mount))
@@ -401,6 +410,50 @@ out:
return error;
}
+/* Compute the hash value for a user/root/secure extended attribute */
+xfs_dahash_t
+xfs_attr_hashname(
+ const uint8_t *name,
+ int namelen)
+{
+ return xfs_da_hashname(name, namelen);
+}
+
+/* Compute the hash value for any extended attribute from any namespace. */
+xfs_dahash_t
+xfs_attr_hashval(
+ struct xfs_mount *mp,
+ unsigned int attr_flags,
+ const uint8_t *name,
+ int namelen,
+ const void *value,
+ int valuelen)
+{
+ ASSERT(xfs_attr_check_namespace(attr_flags));
+
+ if (attr_flags & XFS_ATTR_PARENT)
+ return xfs_parent_hashattr(mp, name, namelen, value, valuelen);
+
+ return xfs_attr_hashname(name, namelen);
+}
+
+/*
+ * PPTR_REPLACE operations require the caller to set the old and new names and
+ * values explicitly. Update the canonical fields to the new name and value
+ * here now that the removal phase has finished.
+ */
+static void
+xfs_attr_update_pptr_replace_args(
+ struct xfs_da_args *args)
+{
+ ASSERT(args->new_namelen > 0);
+ args->name = args->new_name;
+ args->namelen = args->new_namelen;
+ args->value = args->new_value;
+ args->valuelen = args->new_valuelen;
+ xfs_attr_sethash(args);
+}
+
/*
* Handle the state change on completion of a multi-state attr operation.
*
@@ -418,14 +471,15 @@ xfs_attr_complete_op(
enum xfs_delattr_state replace_state)
{
struct xfs_da_args *args = attr->xattri_da_args;
- bool do_replace = args->op_flags & XFS_DA_OP_REPLACE;
+
+ if (!(args->op_flags & XFS_DA_OP_REPLACE))
+ replace_state = XFS_DAS_DONE;
+ else if (xfs_attr_intent_op(attr) == XFS_ATTRI_OP_FLAGS_PPTR_REPLACE)
+ xfs_attr_update_pptr_replace_args(args);
args->op_flags &= ~XFS_DA_OP_REPLACE;
args->attr_filter &= ~XFS_ATTR_INCOMPLETE;
- if (do_replace)
- return replace_state;
-
- return XFS_DAS_DONE;
+ return replace_state;
}
static int
@@ -647,8 +701,8 @@ xfs_attr_leaf_remove_attr(
int forkoff;
int error;
- error = xfs_attr3_leaf_read(args->trans, args->dp, args->blkno,
- &bp);
+ error = xfs_attr3_leaf_read(args->trans, args->dp, args->owner,
+ args->blkno, &bp);
if (error)
return error;
@@ -679,7 +733,7 @@ xfs_attr_leaf_shrink(
if (!xfs_attr_is_leaf(dp))
return 0;
- error = xfs_attr3_leaf_read(args->trans, args->dp, 0, &bp);
+ error = xfs_attr3_leaf_read(args->trans, args->dp, args->owner, 0, &bp);
if (error)
return error;
@@ -868,6 +922,11 @@ xfs_attr_lookup(
return -ENOATTR;
}
+ /* Prerequisite for xfs_attr_is_leaf */
+ error = xfs_iread_extents(args->trans, args->dp, XFS_ATTR_FORK);
+ if (error)
+ return error;
+
if (xfs_attr_is_leaf(dp)) {
error = xfs_attr_leaf_hasname(args, &bp);
@@ -883,74 +942,72 @@ xfs_attr_lookup(
return error;
}
-static void
-xfs_attr_defer_add(
- struct xfs_da_args *args,
- unsigned int op_flags)
+int
+xfs_attr_add_fork(
+ struct xfs_inode *ip, /* incore inode pointer */
+ int size, /* space new attribute needs */
+ int rsvd) /* xact may use reserved blks */
{
+ struct xfs_mount *mp = ip->i_mount;
+ struct xfs_trans *tp; /* transaction pointer */
+ unsigned int blks; /* space reservation */
+ int error; /* error return value */
- struct xfs_attr_intent *new;
+ ASSERT(!XFS_NOT_DQATTACHED(mp, ip));
- new = kmem_cache_zalloc(xfs_attr_intent_cache,
- GFP_KERNEL | __GFP_NOFAIL);
- new->xattri_op_flags = op_flags;
- new->xattri_da_args = args;
+ blks = XFS_ADDAFORK_SPACE_RES(mp);
- 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);
- }
+ error = xfs_trans_alloc_inode(ip, &M_RES(mp)->tr_addafork, blks, 0,
+ rsvd, &tp);
+ if (error)
+ return error;
+
+ if (xfs_inode_has_attr_fork(ip))
+ goto trans_cancel;
+
+ error = xfs_bmap_add_attrfork(tp, ip, size, rsvd);
+ if (error)
+ goto trans_cancel;
- xfs_defer_add(args->trans, &new->xattri_list, &xfs_attr_defer_type);
- trace_xfs_attr_defer_add(new->xattri_dela_state, args->dp);
+ error = xfs_trans_commit(tp);
+ xfs_iunlock(ip, XFS_ILOCK_EXCL);
+ return error;
+
+trans_cancel:
+ xfs_trans_cancel(tp);
+ xfs_iunlock(ip, XFS_ILOCK_EXCL);
+ return error;
}
/*
- * Note: If args->value is NULL the attribute will be removed, just like the
- * Linux ->setattr API.
+ * Make a change to the xattr structure.
+ *
+ * The caller must have initialized @args, attached dquots, and must not hold
+ * any ILOCKs. Reserved data blocks may be used if @rsvd is set.
+ *
+ * Returns -EEXIST for XFS_ATTRUPDATE_CREATE if the name already exists.
+ * Returns -ENOATTR for XFS_ATTRUPDATE_REMOVE if the name does not exist.
+ * Returns 0 on success, or a negative errno if something else went wrong.
*/
int
xfs_attr_set(
- struct xfs_da_args *args)
+ struct xfs_da_args *args,
+ enum xfs_attr_update op,
+ bool rsvd)
{
struct xfs_inode *dp = args->dp;
struct xfs_mount *mp = dp->i_mount;
struct xfs_trans_res tres;
- bool rsvd = (args->attr_filter & XFS_ATTR_ROOT);
int error, local;
int rmt_blks = 0;
- unsigned int total;
+ unsigned int total = 0;
- if (xfs_is_shutdown(dp->i_mount))
- return -EIO;
+ ASSERT(!args->trans);
- error = xfs_qm_dqattach(dp);
- if (error)
- return error;
-
- args->geo = mp->m_attr_geo;
- args->whichfork = XFS_ATTR_FORK;
- args->hashval = xfs_da_hashname(args->name, args->namelen);
-
- /*
- * We have no control over the attribute names that userspace passes us
- * to remove, so we have to allow the name lookup prior to attribute
- * removal to fail as well. Preserve the logged flag, since we need
- * to pass that through to the logging code.
- */
- args->op_flags = XFS_DA_OP_OKNOENT |
- (args->op_flags & XFS_DA_OP_LOGGED);
-
- if (args->value) {
+ switch (op) {
+ case XFS_ATTRUPDATE_UPSERT:
+ case XFS_ATTRUPDATE_CREATE:
+ case XFS_ATTRUPDATE_REPLACE:
XFS_STATS_INC(mp, xs_attr_set);
args->total = xfs_attr_calc_size(args, &local);
@@ -963,33 +1020,36 @@ xfs_attr_set(
xfs_attr_sf_entsize_byname(args->namelen,
args->valuelen);
- error = xfs_bmap_add_attrfork(dp, sf_size, rsvd);
+ error = xfs_attr_add_fork(dp, sf_size, rsvd);
if (error)
return error;
}
if (!local)
rmt_blks = xfs_attr3_rmt_blocks(mp, args->valuelen);
- } else {
+
+ tres = xfs_attr_set_resv(args);
+ total = args->total;
+ break;
+ case XFS_ATTRUPDATE_REMOVE:
XFS_STATS_INC(mp, xs_attr_remove);
- rmt_blks = xfs_attr3_rmt_blocks(mp, XFS_XATTR_SIZE_MAX);
+ rmt_blks = xfs_attr3_max_rmt_blocks(mp);
+ tres = M_RES(mp)->tr_attrrm;
+ total = XFS_ATTRRM_SPACE_RES(mp);
+ break;
}
/*
* Root fork attributes can use reserved data blocks for this
* operation if necessary
*/
- xfs_init_attr_trans(args, &tres, &total);
error = xfs_trans_alloc_inode(dp, &tres, total, 0, rsvd, &args->trans);
if (error)
return error;
- if (args->value || xfs_inode_hasattr(dp)) {
- error = xfs_iext_count_may_overflow(dp, XFS_ATTR_FORK,
+ if (op != XFS_ATTRUPDATE_REMOVE || xfs_inode_hasattr(dp)) {
+ error = xfs_iext_count_extend(args->trans, dp, XFS_ATTR_FORK,
XFS_IEXT_ATTR_MANIP_CNT(rmt_blks));
- if (error == -EFBIG)
- error = xfs_iext_count_upgrade(args->trans, dp,
- XFS_IEXT_ATTR_MANIP_CNT(rmt_blks));
if (error)
goto out_trans_cancel;
}
@@ -997,26 +1057,26 @@ xfs_attr_set(
error = xfs_attr_lookup(args);
switch (error) {
case -EEXIST:
- if (!args->value) {
+ if (op == XFS_ATTRUPDATE_REMOVE) {
/* if no value, we are performing a remove operation */
- xfs_attr_defer_add(args, XFS_ATTRI_OP_FLAGS_REMOVE);
+ xfs_attr_defer_add(args, XFS_ATTR_DEFER_REMOVE);
break;
}
/* Pure create fails if the attr already exists */
- if (args->attr_flags & XATTR_CREATE)
+ if (op == XFS_ATTRUPDATE_CREATE)
goto out_trans_cancel;
- xfs_attr_defer_add(args, XFS_ATTRI_OP_FLAGS_REPLACE);
+ xfs_attr_defer_add(args, XFS_ATTR_DEFER_REPLACE);
break;
case -ENOATTR:
/* Can't remove what isn't there. */
- if (!args->value)
+ if (op == XFS_ATTRUPDATE_REMOVE)
goto out_trans_cancel;
/* Pure replace fails if no existing attr to replace. */
- if (args->attr_flags & XATTR_REPLACE)
+ if (op == XFS_ATTRUPDATE_REPLACE)
goto out_trans_cancel;
- xfs_attr_defer_add(args, XFS_ATTRI_OP_FLAGS_SET);
+ xfs_attr_defer_add(args, XFS_ATTR_DEFER_SET);
break;
default:
goto out_trans_cancel;
@@ -1029,8 +1089,7 @@ xfs_attr_set(
if (xfs_has_wsync(mp))
xfs_trans_set_sync(args->trans);
- if (!(args->op_flags & XFS_DA_OP_NOTIME))
- xfs_trans_ichgtime(args->trans, dp, XFS_ICHGTIME_CHG);
+ xfs_trans_ichgtime(args->trans, dp, XFS_ICHGTIME_CHG);
/*
* Commit the last in the sequence of transactions.
@@ -1039,6 +1098,7 @@ xfs_attr_set(
error = xfs_trans_commit(args->trans);
out_unlock:
xfs_iunlock(dp, XFS_ILOCK_EXCL);
+ args->trans = NULL;
return error;
out_trans_cancel:
@@ -1051,7 +1111,7 @@ out_trans_cancel:
* External routines when attribute list is inside the inode
*========================================================================*/
-static inline int xfs_attr_sf_totsize(struct xfs_inode *dp)
+int xfs_attr_sf_totsize(struct xfs_inode *dp)
{
struct xfs_attr_sf_hdr *sf = dp->i_af.if_data;
@@ -1154,7 +1214,7 @@ xfs_attr_leaf_try_add(
struct xfs_buf *bp;
int error;
- error = xfs_attr3_leaf_read(args->trans, args->dp, 0, &bp);
+ error = xfs_attr3_leaf_read(args->trans, args->dp, args->owner, 0, &bp);
if (error)
return error;
@@ -1202,7 +1262,7 @@ xfs_attr_leaf_hasname(
{
int error = 0;
- error = xfs_attr3_leaf_read(args->trans, args->dp, 0, bp);
+ error = xfs_attr3_leaf_read(args->trans, args->dp, args->owner, 0, bp);
if (error)
return error;
@@ -1511,12 +1571,23 @@ out_release:
return error;
}
+/* Enforce that there is at most one namespace bit per attr. */
+inline bool xfs_attr_check_namespace(unsigned int attr_flags)
+{
+ return hweight32(attr_flags & XFS_ATTR_NSP_ONDISK_MASK) < 2;
+}
+
/* Returns true if the attribute entry name is valid. */
bool
xfs_attr_namecheck(
+ unsigned int attr_flags,
const void *name,
size_t length)
{
+ /* Only one namespace bit allowed. */
+ if (!xfs_attr_check_namespace(attr_flags))
+ return false;
+
/*
* MAXNAMELEN includes the trailing null, but (name/length) leave it
* out, so use >= for the length check.
@@ -1524,6 +1595,10 @@ xfs_attr_namecheck(
if (length >= MAXNAMELEN)
return false;
+ /* Parent pointers have their own validation. */
+ if (attr_flags & XFS_ATTR_PARENT)
+ return xfs_parent_namecheck(attr_flags, name, length);
+
/* There shouldn't be any nulls here */
return !memchr(name, 0, length);
}
diff --git a/fs/xfs/libxfs/xfs_attr.h b/fs/xfs/libxfs/xfs_attr.h
index 81be9b3e40..0e51d0723f 100644
--- a/fs/xfs/libxfs/xfs_attr.h
+++ b/fs/xfs/libxfs/xfs_attr.h
@@ -47,8 +47,9 @@ struct xfs_attrlist_cursor_kern {
/* void; state communicated via *context */
-typedef void (*put_listent_func_t)(struct xfs_attr_list_context *, int,
- unsigned char *, int, int);
+typedef void (*put_listent_func_t)(struct xfs_attr_list_context *context,
+ int flags, unsigned char *name, int namelen, void *value,
+ int valuelen);
struct xfs_attr_list_context {
struct xfs_trans *tp;
@@ -510,8 +511,8 @@ struct xfs_attr_intent {
struct xfs_da_args *xattri_da_args;
/*
- * Shared buffer containing the attr name and value so that the logging
- * code can share large memory buffers between log items.
+ * Shared buffer containing the attr name, new name, and value so that
+ * the logging code can share large memory buffers between log items.
*/
struct xfs_attri_log_nameval *xattri_nameval;
@@ -529,6 +530,11 @@ struct xfs_attr_intent {
struct xfs_bmbt_irec xattri_map;
};
+static inline unsigned int
+xfs_attr_intent_op(const struct xfs_attr_intent *attr)
+{
+ return attr->xattri_op_flags & XFS_ATTRI_OP_FLAGS_TYPE_MASK;
+}
/*========================================================================
* Function prototypes for the kernel.
@@ -544,13 +550,22 @@ int xfs_inode_hasattr(struct xfs_inode *ip);
bool xfs_attr_is_leaf(struct xfs_inode *ip);
int xfs_attr_get_ilocked(struct xfs_da_args *args);
int xfs_attr_get(struct xfs_da_args *args);
-int xfs_attr_set(struct xfs_da_args *args);
+
+enum xfs_attr_update {
+ XFS_ATTRUPDATE_REMOVE, /* remove attr */
+ XFS_ATTRUPDATE_UPSERT, /* set value, replace any existing attr */
+ XFS_ATTRUPDATE_CREATE, /* set value, fail if attr already exists */
+ XFS_ATTRUPDATE_REPLACE, /* set value, fail if attr does not exist */
+};
+
+int xfs_attr_set(struct xfs_da_args *args, enum xfs_attr_update op, bool rsvd);
int xfs_attr_set_iter(struct xfs_attr_intent *attr);
int xfs_attr_remove_iter(struct xfs_attr_intent *attr);
-bool xfs_attr_namecheck(const void *name, size_t length);
+bool xfs_attr_check_namespace(unsigned int attr_flags);
+bool xfs_attr_namecheck(unsigned int attr_flags, const void *name,
+ size_t length);
int xfs_attr_calc_size(struct xfs_da_args *args, int *local);
-void xfs_init_attr_trans(struct xfs_da_args *args, struct xfs_trans_res *tres,
- unsigned int *total);
+struct xfs_trans_res xfs_attr_set_resv(const struct xfs_da_args *args);
/*
* Check to see if the attr should be upgraded from non-existent or shortform to
@@ -590,7 +605,6 @@ xfs_attr_init_add_state(struct xfs_da_args *args)
static inline enum xfs_delattr_state
xfs_attr_init_remove_state(struct xfs_da_args *args)
{
- args->op_flags |= XFS_DA_OP_REMOVE;
if (xfs_attr_is_shortform(args->dp))
return XFS_DAS_SF_REMOVE;
if (xfs_attr_is_leaf(args->dp))
@@ -614,8 +628,25 @@ xfs_attr_init_replace_state(struct xfs_da_args *args)
return xfs_attr_init_add_state(args);
}
+xfs_dahash_t xfs_attr_hashname(const uint8_t *name, int namelen);
+
+xfs_dahash_t xfs_attr_hashval(struct xfs_mount *mp, unsigned int attr_flags,
+ const uint8_t *name, int namelen, const void *value,
+ int valuelen);
+
+/* Set the hash value for any extended attribute from any namespace. */
+static inline void xfs_attr_sethash(struct xfs_da_args *args)
+{
+ args->hashval = xfs_attr_hashval(args->dp->i_mount, args->attr_filter,
+ args->name, args->namelen,
+ args->value, args->valuelen);
+}
+
extern struct kmem_cache *xfs_attr_intent_cache;
int __init xfs_attr_intent_init_cache(void);
void xfs_attr_intent_destroy_cache(void);
+int xfs_attr_sf_totsize(struct xfs_inode *dp);
+int xfs_attr_add_fork(struct xfs_inode *ip, int size, int rsvd);
+
#endif /* __XFS_ATTR_H__ */
diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c
index ac904cc1a9..b9e98950eb 100644
--- a/fs/xfs/libxfs/xfs_attr_leaf.c
+++ b/fs/xfs/libxfs/xfs_attr_leaf.c
@@ -388,6 +388,27 @@ xfs_attr3_leaf_verify(
return NULL;
}
+xfs_failaddr_t
+xfs_attr3_leaf_header_check(
+ struct xfs_buf *bp,
+ xfs_ino_t owner)
+{
+ struct xfs_mount *mp = bp->b_mount;
+
+ if (xfs_has_crc(mp)) {
+ struct xfs_attr3_leafblock *hdr3 = bp->b_addr;
+
+ if (hdr3->hdr.info.hdr.magic !=
+ cpu_to_be16(XFS_ATTR3_LEAF_MAGIC))
+ return __this_address;
+
+ if (be64_to_cpu(hdr3->hdr.info.owner) != owner)
+ return __this_address;
+ }
+
+ return NULL;
+}
+
static void
xfs_attr3_leaf_write_verify(
struct xfs_buf *bp)
@@ -448,16 +469,30 @@ int
xfs_attr3_leaf_read(
struct xfs_trans *tp,
struct xfs_inode *dp,
+ xfs_ino_t owner,
xfs_dablk_t bno,
struct xfs_buf **bpp)
{
+ xfs_failaddr_t fa;
int err;
err = xfs_da_read_buf(tp, dp, bno, 0, bpp, XFS_ATTR_FORK,
&xfs_attr3_leaf_buf_ops);
- if (!err && tp && *bpp)
+ if (err || !(*bpp))
+ return err;
+
+ fa = xfs_attr3_leaf_header_check(*bpp, owner);
+ if (fa) {
+ __xfs_buf_mark_corrupt(*bpp, fa);
+ xfs_trans_brelse(tp, *bpp);
+ *bpp = NULL;
+ xfs_dirattr_mark_sick(dp, XFS_ATTR_FORK);
+ return -EFSCORRUPTED;
+ }
+
+ if (tp)
xfs_trans_buf_set_type(tp, *bpp, XFS_BLFT_ATTR_LEAF_BUF);
- return err;
+ return 0;
}
/*========================================================================
@@ -472,28 +507,57 @@ xfs_attr3_leaf_read(
* INCOMPLETE flag will not be set in attr->attr_filter, but rather
* XFS_DA_OP_RECOVERY will be set in args->op_flags.
*/
+static inline unsigned int xfs_attr_match_mask(const struct xfs_da_args *args)
+{
+ if (args->op_flags & XFS_DA_OP_RECOVERY)
+ return XFS_ATTR_NSP_ONDISK_MASK;
+ return XFS_ATTR_NSP_ONDISK_MASK | XFS_ATTR_INCOMPLETE;
+}
+
+static inline bool
+xfs_attr_parent_match(
+ const struct xfs_da_args *args,
+ const void *value,
+ unsigned int valuelen)
+{
+ ASSERT(args->value != NULL);
+
+ /* Parent pointers do not use remote values */
+ if (!value)
+ return false;
+
+ /*
+ * The only value we support is a parent rec. However, we'll accept
+ * any valuelen so that offline repair can delete ATTR_PARENT values
+ * that are not parent pointers.
+ */
+ if (valuelen != args->valuelen)
+ return false;
+
+ return memcmp(args->value, value, valuelen) == 0;
+}
+
static bool
xfs_attr_match(
struct xfs_da_args *args,
- uint8_t namelen,
- unsigned char *name,
- int flags)
+ unsigned int attr_flags,
+ const unsigned char *name,
+ unsigned int namelen,
+ const void *value,
+ unsigned int valuelen)
{
+ unsigned int mask = xfs_attr_match_mask(args);
if (args->namelen != namelen)
return false;
+ if ((args->attr_filter & mask) != (attr_flags & mask))
+ return false;
if (memcmp(args->name, name, namelen) != 0)
return false;
- /* Recovery ignores the INCOMPLETE flag. */
- if ((args->op_flags & XFS_DA_OP_RECOVERY) &&
- args->attr_filter == (flags & XFS_ATTR_NSP_ONDISK_MASK))
- return true;
+ if (attr_flags & XFS_ATTR_PARENT)
+ return xfs_attr_parent_match(args, value, valuelen);
- /* All remaining matches need to be filtered by INCOMPLETE state. */
- if (args->attr_filter !=
- (flags & (XFS_ATTR_NSP_ONDISK_MASK | XFS_ATTR_INCOMPLETE)))
- return false;
return true;
}
@@ -504,6 +568,13 @@ xfs_attr_copy_value(
int valuelen)
{
/*
+ * Parent pointer lookups require the caller to specify the name and
+ * value, so don't copy anything.
+ */
+ if (args->attr_filter & XFS_ATTR_PARENT)
+ return 0;
+
+ /*
* No copy if all we have to do is get the length
*/
if (!args->valuelen) {
@@ -711,8 +782,9 @@ xfs_attr_sf_findname(
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))
+ if (xfs_attr_match(args, sfe->flags, sfe->nameval,
+ sfe->namelen, &sfe->nameval[sfe->namelen],
+ sfe->valuelen))
return sfe;
}
@@ -819,7 +891,8 @@ xfs_attr_sf_removename(
*/
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))) {
+ !(args->op_flags & (XFS_DA_OP_ADDNAME | XFS_DA_OP_REPLACE)) &&
+ !xfs_has_parent(mp)) {
xfs_attr_fork_remove(dp, args->trans);
} else {
xfs_idata_realloc(dp, -size, XFS_ATTR_FORK);
@@ -828,7 +901,8 @@ xfs_attr_sf_removename(
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);
+ dp->i_df.if_format == XFS_DINODE_FMT_BTREE ||
+ xfs_has_parent(mp));
xfs_trans_log_inode(args->trans, dp,
XFS_ILOG_CORE | XFS_ILOG_ADATA);
}
@@ -904,6 +978,7 @@ xfs_attr_shortform_to_leaf(
nargs.whichfork = XFS_ATTR_FORK;
nargs.trans = args->trans;
nargs.op_flags = XFS_DA_OP_OKNOENT;
+ nargs.owner = args->owner;
sfe = xfs_attr_sf_firstentry(sf);
for (i = 0; i < sf->count; i++) {
@@ -911,9 +986,13 @@ xfs_attr_shortform_to_leaf(
nargs.namelen = sfe->namelen;
nargs.value = &sfe->nameval[nargs.namelen];
nargs.valuelen = sfe->valuelen;
- nargs.hashval = xfs_da_hashname(sfe->nameval,
- sfe->namelen);
nargs.attr_filter = sfe->flags & XFS_ATTR_NSP_ONDISK_MASK;
+ if (!xfs_attr_check_namespace(sfe->flags)) {
+ xfs_da_mark_sick(args);
+ error = -EFSCORRUPTED;
+ goto out;
+ }
+ xfs_attr_sethash(&nargs);
error = xfs_attr3_leaf_lookup_int(bp, &nargs); /* set a->index */
ASSERT(error == -ENOATTR);
error = xfs_attr3_leaf_add(bp, &nargs);
@@ -1027,7 +1106,7 @@ xfs_attr_shortform_verify(
* one namespace flag per xattr, so we can just count the
* bits (i.e. hweight) here.
*/
- if (hweight8(sfep->flags & XFS_ATTR_NSP_ONDISK_MASK) > 1)
+ if (!xfs_attr_check_namespace(sfep->flags))
return __this_address;
sfep = next_sfep;
@@ -1106,6 +1185,7 @@ xfs_attr3_leaf_to_shortform(
nargs.whichfork = XFS_ATTR_FORK;
nargs.trans = args->trans;
nargs.op_flags = XFS_DA_OP_OKNOENT;
+ nargs.owner = args->owner;
for (i = 0; i < ichdr.count; entry++, i++) {
if (entry->flags & XFS_ATTR_INCOMPLETE)
@@ -1158,7 +1238,7 @@ xfs_attr3_leaf_to_node(
error = xfs_da_grow_inode(args, &blkno);
if (error)
goto out;
- error = xfs_attr3_leaf_read(args->trans, dp, 0, &bp1);
+ error = xfs_attr3_leaf_read(args->trans, dp, args->owner, 0, &bp1);
if (error)
goto out;
@@ -1237,7 +1317,7 @@ xfs_attr3_leaf_create(
ichdr.magic = XFS_ATTR3_LEAF_MAGIC;
hdr3->blkno = cpu_to_be64(xfs_buf_daddr(bp));
- hdr3->owner = cpu_to_be64(dp->i_ino);
+ hdr3->owner = cpu_to_be64(args->owner);
uuid_copy(&hdr3->uuid, &mp->m_sb.sb_meta_uuid);
ichdr.freemap[0].base = sizeof(struct xfs_attr3_leaf_hdr);
@@ -1993,7 +2073,7 @@ xfs_attr3_leaf_toosmall(
if (blkno == 0)
continue;
error = xfs_attr3_leaf_read(state->args->trans, state->args->dp,
- blkno, &bp);
+ state->args->owner, blkno, &bp);
if (error)
return error;
@@ -2401,18 +2481,23 @@ xfs_attr3_leaf_lookup_int(
*/
if (entry->flags & XFS_ATTR_LOCAL) {
name_loc = xfs_attr3_leaf_name_local(leaf, probe);
- if (!xfs_attr_match(args, name_loc->namelen,
- name_loc->nameval, entry->flags))
+ if (!xfs_attr_match(args, entry->flags,
+ name_loc->nameval, name_loc->namelen,
+ &name_loc->nameval[name_loc->namelen],
+ be16_to_cpu(name_loc->valuelen)))
continue;
args->index = probe;
return -EEXIST;
} else {
+ unsigned int valuelen;
+
name_rmt = xfs_attr3_leaf_name_remote(leaf, probe);
- if (!xfs_attr_match(args, name_rmt->namelen,
- name_rmt->name, entry->flags))
+ valuelen = be32_to_cpu(name_rmt->valuelen);
+ if (!xfs_attr_match(args, entry->flags, name_rmt->name,
+ name_rmt->namelen, NULL, valuelen))
continue;
args->index = probe;
- args->rmtvaluelen = be32_to_cpu(name_rmt->valuelen);
+ args->rmtvaluelen = valuelen;
args->rmtblkno = be32_to_cpu(name_rmt->valueblk);
args->rmtblkcnt = xfs_attr3_rmt_blocks(
args->dp->i_mount,
@@ -2715,7 +2800,8 @@ xfs_attr3_leaf_clearflag(
/*
* Set up the operation.
*/
- error = xfs_attr3_leaf_read(args->trans, args->dp, args->blkno, &bp);
+ error = xfs_attr3_leaf_read(args->trans, args->dp, args->owner,
+ args->blkno, &bp);
if (error)
return error;
@@ -2779,7 +2865,8 @@ xfs_attr3_leaf_setflag(
/*
* Set up the operation.
*/
- error = xfs_attr3_leaf_read(args->trans, args->dp, args->blkno, &bp);
+ error = xfs_attr3_leaf_read(args->trans, args->dp, args->owner,
+ args->blkno, &bp);
if (error)
return error;
@@ -2838,7 +2925,8 @@ xfs_attr3_leaf_flipflags(
/*
* Read the block containing the "old" attr
*/
- error = xfs_attr3_leaf_read(args->trans, args->dp, args->blkno, &bp1);
+ error = xfs_attr3_leaf_read(args->trans, args->dp, args->owner,
+ args->blkno, &bp1);
if (error)
return error;
@@ -2846,8 +2934,8 @@ xfs_attr3_leaf_flipflags(
* Read the block containing the "new" attr, if it is different
*/
if (args->blkno2 != args->blkno) {
- error = xfs_attr3_leaf_read(args->trans, args->dp, args->blkno2,
- &bp2);
+ error = xfs_attr3_leaf_read(args->trans, args->dp, args->owner,
+ args->blkno2, &bp2);
if (error)
return error;
} else {
diff --git a/fs/xfs/libxfs/xfs_attr_leaf.h b/fs/xfs/libxfs/xfs_attr_leaf.h
index 9b9948639c..bac2195898 100644
--- a/fs/xfs/libxfs/xfs_attr_leaf.h
+++ b/fs/xfs/libxfs/xfs_attr_leaf.h
@@ -98,12 +98,14 @@ int xfs_attr_leaf_order(struct xfs_buf *leaf1_bp,
struct xfs_buf *leaf2_bp);
int xfs_attr_leaf_newentsize(struct xfs_da_args *args, int *local);
int xfs_attr3_leaf_read(struct xfs_trans *tp, struct xfs_inode *dp,
- xfs_dablk_t bno, struct xfs_buf **bpp);
+ xfs_ino_t owner, xfs_dablk_t bno, struct xfs_buf **bpp);
void xfs_attr3_leaf_hdr_from_disk(struct xfs_da_geometry *geo,
struct xfs_attr3_icleaf_hdr *to,
struct xfs_attr_leafblock *from);
void xfs_attr3_leaf_hdr_to_disk(struct xfs_da_geometry *geo,
struct xfs_attr_leafblock *to,
struct xfs_attr3_icleaf_hdr *from);
+xfs_failaddr_t xfs_attr3_leaf_header_check(struct xfs_buf *bp,
+ xfs_ino_t owner);
#endif /* __XFS_ATTR_LEAF_H__ */
diff --git a/fs/xfs/libxfs/xfs_attr_remote.c b/fs/xfs/libxfs/xfs_attr_remote.c
index ff04128287..4c44ce1c8a 100644
--- a/fs/xfs/libxfs/xfs_attr_remote.c
+++ b/fs/xfs/libxfs/xfs_attr_remote.c
@@ -43,19 +43,32 @@
* the logging system and therefore never have a log item.
*/
-/*
- * Each contiguous block has a header, so it is not just a simple attribute
- * length to FSB conversion.
- */
-int
+/* How many bytes can be stored in a remote value buffer? */
+inline unsigned int
+xfs_attr3_rmt_buf_space(
+ struct xfs_mount *mp)
+{
+ unsigned int blocksize = mp->m_attr_geo->blksize;
+
+ if (xfs_has_crc(mp))
+ return blocksize - sizeof(struct xfs_attr3_rmt_hdr);
+
+ return blocksize;
+}
+
+/* Compute number of fsblocks needed to store a remote attr value */
+unsigned int
xfs_attr3_rmt_blocks(
- struct xfs_mount *mp,
- int attrlen)
+ struct xfs_mount *mp,
+ unsigned int attrlen)
{
- if (xfs_has_crc(mp)) {
- int buflen = XFS_ATTR3_RMT_BUF_SPACE(mp, mp->m_sb.sb_blocksize);
- return (attrlen + buflen - 1) / buflen;
- }
+ /*
+ * Each contiguous block has a header, so it is not just a simple
+ * attribute length to FSB conversion.
