@@ -40,6 +40,7 @@ xfs-y += $(addprefix libxfs/, \
xfs_inode_fork.o \
xfs_inode_buf.o \
xfs_log_rlimit.o \
+ xfs_parent.o \
xfs_ag_resv.o \
xfs_rmap.o \
xfs_rmap_btree.o \
@@ -886,7 +886,7 @@ xfs_attr_lookup(
return error;
}
-static int
+int
xfs_attr_intent_init(
struct xfs_da_args *args,
unsigned int op_flags, /* op flag (set or remove) */
@@ -904,7 +904,7 @@ xfs_attr_intent_init(
}
/* Sets an attribute for an inode as a deferred operation */
-static int
+int
xfs_attr_defer_add(
struct xfs_da_args *args)
{
@@ -544,6 +544,7 @@ 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_defer_add(struct xfs_da_args *args);
int xfs_attr_set(struct xfs_da_args *args);
int xfs_attr_set_iter(struct xfs_attr_intent *attr);
int xfs_attr_remove_iter(struct xfs_attr_intent *attr);
@@ -552,7 +553,8 @@ bool xfs_attr_namecheck(struct xfs_mount *mp, 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);
-
+int xfs_attr_intent_init(struct xfs_da_args *args, unsigned int op_flags,
+ struct xfs_attr_intent **attr);
/*
* Check to see if the attr should be upgraded from non-existent or shortform to
* single-leaf-block attribute list.
@@ -826,16 +826,4 @@ struct xfs_parent_name_rec {
__be32 p_diroffset;
};
-/*
- * incore version of the above, also contains name pointers so callers
- * can pass/obtain all the parent pointer information in a single structure
- */
-struct xfs_parent_name_irec {
- xfs_ino_t p_ino;
- uint32_t p_gen;
- xfs_dir2_dataptr_t p_diroffset;
- const char *p_name;
- uint8_t p_namelen;
-};
-
#endif /* __XFS_DA_FORMAT_H__ */
new file mode 100644
@@ -0,0 +1,139 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2022 Oracle, Inc.
+ * 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_da_btree.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"
+
+struct kmem_cache *xfs_parent_intent_cache;
+
+/*
+ * Parent pointer attribute handling.
+ *
+ * Because the attribute value is a filename component, it will never be longer
+ * than 255 bytes. This means the attribute will always be a local format
+ * attribute as it is xfs_attr_leaf_entsize_local_max() for v5 filesystems will
+ * always be larger than this (max is 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.
+ */
+
+
+/* Initializes a xfs_parent_name_rec to be stored as an attribute name */
+void
+xfs_init_parent_name_rec(
+ struct xfs_parent_name_rec *rec,
+ struct xfs_inode *ip,
+ uint32_t p_diroffset)
+{
+ xfs_ino_t p_ino = ip->i_ino;
+ uint32_t p_gen = VFS_I(ip)->i_generation;
+
+ rec->p_ino = cpu_to_be64(p_ino);
+ rec->p_gen = cpu_to_be32(p_gen);
+ rec->p_diroffset = cpu_to_be32(p_diroffset);
+}
+
+int
+__xfs_parent_init(
+ struct xfs_mount *mp,
+ struct xfs_parent_defer **parentp)
+{
+ struct xfs_parent_defer *parent;
+ int error;
+
+ error = xfs_attr_grab_log_assist(mp);
+ if (error)
+ return error;
+
+ parent = kmem_cache_zalloc(xfs_parent_intent_cache, GFP_KERNEL);
+ if (!parent) {
+ xfs_attr_rele_log_assist(mp);
+ return -ENOMEM;
+ }
+
+ /* init parent da_args */
+ parent->args.geo = mp->m_attr_geo;
+ parent->args.whichfork = XFS_ATTR_FORK;
+ parent->args.attr_filter = XFS_ATTR_PARENT;
+ parent->args.op_flags = XFS_DA_OP_OKNOENT | XFS_DA_OP_LOGGED;
+ parent->args.name = (const uint8_t *)&parent->rec;
+ parent->args.namelen = sizeof(struct xfs_parent_name_rec);
+
+ *parentp = parent;
+ return 0;
+}
+
+int
+xfs_parent_defer_add(
+ struct xfs_trans *tp,
+ struct xfs_parent_defer *parent,
+ struct xfs_inode *dp,
+ struct xfs_name *parent_name,
+ xfs_dir2_dataptr_t diroffset,
+ struct xfs_inode *child)
+{
+ struct xfs_da_args *args = &parent->args;
+
+ xfs_init_parent_name_rec(&parent->rec, dp, diroffset);
+ args->hashval = xfs_da_hashname(args->name, args->namelen);
+
+ args->trans = tp;
+ args->dp = child;
+ if (parent_name) {
+ parent->args.value = (void *)parent_name->name;
+ parent->args.valuelen = parent_name->len;
+ }
+
+ return xfs_attr_defer_add(args);
+}
+
+void
+__xfs_parent_cancel(
+ xfs_mount_t *mp,
+ struct xfs_parent_defer *parent)
+{
+ xlog_drop_incompat_feat(mp->m_log);
+ kmem_cache_free(xfs_parent_intent_cache, parent);
+}
+
+unsigned int
+xfs_pptr_calc_space_res(
+ struct xfs_mount *mp,
+ unsigned int namelen)
+{
+ /*
+ * Pptrs 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);
+}
+
new file mode 100644
@@ -0,0 +1,57 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2022 Oracle, Inc.
