mirror of
https://mirrors.bfsu.edu.cn/git/linux.git
synced 2024-12-06 02:24:14 +08:00
f4288f0182
I found a race involving the larp control knob, aka the debugging knob that lets developers enable logging of extended attribute updates: Thread 1 Thread 2 echo 0 > /sys/fs/xfs/debug/larp setxattr(REPLACE) xfs_has_larp (returns false) xfs_attr_set echo 1 > /sys/fs/xfs/debug/larp xfs_attr_defer_replace xfs_attr_init_replace_state xfs_has_larp (returns true) xfs_attr_init_remove_state <oops, wrong DAS state!> This isn't a particularly severe problem right now because xattr logging is only enabled when CONFIG_XFS_DEBUG=y, and developers *should* know what they're doing. However, the eventual intent is that callers should be able to ask for the assistance of the log in persisting xattr updates. This capability might not be required for /all/ callers, which means that dynamic control must work correctly. Once an xattr update has decided whether or not to use logged xattrs, it needs to stay in that mode until the end of the operation regardless of what subsequent parallel operations might do. Therefore, it is an error to continue sampling xfs_globals.larp once xfs_attr_change has made a decision about larp, and it was not correct for me to have told Allison that ->create_intent functions can sample the global log incompat feature bitfield to decide to elide a log item. Instead, create a new op flag for the xfs_da_args structure, and convert all other callers of xfs_has_larp and xfs_sb_version_haslogxattrs within the attr update state machine to look for the operations flag. Signed-off-by: Darrick J. Wong <djwong@kernel.org> Reviewed-by: Allison Henderson <allison.henderson@oracle.com>
240 lines
9.0 KiB
C
240 lines
9.0 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
/*
|
|
* Copyright (c) 2000,2002,2005 Silicon Graphics, Inc.
|
|
* Copyright (c) 2013 Red Hat, Inc.
|
|
* All Rights Reserved.
|
|
*/
|
|
#ifndef __XFS_DA_BTREE_H__
|
|
#define __XFS_DA_BTREE_H__
|
|
|
|
struct xfs_inode;
|
|
struct xfs_trans;
|
|
|
|
/*
|
|
* Directory/attribute geometry information. There will be one of these for each
|
|
* data fork type, and it will be passed around via the xfs_da_args. Global
|
|
* structures will be attached to the xfs_mount.
|
|
*/
|
|
struct xfs_da_geometry {
|
|
unsigned int blksize; /* da block size in bytes */
|
|
unsigned int fsbcount; /* da block size in filesystem blocks */
|
|
uint8_t fsblog; /* log2 of _filesystem_ block size */
|
|
uint8_t blklog; /* log2 of da block size */
|
|
unsigned int node_hdr_size; /* danode header size in bytes */
|
|
unsigned int node_ents; /* # of entries in a danode */
|
|
unsigned int magicpct; /* 37% of block size in bytes */
|
|
xfs_dablk_t datablk; /* blockno of dir data v2 */
|
|
unsigned int leaf_hdr_size; /* dir2 leaf header size */
|
|
unsigned int leaf_max_ents; /* # of entries in dir2 leaf */
|
|
xfs_dablk_t leafblk; /* blockno of leaf data v2 */
|
|
unsigned int free_hdr_size; /* dir2 free header size */
|
|
unsigned int free_max_bests; /* # of bests entries in dir2 free */
|
|
xfs_dablk_t freeblk; /* blockno of free data v2 */
|
|
xfs_extnum_t max_extents; /* Max. extents in corresponding fork */
|
|
|
|
xfs_dir2_data_aoff_t data_first_offset;
|
|
size_t data_entry_offset;
|
|
};
|
|
|
|
/*========================================================================
|
|
* Btree searching and modification structure definitions.
|
|
*========================================================================*/
|
|
|
|
/*
|
|
* Search comparison results
|
|
*/
|
|
enum xfs_dacmp {
|
|
XFS_CMP_DIFFERENT, /* names are completely different */
|
|
XFS_CMP_EXACT, /* names are exactly the same */
|
|
XFS_CMP_CASE /* names are same but differ in case */
|
|
};
|
|
|
|
/*
|
|
* Structure to ease passing around component names.