+ */
+ if (xfs_has_crc(mp))
+ return howmany(attrlen, xfs_attr3_rmt_buf_space(mp));
+
return XFS_B_TO_FSB(mp, attrlen);
}
@@ -92,7 +105,6 @@ xfs_attr3_rmt_verify(
struct xfs_mount *mp,
struct xfs_buf *bp,
void *ptr,
- int fsbsize,
xfs_daddr_t bno)
{
struct xfs_attr3_rmt_hdr *rmt = ptr;
@@ -103,7 +115,7 @@ xfs_attr3_rmt_verify(
return __this_address;
if (be64_to_cpu(rmt->rm_blkno) != bno)
return __this_address;
- if (be32_to_cpu(rmt->rm_bytes) > fsbsize - sizeof(*rmt))
+ if (be32_to_cpu(rmt->rm_bytes) > mp->m_attr_geo->blksize - sizeof(*rmt))
return __this_address;
if (be32_to_cpu(rmt->rm_offset) +
be32_to_cpu(rmt->rm_bytes) > XFS_XATTR_SIZE_MAX)
@@ -122,9 +134,9 @@ __xfs_attr3_rmt_read_verify(
{
struct xfs_mount *mp = bp->b_mount;
char *ptr;
- int len;
+ unsigned int len;
xfs_daddr_t bno;
- int blksize = mp->m_attr_geo->blksize;
+ unsigned int blksize = mp->m_attr_geo->blksize;
/* no verification of non-crc buffers */
if (!xfs_has_crc(mp))
@@ -141,7 +153,7 @@ __xfs_attr3_rmt_read_verify(
*failaddr = __this_address;
return -EFSBADCRC;
}
- *failaddr = xfs_attr3_rmt_verify(mp, bp, ptr, blksize, bno);
+ *failaddr = xfs_attr3_rmt_verify(mp, bp, ptr, bno);
if (*failaddr)
return -EFSCORRUPTED;
len -= blksize;
@@ -186,7 +198,7 @@ xfs_attr3_rmt_write_verify(
{
struct xfs_mount *mp = bp->b_mount;
xfs_failaddr_t fa;
- int blksize = mp->m_attr_geo->blksize;
+ unsigned int blksize = mp->m_attr_geo->blksize;
char *ptr;
int len;
xfs_daddr_t bno;
@@ -203,7 +215,7 @@ xfs_attr3_rmt_write_verify(
while (len > 0) {
struct xfs_attr3_rmt_hdr *rmt = (struct xfs_attr3_rmt_hdr *)ptr;
- fa = xfs_attr3_rmt_verify(mp, bp, ptr, blksize, bno);
+ fa = xfs_attr3_rmt_verify(mp, bp, ptr, bno);
if (fa) {
xfs_verifier_error(bp, -EFSCORRUPTED, fa);
return;
@@ -280,30 +292,30 @@ xfs_attr_rmtval_copyout(
struct xfs_mount *mp,
struct xfs_buf *bp,
struct xfs_inode *dp,
- int *offset,
- int *valuelen,
+ xfs_ino_t owner,
+ unsigned int *offset,
+ unsigned int *valuelen,
uint8_t **dst)
{
char *src = bp->b_addr;
- xfs_ino_t ino = dp->i_ino;
xfs_daddr_t bno = xfs_buf_daddr(bp);
- int len = BBTOB(bp->b_length);
- int blksize = mp->m_attr_geo->blksize;
+ unsigned int len = BBTOB(bp->b_length);
+ unsigned int blksize = mp->m_attr_geo->blksize;
ASSERT(len >= blksize);
while (len > 0 && *valuelen > 0) {
- int hdr_size = 0;
- int byte_cnt = XFS_ATTR3_RMT_BUF_SPACE(mp, blksize);
+ unsigned int hdr_size = 0;
+ unsigned int byte_cnt = xfs_attr3_rmt_buf_space(mp);
byte_cnt = min(*valuelen, byte_cnt);
if (xfs_has_crc(mp)) {
- if (xfs_attr3_rmt_hdr_ok(src, ino, *offset,
+ if (xfs_attr3_rmt_hdr_ok(src, owner, *offset,
byte_cnt, bno)) {
xfs_alert(mp,
"remote attribute header mismatch bno/off/len/owner (0x%llx/0x%x/Ox%x/0x%llx)",
- bno, *offset, byte_cnt, ino);
+ bno, *offset, byte_cnt, owner);
xfs_dirattr_mark_sick(dp, XFS_ATTR_FORK);
return -EFSCORRUPTED;
}
@@ -330,20 +342,20 @@ xfs_attr_rmtval_copyin(
struct xfs_mount *mp,
struct xfs_buf *bp,
xfs_ino_t ino,
- int *offset,
- int *valuelen,
+ unsigned int *offset,
+ unsigned int *valuelen,
uint8_t **src)
{
char *dst = bp->b_addr;
xfs_daddr_t bno = xfs_buf_daddr(bp);
- int len = BBTOB(bp->b_length);
- int blksize = mp->m_attr_geo->blksize;
+ unsigned int len = BBTOB(bp->b_length);
+ unsigned int blksize = mp->m_attr_geo->blksize;
ASSERT(len >= blksize);
while (len > 0 && *valuelen > 0) {
- int hdr_size;
- int byte_cnt = XFS_ATTR3_RMT_BUF_SPACE(mp, blksize);
+ unsigned int hdr_size;
+ unsigned int byte_cnt = xfs_attr3_rmt_buf_space(mp);
byte_cnt = min(*valuelen, byte_cnt);
hdr_size = xfs_attr3_rmt_hdr_set(mp, dst, ino, *offset,
@@ -389,12 +401,12 @@ xfs_attr_rmtval_get(
struct xfs_buf *bp;
xfs_dablk_t lblkno = args->rmtblkno;
uint8_t *dst = args->value;
- int valuelen;
+ unsigned int valuelen;
int nmap;
int error;
- int blkcnt = args->rmtblkcnt;
+ unsigned int blkcnt = args->rmtblkcnt;
int i;
- int offset = 0;
+ unsigned int offset = 0;
trace_xfs_attr_rmtval_get(args);
@@ -427,8 +439,7 @@ xfs_attr_rmtval_get(
return error;
error = xfs_attr_rmtval_copyout(mp, bp, args->dp,
- &offset, &valuelen,
- &dst);
+ args->owner, &offset, &valuelen, &dst);
xfs_buf_relse(bp);
if (error)
return error;
@@ -453,7 +464,7 @@ xfs_attr_rmt_find_hole(
struct xfs_inode *dp = args->dp;
struct xfs_mount *mp = dp->i_mount;
int error;
- int blkcnt;
+ unsigned int blkcnt;
xfs_fileoff_t lfileoff = 0;
/*
@@ -482,11 +493,11 @@ xfs_attr_rmtval_set_value(
struct xfs_bmbt_irec map;
xfs_dablk_t lblkno;
uint8_t *src = args->value;
- int blkcnt;
- int valuelen;
+ unsigned int blkcnt;
+ unsigned int valuelen;
int nmap;
int error;
- int offset = 0;
+ unsigned int offset = 0;
/*
* Roll through the "value", copying the attribute value to the
@@ -522,8 +533,8 @@ xfs_attr_rmtval_set_value(
return error;
bp->b_ops = &xfs_attr3_rmt_buf_ops;
- xfs_attr_rmtval_copyin(mp, bp, args->dp->i_ino, &offset,
- &valuelen, &src);
+ xfs_attr_rmtval_copyin(mp, bp, args->owner, &offset, &valuelen,
+ &src);
error = xfs_bwrite(bp); /* GROT: NOTE: synchronous write */
xfs_buf_relse(bp);
@@ -626,7 +637,6 @@ xfs_attr_rmtval_set_blk(
if (error)
return error;
- ASSERT(nmap == 1);
ASSERT((map->br_startblock != DELAYSTARTBLOCK) &&
(map->br_startblock != HOLESTARTBLOCK));
@@ -646,7 +656,7 @@ xfs_attr_rmtval_invalidate(
struct xfs_da_args *args)
{
xfs_dablk_t lblkno;
- int blkcnt;
+ unsigned int blkcnt;
int error;
/*
diff --git a/fs/xfs/libxfs/xfs_attr_remote.h b/fs/xfs/libxfs/xfs_attr_remote.h
index d097ec6c4d..e3c6c7d774 100644
--- a/fs/xfs/libxfs/xfs_attr_remote.h
+++ b/fs/xfs/libxfs/xfs_attr_remote.h
@@ -6,7 +6,13 @@
#ifndef __XFS_ATTR_REMOTE_H__
#define __XFS_ATTR_REMOTE_H__
-int xfs_attr3_rmt_blocks(struct xfs_mount *mp, int attrlen);
+unsigned int xfs_attr3_rmt_blocks(struct xfs_mount *mp, unsigned int attrlen);
+
+/* Number of rmt blocks needed to store the maximally sized attr value */
+static inline unsigned int xfs_attr3_max_rmt_blocks(struct xfs_mount *mp)
+{
+ return xfs_attr3_rmt_blocks(mp, XFS_XATTR_SIZE_MAX);
+}
int xfs_attr_rmtval_get(struct xfs_da_args *args);
int xfs_attr_rmtval_stale(struct xfs_inode *ip, struct xfs_bmbt_irec *map,
diff --git a/fs/xfs/libxfs/xfs_attr_sf.h b/fs/xfs/libxfs/xfs_attr_sf.h
index bc44222230..73bdc0e556 100644
--- a/fs/xfs/libxfs/xfs_attr_sf.h
+++ b/fs/xfs/libxfs/xfs_attr_sf.h
@@ -16,6 +16,7 @@ typedef struct xfs_attr_sf_sort {
uint8_t flags; /* flags bits (see xfs_attr_leaf.h) */
xfs_dahash_t hash; /* this entry's hash value */
unsigned char *name; /* name value, pointer into buffer */
+ void *value;
} xfs_attr_sf_sort_t;
#define XFS_ATTR_SF_ENTSIZE_MAX /* max space for name&value */ \
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 656c95a22f..6af6f744fd 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -779,7 +779,7 @@ xfs_bmap_local_to_extents_empty(
}
-STATIC int /* error */
+int /* error */
xfs_bmap_local_to_extents(
xfs_trans_t *tp, /* transaction pointer */
xfs_inode_t *ip, /* incore inode pointer */
@@ -789,7 +789,8 @@ xfs_bmap_local_to_extents(
void (*init_fn)(struct xfs_trans *tp,
struct xfs_buf *bp,
struct xfs_inode *ip,
- struct xfs_ifork *ifp))
+ struct xfs_ifork *ifp, void *priv),
+ void *priv)
{
int error = 0;
int flags; /* logging flags returned */
@@ -850,7 +851,7 @@ xfs_bmap_local_to_extents(
* log here. Note that init_fn must also set the buffer log item type
* correctly.
*/
- init_fn(tp, bp, ip, ifp);
+ init_fn(tp, bp, ip, ifp, priv);
/* account for the change in fork size */
xfs_idata_realloc(ip, -ifp->if_bytes, whichfork);
@@ -976,13 +977,14 @@ xfs_bmap_add_attrfork_local(
dargs.total = dargs.geo->fsbcount;
dargs.whichfork = XFS_DATA_FORK;
dargs.trans = tp;
+ dargs.owner = ip->i_ino;
return xfs_dir2_sf_to_block(&dargs);
}
if (S_ISLNK(VFS_I(ip)->i_mode))
return xfs_bmap_local_to_extents(tp, ip, 1, flags,
- XFS_DATA_FORK,
- xfs_symlink_local_to_remote);
+ XFS_DATA_FORK, xfs_symlink_local_to_remote,
+ NULL);
/* should only be called for types that support local format data */
ASSERT(0);
@@ -1023,40 +1025,29 @@ xfs_bmap_set_attrforkoff(
}
/*
- * Convert inode from non-attributed to attributed.
- * Must not be in a transaction, ip must not be locked.
+ * Convert inode from non-attributed to attributed. Caller must hold the
+ * ILOCK_EXCL and the file cannot have an attr fork.
*/
int /* error code */
xfs_bmap_add_attrfork(
- xfs_inode_t *ip, /* incore inode pointer */
+ struct xfs_trans *tp,
+ struct xfs_inode *ip, /* incore inode pointer */
int size, /* space new attribute needs */
int rsvd) /* xact may use reserved blks */
{
- xfs_mount_t *mp; /* mount structure */
- xfs_trans_t *tp; /* transaction pointer */
- int blks; /* space reservation */
+ struct xfs_mount *mp = tp->t_mountp;
int version = 1; /* superblock attr version */
int logflags; /* logging flags */
int error; /* error return value */
- ASSERT(xfs_inode_has_attr_fork(ip) == 0);
-
- mp = ip->i_mount;
+ xfs_assert_ilocked(ip, XFS_ILOCK_EXCL);
ASSERT(!XFS_NOT_DQATTACHED(mp, ip));
-
- blks = XFS_ADDAFORK_SPACE_RES(mp);
-
- error = xfs_trans_alloc_inode(ip, &M_RES(mp)->tr_addafork, blks, 0,
- rsvd, &tp);
- if (error)
- return error;
- if (xfs_inode_has_attr_fork(ip))
- goto trans_cancel;
+ ASSERT(!xfs_inode_has_attr_fork(ip));
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
error = xfs_bmap_set_attrforkoff(ip, size, &version);
if (error)
- goto trans_cancel;
+ return error;
xfs_ifork_init_attr(ip, XFS_DINODE_FMT_EXTENTS, 0);
logflags = 0;
@@ -1077,7 +1068,7 @@ xfs_bmap_add_attrfork(
if (logflags)
xfs_trans_log_inode(tp, ip, logflags);
if (error)
- goto trans_cancel;
+ return error;
if (!xfs_has_attr(mp) ||
(!xfs_has_attr2(mp) && version == 2)) {
bool log_sb = false;
@@ -1096,14 +1087,7 @@ xfs_bmap_add_attrfork(
xfs_log_sb(tp);
}
- error = xfs_trans_commit(tp);
- xfs_iunlock(ip, XFS_ILOCK_EXCL);
- return error;
-
-trans_cancel:
- xfs_trans_cancel(tp);
- xfs_iunlock(ip, XFS_ILOCK_EXCL);
- return error;
+ return 0;
}
/*
@@ -1586,6 +1570,7 @@ xfs_bmap_add_extent_delay_real(
if (error)
goto done;
}
+ ASSERT(da_new <= da_old);
break;
case BMAP_LEFT_FILLING | BMAP_RIGHT_FILLING | BMAP_LEFT_CONTIG:
@@ -1616,6 +1601,7 @@ xfs_bmap_add_extent_delay_real(
if (error)
goto done;
}
+ ASSERT(da_new <= da_old);
break;
case BMAP_LEFT_FILLING | BMAP_RIGHT_FILLING | BMAP_RIGHT_CONTIG:
@@ -1650,6 +1636,7 @@ xfs_bmap_add_extent_delay_real(
if (error)
goto done;
}
+ ASSERT(da_new <= da_old);
break;
case BMAP_LEFT_FILLING | BMAP_RIGHT_FILLING:
@@ -1684,6 +1671,7 @@ xfs_bmap_add_extent_delay_real(
goto done;
}
}
+ ASSERT(da_new <= da_old);
break;
case BMAP_LEFT_FILLING | BMAP_LEFT_CONTIG:
@@ -1722,6 +1710,7 @@ xfs_bmap_add_extent_delay_real(
if (error)
goto done;
}
+ ASSERT(da_new <= da_old);
break;
case BMAP_LEFT_FILLING:
@@ -1812,6 +1801,7 @@ xfs_bmap_add_extent_delay_real(
xfs_iext_update_extent(bma->ip, state, &bma->icur, &PREV);
xfs_iext_next(ifp, &bma->icur);
xfs_iext_update_extent(bma->ip, state, &bma->icur, &RIGHT);
+ ASSERT(da_new <= da_old);
break;
case BMAP_RIGHT_FILLING:
@@ -1861,6 +1851,7 @@ xfs_bmap_add_extent_delay_real(
PREV.br_blockcount = temp;
xfs_iext_insert(bma->ip, &bma->icur, &PREV, state);
xfs_iext_next(ifp, &bma->icur);
+ ASSERT(da_new <= da_old);
break;
case 0:
@@ -1975,7 +1966,7 @@ xfs_bmap_add_extent_delay_real(
}
if (da_new != da_old)
- xfs_mod_delalloc(mp, (int64_t)da_new - da_old);
+ xfs_mod_delalloc(bma->ip, 0, (int64_t)da_new - da_old);
if (bma->cur) {
da_new += bma->cur->bc_bmap.allocated;
@@ -1983,11 +1974,10 @@ xfs_bmap_add_extent_delay_real(
}
/* adjust for changes in reserved delayed indirect blocks */
- if (da_new != da_old) {
- ASSERT(state == 0 || da_new < da_old);
- error = xfs_mod_fdblocks(mp, (int64_t)(da_old - da_new),
- false);
- }
+ if (da_new < da_old)
+ xfs_add_fdblocks(mp, da_old - da_new);
+ else if (da_new > da_old)
+ error = xfs_dec_fdblocks(mp, da_new - da_old, true);
xfs_bmap_check_leaf_extents(bma->cur, bma->ip, whichfork);
done:
@@ -2688,12 +2678,12 @@ xfs_bmap_add_extent_hole_delay(
}
if (oldlen != newlen) {
ASSERT(oldlen > newlen);
- xfs_mod_fdblocks(ip->i_mount, (int64_t)(oldlen - newlen),
- false);
+ xfs_add_fdblocks(ip->i_mount, oldlen - newlen);
+
/*
* Nothing to do for disk quota accounting here.
*/
- xfs_mod_delalloc(ip->i_mount, (int64_t)newlen - oldlen);
+ xfs_mod_delalloc(ip, 0, (int64_t)newlen - oldlen);
}
}
@@ -3370,7 +3360,7 @@ xfs_bmap_alloc_account(
* yet.
*/
if (ap->wasdel) {
- xfs_mod_delalloc(ap->ip->i_mount, -(int64_t)ap->length);
+ xfs_mod_delalloc(ap->ip, -(int64_t)ap->length, 0);
return;
}
@@ -3394,7 +3384,7 @@ xfs_bmap_alloc_account(
xfs_trans_log_inode(ap->tp, ap->ip, XFS_ILOG_CORE);
if (ap->wasdel) {
ap->ip->i_delayed_blks -= ap->length;
- xfs_mod_delalloc(ap->ip->i_mount, -(int64_t)ap->length);
+ xfs_mod_delalloc(ap->ip, -(int64_t)ap->length, 0);
fld = isrt ? XFS_TRANS_DQ_DELRTBCOUNT : XFS_TRANS_DQ_DELBCOUNT;
} else {
fld = isrt ? XFS_TRANS_DQ_RTBCOUNT : XFS_TRANS_DQ_BCOUNT;
@@ -4066,21 +4056,34 @@ xfs_bmapi_reserve_delalloc(
struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork);
xfs_extlen_t alen;
xfs_extlen_t indlen;
+ uint64_t fdblocks;
int error;
- xfs_fileoff_t aoff = off;
+ xfs_fileoff_t aoff;
+ bool use_cowextszhint =
+ whichfork == XFS_COW_FORK && !prealloc;
+retry:
/*
* Cap the alloc length. Keep track of prealloc so we know whether to
* tag the inode before we return.
*/
+ aoff = off;
alen = XFS_FILBLKS_MIN(len + prealloc, XFS_MAX_BMBT_EXTLEN);
if (!eof)
alen = XFS_FILBLKS_MIN(alen, got->br_startoff - aoff);
if (prealloc && alen >= len)
prealloc = alen - len;
- /* Figure out the extent size, adjust alen */
- if (whichfork == XFS_COW_FORK) {
+ /*
+ * If we're targetting the COW fork but aren't creating a speculative
+ * posteof preallocation, try to expand the reservation to align with
+ * the COW extent size hint if there's sufficient free space.
+ *
+ * Unlike the data fork, the CoW cancellation functions will free all
+ * the reservations at inactivation, so we don't require that every
+ * delalloc reservation have a dirty pagecache.
+ */
+ if (use_cowextszhint) {
struct xfs_bmbt_irec prev;
xfs_extlen_t extsz = xfs_get_cowextsz_hint(ip);
@@ -4099,7 +4102,7 @@ xfs_bmapi_reserve_delalloc(
*/
error = xfs_quota_reserve_blkres(ip, alen);
if (error)
- return error;
+ goto out;
/*
* Split changing sb for alen and indlen since they could be coming
@@ -4108,17 +4111,21 @@ xfs_bmapi_reserve_delalloc(
indlen = (xfs_extlen_t)xfs_bmap_worst_indlen(ip, alen);
ASSERT(indlen > 0);
- error = xfs_mod_fdblocks(mp, -((int64_t)alen), false);
- if (error)
- goto out_unreserve_quota;
+ fdblocks = indlen;
+ if (XFS_IS_REALTIME_INODE(ip)) {
+ error = xfs_dec_frextents(mp, xfs_rtb_to_rtx(mp, alen));
+ if (error)
+ goto out_unreserve_quota;
+ } else {
+ fdblocks += alen;
+ }
- error = xfs_mod_fdblocks(mp, -((int64_t)indlen), false);
+ error = xfs_dec_fdblocks(mp, fdblocks, false);
if (error)
- goto out_unreserve_blocks;
-
+ goto out_unreserve_frextents;
ip->i_delayed_blks += alen;
- xfs_mod_delalloc(ip->i_mount, alen + indlen);
+ xfs_mod_delalloc(ip, alen, indlen);
got->br_startoff = aoff;
got->br_startblock = nullstartblock(indlen);
@@ -4139,11 +4146,23 @@ xfs_bmapi_reserve_delalloc(
return 0;
-out_unreserve_blocks:
- xfs_mod_fdblocks(mp, alen, false);
+out_unreserve_frextents:
+ if (XFS_IS_REALTIME_INODE(ip))
+ xfs_add_frextents(mp, xfs_rtb_to_rtx(mp, alen));
out_unreserve_quota:
if (XFS_IS_QUOTA_ON(mp))
xfs_quota_unreserve_blkres(ip, alen);
+out:
+ if (error == -ENOSPC || error == -EDQUOT) {
+ trace_xfs_delalloc_enospc(ip, off, len);
+
+ if (prealloc || use_cowextszhint) {
+ /* retry without any preallocation */
+ use_cowextszhint = false;
+ prealloc = 0;
+ goto retry;
+ }
+ }
return error;
}
@@ -4191,26 +4210,10 @@ xfs_bmapi_allocate(
struct xfs_mount *mp = bma->ip->i_mount;
int whichfork = xfs_bmapi_whichfork(bma->flags);
struct xfs_ifork *ifp = xfs_ifork_ptr(bma->ip, whichfork);
- int tmp_logflags = 0;
int error;
ASSERT(bma->length > 0);
-
- /*
- * For the wasdelay case, we could also just allocate the stuff asked
- * for in this bmap call but that wouldn't be as good.
- */
- if (bma->wasdel) {
- bma->length = (xfs_extlen_t)bma->got.br_blockcount;
- bma->offset = bma->got.br_startoff;
- if (!xfs_iext_peek_prev_extent(ifp, &bma->icur, &bma->prev))
- bma->prev.br_startoff = NULLFILEOFF;
- } else {
- bma->length = XFS_FILBLKS_MIN(bma->length, XFS_MAX_BMBT_EXTLEN);
- if (!bma->eof)
- bma->length = XFS_FILBLKS_MIN(bma->length,
- bma->got.br_startoff - bma->offset);
- }
+ ASSERT(bma->length <= XFS_MAX_BMBT_EXTLEN);
if (bma->flags & XFS_BMAPI_CONTIG)
bma->minlen = bma->length;
@@ -4226,8 +4229,15 @@ xfs_bmapi_allocate(
} else {
error = xfs_bmap_alloc_userdata(bma);
}
- if (error || bma->blkno == NULLFSBLOCK)
+ if (error)
return error;
+ if (bma->blkno == NULLFSBLOCK)
+ return -ENOSPC;
+
+ if (WARN_ON_ONCE(!xfs_valid_startblock(bma->ip, bma->blkno))) {
+ xfs_bmap_mark_sick(bma->ip, whichfork);
+ return -EFSCORRUPTED;
+ }
if (bma->flags & XFS_BMAPI_ZERO) {
error = xfs_zero_extent(bma->ip, bma->blkno, bma->length);
@@ -4260,8 +4270,6 @@ xfs_bmapi_allocate(
error = xfs_bmap_add_extent_hole_real(bma->tp, bma->ip,
whichfork, &bma->icur, &bma->cur, &bma->got,
&bma->logflags, bma->flags);
-
- bma->logflags |= tmp_logflags;
if (error)
return error;
@@ -4406,6 +4414,15 @@ xfs_bmapi_finish(
* extent state if necessary. Details behaviour is controlled by the flags
* parameter. Only allocates blocks from a single allocation group, to avoid
* locking problems.
+ *
+ * Returns 0 on success and places the extent mappings in mval. nmaps is used
+ * as an input/output parameter where the caller specifies the maximum number
+ * of mappings that may be returned and xfs_bmapi_write passes back the number
+ * of mappings (including existing mappings) it found.
+ *
+ * Returns a negative error code on failure, including -ENOSPC when it could not
+ * allocate any blocks and -ENOSR when it did allocate blocks to convert a
+ * delalloc range, but those blocks were before the passed in range.
*/
int
xfs_bmapi_write(
@@ -4524,20 +4541,33 @@ xfs_bmapi_write(
* allocation length request (which can be 64 bits in
* length) and the bma length request, which is
* xfs_extlen_t and therefore 32 bits. Hence we have to
- * check for 32-bit overflows and handle them here.
+ * be careful and do the min() using the larger type to
+ * avoid overflows.
*/
- if (len > (xfs_filblks_t)XFS_MAX_BMBT_EXTLEN)
- bma.length = XFS_MAX_BMBT_EXTLEN;
- else
- bma.length = len;
+ bma.length = XFS_FILBLKS_MIN(len, XFS_MAX_BMBT_EXTLEN);
+
+ if (wasdelay) {
+ bma.length = XFS_FILBLKS_MIN(bma.length,
+ bma.got.br_blockcount -
+ (bno - bma.got.br_startoff));
+ } else {
+ if (!eof)
+ bma.length = XFS_FILBLKS_MIN(bma.length,
+ bma.got.br_startoff - bno);
+ }
- ASSERT(len > 0);
ASSERT(bma.length > 0);
error = xfs_bmapi_allocate(&bma);
- if (error)
+ if (error) {
+ /*
+ * If we already allocated space in a previous
+ * iteration return what we go so far when
+ * running out of space.
+ */
+ if (error == -ENOSPC && bma.nallocs)
+ break;
goto error0;
- if (bma.blkno == NULLFSBLOCK)
- break;
+ }
/*
* If this is a CoW allocation, record the data in
@@ -4575,7 +4605,6 @@ xfs_bmapi_write(
if (!xfs_iext_next_extent(ifp, &bma.icur, &bma.got))
eof = true;
}
- *nmap = n;
error = xfs_bmap_btree_to_extents(tp, ip, bma.cur, &bma.logflags,
whichfork);
@@ -4586,7 +4615,22 @@ xfs_bmapi_write(
ifp->if_nextents > XFS_IFORK_MAXEXT(ip, whichfork));
xfs_bmapi_finish(&bma, whichfork, 0);
xfs_bmap_validate_ret(orig_bno, orig_len, orig_flags, orig_mval,
- orig_nmap, *nmap);
+ orig_nmap, n);
+
+ /*
+ * When converting delayed allocations, xfs_bmapi_allocate ignores
+ * the passed in bno and always converts from the start of the found
+ * delalloc extent.
+ *
+ * To avoid a successful return with *nmap set to 0, return the magic
+ * -ENOSR error code for this particular case so that the caller can
+ * handle it.
+ */
+ if (!n) {
+ ASSERT(bma.nallocs >= *nmap);
+ return -ENOSR;
+ }
+ *nmap = n;
return 0;
error0:
xfs_bmapi_finish(&bma, whichfork, error);
@@ -4599,8 +4643,8 @@ error0:
* invocations to allocate the target offset if a large enough physical extent
* is not available.
*/
-int
-xfs_bmapi_convert_delalloc(
+static int
+xfs_bmapi_convert_one_delalloc(
struct xfs_inode *ip,
int whichfork,
xfs_off_t offset,
@@ -4630,11 +4674,8 @@ xfs_bmapi_convert_delalloc(
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_trans_ijoin(tp, ip, 0);
- error = xfs_iext_count_may_overflow(ip, whichfork,
+ error = xfs_iext_count_extend(tp, ip, whichfork,
XFS_IEXT_ADD_NOSPLIT_CNT);
- if (error == -EFBIG)
- error = xfs_iext_count_upgrade(tp, ip,
- XFS_IEXT_ADD_NOSPLIT_CNT);
if (error)
goto out_trans_cancel;
@@ -4657,19 +4698,25 @@ xfs_bmapi_convert_delalloc(
if (!isnullstartblock(bma.got.br_startblock)) {
xfs_bmbt_to_iomap(ip, iomap, &bma.got, 0, flags,
xfs_iomap_inode_sequence(ip, flags));
- *seq = READ_ONCE(ifp->if_seq);
+ if (seq)
+ *seq = READ_ONCE(ifp->if_seq);
goto out_trans_cancel;
}
bma.tp = tp;
bma.ip = ip;
bma.wasdel = true;
- bma.offset = bma.got.br_startoff;
- bma.length = max_t(xfs_filblks_t, bma.got.br_blockcount,
- XFS_MAX_BMBT_EXTLEN);
bma.minleft = xfs_bmapi_minleft(tp, ip, whichfork);
/*
+ * Always allocate convert from the start of the delalloc extent even if
+ * that is outside the passed in range to create large contiguous
+ * extents on disk.
+ */
+ bma.offset = bma.got.br_startoff;
+ bma.length = bma.got.br_blockcount;
+
+ /*
* When we're converting the delalloc reservations backing dirty pages
* in the page cache, we must be careful about how we create the new
* extents:
@@ -4693,22 +4740,14 @@ xfs_bmapi_convert_delalloc(
if (error)
goto out_finish;
- error = -ENOSPC;
- if (WARN_ON_ONCE(bma.blkno == NULLFSBLOCK))
- goto out_finish;
- if (WARN_ON_ONCE(!xfs_valid_startblock(ip, bma.got.br_startblock))) {
- xfs_bmap_mark_sick(ip, whichfork);
- error = -EFSCORRUPTED;
- goto out_finish;
- }
-
XFS_STATS_ADD(mp, xs_xstrat_bytes, XFS_FSB_TO_B(mp, bma.length));
XFS_STATS_INC(mp, xs_xstrat_quick);
ASSERT(!isnullstartblock(bma.got.br_startblock));
xfs_bmbt_to_iomap(ip, iomap, &bma.got, 0, flags,
xfs_iomap_inode_sequence(ip, flags));
- *seq = READ_ONCE(ifp->if_seq);
+ if (seq)
+ *seq = READ_ONCE(ifp->if_seq);
if (whichfork == XFS_COW_FORK)
xfs_refcount_alloc_cow_extent(tp, bma.blkno, bma.length);
@@ -4731,6 +4770,36 @@ out_trans_cancel:
return error;
}
+/*
+ * Pass in a dellalloc extent and convert it to real extents, return the real
+ * extent that maps offset_fsb in iomap.
+ */
+int
+xfs_bmapi_convert_delalloc(
+ struct xfs_inode *ip,
+ int whichfork,
+ loff_t offset,
+ struct iomap *iomap,
+ unsigned int *seq)
+{
+ int error;
+
+ /*
+ * Attempt to allocate whatever delalloc extent currently backs offset
+ * and put the result into iomap. Allocate in a loop because it may
+ * take several attempts to allocate real blocks for a contiguous
+ * delalloc extent if free space is sufficiently fragmented.
+ */
+ do {
+ error = xfs_bmapi_convert_one_delalloc(ip, whichfork, offset,
+ iomap, seq);
+ if (error)
+ return error;
+ } while (iomap->offset + iomap->length <= offset);
+
+ return 0;
+}
+
int
xfs_bmapi_remap(
struct xfs_trans *tp,
@@ -4822,32 +4891,18 @@ error0:
* ores == 1). The number of stolen blocks is returned. The availability and
* subsequent accounting of stolen blocks is the responsibility of the caller.
*/
-static xfs_filblks_t
+static void
xfs_bmap_split_indlen(
xfs_filblks_t ores, /* original res. */
xfs_filblks_t *indlen1, /* ext1 worst indlen */
- xfs_filblks_t *indlen2, /* ext2 worst indlen */
- xfs_filblks_t avail) /* stealable blocks */
+ xfs_filblks_t *indlen2) /* ext2 worst indlen */
{
xfs_filblks_t len1 = *indlen1;
xfs_filblks_t len2 = *indlen2;
xfs_filblks_t nres = len1 + len2; /* new total res. */
- xfs_filblks_t stolen = 0;
xfs_filblks_t resfactor;
/*
- * Steal as many blocks as we can to try and satisfy the worst case
- * indlen for both new extents.
- */
- if (ores < nres && avail)
- stolen = XFS_FILBLKS_MIN(nres - ores, avail);
- ores += stolen;
-
- /* nothing else to do if we've satisfied the new reservation */
- if (ores >= nres)
- return stolen;
-
- /*
* We can't meet the total required reservation for the two extents.
* Calculate the percent of the overall shortage between both extents
* and apply this percentage to each of the requested indlen values.
@@ -4891,11 +4946,9 @@ xfs_bmap_split_indlen(
*indlen1 = len1;
*indlen2 = len2;
-
- return stolen;
}
-int
+void
xfs_bmap_del_extent_delay(
struct xfs_inode *ip,
int whichfork,
@@ -4908,9 +4961,9 @@ xfs_bmap_del_extent_delay(
struct xfs_bmbt_irec new;
int64_t da_old, da_new, da_diff = 0;
xfs_fileoff_t del_endoff, got_endoff;
- xfs_filblks_t got_indlen, new_indlen, stolen;
+ xfs_filblks_t got_indlen, new_indlen, stolen = 0;
uint32_t state = xfs_bmap_fork_to_state(whichfork);
- int error = 0;
+ uint64_t fdblocks;
bool isrt;
XFS_STATS_INC(mp, xs_del_exlist);
@@ -4925,18 +4978,12 @@ xfs_bmap_del_extent_delay(
ASSERT(got->br_startoff <= del->br_startoff);
ASSERT(got_endoff >= del_endoff);
- if (isrt)
- xfs_mod_frextents(mp, xfs_rtb_to_rtx(mp, del->br_blockcount));
-
/*
* Update the inode delalloc counter now and wait to update the
* sb counters as we might have to borrow some blocks for the
* indirect block accounting.
*/
- ASSERT(!isrt);
- error = xfs_quota_unreserve_blkres(ip, del->br_blockcount);
- if (error)
- return error;
+ xfs_quota_unreserve_blkres(ip, del->br_blockcount);
ip->i_delayed_blks -= del->br_blockcount;
if (got->br_startoff == del->br_startoff)
@@ -4990,8 +5037,24 @@ xfs_bmap_del_extent_delay(
new_indlen = xfs_bmap_worst_indlen(ip, new.br_blockcount);
WARN_ON_ONCE(!got_indlen || !new_indlen);
- stolen = xfs_bmap_split_indlen(da_old, &got_indlen, &new_indlen,
- del->br_blockcount);
+ /*
+ * Steal as many blocks as we can to try and satisfy the worst
+ * case indlen for both new extents.
+ *
+ * However, we can't just steal reservations from the data
+ * blocks if this is an RT inodes as the data and metadata
+ * blocks come from different pools. We'll have to live with
+ * under-filled indirect reservation in this case.
+ */
+ da_new = got_indlen + new_indlen;
+ if (da_new > da_old && !isrt) {
+ stolen = XFS_FILBLKS_MIN(da_new - da_old,
+ del->br_blockcount);
+ da_old += stolen;
+ }
+ if (da_new > da_old)
+ xfs_bmap_split_indlen(da_old, &got_indlen, &new_indlen);
+ da_new = got_indlen + new_indlen;
got->br_startblock = nullstartblock((int)got_indlen);
@@ -5003,20 +5066,21 @@ xfs_bmap_del_extent_delay(
xfs_iext_next(ifp, icur);
xfs_iext_insert(ip, icur, &new, state);
- da_new = got_indlen + new_indlen - stolen;
del->br_blockcount -= stolen;
break;
}
ASSERT(da_old >= da_new);
da_diff = da_old - da_new;
- if (!isrt)
- da_diff += del->br_blockcount;
- if (da_diff) {
- xfs_mod_fdblocks(mp, da_diff, false);
- xfs_mod_delalloc(mp, -da_diff);
- }
- return error;
+ fdblocks = da_diff;
+
+ if (isrt)
+ xfs_add_frextents(mp, xfs_rtb_to_rtx(mp, del->br_blockcount));
+ else
+ fdblocks += del->br_blockcount;
+
+ xfs_add_fdblocks(mp, fdblocks);
+ xfs_mod_delalloc(ip, -(int64_t)del->br_blockcount, -da_diff);
}
void
@@ -5107,8 +5171,7 @@ xfs_bmap_del_extent_real(
{
xfs_fsblock_t del_endblock=0; /* first block past del */
xfs_fileoff_t del_endoff; /* first offset past del */
- int do_fx; /* free extent at end of routine */
- int error; /* error return value */
+ int error = 0; /* error return value */
struct xfs_bmbt_irec got; /* current extent entry */
xfs_fileoff_t got_endoff; /* first offset past got */
int i; /* temp state */
@@ -5151,20 +5214,10 @@ xfs_bmap_del_extent_real(
return -ENOSPC;
*logflagsp = XFS_ILOG_CORE;
- if (xfs_ifork_is_realtime(ip, whichfork)) {
- if (!(bflags & XFS_BMAPI_REMAP)) {
- error = xfs_rtfree_blocks(tp, del->br_startblock,
- del->br_blockcount);
- if (error)
- return error;
- }
-
- do_fx = 0;
+ if (xfs_ifork_is_realtime(ip, whichfork))
qfield = XFS_TRANS_DQ_RTBCOUNT;
- } else {
- do_fx = 1;
+ else
qfield = XFS_TRANS_DQ_BCOUNT;
- }
nblks = del->br_blockcount;
del_endblock = del->br_startblock + del->br_blockcount;
@@ -5312,18 +5365,29 @@ xfs_bmap_del_extent_real(
/*
* If we need to, add to list of extents to delete.
*/
- if (do_fx && !(bflags & XFS_BMAPI_REMAP)) {
+ if (!(bflags & XFS_BMAPI_REMAP)) {
if (xfs_is_reflink_inode(ip) && whichfork == XFS_DATA_FORK) {
xfs_refcount_decrease_extent(tp, del);
+ } else if (xfs_ifork_is_realtime(ip, whichfork)) {
+ /*
+ * Ensure the bitmap and summary inodes are locked
+ * and joined to the transaction before modifying them.
+ */
+ if (!(tp->t_flags & XFS_TRANS_RTBITMAP_LOCKED)) {
+ tp->t_flags |= XFS_TRANS_RTBITMAP_LOCKED;
+ xfs_rtbitmap_lock(tp, mp);
+ }
+ error = xfs_rtfree_blocks(tp, del->br_startblock,
+ del->br_blockcount);
} else {
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)
- return error;
}
+ if (error)
+ return error;
}
/*
@@ -5414,16 +5478,6 @@ __xfs_bunmapi(
} else
cur = NULL;
- if (isrt) {
- /*
- * Synchronize by locking the bitmap inode.
- */
- xfs_ilock(mp->m_rbmip, XFS_ILOCK_EXCL|XFS_ILOCK_RTBITMAP);
- xfs_trans_ijoin(tp, mp->m_rbmip, XFS_ILOCK_EXCL);
- xfs_ilock(mp->m_rsumip, XFS_ILOCK_EXCL|XFS_ILOCK_RTSUM);
- xfs_trans_ijoin(tp, mp->m_rsumip, XFS_ILOCK_EXCL);
- }
-
extno = 0;
while (end != (xfs_fileoff_t)-1 && end >= start &&
(nexts == 0 || extno < nexts)) {
@@ -5584,18 +5638,16 @@ __xfs_bunmapi(
delete:
if (wasdel) {
- error = xfs_bmap_del_extent_delay(ip, whichfork, &icur,
- &got, &del);
+ xfs_bmap_del_extent_delay(ip, whichfork, &icur, &got, &del);
} else {
error = xfs_bmap_del_extent_real(ip, tp, &icur, cur,
&del, &tmp_logflags, whichfork,
flags);
logflags |= tmp_logflags;
+ if (error)
+ goto error0;
}
- if (error)
- goto error0;
-
end = del.br_startoff - 1;
nodelete:
/*
@@ -6354,6 +6406,7 @@ xfs_bunmapi_range(
error = xfs_defer_finish(tpp);
if (error)
goto out;
+ cond_resched();
}
out:
return error;
diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h
index f766259530..667b0c2b33 100644
--- a/fs/xfs/libxfs/xfs_bmap.h
+++ b/fs/xfs/libxfs/xfs_bmap.h
@@ -158,7 +158,7 @@ static inline bool xfs_bmap_is_real_extent(const struct xfs_bmbt_irec *irec)
* Return true if the extent is a real, allocated extent, or false if it is a
* delayed allocation, and unwritten extent or a hole.
