xfs: Set up infrastructure for log attribute replay

Currently attributes are modified directly across one or more
transactions. But they are not logged or replayed in the event of an
error. The goal of log attr replay is to enable logging and replaying
of attribute operations using the existing delayed operations
infrastructure.  This will later enable the attributes to become part of
larger multi part operations that also must first be recorded to the
log.  This is mostly of interest in the scheme of parent pointers which
would need to maintain an attribute containing parent inode information
any time an inode is moved, created, or removed.  Parent pointers would
then be of interest to any feature that would need to quickly derive an
inode path from the mount point. Online scrub, nfs lookups and fs grow
or shrink operations are all features that could take advantage of this.

This patch adds two new log item types for setting or removing
attributes as deferred operations.  The xfs_attri_log_item will log an
intent to set or remove an attribute.  The corresponding
xfs_attrd_log_item holds a reference to the xfs_attri_log_item and is
freed once the transaction is done.  Both log items use a generic
xfs_attr_log_format structure that contains the attribute name, value,
flags, inode, and an op_flag that indicates if the operations is a set
or remove.

[dchinner: added extra little bits needed for intent whiteouts]
Signed-off-by: Allison Henderson <allison.henderson@oracle.com>
Reviewed-by: Chandan Babu R <chandanrlinux@gmail.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Dave Chinner <david@fromorbit.com>

fs/xfs/Makefile

@@ -102,6 +102,7 @@ xfs-y				+= xfs_log.o \
 				   xfs_buf_item_recover.o \
 				   xfs_dquot_item_recover.o \
 				   xfs_extfree_item.o \
+				   xfs_attr_item.o \
 				   xfs_icreate_item.o \
 				   xfs_inode_item.o \
 				   xfs_inode_item_recover.o \

fs/xfs/libxfs/xfs_attr.c

@@ -24,6 +24,10 @@
 #include "xfs_quota.h"
 #include "xfs_trans_space.h"
 #include "xfs_trace.h"
+#include "xfs_attr_item.h"
+
+struct kmem_cache		*xfs_attri_cache;
+struct kmem_cache		*xfs_attrd_cache;
 
 /*
  * xfs_attr.c
@@ -61,8 +65,6 @@ STATIC int xfs_attr_node_hasname(xfs_da_args_t *args,
 				 struct xfs_da_state **state);
 STATIC int xfs_attr_fillstate(xfs_da_state_t *state);
 STATIC int xfs_attr_refillstate(xfs_da_state_t *state);
-STATIC int xfs_attr_set_iter(struct xfs_delattr_context *dac,
-			     struct xfs_buf **leaf_bp);
 STATIC int xfs_attr_node_removename(struct xfs_da_args *args,
 				    struct xfs_da_state *state);
 
@@ -166,7 +168,7 @@ xfs_attr_get(
 /*
  * Calculate how many blocks we need for the new attribute,
  */
-STATIC int
+int
 xfs_attr_calc_size(
 	struct xfs_da_args	*args,
 	int			*local)
@@ -840,6 +842,40 @@ xfs_attr_set(
 	goto out_unlock;
 }
 
+int __init
+xfs_attri_init_cache(void)
+{
+	xfs_attri_cache = kmem_cache_create("xfs_attri",
+					    sizeof(struct xfs_attri_log_item),
+					    0, 0, NULL);
+
+	return xfs_attri_cache != NULL ? 0 : -ENOMEM;
+}
+
+void
+xfs_attri_destroy_cache(void)
+{
+	kmem_cache_destroy(xfs_attri_cache);
+	xfs_attri_cache = NULL;
+}
+
+int __init
+xfs_attrd_init_cache(void)
+{
+	xfs_attrd_cache = kmem_cache_create("xfs_attrd",
+					    sizeof(struct xfs_attrd_log_item),
+					    0, 0, NULL);
+
+	return xfs_attrd_cache != NULL ? 0 : -ENOMEM;
+}
+
+void
+xfs_attrd_destroy_cache(void)
+{
+	kmem_cache_destroy(xfs_attrd_cache);
+	xfs_attrd_cache = NULL;
+}
+
 /*========================================================================
  * External routines when attribute list is inside the inode
  *========================================================================*/

fs/xfs/libxfs/xfs_attr.h

@@ -28,6 +28,11 @@ struct xfs_attr_list_context;
  */
 #define	ATTR_MAX_VALUELEN	(64*1024)	/* max length of a value */
 