|
|
*/
|
|
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 */
|
|
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 */
|
|
struct xfs_inode *dp; /* directory inode to manipulate */
|
|
struct xfs_trans *trans; /* current trans (changes over time) */
|
|
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 */
|
|
int index; /* index of attr of interest in blk */
|
|
xfs_dablk_t rmtblkno; /* remote attr value starting blkno */
|
|
int rmtblkcnt; /* remote attr value block count */
|
|
int rmtvaluelen; /* remote attr value length in bytes */
|
|
xfs_dablk_t blkno2; /* blkno of 2nd attr leaf of interest */
|
|
int index2; /* index of 2nd attr in blk */
|
|
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;
|
|
|
|
/*
|
|
* Operation flags:
|
|
*/
|
|
#define XFS_DA_OP_JUSTCHECK (1u << 0) /* check for ok with no space */
|
|
#define XFS_DA_OP_REPLACE (1u << 1) /* this is an atomic replace op */
|
|
#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_FLAGS \
|
|
{ XFS_DA_OP_JUSTCHECK, "JUSTCHECK" }, \
|
|
{ XFS_DA_OP_REPLACE, "REPLACE" }, \
|
|
{ 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" }
|
|
|
|
/*
|
|
* Storage for holding state during Btree searches and split/join ops.
|
|
*
|
|
* Only need space for 5 intermediate nodes. With a minimum of 62-way
|
|
* fanout to the Btree, we can support over 900 million directory blocks,
|
|
* which is slightly more than enough.
|
|
*/
|
|
typedef struct xfs_da_state_blk {
|
|
struct xfs_buf *bp; /* buffer containing block */
|
|
xfs_dablk_t blkno; /* filesystem blkno of buffer */
|
|
xfs_daddr_t disk_blkno; /* on-disk blkno (in BBs) of buffer */
|
|
int index; /* relevant index into block */
|
|
xfs_dahash_t hashval; /* last hash value in block */
|
|
int magic; /* blk's magic number, ie: blk type */
|
|
} xfs_da_state_blk_t;
|
|
|
|
typedef struct xfs_da_state_path {
|
|
int active; /* number of active levels */
|
|
xfs_da_state_blk_t blk[XFS_DA_NODE_MAXDEPTH];
|
|
} xfs_da_state_path_t;
|
|
|
|
typedef struct xfs_da_state {
|
|
xfs_da_args_t *args; /* filename arguments */
|
|
struct xfs_mount *mp; /* filesystem mount point */
|
|
xfs_da_state_path_t path; /* search/split paths */
|
|
xfs_da_state_path_t altpath; /* alternate path for join */
|
|
unsigned char inleaf; /* insert into 1->lf, 0->splf */
|
|
unsigned char extravalid; /* T/F: extrablk is in use */
|
|
unsigned char extraafter; /* T/F: extrablk is after new */
|
|
xfs_da_state_blk_t extrablk; /* for double-splits on leaves */
|
|
/* for dirv2 extrablk is data */
|
|
} xfs_da_state_t;
|
|
|
|
/*
|
|
* In-core version of the node header to abstract the differences in the v2 and
|
|
* v3 disk format of the headers. Callers need to convert to/from disk format as
|
|
* appropriate.
|
|
*/
|
|
struct xfs_da3_icnode_hdr {
|
|
uint32_t forw;
|
|
uint32_t back;
|
|
uint16_t magic;
|
|
uint16_t count;
|
|
uint16_t level;
|
|
|
|
/*
|
|
* Pointer to the on-disk format entries, which are behind the
|
|
* variable size (v4 vs v5) header in the on-disk block.
|
|
*/
|
|
struct xfs_da_node_entry *btree;
|
|
};
|
|
|
|
/*
|
|
* Utility macros to aid in logging changed structure fields.