*/
-static inline bool xfs_bmap_is_written_extent(struct xfs_bmbt_irec *irec)
+static inline bool xfs_bmap_is_written_extent(const struct xfs_bmbt_irec *irec)
{
return xfs_bmap_is_real_extent(irec) &&
irec->br_state != XFS_EXT_UNWRITTEN;
@@ -176,9 +176,16 @@ int xfs_bmap_longest_free_extent(struct xfs_perag *pag,
void xfs_trim_extent(struct xfs_bmbt_irec *irec, xfs_fileoff_t bno,
xfs_filblks_t len);
unsigned int xfs_bmap_compute_attr_offset(struct xfs_mount *mp);
-int xfs_bmap_add_attrfork(struct xfs_inode *ip, int size, int rsvd);
+int xfs_bmap_add_attrfork(struct xfs_trans *tp, struct xfs_inode *ip,
+ int size, int rsvd);
void xfs_bmap_local_to_extents_empty(struct xfs_trans *tp,
struct xfs_inode *ip, int whichfork);
+int xfs_bmap_local_to_extents(struct xfs_trans *tp, struct xfs_inode *ip,
+ xfs_extlen_t total, int *logflagsp, int whichfork,
+ void (*init_fn)(struct xfs_trans *tp, struct xfs_buf *bp,
+ struct xfs_inode *ip, struct xfs_ifork *ifp,
+ void *priv),
+ void *priv);
void xfs_bmap_compute_maxlevels(struct xfs_mount *mp, int whichfork);
int xfs_bmap_first_unused(struct xfs_trans *tp, struct xfs_inode *ip,
xfs_extlen_t len, xfs_fileoff_t *unused, int whichfork);
@@ -195,7 +202,7 @@ int xfs_bmapi_write(struct xfs_trans *tp, struct xfs_inode *ip,
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);
-int xfs_bmap_del_extent_delay(struct xfs_inode *ip, int whichfork,
+void xfs_bmap_del_extent_delay(struct xfs_inode *ip, int whichfork,
struct xfs_iext_cursor *cur, struct xfs_bmbt_irec *got,
struct xfs_bmbt_irec *del);
void xfs_bmap_del_extent_cow(struct xfs_inode *ip,
diff --git a/fs/xfs/libxfs/xfs_da_btree.c b/fs/xfs/libxfs/xfs_da_btree.c
index 718d071bb2..16a529a887 100644
--- a/fs/xfs/libxfs/xfs_da_btree.c
+++ b/fs/xfs/libxfs/xfs_da_btree.c
@@ -252,6 +252,51 @@ xfs_da3_node_verify(
return NULL;
}
+xfs_failaddr_t
+xfs_da3_node_header_check(
+ struct xfs_buf *bp,
+ xfs_ino_t owner)
+{
+ struct xfs_mount *mp = bp->b_mount;
+
+ if (xfs_has_crc(mp)) {
+ struct xfs_da3_blkinfo *hdr3 = bp->b_addr;
+
+ if (hdr3->hdr.magic != cpu_to_be16(XFS_DA3_NODE_MAGIC))
+ return __this_address;
+
+ if (be64_to_cpu(hdr3->owner) != owner)
+ return __this_address;
+ }
+
+ return NULL;
+}
+
+xfs_failaddr_t
+xfs_da3_header_check(
+ struct xfs_buf *bp,
+ xfs_ino_t owner)
+{
+ struct xfs_mount *mp = bp->b_mount;
+ struct xfs_da_blkinfo *hdr = bp->b_addr;
+
+ if (!xfs_has_crc(mp))
+ return NULL;
+
+ switch (hdr->magic) {
+ case cpu_to_be16(XFS_ATTR3_LEAF_MAGIC):
+ return xfs_attr3_leaf_header_check(bp, owner);
+ case cpu_to_be16(XFS_DA3_NODE_MAGIC):
+ return xfs_da3_node_header_check(bp, owner);
+ case cpu_to_be16(XFS_DIR3_LEAF1_MAGIC):
+ case cpu_to_be16(XFS_DIR3_LEAFN_MAGIC):
+ return xfs_dir3_leaf_header_check(bp, owner);
+ }
+
+ ASSERT(0);
+ return NULL;
+}
+
static void
xfs_da3_node_write_verify(
struct xfs_buf *bp)
@@ -486,7 +531,7 @@ xfs_da3_node_create(
memset(hdr3, 0, sizeof(struct xfs_da3_node_hdr));
ichdr.magic = XFS_DA3_NODE_MAGIC;
hdr3->info.blkno = cpu_to_be64(xfs_buf_daddr(bp));
- hdr3->info.owner = cpu_to_be64(args->dp->i_ino);
+ hdr3->info.owner = cpu_to_be64(args->owner);
uuid_copy(&hdr3->info.uuid, &mp->m_sb.sb_meta_uuid);
} else {
ichdr.magic = XFS_DA_NODE_MAGIC;
@@ -1199,6 +1244,7 @@ xfs_da3_root_join(
struct xfs_da3_icnode_hdr oldroothdr;
int error;
struct xfs_inode *dp = state->args->dp;
+ xfs_failaddr_t fa;
trace_xfs_da_root_join(state->args);
@@ -1225,6 +1271,13 @@ xfs_da3_root_join(
error = xfs_da3_node_read(args->trans, dp, child, &bp, args->whichfork);
if (error)
return error;
+ fa = xfs_da3_header_check(bp, args->owner);
+ if (fa) {
+ __xfs_buf_mark_corrupt(bp, fa);
+ xfs_trans_brelse(args->trans, bp);
+ xfs_da_mark_sick(args);
+ return -EFSCORRUPTED;
+ }
xfs_da_blkinfo_onlychild_validate(bp->b_addr, oldroothdr.level);
/*
@@ -1259,6 +1312,7 @@ xfs_da3_node_toosmall(
struct xfs_da_blkinfo *info;
xfs_dablk_t blkno;
struct xfs_buf *bp;
+ xfs_failaddr_t fa;
struct xfs_da3_icnode_hdr nodehdr;
int count;
int forward;
@@ -1333,6 +1387,13 @@ xfs_da3_node_toosmall(
state->args->whichfork);
if (error)
return error;
+ fa = xfs_da3_node_header_check(bp, state->args->owner);
+ if (fa) {
+ __xfs_buf_mark_corrupt(bp, fa);
+ xfs_trans_brelse(state->args->trans, bp);
+ xfs_da_mark_sick(state->args);
+ return -EFSCORRUPTED;
+ }
node = bp->b_addr;
xfs_da3_node_hdr_from_disk(dp->i_mount, &thdr, node);
@@ -1591,6 +1652,7 @@ xfs_da3_node_lookup_int(
struct xfs_da_node_entry *btree;
struct xfs_da3_icnode_hdr nodehdr;
struct xfs_da_args *args;
+ xfs_failaddr_t fa;
xfs_dablk_t blkno;
xfs_dahash_t hashval;
xfs_dahash_t btreehashval;
@@ -1629,6 +1691,12 @@ xfs_da3_node_lookup_int(
if (magic == XFS_ATTR_LEAF_MAGIC ||
magic == XFS_ATTR3_LEAF_MAGIC) {
+ fa = xfs_attr3_leaf_header_check(blk->bp, args->owner);
+ if (fa) {
+ __xfs_buf_mark_corrupt(blk->bp, fa);
+ xfs_da_mark_sick(args);
+ return -EFSCORRUPTED;
+ }
blk->magic = XFS_ATTR_LEAF_MAGIC;
blk->hashval = xfs_attr_leaf_lasthash(blk->bp, NULL);
break;
@@ -1636,6 +1704,12 @@ xfs_da3_node_lookup_int(
if (magic == XFS_DIR2_LEAFN_MAGIC ||
magic == XFS_DIR3_LEAFN_MAGIC) {
+ fa = xfs_dir3_leaf_header_check(blk->bp, args->owner);
+ if (fa) {
+ __xfs_buf_mark_corrupt(blk->bp, fa);
+ xfs_da_mark_sick(args);
+ return -EFSCORRUPTED;
+ }
blk->magic = XFS_DIR2_LEAFN_MAGIC;
blk->hashval = xfs_dir2_leaf_lasthash(args->dp,
blk->bp, NULL);
@@ -1648,6 +1722,13 @@ xfs_da3_node_lookup_int(
return -EFSCORRUPTED;
}
+ fa = xfs_da3_node_header_check(blk->bp, args->owner);
+ if (fa) {
+ __xfs_buf_mark_corrupt(blk->bp, fa);
+ xfs_da_mark_sick(args);
+ return -EFSCORRUPTED;
+ }
+
blk->magic = XFS_DA_NODE_MAGIC;
/*
@@ -1820,6 +1901,7 @@ xfs_da3_blk_link(
struct xfs_da_blkinfo *tmp_info;
struct xfs_da_args *args;
struct xfs_buf *bp;
+ xfs_failaddr_t fa;
int before = 0;
int error;
struct xfs_inode *dp = state->args->dp;
@@ -1863,6 +1945,13 @@ xfs_da3_blk_link(
&bp, args->whichfork);
if (error)
return error;
+ fa = xfs_da3_header_check(bp, args->owner);
+ if (fa) {
+ __xfs_buf_mark_corrupt(bp, fa);
+ xfs_trans_brelse(args->trans, bp);
+ xfs_da_mark_sick(args);
+ return -EFSCORRUPTED;
+ }
ASSERT(bp != NULL);
tmp_info = bp->b_addr;
ASSERT(tmp_info->magic == old_info->magic);
@@ -1884,6 +1973,13 @@ xfs_da3_blk_link(
&bp, args->whichfork);
if (error)
return error;
+ fa = xfs_da3_header_check(bp, args->owner);
+ if (fa) {
+ __xfs_buf_mark_corrupt(bp, fa);
+ xfs_trans_brelse(args->trans, bp);
+ xfs_da_mark_sick(args);
+ return -EFSCORRUPTED;
+ }
ASSERT(bp != NULL);
tmp_info = bp->b_addr;
ASSERT(tmp_info->magic == old_info->magic);
@@ -1913,6 +2009,7 @@ xfs_da3_blk_unlink(
struct xfs_da_blkinfo *tmp_info;
struct xfs_da_args *args;
struct xfs_buf *bp;
+ xfs_failaddr_t fa;
int error;
/*
@@ -1943,6 +2040,13 @@ xfs_da3_blk_unlink(
&bp, args->whichfork);
if (error)
return error;
+ fa = xfs_da3_header_check(bp, args->owner);
+ if (fa) {
+ __xfs_buf_mark_corrupt(bp, fa);
+ xfs_trans_brelse(args->trans, bp);
+ xfs_da_mark_sick(args);
+ return -EFSCORRUPTED;
+ }
ASSERT(bp != NULL);
tmp_info = bp->b_addr;
ASSERT(tmp_info->magic == save_info->magic);
@@ -1960,6 +2064,13 @@ xfs_da3_blk_unlink(
&bp, args->whichfork);
if (error)
return error;
+ fa = xfs_da3_header_check(bp, args->owner);
+ if (fa) {
+ __xfs_buf_mark_corrupt(bp, fa);
+ xfs_trans_brelse(args->trans, bp);
+ xfs_da_mark_sick(args);
+ return -EFSCORRUPTED;
+ }
ASSERT(bp != NULL);
tmp_info = bp->b_addr;
ASSERT(tmp_info->magic == save_info->magic);
@@ -1996,6 +2107,7 @@ xfs_da3_path_shift(
struct xfs_da_node_entry *btree;
struct xfs_da3_icnode_hdr nodehdr;
struct xfs_buf *bp;
+ xfs_failaddr_t fa;
xfs_dablk_t blkno = 0;
int level;
int error;
@@ -2074,6 +2186,12 @@ xfs_da3_path_shift(
switch (be16_to_cpu(info->magic)) {
case XFS_DA_NODE_MAGIC:
case XFS_DA3_NODE_MAGIC:
+ fa = xfs_da3_node_header_check(blk->bp, args->owner);
+ if (fa) {
+ __xfs_buf_mark_corrupt(blk->bp, fa);
+ xfs_da_mark_sick(args);
+ return -EFSCORRUPTED;
+ }
blk->magic = XFS_DA_NODE_MAGIC;
xfs_da3_node_hdr_from_disk(dp->i_mount, &nodehdr,
bp->b_addr);
@@ -2087,6 +2205,12 @@ xfs_da3_path_shift(
break;
case XFS_ATTR_LEAF_MAGIC:
case XFS_ATTR3_LEAF_MAGIC:
+ fa = xfs_attr3_leaf_header_check(blk->bp, args->owner);
+ if (fa) {
+ __xfs_buf_mark_corrupt(blk->bp, fa);
+ xfs_da_mark_sick(args);
+ return -EFSCORRUPTED;
+ }
blk->magic = XFS_ATTR_LEAF_MAGIC;
ASSERT(level == path->active-1);
blk->index = 0;
@@ -2094,6 +2218,12 @@ xfs_da3_path_shift(
break;
case XFS_DIR2_LEAFN_MAGIC:
case XFS_DIR3_LEAFN_MAGIC:
+ fa = xfs_dir3_leaf_header_check(blk->bp, args->owner);
+ if (fa) {
+ __xfs_buf_mark_corrupt(blk->bp, fa);
+ xfs_da_mark_sick(args);
+ return -EFSCORRUPTED;
+ }
blk->magic = XFS_DIR2_LEAFN_MAGIC;
ASSERT(level == path->active-1);
blk->index = 0;
@@ -2167,8 +2297,8 @@ xfs_da_grow_inode_int(
struct xfs_inode *dp = args->dp;
int w = args->whichfork;
xfs_rfsblock_t nblks = dp->i_nblocks;
- struct xfs_bmbt_irec map, *mapp;
- int nmap, error, got, i, mapi;
+ struct xfs_bmbt_irec map, *mapp = &map;
+ int nmap, error, got, i, mapi = 1;
/*
* Find a spot in the file space to put the new block.
@@ -2184,14 +2314,7 @@ xfs_da_grow_inode_int(
error = xfs_bmapi_write(tp, dp, *bno, count,
xfs_bmapi_aflag(w)|XFS_BMAPI_METADATA|XFS_BMAPI_CONTIG,
args->total, &map, &nmap);
- if (error)
- return error;
-
- ASSERT(nmap <= 1);
- if (nmap == 1) {
- mapp = &map;
- mapi = 1;
- } else if (nmap == 0 && count > 1) {
+ if (error == -ENOSPC && count > 1) {
xfs_fileoff_t b;
int c;
@@ -2209,16 +2332,13 @@ xfs_da_grow_inode_int(
args->total, &mapp[mapi], &nmap);
if (error)
goto out_free_map;
- if (nmap < 1)
- break;
mapi += nmap;
b = mapp[mapi - 1].br_startoff +
mapp[mapi - 1].br_blockcount;
}
- } else {
- mapi = 0;
- mapp = NULL;
}
+ if (error)
+ goto out_free_map;
/*
* Count the blocks we got, make sure it matches the total.
@@ -2290,6 +2410,7 @@ xfs_da3_swap_lastblock(
struct xfs_buf *last_buf;
struct xfs_buf *sib_buf;
struct xfs_buf *par_buf;
+ xfs_failaddr_t fa;
xfs_dahash_t dead_hash;
xfs_fileoff_t lastoff;
xfs_dablk_t dead_blkno;
@@ -2326,6 +2447,14 @@ xfs_da3_swap_lastblock(
error = xfs_da3_node_read(tp, dp, last_blkno, &last_buf, w);
if (error)
return error;
+ fa = xfs_da3_header_check(last_buf, args->owner);
+ if (fa) {
+ __xfs_buf_mark_corrupt(last_buf, fa);
+ xfs_trans_brelse(tp, last_buf);
+ xfs_da_mark_sick(args);
+ return -EFSCORRUPTED;
+ }
+
/*
* Copy the last block into the dead buffer and log it.
*/
@@ -2364,6 +2493,13 @@ xfs_da3_swap_lastblock(
error = xfs_da3_node_read(tp, dp, sib_blkno, &sib_buf, w);
if (error)
goto done;
+ fa = xfs_da3_header_check(sib_buf, args->owner);
+ if (fa) {
+ __xfs_buf_mark_corrupt(sib_buf, fa);
+ xfs_da_mark_sick(args);
+ error = -EFSCORRUPTED;
+ goto done;
+ }
sib_info = sib_buf->b_addr;
if (XFS_IS_CORRUPT(mp,
be32_to_cpu(sib_info->forw) != last_blkno ||
@@ -2385,6 +2521,13 @@ xfs_da3_swap_lastblock(
error = xfs_da3_node_read(tp, dp, sib_blkno, &sib_buf, w);
if (error)
goto done;
+ fa = xfs_da3_header_check(sib_buf, args->owner);
+ if (fa) {
+ __xfs_buf_mark_corrupt(sib_buf, fa);
+ xfs_da_mark_sick(args);
+ error = -EFSCORRUPTED;
+ goto done;
+ }
sib_info = sib_buf->b_addr;
if (XFS_IS_CORRUPT(mp,
be32_to_cpu(sib_info->back) != last_blkno ||
@@ -2408,6 +2551,13 @@ xfs_da3_swap_lastblock(
error = xfs_da3_node_read(tp, dp, par_blkno, &par_buf, w);
if (error)
goto done;
+ fa = xfs_da3_node_header_check(par_buf, args->owner);
+ if (fa) {
+ __xfs_buf_mark_corrupt(par_buf, fa);
+ xfs_da_mark_sick(args);
+ error = -EFSCORRUPTED;
+ goto done;
+ }
par_node = par_buf->b_addr;
xfs_da3_node_hdr_from_disk(dp->i_mount, &par_hdr, par_node);
if (XFS_IS_CORRUPT(mp,
@@ -2457,6 +2607,13 @@ xfs_da3_swap_lastblock(
error = xfs_da3_node_read(tp, dp, par_blkno, &par_buf, w);
if (error)
goto done;
+ fa = xfs_da3_node_header_check(par_buf, args->owner);
+ if (fa) {
+ __xfs_buf_mark_corrupt(par_buf, fa);
+ xfs_da_mark_sick(args);
+ error = -EFSCORRUPTED;
+ goto done;
+ }
par_node = par_buf->b_addr;
xfs_da3_node_hdr_from_disk(dp->i_mount, &par_hdr, par_node);
if (XFS_IS_CORRUPT(mp, par_hdr.level != level)) {
diff --git a/fs/xfs/libxfs/xfs_da_btree.h b/fs/xfs/libxfs/xfs_da_btree.h
index 706baf36e1..354d5d6504 100644
--- a/fs/xfs/libxfs/xfs_da_btree.h
+++ b/fs/xfs/libxfs/xfs_da_btree.h
@@ -54,17 +54,24 @@ enum xfs_dacmp {
*/
typedef struct xfs_da_args {
struct xfs_da_geometry *geo; /* da block geometry */
- const uint8_t *name; /* string (maybe not NULL terminated) */
- int namelen; /* length of string (maybe no NULL) */
- uint8_t filetype; /* filetype of inode for directories */
+ const uint8_t *name; /* string (maybe not NULL terminated) */
+ const uint8_t *new_name; /* new attr name */
void *value; /* set of bytes (maybe contain NULLs) */
- int valuelen; /* length of value */
- unsigned int attr_filter; /* XFS_ATTR_{ROOT,SECURE,INCOMPLETE} */
- unsigned int attr_flags; /* XATTR_{CREATE,REPLACE} */
- xfs_dahash_t hashval; /* hash value of name */
- xfs_ino_t inumber; /* input/output inode number */
+ void *new_value; /* new xattr value (may contain NULLs) */
struct xfs_inode *dp; /* directory inode to manipulate */
struct xfs_trans *trans; /* current trans (changes over time) */
+
+ xfs_ino_t inumber; /* input/output inode number */
+ xfs_ino_t owner; /* inode that owns the dir/attr data */
+
+ int valuelen; /* length of value */
+ int new_valuelen; /* length of new_value */
+ uint8_t filetype; /* filetype of inode for directories */
+ uint8_t op_flags; /* operation flags */
+ uint8_t attr_filter; /* XFS_ATTR_{ROOT,SECURE,INCOMPLETE} */
+ short namelen; /* length of string (maybe no NULL) */
+ short new_namelen; /* length of new attr name */
+ xfs_dahash_t hashval; /* hash value of name */
xfs_extlen_t total; /* total blocks needed, for 1st bmap */
int whichfork; /* data or attribute fork */
xfs_dablk_t blkno; /* blkno of attr leaf of interest */
@@ -77,7 +84,6 @@ typedef struct xfs_da_args {
xfs_dablk_t rmtblkno2; /* remote attr value starting blkno */
int rmtblkcnt2; /* remote attr value block count */
int rmtvaluelen2; /* remote attr value length in bytes */
- uint32_t op_flags; /* operation flags */
enum xfs_dacmp cmpresult; /* name compare result for lookups */
} xfs_da_args_t;
@@ -89,10 +95,8 @@ typedef struct xfs_da_args {
#define XFS_DA_OP_ADDNAME (1u << 2) /* this is an add operation */
#define XFS_DA_OP_OKNOENT (1u << 3) /* lookup op, ENOENT ok, else die */
#define XFS_DA_OP_CILOOKUP (1u << 4) /* lookup returns CI name if found */
-#define XFS_DA_OP_NOTIME (1u << 5) /* don't update inode timestamps */
-#define XFS_DA_OP_REMOVE (1u << 6) /* this is a remove operation */
-#define XFS_DA_OP_RECOVERY (1u << 7) /* Log recovery operation */
-#define XFS_DA_OP_LOGGED (1u << 8) /* Use intent items to track op */
+#define XFS_DA_OP_RECOVERY (1u << 5) /* Log recovery operation */
+#define XFS_DA_OP_LOGGED (1u << 6) /* Use intent items to track op */
#define XFS_DA_OP_FLAGS \
{ XFS_DA_OP_JUSTCHECK, "JUSTCHECK" }, \
@@ -100,8 +104,6 @@ typedef struct xfs_da_args {
{ XFS_DA_OP_ADDNAME, "ADDNAME" }, \
{ XFS_DA_OP_OKNOENT, "OKNOENT" }, \
{ XFS_DA_OP_CILOOKUP, "CILOOKUP" }, \
- { XFS_DA_OP_NOTIME, "NOTIME" }, \
- { XFS_DA_OP_REMOVE, "REMOVE" }, \
{ XFS_DA_OP_RECOVERY, "RECOVERY" }, \
{ XFS_DA_OP_LOGGED, "LOGGED" }
@@ -235,6 +237,8 @@ void xfs_da3_node_hdr_from_disk(struct xfs_mount *mp,
struct xfs_da3_icnode_hdr *to, struct xfs_da_intnode *from);
void xfs_da3_node_hdr_to_disk(struct xfs_mount *mp,
struct xfs_da_intnode *to, struct xfs_da3_icnode_hdr *from);
+xfs_failaddr_t xfs_da3_header_check(struct xfs_buf *bp, xfs_ino_t owner);
+xfs_failaddr_t xfs_da3_node_header_check(struct xfs_buf *bp, xfs_ino_t owner);
extern struct kmem_cache *xfs_da_state_cache;
diff --git a/fs/xfs/libxfs/xfs_da_format.h b/fs/xfs/libxfs/xfs_da_format.h
index 060e5c96b7..86de99e2f7 100644
--- a/fs/xfs/libxfs/xfs_da_format.h
+++ b/fs/xfs/libxfs/xfs_da_format.h
@@ -714,12 +714,30 @@ struct xfs_attr3_leafblock {
#define XFS_ATTR_LOCAL_BIT 0 /* attr is stored locally */
#define XFS_ATTR_ROOT_BIT 1 /* limit access to trusted attrs */
#define XFS_ATTR_SECURE_BIT 2 /* limit access to secure attrs */
+#define XFS_ATTR_PARENT_BIT 3 /* parent pointer attrs */
#define XFS_ATTR_INCOMPLETE_BIT 7 /* attr in middle of create/delete */
#define XFS_ATTR_LOCAL (1u << XFS_ATTR_LOCAL_BIT)
#define XFS_ATTR_ROOT (1u << XFS_ATTR_ROOT_BIT)
#define XFS_ATTR_SECURE (1u << XFS_ATTR_SECURE_BIT)
+#define XFS_ATTR_PARENT (1u << XFS_ATTR_PARENT_BIT)
#define XFS_ATTR_INCOMPLETE (1u << XFS_ATTR_INCOMPLETE_BIT)
-#define XFS_ATTR_NSP_ONDISK_MASK (XFS_ATTR_ROOT | XFS_ATTR_SECURE)
+
+#define XFS_ATTR_NSP_ONDISK_MASK (XFS_ATTR_ROOT | \
+ XFS_ATTR_SECURE | \
+ XFS_ATTR_PARENT)
+
+/* Private attr namespaces not exposed to userspace */
+#define XFS_ATTR_PRIVATE_NSP_MASK (XFS_ATTR_PARENT)
+
+#define XFS_ATTR_ONDISK_MASK (XFS_ATTR_NSP_ONDISK_MASK | \
+ XFS_ATTR_LOCAL | \
+ XFS_ATTR_INCOMPLETE)
+
+#define XFS_ATTR_NAMESPACE_STR \
+ { XFS_ATTR_LOCAL, "local" }, \
+ { XFS_ATTR_ROOT, "root" }, \
+ { XFS_ATTR_SECURE, "secure" }, \
+ { XFS_ATTR_PARENT, "parent" }
/*
* Alignment for namelist and valuelist entries (since they are mixed
@@ -862,9 +880,7 @@ struct xfs_attr3_rmt_hdr {
#define XFS_ATTR3_RMT_CRC_OFF offsetof(struct xfs_attr3_rmt_hdr, rm_crc)
-#define XFS_ATTR3_RMT_BUF_SPACE(mp, bufsize) \
- ((bufsize) - (xfs_has_crc((mp)) ? \
- sizeof(struct xfs_attr3_rmt_hdr) : 0))
+unsigned int xfs_attr3_rmt_buf_space(struct xfs_mount *mp);
/* Number of bytes in a directory block. */
static inline unsigned int xfs_dir2_dirblock_bytes(struct xfs_sb *sbp)
@@ -875,4 +891,17 @@ static inline unsigned int xfs_dir2_dirblock_bytes(struct xfs_sb *sbp)
xfs_failaddr_t xfs_da3_blkinfo_verify(struct xfs_buf *bp,
struct xfs_da3_blkinfo *hdr3);
+/*
+ * Parent pointer attribute format definition
+ *
+ * The xattr name contains the dirent name.
+ * The xattr value encodes the parent inode number and generation to ease
+ * opening parents by handle.
+ * The xattr hashval is xfs_dir2_namehash() ^ p_ino
+ */
+struct xfs_parent_rec {
+ __be64 p_ino;
+ __be32 p_gen;
+} __packed;
+
#endif /* __XFS_DA_FORMAT_H__ */
diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c
index c13276095c..4a078e07e1 100644
--- a/fs/xfs/libxfs/xfs_defer.c
+++ b/fs/xfs/libxfs/xfs_defer.c
@@ -27,6 +27,7 @@
#include "xfs_da_btree.h"
#include "xfs_attr.h"
#include "xfs_trans_priv.h"
+#include "xfs_exchmaps.h"
static struct kmem_cache *xfs_defer_pending_cache;
@@ -1091,7 +1092,11 @@ xfs_defer_ops_continue(
ASSERT(!(tp->t_flags & XFS_TRANS_DIRTY));
/* Lock the captured resources to the new transaction. */
- if (dfc->dfc_held.dr_inos == 2)
+ if (dfc->dfc_held.dr_inos > 2) {
+ xfs_sort_inodes(dfc->dfc_held.dr_ip, dfc->dfc_held.dr_inos);
+ xfs_lock_inodes(dfc->dfc_held.dr_ip, dfc->dfc_held.dr_inos,
+ XFS_ILOCK_EXCL);
+ } else if (dfc->dfc_held.dr_inos == 2)
xfs_lock_two_inodes(dfc->dfc_held.dr_ip[0], XFS_ILOCK_EXCL,
dfc->dfc_held.dr_ip[1], XFS_ILOCK_EXCL);
else if (dfc->dfc_held.dr_inos == 1)
@@ -1176,6 +1181,10 @@ xfs_defer_init_item_caches(void)
error = xfs_attr_intent_init_cache();
if (error)
goto err;
+ error = xfs_exchmaps_intent_init_cache();
+ if (error)
+ goto err;
+
return 0;
err:
xfs_defer_destroy_item_caches();
@@ -1186,6 +1195,7 @@ err:
void
xfs_defer_destroy_item_caches(void)
{
+ xfs_exchmaps_intent_destroy_cache();
xfs_attr_intent_destroy_cache();
xfs_extfree_intent_destroy_cache();
xfs_bmap_intent_destroy_cache();
diff --git a/fs/xfs/libxfs/xfs_defer.h b/fs/xfs/libxfs/xfs_defer.h
index 18a9fb92dd..8b338031e4 100644
--- a/fs/xfs/libxfs/xfs_defer.h
+++ b/fs/xfs/libxfs/xfs_defer.h
@@ -72,12 +72,18 @@ extern const struct xfs_defer_op_type xfs_rmap_update_defer_type;
extern const struct xfs_defer_op_type xfs_extent_free_defer_type;
extern const struct xfs_defer_op_type xfs_agfl_free_defer_type;
extern const struct xfs_defer_op_type xfs_attr_defer_type;
-
+extern const struct xfs_defer_op_type xfs_exchmaps_defer_type;
/*
* Deferred operation item relogging limits.
*/
-#define XFS_DEFER_OPS_NR_INODES 2 /* join up to two inodes */
+
+/*
+ * Rename w/ parent pointers can require up to 5 inodes with deferred ops to
+ * be joined to the transaction: src_dp, target_dp, src_ip, target_ip, and wip.
+ * These inodes are locked in sorted order by their inode numbers
+ */
+#define XFS_DEFER_OPS_NR_INODES 5
#define XFS_DEFER_OPS_NR_BUFS 2 /* join up to two buffers */
/* Resources that must be held across a transaction roll. */
diff --git a/fs/xfs/libxfs/xfs_dir2.c b/fs/xfs/libxfs/xfs_dir2.c
index 4821519efa..457f9a38f8 100644
--- a/fs/xfs/libxfs/xfs_dir2.c
+++ b/fs/xfs/libxfs/xfs_dir2.c
@@ -250,11 +250,68 @@ xfs_dir_init(
args->geo = dp->i_mount->m_dir_geo;
args->dp = dp;
args->trans = tp;
+ args->owner = dp->i_ino;
error = xfs_dir2_sf_create(args, pdp->i_ino);
kfree(args);
return error;
}
+enum xfs_dir2_fmt
+xfs_dir2_format(
+ struct xfs_da_args *args,
+ int *error)
+{
+ struct xfs_inode *dp = args->dp;
+ struct xfs_mount *mp = dp->i_mount;
+ struct xfs_da_geometry *geo = mp->m_dir_geo;
+ xfs_fileoff_t eof;
+
+ xfs_assert_ilocked(dp, XFS_ILOCK_SHARED | XFS_ILOCK_EXCL);
+
+ *error = 0;
+ if (dp->i_df.if_format == XFS_DINODE_FMT_LOCAL)
+ return XFS_DIR2_FMT_SF;
+
+ *error = xfs_bmap_last_offset(dp, &eof, XFS_DATA_FORK);
+ if (*error)
+ return XFS_DIR2_FMT_ERROR;
+
+ if (eof == XFS_B_TO_FSB(mp, geo->blksize)) {
+ if (XFS_IS_CORRUPT(mp, dp->i_disk_size != geo->blksize)) {
+ xfs_da_mark_sick(args);
+ *error = -EFSCORRUPTED;
+ return XFS_DIR2_FMT_ERROR;
+ }
+ return XFS_DIR2_FMT_BLOCK;
+ }
+ if (eof == geo->leafblk + geo->fsbcount)
+ return XFS_DIR2_FMT_LEAF;
+ return XFS_DIR2_FMT_NODE;
+}
+
+int
+xfs_dir_createname_args(
+ struct xfs_da_args *args)
+{
+ int error;
+
+ if (!args->inumber)
+ args->op_flags |= XFS_DA_OP_JUSTCHECK;
+
+ switch (xfs_dir2_format(args, &error)) {
+ case XFS_DIR2_FMT_SF:
+ return xfs_dir2_sf_addname(args);
+ case XFS_DIR2_FMT_BLOCK:
+ return xfs_dir2_block_addname(args);
+ case XFS_DIR2_FMT_LEAF:
+ return xfs_dir2_leaf_addname(args);
+ case XFS_DIR2_FMT_NODE:
+ return xfs_dir2_node_addname(args);
+ default:
+ return error;
+ }
+}
+
/*
* Enter a name in a directory, or check for available space.
* If inum is 0, only the available space test is performed.
@@ -269,7 +326,6 @@ xfs_dir_createname(
{
struct xfs_da_args *args;
int rval;
- bool v;
ASSERT(S_ISDIR(VFS_I(dp)->i_mode));
@@ -295,31 +351,9 @@ xfs_dir_createname(
args->whichfork = XFS_DATA_FORK;
args->trans = tp;
args->op_flags = XFS_DA_OP_ADDNAME | XFS_DA_OP_OKNOENT;
- if (!inum)
- args->op_flags |= XFS_DA_OP_JUSTCHECK;
-
- if (dp->i_df.if_format == XFS_DINODE_FMT_LOCAL) {
- rval = xfs_dir2_sf_addname(args);
- goto out_free;
- }
-
- rval = xfs_dir2_isblock(args, &v);
- if (rval)
- goto out_free;
- if (v) {
- rval = xfs_dir2_block_addname(args);
- goto out_free;
- }
+ args->owner = dp->i_ino;
- rval = xfs_dir2_isleaf(args, &v);
- if (rval)
- goto out_free;
- if (v)
- rval = xfs_dir2_leaf_addname(args);
- else
- rval = xfs_dir2_node_addname(args);
-
-out_free:
+ rval = xfs_dir_createname_args(args);
kfree(args);
return rval;
}
@@ -350,6 +384,34 @@ xfs_dir_cilookup_result(
return -EEXIST;
}
+int
+xfs_dir_lookup_args(
+ struct xfs_da_args *args)
+{
+ int error;
+
+ switch (xfs_dir2_format(args, &error)) {
+ case XFS_DIR2_FMT_SF:
+ error = xfs_dir2_sf_lookup(args);
+ break;
+ case XFS_DIR2_FMT_BLOCK:
+ error = xfs_dir2_block_lookup(args);
+ break;
+ case XFS_DIR2_FMT_LEAF:
+ error = xfs_dir2_leaf_lookup(args);
+ break;
+ case XFS_DIR2_FMT_NODE:
+ error = xfs_dir2_node_lookup(args);
+ break;
+ default:
+ break;
+ }
+
+ if (error != -EEXIST)
+ return error;
+ return 0;
+}
+
/*
* Lookup a name in a directory, give back the inode number.
* If ci_name is not NULL, returns the actual name in ci_name if it differs
@@ -366,7 +428,6 @@ xfs_dir_lookup(
{
struct xfs_da_args *args;
int rval;
- bool v;
int lock_mode;
ASSERT(S_ISDIR(VFS_I(dp)->i_mode));
@@ -383,34 +444,12 @@ xfs_dir_lookup(
args->whichfork = XFS_DATA_FORK;
args->trans = tp;
args->op_flags = XFS_DA_OP_OKNOENT;
+ args->owner = dp->i_ino;
if (ci_name)
args->op_flags |= XFS_DA_OP_CILOOKUP;
lock_mode = xfs_ilock_data_map_shared(dp);
- if (dp->i_df.if_format == XFS_DINODE_FMT_LOCAL) {
- rval = xfs_dir2_sf_lookup(args);
- goto out_check_rval;
- }
-
- rval = xfs_dir2_isblock(args, &v);
- if (rval)
- goto out_free;
- if (v) {
- rval = xfs_dir2_block_lookup(args);
- goto out_check_rval;
- }
-
- rval = xfs_dir2_isleaf(args, &v);
- if (rval)
- goto out_free;
- if (v)
- rval = xfs_dir2_leaf_lookup(args);
- else
- rval = xfs_dir2_node_lookup(args);
-
-out_check_rval:
- if (rval == -EEXIST)
- rval = 0;
+ rval = xfs_dir_lookup_args(args);
if (!rval) {
*inum = args->inumber;
if (ci_name) {
@@ -418,12 +457,31 @@ out_check_rval:
ci_name->len = args->valuelen;
}
}
-out_free:
xfs_iunlock(dp, lock_mode);
kfree(args);
return rval;
}
+int
+xfs_dir_removename_args(
+ struct xfs_da_args *args)
+{
+ int error;
+
+ switch (xfs_dir2_format(args, &error)) {
+ case XFS_DIR2_FMT_SF:
+ return xfs_dir2_sf_removename(args);
+ case XFS_DIR2_FMT_BLOCK:
+ return xfs_dir2_block_removename(args);
+ case XFS_DIR2_FMT_LEAF:
+ return xfs_dir2_leaf_removename(args);
+ case XFS_DIR2_FMT_NODE:
+ return xfs_dir2_node_removename(args);
+ default:
+ return error;
+ }
+}
+
/*
* Remove an entry from a directory.