+static inline bool xfs_has_larp(struct xfs_mount *mp)
+{
+	return false;
+}
+
 /*
  * Kernel-internal version of the attrlist cursor.
  */
@@ -461,6 +466,11 @@ enum xfs_delattr_state {
 struct xfs_delattr_context {
 	struct xfs_da_args      *da_args;
 
+	/*
+	 * Used by xfs_attr_set to hold a leaf buffer across a transaction roll
+	 */
+	struct xfs_buf		*leaf_bp;
+
 	/* Used in xfs_attr_rmtval_set_blk to roll through allocating blocks */
 	struct xfs_bmbt_irec	map;
 	xfs_dablk_t		lblkno;
@@ -474,6 +484,23 @@ struct xfs_delattr_context {
 	enum xfs_delattr_state  dela_state;
 };
 
+/*
+ * List of attrs to commit later.
+ */
+struct xfs_attr_item {
+	struct xfs_delattr_context	xattri_dac;
+
+	/*
+	 * Indicates if the attr operation is a set or a remove
+	 * XFS_ATTR_OP_FLAGS_{SET,REMOVE}
+	 */
+	unsigned int			xattri_op_flags;
+
+	/* used to log this item to an intent */
+	struct list_head		xattri_list;
+};
+
+
 /*========================================================================
  * Function prototypes for the kernel.
  *========================================================================*/
@@ -490,10 +517,21 @@ 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);
 int xfs_attr_set_args(struct xfs_da_args *args);
+int xfs_attr_set_iter(struct xfs_delattr_context *dac,
+		      struct xfs_buf **leaf_bp);
 int xfs_attr_remove_args(struct xfs_da_args *args);
 int xfs_attr_remove_iter(struct xfs_delattr_context *dac);
 bool xfs_attr_namecheck(const void *name, size_t length);
 void xfs_delattr_context_init(struct xfs_delattr_context *dac,
 			      struct xfs_da_args *args);
+int xfs_attr_calc_size(struct xfs_da_args *args, int *local);
+
+extern struct kmem_cache	*xfs_attri_cache;
+extern struct kmem_cache	*xfs_attrd_cache;
+
+int __init xfs_attri_init_cache(void);
+void xfs_attri_destroy_cache(void);
+int __init xfs_attrd_init_cache(void);
+void xfs_attrd_destroy_cache(void);
 
 #endif	/* __XFS_ATTR_H__ */

fs/xfs/libxfs/xfs_defer.c

@@ -23,6 +23,7 @@
 #include "xfs_bmap.h"
 #include "xfs_alloc.h"
 #include "xfs_buf.h"
+#include "xfs_attr.h"
 
 static struct kmem_cache	*xfs_defer_pending_cache;
 
@@ -869,7 +870,12 @@ xfs_defer_init_item_caches(void)
 	error = xfs_extfree_intent_init_cache();
 	if (error)
 		goto err;
-
+	error = xfs_attri_init_cache();
+	if (error)
+		goto err;
+	error = xfs_attrd_init_cache();
+	if (error)
+		goto err;
 	return 0;
 err:
 	xfs_defer_destroy_item_caches();
@@ -880,6 +886,8 @@ xfs_defer_init_item_caches(void)
 void
 xfs_defer_destroy_item_caches(void)
 {
+	xfs_attri_destroy_cache();
+	xfs_attrd_destroy_cache();
 	xfs_extfree_intent_destroy_cache();
 	xfs_bmap_intent_destroy_cache();
 	xfs_refcount_intent_destroy_cache();

fs/xfs/libxfs/xfs_defer.h

@@ -63,6 +63,8 @@ extern const struct xfs_defer_op_type xfs_refcount_update_defer_type;
 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;
+
 