+ * All Rights Reserved.
+ */
+#ifndef __XFS_PARENT_H__
+#define __XFS_PARENT_H__
+
+extern struct kmem_cache *xfs_parent_intent_cache;
+
+/*
+ * Dynamically allocd structure used to wrap the needed data to pass around
+ * the defer ops machinery
+ */
+struct xfs_parent_defer {
+ struct xfs_parent_name_rec rec;
+ struct xfs_da_args args;
+};
+
+/*
+ * Parent pointer attribute prototypes
+ */
+void xfs_init_parent_name_rec(struct xfs_parent_name_rec *rec,
+ struct xfs_inode *ip,
+ uint32_t p_diroffset);
+int __xfs_parent_init(struct xfs_mount *mp, struct xfs_parent_defer **parentp);
+
+static inline int
+xfs_parent_start(
+ struct xfs_mount *mp,
+ struct xfs_parent_defer **pp)
+{
+ *pp = NULL;
+
+ if (xfs_has_parent(mp))
+ return __xfs_parent_init(mp, pp);
+ return 0;
+}
+
+int xfs_parent_defer_add(struct xfs_trans *tp, struct xfs_parent_defer *parent,
+ struct xfs_inode *dp, struct xfs_name *parent_name,
+ xfs_dir2_dataptr_t diroffset, struct xfs_inode *child);
+void __xfs_parent_cancel(struct xfs_mount *mp, struct xfs_parent_defer *parent);
+
+static inline void
+xfs_parent_finish(
+ struct xfs_mount *mp,
+ struct xfs_parent_defer *p)
+{
+ if (p)
+ __xfs_parent_cancel(mp, p);
+}
+
+unsigned int xfs_pptr_calc_space_res(struct xfs_mount *mp,
+ unsigned int namelen);
+
+#endif /* __XFS_PARENT_H__ */
@@ -37,6 +37,8 @@
#include "xfs_reflink.h"
#include "xfs_ag.h"
#include "xfs_log_priv.h"
+#include "xfs_parent.h"
+#include "xfs_xattr.h"
struct kmem_cache *xfs_inode_cache;
@@ -946,10 +948,32 @@ xfs_bumplink(
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
}
+static 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_pptr_calc_space_res(mp, namelen);
+
+ return ret;
+}
+
+static unsigned int
+xfs_mkdir_space_res(
+ struct xfs_mount *mp,
+ unsigned int namelen)
+{
+ return xfs_create_space_res(mp, namelen);
+}
+
int
xfs_create(
struct user_namespace *mnt_userns,
- xfs_inode_t *dp,
+ struct xfs_inode *dp,
struct xfs_name *name,
umode_t mode,
dev_t rdev,
@@ -961,7 +985,7 @@ xfs_create(
struct xfs_inode *ip = NULL;
struct xfs_trans *tp = NULL;
int error;
- bool unlock_dp_on_error = false;
+ bool unlock_dp_on_error = false;
prid_t prid;
struct xfs_dquot *udqp = NULL;
struct xfs_dquot *gdqp = NULL;
@@ -969,6 +993,8 @@ xfs_create(
struct xfs_trans_res *tres;
uint resblks;
xfs_ino_t ino;
+ xfs_dir2_dataptr_t diroffset;
+ struct xfs_parent_defer *parent;
trace_xfs_create(dp, name);
@@ -988,13 +1014,17 @@ xfs_create(
return error;
if (is_dir) {
- resblks = XFS_MKDIR_SPACE_RES(mp, name->len);
+ resblks = xfs_mkdir_space_res(mp, name->len);
tres = &M_RES(mp)->tr_mkdir;
} else {
- resblks = XFS_CREATE_SPACE_RES(mp, name->len);
+ resblks = xfs_create_space_res(mp, name->len);
tres = &M_RES(mp)->tr_create;
}
+ error = xfs_parent_start(mp, &parent);
+ if (error)
+ goto out_release_dquots;
+
/*
* Initially assume that the file does not exist and
* reserve the resources for that case. If that is not
@@ -1010,7 +1040,7 @@ xfs_create(
resblks, &tp);
}
if (error)
- goto out_release_dquots;
+ goto out_parent;
xfs_ilock(dp, XFS_ILOCK_EXCL | XFS_ILOCK_PARENT);
unlock_dp_on_error = true;
@@ -1020,6 +1050,7 @@ xfs_create(
* entry pointing to them, but a directory also the "." entry
* pointing to itself.