*/
@@ -431,13 +489,12 @@ int
xfs_dir_removename(
struct xfs_trans *tp,
struct xfs_inode *dp,
- struct xfs_name *name,
+ const struct xfs_name *name,
xfs_ino_t ino,
xfs_extlen_t total) /* bmap's total block count */
{
struct xfs_da_args *args;
int rval;
- bool v;
ASSERT(S_ISDIR(VFS_I(dp)->i_mode));
XFS_STATS_INC(dp->i_mount, xs_dir_remove);
@@ -456,30 +513,30 @@ xfs_dir_removename(
args->total = total;
args->whichfork = XFS_DATA_FORK;
args->trans = tp;
+ args->owner = dp->i_ino;
+ rval = xfs_dir_removename_args(args);
+ kfree(args);
+ return rval;
+}
- if (dp->i_df.if_format == XFS_DINODE_FMT_LOCAL) {
- rval = xfs_dir2_sf_removename(args);
- goto out_free;
- }
+int
+xfs_dir_replace_args(
+ struct xfs_da_args *args)
+{
+ int error;
- rval = xfs_dir2_isblock(args, &v);
- if (rval)
- goto out_free;
- if (v) {
- rval = xfs_dir2_block_removename(args);
- goto out_free;
+ switch (xfs_dir2_format(args, &error)) {
+ case XFS_DIR2_FMT_SF:
+ return xfs_dir2_sf_replace(args);
+ case XFS_DIR2_FMT_BLOCK:
+ return xfs_dir2_block_replace(args);
+ case XFS_DIR2_FMT_LEAF:
+ return xfs_dir2_leaf_replace(args);
+ case XFS_DIR2_FMT_NODE:
+ return xfs_dir2_node_replace(args);
+ default:
+ return error;
}
-
- rval = xfs_dir2_isleaf(args, &v);
- if (rval)
- goto out_free;
- if (v)
- rval = xfs_dir2_leaf_removename(args);
- else
- rval = xfs_dir2_node_removename(args);
-out_free:
- kfree(args);
- return rval;
}
/*
@@ -495,7 +552,6 @@ xfs_dir_replace(
{
struct xfs_da_args *args;
int rval;
- bool v;
ASSERT(S_ISDIR(VFS_I(dp)->i_mode));
@@ -517,28 +573,8 @@ xfs_dir_replace(
args->total = total;
args->whichfork = XFS_DATA_FORK;
args->trans = tp;
-
- if (dp->i_df.if_format == XFS_DINODE_FMT_LOCAL) {
- rval = xfs_dir2_sf_replace(args);
- goto out_free;
- }
-
- rval = xfs_dir2_isblock(args, &v);
- if (rval)
- goto out_free;
- if (v) {
- rval = xfs_dir2_block_replace(args);
- goto out_free;
- }
-
- rval = xfs_dir2_isleaf(args, &v);
- if (rval)
- goto out_free;
- if (v)
- rval = xfs_dir2_leaf_replace(args);
- else
- rval = xfs_dir2_node_replace(args);
-out_free:
+ args->owner = dp->i_ino;
+ rval = xfs_dir_replace_args(args);
kfree(args);
return rval;
}
@@ -607,57 +643,6 @@ xfs_dir2_grow_inode(
}
/*
- * See if the directory is a single-block form directory.
- */
-int
-xfs_dir2_isblock(
- struct xfs_da_args *args,
- bool *isblock)
-{
- struct xfs_mount *mp = args->dp->i_mount;
- xfs_fileoff_t eof;
- int error;
-
- error = xfs_bmap_last_offset(args->dp, &eof, XFS_DATA_FORK);
- if (error)
- return error;
-
- *isblock = false;
- if (XFS_FSB_TO_B(mp, eof) != args->geo->blksize)
- return 0;
-
- *isblock = true;
- if (XFS_IS_CORRUPT(mp, args->dp->i_disk_size != args->geo->blksize)) {
- xfs_da_mark_sick(args);
- return -EFSCORRUPTED;
- }
- return 0;
-}
-
-/*
- * See if the directory is a single-leaf form directory.
- */
-int
-xfs_dir2_isleaf(
- struct xfs_da_args *args,
- bool *isleaf)
-{
- xfs_fileoff_t eof;
- int error;
-
- error = xfs_bmap_last_offset(args->dp, &eof, XFS_DATA_FORK);
- if (error)
- return error;
-
- *isleaf = false;
- if (eof != args->geo->leafblk + args->geo->fsbcount)
- return 0;
-
- *isleaf = true;
- return 0;
-}
-
-/*
* Remove the given block from the directory.
* This routine is used for data and free blocks, leaf/node are done
* by xfs_da_shrink_inode.
diff --git a/fs/xfs/libxfs/xfs_dir2.h b/fs/xfs/libxfs/xfs_dir2.h
index 8497d041f3..6dbe6e9ecb 100644
--- a/fs/xfs/libxfs/xfs_dir2.h
+++ b/fs/xfs/libxfs/xfs_dir2.h
@@ -36,6 +36,16 @@ xfs_dir2_samename(
return !memcmp(n1->name, n2->name, n1->len);
}
+enum xfs_dir2_fmt {
+ XFS_DIR2_FMT_SF,
+ XFS_DIR2_FMT_BLOCK,
+ XFS_DIR2_FMT_LEAF,
+ XFS_DIR2_FMT_NODE,
+ XFS_DIR2_FMT_ERROR,
+};
+
+enum xfs_dir2_fmt xfs_dir2_format(struct xfs_da_args *args, int *error);
+
/*
* Convert inode mode to directory entry filetype
*/
@@ -58,7 +68,7 @@ extern int xfs_dir_lookup(struct xfs_trans *tp, struct xfs_inode *dp,
const struct xfs_name *name, xfs_ino_t *inum,
struct xfs_name *ci_name);
extern int xfs_dir_removename(struct xfs_trans *tp, struct xfs_inode *dp,
- struct xfs_name *name, xfs_ino_t ino,
+ const struct xfs_name *name, xfs_ino_t ino,
xfs_extlen_t tot);
extern int xfs_dir_replace(struct xfs_trans *tp, struct xfs_inode *dp,
const struct xfs_name *name, xfs_ino_t inum,
@@ -66,6 +76,11 @@ extern int xfs_dir_replace(struct xfs_trans *tp, struct xfs_inode *dp,
extern int xfs_dir_canenter(struct xfs_trans *tp, struct xfs_inode *dp,
struct xfs_name *name);
+int xfs_dir_lookup_args(struct xfs_da_args *args);
+int xfs_dir_createname_args(struct xfs_da_args *args);
+int xfs_dir_removename_args(struct xfs_da_args *args);
+int xfs_dir_replace_args(struct xfs_da_args *args);
+
/*
* Direct call from the bmap code, bypassing the generic directory layer.
*/
@@ -74,8 +89,6 @@ extern int xfs_dir2_sf_to_block(struct xfs_da_args *args);
/*
* Interface routines used by userspace utilities
*/
-extern int xfs_dir2_isblock(struct xfs_da_args *args, bool *isblock);
-extern int xfs_dir2_isleaf(struct xfs_da_args *args, bool *isleaf);
extern int xfs_dir2_shrink_inode(struct xfs_da_args *args, xfs_dir2_db_t db,
struct xfs_buf *bp);
@@ -101,6 +114,10 @@ extern struct xfs_dir2_data_free *xfs_dir2_data_freefind(
extern int xfs_dir_ino_validate(struct xfs_mount *mp, xfs_ino_t ino);
+xfs_failaddr_t xfs_dir3_leaf_header_check(struct xfs_buf *bp, xfs_ino_t owner);
+xfs_failaddr_t xfs_dir3_data_header_check(struct xfs_buf *bp, xfs_ino_t owner);
+xfs_failaddr_t xfs_dir3_block_header_check(struct xfs_buf *bp, xfs_ino_t owner);
+
extern const struct xfs_buf_ops xfs_dir3_block_buf_ops;
extern const struct xfs_buf_ops xfs_dir3_leafn_buf_ops;
extern const struct xfs_buf_ops xfs_dir3_leaf1_buf_ops;
diff --git a/fs/xfs/libxfs/xfs_dir2_block.c b/fs/xfs/libxfs/xfs_dir2_block.c
index a2da007adb..0f93ed1a4a 100644
--- a/fs/xfs/libxfs/xfs_dir2_block.c
+++ b/fs/xfs/libxfs/xfs_dir2_block.c
@@ -115,17 +115,20 @@ const struct xfs_buf_ops xfs_dir3_block_buf_ops = {
.verify_struct = xfs_dir3_block_verify,
};
-static xfs_failaddr_t
+xfs_failaddr_t
xfs_dir3_block_header_check(
- struct xfs_inode *dp,
- struct xfs_buf *bp)
+ struct xfs_buf *bp,
+ xfs_ino_t owner)
{
- struct xfs_mount *mp = dp->i_mount;
+ struct xfs_mount *mp = bp->b_mount;
if (xfs_has_crc(mp)) {
struct xfs_dir3_blk_hdr *hdr3 = bp->b_addr;
- if (be64_to_cpu(hdr3->owner) != dp->i_ino)
+ if (hdr3->magic != cpu_to_be32(XFS_DIR3_BLOCK_MAGIC))
+ return __this_address;
+
+ if (be64_to_cpu(hdr3->owner) != owner)
return __this_address;
}
@@ -136,6 +139,7 @@ int
xfs_dir3_block_read(
struct xfs_trans *tp,
struct xfs_inode *dp,
+ xfs_ino_t owner,
struct xfs_buf **bpp)
{
struct xfs_mount *mp = dp->i_mount;
@@ -148,7 +152,7 @@ xfs_dir3_block_read(
return err;
/* Check things that we can't do in the verifier. */
- fa = xfs_dir3_block_header_check(dp, *bpp);
+ fa = xfs_dir3_block_header_check(*bpp, owner);
if (fa) {
__xfs_buf_mark_corrupt(*bpp, fa);
xfs_trans_brelse(tp, *bpp);
@@ -163,12 +167,13 @@ xfs_dir3_block_read(
static void
xfs_dir3_block_init(
- struct xfs_mount *mp,
- struct xfs_trans *tp,
- struct xfs_buf *bp,
- struct xfs_inode *dp)
+ struct xfs_da_args *args,
+ struct xfs_buf *bp)
{
- struct xfs_dir3_blk_hdr *hdr3 = bp->b_addr;
+ struct xfs_trans *tp = args->trans;
+ struct xfs_inode *dp = args->dp;
+ struct xfs_mount *mp = dp->i_mount;
+ struct xfs_dir3_blk_hdr *hdr3 = bp->b_addr;
bp->b_ops = &xfs_dir3_block_buf_ops;
xfs_trans_buf_set_type(tp, bp, XFS_BLFT_DIR_BLOCK_BUF);
@@ -177,7 +182,7 @@ xfs_dir3_block_init(
memset(hdr3, 0, sizeof(*hdr3));
hdr3->magic = cpu_to_be32(XFS_DIR3_BLOCK_MAGIC);
hdr3->blkno = cpu_to_be64(xfs_buf_daddr(bp));
- hdr3->owner = cpu_to_be64(dp->i_ino);
+ hdr3->owner = cpu_to_be64(args->owner);
uuid_copy(&hdr3->uuid, &mp->m_sb.sb_meta_uuid);
return;
@@ -382,7 +387,7 @@ xfs_dir2_block_addname(
tp = args->trans;
/* Read the (one and only) directory block into bp. */
- error = xfs_dir3_block_read(tp, dp, &bp);
+ error = xfs_dir3_block_read(tp, dp, args->owner, &bp);
if (error)
return error;
@@ -697,7 +702,7 @@ xfs_dir2_block_lookup_int(
dp = args->dp;
tp = args->trans;
- error = xfs_dir3_block_read(tp, dp, &bp);
+ error = xfs_dir3_block_read(tp, dp, args->owner, &bp);
if (error)
return error;
@@ -981,7 +986,8 @@ xfs_dir2_leaf_to_block(
* Read the data block if we don't already have it, give up if it fails.
*/
if (!dbp) {
- error = xfs_dir3_data_read(tp, dp, args->geo->datablk, 0, &dbp);
+ error = xfs_dir3_data_read(tp, dp, args->owner,
+ args->geo->datablk, 0, &dbp);
if (error)
return error;
}
@@ -1009,7 +1015,7 @@ xfs_dir2_leaf_to_block(
/*
* Start converting it to block form.
*/
- xfs_dir3_block_init(mp, tp, dbp, dp);
+ xfs_dir3_block_init(args, dbp);
needlog = 1;
needscan = 0;
@@ -1129,7 +1135,7 @@ xfs_dir2_sf_to_block(
error = xfs_dir3_data_init(args, blkno, &bp);
if (error)
goto out_free;
- xfs_dir3_block_init(mp, tp, bp, dp);
+ xfs_dir3_block_init(args, bp);
hdr = bp->b_addr;
/*
@@ -1169,7 +1175,7 @@ xfs_dir2_sf_to_block(
* Create entry for .
*/
dep = bp->b_addr + offset;
- dep->inumber = cpu_to_be64(dp->i_ino);
+ dep->inumber = cpu_to_be64(args->owner);
dep->namelen = 1;
dep->name[0] = '.';
xfs_dir2_data_put_ftype(mp, dep, XFS_DIR3_FT_DIR);
diff --git a/fs/xfs/libxfs/xfs_dir2_data.c b/fs/xfs/libxfs/xfs_dir2_data.c
index 7a6d965bea..ea0b9628df 100644
--- a/fs/xfs/libxfs/xfs_dir2_data.c
+++ b/fs/xfs/libxfs/xfs_dir2_data.c
@@ -395,17 +395,20 @@ static const struct xfs_buf_ops xfs_dir3_data_reada_buf_ops = {
.verify_write = xfs_dir3_data_write_verify,
};
-static xfs_failaddr_t
+xfs_failaddr_t
xfs_dir3_data_header_check(
- struct xfs_inode *dp,
- struct xfs_buf *bp)
+ struct xfs_buf *bp,
+ xfs_ino_t owner)
{
- struct xfs_mount *mp = dp->i_mount;
+ struct xfs_mount *mp = bp->b_mount;
if (xfs_has_crc(mp)) {
struct xfs_dir3_data_hdr *hdr3 = bp->b_addr;
- if (be64_to_cpu(hdr3->hdr.owner) != dp->i_ino)
+ if (hdr3->hdr.magic != cpu_to_be32(XFS_DIR3_DATA_MAGIC))
+ return __this_address;
+
+ if (be64_to_cpu(hdr3->hdr.owner) != owner)
return __this_address;
}
@@ -416,6 +419,7 @@ int
xfs_dir3_data_read(
struct xfs_trans *tp,
struct xfs_inode *dp,
+ xfs_ino_t owner,
xfs_dablk_t bno,
unsigned int flags,
struct xfs_buf **bpp)
@@ -429,7 +433,7 @@ xfs_dir3_data_read(
return err;
/* Check things that we can't do in the verifier. */
- fa = xfs_dir3_data_header_check(dp, *bpp);
+ fa = xfs_dir3_data_header_check(*bpp, owner);
if (fa) {
__xfs_buf_mark_corrupt(*bpp, fa);
xfs_trans_brelse(tp, *bpp);
@@ -725,7 +729,7 @@ xfs_dir3_data_init(
memset(hdr3, 0, sizeof(*hdr3));
hdr3->magic = cpu_to_be32(XFS_DIR3_DATA_MAGIC);
hdr3->blkno = cpu_to_be64(xfs_buf_daddr(bp));
- hdr3->owner = cpu_to_be64(dp->i_ino);
+ hdr3->owner = cpu_to_be64(args->owner);
uuid_copy(&hdr3->uuid, &mp->m_sb.sb_meta_uuid);
} else
diff --git a/fs/xfs/libxfs/xfs_dir2_leaf.c b/fs/xfs/libxfs/xfs_dir2_leaf.c
index 08dda5ce9d..71c2f22a3f 100644
--- a/fs/xfs/libxfs/xfs_dir2_leaf.c
+++ b/fs/xfs/libxfs/xfs_dir2_leaf.c
@@ -208,6 +208,29 @@ xfs_dir3_leaf_verify(
return xfs_dir3_leaf_check_int(mp, &leafhdr, bp->b_addr, true);
}
+xfs_failaddr_t
+xfs_dir3_leaf_header_check(
+ struct xfs_buf *bp,
+ xfs_ino_t owner)
+{
+ struct xfs_mount *mp = bp->b_mount;
+
+ if (xfs_has_crc(mp)) {
+ struct xfs_dir3_leaf *hdr3 = bp->b_addr;
+
+ if (hdr3->hdr.info.hdr.magic !=
+ cpu_to_be16(XFS_DIR3_LEAF1_MAGIC) &&
+ hdr3->hdr.info.hdr.magic !=
+ cpu_to_be16(XFS_DIR3_LEAFN_MAGIC))
+ return __this_address;
+
+ if (be64_to_cpu(hdr3->hdr.info.owner) != owner)
+ return __this_address;
+ }
+
+ return NULL;
+}
+
static void
xfs_dir3_leaf_read_verify(
struct xfs_buf *bp)
@@ -271,32 +294,60 @@ int
xfs_dir3_leaf_read(
struct xfs_trans *tp,
struct xfs_inode *dp,
+ xfs_ino_t owner,
xfs_dablk_t fbno,
struct xfs_buf **bpp)
{
+ xfs_failaddr_t fa;
int err;
err = xfs_da_read_buf(tp, dp, fbno, 0, bpp, XFS_DATA_FORK,
&xfs_dir3_leaf1_buf_ops);
- if (!err && tp && *bpp)
+ if (err || !(*bpp))
+ return err;
+
+ fa = xfs_dir3_leaf_header_check(*bpp, owner);
+ if (fa) {
+ __xfs_buf_mark_corrupt(*bpp, fa);
+ xfs_trans_brelse(tp, *bpp);
+ *bpp = NULL;
+ xfs_dirattr_mark_sick(dp, XFS_DATA_FORK);
+ return -EFSCORRUPTED;
+ }
+
+ if (tp)
xfs_trans_buf_set_type(tp, *bpp, XFS_BLFT_DIR_LEAF1_BUF);
- return err;
+ return 0;
}
int
xfs_dir3_leafn_read(
struct xfs_trans *tp,
struct xfs_inode *dp,
+ xfs_ino_t owner,
xfs_dablk_t fbno,
struct xfs_buf **bpp)
{
+ xfs_failaddr_t fa;
int err;
err = xfs_da_read_buf(tp, dp, fbno, 0, bpp, XFS_DATA_FORK,
&xfs_dir3_leafn_buf_ops);
- if (!err && tp && *bpp)
+ if (err || !(*bpp))
+ return err;
+
+ fa = xfs_dir3_leaf_header_check(*bpp, owner);
+ if (fa) {
+ __xfs_buf_mark_corrupt(*bpp, fa);
+ xfs_trans_brelse(tp, *bpp);
+ *bpp = NULL;
+ xfs_dirattr_mark_sick(dp, XFS_DATA_FORK);
+ return -EFSCORRUPTED;
+ }
+
+ if (tp)
xfs_trans_buf_set_type(tp, *bpp, XFS_BLFT_DIR_LEAFN_BUF);
- return err;
+ return 0;
}
/*
@@ -304,12 +355,12 @@ xfs_dir3_leafn_read(
*/
static void
xfs_dir3_leaf_init(
- struct xfs_mount *mp,
- struct xfs_trans *tp,
+ struct xfs_da_args *args,
struct xfs_buf *bp,
- xfs_ino_t owner,
uint16_t type)
{
+ struct xfs_mount *mp = args->dp->i_mount;
+ struct xfs_trans *tp = args->trans;
struct xfs_dir2_leaf *leaf = bp->b_addr;
ASSERT(type == XFS_DIR2_LEAF1_MAGIC || type == XFS_DIR2_LEAFN_MAGIC);
@@ -323,7 +374,7 @@ xfs_dir3_leaf_init(
? cpu_to_be16(XFS_DIR3_LEAF1_MAGIC)
: cpu_to_be16(XFS_DIR3_LEAFN_MAGIC);
leaf3->info.blkno = cpu_to_be64(xfs_buf_daddr(bp));
- leaf3->info.owner = cpu_to_be64(owner);
+ leaf3->info.owner = cpu_to_be64(args->owner);
uuid_copy(&leaf3->info.uuid, &mp->m_sb.sb_meta_uuid);
} else {
memset(leaf, 0, sizeof(*leaf));
@@ -356,7 +407,6 @@ xfs_dir3_leaf_get_buf(
{
struct xfs_inode *dp = args->dp;
struct xfs_trans *tp = args->trans;
- struct xfs_mount *mp = dp->i_mount;
struct xfs_buf *bp;
int error;
@@ -369,7 +419,7 @@ xfs_dir3_leaf_get_buf(
if (error)
return error;
- xfs_dir3_leaf_init(mp, tp, bp, dp->i_ino, magic);
+ xfs_dir3_leaf_init(args, bp, magic);
xfs_dir3_leaf_log_header(args, bp);
if (magic == XFS_DIR2_LEAF1_MAGIC)
xfs_dir3_leaf_log_tail(args, bp);
@@ -647,7 +697,8 @@ xfs_dir2_leaf_addname(
trace_xfs_dir2_leaf_addname(args);
- error = xfs_dir3_leaf_read(tp, dp, args->geo->leafblk, &lbp);
+ error = xfs_dir3_leaf_read(tp, dp, args->owner, args->geo->leafblk,
+ &lbp);
if (error)
return error;
@@ -834,9 +885,9 @@ xfs_dir2_leaf_addname(
* Already had space in some data block.
* Just read that one in.
*/
- error = xfs_dir3_data_read(tp, dp,
- xfs_dir2_db_to_da(args->geo, use_block),
- 0, &dbp);
+ error = xfs_dir3_data_read(tp, dp, args->owner,
+ xfs_dir2_db_to_da(args->geo, use_block), 0,
+ &dbp);
if (error) {
xfs_trans_brelse(tp, lbp);
return error;
@@ -1238,7 +1289,8 @@ xfs_dir2_leaf_lookup_int(
tp = args->trans;
mp = dp->i_mount;
- error = xfs_dir3_leaf_read(tp, dp, args->geo->leafblk, &lbp);
+ error = xfs_dir3_leaf_read(tp, dp, args->owner, args->geo->leafblk,
+ &lbp);
if (error)
return error;
@@ -1276,9 +1328,9 @@ xfs_dir2_leaf_lookup_int(
if (newdb != curdb) {
if (dbp)
xfs_trans_brelse(tp, dbp);
- error = xfs_dir3_data_read(tp, dp,
- xfs_dir2_db_to_da(args->geo, newdb),
- 0, &dbp);
+ error = xfs_dir3_data_read(tp, dp, args->owner,
+ xfs_dir2_db_to_da(args->geo, newdb), 0,
+ &dbp);
if (error) {
xfs_trans_brelse(tp, lbp);
return error;
@@ -1318,9 +1370,9 @@ xfs_dir2_leaf_lookup_int(
ASSERT(cidb != -1);
if (cidb != curdb) {
xfs_trans_brelse(tp, dbp);
- error = xfs_dir3_data_read(tp, dp,
- xfs_dir2_db_to_da(args->geo, cidb),
- 0, &dbp);
+ error = xfs_dir3_data_read(tp, dp, args->owner,
+ xfs_dir2_db_to_da(args->geo, cidb), 0,
+ &dbp);
if (error) {
xfs_trans_brelse(tp, lbp);
return error;
@@ -1614,7 +1666,8 @@ xfs_dir2_leaf_trim_data(
/*
* Read the offending data block. We need its buffer.
*/
- error = xfs_dir3_data_read(tp, dp, xfs_dir2_db_to_da(geo, db), 0, &dbp);
+ error = xfs_dir3_data_read(tp, dp, args->owner,
+ xfs_dir2_db_to_da(geo, db), 0, &dbp);
if (error)
return error;
@@ -1753,7 +1806,8 @@ xfs_dir2_node_to_leaf(
/*
* Read the freespace block.
*/
- error = xfs_dir2_free_read(tp, dp, args->geo->freeblk, &fbp);
+ error = xfs_dir2_free_read(tp, dp, args->owner, args->geo->freeblk,
+ &fbp);
if (error)
return error;
xfs_dir2_free_hdr_from_disk(mp, &freehdr, fbp->b_addr);
diff --git a/fs/xfs/libxfs/xfs_dir2_node.c b/fs/xfs/libxfs/xfs_dir2_node.c
index be0b883402..fe8d4fa131 100644
--- a/fs/xfs/libxfs/xfs_dir2_node.c
+++ b/fs/xfs/libxfs/xfs_dir2_node.c
@@ -175,11 +175,11 @@ const struct xfs_buf_ops xfs_dir3_free_buf_ops = {
/* Everything ok in the free block header? */
static xfs_failaddr_t
xfs_dir3_free_header_check(
- struct xfs_inode *dp,
- xfs_dablk_t fbno,
- struct xfs_buf *bp)
+ struct xfs_buf *bp,
+ xfs_ino_t owner,
+ xfs_dablk_t fbno)
{
- struct xfs_mount *mp = dp->i_mount;
+ struct xfs_mount *mp = bp->b_mount;
int maxbests = mp->m_dir_geo->free_max_bests;
unsigned int firstdb;
@@ -195,7 +195,7 @@ xfs_dir3_free_header_check(
return __this_address;
if (be32_to_cpu(hdr3->nvalid) < be32_to_cpu(hdr3->nused))
return __this_address;
- if (be64_to_cpu(hdr3->hdr.owner) != dp->i_ino)
+ if (be64_to_cpu(hdr3->hdr.owner) != owner)
return __this_address;
} else {
struct xfs_dir2_free_hdr *hdr = bp->b_addr;
@@ -214,6 +214,7 @@ static int
__xfs_dir3_free_read(
struct xfs_trans *tp,
struct xfs_inode *dp,
+ xfs_ino_t owner,
xfs_dablk_t fbno,
unsigned int flags,
struct xfs_buf **bpp)
@@ -227,7 +228,7 @@ __xfs_dir3_free_read(
return err;
/* Check things that we can't do in the verifier. */
- fa = xfs_dir3_free_header_check(dp, fbno, *bpp);
+ fa = xfs_dir3_free_header_check(*bpp, owner, fbno);
if (fa) {
__xfs_buf_mark_corrupt(*bpp, fa);
xfs_trans_brelse(tp, *bpp);
@@ -299,20 +300,23 @@ int
xfs_dir2_free_read(
struct xfs_trans *tp,
struct xfs_inode *dp,
+ xfs_ino_t owner,
xfs_dablk_t fbno,
struct xfs_buf **bpp)
{
- return __xfs_dir3_free_read(tp, dp, fbno, 0, bpp);
+ return __xfs_dir3_free_read(tp, dp, owner, fbno, 0, bpp);
}
static int
xfs_dir2_free_try_read(
struct xfs_trans *tp,
struct xfs_inode *dp,
+ xfs_ino_t owner,
xfs_dablk_t fbno,
struct xfs_buf **bpp)
{
- return __xfs_dir3_free_read(tp, dp, fbno, XFS_DABUF_MAP_HOLE_OK, bpp);
+ return __xfs_dir3_free_read(tp, dp, owner, fbno, XFS_DABUF_MAP_HOLE_OK,
+ bpp);
}
static int
@@ -349,7 +353,7 @@ xfs_dir3_free_get_buf(
hdr.magic = XFS_DIR3_FREE_MAGIC;
hdr3->hdr.blkno = cpu_to_be64(xfs_buf_daddr(bp));
- hdr3->hdr.owner = cpu_to_be64(dp->i_ino);
+ hdr3->hdr.owner = cpu_to_be64(args->owner);
uuid_copy(&hdr3->hdr.uuid, &mp->m_sb.sb_meta_uuid);
} else
hdr.magic = XFS_DIR2_FREE_MAGIC;
@@ -717,7 +721,7 @@ xfs_dir2_leafn_lookup_for_addname(
if (curbp)
xfs_trans_brelse(tp, curbp);
- error = xfs_dir2_free_read(tp, dp,
+ error = xfs_dir2_free_read(tp, dp, args->owner,
xfs_dir2_db_to_da(args->geo,
newfdb),
&curbp);
@@ -863,7 +867,7 @@ xfs_dir2_leafn_lookup_for_entry(
ASSERT(state->extravalid);
curbp = state->extrablk.bp;
} else {
- error = xfs_dir3_data_read(tp, dp,
+ error = xfs_dir3_data_read(tp, dp, args->owner,
xfs_dir2_db_to_da(args->geo,
newdb),
0, &curbp);
@@ -1356,8 +1360,8 @@ xfs_dir2_leafn_remove(
* read in the free block.
*/
fdb = xfs_dir2_db_to_fdb(geo, db);
- error = xfs_dir2_free_read(tp, dp, xfs_dir2_db_to_da(geo, fdb),
- &fbp);
+ error = xfs_dir2_free_read(tp, dp, args->owner,
+ xfs_dir2_db_to_da(geo, fdb), &fbp);
if (error)
return error;
free = fbp->b_addr;
@@ -1562,7 +1566,8 @@ xfs_dir2_leafn_toosmall(
/*
* Read the sibling leaf block.
*/
- error = xfs_dir3_leafn_read(state->args->trans, dp, blkno, &bp);
+ error = xfs_dir3_leafn_read(state->args->trans, dp,
+ state->args->owner, blkno, &bp);
if (error)
return error;
@@ -1715,7 +1720,7 @@ xfs_dir2_node_add_datablk(
* that was just allocated.
*/
fbno = xfs_dir2_db_to_fdb(args->geo, *dbno);
- error = xfs_dir2_free_try_read(tp, dp,
+ error = xfs_dir2_free_try_read(tp, dp, args->owner,
xfs_dir2_db_to_da(args->geo, fbno), &fbp);
if (error)
return error;
@@ -1862,7 +1867,7 @@ xfs_dir2_node_find_freeblk(
* so this might not succeed. This should be really rare, so
* there's no reason to avoid it.
*/
- error = xfs_dir2_free_try_read(tp, dp,
+ error = xfs_dir2_free_try_read(tp, dp, args->owner,
xfs_dir2_db_to_da(args->geo, fbno),
&fbp);
if (error)
@@ -1948,9 +1953,8 @@ xfs_dir2_node_addname_int(
&freehdr, &findex);
} else {
/* Read the data block in. */
- error = xfs_dir3_data_read(tp, dp,
- xfs_dir2_db_to_da(args->geo, dbno),
- 0, &dbp);
+ error = xfs_dir3_data_read(tp, dp, args->owner,
+ xfs_dir2_db_to_da(args->geo, dbno), 0, &dbp);
}
if (error)
return error;
@@ -2302,7 +2306,7 @@ xfs_dir2_node_trim_free(
/*
* Read the freespace block.
*/
- error = xfs_dir2_free_try_read(tp, dp, fo, &bp);
+ error = xfs_dir2_free_try_read(tp, dp, args->owner, fo, &bp);
if (error)
return error;
/*
diff --git a/fs/xfs/libxfs/xfs_dir2_priv.h b/fs/xfs/libxfs/xfs_dir2_priv.h
index 1db2e60ba8..3befb32509 100644
--- a/fs/xfs/libxfs/xfs_dir2_priv.h
+++ b/fs/xfs/libxfs/xfs_dir2_priv.h
@@ -50,8 +50,8 @@ extern int xfs_dir_cilookup_result(struct xfs_da_args *args,
/* xfs_dir2_block.c */
-extern int xfs_dir3_block_read(struct xfs_trans *tp, struct xfs_inode *dp,
- struct xfs_buf **bpp);
+int xfs_dir3_block_read(struct xfs_trans *tp, struct xfs_inode *dp,
+ xfs_ino_t owner, struct xfs_buf **bpp);
extern int xfs_dir2_block_addname(struct xfs_da_args *args);
extern int xfs_dir2_block_lookup(struct xfs_da_args *args);
extern int xfs_dir2_block_removename(struct xfs_da_args *args);
@@ -78,7 +78,8 @@ extern void xfs_dir3_data_check(struct xfs_inode *dp, struct xfs_buf *bp);
extern xfs_failaddr_t __xfs_dir3_data_check(struct xfs_inode *dp,
struct xfs_buf *bp);
int xfs_dir3_data_read(struct xfs_trans *tp, struct xfs_inode *dp,
- xfs_dablk_t bno, unsigned int flags, struct xfs_buf **bpp);
+ xfs_ino_t owner, xfs_dablk_t bno, unsigned int flags,
+ struct xfs_buf **bpp);
int xfs_dir3_data_readahead(struct xfs_inode *dp, xfs_dablk_t bno,
unsigned int flags);
@@ -95,9 +96,9 @@ void xfs_dir2_leaf_hdr_from_disk(struct xfs_mount *mp,
void xfs_dir2_leaf_hdr_to_disk(struct xfs_mount *mp, struct xfs_dir2_leaf *to,
struct xfs_dir3_icleaf_hdr *from);
int xfs_dir3_leaf_read(struct xfs_trans *tp, struct xfs_inode *dp,
- xfs_dablk_t fbno, struct xfs_buf **bpp);
+ xfs_ino_t owner, xfs_dablk_t fbno, struct xfs_buf **bpp);
int xfs_dir3_leafn_read(struct xfs_trans *tp, struct xfs_inode *dp,
- xfs_dablk_t fbno, struct xfs_buf **bpp);
+ xfs_ino_t owner, xfs_dablk_t fbno, struct xfs_buf **bpp);
extern int xfs_dir2_block_to_leaf(struct xfs_da_args *args,
struct xfs_buf *dbp);
extern int xfs_dir2_leaf_addname(struct xfs_da_args *args);
@@ -154,8 +155,8 @@ extern int xfs_dir2_node_removename(struct xfs_da_args *args);
extern int xfs_dir2_node_replace(struct xfs_da_args *args);
extern int xfs_dir2_node_trim_free(struct xfs_da_args *args, xfs_fileoff_t fo,
int *rvalp);
-extern int xfs_dir2_free_read(struct xfs_trans *tp, struct xfs_inode *dp,
- xfs_dablk_t fbno, struct xfs_buf **bpp);
+int xfs_dir2_free_read(struct xfs_trans *tp, struct xfs_inode *dp,
+ xfs_ino_t owner, xfs_dablk_t fbno, struct xfs_buf **bpp);
/* xfs_dir2_sf.c */
xfs_ino_t xfs_dir2_sf_get_ino(struct xfs_mount *mp, struct xfs_dir2_sf_hdr *hdr,
diff --git a/fs/xfs/libxfs/xfs_errortag.h b/fs/xfs/libxfs/xfs_errortag.h
index 01a9e86b30..7002d7676a 100644
--- a/fs/xfs/libxfs/xfs_errortag.h
+++ b/fs/xfs/libxfs/xfs_errortag.h
@@ -63,7 +63,8 @@
#define XFS_ERRTAG_ATTR_LEAF_TO_NODE 41
#define XFS_ERRTAG_WB_DELAY_MS 42
#define XFS_ERRTAG_WRITE_DELAY_MS 43
-#define XFS_ERRTAG_MAX 44
+#define XFS_ERRTAG_EXCHMAPS_FINISH_ONE 44
+#define XFS_ERRTAG_MAX 45
/*
* Random factors for above tags, 1 means always, 2 means 1/2 time, etc.
@@ -111,5 +112,6 @@
#define XFS_RANDOM_ATTR_LEAF_TO_NODE 1
#define XFS_RANDOM_WB_DELAY_MS 3000
#define XFS_RANDOM_WRITE_DELAY_MS 3000
+#define XFS_RANDOM_EXCHMAPS_FINISH_ONE 1
#endif /* __XFS_ERRORTAG_H_ */
diff --git a/fs/xfs/libxfs/xfs_exchmaps.c b/fs/xfs/libxfs/xfs_exchmaps.c
new file mode 100644
index 0000000000..2021396651
--- /dev/null
+++ b/fs/xfs/libxfs/xfs_exchmaps.c
@@ -0,0 +1,1235 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2020-2024 Oracle. All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_defer.h"
+#include "xfs_inode.h"
+#include "xfs_trans.h"
+#include "xfs_bmap.h"
+#include "xfs_icache.h"
+#include "xfs_quota.h"
+#include "xfs_exchmaps.h"
+#include "xfs_trace.h"
+#include "xfs_bmap_btree.h"
+#include "xfs_trans_space.h"
+#include "xfs_error.h"
+#include "xfs_errortag.h"
+#include "xfs_health.h"
+#include "xfs_exchmaps_item.h"
+#include "xfs_da_format.h"
+#include "xfs_da_btree.h"
+#include "xfs_attr_leaf.h"
+#include "xfs_attr.h"
+#include "xfs_dir2_priv.h"
+#include "xfs_dir2.h"
+#include "xfs_symlink_remote.h"
+
+struct kmem_cache *xfs_exchmaps_intent_cache;
+
+/* bmbt mappings adjacent to a pair of records. */
+struct xfs_exchmaps_adjacent {
+ struct xfs_bmbt_irec left1;
+ struct xfs_bmbt_irec right1;
+ struct xfs_bmbt_irec left2;
+ struct xfs_bmbt_irec right2;
+};
+
+#define ADJACENT_INIT { \
+ .left1 = { .br_startblock = HOLESTARTBLOCK }, \
+ .right1 = { .br_startblock = HOLESTARTBLOCK }, \
+ .left2 = { .br_startblock = HOLESTARTBLOCK }, \
+ .right2 = { .br_startblock = HOLESTARTBLOCK }, \
+}
+
+/* Information to reset reflink flag / CoW fork state after an exchange. */
+
+/*
+ * If the reflink flag is set on either inode, make sure it has an incore CoW
+ * fork, since all reflink inodes must have them. If there's a CoW fork and it
+ * has mappings in it, make sure the inodes are tagged appropriately so that
+ * speculative preallocations can be GC'd if we run low of space.
+ */
+static inline void
+xfs_exchmaps_ensure_cowfork(
+ struct xfs_inode *ip)
+{
+ struct xfs_ifork *cfork;
+
+ if (xfs_is_reflink_inode(ip))
+ xfs_ifork_init_cow(ip);
+
+ cfork = xfs_ifork_ptr(ip, XFS_COW_FORK);
+ if (!cfork)
+ return;
+ if (cfork->if_bytes > 0)
+ xfs_inode_set_cowblocks_tag(ip);
+ else
+ xfs_inode_clear_cowblocks_tag(ip);
+}
+
+/*
+ * Adjust the on-disk inode size upwards if needed so that we never add
+ * mappings into the file past EOF. This is crucial so that log recovery won't
+ * get confused by the sudden appearance of post-eof mappings.