|
|
*/
|
|
#define XFS_DA_LOGOFF(BASE, ADDR) ((char *)(ADDR) - (char *)(BASE))
|
|
#define XFS_DA_LOGRANGE(BASE, ADDR, SIZE) \
|
|
(uint)(XFS_DA_LOGOFF(BASE, ADDR)), \
|
|
(uint)(XFS_DA_LOGOFF(BASE, ADDR)+(SIZE)-1)
|
|
|
|
/*========================================================================
|
|
* Function prototypes.
|
|
*========================================================================*/
|
|
|
|
/*
|
|
* Routines used for growing the Btree.
|
|
*/
|
|
int xfs_da3_node_create(struct xfs_da_args *args, xfs_dablk_t blkno,
|
|
int level, struct xfs_buf **bpp, int whichfork);
|
|
int xfs_da3_split(xfs_da_state_t *state);
|
|
|
|
/*
|
|
* Routines used for shrinking the Btree.
|
|
*/
|
|
int xfs_da3_join(xfs_da_state_t *state);
|
|
void xfs_da3_fixhashpath(struct xfs_da_state *state,
|
|
struct xfs_da_state_path *path_to_to_fix);
|
|
|
|
/*
|
|
* Routines used for finding things in the Btree.
|
|
*/
|
|
int xfs_da3_node_lookup_int(xfs_da_state_t *state, int *result);
|
|
int xfs_da3_path_shift(xfs_da_state_t *state, xfs_da_state_path_t *path,
|
|
int forward, int release, int *result);
|
|
/*
|
|
* Utility routines.
|
|
*/
|
|
int xfs_da3_blk_link(xfs_da_state_t *state, xfs_da_state_blk_t *old_blk,
|
|
xfs_da_state_blk_t *new_blk);
|
|
int xfs_da3_node_read(struct xfs_trans *tp, struct xfs_inode *dp,
|
|
xfs_dablk_t bno, struct xfs_buf **bpp, int whichfork);
|
|
int xfs_da3_node_read_mapped(struct xfs_trans *tp, struct xfs_inode *dp,
|
|
xfs_daddr_t mappedbno, struct xfs_buf **bpp,
|
|
int whichfork);
|
|
|
|
/*
|
|
* Utility routines.
|
|
*/
|
|
|
|
#define XFS_DABUF_MAP_HOLE_OK (1u << 0)
|
|
|
|
int xfs_da_grow_inode(xfs_da_args_t *args, xfs_dablk_t *new_blkno);
|
|
int xfs_da_grow_inode_int(struct xfs_da_args *args, xfs_fileoff_t *bno,
|
|
int count);
|
|
int xfs_da_get_buf(struct xfs_trans *trans, struct xfs_inode *dp,
|
|
xfs_dablk_t bno, struct xfs_buf **bp, int whichfork);
|
|
int xfs_da_read_buf(struct xfs_trans *trans, struct xfs_inode *dp,
|
|
xfs_dablk_t bno, unsigned int flags, struct xfs_buf **bpp,
|
|
int whichfork, const struct xfs_buf_ops *ops);
|
|
int xfs_da_reada_buf(struct xfs_inode *dp, xfs_dablk_t bno,
|
|
unsigned int flags, int whichfork,
|
|
const struct xfs_buf_ops *ops);
|
|
int xfs_da_shrink_inode(xfs_da_args_t *args, xfs_dablk_t dead_blkno,
|
|
struct xfs_buf *dead_buf);
|
|
|
|
uint xfs_da_hashname(const uint8_t *name_string, int name_length);
|
|
enum xfs_dacmp xfs_da_compname(struct xfs_da_args *args,
|
|
const unsigned char *name, int len);
|
|
|
|
|
|
struct xfs_da_state *xfs_da_state_alloc(struct xfs_da_args *args);
|
|
void xfs_da_state_free(xfs_da_state_t *state);
|
|
void xfs_da_state_reset(struct xfs_da_state *state, struct xfs_da_args *args);
|
|
|
|
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);
|
|
|
|
extern struct kmem_cache *xfs_da_state_cache;
|
|
|
|
#endif /* __XFS_DA_BTREE_H__ */
|