 /*
  * Deferred operation item relogging limits.

fs/xfs/libxfs/xfs_log_format.h

@@ -113,7 +113,12 @@ struct xfs_unmount_log_format {
 #define XLOG_REG_TYPE_CUD_FORMAT	24
 #define XLOG_REG_TYPE_BUI_FORMAT	25
 #define XLOG_REG_TYPE_BUD_FORMAT	26
-#define XLOG_REG_TYPE_MAX		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_VALUE	30
+#define XLOG_REG_TYPE_MAX		30
+
 
 /*
  * Flags to log operation header
@@ -236,6 +241,8 @@ typedef struct xfs_trans_header {
 #define	XFS_LI_CUD		0x1243
 #define	XFS_LI_BUI		0x1244	/* bmbt update intent */
 #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_TYPE_DESC \
 	{ XFS_LI_EFI,		"XFS_LI_EFI" }, \
@@ -251,7 +258,9 @@ typedef struct xfs_trans_header {
 	{ XFS_LI_CUI,		"XFS_LI_CUI" }, \
 	{ XFS_LI_CUD,		"XFS_LI_CUD" }, \
 	{ XFS_LI_BUI,		"XFS_LI_BUI" }, \
-	{ XFS_LI_BUD,		"XFS_LI_BUD" }
+	{ XFS_LI_BUD,		"XFS_LI_BUD" }, \
+	{ XFS_LI_ATTRI,		"XFS_LI_ATTRI" }, \
+	{ XFS_LI_ATTRD,		"XFS_LI_ATTRD" }
 
 /*
  * Inode Log Item Format definitions.
@@ -893,4 +902,35 @@ struct xfs_icreate_log {
 	__be32		icl_gen;	/* inode generation number to use */
 };
 
+/*
+ * Flags for deferred attribute operations.
+ * Upper bits are flags, lower byte is type code
+ */
+#define XFS_ATTR_OP_FLAGS_SET		1	/* Set the attribute */
+#define XFS_ATTR_OP_FLAGS_REMOVE	2	/* Remove the attribute */
+#define XFS_ATTR_OP_FLAGS_TYPE_MASK	0xFF	/* Flags type mask */
+
+/*
+ * This is the structure used to lay out an attr log item in the
+ * 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 */
+	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 */
+	uint32_t	alfi_value_len;	/* attr value length */
+	uint32_t	alfi_attr_flags;/* attr flags */
+};
+
+struct xfs_attrd_log_format {
+	uint16_t	alfd_type;	/* attrd log item type */
+	uint16_t	alfd_size;	/* size of this item */
+	uint32_t	__pad;		/* pad to 64 bit aligned */
+	uint64_t	alfd_alf_id;	/* id of corresponding attri */
+};
+
 #endif /* __XFS_LOG_FORMAT_H__ */

fs/xfs/libxfs/xfs_log_recover.h

@@ -72,6 +72,8 @@ extern const struct xlog_recover_item_ops xlog_rui_item_ops;
 extern const struct xlog_recover_item_ops xlog_rud_item_ops;
 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;
 
 /*
  * Macros, structures, prototypes for internal log manager use.