+ */
+STATIC void
+xfs_exchmaps_update_size(
+ struct xfs_trans *tp,
+ struct xfs_inode *ip,
+ struct xfs_bmbt_irec *imap,
+ xfs_fsize_t new_isize)
+{
+ struct xfs_mount *mp = tp->t_mountp;
+ xfs_fsize_t len;
+
+ if (new_isize < 0)
+ return;
+
+ len = min(XFS_FSB_TO_B(mp, imap->br_startoff + imap->br_blockcount),
+ new_isize);
+
+ if (len <= ip->i_disk_size)
+ return;
+
+ trace_xfs_exchmaps_update_inode_size(ip, len);
+
+ ip->i_disk_size = len;
+ xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+}
+
+/* Advance the incore state tracking after exchanging a mapping. */
+static inline void
+xmi_advance(
+ struct xfs_exchmaps_intent *xmi,
+ const struct xfs_bmbt_irec *irec)
+{
+ xmi->xmi_startoff1 += irec->br_blockcount;
+ xmi->xmi_startoff2 += irec->br_blockcount;
+ xmi->xmi_blockcount -= irec->br_blockcount;
+}
+
+/* Do we still have more mappings to exchange? */
+static inline bool
+xmi_has_more_exchange_work(const struct xfs_exchmaps_intent *xmi)
+{
+ return xmi->xmi_blockcount > 0;
+}
+
+/* Do we have post-operation cleanups to perform? */
+static inline bool
+xmi_has_postop_work(const struct xfs_exchmaps_intent *xmi)
+{
+ return xmi->xmi_flags & (XFS_EXCHMAPS_CLEAR_INO1_REFLINK |
+ XFS_EXCHMAPS_CLEAR_INO2_REFLINK |
+ __XFS_EXCHMAPS_INO2_SHORTFORM);
+}
+
+/* Check all mappings to make sure we can actually exchange them. */
+int
+xfs_exchmaps_check_forks(
+ struct xfs_mount *mp,
+ const struct xfs_exchmaps_req *req)
+{
+ struct xfs_ifork *ifp1, *ifp2;
+ int whichfork = xfs_exchmaps_reqfork(req);
+
+ /* No fork? */
+ ifp1 = xfs_ifork_ptr(req->ip1, whichfork);
+ ifp2 = xfs_ifork_ptr(req->ip2, whichfork);
+ if (!ifp1 || !ifp2)
+ return -EINVAL;
+
+ /* We don't know how to exchange local format forks. */
+ if (ifp1->if_format == XFS_DINODE_FMT_LOCAL ||
+ ifp2->if_format == XFS_DINODE_FMT_LOCAL)
+ return -EINVAL;
+
+ return 0;
+}
+
+#ifdef CONFIG_XFS_QUOTA
+/* Log the actual updates to the quota accounting. */
+static inline void
+xfs_exchmaps_update_quota(
+ struct xfs_trans *tp,
+ struct xfs_exchmaps_intent *xmi,
+ struct xfs_bmbt_irec *irec1,
+ struct xfs_bmbt_irec *irec2)
+{
+ int64_t ip1_delta = 0, ip2_delta = 0;
+ unsigned int qflag;
+
+ qflag = XFS_IS_REALTIME_INODE(xmi->xmi_ip1) ? XFS_TRANS_DQ_RTBCOUNT :
+ XFS_TRANS_DQ_BCOUNT;
+
+ if (xfs_bmap_is_real_extent(irec1)) {
+ ip1_delta -= irec1->br_blockcount;
+ ip2_delta += irec1->br_blockcount;
+ }
+
+ if (xfs_bmap_is_real_extent(irec2)) {
+ ip1_delta += irec2->br_blockcount;
+ ip2_delta -= irec2->br_blockcount;
+ }
+
+ xfs_trans_mod_dquot_byino(tp, xmi->xmi_ip1, qflag, ip1_delta);
+ xfs_trans_mod_dquot_byino(tp, xmi->xmi_ip2, qflag, ip2_delta);
+}
+#else
+# define xfs_exchmaps_update_quota(tp, xmi, irec1, irec2) ((void)0)
+#endif
+
+/* Decide if we want to skip this mapping from file1. */
+static inline bool
+xfs_exchmaps_can_skip_mapping(
+ struct xfs_exchmaps_intent *xmi,
+ struct xfs_bmbt_irec *irec)
+{
+ struct xfs_mount *mp = xmi->xmi_ip1->i_mount;
+
+ /* Do not skip this mapping if the caller did not tell us to. */
+ if (!(xmi->xmi_flags & XFS_EXCHMAPS_INO1_WRITTEN))
+ return false;
+
+ /* Do not skip mapped, written mappings. */
+ if (xfs_bmap_is_written_extent(irec))
+ return false;
+
+ /*
+ * The mapping is unwritten or a hole. It cannot be a delalloc
+ * reservation because we already excluded those. It cannot be an
+ * unwritten extent with dirty page cache because we flushed the page
+ * cache. For files where the allocation unit is 1FSB (files on the
+ * data dev, rt files if the extent size is 1FSB), we can safely
+ * skip this mapping.
+ */
+ if (!xfs_inode_has_bigrtalloc(xmi->xmi_ip1))
+ return true;
+
+ /*
+ * For a realtime file with a multi-fsb allocation unit, the decision
+ * is trickier because we can only swap full allocation units.
+ * Unwritten mappings can appear in the middle of an rtx if the rtx is
+ * partially written, but they can also appear for preallocations.
+ *
+ * If the mapping is a hole, skip it entirely. Holes should align with
+ * rtx boundaries.
+ */
+ if (!xfs_bmap_is_real_extent(irec))
+ return true;
+
+ /*
+ * All mappings below this point are unwritten.
+ *
+ * - If the beginning is not aligned to an rtx, trim the end of the
+ * mapping so that it does not cross an rtx boundary, and swap it.
+ *
+ * - If both ends are aligned to an rtx, skip the entire mapping.
+ */
+ if (!isaligned_64(irec->br_startoff, mp->m_sb.sb_rextsize)) {
+ xfs_fileoff_t new_end;
+
+ new_end = roundup_64(irec->br_startoff, mp->m_sb.sb_rextsize);
+ irec->br_blockcount = min(irec->br_blockcount,
+ new_end - irec->br_startoff);
+ return false;
+ }
+ if (isaligned_64(irec->br_blockcount, mp->m_sb.sb_rextsize))
+ return true;
+
+ /*
+ * All mappings below this point are unwritten, start on an rtx
+ * boundary, and do not end on an rtx boundary.
+ *
+ * - If the mapping is longer than one rtx, trim the end of the mapping
+ * down to an rtx boundary and skip it.
+ *
+ * - The mapping is shorter than one rtx. Swap it.
+ */
+ if (irec->br_blockcount > mp->m_sb.sb_rextsize) {
+ xfs_fileoff_t new_end;
+
+ new_end = rounddown_64(irec->br_startoff + irec->br_blockcount,
+ mp->m_sb.sb_rextsize);
+ irec->br_blockcount = new_end - irec->br_startoff;
+ return true;
+ }
+
+ return false;
+}
+
+/*
+ * Walk forward through the file ranges in @xmi until we find two different
+ * mappings to exchange. If there is work to do, return the mappings;
+ * otherwise we've reached the end of the range and xmi_blockcount will be
+ * zero.
+ *
+ * If the walk skips over a pair of mappings to the same storage, save them as
+ * the left records in @adj (if provided) so that the simulation phase can
+ * avoid an extra lookup.
+ */
+static int
+xfs_exchmaps_find_mappings(
+ struct xfs_exchmaps_intent *xmi,
+ struct xfs_bmbt_irec *irec1,
+ struct xfs_bmbt_irec *irec2,
+ struct xfs_exchmaps_adjacent *adj)
+{
+ int nimaps;
+ int bmap_flags;
+ int error;
+
+ bmap_flags = xfs_bmapi_aflag(xfs_exchmaps_whichfork(xmi));
+
+ for (; xmi_has_more_exchange_work(xmi); xmi_advance(xmi, irec1)) {
+ /* Read mapping from the first file */
+ nimaps = 1;
+ error = xfs_bmapi_read(xmi->xmi_ip1, xmi->xmi_startoff1,
+ xmi->xmi_blockcount, irec1, &nimaps,
+ bmap_flags);
+ if (error)
+ return error;
+ if (nimaps != 1 ||
+ irec1->br_startblock == DELAYSTARTBLOCK ||
+ irec1->br_startoff != xmi->xmi_startoff1) {
+ /*
+ * We should never get no mapping or a delalloc mapping
+ * or something that doesn't match what we asked for,
+ * since the caller flushed both inodes and we hold the
+ * ILOCKs for both inodes.
+ */
+ ASSERT(0);
+ return -EINVAL;
+ }
+
+ if (xfs_exchmaps_can_skip_mapping(xmi, irec1)) {
+ trace_xfs_exchmaps_mapping1_skip(xmi->xmi_ip1, irec1);
+ continue;
+ }
+
+ /* Read mapping from the second file */
+ nimaps = 1;
+ error = xfs_bmapi_read(xmi->xmi_ip2, xmi->xmi_startoff2,
+ irec1->br_blockcount, irec2, &nimaps,
+ bmap_flags);
+ if (error)
+ return error;
+ if (nimaps != 1 ||
+ irec2->br_startblock == DELAYSTARTBLOCK ||
+ irec2->br_startoff != xmi->xmi_startoff2) {
+ /*
+ * We should never get no mapping or a delalloc mapping
+ * or something that doesn't match what we asked for,
+ * since the caller flushed both inodes and we hold the
+ * ILOCKs for both inodes.
+ */
+ ASSERT(0);
+ return -EINVAL;
+ }
+
+ /*
+ * We can only exchange as many blocks as the smaller of the
+ * two mapping maps.
+ */
+ irec1->br_blockcount = min(irec1->br_blockcount,
+ irec2->br_blockcount);
+
+ trace_xfs_exchmaps_mapping1(xmi->xmi_ip1, irec1);
+ trace_xfs_exchmaps_mapping2(xmi->xmi_ip2, irec2);
+
+ /* We found something to exchange, so return it. */
+ if (irec1->br_startblock != irec2->br_startblock)
+ return 0;
+
+ /*
+ * Two mappings pointing to the same physical block must not
+ * have different states; that's filesystem corruption. Move
+ * on to the next mapping if they're both holes or both point
+ * to the same physical space extent.
+ */
+ if (irec1->br_state != irec2->br_state) {
+ xfs_bmap_mark_sick(xmi->xmi_ip1,
+ xfs_exchmaps_whichfork(xmi));
+ xfs_bmap_mark_sick(xmi->xmi_ip2,
+ xfs_exchmaps_whichfork(xmi));
+ return -EFSCORRUPTED;
+ }
+
+ /*
+ * Save the mappings if we're estimating work and skipping
+ * these identical mappings.
+ */
+ if (adj) {
+ memcpy(&adj->left1, irec1, sizeof(*irec1));
+ memcpy(&adj->left2, irec2, sizeof(*irec2));
+ }
+ }
+
+ return 0;
+}
+
+/* Exchange these two mappings. */
+static void
+xfs_exchmaps_one_step(
+ struct xfs_trans *tp,
+ struct xfs_exchmaps_intent *xmi,
+ struct xfs_bmbt_irec *irec1,
+ struct xfs_bmbt_irec *irec2)
+{
+ int whichfork = xfs_exchmaps_whichfork(xmi);
+
+ xfs_exchmaps_update_quota(tp, xmi, irec1, irec2);
+
+ /* Remove both mappings. */
+ xfs_bmap_unmap_extent(tp, xmi->xmi_ip1, whichfork, irec1);
+ xfs_bmap_unmap_extent(tp, xmi->xmi_ip2, whichfork, irec2);
+
+ /*
+ * Re-add both mappings. We exchange the file offsets between the two
+ * maps and add the opposite map, which has the effect of filling the
+ * logical offsets we just unmapped, but with with the physical mapping
+ * information exchanged.
+ */
+ swap(irec1->br_startoff, irec2->br_startoff);
+ xfs_bmap_map_extent(tp, xmi->xmi_ip1, whichfork, irec2);
+ xfs_bmap_map_extent(tp, xmi->xmi_ip2, whichfork, irec1);
+
+ /* Make sure we're not adding mappings past EOF. */
+ if (whichfork == XFS_DATA_FORK) {
+ xfs_exchmaps_update_size(tp, xmi->xmi_ip1, irec2,
+ xmi->xmi_isize1);
+ xfs_exchmaps_update_size(tp, xmi->xmi_ip2, irec1,
+ xmi->xmi_isize2);
+ }
+
+ /*
+ * Advance our cursor and exit. The caller (either defer ops or log
+ * recovery) will log the XMD item, and if *blockcount is nonzero, it
+ * will log a new XMI item for the remainder and call us back.
+ */
+ xmi_advance(xmi, irec1);
+}
+
+/* Convert inode2's leaf attr fork back to shortform, if possible.. */
+STATIC int
+xfs_exchmaps_attr_to_sf(
+ struct xfs_trans *tp,
+ struct xfs_exchmaps_intent *xmi)
+{
+ struct xfs_da_args args = {
+ .dp = xmi->xmi_ip2,
+ .geo = tp->t_mountp->m_attr_geo,
+ .whichfork = XFS_ATTR_FORK,
+ .trans = tp,
+ .owner = xmi->xmi_ip2->i_ino,
+ };
+ struct xfs_buf *bp;
+ int forkoff;
+ int error;
+
+ if (!xfs_attr_is_leaf(xmi->xmi_ip2))
+ return 0;
+
+ error = xfs_attr3_leaf_read(tp, xmi->xmi_ip2, xmi->xmi_ip2->i_ino, 0,
+ &bp);
+ if (error)
+ return error;
+
+ forkoff = xfs_attr_shortform_allfit(bp, xmi->xmi_ip2);
+ if (forkoff == 0)
+ return 0;
+
+ return xfs_attr3_leaf_to_shortform(bp, &args, forkoff);
+}
+
+/* Convert inode2's block dir fork back to shortform, if possible.. */
+STATIC int
+xfs_exchmaps_dir_to_sf(
+ struct xfs_trans *tp,
+ struct xfs_exchmaps_intent *xmi)
+{
+ struct xfs_da_args args = {
+ .dp = xmi->xmi_ip2,
+ .geo = tp->t_mountp->m_dir_geo,
+ .whichfork = XFS_DATA_FORK,
+ .trans = tp,
+ .owner = xmi->xmi_ip2->i_ino,
+ };
+ struct xfs_dir2_sf_hdr sfh;
+ struct xfs_buf *bp;
+ int size;
+ int error = 0;
+
+ if (xfs_dir2_format(&args, &error) != XFS_DIR2_FMT_BLOCK)
+ return error;
+
+ error = xfs_dir3_block_read(tp, xmi->xmi_ip2, xmi->xmi_ip2->i_ino, &bp);
+ if (error)
+ return error;
+
+ size = xfs_dir2_block_sfsize(xmi->xmi_ip2, bp->b_addr, &sfh);
+ if (size > xfs_inode_data_fork_size(xmi->xmi_ip2))
+ return 0;
+
+ return xfs_dir2_block_to_sf(&args, bp, size, &sfh);
+}
+
+/* Convert inode2's remote symlink target back to shortform, if possible. */
+STATIC int
+xfs_exchmaps_link_to_sf(
+ struct xfs_trans *tp,
+ struct xfs_exchmaps_intent *xmi)
+{
+ struct xfs_inode *ip = xmi->xmi_ip2;
+ struct xfs_ifork *ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK);
+ char *buf;
+ int error;
+
+ if (ifp->if_format == XFS_DINODE_FMT_LOCAL ||
+ ip->i_disk_size > xfs_inode_data_fork_size(ip))
+ return 0;
+
+ /* Read the current symlink target into a buffer. */
+ buf = kmalloc(ip->i_disk_size + 1,
+ GFP_KERNEL | __GFP_NOLOCKDEP | __GFP_NOFAIL);
+ if (!buf) {
+ ASSERT(0);
+ return -ENOMEM;
+ }
+
+ error = xfs_symlink_remote_read(ip, buf);
+ if (error)
+ goto free;
+
+ /* Remove the blocks. */
+ error = xfs_symlink_remote_truncate(tp, ip);
+ if (error)
+ goto free;
+
+ /* Convert fork to local format and log our changes. */
+ xfs_idestroy_fork(ifp);
+ ifp->if_bytes = 0;
+ ifp->if_format = XFS_DINODE_FMT_LOCAL;
+ xfs_init_local_fork(ip, XFS_DATA_FORK, buf, ip->i_disk_size);
+ xfs_trans_log_inode(tp, ip, XFS_ILOG_DDATA | XFS_ILOG_CORE);
+free:
+ kfree(buf);
+ return error;
+}
+
+/* Clear the reflink flag after an exchange. */
+static inline void
+xfs_exchmaps_clear_reflink(
+ struct xfs_trans *tp,
+ struct xfs_inode *ip)
+{
+ trace_xfs_reflink_unset_inode_flag(ip);
+
+ ip->i_diflags2 &= ~XFS_DIFLAG2_REFLINK;
+ xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+}
+
+/* Finish whatever work might come after an exchange operation. */
+static int
+xfs_exchmaps_do_postop_work(
+ struct xfs_trans *tp,
+ struct xfs_exchmaps_intent *xmi)
+{
+ if (xmi->xmi_flags & __XFS_EXCHMAPS_INO2_SHORTFORM) {
+ int error = 0;
+
+ if (xmi->xmi_flags & XFS_EXCHMAPS_ATTR_FORK)
+ error = xfs_exchmaps_attr_to_sf(tp, xmi);
+ else if (S_ISDIR(VFS_I(xmi->xmi_ip2)->i_mode))
+ error = xfs_exchmaps_dir_to_sf(tp, xmi);
+ else if (S_ISLNK(VFS_I(xmi->xmi_ip2)->i_mode))
+ error = xfs_exchmaps_link_to_sf(tp, xmi);
+ xmi->xmi_flags &= ~__XFS_EXCHMAPS_INO2_SHORTFORM;
+ if (error)
+ return error;
+ }
+
+ if (xmi->xmi_flags & XFS_EXCHMAPS_CLEAR_INO1_REFLINK) {
+ xfs_exchmaps_clear_reflink(tp, xmi->xmi_ip1);
+ xmi->xmi_flags &= ~XFS_EXCHMAPS_CLEAR_INO1_REFLINK;
+ }
+
+ if (xmi->xmi_flags & XFS_EXCHMAPS_CLEAR_INO2_REFLINK) {
+ xfs_exchmaps_clear_reflink(tp, xmi->xmi_ip2);
+ xmi->xmi_flags &= ~XFS_EXCHMAPS_CLEAR_INO2_REFLINK;
+ }
+
+ return 0;
+}
+
+/* Finish one step in a mapping exchange operation, possibly relogging. */
+int
+xfs_exchmaps_finish_one(
+ struct xfs_trans *tp,
+ struct xfs_exchmaps_intent *xmi)
+{
+ struct xfs_bmbt_irec irec1, irec2;
+ int error;
+
+ if (xmi_has_more_exchange_work(xmi)) {
+ /*
+ * If the operation state says that some range of the files
+ * have not yet been exchanged, look for mappings in that range
+ * to exchange. If we find some mappings, exchange them.
+ */
+ error = xfs_exchmaps_find_mappings(xmi, &irec1, &irec2, NULL);
+ if (error)
+ return error;
+
+ if (xmi_has_more_exchange_work(xmi))
+ xfs_exchmaps_one_step(tp, xmi, &irec1, &irec2);
+
+ /*
+ * If the caller asked us to exchange the file sizes after the
+ * exchange and either we just exchanged the last mappings in
+ * the range or we didn't find anything to exchange, update the
+ * ondisk file sizes.
+ */
+ if ((xmi->xmi_flags & XFS_EXCHMAPS_SET_SIZES) &&
+ !xmi_has_more_exchange_work(xmi)) {
+ xmi->xmi_ip1->i_disk_size = xmi->xmi_isize1;
+ xmi->xmi_ip2->i_disk_size = xmi->xmi_isize2;
+
+ xfs_trans_log_inode(tp, xmi->xmi_ip1, XFS_ILOG_CORE);
+ xfs_trans_log_inode(tp, xmi->xmi_ip2, XFS_ILOG_CORE);
+ }
+ } else if (xmi_has_postop_work(xmi)) {
+ /*
+ * Now that we're finished with the exchange operation,
+ * complete the post-op cleanup work.
+ */
+ error = xfs_exchmaps_do_postop_work(tp, xmi);
+ if (error)
+ return error;
+ }
+
+ if (XFS_TEST_ERROR(false, tp->t_mountp, XFS_ERRTAG_EXCHMAPS_FINISH_ONE))
+ return -EIO;
+
+ /* If we still have work to do, ask for a new transaction. */
+ if (xmi_has_more_exchange_work(xmi) || xmi_has_postop_work(xmi)) {
+ trace_xfs_exchmaps_defer(tp->t_mountp, xmi);
+ return -EAGAIN;
+ }
+
+ /*
+ * If we reach here, we've finished all the exchange work and the post
+ * operation work. The last thing we need to do before returning to
+ * the caller is to make sure that COW forks are set up correctly.
+ */
+ if (!(xmi->xmi_flags & XFS_EXCHMAPS_ATTR_FORK)) {
+ xfs_exchmaps_ensure_cowfork(xmi->xmi_ip1);
+ xfs_exchmaps_ensure_cowfork(xmi->xmi_ip2);
+ }
+
+ return 0;
+}
+
+/*
+ * Compute the amount of bmbt blocks we should reserve for each file. In the
+ * worst case, each exchange will fill a hole with a new mapping, which could
+ * result in a btree split every time we add a new leaf block.
+ */
+static inline uint64_t
+xfs_exchmaps_bmbt_blocks(
+ struct xfs_mount *mp,
+ const struct xfs_exchmaps_req *req)
+{
+ return howmany_64(req->nr_exchanges,
+ XFS_MAX_CONTIG_BMAPS_PER_BLOCK(mp)) *
+ XFS_EXTENTADD_SPACE_RES(mp, xfs_exchmaps_reqfork(req));
+}
+
+/* Compute the space we should reserve for the rmap btree expansions. */
+static inline uint64_t
+xfs_exchmaps_rmapbt_blocks(
+ struct xfs_mount *mp,
+ const struct xfs_exchmaps_req *req)
+{
+ if (!xfs_has_rmapbt(mp))
+ return 0;
+ if (XFS_IS_REALTIME_INODE(req->ip1))
+ return 0;
+
+ return howmany_64(req->nr_exchanges,
+ XFS_MAX_CONTIG_RMAPS_PER_BLOCK(mp)) *
+ XFS_RMAPADD_SPACE_RES(mp);
+}
+
+/* Estimate the bmbt and rmapbt overhead required to exchange mappings. */
+int
+xfs_exchmaps_estimate_overhead(
+ struct xfs_exchmaps_req *req)
+{
+ struct xfs_mount *mp = req->ip1->i_mount;
+ xfs_filblks_t bmbt_blocks;
+ xfs_filblks_t rmapbt_blocks;
+ xfs_filblks_t resblks = req->resblks;
+
+ /*
+ * Compute the number of bmbt and rmapbt blocks we might need to handle
+ * the estimated number of exchanges.
+ */
+ bmbt_blocks = xfs_exchmaps_bmbt_blocks(mp, req);
+ rmapbt_blocks = xfs_exchmaps_rmapbt_blocks(mp, req);
+
+ trace_xfs_exchmaps_overhead(mp, bmbt_blocks, rmapbt_blocks);
+
+ /* Make sure the change in file block count doesn't overflow. */
+ if (check_add_overflow(req->ip1_bcount, bmbt_blocks, &req->ip1_bcount))
+ return -EFBIG;
+ if (check_add_overflow(req->ip2_bcount, bmbt_blocks, &req->ip2_bcount))
+ return -EFBIG;
+
+ /*
+ * Add together the number of blocks we need to handle btree growth,
+ * then add it to the number of blocks we need to reserve to this
+ * transaction.
+ */
+ if (check_add_overflow(resblks, bmbt_blocks, &resblks))
+ return -ENOSPC;
+ if (check_add_overflow(resblks, bmbt_blocks, &resblks))
+ return -ENOSPC;
+ if (check_add_overflow(resblks, rmapbt_blocks, &resblks))
+ return -ENOSPC;
+ if (check_add_overflow(resblks, rmapbt_blocks, &resblks))
+ return -ENOSPC;
+
+ /* Can't actually reserve more than UINT_MAX blocks. */
+ if (req->resblks > UINT_MAX)
+ return -ENOSPC;
+
+ req->resblks = resblks;
+ trace_xfs_exchmaps_final_estimate(req);
+ return 0;
+}
+
+/* Decide if we can merge two real mappings. */
+static inline bool
+xmi_can_merge(
+ const struct xfs_bmbt_irec *b1,
+ const struct xfs_bmbt_irec *b2)
+{
+ /* Don't merge holes. */
+ if (b1->br_startblock == HOLESTARTBLOCK ||
+ b2->br_startblock == HOLESTARTBLOCK)
+ return false;
+
+ /* We don't merge holes. */
+ if (!xfs_bmap_is_real_extent(b1) || !xfs_bmap_is_real_extent(b2))
+ return false;
+
+ if (b1->br_startoff + b1->br_blockcount == b2->br_startoff &&
+ b1->br_startblock + b1->br_blockcount == b2->br_startblock &&
+ b1->br_state == b2->br_state &&
+ b1->br_blockcount + b2->br_blockcount <= XFS_MAX_BMBT_EXTLEN)
+ return true;
+
+ return false;
+}
+
+/*
+ * Decide if we can merge three mappings. Caller must ensure all three
+ * mappings must not be holes or delalloc reservations.
+ */
+static inline bool
+xmi_can_merge_all(
+ const struct xfs_bmbt_irec *l,
+ const struct xfs_bmbt_irec *m,
+ const struct xfs_bmbt_irec *r)
+{
+ xfs_filblks_t new_len;
+
+ new_len = l->br_blockcount + m->br_blockcount + r->br_blockcount;
+ return new_len <= XFS_MAX_BMBT_EXTLEN;
+}
+
+#define CLEFT_CONTIG 0x01
+#define CRIGHT_CONTIG 0x02
+#define CHOLE 0x04
+#define CBOTH_CONTIG (CLEFT_CONTIG | CRIGHT_CONTIG)
+
+#define NLEFT_CONTIG 0x10
+#define NRIGHT_CONTIG 0x20
+#define NHOLE 0x40
+#define NBOTH_CONTIG (NLEFT_CONTIG | NRIGHT_CONTIG)
+
+/* Estimate the effect of a single exchange on mapping count. */
+static inline int
+xmi_delta_nextents_step(
+ struct xfs_mount *mp,
+ const struct xfs_bmbt_irec *left,
+ const struct xfs_bmbt_irec *curr,
+ const struct xfs_bmbt_irec *new,
+ const struct xfs_bmbt_irec *right)
+{
+ bool lhole, rhole, chole, nhole;
+ unsigned int state = 0;
+ int ret = 0;
+
+ lhole = left->br_startblock == HOLESTARTBLOCK;
+ rhole = right->br_startblock == HOLESTARTBLOCK;
+ chole = curr->br_startblock == HOLESTARTBLOCK;
+ nhole = new->br_startblock == HOLESTARTBLOCK;
+
+ if (chole)
+ state |= CHOLE;
+ if (!lhole && !chole && xmi_can_merge(left, curr))
+ state |= CLEFT_CONTIG;
+ if (!rhole && !chole && xmi_can_merge(curr, right))
+ state |= CRIGHT_CONTIG;
+ if ((state & CBOTH_CONTIG) == CBOTH_CONTIG &&
+ !xmi_can_merge_all(left, curr, right))
+ state &= ~CRIGHT_CONTIG;
+
+ if (nhole)
+ state |= NHOLE;
+ if (!lhole && !nhole && xmi_can_merge(left, new))
+ state |= NLEFT_CONTIG;
+ if (!rhole && !nhole && xmi_can_merge(new, right))
+ state |= NRIGHT_CONTIG;
+ if ((state & NBOTH_CONTIG) == NBOTH_CONTIG &&
+ !xmi_can_merge_all(left, new, right))
+ state &= ~NRIGHT_CONTIG;
+
+ switch (state & (CLEFT_CONTIG | CRIGHT_CONTIG | CHOLE)) {
+ case CLEFT_CONTIG | CRIGHT_CONTIG:
+ /*
+ * left/curr/right are the same mapping, so deleting curr
+ * causes 2 new mappings to be created.
+ */
+ ret += 2;
+ break;
+ case 0:
+ /*
+ * curr is not contiguous with any mapping, so we remove curr
+ * completely
+ */
+ ret--;
+ break;
+ case CHOLE:
+ /* hole, do nothing */
+ break;
+ case CLEFT_CONTIG:
+ case CRIGHT_CONTIG:
+ /* trim either left or right, no change */
+ break;
+ }
+
+ switch (state & (NLEFT_CONTIG | NRIGHT_CONTIG | NHOLE)) {
+ case NLEFT_CONTIG | NRIGHT_CONTIG:
+ /*
+ * left/curr/right will become the same mapping, so adding
+ * curr causes the deletion of right.
+ */
+ ret--;
+ break;
+ case 0:
+ /* new is not contiguous with any mapping */
+ ret++;
+ break;
+ case NHOLE:
+ /* hole, do nothing. */
+ break;
+ case NLEFT_CONTIG:
+ case NRIGHT_CONTIG:
+ /* new is absorbed into left or right, no change */
+ break;
+ }
+
+ trace_xfs_exchmaps_delta_nextents_step(mp, left, curr, new, right, ret,
+ state);
+ return ret;
+}
+
+/* Make sure we don't overflow the extent (mapping) counters. */
+static inline int
+xmi_ensure_delta_nextents(
+ struct xfs_exchmaps_req *req,
+ struct xfs_inode *ip,
+ int64_t delta)
+{
+ struct xfs_mount *mp = ip->i_mount;
+ int whichfork = xfs_exchmaps_reqfork(req);
+ struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork);
+ uint64_t new_nextents;
+ xfs_extnum_t max_nextents;
+
+ if (delta < 0)
+ return 0;
+
+ /*
+ * It's always an error if the delta causes integer overflow. delta
+ * needs an explicit cast here to avoid warnings about implicit casts
+ * coded into the overflow check.
+ */
+ if (check_add_overflow(ifp->if_nextents, (uint64_t)delta,
+ &new_nextents))
+ return -EFBIG;
+
+ if (XFS_TEST_ERROR(false, mp, XFS_ERRTAG_REDUCE_MAX_IEXTENTS) &&
+ new_nextents > 10)
+ return -EFBIG;
+
+ /*
+ * We always promote both inodes to have large extent counts if the
+ * superblock feature is enabled, so we only need to check against the
+ * theoretical maximum.
+ */
+ max_nextents = xfs_iext_max_nextents(xfs_has_large_extent_counts(mp),
+ whichfork);
+ if (new_nextents > max_nextents)
+ return -EFBIG;
+
+ return 0;
+}
+
+/* Find the next mapping after irec. */
+static inline int
+xmi_next(
+ struct xfs_inode *ip,
+ int bmap_flags,
+ const struct xfs_bmbt_irec *irec,
+ struct xfs_bmbt_irec *nrec)
+{
+ xfs_fileoff_t off;
+ xfs_filblks_t blockcount;
+ int nimaps = 1;
+ int error;
+
+ off = irec->br_startoff + irec->br_blockcount;
+ blockcount = XFS_MAX_FILEOFF - off;
+ error = xfs_bmapi_read(ip, off, blockcount, nrec, &nimaps, bmap_flags);
+ if (error)
+ return error;
+ if (nrec->br_startblock == DELAYSTARTBLOCK ||
+ nrec->br_startoff != off) {
+ /*
+ * If we don't get the mapping we want, return a zero-length
+ * mapping, which our estimator function will pretend is a hole.
+ * We shouldn't get delalloc reservations.
+ */
+ nrec->br_startblock = HOLESTARTBLOCK;
+ }
+
+ return 0;
+}
+
+int __init
+xfs_exchmaps_intent_init_cache(void)
+{
+ xfs_exchmaps_intent_cache = kmem_cache_create("xfs_exchmaps_intent",
+ sizeof(struct xfs_exchmaps_intent),
+ 0, 0, NULL);
+
+ return xfs_exchmaps_intent_cache != NULL ? 0 : -ENOMEM;
+}
+
+void
+xfs_exchmaps_intent_destroy_cache(void)
+{
+ kmem_cache_destroy(xfs_exchmaps_intent_cache);
+ xfs_exchmaps_intent_cache = NULL;
+}
+
+/*
+ * Decide if we will exchange the reflink flags between the two files after the
+ * exchange. The only time we want to do this is if we're exchanging all
+ * mappings under EOF and the inode reflink flags have different states.
+ */
+static inline bool
+xmi_can_exchange_reflink_flags(
+ const struct xfs_exchmaps_req *req,
+ unsigned int reflink_state)
+{
+ struct xfs_mount *mp = req->ip1->i_mount;
+
+ if (hweight32(reflink_state) != 1)
+ return false;
+ if (req->startoff1 != 0 || req->startoff2 != 0)
+ return false;
+ if (req->blockcount != XFS_B_TO_FSB(mp, req->ip1->i_disk_size))
+ return false;
+ if (req->blockcount != XFS_B_TO_FSB(mp, req->ip2->i_disk_size))
+ return false;
+ return true;
+}
+
+
+/* Allocate and initialize a new incore intent item from a request. */
+struct xfs_exchmaps_intent *
+xfs_exchmaps_init_intent(
+ const struct xfs_exchmaps_req *req)
+{
+ struct xfs_exchmaps_intent *xmi;
+ unsigned int rs = 0;
+
+ xmi = kmem_cache_zalloc(xfs_exchmaps_intent_cache,
+ GFP_NOFS | __GFP_NOFAIL);
+ INIT_LIST_HEAD(&xmi->xmi_list);
+ xmi->xmi_ip1 = req->ip1;
+ xmi->xmi_ip2 = req->ip2;
+ xmi->xmi_startoff1 = req->startoff1;
+ xmi->xmi_startoff2 = req->startoff2;
+ xmi->xmi_blockcount = req->blockcount;
+ xmi->xmi_isize1 = xmi->xmi_isize2 = -1;
+ xmi->xmi_flags = req->flags & XFS_EXCHMAPS_PARAMS;
+
+ if (xfs_exchmaps_whichfork(xmi) == XFS_ATTR_FORK) {
+ xmi->xmi_flags |= __XFS_EXCHMAPS_INO2_SHORTFORM;
+ return xmi;
+ }
+
+ if (req->flags & XFS_EXCHMAPS_SET_SIZES) {
+ xmi->xmi_flags |= XFS_EXCHMAPS_SET_SIZES;
+ xmi->xmi_isize1 = req->ip2->i_disk_size;
+ xmi->xmi_isize2 = req->ip1->i_disk_size;
+ }
+
+ /* Record the state of each inode's reflink flag before the op. */
+ if (xfs_is_reflink_inode(req->ip1))
+ rs |= 1;
+ if (xfs_is_reflink_inode(req->ip2))
+ rs |= 2;
+
+ /*
+ * Figure out if we're clearing the reflink flags (which effectively
+ * exchanges them) after the operation.
+ */
+ if (xmi_can_exchange_reflink_flags(req, rs)) {
+ if (rs & 1)
+ xmi->xmi_flags |= XFS_EXCHMAPS_CLEAR_INO1_REFLINK;
+ if (rs & 2)
+ xmi->xmi_flags |= XFS_EXCHMAPS_CLEAR_INO2_REFLINK;
+ }
+
+ if (S_ISDIR(VFS_I(xmi->xmi_ip2)->i_mode) ||
+ S_ISLNK(VFS_I(xmi->xmi_ip2)->i_mode))
+ xmi->xmi_flags |= __XFS_EXCHMAPS_INO2_SHORTFORM;
+
+ return xmi;
+}
+
+/*
+ * Estimate the number of exchange operations and the number of file blocks
+ * in each file that will be affected by the exchange operation.
+ */
+int
+xfs_exchmaps_estimate(
+ struct xfs_exchmaps_req *req)
+{
+ struct xfs_exchmaps_intent *xmi;
+ struct xfs_bmbt_irec irec1, irec2;
+ struct xfs_exchmaps_adjacent adj = ADJACENT_INIT;
+ xfs_filblks_t ip1_blocks = 0, ip2_blocks = 0;
+ int64_t d_nexts1, d_nexts2;
+ int bmap_flags;
+ int error;
+
+ ASSERT(!(req->flags & ~XFS_EXCHMAPS_PARAMS));
+
+ bmap_flags = xfs_bmapi_aflag(xfs_exchmaps_reqfork(req));
+ xmi = xfs_exchmaps_init_intent(req);
+
+ /*
+ * To guard against the possibility of overflowing the extent counters,
+ * we have to estimate an upper bound on the potential increase in that
+ * counter. We can split the mapping at each end of the range, and for
+ * each step of the exchange we can split the mapping that we're
+ * working on if the mappings do not align.
+ */
+ d_nexts1 = d_nexts2 = 3;
+
+ while (xmi_has_more_exchange_work(xmi)) {
+ /*
+ * Walk through the file ranges until we find something to
+ * exchange. Because we're simulating the exchange, pass in
+ * adj to capture skipped mappings for correct estimation of
+ * bmbt record merges.