*/
+ init_xattrs = init_xattrs || xfs_has_parent(mp);
error = xfs_dialloc(&tp, dp->i_ino, mode, &ino);
if (!error)
error = xfs_init_new_inode(mnt_userns, tp, dp, ino, mode,
@@ -1034,11 +1065,11 @@ xfs_create(
* the transaction cancel unlocking dp so don't do it explicitly in the
* error path.
*/
- xfs_trans_ijoin(tp, dp, XFS_ILOCK_EXCL);
- unlock_dp_on_error = false;
+ xfs_trans_ijoin(tp, dp, 0);
error = xfs_dir_createname(tp, dp, name, ip->i_ino,
- resblks - XFS_IALLOC_SPACE_RES(mp), NULL);
+ resblks - XFS_IALLOC_SPACE_RES(mp),
+ &diroffset);
if (error) {
ASSERT(error != -ENOSPC);
goto out_trans_cancel;
@@ -1054,6 +1085,17 @@ xfs_create(
xfs_bumplink(tp, dp);
}
+ /*
+ * If we have parent pointers, we need to add the attribute containing
+ * the parent information now.
+ */
+ if (parent) {
+ error = xfs_parent_defer_add(tp, parent, dp, name, diroffset,
+ ip);
+ if (error)
+ goto out_trans_cancel;
+ }
+
/*
* If this is a synchronous mount, make sure that the
* create transaction goes to disk before returning to
@@ -1079,6 +1121,8 @@ xfs_create(
*ipp = ip;
xfs_iunlock(ip, XFS_ILOCK_EXCL);
+ xfs_iunlock(dp, XFS_ILOCK_EXCL);
+ xfs_parent_finish(mp, parent);
return 0;
out_trans_cancel:
@@ -1090,10 +1134,12 @@ xfs_create(
* transactions and deadlocks from xfs_inactive.
*/
if (ip) {
+ xfs_iunlock(ip, XFS_ILOCK_EXCL);
xfs_finish_inode_setup(ip);
xfs_irele(ip);
- xfs_iunlock(ip, XFS_ILOCK_EXCL);
}
+ out_parent:
+ xfs_parent_finish(mp, parent);
out_release_dquots:
xfs_qm_dqrele(udqp);
xfs_qm_dqrele(gdqp);
@@ -41,6 +41,7 @@
#include "xfs_attr_item.h"
#include "xfs_xattr.h"
#include "xfs_iunlink_item.h"
+#include "xfs_parent.h"
#include <linux/magic.h>
#include <linux/fs_context.h>
@@ -2115,8 +2116,16 @@ xfs_init_caches(void)
if (!xfs_iunlink_cache)
goto out_destroy_attri_cache;
+ xfs_parent_intent_cache = kmem_cache_create("xfs_parent_intent",
+ sizeof(struct xfs_parent_defer),
+ 0, 0, NULL);
+ if (!xfs_parent_intent_cache)
+ goto out_destroy_iul_cache;
+
return 0;
+ out_destroy_iul_cache:
+ kmem_cache_destroy(xfs_iunlink_cache);
out_destroy_attri_cache:
kmem_cache_destroy(xfs_attri_cache);
out_destroy_attrd_cache:
@@ -2171,6 +2180,7 @@ xfs_destroy_caches(void)
* destroy caches.
*/
rcu_barrier();
+ kmem_cache_destroy(xfs_parent_intent_cache);
kmem_cache_destroy(xfs_iunlink_cache);
kmem_cache_destroy(xfs_attri_cache);
kmem_cache_destroy(xfs_attrd_cache);
@@ -27,7 +27,7 @@
* they must release the permission by calling xlog_drop_incompat_feat
* when they're done.
*/
-static inline int
+int
xfs_attr_grab_log_assist(
struct xfs_mount *mp)
{
@@ -61,7 +61,7 @@ xfs_attr_grab_log_assist(
return error;
}
-static inline void
+void
xfs_attr_rele_log_assist(
struct xfs_mount *mp)
{
@@ -7,6 +7,8 @@
#define __XFS_XATTR_H__
int xfs_attr_change(struct xfs_da_args *args);
+int xfs_attr_grab_log_assist(struct xfs_mount *mp);
+void xfs_attr_rele_log_assist(struct xfs_mount *mp);
extern const struct xattr_handler *xfs_xattr_handlers[];