fs/xfs/scrub/common.c

@@ -23,6 +23,8 @@
 #include "xfs_rmap_btree.h"
 #include "xfs_log.h"
 #include "xfs_trans_priv.h"
+#include "xfs_da_format.h"
+#include "xfs_da_btree.h"
 #include "xfs_attr.h"
 #include "xfs_reflink.h"
 #include "xfs_ag.h"

fs/xfs/xfs_attr_item.h

+/* SPDX-License-Identifier: GPL-2.0-or-later
+ *
+ * Copyright (C) 2022 Oracle.  All Rights Reserved.
+ * Author: Allison Henderson <allison.henderson@oracle.com>
+ */
+#ifndef	__XFS_ATTR_ITEM_H__
+#define	__XFS_ATTR_ITEM_H__
+
+/* kernel only ATTRI/ATTRD definitions */
+
+struct xfs_mount;
+struct kmem_zone;
+
+/*
+ * This is the "attr intention" log item.  It is used to log the fact that some
+ * extended attribute operations need to be processed.  An operation is
+ * currently either a set or remove.  Set or remove operations are described by
+ * the xfs_attr_item which may be logged to this intent.
+ *
+ * During a normal attr operation, name and value point to the name and value
+ * fields of the caller's xfs_da_args structure.  During a recovery, the name
+ * and value buffers are copied from the log, and stored in a trailing buffer
+ * attached to the xfs_attr_item until they are committed.  They are freed when
+ * the xfs_attr_item itself is freed when the work is done.
+ */
+struct xfs_attri_log_item {
+	struct xfs_log_item		attri_item;
+	atomic_t			attri_refcount;
+	int				attri_name_len;
+	int				attri_value_len;
+	void				*attri_name;
+	void				*attri_value;
+	struct xfs_attri_log_format	attri_format;
+};
+
+/*
+ * This is the "attr done" log item.  It is used to log the fact that some attrs
+ * earlier mentioned in an attri item have been freed.
+ */
+struct xfs_attrd_log_item {
+	struct xfs_log_item		attrd_item;
+	struct xfs_attri_log_item	*attrd_attrip;
+	struct xfs_attrd_log_format	attrd_format;
+};
+
+#endif	/* __XFS_ATTR_ITEM_H__ */

fs/xfs/xfs_attr_list.c

@@ -15,6 +15,7 @@
 #include "xfs_inode.h"
 #include "xfs_trans.h"
 #include "xfs_bmap.h"
+#include "xfs_da_btree.h"
 #include "xfs_attr.h"
 #include "xfs_attr_sf.h"
 #include "xfs_attr_leaf.h"

fs/xfs/xfs_ioctl32.c

@@ -17,6 +17,8 @@
 #include "xfs_itable.h"
 #include "xfs_fsops.h"
 #include "xfs_rtalloc.h"
+#include "xfs_da_format.h"
+#include "xfs_da_btree.h"
 #include "xfs_attr.h"
 #include "xfs_ioctl.h"
 #include "xfs_ioctl32.h"

fs/xfs/xfs_iops.c

@@ -13,6 +13,8 @@
 #include "xfs_inode.h"
 #include "xfs_acl.h"
 #include "xfs_quota.h"
+#include "xfs_da_format.h"
+#include "xfs_da_btree.h"
 #include "xfs_attr.h"
 #include "xfs_trans.h"
 #include "xfs_trace.h"

fs/xfs/xfs_log_recover.c

@@ -1800,6 +1800,8 @@ static const struct xlog_recover_item_ops *xlog_recover_item_ops[] = {
 	&xlog_cud_item_ops,
 	&xlog_bui_item_ops,
 	&xlog_bud_item_ops,
+	&xlog_attri_item_ops,
+	&xlog_attrd_item_ops,
 };
 
 static const struct xlog_recover_item_ops *

fs/xfs/xfs_ondisk.h

@@ -132,6 +132,8 @@ xfs_check_ondisk_structs(void)
 	XFS_CHECK_STRUCT_SIZE(struct xfs_inode_log_format,	56);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_qoff_logformat,	20);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_trans_header,		16);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_attri_log_format,	40);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_attrd_log_format,	16);
 
 	/*
 	 * The v5 superblock format extended several v4 header structures with