+ */
+ error = xfs_exchmaps_find_mappings(xmi, &irec1, &irec2, &adj);
+ if (error)
+ goto out_free;
+ if (!xmi_has_more_exchange_work(xmi))
+ break;
+
+ /* Update accounting. */
+ if (xfs_bmap_is_real_extent(&irec1))
+ ip1_blocks += irec1.br_blockcount;
+ if (xfs_bmap_is_real_extent(&irec2))
+ ip2_blocks += irec2.br_blockcount;
+ req->nr_exchanges++;
+
+ /* Read the next mappings from both files. */
+ error = xmi_next(req->ip1, bmap_flags, &irec1, &adj.right1);
+ if (error)
+ goto out_free;
+
+ error = xmi_next(req->ip2, bmap_flags, &irec2, &adj.right2);
+ if (error)
+ goto out_free;
+
+ /* Update extent count deltas. */
+ d_nexts1 += xmi_delta_nextents_step(req->ip1->i_mount,
+ &adj.left1, &irec1, &irec2, &adj.right1);
+
+ d_nexts2 += xmi_delta_nextents_step(req->ip1->i_mount,
+ &adj.left2, &irec2, &irec1, &adj.right2);
+
+ /* Now pretend we exchanged the mappings. */
+ if (xmi_can_merge(&adj.left2, &irec1))
+ adj.left2.br_blockcount += irec1.br_blockcount;
+ else
+ memcpy(&adj.left2, &irec1, sizeof(irec1));
+
+ if (xmi_can_merge(&adj.left1, &irec2))
+ adj.left1.br_blockcount += irec2.br_blockcount;
+ else
+ memcpy(&adj.left1, &irec2, sizeof(irec2));
+
+ xmi_advance(xmi, &irec1);
+ }
+
+ /* Account for the blocks that are being exchanged. */
+ if (XFS_IS_REALTIME_INODE(req->ip1) &&
+ xfs_exchmaps_reqfork(req) == XFS_DATA_FORK) {
+ req->ip1_rtbcount = ip1_blocks;
+ req->ip2_rtbcount = ip2_blocks;
+ } else {
+ req->ip1_bcount = ip1_blocks;
+ req->ip2_bcount = ip2_blocks;
+ }
+
+ /*
+ * Make sure that both forks have enough slack left in their extent
+ * counters that the exchange operation will not overflow.
+ */
+ trace_xfs_exchmaps_delta_nextents(req, d_nexts1, d_nexts2);
+ if (req->ip1 == req->ip2) {
+ error = xmi_ensure_delta_nextents(req, req->ip1,
+ d_nexts1 + d_nexts2);
+ } else {
+ error = xmi_ensure_delta_nextents(req, req->ip1, d_nexts1);
+ if (error)
+ goto out_free;
+ error = xmi_ensure_delta_nextents(req, req->ip2, d_nexts2);
+ }
+ if (error)
+ goto out_free;
+
+ trace_xfs_exchmaps_initial_estimate(req);
+ error = xfs_exchmaps_estimate_overhead(req);
+out_free:
+ kmem_cache_free(xfs_exchmaps_intent_cache, xmi);
+ return error;
+}
+
+/* Set the reflink flag before an operation. */
+static inline void
+xfs_exchmaps_set_reflink(
+ struct xfs_trans *tp,
+ struct xfs_inode *ip)
+{
+ trace_xfs_reflink_set_inode_flag(ip);
+
+ ip->i_diflags2 |= XFS_DIFLAG2_REFLINK;
+ xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+}
+
+/*
+ * If either file has shared blocks and we're exchanging data forks, we must
+ * flag the other file as having shared blocks so that we get the shared-block
+ * rmap functions if we need to fix up the rmaps.
+ */
+void
+xfs_exchmaps_ensure_reflink(
+ struct xfs_trans *tp,
+ const struct xfs_exchmaps_intent *xmi)
+{
+ unsigned int rs = 0;
+
+ if (xfs_is_reflink_inode(xmi->xmi_ip1))
+ rs |= 1;
+ if (xfs_is_reflink_inode(xmi->xmi_ip2))
+ rs |= 2;
+
+ if ((rs & 1) && !xfs_is_reflink_inode(xmi->xmi_ip2))
+ xfs_exchmaps_set_reflink(tp, xmi->xmi_ip2);
+
+ if ((rs & 2) && !xfs_is_reflink_inode(xmi->xmi_ip1))
+ xfs_exchmaps_set_reflink(tp, xmi->xmi_ip1);
+}
+
+/* Set the large extent count flag before an operation if needed. */
+static inline void
+xfs_exchmaps_ensure_large_extent_counts(
+ struct xfs_trans *tp,
+ struct xfs_inode *ip)
+{
+ if (xfs_inode_has_large_extent_counts(ip))
+ return;
+
+ ip->i_diflags2 |= XFS_DIFLAG2_NREXT64;
+ xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+}
+
+/* Widen the extent counter fields of both inodes if necessary. */
+void
+xfs_exchmaps_upgrade_extent_counts(
+ struct xfs_trans *tp,
+ const struct xfs_exchmaps_intent *xmi)
+{
+ if (!xfs_has_large_extent_counts(tp->t_mountp))
+ return;
+
+ xfs_exchmaps_ensure_large_extent_counts(tp, xmi->xmi_ip1);
+ xfs_exchmaps_ensure_large_extent_counts(tp, xmi->xmi_ip2);
+}
+
+/*
+ * Schedule an exchange a range of mappings from one inode to another.
+ *
+ * The use of file mapping exchange log intent items ensures the operation can
+ * be resumed even if the system goes down. The caller must commit the
+ * transaction to start the work.
+ *
+ * The caller must ensure the inodes must be joined to the transaction and
+ * ILOCKd; they will still be joined to the transaction at exit.
+ */
+void
+xfs_exchange_mappings(
+ struct xfs_trans *tp,
+ const struct xfs_exchmaps_req *req)
+{
+ struct xfs_exchmaps_intent *xmi;
+
+ BUILD_BUG_ON(XFS_EXCHMAPS_INTERNAL_FLAGS & XFS_EXCHMAPS_LOGGED_FLAGS);
+
+ xfs_assert_ilocked(req->ip1, XFS_ILOCK_EXCL);
+ xfs_assert_ilocked(req->ip2, XFS_ILOCK_EXCL);
+ ASSERT(!(req->flags & ~XFS_EXCHMAPS_LOGGED_FLAGS));
+ if (req->flags & XFS_EXCHMAPS_SET_SIZES)
+ ASSERT(!(req->flags & XFS_EXCHMAPS_ATTR_FORK));
+ ASSERT(xfs_has_exchange_range(tp->t_mountp));
+
+ if (req->blockcount == 0)
+ return;
+
+ xmi = xfs_exchmaps_init_intent(req);
+ xfs_exchmaps_defer_add(tp, xmi);
+ xfs_exchmaps_ensure_reflink(tp, xmi);
+ xfs_exchmaps_upgrade_extent_counts(tp, xmi);
+}
diff --git a/fs/xfs/libxfs/xfs_exchmaps.h b/fs/xfs/libxfs/xfs_exchmaps.h
new file mode 100644
index 0000000000..fa822dff20
--- /dev/null
+++ b/fs/xfs/libxfs/xfs_exchmaps.h
@@ -0,0 +1,124 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (c) 2020-2024 Oracle. All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#ifndef __XFS_EXCHMAPS_H__
+#define __XFS_EXCHMAPS_H__
+
+/* In-core deferred operation info about a file mapping exchange request. */
+struct xfs_exchmaps_intent {
+ /* List of other incore deferred work. */
+ struct list_head xmi_list;
+
+ /* Inodes participating in the operation. */
+ struct xfs_inode *xmi_ip1;
+ struct xfs_inode *xmi_ip2;
+
+ /* File offset range information. */
+ xfs_fileoff_t xmi_startoff1;
+ xfs_fileoff_t xmi_startoff2;
+ xfs_filblks_t xmi_blockcount;
+
+ /* Set these file sizes after the operation, unless negative. */
+ xfs_fsize_t xmi_isize1;
+ xfs_fsize_t xmi_isize2;
+
+ uint64_t xmi_flags; /* XFS_EXCHMAPS_* flags */
+};
+
+/* Try to convert inode2 from block to short format at the end, if possible. */
+#define __XFS_EXCHMAPS_INO2_SHORTFORM (1ULL << 63)
+
+#define XFS_EXCHMAPS_INTERNAL_FLAGS (__XFS_EXCHMAPS_INO2_SHORTFORM)
+
+/* flags that can be passed to xfs_exchmaps_{estimate,mappings} */
+#define XFS_EXCHMAPS_PARAMS (XFS_EXCHMAPS_ATTR_FORK | \
+ XFS_EXCHMAPS_SET_SIZES | \
+ XFS_EXCHMAPS_INO1_WRITTEN)
+
+static inline int
+xfs_exchmaps_whichfork(const struct xfs_exchmaps_intent *xmi)
+{
+ if (xmi->xmi_flags & XFS_EXCHMAPS_ATTR_FORK)
+ return XFS_ATTR_FORK;
+ return XFS_DATA_FORK;
+}
+
+/* Parameters for a mapping exchange request. */
+struct xfs_exchmaps_req {
+ /* Inodes participating in the operation. */
+ struct xfs_inode *ip1;
+ struct xfs_inode *ip2;
+
+ /* File offset range information. */
+ xfs_fileoff_t startoff1;
+ xfs_fileoff_t startoff2;
+ xfs_filblks_t blockcount;
+
+ /* XFS_EXCHMAPS_* operation flags */
+ uint64_t flags;
+
+ /*
+ * Fields below this line are filled out by xfs_exchmaps_estimate;
+ * callers should initialize this part of the struct to zero.
+ */
+
+ /*
+ * Data device blocks to be moved out of ip1, and free space needed to
+ * handle the bmbt changes.
+ */
+ xfs_filblks_t ip1_bcount;
+
+ /*
+ * Data device blocks to be moved out of ip2, and free space needed to
+ * handle the bmbt changes.
+ */
+ xfs_filblks_t ip2_bcount;
+
+ /* rt blocks to be moved out of ip1. */
+ xfs_filblks_t ip1_rtbcount;
+
+ /* rt blocks to be moved out of ip2. */
+ xfs_filblks_t ip2_rtbcount;
+
+ /* Free space needed to handle the bmbt changes */
+ unsigned long long resblks;
+
+ /* Number of exchanges needed to complete the operation */
+ unsigned long long nr_exchanges;
+};
+
+static inline int
+xfs_exchmaps_reqfork(const struct xfs_exchmaps_req *req)
+{
+ if (req->flags & XFS_EXCHMAPS_ATTR_FORK)
+ return XFS_ATTR_FORK;
+ return XFS_DATA_FORK;
+}
+
+int xfs_exchmaps_estimate_overhead(struct xfs_exchmaps_req *req);
+int xfs_exchmaps_estimate(struct xfs_exchmaps_req *req);
+
+extern struct kmem_cache *xfs_exchmaps_intent_cache;
+
+int __init xfs_exchmaps_intent_init_cache(void);
+void xfs_exchmaps_intent_destroy_cache(void);
+
+struct xfs_exchmaps_intent *xfs_exchmaps_init_intent(
+ const struct xfs_exchmaps_req *req);
+void xfs_exchmaps_ensure_reflink(struct xfs_trans *tp,
+ const struct xfs_exchmaps_intent *xmi);
+void xfs_exchmaps_upgrade_extent_counts(struct xfs_trans *tp,
+ const struct xfs_exchmaps_intent *xmi);
+
+int xfs_exchmaps_finish_one(struct xfs_trans *tp,
+ struct xfs_exchmaps_intent *xmi);
+
+int xfs_exchmaps_check_forks(struct xfs_mount *mp,
+ const struct xfs_exchmaps_req *req);
+
+void xfs_exchange_mappings(struct xfs_trans *tp,
+ const struct xfs_exchmaps_req *req);
+
+#endif /* __XFS_EXCHMAPS_H__ */
diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h
index 2b2f9050fb..61f51becff 100644
--- a/fs/xfs/libxfs/xfs_format.h
+++ b/fs/xfs/libxfs/xfs_format.h
@@ -367,19 +367,23 @@ xfs_sb_has_ro_compat_feature(
return (sbp->sb_features_ro_compat & feature) != 0;
}
-#define XFS_SB_FEAT_INCOMPAT_FTYPE (1 << 0) /* filetype in dirent */
-#define XFS_SB_FEAT_INCOMPAT_SPINODES (1 << 1) /* sparse inode chunks */
-#define XFS_SB_FEAT_INCOMPAT_META_UUID (1 << 2) /* metadata UUID */
-#define XFS_SB_FEAT_INCOMPAT_BIGTIME (1 << 3) /* large timestamps */
-#define XFS_SB_FEAT_INCOMPAT_NEEDSREPAIR (1 << 4) /* needs xfs_repair */
-#define XFS_SB_FEAT_INCOMPAT_NREXT64 (1 << 5) /* large extent counters */
+#define XFS_SB_FEAT_INCOMPAT_FTYPE (1 << 0) /* filetype in dirent */
+#define XFS_SB_FEAT_INCOMPAT_SPINODES (1 << 1) /* sparse inode chunks */
+#define XFS_SB_FEAT_INCOMPAT_META_UUID (1 << 2) /* metadata UUID */
+#define XFS_SB_FEAT_INCOMPAT_BIGTIME (1 << 3) /* large timestamps */
+#define XFS_SB_FEAT_INCOMPAT_NEEDSREPAIR (1 << 4) /* needs xfs_repair */
+#define XFS_SB_FEAT_INCOMPAT_NREXT64 (1 << 5) /* large extent counters */
+#define XFS_SB_FEAT_INCOMPAT_EXCHRANGE (1 << 6) /* exchangerange supported */
+#define XFS_SB_FEAT_INCOMPAT_PARENT (1 << 7) /* parent pointers */
#define XFS_SB_FEAT_INCOMPAT_ALL \
- (XFS_SB_FEAT_INCOMPAT_FTYPE| \
- XFS_SB_FEAT_INCOMPAT_SPINODES| \
- XFS_SB_FEAT_INCOMPAT_META_UUID| \
- XFS_SB_FEAT_INCOMPAT_BIGTIME| \
- XFS_SB_FEAT_INCOMPAT_NEEDSREPAIR| \
- XFS_SB_FEAT_INCOMPAT_NREXT64)
+ (XFS_SB_FEAT_INCOMPAT_FTYPE | \
+ XFS_SB_FEAT_INCOMPAT_SPINODES | \
+ XFS_SB_FEAT_INCOMPAT_META_UUID | \
+ XFS_SB_FEAT_INCOMPAT_BIGTIME | \
+ XFS_SB_FEAT_INCOMPAT_NEEDSREPAIR | \
+ XFS_SB_FEAT_INCOMPAT_NREXT64 | \
+ XFS_SB_FEAT_INCOMPAT_EXCHRANGE | \
+ XFS_SB_FEAT_INCOMPAT_PARENT)
#define XFS_SB_FEAT_INCOMPAT_UNKNOWN ~XFS_SB_FEAT_INCOMPAT_ALL
static inline bool
@@ -898,6 +902,12 @@ static inline uint xfs_dinode_size(int version)
#define XFS_MAXLINK ((1U << 31) - 1U)
/*
+ * Any file that hits the maximum ondisk link count should be pinned to avoid
+ * a use-after-free situation.
+ */
+#define XFS_NLINK_PINNED (~0U)
+
+/*
* Values for di_format
*
* This enum is used in string mapping in xfs_trace.h; please keep the
diff --git a/fs/xfs/libxfs/xfs_fs.h b/fs/xfs/libxfs/xfs_fs.h
index ca1b17d014..454b63ef72 100644
--- a/fs/xfs/libxfs/xfs_fs.h
+++ b/fs/xfs/libxfs/xfs_fs.h
@@ -239,6 +239,8 @@ typedef struct xfs_fsop_resblks {
#define XFS_FSOP_GEOM_FLAGS_BIGTIME (1 << 21) /* 64-bit nsec timestamps */
#define XFS_FSOP_GEOM_FLAGS_INOBTCNT (1 << 22) /* inobt btree counter */
#define XFS_FSOP_GEOM_FLAGS_NREXT64 (1 << 23) /* large extent counters */
+#define XFS_FSOP_GEOM_FLAGS_EXCHANGE_RANGE (1 << 24) /* exchange range */
+#define XFS_FSOP_GEOM_FLAGS_PARENT (1 << 25) /* linux parent pointers */
/*
* Minimum and maximum sizes need for growth checks.
@@ -409,6 +411,7 @@ struct xfs_bulkstat {
#define XFS_BS_SICK_XATTR (1 << 5) /* extended attributes */
#define XFS_BS_SICK_SYMLINK (1 << 6) /* symbolic link remote target */
#define XFS_BS_SICK_PARENT (1 << 7) /* parent pointers */
+#define XFS_BS_SICK_DIRTREE (1 << 8) /* directory tree structure */
/*
* Project quota id helpers (previously projid was 16bit only
@@ -632,7 +635,9 @@ typedef struct xfs_fsop_attrmulti_handlereq {
/*
* per machine unique filesystem identifier types.
*/
-typedef struct { __u32 val[2]; } xfs_fsid_t; /* file system id type */
+typedef struct xfs_fsid {
+ __u32 val[2]; /* file system id type */
+} xfs_fsid_t;
typedef struct xfs_fid {
__u16 fid_len; /* length of remainder */
@@ -715,9 +720,19 @@ struct xfs_scrub_metadata {
#define XFS_SCRUB_TYPE_QUOTACHECK 25 /* quota counters */
#define XFS_SCRUB_TYPE_NLINKS 26 /* inode link counts */
#define XFS_SCRUB_TYPE_HEALTHY 27 /* everything checked out ok */
+#define XFS_SCRUB_TYPE_DIRTREE 28 /* directory tree structure */
/* Number of scrub subcommands. */
-#define XFS_SCRUB_TYPE_NR 28
+#define XFS_SCRUB_TYPE_NR 29
+
+/*
+ * This special type code only applies to the vectored scrub implementation.
+ *
+ * If any of the previous scrub vectors recorded runtime errors or have
+ * sv_flags bits set that match the OFLAG bits in the barrier vector's
+ * sv_flags, set the barrier's sv_ret to -ECANCELED and return to userspace.
+ */
+#define XFS_SCRUB_TYPE_BARRIER (0xFFFFFFFF)
/* i: Repair this metadata. */
#define XFS_SCRUB_IFLAG_REPAIR (1u << 0)
@@ -763,6 +778,29 @@ struct xfs_scrub_metadata {
XFS_SCRUB_OFLAG_NO_REPAIR_NEEDED)
#define XFS_SCRUB_FLAGS_ALL (XFS_SCRUB_FLAGS_IN | XFS_SCRUB_FLAGS_OUT)
+/* Vectored scrub calls to reduce the number of kernel transitions. */
+
+struct xfs_scrub_vec {
+ __u32 sv_type; /* XFS_SCRUB_TYPE_* */
+ __u32 sv_flags; /* XFS_SCRUB_FLAGS_* */
+ __s32 sv_ret; /* 0 or a negative error code */
+ __u32 sv_reserved; /* must be zero */
+};
+
+/* Vectored metadata scrub control structure. */
+struct xfs_scrub_vec_head {
+ __u64 svh_ino; /* inode number. */
+ __u32 svh_gen; /* inode generation. */
+ __u32 svh_agno; /* ag number. */
+ __u32 svh_flags; /* XFS_SCRUB_VEC_FLAGS_* */
+ __u16 svh_rest_us; /* wait this much time between vector items */
+ __u16 svh_nr; /* number of svh_vectors */
+ __u64 svh_reserved; /* must be zero */
+ __u64 svh_vectors; /* pointer to buffer of xfs_scrub_vec */
+};
+
+#define XFS_SCRUB_VEC_FLAGS_ALL (0)
+
/*
* ioctl limits
*/
@@ -772,6 +810,118 @@ struct xfs_scrub_metadata {
# define XFS_XATTR_LIST_MAX 65536
#endif
+/*
+ * Exchange part of file1 with part of the file that this ioctl that is being
+ * called against (which we'll call file2). Filesystems must be able to
+ * restart and complete the operation even after the system goes down.
+ */
+struct xfs_exchange_range {
+ __s32 file1_fd;
+ __u32 pad; /* must be zeroes */
+ __u64 file1_offset; /* file1 offset, bytes */
+ __u64 file2_offset; /* file2 offset, bytes */
+ __u64 length; /* bytes to exchange */
+
+ __u64 flags; /* see XFS_EXCHANGE_RANGE_* below */
+};
+
+/*
+ * Exchange file data all the way to the ends of both files, and then exchange
+ * the file sizes. This flag can be used to replace a file's contents with a
+ * different amount of data. length will be ignored.
+ */
+#define XFS_EXCHANGE_RANGE_TO_EOF (1ULL << 0)
+
+/* Flush all changes in file data and file metadata to disk before returning. */
+#define XFS_EXCHANGE_RANGE_DSYNC (1ULL << 1)
+
+/* Dry run; do all the parameter verification but do not change anything. */
+#define XFS_EXCHANGE_RANGE_DRY_RUN (1ULL << 2)
+
+/*
+ * Exchange only the parts of the two files where the file allocation units
+ * mapped to file1's range have been written to. This can accelerate
+ * scatter-gather atomic writes with a temp file if all writes are aligned to
+ * the file allocation unit.
+ */
+#define XFS_EXCHANGE_RANGE_FILE1_WRITTEN (1ULL << 3)
+
+#define XFS_EXCHANGE_RANGE_ALL_FLAGS (XFS_EXCHANGE_RANGE_TO_EOF | \
+ XFS_EXCHANGE_RANGE_DSYNC | \
+ XFS_EXCHANGE_RANGE_DRY_RUN | \
+ XFS_EXCHANGE_RANGE_FILE1_WRITTEN)
+
+/* Iterating parent pointers of files. */
+
+/* target was the root directory */
+#define XFS_GETPARENTS_OFLAG_ROOT (1U << 0)
+
+/* Cursor is done iterating pptrs */
+#define XFS_GETPARENTS_OFLAG_DONE (1U << 1)
+
+#define XFS_GETPARENTS_OFLAGS_ALL (XFS_GETPARENTS_OFLAG_ROOT | \
+ XFS_GETPARENTS_OFLAG_DONE)
+
+#define XFS_GETPARENTS_IFLAGS_ALL (0)
+
+struct xfs_getparents_rec {
+ struct xfs_handle gpr_parent; /* Handle to parent */
+ __u32 gpr_reclen; /* Length of entire record */
+ __u32 gpr_reserved; /* zero */
+ char gpr_name[]; /* Null-terminated filename */
+};
+
+/* Iterate through this file's directory parent pointers */
+struct xfs_getparents {
+ /*
+ * Structure to track progress in iterating the parent pointers.
+ * Must be initialized to zeroes before the first ioctl call, and
+ * not touched by callers after that.
+ */
+ struct xfs_attrlist_cursor gp_cursor;
+
+ /* Input flags: XFS_GETPARENTS_IFLAG* */
+ __u16 gp_iflags;
+
+ /* Output flags: XFS_GETPARENTS_OFLAG* */
+ __u16 gp_oflags;
+
+ /* Size of the gp_buffer in bytes */
+ __u32 gp_bufsize;
+
+ /* Must be set to zero */
+ __u64 gp_reserved;
+
+ /* Pointer to a buffer in which to place xfs_getparents_rec */
+ __u64 gp_buffer;
+};
+
+static inline struct xfs_getparents_rec *
+xfs_getparents_first_rec(struct xfs_getparents *gp)
+{
+ return (struct xfs_getparents_rec *)(uintptr_t)gp->gp_buffer;
+}
+
+static inline struct xfs_getparents_rec *
+xfs_getparents_next_rec(struct xfs_getparents *gp,
+ struct xfs_getparents_rec *gpr)
+{
+ void *next = ((void *)gpr + gpr->gpr_reclen);
+ void *end = (void *)(uintptr_t)(gp->gp_buffer + gp->gp_bufsize);
+
+ if (next >= end)
+ return NULL;
+
+ return next;
+}
+
+/* Iterate through this file handle's directory parent pointers. */
+struct xfs_getparents_by_handle {
+ /* Handle to file whose parents we want. */
+ struct xfs_handle gph_handle;
+
+ struct xfs_getparents gph_request;
+};
/*
* ioctl commands that are used by Linux filesystems
@@ -808,6 +958,9 @@ struct xfs_scrub_metadata {
/* XFS_IOC_GETFSMAP ------ hoisted 59 */
#define XFS_IOC_SCRUB_METADATA _IOWR('X', 60, struct xfs_scrub_metadata)
#define XFS_IOC_AG_GEOMETRY _IOWR('X', 61, struct xfs_ag_geometry)
+#define XFS_IOC_GETPARENTS _IOWR('X', 62, struct xfs_getparents)
+#define XFS_IOC_GETPARENTS_BY_HANDLE _IOWR('X', 63, struct xfs_getparents_by_handle)
+#define XFS_IOC_SCRUBV_METADATA _IOWR('X', 64, struct xfs_scrub_vec_head)
/*
* ioctl commands that replace IRIX syssgi()'s
@@ -843,6 +996,7 @@ struct xfs_scrub_metadata {
#define XFS_IOC_FSGEOMETRY _IOR ('X', 126, struct xfs_fsop_geom)
#define XFS_IOC_BULKSTAT _IOR ('X', 127, struct xfs_bulkstat_req)
#define XFS_IOC_INUMBERS _IOR ('X', 128, struct xfs_inumbers_req)
+#define XFS_IOC_EXCHANGE_RANGE _IOW ('X', 129, struct xfs_exchange_range)
/* XFS_IOC_GETFSUUID ---------- deprecated 140 */
diff --git a/fs/xfs/libxfs/xfs_health.h b/fs/xfs/libxfs/xfs_health.h
index 3c64b5f9bd..b0edb4288e 100644
--- a/fs/xfs/libxfs/xfs_health.h
+++ b/fs/xfs/libxfs/xfs_health.h
@@ -95,6 +95,7 @@ struct xfs_da_args;
/* Don't propagate sick status to ag health summary during inactivation */
#define XFS_SICK_INO_FORGET (1 << 12)
+#define XFS_SICK_INO_DIRTREE (1 << 13) /* directory tree structure */
/* Primary evidence of health problems in a given group. */
#define XFS_SICK_FS_PRIMARY (XFS_SICK_FS_COUNTERS | \
@@ -125,7 +126,8 @@ struct xfs_da_args;
XFS_SICK_INO_DIR | \
XFS_SICK_INO_XATTR | \
XFS_SICK_INO_SYMLINK | \
- XFS_SICK_INO_PARENT)
+ XFS_SICK_INO_PARENT | \
+ XFS_SICK_INO_DIRTREE)
#define XFS_SICK_INO_ZAPPED (XFS_SICK_INO_BMBTD_ZAPPED | \
XFS_SICK_INO_BMBTA_ZAPPED | \
diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
index e5ac3e5430..14c81f227c 100644
--- a/fs/xfs/libxfs/xfs_ialloc.c
+++ b/fs/xfs/libxfs/xfs_ialloc.c
@@ -1058,6 +1058,33 @@ xfs_inobt_first_free_inode(
}
/*
+ * If this AG has corrupt inodes, check if allocating this inode would fail
+ * with corruption errors. Returns 0 if we're clear, or EAGAIN to try again
+ * somewhere else.
+ */
+static int
+xfs_dialloc_check_ino(
+ struct xfs_perag *pag,
+ struct xfs_trans *tp,
+ xfs_ino_t ino)
+{
+ struct xfs_imap imap;
+ struct xfs_buf *bp;
+ int error;
+
+ error = xfs_imap(pag, tp, ino, &imap, 0);
+ if (error)
+ return -EAGAIN;
+
+ error = xfs_imap_to_bp(pag->pag_mount, tp, &imap, &bp);
+ if (error)
+ return -EAGAIN;
+
+ xfs_trans_brelse(tp, bp);
+ return 0;
+}
+
+/*
* Allocate an inode using the inobt-only algorithm.
*/
STATIC int
@@ -1309,6 +1336,13 @@ alloc_inode:
ASSERT((XFS_AGINO_TO_OFFSET(mp, rec.ir_startino) %
XFS_INODES_PER_CHUNK) == 0);
ino = XFS_AGINO_TO_INO(mp, pag->pag_agno, rec.ir_startino + offset);
+
+ if (xfs_ag_has_sickness(pag, XFS_SICK_AG_INODES)) {
+ error = xfs_dialloc_check_ino(pag, tp, ino);
+ if (error)
+ goto error0;
+ }
+
rec.ir_free &= ~XFS_INOBT_MASK(offset);
rec.ir_freecount--;
error = xfs_inobt_update(cur, &rec);
@@ -1584,6 +1618,12 @@ xfs_dialloc_ag(
XFS_INODES_PER_CHUNK) == 0);
ino = XFS_AGINO_TO_INO(mp, pag->pag_agno, rec.ir_startino + offset);
+ if (xfs_ag_has_sickness(pag, XFS_SICK_AG_INODES)) {
+ error = xfs_dialloc_check_ino(pag, tp, ino);
+ if (error)
+ goto error_cur;
+ }
+
/*
* Modify or remove the finobt record.
*/
@@ -1699,7 +1739,7 @@ xfs_dialloc_good_ag(
return false;
if (!xfs_perag_initialised_agi(pag)) {
- error = xfs_ialloc_read_agi(pag, tp, NULL);
+ error = xfs_ialloc_read_agi(pag, tp, 0, NULL);
if (error)
return false;
}
@@ -1768,7 +1808,7 @@ xfs_dialloc_try_ag(
* Then read in the AGI buffer and recheck with the AGI buffer
* lock held.
*/
- error = xfs_ialloc_read_agi(pag, *tpp, &agbp);
+ error = xfs_ialloc_read_agi(pag, *tpp, 0, &agbp);
if (error)
return error;
@@ -2286,7 +2326,7 @@ xfs_difree(
/*
* Get the allocation group header.
*/
- error = xfs_ialloc_read_agi(pag, tp, &agbp);
+ error = xfs_ialloc_read_agi(pag, tp, 0, &agbp);
if (error) {
xfs_warn(mp, "%s: xfs_ialloc_read_agi() returned error %d.",
__func__, error);
@@ -2332,7 +2372,7 @@ xfs_imap_lookup(
int error;
int i;
- error = xfs_ialloc_read_agi(pag, tp, &agbp);
+ error = xfs_ialloc_read_agi(pag, tp, 0, &agbp);
if (error) {
xfs_alert(mp,
"%s: xfs_ialloc_read_agi() returned error %d, agno %d",
@@ -2675,6 +2715,7 @@ int
xfs_read_agi(
struct xfs_perag *pag,
struct xfs_trans *tp,
+ xfs_buf_flags_t flags,
struct xfs_buf **agibpp)
{
struct xfs_mount *mp = pag->pag_mount;
@@ -2684,7 +2725,7 @@ xfs_read_agi(
error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp,
XFS_AG_DADDR(mp, pag->pag_agno, XFS_AGI_DADDR(mp)),
- XFS_FSS_TO_BB(mp, 1), 0, agibpp, &xfs_agi_buf_ops);
+ XFS_FSS_TO_BB(mp, 1), flags, agibpp, &xfs_agi_buf_ops);
if (xfs_metadata_is_sick(error))
xfs_ag_mark_sick(pag, XFS_SICK_AG_AGI);
if (error)
@@ -2704,6 +2745,7 @@ int
xfs_ialloc_read_agi(
struct xfs_perag *pag,
struct xfs_trans *tp,
+ int flags,
struct xfs_buf **agibpp)
{
struct xfs_buf *agibp;
@@ -2712,7 +2754,9 @@ xfs_ialloc_read_agi(
trace_xfs_ialloc_read_agi(pag->pag_mount, pag->pag_agno);
- error = xfs_read_agi(pag, tp, &agibp);
+ error = xfs_read_agi(pag, tp,
+ (flags & XFS_IALLOC_FLAG_TRYLOCK) ? XBF_TRYLOCK : 0,
+ &agibp);
if (error)
return error;
diff --git a/fs/xfs/libxfs/xfs_ialloc.h b/fs/xfs/libxfs/xfs_ialloc.h
index f1412183bb..b549627e3a 100644
--- a/fs/xfs/libxfs/xfs_ialloc.h
+++ b/fs/xfs/libxfs/xfs_ialloc.h
@@ -63,10 +63,11 @@ xfs_ialloc_log_agi(
struct xfs_buf *bp, /* allocation group header buffer */
uint32_t fields); /* bitmask of fields to log */
-int xfs_read_agi(struct xfs_perag *pag, struct xfs_trans *tp,
+int xfs_read_agi(struct xfs_perag *pag, struct xfs_trans *tp, xfs_buf_flags_t flags,
struct xfs_buf **agibpp);
int xfs_ialloc_read_agi(struct xfs_perag *pag, struct xfs_trans *tp,
- struct xfs_buf **agibpp);
+ int flags, struct xfs_buf **agibpp);
+#define XFS_IALLOC_FLAG_TRYLOCK (1U << 0) /* use trylock for buffer locking */
/*
* Lookup a record by ino in the btree given by cur.
diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c
index cc661fca6f..42e9fd47f6 100644
--- a/fs/xfs/libxfs/xfs_ialloc_btree.c
+++ b/fs/xfs/libxfs/xfs_ialloc_btree.c
@@ -745,7 +745,7 @@ xfs_finobt_count_blocks(
struct xfs_btree_cur *cur;
int error;
- error = xfs_ialloc_read_agi(pag, tp, &agbp);
+ error = xfs_ialloc_read_agi(pag, tp, 0, &agbp);
if (error)
return error;
@@ -768,7 +768,7 @@ xfs_finobt_read_blocks(
struct xfs_agi *agi;
int error;
- error = xfs_ialloc_read_agi(pag, tp, &agbp);
+ error = xfs_ialloc_read_agi(pag, tp, 0, &agbp);
if (error)
return error;
diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c
index d0dcce462b..513b50da62 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.c
+++ b/fs/xfs/libxfs/xfs_inode_buf.c
@@ -374,17 +374,40 @@ xfs_dinode_verify_fork(
/*
* For fork types that can contain local data, check that the fork
* format matches the size of local data contained within the fork.
- *
- * For all types, check that when the size says the should be in extent
- * or btree format, the inode isn't claiming it is in local format.
*/
if (whichfork == XFS_DATA_FORK) {
- if (S_ISDIR(mode) || S_ISLNK(mode)) {
+ /*
+ * A directory small enough to fit in the inode must be stored
+ * in local format. The directory sf <-> extents conversion
+ * code updates the directory size accordingly. Directories
+ * being truncated have zero size and are not subject to this
+ * check.
+ */
+ if (S_ISDIR(mode)) {
+ if (dip->di_size &&
+ be64_to_cpu(dip->di_size) <= fork_size &&
+ fork_format != XFS_DINODE_FMT_LOCAL)
+ return __this_address;
+ }
+
+ /*
+ * A symlink with a target small enough to fit in the inode can
+ * be stored in extents format if xattrs were added (thus
+ * converting the data fork from shortform to remote format)
+ * and then removed.
+ */
+ if (S_ISLNK(mode)) {
if (be64_to_cpu(dip->di_size) <= fork_size &&
+ fork_format != XFS_DINODE_FMT_EXTENTS &&
fork_format != XFS_DINODE_FMT_LOCAL)
return __this_address;
}
+ /*
+ * For all types, check that when the size says the fork should
+ * be in extent or btree format, the inode isn't claiming to be
+ * in local format.
+ */
if (be64_to_cpu(dip->di_size) > fork_size &&
fork_format == XFS_DINODE_FMT_LOCAL)
return __this_address;
@@ -491,6 +514,14 @@ xfs_dinode_verify(
return __this_address;
}
+ if (dip->di_version > 1) {
+ if (dip->di_onlink)
+ return __this_address;
+ } else {
+ if (dip->di_nlink)
+ return __this_address;
+ }
+
/* don't allow invalid i_size */
di_size = be64_to_cpu(dip->di_size);
if (di_size & (1ULL << 63))
@@ -500,9 +531,19 @@ xfs_dinode_verify(
if (mode && xfs_mode_to_ftype(mode) == XFS_DIR3_FT_UNKNOWN)
return __this_address;
- /* No zero-length symlinks/dirs. */
- if ((S_ISLNK(mode) || S_ISDIR(mode)) && di_size == 0)
- return __this_address;
+ /*
+ * No zero-length symlinks/dirs unless they're unlinked and hence being
+ * inactivated.
+ */
+ if ((S_ISLNK(mode) || S_ISDIR(mode)) && di_size == 0) {
+ if (dip->di_version > 1) {
+ if (dip->di_nlink)
+ return __this_address;
+ } else {
+ if (dip->di_onlink)
+ return __this_address;
+ }
+ }
fa = xfs_dinode_verify_nrext64(mp, dip);
if (fa)
diff --git a/fs/xfs/libxfs/xfs_inode_fork.c b/fs/xfs/libxfs/xfs_inode_fork.c
index 7d660a9739..9d11ae0159 100644
--- a/fs/xfs/libxfs/xfs_inode_fork.c
+++ b/fs/xfs/libxfs/xfs_inode_fork.c
@@ -765,53 +765,46 @@ xfs_ifork_verify_local_attr(
return 0;
}
+/*
+ * Check if the inode fork supports adding nr_to_add more extents.
+ *
+ * If it doesn't but we can upgrade it to large extent counters, do the upgrade.
+ * If we can't upgrade or are already using big counters but still can't fit the
+ * additional extents, return -EFBIG.
+ */
int
-xfs_iext_count_may_overflow(
+xfs_iext_count_extend(
+ struct xfs_trans *tp,
struct xfs_inode *ip,
int whichfork,
- int nr_to_add)
+ uint nr_to_add)
{
+ struct xfs_mount *mp = ip->i_mount;
+ bool has_large =
+ xfs_inode_has_large_extent_counts(ip);
struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork);
- uint64_t max_exts;
uint64_t nr_exts;
+ ASSERT(nr_to_add <= XFS_MAX_EXTCNT_UPGRADE_NR);
+
if (whichfork == XFS_COW_FORK)
return 0;
- max_exts = xfs_iext_max_nextents(xfs_inode_has_large_extent_counts(ip),
- whichfork);
-
- if (XFS_TEST_ERROR(false, ip->i_mount, XFS_ERRTAG_REDUCE_MAX_IEXTENTS))
- max_exts = 10;
-
+ /* no point in upgrading if if_nextents overflows */
nr_exts = ifp->if_nextents + nr_to_add;
- if (nr_exts < ifp->if_nextents || nr_exts > max_exts)
+ if (nr_exts < ifp->if_nextents)
return -EFBIG;
- return 0;
-}
-
-/*
- * Upgrade this inode's extent counter fields to be able to handle a potential
- * increase in the extent count by nr_to_add. Normally this is the same
- * quantity that caused xfs_iext_count_may_overflow() to return -EFBIG.
- */
-int
-xfs_iext_count_upgrade(
- struct xfs_trans *tp,
- struct xfs_inode *ip,
- uint nr_to_add)
-{
- ASSERT(nr_to_add <= XFS_MAX_EXTCNT_UPGRADE_NR);
-
- if (!xfs_has_large_extent_counts(ip->i_mount) ||
- xfs_inode_has_large_extent_counts(ip) ||
- XFS_TEST_ERROR(false, ip->i_mount, XFS_ERRTAG_REDUCE_MAX_IEXTENTS))
+ if (XFS_TEST_ERROR(false, mp, XFS_ERRTAG_REDUCE_MAX_IEXTENTS) &&
+ nr_exts > 10)
return -EFBIG;
- ip->i_diflags2 |= XFS_DIFLAG2_NREXT64;
- xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
-
+ if (nr_exts > xfs_iext_max_nextents(has_large, whichfork)) {
+ if (has_large || !xfs_has_large_extent_counts(mp))
+ return -EFBIG;
+ ip->i_diflags2 |= XFS_DIFLAG2_NREXT64;
+ xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+ }
return 0;
}
diff --git a/fs/xfs/libxfs/xfs_inode_fork.h b/fs/xfs/libxfs/xfs_inode_fork.h
index bd53eb951b..2373d12fd4 100644
--- a/fs/xfs/libxfs/xfs_inode_fork.h
+++ b/fs/xfs/libxfs/xfs_inode_fork.h
@@ -256,10 +256,8 @@ extern void xfs_ifork_init_cow(struct xfs_inode *ip);
int xfs_ifork_verify_local_data(struct xfs_inode *ip);
int xfs_ifork_verify_local_attr(struct xfs_inode *ip);
-int xfs_iext_count_may_overflow(struct xfs_inode *ip, int whichfork,
- int nr_to_add);
-int xfs_iext_count_upgrade(struct xfs_trans *tp, struct xfs_inode *ip,
- uint nr_to_add);
+int xfs_iext_count_extend(struct xfs_trans *tp, struct xfs_inode *ip,
+ int whichfork, uint nr_to_add);
bool xfs_ifork_is_realtime(struct xfs_inode *ip, int whichfork);
/* returns true if the fork has extents but they are not read in yet. */
diff --git a/fs/xfs/libxfs/xfs_log_format.h b/fs/xfs/libxfs/xfs_log_format.h
index 16872972e1..3e6682ed65 100644
--- a/fs/xfs/libxfs/xfs_log_format.h
+++ b/fs/xfs/libxfs/xfs_log_format.h
@@ -115,10 +115,13 @@ struct xfs_unmount_log_format {
#define XLOG_REG_TYPE_BUD_FORMAT 26
#define XLOG_REG_TYPE_ATTRI_FORMAT 27
#define XLOG_REG_TYPE_ATTRD_FORMAT 28
-#define XLOG_REG_TYPE_ATTR_NAME 29
+#define XLOG_REG_TYPE_ATTR_NAME 29
#define XLOG_REG_TYPE_ATTR_VALUE 30
-#define XLOG_REG_TYPE_MAX 30
-
+#define XLOG_REG_TYPE_XMI_FORMAT 31
+#define XLOG_REG_TYPE_XMD_FORMAT 32
+#define XLOG_REG_TYPE_ATTR_NEWNAME 33
+#define XLOG_REG_TYPE_ATTR_NEWVALUE 34
+#define XLOG_REG_TYPE_MAX 34
/*
* Flags to log operation header
@@ -243,6 +246,8 @@ typedef struct xfs_trans_header {
#define XFS_LI_BUD 0x1245
#define XFS_LI_ATTRI 0x1246 /* attr set/remove intent*/
#define XFS_LI_ATTRD 0x1247 /* attr set/remove done */
+#define XFS_LI_XMI 0x1248 /* mapping exchange intent */
+#define XFS_LI_XMD 0x1249 /* mapping exchange done */
#define XFS_LI_TYPE_DESC \
{ XFS_LI_EFI, "XFS_LI_EFI" }, \
@@ -260,7 +265,9 @@ typedef struct xfs_trans_header {
{ XFS_LI_BUI, "XFS_LI_BUI" }, \
{ XFS_LI_BUD, "XFS_LI_BUD" }, \
{ XFS_LI_ATTRI, "XFS_LI_ATTRI" }, \
- { XFS_LI_ATTRD, "XFS_LI_ATTRD" }
+ { XFS_LI_ATTRD, "XFS_LI_ATTRD" }, \
+ { XFS_LI_XMI, "XFS_LI_XMI" }, \
+ { XFS_LI_XMD, "XFS_LI_XMD" }
/*
* Inode Log Item Format definitions.
@@ -879,6 +886,61 @@ struct xfs_bud_log_format {
};
/*
+ * XMI/XMD (file mapping exchange) log format definitions
+ */
+
+/* This is the structure used to lay out an mapping exchange log item. */
+struct xfs_xmi_log_format {
+ uint16_t xmi_type; /* xmi log item type */
+ uint16_t xmi_size; /* size of this item */
+ uint32_t __pad; /* must be zero */
+ uint64_t xmi_id; /* xmi identifier */
+
+ uint64_t xmi_inode1; /* inumber of first file */
+ uint64_t xmi_inode2; /* inumber of second file */
+ uint32_t xmi_igen1; /* generation of first file */
+ uint32_t xmi_igen2; /* generation of second file */
+ uint64_t xmi_startoff1; /* block offset into file1 */
+ uint64_t xmi_startoff2; /* block offset into file2 */
+ uint64_t xmi_blockcount; /* number of blocks */
+ uint64_t xmi_flags; /* XFS_EXCHMAPS_* */
+ uint64_t xmi_isize1; /* intended file1 size */
+ uint64_t xmi_isize2; /* intended file2 size */
+};
+
+/* Exchange mappings between extended attribute forks instead of data forks. */
+#define XFS_EXCHMAPS_ATTR_FORK (1ULL << 0)
+
+/* Set the file sizes when finished. */
+#define XFS_EXCHMAPS_SET_SIZES (1ULL << 1)
+
+/*
+ * Exchange the mappings of the two files only if the file allocation units
+ * mapped to file1's range have been written.
+ */
+#define XFS_EXCHMAPS_INO1_WRITTEN (1ULL << 2)
+
+/* Clear the reflink flag from inode1 after the operation. */
+#define XFS_EXCHMAPS_CLEAR_INO1_REFLINK (1ULL << 3)
+
+/* Clear the reflink flag from inode2 after the operation. */
+#define XFS_EXCHMAPS_CLEAR_INO2_REFLINK (1ULL << 4)
+
+#define XFS_EXCHMAPS_LOGGED_FLAGS (XFS_EXCHMAPS_ATTR_FORK | \
+ XFS_EXCHMAPS_SET_SIZES | \
+ XFS_EXCHMAPS_INO1_WRITTEN | \
+ XFS_EXCHMAPS_CLEAR_INO1_REFLINK | \
+ XFS_EXCHMAPS_CLEAR_INO2_REFLINK)
+
+/* This is the structure used to lay out an mapping exchange done log item. */
+struct xfs_xmd_log_format {
+ uint16_t xmd_type; /* xmd log item type */
+ uint16_t xmd_size; /* size of this item */
+ uint32_t __pad;
+ uint64_t xmd_xmi_id; /* id of corresponding xmi */
+};
+
+/*
* Dquot Log format definitions.
*
* The first two fields must be the type and size fitting into
@@ -966,6 +1028,9 @@ struct xfs_icreate_log {
#define XFS_ATTRI_OP_FLAGS_SET 1 /* Set the attribute */
#define XFS_ATTRI_OP_FLAGS_REMOVE 2 /* Remove the attribute */
#define XFS_ATTRI_OP_FLAGS_REPLACE 3 /* Replace the attribute */
+#define XFS_ATTRI_OP_FLAGS_PPTR_SET 4 /* Set parent pointer */
+#define XFS_ATTRI_OP_FLAGS_PPTR_REMOVE 5 /* Remove parent pointer */
+#define XFS_ATTRI_OP_FLAGS_PPTR_REPLACE 6 /* Replace parent pointer */
#define XFS_ATTRI_OP_FLAGS_TYPE_MASK 0xFF /* Flags type mask */
/*
@@ -974,6 +1039,7 @@ struct xfs_icreate_log {
*/
#define XFS_ATTRI_FILTER_MASK (XFS_ATTR_ROOT | \
XFS_ATTR_SECURE | \
+ XFS_ATTR_PARENT | \
XFS_ATTR_INCOMPLETE)
/*
@@ -983,11 +1049,22 @@ struct xfs_icreate_log {
struct xfs_attri_log_format {
uint16_t alfi_type; /* attri log item type */
uint16_t alfi_size; /* size of this item */
- uint32_t __pad; /* pad to 64 bit aligned */
+ uint32_t alfi_igen; /* generation of alfi_ino for pptr ops */
uint64_t alfi_id; /* attri identifier */
uint64_t alfi_ino; /* the inode for this attr operation */
uint32_t alfi_op_flags; /* marks the op as a set or remove */
- uint32_t alfi_name_len; /* attr name length */
+ union {
+ uint32_t alfi_name_len; /* attr name length */
+ struct {
+ /*
+ * For PPTR_REPLACE, these are the lengths of the old
+ * and new attr names. The new and old values must
+ * have the same length.
+ */
+ uint16_t alfi_old_name_len;
+ uint16_t alfi_new_name_len;
+ };
+ };
uint32_t alfi_value_len; /* attr value length */
uint32_t alfi_attr_filter;/* attr filter flags */
};
diff --git a/fs/xfs/libxfs/xfs_log_recover.h b/fs/xfs/libxfs/xfs_log_recover.h
index 9fe7a9564b..521d327e4c 100644
--- a/fs/xfs/libxfs/xfs_log_recover.h
+++ b/fs/xfs/libxfs/xfs_log_recover.h
@@ -75,6 +75,8 @@ extern const struct xlog_recover_item_ops xlog_cui_item_ops;
extern const struct xlog_recover_item_ops xlog_cud_item_ops;
extern const struct xlog_recover_item_ops xlog_attri_item_ops;
extern const struct xlog_recover_item_ops xlog_attrd_item_ops;
+extern const struct xlog_recover_item_ops xlog_xmi_item_ops;
+extern const struct xlog_recover_item_ops xlog_xmd_item_ops;
/*
* Macros, structures, prototypes for internal log manager use.
@@ -121,6 +123,8 @@ bool xlog_is_buffer_cancelled(struct xlog *log, xfs_daddr_t blkno, uint len);
int xlog_recover_iget(struct xfs_mount *mp, xfs_ino_t ino,
struct xfs_inode **ipp);
+int xlog_recover_iget_handle(struct xfs_mount *mp, xfs_ino_t ino, uint32_t gen,
+ struct xfs_inode **ipp);
void xlog_recover_release_intent(struct xlog *log, unsigned short intent_type,
uint64_t intent_id);
int xlog_alloc_buf_cancel_table(struct xlog *log);
diff --git a/fs/xfs/libxfs/xfs_log_rlimit.c b/fs/xfs/libxfs/xfs_log_rlimit.c
index 9975b93a74..d3bd6a86c8 100644
--- a/fs/xfs/libxfs/xfs_log_rlimit.c
+++ b/fs/xfs/libxfs/xfs_log_rlimit.c
@@ -17,6 +17,34 @@
#include "xfs_trace.h"
/*
+ * Shortly after enabling the large extents count feature in 2023, longstanding
+ * bugs were found in the code that computes the minimum log size. Luckily,
+ * the bugs resulted in over-estimates of that size, so there's no impact to
+ * existing users. However, we don't want to reduce the minimum log size
+ * because that can create the situation where a newer mkfs writes a new
+ * filesystem that an older kernel won't mount.
+ *
+ * Several years prior, we also discovered that the transaction reservations
+ * for rmap and reflink operations were unnecessarily large. That was fixed,
+ * but the minimum log size computation was left alone to avoid the
+ * compatibility problems noted above. Fix that too.
+ *
+ * Therefore, we only may correct the computation starting with filesystem
+ * features that didn't exist in 2023. In other words, only turn this on if
+ * the filesystem has parent pointers.
+ *
+ * This function can be called before the XFS_HAS_* flags have been set up,
+ * (e.g. mkfs) so we must check the ondisk superblock.
+ */
+static inline bool
+xfs_want_minlogsize_fixes(
+ struct xfs_sb *sb)
+{
+ return xfs_sb_is_v5(sb) &&
+ xfs_sb_has_incompat_feature(sb, XFS_SB_FEAT_INCOMPAT_PARENT);
+}
+
+/*
* Calculate the maximum length in bytes that would be required for a local
* attribute value as large attributes out of line are not logged.
*/
@@ -31,6 +59,15 @@ xfs_log_calc_max_attrsetm_res(
MAXNAMELEN - 1;
nblks = XFS_DAENTER_SPACE_RES(mp, XFS_ATTR_FORK);
nblks += XFS_B_TO_FSB(mp, size);
+
+ /*
+ * If the feature set is new enough, correct a unit conversion error in
+ * the xattr transaction reservation code that resulted in oversized
+ * minimum log size computations.
+ */
+ if (xfs_want_minlogsize_fixes(&mp->m_sb))
+ size = XFS_B_TO_FSB(mp, size);
+
nblks += XFS_NEXTENTADD_SPACE_RES(mp, size, XFS_ATTR_FORK);
return M_RES(mp)->tr_attrsetm.tr_logres +
@@ -49,6 +86,15 @@ xfs_log_calc_trans_resv_for_minlogblocks(
unsigned int rmap_maxlevels = mp->m_rmap_maxlevels;
/*
+ * If the feature set is new enough, drop the oversized minimum log
+ * size computation introduced by the original reflink code.
+ */
+ if (xfs_want_minlogsize_fixes(&mp->m_sb)) {
+ xfs_trans_resv_calc(mp, resv);
+ return;
+ }
+
+ /*
* In the early days of rmap+reflink, we always set the rmap maxlevels
* to 9 even if the AG was small enough that it would never grow to
* that height. Transaction reservation sizes influence the minimum
diff --git a/fs/xfs/libxfs/xfs_ondisk.h b/fs/xfs/libxfs/xfs_ondisk.h
index 81885a6a02..e8cdd77d03 100644
--- a/fs/xfs/libxfs/xfs_ondisk.h
+++ b/fs/xfs/libxfs/xfs_ondisk.h
@@ -119,6 +119,7 @@ xfs_check_ondisk_structs(void)
XFS_CHECK_OFFSET(xfs_dir2_sf_entry_t, offset, 1);
XFS_CHECK_OFFSET(xfs_dir2_sf_entry_t, name, 3);
XFS_CHECK_STRUCT_SIZE(xfs_dir2_sf_hdr_t, 10);
+ XFS_CHECK_STRUCT_SIZE(struct xfs_parent_rec, 12);
/* log structures */
XFS_CHECK_STRUCT_SIZE(struct xfs_buf_log_format, 88);
@@ -155,6 +156,11 @@ xfs_check_ondisk_structs(void)
XFS_CHECK_OFFSET(struct xfs_efi_log_format_32, efi_extents, 16);
XFS_CHECK_OFFSET(struct xfs_efi_log_format_64, efi_extents, 16);
+ /* parent pointer ioctls */
+ XFS_CHECK_STRUCT_SIZE(struct xfs_getparents_rec, 32);
+ XFS_CHECK_STRUCT_SIZE(struct xfs_getparents, 40);
+ XFS_CHECK_STRUCT_SIZE(struct xfs_getparents_by_handle, 64);
+
/*
* The v5 superblock format extended several v4 header structures with
* additional data. While new fields are only accessible on v5
diff --git a/fs/xfs/libxfs/xfs_parent.c b/fs/xfs/libxfs/xfs_parent.c
new file mode 100644
index 0000000000..69366c44a7
--- /dev/null
+++ b/fs/xfs/libxfs/xfs_parent.c
@@ -0,0 +1,379 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2022-2024 Oracle.
+ * All rights reserved.
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_format.h"
+#include "xfs_da_format.h"
+#include "xfs_log_format.h"
+#include "xfs_shared.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_bmap_btree.h"
+#include "xfs_inode.h"
+#include "xfs_error.h"
+#include "xfs_trace.h"
+#include "xfs_trans.h"
+#include "xfs_da_btree.h"
+#include "xfs_attr.h"
+#include "xfs_dir2.h"
+#include "xfs_dir2_priv.h"
+#include "xfs_attr_sf.h"
+#include "xfs_bmap.h"
+#include "xfs_defer.h"
+#include "xfs_log.h"
+#include "xfs_xattr.h"
+#include "xfs_parent.h"
+#include "xfs_trans_space.h"
+#include "xfs_attr_item.h"
+#include "xfs_health.h"
+
+struct kmem_cache *xfs_parent_args_cache;
+
+/*
+ * Parent pointer attribute handling.
+ *
+ * Because the attribute name is a filename component, it will never be longer
+ * than 255 bytes and must not contain nulls or slashes. These are roughly the
+ * same constraints that apply to attribute names.
+ *
+ * The attribute value must always be a struct xfs_parent_rec. This means the
+ * attribute will never be in remote format because 12 bytes is nowhere near
+ * xfs_attr_leaf_entsize_local_max() (~75% of block size).
+ *
+ * Creating a new parent attribute will always create a new attribute - there
+ * should never, ever be an existing attribute in the tree for a new inode.
+ * ENOSPC behavior is problematic - creating the inode without the parent
+ * pointer is effectively a corruption, so we allow parent attribute creation
+ * to dip into the reserve block pool to avoid unexpected ENOSPC errors from
+ * occurring.
+ */
+
+/* Return true if parent pointer attr name is valid. */
+bool
+xfs_parent_namecheck(
+ unsigned int attr_flags,
+ const void *name,
+ size_t length)
+{
+ /*
+ * Parent pointers always use logged operations, so there should never
+ * be incomplete xattrs.
+ */
+ if (attr_flags & XFS_ATTR_INCOMPLETE)
+ return false;
+
+ return xfs_dir2_namecheck(name, length);
+}
+
+/* Return true if parent pointer attr value is valid. */
+bool
+xfs_parent_valuecheck(
+ struct xfs_mount *mp,
+ const void *value,
+ size_t valuelen)
+{
+ const struct xfs_parent_rec *rec = value;
+
+ if (!xfs_has_parent(mp))
+ return false;
+
+ /* The xattr value must be a parent record. */
+ if (valuelen != sizeof(struct xfs_parent_rec))
+ return false;
+
+ /* The parent record must be local. */
+ if (value == NULL)
+ return false;
+
+ /* The parent inumber must be valid. */
+ if (!xfs_verify_dir_ino(mp, be64_to_cpu(rec->p_ino)))
+ return false;
+
+ return true;
+}
+
+/* Compute the attribute name hash for a parent pointer. */
+xfs_dahash_t
+xfs_parent_hashval(
+ struct xfs_mount *mp,
+ const uint8_t *name,
+ int namelen,
+ xfs_ino_t parent_ino)
+{
+ struct xfs_name xname = {
+ .name = name,
+ .len = namelen,
+ };
+
+ /*
+ * Use the same dirent name hash as would be used on the directory, but
+ * mix in the parent inode number to avoid collisions on hardlinked
+ * files with identical names but different parents.
+ */
+ return xfs_dir2_hashname(mp, &xname) ^
+ upper_32_bits(parent_ino) ^ lower_32_bits(parent_ino);
+}
+
+/* Compute the attribute name hash from the xattr components. */
+xfs_dahash_t
+xfs_parent_hashattr(
+ struct xfs_mount *mp,
+ const uint8_t *name,
+ int namelen,
+ const void *value,
+ int valuelen)
+{
+ const struct xfs_parent_rec *rec = value;
+
+ /* Requires a local attr value in xfs_parent_rec format */
+ if (valuelen != sizeof(struct xfs_parent_rec)) {
+ ASSERT(valuelen == sizeof(struct xfs_parent_rec));
+ return 0;
+ }
+
+ if (!value) {
+ ASSERT(value != NULL);
+ return 0;
+ }
+
+ return xfs_parent_hashval(mp, name, namelen, be64_to_cpu(rec->p_ino));
+}
+
+/*
+ * Initialize the parent pointer arguments structure. Caller must have zeroed
+ * the contents of @args. @tp is only required for updates.
+ */
+static void
+xfs_parent_da_args_init(
+ struct xfs_da_args *args,
+ struct xfs_trans *tp,
+ struct xfs_parent_rec *rec,
+ struct xfs_inode *child,
+ xfs_ino_t owner,
+ const struct xfs_name *parent_name)
+{
+ args->geo = child->i_mount->m_attr_geo;
+ args->whichfork = XFS_ATTR_FORK;
+ args->attr_filter = XFS_ATTR_PARENT;
+ args->op_flags = XFS_DA_OP_LOGGED | XFS_DA_OP_OKNOENT;
+ args->trans = tp;
+ args->dp = child;
+ args->owner = owner;
+ args->name = parent_name->name;
+ args->namelen = parent_name->len;
+ args->value = rec;
+ args->valuelen = sizeof(struct xfs_parent_rec);
+ xfs_attr_sethash(args);
+}
+
+/* Make sure the incore state is ready for a parent pointer query/update. */
+static inline int
+xfs_parent_iread_extents(
+ struct xfs_trans *tp,
+ struct xfs_inode *child)
+{
+ /* Parent pointers require that the attr fork must exist. */
+ if (XFS_IS_CORRUPT(child->i_mount, !xfs_inode_has_attr_fork(child))) {
+ xfs_inode_mark_sick(child, XFS_SICK_INO_PARENT);
+ return -EFSCORRUPTED;
+ }
+
+ return xfs_iread_extents(tp, child, XFS_ATTR_FORK);
+}
+
+/* Add a parent pointer to reflect a dirent addition. */
+int
+xfs_parent_addname(
+ struct xfs_trans *tp,
+ struct xfs_parent_args *ppargs,
+ struct xfs_inode *dp,
+ const struct xfs_name *parent_name,
+ struct xfs_inode *child)
+{
+ int error;
+
+ error = xfs_parent_iread_extents(tp, child);
+ if (error)
+ return error;
+
+ xfs_inode_to_parent_rec(&ppargs->rec, dp);
+ xfs_parent_da_args_init(&ppargs->args, tp, &ppargs->rec, child,
+ child->i_ino, parent_name);
+ xfs_attr_defer_add(&ppargs->args, XFS_ATTR_DEFER_SET);
+ return 0;
+}
+
+/* Remove a parent pointer to reflect a dirent removal. */
+int
+xfs_parent_removename(
+ struct xfs_trans *tp,
+ struct xfs_parent_args *ppargs,
+ struct xfs_inode *dp,
+ const struct xfs_name *parent_name,
+ struct xfs_inode *child)
+{
+ int error;
+
+ error = xfs_parent_iread_extents(tp, child);
+ if (error)
+ return error;
+
+ xfs_inode_to_parent_rec(&ppargs->rec, dp);
+ xfs_parent_da_args_init(&ppargs->args, tp, &ppargs->rec, child,
+ child->i_ino, parent_name);
+ xfs_attr_defer_add(&ppargs->args, XFS_ATTR_DEFER_REMOVE);
+ return 0;
+}
+
+/* Replace one parent pointer with another to reflect a rename. */
+int
+xfs_parent_replacename(
+ struct xfs_trans *tp,
+ struct xfs_parent_args *ppargs,
+ struct xfs_inode *old_dp,
+ const struct xfs_name *old_name,
+ struct xfs_inode *new_dp,
+ const struct xfs_name *new_name,
+ struct xfs_inode *child)
+{
+ int error;
+
+ error = xfs_parent_iread_extents(tp, child);
+ if (error)
+ return error;
+
+ xfs_inode_to_parent_rec(&ppargs->rec, old_dp);
+ xfs_parent_da_args_init(&ppargs->args, tp, &ppargs->rec, child,
+ child->i_ino, old_name);
+
+ xfs_inode_to_parent_rec(&ppargs->new_rec, new_dp);
+ ppargs->args.new_name = new_name->name;
+ ppargs->args.new_namelen = new_name->len;
+ ppargs->args.new_value = &ppargs->new_rec;
+ ppargs->args.new_valuelen = sizeof(struct xfs_parent_rec);
+ xfs_attr_defer_add(&ppargs->args, XFS_ATTR_DEFER_REPLACE);
+ return 0;
+}
+
+/*
+ * Extract parent pointer information from any parent pointer xattr into
+ * @parent_ino/gen. The last two parameters can be NULL pointers.
+ *
+ * Returns 0 if this is not a parent pointer xattr at all; or -EFSCORRUPTED for
+ * garbage.
+ */
+int
+xfs_parent_from_attr(
+ struct xfs_mount *mp,
+ unsigned int attr_flags,
+ const unsigned char *name,
+ unsigned int namelen,
+ const void *value,
+ unsigned int valuelen,
+ xfs_ino_t *parent_ino,
+ uint32_t *parent_gen)
+{
+ const struct xfs_parent_rec *rec = value;
+
+ ASSERT(attr_flags & XFS_ATTR_PARENT);
+
+ if (!xfs_parent_namecheck(attr_flags, name, namelen))
+ return -EFSCORRUPTED;
+ if (!xfs_parent_valuecheck(mp, value, valuelen))
+ return -EFSCORRUPTED;
+
+ if (parent_ino)
+ *parent_ino = be64_to_cpu(rec->p_ino);
+ if (parent_gen)
+ *parent_gen = be32_to_cpu(rec->p_gen);
+ return 0;
+}
+
+/*
+ * Look up a parent pointer record (@parent_name -> @pptr) of @ip.
+ *
+ * Caller must hold at least ILOCK_SHARED. The scratchpad need not be
+ * initialized.
+ *
+ * Returns 0 if the pointer is found, -ENOATTR if there is no match, or a
+ * negative errno.
+ */
+int
+xfs_parent_lookup(
+ struct xfs_trans *tp,
+ struct xfs_inode *ip,
+ const struct xfs_name *parent_name,
+ struct xfs_parent_rec *pptr,
+ struct xfs_da_args *scratch)
+{
+ memset(scratch, 0, sizeof(struct xfs_da_args));
+ xfs_parent_da_args_init(scratch, tp, pptr, ip, ip->i_ino, parent_name);
+ return xfs_attr_get_ilocked(scratch);
+}
+
+/* Sanity-check a parent pointer before we try to perform repairs. */
+static inline bool
+xfs_parent_sanity_check(
+ struct xfs_mount *mp,
+ const struct xfs_name *parent_name,
+ const struct xfs_parent_rec *pptr)
+{
+ if (!xfs_parent_namecheck(XFS_ATTR_PARENT, parent_name->name,
+ parent_name->len))
+ return false;
+
+ if (!xfs_parent_valuecheck(mp, pptr, sizeof(*pptr)))
+ return false;
+
+ return true;
+}
+
+
+/*
+ * Attach the parent pointer (@parent_name -> @pptr) to @ip immediately.
+ * Caller must not have a transaction or hold the ILOCK. This is for
+ * specialized repair functions only. The scratchpad need not be initialized.
+ */
+int
+xfs_parent_set(
+ struct xfs_inode *ip,
+ xfs_ino_t owner,
+ const struct xfs_name *parent_name,
+ struct xfs_parent_rec *pptr,
+ struct xfs_da_args *scratch)
+{
+ if (!xfs_parent_sanity_check(ip->i_mount, parent_name, pptr)) {
+ ASSERT(0);
+ return -EFSCORRUPTED;
+ }
+
+ memset(scratch, 0, sizeof(struct xfs_da_args));
+ xfs_parent_da_args_init(scratch, NULL, pptr, ip, owner, parent_name);
+ return xfs_attr_set(scratch, XFS_ATTRUPDATE_CREATE, false);
+}
+
+/*
+ * Remove the parent pointer (@parent_name -> @pptr) from @ip immediately.
+ * Caller must not have a transaction or hold the ILOCK. This is for
+ * specialized repair functions only. The scratchpad need not be initialized.
+ */
+int
+xfs_parent_unset(
+ struct xfs_inode *ip,
+ xfs_ino_t owner,
+ const struct xfs_name *parent_name,
+ struct xfs_parent_rec *pptr,
+ struct xfs_da_args *scratch)
+{
+ if (!xfs_parent_sanity_check(ip->i_mount, parent_name, pptr)) {
+ ASSERT(0);
+ return -EFSCORRUPTED;
+ }
+
+ memset(scratch, 0, sizeof(struct xfs_da_args));
+ xfs_parent_da_args_init(scratch, NULL, pptr, ip, owner, parent_name);
+ return xfs_attr_set(scratch, XFS_ATTRUPDATE_REMOVE, false);
+}
diff --git a/fs/xfs/libxfs/xfs_parent.h b/fs/xfs/libxfs/xfs_parent.h
new file mode 100644
index 0000000000..b8036527cd
--- /dev/null
+++ b/fs/xfs/libxfs/xfs_parent.h
@@ -0,0 +1,110 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2022-2024 Oracle.
+ * All Rights Reserved.
+ */
+#ifndef __XFS_PARENT_H__
+#define __XFS_PARENT_H__
+
+/* Metadata validators */
+bool xfs_parent_namecheck(unsigned int attr_flags, const void *name,
+ size_t length);
+bool xfs_parent_valuecheck(struct xfs_mount *mp, const void *value,
+ size_t valuelen);
+
+xfs_dahash_t xfs_parent_hashval(struct xfs_mount *mp, const uint8_t *name,
+ int namelen, xfs_ino_t parent_ino);
+xfs_dahash_t xfs_parent_hashattr(struct xfs_mount *mp, const uint8_t *name,
+ int namelen, const void *value, int valuelen);
+
+/* Initializes a xfs_parent_rec to be stored as an attribute name. */
+static inline void
+xfs_parent_rec_init(
+ struct xfs_parent_rec *rec,
+ xfs_ino_t ino,
+ uint32_t gen)
+{
+ rec->p_ino = cpu_to_be64(ino);
+ rec->p_gen = cpu_to_be32(gen);
+}
+
+/* Initializes a xfs_parent_rec to be stored as an attribute name. */
+static inline void
+xfs_inode_to_parent_rec(
+ struct xfs_parent_rec *rec,
+ const struct xfs_inode *dp)
+{
+ xfs_parent_rec_init(rec, dp->i_ino, VFS_IC(dp)->i_generation);
+}
+
+extern struct kmem_cache *xfs_parent_args_cache;
+
+/*
+ * Parent pointer information needed to pass around the deferred xattr update
+ * machinery.
+ */
+struct xfs_parent_args {
+ struct xfs_parent_rec rec;
+ struct xfs_parent_rec new_rec;
+ struct xfs_da_args args;
+};
+
+/*
+ * Start a parent pointer update by allocating the context object we need to
+ * perform a parent pointer update.
+ */
+static inline int
+xfs_parent_start(
+ struct xfs_mount *mp,
+ struct xfs_parent_args **ppargsp)
+{
+ if (!xfs_has_parent(mp)) {
+ *ppargsp = NULL;
+ return 0;
+ }
+
+ *ppargsp = kmem_cache_zalloc(xfs_parent_args_cache, GFP_KERNEL);
+ if (!*ppargsp)
+ return -ENOMEM;
+ return 0;
+}
+
+/* Finish a parent pointer update by freeing the context object. */
+static inline void
+xfs_parent_finish(
+ struct xfs_mount *mp,
+ struct xfs_parent_args *ppargs)
+{
+ if (ppargs)
+ kmem_cache_free(xfs_parent_args_cache, ppargs);
+}
+
+int xfs_parent_addname(struct xfs_trans *tp, struct xfs_parent_args *ppargs,
+ struct xfs_inode *dp, const struct xfs_name *parent_name,
+ struct xfs_inode *child);
+int xfs_parent_removename(struct xfs_trans *tp, struct xfs_parent_args *ppargs,
+ struct xfs_inode *dp, const struct xfs_name *parent_name,
+ struct xfs_inode *child);
+int xfs_parent_replacename(struct xfs_trans *tp,
+ struct xfs_parent_args *ppargs,
+ struct xfs_inode *old_dp, const struct xfs_name *old_name,
+ struct xfs_inode *new_dp, const struct xfs_name *new_name,
+ struct xfs_inode *child);
+
+int xfs_parent_from_attr(struct xfs_mount *mp, unsigned int attr_flags,
+ const unsigned char *name, unsigned int namelen,
+ const void *value, unsigned int valuelen,
+ xfs_ino_t *parent_ino, uint32_t *parent_gen);
+
+/* Repair functions */
+int xfs_parent_lookup(struct xfs_trans *tp, struct xfs_inode *ip,
+ const struct xfs_name *name, struct xfs_parent_rec *pptr,
+ struct xfs_da_args *scratch);
+int xfs_parent_set(struct xfs_inode *ip, xfs_ino_t owner,
+ const struct xfs_name *name, struct xfs_parent_rec *pptr,
+ struct xfs_da_args *scratch);
+int xfs_parent_unset(struct xfs_inode *ip, xfs_ino_t owner,
+ const struct xfs_name *name, struct xfs_parent_rec *pptr,
+ struct xfs_da_args *scratch);
+
+#endif /* __XFS_PARENT_H__ */
diff --git a/fs/xfs/libxfs/xfs_rtbitmap.c b/fs/xfs/libxfs/xfs_rtbitmap.c
index f246d6dbf4..386b672c50 100644
--- a/fs/xfs/libxfs/xfs_rtbitmap.c
+++ b/fs/xfs/libxfs/xfs_rtbitmap.c
@@ -1168,3 +1168,60 @@ xfs_rtsummary_wordcount(
blocks = xfs_rtsummary_blockcount(mp, rsumlevels, rbmblocks);
return XFS_FSB_TO_B(mp, blocks) >> XFS_WORDLOG;
}
+
+/*
+ * Lock both realtime free space metadata inodes for a freespace update. If a
+ * transaction is given, the inodes will be joined to the transaction and the
+ * ILOCKs will be released on transaction commit.
+ */
+void
+xfs_rtbitmap_lock(
+ struct xfs_trans *tp,
+ struct xfs_mount *mp)
+{
+ xfs_ilock(mp->m_rbmip, XFS_ILOCK_EXCL | XFS_ILOCK_RTBITMAP);
+ if (tp)
+ xfs_trans_ijoin(tp, mp->m_rbmip, XFS_ILOCK_EXCL);
+
+ xfs_ilock(mp->m_rsumip, XFS_ILOCK_EXCL | XFS_ILOCK_RTSUM);
+ if (tp)
+ xfs_trans_ijoin(tp, mp->m_rsumip, XFS_ILOCK_EXCL);
+}
+
+/* Unlock both realtime free space metadata inodes after a freespace update. */
+void
+xfs_rtbitmap_unlock(
+ struct xfs_mount *mp)
+{
+ xfs_iunlock(mp->m_rsumip, XFS_ILOCK_EXCL | XFS_ILOCK_RTSUM);
+ xfs_iunlock(mp->m_rbmip, XFS_ILOCK_EXCL | XFS_ILOCK_RTBITMAP);
+}
+
+/*
+ * Lock the realtime free space metadata inodes for a freespace scan. Callers
+ * must walk metadata blocks in order of increasing file offset.
+ */
+void
+xfs_rtbitmap_lock_shared(
+ struct xfs_mount *mp,
+ unsigned int rbmlock_flags)
+{
+ if (rbmlock_flags & XFS_RBMLOCK_BITMAP)
+ xfs_ilock(mp->m_rbmip, XFS_ILOCK_SHARED | XFS_ILOCK_RTBITMAP);
+
+ if (rbmlock_flags & XFS_RBMLOCK_SUMMARY)
+ xfs_ilock(mp->m_rsumip, XFS_ILOCK_SHARED | XFS_ILOCK_RTSUM);
+}
+
+/* Unlock the realtime free space metadata inodes after a freespace scan. */
+void
+xfs_rtbitmap_unlock_shared(
+ struct xfs_mount *mp,
+ unsigned int rbmlock_flags)
+{
+ if (rbmlock_flags & XFS_RBMLOCK_SUMMARY)
+ xfs_iunlock(mp->m_rsumip, XFS_ILOCK_SHARED | XFS_ILOCK_RTSUM);
+
+ if (rbmlock_flags & XFS_RBMLOCK_BITMAP)
+ xfs_iunlock(mp->m_rbmip, XFS_ILOCK_SHARED | XFS_ILOCK_RTBITMAP);
+}
diff --git a/fs/xfs/libxfs/xfs_rtbitmap.h b/fs/xfs/libxfs/xfs_rtbitmap.h
index 152a66750a..6186585f2c 100644
--- a/fs/xfs/libxfs/xfs_rtbitmap.h
+++ b/fs/xfs/libxfs/xfs_rtbitmap.h
@@ -360,6 +360,19 @@ xfs_filblks_t xfs_rtsummary_blockcount(struct xfs_mount *mp,
unsigned int rsumlevels, xfs_extlen_t rbmblocks);
unsigned long long xfs_rtsummary_wordcount(struct xfs_mount *mp,
unsigned int rsumlevels, xfs_extlen_t rbmblocks);
+
+void xfs_rtbitmap_lock(struct xfs_trans *tp, struct xfs_mount *mp);
+void xfs_rtbitmap_unlock(struct xfs_mount *mp);
+
+/* Lock the rt bitmap inode in shared mode */
+#define XFS_RBMLOCK_BITMAP (1U << 0)
+/* Lock the rt summary inode in shared mode */
+#define XFS_RBMLOCK_SUMMARY (1U << 1)
+
+void xfs_rtbitmap_lock_shared(struct xfs_mount *mp,
+ unsigned int rbmlock_flags);
+void xfs_rtbitmap_unlock_shared(struct xfs_mount *mp,
+ unsigned int rbmlock_flags);
#else /* CONFIG_XFS_RT */
# define xfs_rtfree_extent(t,b,l) (-ENOSYS)
# define xfs_rtfree_blocks(t,rb,rl) (-ENOSYS)
@@ -378,6 +391,10 @@ xfs_rtbitmap_blockcount(struct xfs_mount *mp, xfs_rtbxlen_t rtextents)
# define xfs_rtbitmap_wordcount(mp, r) (0)
# define xfs_rtsummary_blockcount(mp, l, b) (0)
# define xfs_rtsummary_wordcount(mp, l, b) (0)
+# define xfs_rtbitmap_lock(tp, mp) do { } while (0)
+# define xfs_rtbitmap_unlock(mp) do { } while (0)
+# define xfs_rtbitmap_lock_shared(mp, lf) do { } while (0)
+# define xfs_rtbitmap_unlock_shared(mp, lf) do { } while (0)
#endif /* CONFIG_XFS_RT */
#endif /* __XFS_RTBITMAP_H__ */
diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index 73a4b895de..6b56f0f6d4 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -26,6 +26,7 @@
#include "xfs_health.h"
#include "xfs_ag.h"
#include "xfs_rtbitmap.h"
+#include "xfs_exchrange.h"
/*
* Physical superblock buffer manipulations. Shared with libxfs in userspace.
@@ -175,6 +176,10 @@ xfs_sb_version_to_features(
features |= XFS_FEAT_NEEDSREPAIR;
if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_NREXT64)
features |= XFS_FEAT_NREXT64;
+ if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_EXCHRANGE)
+ features |= XFS_FEAT_EXCHANGE_RANGE;
+ if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_PARENT)
+ features |= XFS_FEAT_PARENT;
return features;
}
@@ -1033,11 +1038,12 @@ xfs_log_sb(
* and hence we don't need have to update it here.
*/
if (xfs_has_lazysbcount(mp)) {
- mp->m_sb.sb_icount = percpu_counter_sum(&mp->m_icount);
+ mp->m_sb.sb_icount = percpu_counter_sum_positive(&mp->m_icount);
mp->m_sb.sb_ifree = min_t(uint64_t,
- percpu_counter_sum(&mp->m_ifree),
+ percpu_counter_sum_positive(&mp->m_ifree),
mp->m_sb.sb_icount);
- mp->m_sb.sb_fdblocks = percpu_counter_sum(&mp->m_fdblocks);
+ mp->m_sb.sb_fdblocks =
+ percpu_counter_sum_positive(&mp->m_fdblocks);
}
xfs_sb_to_disk(bp->b_addr, &mp->m_sb);
@@ -1251,6 +1257,8 @@ xfs_fs_geometry(
geo->flags |= XFS_FSOP_GEOM_FLAGS_BIGTIME;
if (xfs_has_inobtcounts(mp))
geo->flags |= XFS_FSOP_GEOM_FLAGS_INOBTCNT;
+ if (xfs_has_parent(mp))
+ geo->flags |= XFS_FSOP_GEOM_FLAGS_PARENT;
if (xfs_has_sector(mp)) {
geo->flags |= XFS_FSOP_GEOM_FLAGS_SECTOR;
geo->logsectsize = sbp->sb_logsectsize;
@@ -1259,6 +1267,8 @@ xfs_fs_geometry(
}
if (xfs_has_large_extent_counts(mp))
geo->flags |= XFS_FSOP_GEOM_FLAGS_NREXT64;
+ if (xfs_has_exchange_range(mp))
+ geo->flags |= XFS_FSOP_GEOM_FLAGS_EXCHANGE_RANGE;
geo->rtsectsize = sbp->sb_blocksize;
geo->dirblocksize = xfs_dir2_dirblock_bytes(sbp);
diff --git a/fs/xfs/libxfs/xfs_shared.h b/fs/xfs/libxfs/xfs_shared.h
index dfd61fa833..34f104ed37 100644
--- a/fs/xfs/libxfs/xfs_shared.h
+++ b/fs/xfs/libxfs/xfs_shared.h
@@ -124,7 +124,6 @@ void xfs_log_get_max_trans_res(struct xfs_mount *mp,
#define XFS_TRANS_RES_FDBLKS (1u << 6)
/* Transaction contains an intent done log item */
#define XFS_TRANS_HAS_INTENT_DONE (1u << 7)
-
/*
* LOWMODE is used by the allocator to activate the lowspace algorithm - when
* free space is running low the extent allocator may choose to allocate an
@@ -136,7 +135,10 @@ void xfs_log_get_max_trans_res(struct xfs_mount *mp,
* for free space from AG 0. If the correct transaction reservations have been
* made then this algorithm will eventually find all the space it needs.
*/
-#define XFS_TRANS_LOWMODE 0x100 /* allocate in low space mode */
+#define XFS_TRANS_LOWMODE (1u << 8)
+
+/* Transaction has locked the rtbitmap and rtsum inodes */
+#define XFS_TRANS_RTBITMAP_LOCKED (1u << 9)
/*
* Field values for xfs_trans_mod_sb.
diff --git a/fs/xfs/libxfs/xfs_symlink_remote.c b/fs/xfs/libxfs/xfs_symlink_remote.c
index ffb1317a92..f228127a88 100644
--- a/fs/xfs/libxfs/xfs_symlink_remote.c
+++ b/fs/xfs/libxfs/xfs_symlink_remote.c
@@ -169,7 +169,8 @@ xfs_symlink_local_to_remote(
struct xfs_trans *tp,
struct xfs_buf *bp,
struct xfs_inode *ip,
- struct xfs_ifork *ifp)
+ struct xfs_ifork *ifp,
+ void *priv)
{
struct xfs_mount *mp = ip->i_mount;
char *buf;
@@ -310,6 +311,7 @@ int
xfs_symlink_write_target(
struct xfs_trans *tp,
struct xfs_inode *ip,
+ xfs_ino_t owner,
const char *target_path,
int pathlen,
xfs_fsblock_t fs_blocks,
@@ -364,8 +366,7 @@ xfs_symlink_write_target(
byte_cnt = min(byte_cnt, pathlen);
buf = bp->b_addr;
- buf += xfs_symlink_hdr_set(mp, ip->i_ino, offset, byte_cnt,
- bp);
+ buf += xfs_symlink_hdr_set(mp, owner, offset, byte_cnt, bp);
memcpy(buf, cur_chunk, byte_cnt);
@@ -380,3 +381,50 @@ xfs_symlink_write_target(
ASSERT(pathlen == 0);
return 0;
}
+
+/* Remove all the blocks from a symlink and invalidate buffers. */
+int
+xfs_symlink_remote_truncate(
+ struct xfs_trans *tp,
+ struct xfs_inode *ip)
+{
+ struct xfs_bmbt_irec mval[XFS_SYMLINK_MAPS];
+ struct xfs_mount *mp = tp->t_mountp;
+ struct xfs_buf *bp;
+ int nmaps = XFS_SYMLINK_MAPS;
+ int done = 0;
+ int i;
+ int error;
+
+ /* Read mappings and invalidate buffers. */
+ error = xfs_bmapi_read(ip, 0, XFS_MAX_FILEOFF, mval, &nmaps, 0);
+ if (error)
+ return error;
+
+ for (i = 0; i < nmaps; i++) {
+ if (!xfs_bmap_is_real_extent(&mval[i]))
+ break;
+
+ error = xfs_trans_get_buf(tp, mp->m_ddev_targp,
+ XFS_FSB_TO_DADDR(mp, mval[i].br_startblock),
+ XFS_FSB_TO_BB(mp, mval[i].br_blockcount), 0,
+ &bp);
+ if (error)
+ return error;
+
+ xfs_trans_binval(tp, bp);
+ }
+
+ /* Unmap the remote blocks. */
+ error = xfs_bunmapi(tp, ip, 0, XFS_MAX_FILEOFF, 0, nmaps, &done);
+ if (error)
+ return error;
+ if (!done) {
+ ASSERT(done);
+ xfs_inode_mark_sick(ip, XFS_SICK_INO_SYMLINK);
+ return -EFSCORRUPTED;
+ }
+
+ xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+ return 0;
+}
diff --git a/fs/xfs/libxfs/xfs_symlink_remote.h b/fs/xfs/libxfs/xfs_symlink_remote.h
index a63bd38ae4..c1672fe1f1 100644
--- a/fs/xfs/libxfs/xfs_symlink_remote.h
+++ b/fs/xfs/libxfs/xfs_symlink_remote.h
@@ -16,11 +16,13 @@ int xfs_symlink_hdr_set(struct xfs_mount *mp, xfs_ino_t ino, uint32_t offset,
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);
+ struct xfs_inode *ip, struct xfs_ifork *ifp,
+ void *priv);
xfs_failaddr_t xfs_symlink_shortform_verify(void *sfp, int64_t size);
int xfs_symlink_remote_read(struct xfs_inode *ip, char *link);
int xfs_symlink_write_target(struct xfs_trans *tp, struct xfs_inode *ip,
- const char *target_path, int pathlen, xfs_fsblock_t fs_blocks,
- uint resblks);
+ xfs_ino_t owner, const char *target_path, int pathlen,
+ xfs_fsblock_t fs_blocks, uint resblks);
+int xfs_symlink_remote_truncate(struct xfs_trans *tp, struct xfs_inode *ip);
#endif /* __XFS_SYMLINK_REMOTE_H */
diff --git a/fs/xfs/libxfs/xfs_trans_resv.c b/fs/xfs/libxfs/xfs_trans_resv.c
index 6cd45e8c11..6dbe6e7251 100644
--- a/fs/xfs/libxfs/xfs_trans_resv.c
+++ b/fs/xfs/libxfs/xfs_trans_resv.c
@@ -20,6 +20,9 @@
#include "xfs_qm.h"
#include "xfs_trans_space.h"
#include "xfs_rtbitmap.h"
+#include "xfs_attr_item.h"
+#include "xfs_log.h"
+#include "xfs_da_format.h"
#define _ALLOC true
#define _FREE false
@@ -422,29 +425,110 @@ xfs_calc_itruncate_reservation_minlogsize(
return xfs_calc_itruncate_reservation(mp, true);
}
+static inline unsigned int xfs_calc_pptr_link_overhead(void)
+{
+ return sizeof(struct xfs_attri_log_format) +
+ xlog_calc_iovec_len(sizeof(struct xfs_parent_rec)) +
+ xlog_calc_iovec_len(MAXNAMELEN - 1);
+}
+static inline unsigned int xfs_calc_pptr_unlink_overhead(void)
+{
+ return sizeof(struct xfs_attri_log_format) +
+ xlog_calc_iovec_len(sizeof(struct xfs_parent_rec)) +
+ xlog_calc_iovec_len(MAXNAMELEN - 1);
+}
+static inline unsigned int xfs_calc_pptr_replace_overhead(void)
+{
+ return sizeof(struct xfs_attri_log_format) +
+ xlog_calc_iovec_len(sizeof(struct xfs_parent_rec)) +
+ xlog_calc_iovec_len(MAXNAMELEN - 1) +
+ xlog_calc_iovec_len(sizeof(struct xfs_parent_rec)) +
+ xlog_calc_iovec_len(MAXNAMELEN - 1);
+}
+
/*
* In renaming a files we can modify:
* the five inodes involved: 5 * inode size
* the two directory btrees: 2 * (max depth + v2) * dir block size
* the two directory bmap btrees: 2 * max depth * block size
* And the bmap_finish transaction can free dir and bmap blocks (two sets
- * of bmap blocks) giving:
+ * of bmap blocks) giving (t2):
* the agf for the ags in which the blocks live: 3 * sector size
* the agfl for the ags in which the blocks live: 3 * sector size
* the superblock for the free block count: sector size
* the allocation btrees: 3 exts * 2 trees * (2 * max depth - 1) * block size
+ * If parent pointers are enabled (t3), then each transaction in the chain
+ * must be capable of setting or removing the extended attribute
+ * containing the parent information. It must also be able to handle
+ * the three xattr intent items that track the progress of the parent
+ * pointer update.
*/
STATIC uint
xfs_calc_rename_reservation(
struct xfs_mount *mp)
{
- return XFS_DQUOT_LOGRES(mp) +
- max((xfs_calc_inode_res(mp, 5) +
- xfs_calc_buf_res(2 * XFS_DIROP_LOG_COUNT(mp),
- XFS_FSB_TO_B(mp, 1))),
- (xfs_calc_buf_res(7, mp->m_sb.sb_sectsize) +
- xfs_calc_buf_res(xfs_allocfree_block_count(mp, 3),
- XFS_FSB_TO_B(mp, 1))));
+ unsigned int overhead = XFS_DQUOT_LOGRES(mp);
+ struct xfs_trans_resv *resp = M_RES(mp);
+ unsigned int t1, t2, t3 = 0;
+
+ t1 = xfs_calc_inode_res(mp, 5) +
+ xfs_calc_buf_res(2 * XFS_DIROP_LOG_COUNT(mp),
+ XFS_FSB_TO_B(mp, 1));
+
+ t2 = xfs_calc_buf_res(7, mp->m_sb.sb_sectsize) +
+ xfs_calc_buf_res(xfs_allocfree_block_count(mp, 3),
+ XFS_FSB_TO_B(mp, 1));
+
+ if (xfs_has_parent(mp)) {
+ unsigned int rename_overhead, exchange_overhead;
+
+ t3 = max(resp->tr_attrsetm.tr_logres,
+ resp->tr_attrrm.tr_logres);
+
+ /*
+ * For a standard rename, the three xattr intent log items
+ * are (1) replacing the pptr for the source file; (2)
+ * removing the pptr on the dest file; and (3) adding a
+ * pptr for the whiteout file in the src dir.
+ *
+ * For an RENAME_EXCHANGE, there are two xattr intent
+ * items to replace the pptr for both src and dest
+ * files. Link counts don't change and there is no
+ * whiteout.
+ *
+ * In the worst case we can end up relogging all log
+ * intent items to allow the log tail to move ahead, so
+ * they become overhead added to each transaction in a
+ * processing chain.
+ */
+ rename_overhead = xfs_calc_pptr_replace_overhead() +
+ xfs_calc_pptr_unlink_overhead() +
+ xfs_calc_pptr_link_overhead();
+ exchange_overhead = 2 * xfs_calc_pptr_replace_overhead();
+
+ overhead += max(rename_overhead, exchange_overhead);
+ }
+
+ return overhead + max3(t1, t2, t3);
+}
+
+static inline unsigned int
+xfs_rename_log_count(
+ struct xfs_mount *mp,
+ struct xfs_trans_resv *resp)
+{
+ /* One for the rename, one more for freeing blocks */
+ unsigned int ret = XFS_RENAME_LOG_COUNT;
+
+ /*
+ * Pre-reserve enough log reservation to handle the transaction
+ * rolling needed to remove or add one parent pointer.
+ */
+ if (xfs_has_parent(mp))
+ ret += max(resp->tr_attrsetm.tr_logcount,
+ resp->tr_attrrm.tr_logcount);
+
+ return ret;
}
/*
@@ -461,6 +545,23 @@ xfs_calc_iunlink_remove_reservation(
2 * M_IGEO(mp)->inode_cluster_size;
}
+static inline unsigned int
+xfs_link_log_count(
+ struct xfs_mount *mp,
+ struct xfs_trans_resv *resp)
+{
+ unsigned int ret = XFS_LINK_LOG_COUNT;
+
+ /*
+ * Pre-reserve enough log reservation to handle the transaction
+ * rolling needed to add one parent pointer.
+ */
+ if (xfs_has_parent(mp))
+ ret += resp->tr_attrsetm.tr_logcount;
+
+ return ret;
+}
+
/*
* For creating a link to an inode:
* the parent directory inode: inode size
@@ -477,14 +578,23 @@ STATIC uint
xfs_calc_link_reservation(
struct xfs_mount *mp)
{
- return XFS_DQUOT_LOGRES(mp) +
- xfs_calc_iunlink_remove_reservation(mp) +
- max((xfs_calc_inode_res(mp, 2) +
- xfs_calc_buf_res(XFS_DIROP_LOG_COUNT(mp),
- XFS_FSB_TO_B(mp, 1))),
- (xfs_calc_buf_res(3, mp->m_sb.sb_sectsize) +
- xfs_calc_buf_res(xfs_allocfree_block_count(mp, 1),
- XFS_FSB_TO_B(mp, 1))));
+ unsigned int overhead = XFS_DQUOT_LOGRES(mp);
+ struct xfs_trans_resv *resp = M_RES(mp);
+ unsigned int t1, t2, t3 = 0;
+
+ overhead += xfs_calc_iunlink_remove_reservation(mp);
+ t1 = xfs_calc_inode_res(mp, 2) +
+ xfs_calc_buf_res(XFS_DIROP_LOG_COUNT(mp), XFS_FSB_TO_B(mp, 1));
+ t2 = xfs_calc_buf_res(3, mp->m_sb.sb_sectsize) +
+ xfs_calc_buf_res(xfs_allocfree_block_count(mp, 1),
+ XFS_FSB_TO_B(mp, 1));
+
+ if (xfs_has_parent(mp)) {
+ t3 = resp->tr_attrsetm.tr_logres;
+ overhead += xfs_calc_pptr_link_overhead();
+ }
+
+ return overhead + max3(t1, t2, t3);
}
/*
@@ -499,6 +609,23 @@ xfs_calc_iunlink_add_reservation(xfs_mount_t *mp)
M_IGEO(mp)->inode_cluster_size;
}
+static inline unsigned int
+xfs_remove_log_count(
+ struct xfs_mount *mp,
+ struct xfs_trans_resv *resp)
+{
+ unsigned int ret = XFS_REMOVE_LOG_COUNT;
+
+ /*
+ * Pre-reserve enough log reservation to handle the transaction
+ * rolling needed to add one parent pointer.
+ */
+ if (xfs_has_parent(mp))
+ ret += resp->tr_attrrm.tr_logcount;
+
+ return ret;
+}
+
/*
* For removing a directory entry we can modify:
* the parent directory inode: inode size
@@ -515,14 +642,24 @@ STATIC uint
xfs_calc_remove_reservation(
struct xfs_mount *mp)
{
- return XFS_DQUOT_LOGRES(mp) +
- xfs_calc_iunlink_add_reservation(mp) +
- max((xfs_calc_inode_res(mp, 2) +
- xfs_calc_buf_res(XFS_DIROP_LOG_COUNT(mp),
- XFS_FSB_TO_B(mp, 1))),
- (xfs_calc_buf_res(4, mp->m_sb.sb_sectsize) +
- xfs_calc_buf_res(xfs_allocfree_block_count(mp, 2),
- XFS_FSB_TO_B(mp, 1))));
+ unsigned int overhead = XFS_DQUOT_LOGRES(mp);
+ struct xfs_trans_resv *resp = M_RES(mp);
+ unsigned int t1, t2, t3 = 0;
+
+ overhead += xfs_calc_iunlink_add_reservation(mp);
+
+ t1 = xfs_calc_inode_res(mp, 2) +
+ xfs_calc_buf_res(XFS_DIROP_LOG_COUNT(mp), XFS_FSB_TO_B(mp, 1));
+ t2 = xfs_calc_buf_res(4, mp->m_sb.sb_sectsize) +
+ xfs_calc_buf_res(xfs_allocfree_block_count(mp, 2),
+ XFS_FSB_TO_B(mp, 1));
+
+ if (xfs_has_parent(mp)) {
+ t3 = resp->tr_attrrm.tr_logres;
+ overhead += xfs_calc_pptr_unlink_overhead();
+ }
+
+ return overhead + max3(t1, t2, t3);
}
/*
@@ -571,12 +708,40 @@ xfs_calc_icreate_resv_alloc(
xfs_calc_finobt_res(mp);
}
+static inline unsigned int
+xfs_icreate_log_count(
+ struct xfs_mount *mp,
+ struct xfs_trans_resv *resp)
+{
+ unsigned int ret = XFS_CREATE_LOG_COUNT;
+
+ /*
+ * Pre-reserve enough log reservation to handle the transaction
+ * rolling needed to add one parent pointer.
+ */
+ if (xfs_has_parent(mp))
+ ret += resp->tr_attrsetm.tr_logcount;
+
+ return ret;
+}
+
STATIC uint
-xfs_calc_icreate_reservation(xfs_mount_t *mp)
+xfs_calc_icreate_reservation(
+ struct xfs_mount *mp)
{
- return XFS_DQUOT_LOGRES(mp) +
- max(xfs_calc_icreate_resv_alloc(mp),
- xfs_calc_create_resv_modify(mp));
+ struct xfs_trans_resv *resp = M_RES(mp);
+ unsigned int overhead = XFS_DQUOT_LOGRES(mp);
+ unsigned int t1, t2, t3 = 0;
+
+ t1 = xfs_calc_icreate_resv_alloc(mp);
+ t2 = xfs_calc_create_resv_modify(mp);
+
+ if (xfs_has_parent(mp)) {
+ t3 = resp->tr_attrsetm.tr_logres;
+ overhead += xfs_calc_pptr_link_overhead();
+ }
+
+ return overhead + max3(t1, t2, t3);
}
STATIC uint
@@ -589,6 +754,23 @@ xfs_calc_create_tmpfile_reservation(
return res + xfs_calc_iunlink_add_reservation(mp);
}
+static inline unsigned int
+xfs_mkdir_log_count(
+ struct xfs_mount *mp,
+ struct xfs_trans_resv *resp)
+{
+ unsigned int ret = XFS_MKDIR_LOG_COUNT;
+
+ /*
+ * Pre-reserve enough log reservation to handle the transaction
+ * rolling needed to add one parent pointer.
+ */
+ if (xfs_has_parent(mp))
+ ret += resp->tr_attrsetm.tr_logcount;
+
+ return ret;
+}
+
/*
* Making a new directory is the same as creating a new file.
*/
@@ -599,6 +781,22 @@ xfs_calc_mkdir_reservation(
return xfs_calc_icreate_reservation(mp);
}
+static inline unsigned int
+xfs_symlink_log_count(
+ struct xfs_mount *mp,
+ struct xfs_trans_resv *resp)
+{
+ unsigned int ret = XFS_SYMLINK_LOG_COUNT;
+
+ /*
+ * Pre-reserve enough log reservation to handle the transaction
+ * rolling needed to add one parent pointer.
+ */
+ if (xfs_has_parent(mp))
+ ret += resp->tr_attrsetm.tr_logcount;
+
+ return ret;
+}
/*
* Making a new symplink is the same as creating a new file, but
@@ -911,54 +1109,76 @@ xfs_calc_sb_reservation(
return xfs_calc_buf_res(1, mp->m_sb.sb_sectsize);
}
-void
-xfs_trans_resv_calc(
+/*
+ * Namespace reservations.
+ *
+ * These get tricky when parent pointers are enabled as we have attribute
+ * modifications occurring from within these transactions. Rather than confuse
+ * each of these reservation calculations with the conditional attribute
+ * reservations, add them here in a clear and concise manner. This requires that
+ * the attribute reservations have already been calculated.
+ *
+ * Note that we only include the static attribute reservation here; the runtime
+ * reservation will have to be modified by the size of the attributes being
+ * added/removed/modified. See the comments on the attribute reservation
+ * calculations for more details.
+ */
+STATIC void
+xfs_calc_namespace_reservations(
struct xfs_mount *mp,
struct xfs_trans_resv *resp)
{
- int logcount_adj = 0;
-
- /*
- * The following transactions are logged in physical format and
- * require a permanent reservation on space.
- */
- resp->tr_write.tr_logres = xfs_calc_write_reservation(mp, false);
- resp->tr_write.tr_logcount = XFS_WRITE_LOG_COUNT;
- resp->tr_write.tr_logflags |= XFS_TRANS_PERM_LOG_RES;
-
- resp->tr_itruncate.tr_logres = xfs_calc_itruncate_reservation(mp, false);
- resp->tr_itruncate.tr_logcount = XFS_ITRUNCATE_LOG_COUNT;
- resp->tr_itruncate.tr_logflags |= XFS_TRANS_PERM_LOG_RES;
+ ASSERT(resp->tr_attrsetm.tr_logres > 0);
resp->tr_rename.tr_logres = xfs_calc_rename_reservation(mp);
- resp->tr_rename.tr_logcount = XFS_RENAME_LOG_COUNT;
+ resp->tr_rename.tr_logcount = xfs_rename_log_count(mp, resp);
resp->tr_rename.tr_logflags |= XFS_TRANS_PERM_LOG_RES;
resp->tr_link.tr_logres = xfs_calc_link_reservation(mp);
- resp->tr_link.tr_logcount = XFS_LINK_LOG_COUNT;
+ resp->tr_link.tr_logcount = xfs_link_log_count(mp, resp);
resp->tr_link.tr_logflags |= XFS_TRANS_PERM_LOG_RES;
resp->tr_remove.tr_logres = xfs_calc_remove_reservation(mp);
- resp->tr_remove.tr_logcount = XFS_REMOVE_LOG_COUNT;
+ resp->tr_remove.tr_logcount = xfs_remove_log_count(mp, resp);
resp->tr_remove.tr_logflags |= XFS_TRANS_PERM_LOG_RES;
resp->tr_symlink.tr_logres = xfs_calc_symlink_reservation(mp);
- resp->tr_symlink.tr_logcount = XFS_SYMLINK_LOG_COUNT;
+ resp->tr_symlink.tr_logcount = xfs_symlink_log_count(mp, resp);
resp->tr_symlink.tr_logflags |= XFS_TRANS_PERM_LOG_RES;
resp->tr_create.tr_logres = xfs_calc_icreate_reservation(mp);
- resp->tr_create.tr_logcount = XFS_CREATE_LOG_COUNT;
+ resp->tr_create.tr_logcount = xfs_icreate_log_count(mp, resp);
resp->tr_create.tr_logflags |= XFS_TRANS_PERM_LOG_RES;
+ resp->tr_mkdir.tr_logres = xfs_calc_mkdir_reservation(mp);
+ resp->tr_mkdir.tr_logcount = xfs_mkdir_log_count(mp, resp);
+ resp->tr_mkdir.tr_logflags |= XFS_TRANS_PERM_LOG_RES;
+}
+
+void
+xfs_trans_resv_calc(
+ struct xfs_mount *mp,
+ struct xfs_trans_resv *resp)
+{
+ int logcount_adj = 0;
+
+ /*
+ * The following transactions are logged in physical format and
+ * require a permanent reservation on space.
+ */
+ resp->tr_write.tr_logres = xfs_calc_write_reservation(mp, false);
+ resp->tr_write.tr_logcount = XFS_WRITE_LOG_COUNT;
+ resp->tr_write.tr_logflags |= XFS_TRANS_PERM_LOG_RES;
+
+ resp->tr_itruncate.tr_logres = xfs_calc_itruncate_reservation(mp, false);
+ resp->tr_itruncate.tr_logcount = XFS_ITRUNCATE_LOG_COUNT;
+ resp->tr_itruncate.tr_logflags |= XFS_TRANS_PERM_LOG_RES;
+
resp->tr_create_tmpfile.tr_logres =
xfs_calc_create_tmpfile_reservation(mp);
resp->tr_create_tmpfile.tr_logcount = XFS_CREATE_TMPFILE_LOG_COUNT;
resp->tr_create_tmpfile.tr_logflags |= XFS_TRANS_PERM_LOG_RES;
- resp->tr_mkdir.tr_logres = xfs_calc_mkdir_reservation(mp);
- resp->tr_mkdir.tr_logcount = XFS_MKDIR_LOG_COUNT;
- resp->tr_mkdir.tr_logflags |= XFS_TRANS_PERM_LOG_RES;
-
resp->tr_ifree.tr_logres = xfs_calc_ifree_reservation(mp);
resp->tr_ifree.tr_logcount = XFS_INACTIVE_LOG_COUNT;
resp->tr_ifree.tr_logflags |= XFS_TRANS_PERM_LOG_RES;
@@ -988,6 +1208,8 @@ xfs_trans_resv_calc(
resp->tr_qm_dqalloc.tr_logcount = XFS_WRITE_LOG_COUNT;
resp->tr_qm_dqalloc.tr_logflags |= XFS_TRANS_PERM_LOG_RES;
+ xfs_calc_namespace_reservations(mp, resp);
+
/*
* The following transactions are logged in logical format with
* a default log count.
diff --git a/fs/xfs/libxfs/xfs_trans_space.c b/fs/xfs/libxfs/xfs_trans_space.c
new file mode 100644
index 0000000000..b9dc3752f7
--- /dev/null
+++ b/fs/xfs/libxfs/xfs_trans_space.c
@@ -0,0 +1,121 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2000,2005 Silicon Graphics, Inc.
+ * All Rights Reserved.
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_da_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_da_btree.h"
+#include "xfs_bmap_btree.h"
+#include "xfs_trans_space.h"
+
+/* Calculate the disk space required to add a parent pointer. */
+unsigned int
+xfs_parent_calc_space_res(
+ struct xfs_mount *mp,
+ unsigned int namelen)
+{
+ /*
+ * Parent pointers are always the first attr in an attr tree, and never
+ * larger than a block
+ */
+ return XFS_DAENTER_SPACE_RES(mp, XFS_ATTR_FORK) +
+ XFS_NEXTENTADD_SPACE_RES(mp, namelen, XFS_ATTR_FORK);
+}
+
+unsigned int
+xfs_create_space_res(
+ struct xfs_mount *mp,
+ unsigned int namelen)
+{
+ unsigned int ret;
+
+ ret = XFS_IALLOC_SPACE_RES(mp) + XFS_DIRENTER_SPACE_RES(mp, namelen);
+ if (xfs_has_parent(mp))
+ ret += xfs_parent_calc_space_res(mp, namelen);
+
+ return ret;
+}
+
+unsigned int
+xfs_mkdir_space_res(
+ struct xfs_mount *mp,
+ unsigned int namelen)
+{
+ return xfs_create_space_res(mp, namelen);
+}
+
+unsigned int
+xfs_link_space_res(
+ struct xfs_mount *mp,
+ unsigned int namelen)
+{
+ unsigned int ret;
+
+ ret = XFS_DIRENTER_SPACE_RES(mp, namelen);
+ if (xfs_has_parent(mp))
+ ret += xfs_parent_calc_space_res(mp, namelen);
+
+ return ret;
+}
+
+unsigned int
+xfs_symlink_space_res(
+ struct xfs_mount *mp,
+ unsigned int namelen,
+ unsigned int fsblocks)
+{
+ unsigned int ret;
+
+ ret = XFS_IALLOC_SPACE_RES(mp) + XFS_DIRENTER_SPACE_RES(mp, namelen) +
+ fsblocks;
+
+ if (xfs_has_parent(mp))
+ ret += xfs_parent_calc_space_res(mp, namelen);
+
+ return ret;
+}
+
+unsigned int
+xfs_remove_space_res(
+ struct xfs_mount *mp,
+ unsigned int namelen)
+{
+ unsigned int ret = XFS_DIRREMOVE_SPACE_RES(mp);
+
+ if (xfs_has_parent(mp))
+ ret += xfs_parent_calc_space_res(mp, namelen);
+
+ return ret;
+}
+
+unsigned int
+xfs_rename_space_res(
+ struct xfs_mount *mp,
+ unsigned int src_namelen,
+ bool target_exists,
+ unsigned int target_namelen,
+ bool has_whiteout)
+{
+ unsigned int ret;
+
+ ret = XFS_DIRREMOVE_SPACE_RES(mp) +
+ XFS_DIRENTER_SPACE_RES(mp, target_namelen);
+
+ if (xfs_has_parent(mp)) {
+ if (has_whiteout)
+ ret += xfs_parent_calc_space_res(mp, src_namelen);
+ ret += 2 * xfs_parent_calc_space_res(mp, target_namelen);
+ }
+
+ if (target_exists)
+ ret += xfs_parent_calc_space_res(mp, target_namelen);
+
+ return ret;
+}
diff --git a/fs/xfs/libxfs/xfs_trans_space.h b/fs/xfs/libxfs/xfs_trans_space.h
index 87b31c69a7..1155ff2d37 100644
--- a/fs/xfs/libxfs/xfs_trans_space.h
+++ b/fs/xfs/libxfs/xfs_trans_space.h
@@ -10,6 +10,10 @@
* Components of space reservations.
*/
+/* Worst case number of bmaps that can be held in a block. */
+#define XFS_MAX_CONTIG_BMAPS_PER_BLOCK(mp) \
+ (((mp)->m_bmap_dmxr[0]) - ((mp)->m_bmap_dmnr[0]))
+
/* Worst case number of rmaps that can be held in a block. */
#define XFS_MAX_CONTIG_RMAPS_PER_BLOCK(mp) \
(((mp)->m_rmap_mxr[0]) - ((mp)->m_rmap_mnr[0]))
@@ -76,31 +80,32 @@
/* This macro is not used - see inline code in xfs_attr_set */
#define XFS_ATTRSET_SPACE_RES(mp, v) \
(XFS_DAENTER_SPACE_RES(mp, XFS_ATTR_FORK) + XFS_B_TO_FSB(mp, v))
-#define XFS_CREATE_SPACE_RES(mp,nl) \
- (XFS_IALLOC_SPACE_RES(mp) + XFS_DIRENTER_SPACE_RES(mp,nl))
#define XFS_DIOSTRAT_SPACE_RES(mp, v) \
(XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK) + (v))
#define XFS_GROWFS_SPACE_RES(mp) \
(2 * (mp)->m_alloc_maxlevels)
#define XFS_GROWFSRT_SPACE_RES(mp,b) \
((b) + XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK))
-#define XFS_LINK_SPACE_RES(mp,nl) \
- XFS_DIRENTER_SPACE_RES(mp,nl)
-#define XFS_MKDIR_SPACE_RES(mp,nl) \
- (XFS_IALLOC_SPACE_RES(mp) + XFS_DIRENTER_SPACE_RES(mp,nl))
#define XFS_QM_DQALLOC_SPACE_RES(mp) \
(XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK) + \
XFS_DQUOT_CLUSTER_SIZE_FSB)
#define XFS_QM_QINOCREATE_SPACE_RES(mp) \
XFS_IALLOC_SPACE_RES(mp)
-#define XFS_REMOVE_SPACE_RES(mp) \
- XFS_DIRREMOVE_SPACE_RES(mp)
-#define XFS_RENAME_SPACE_RES(mp,nl) \
- (XFS_DIRREMOVE_SPACE_RES(mp) + XFS_DIRENTER_SPACE_RES(mp,nl))
-#define XFS_SYMLINK_SPACE_RES(mp,nl,b) \
- (XFS_IALLOC_SPACE_RES(mp) + XFS_DIRENTER_SPACE_RES(mp,nl) + (b))
#define XFS_IFREE_SPACE_RES(mp) \
(xfs_has_finobt(mp) ? M_IGEO(mp)->inobt_maxlevels : 0)
+unsigned int xfs_parent_calc_space_res(struct xfs_mount *mp,
+ unsigned int namelen);
+
+unsigned int xfs_create_space_res(struct xfs_mount *mp, unsigned int namelen);
+unsigned int xfs_mkdir_space_res(struct xfs_mount *mp, unsigned int namelen);
+unsigned int xfs_link_space_res(struct xfs_mount *mp, unsigned int namelen);
+unsigned int xfs_symlink_space_res(struct xfs_mount *mp, unsigned int namelen,
+ unsigned int fsblocks);
+unsigned int xfs_remove_space_res(struct xfs_mount *mp, unsigned int namelen);
+
+unsigned int xfs_rename_space_res(struct xfs_mount *mp,
+ unsigned int src_namelen, bool target_exists,
+ unsigned int target_namelen, bool has_whiteout);
#endif /* __XFS_TRANS_SPACE_H__ */