OpenCloudOS-Kernel/fs/xfs/xfs_da_btree.h

337 lines
12 KiB
C
Raw Normal View History

/*
* Copyright (c) 2000,2002,2005 Silicon Graphics, Inc.
* Copyright (c) 2013 Red Hat, Inc.
* All Rights Reserved.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License as
* published by the Free Software Foundation.
*
* This program is distributed in the hope that it would be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write the Free Software Foundation,
* Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
*/
#ifndef __XFS_DA_BTREE_H__
#define __XFS_DA_BTREE_H__
struct xfs_bmap_free;
struct xfs_inode;
struct xfs_trans;
struct zone;
/*========================================================================
* Directory Structure when greater than XFS_LBSIZE(mp) bytes.
*========================================================================*/
/*
* This structure is common to both leaf nodes and non-leaf nodes in the Btree.
*
* It is used to manage a doubly linked list of all blocks at the same
* level in the Btree, and to identify which type of block this is.
*/
#define XFS_DA_NODE_MAGIC 0xfebe /* magic number: non-leaf blocks */
#define XFS_ATTR_LEAF_MAGIC 0xfbee /* magic number: attribute leaf blks */
#define XFS_DIR2_LEAF1_MAGIC 0xd2f1 /* magic number: v2 dirlf single blks */
#define XFS_DIR2_LEAFN_MAGIC 0xd2ff /* magic number: v2 dirlf multi blks */
typedef struct xfs_da_blkinfo {
__be32 forw; /* previous block in list */
__be32 back; /* following block in list */
__be16 magic; /* validity check on block */
__be16 pad; /* unused */
} xfs_da_blkinfo_t;
/*
* CRC enabled directory structure types
*
* The headers change size for the additional verification information, but
* otherwise the tree layouts and contents are unchanged. Hence the da btree
* code can use the struct xfs_da_blkinfo for manipulating the tree links and
* magic numbers without modification for both v2 and v3 nodes.
*/
#define XFS_DA3_NODE_MAGIC 0x3ebe /* magic number: non-leaf blocks */
#define XFS_ATTR3_LEAF_MAGIC 0x3bee /* magic number: attribute leaf blks */
#define XFS_DIR3_LEAF1_MAGIC 0x3df1 /* magic number: v2 dirlf single blks */
#define XFS_DIR3_LEAFN_MAGIC 0x3dff /* magic number: v2 dirlf multi blks */
struct xfs_da3_blkinfo {
/*
* the node link manipulation code relies on the fact that the first
* element of this structure is the struct xfs_da_blkinfo so it can
* ignore the differences in the rest of the structures.
*/
struct xfs_da_blkinfo hdr;
__be32 crc; /* CRC of block */
__be64 blkno; /* first block of the buffer */
__be64 lsn; /* sequence number of last write */
uuid_t uuid; /* filesystem we belong to */
__be64 owner; /* inode that owns the block */
};
/*
* This is the structure of the root and intermediate nodes in the Btree.
* The leaf nodes are defined above.
*
* Entries are not packed.
*
* Since we have duplicate keys, use a binary search but always follow
* all match in the block, not just the first match found.
*/
#define XFS_DA_NODE_MAXDEPTH 5 /* max depth of Btree */
typedef struct xfs_da_node_hdr {
struct xfs_da_blkinfo info; /* block type, links, etc. */
__be16 __count; /* count of active entries */
__be16 __level; /* level above leaves (leaf == 0) */
} xfs_da_node_hdr_t;
struct xfs_da3_node_hdr {
struct xfs_da3_blkinfo info; /* block type, links, etc. */
__be16 __count; /* count of active entries */
__be16 __level; /* level above leaves (leaf == 0) */
__be32 __pad32;
};
#define XFS_DA3_NODE_CRC_OFF (offsetof(struct xfs_da3_node_hdr, info.crc))
typedef struct xfs_da_node_entry {
__be32 hashval; /* hash value for this descendant */
__be32 before; /* Btree block before this key */
} xfs_da_node_entry_t;
typedef struct xfs_da_intnode {
struct xfs_da_node_hdr hdr;
struct xfs_da_node_entry __btree[];
} xfs_da_intnode_t;
struct xfs_da3_intnode {
struct xfs_da3_node_hdr hdr;
struct xfs_da_node_entry __btree[];
};
/*
* 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;
};
extern void xfs_da3_node_hdr_from_disk(struct xfs_da3_icnode_hdr *to,
struct xfs_da_intnode *from);
extern void xfs_da3_node_hdr_to_disk(struct xfs_da_intnode *to,
struct xfs_da3_icnode_hdr *from);
static inline int
xfs_da3_node_hdr_size(struct xfs_da_intnode *dap)
{
if (dap->hdr.info.magic == cpu_to_be16(XFS_DA3_NODE_MAGIC))
return sizeof(struct xfs_da3_node_hdr);
return sizeof(struct xfs_da_node_hdr);
}
static inline struct xfs_da_node_entry *
xfs_da3_node_tree_p(struct xfs_da_intnode *dap)
{
if (dap->hdr.info.magic == cpu_to_be16(XFS_DA3_NODE_MAGIC)) {
struct xfs_da3_intnode *dap3 = (struct xfs_da3_intnode *)dap;
return dap3->__btree;
}
return dap->__btree;
}
extern void xfs_da3_intnode_from_disk(struct xfs_da3_icnode_hdr *to,
struct xfs_da_intnode *from);
extern void xfs_da3_intnode_to_disk(struct xfs_da_intnode *to,
struct xfs_da3_icnode_hdr *from);
#define XFS_LBSIZE(mp) (mp)->m_sb.sb_blocksize
/*========================================================================
* 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 {
const __uint8_t *name; /* string (maybe not NULL terminated) */
int namelen; /* length of string (maybe no NULL) */
__uint8_t *value; /* set of bytes (maybe contain NULLs) */
int valuelen; /* length of value */
int flags; /* argument flags (eg: ATTR_NOCREATE) */
xfs_dahash_t hashval; /* hash value of name */
xfs_ino_t inumber; /* input/output inode number */
struct xfs_inode *dp; /* directory inode to manipulate */
xfs_fsblock_t *firstblock; /* ptr to firstblock for bmap calls */
struct xfs_bmap_free *flist; /* ptr to freelist for bmap_finish */
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 */
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 op_flags; /* operation flags */
enum xfs_dacmp cmpresult; /* name compare result for lookups */
} xfs_da_args_t;
/*
* Operation flags:
*/
#define XFS_DA_OP_JUSTCHECK 0x0001 /* check for ok with no space */
#define XFS_DA_OP_RENAME 0x0002 /* this is an atomic rename op */
#define XFS_DA_OP_ADDNAME 0x0004 /* this is an add operation */
#define XFS_DA_OP_OKNOENT 0x0008 /* lookup/add op, ENOENT ok, else die */
#define XFS_DA_OP_CILOOKUP 0x0010 /* lookup to return CI name if found */
xfs: event tracing support Convert the old xfs tracing support that could only be used with the out of tree kdb and xfsidbg patches to use the generic event tracer. To use it make sure CONFIG_EVENT_TRACING is enabled and then enable all xfs trace channels by: echo 1 > /sys/kernel/debug/tracing/events/xfs/enable or alternatively enable single events by just doing the same in one event subdirectory, e.g. echo 1 > /sys/kernel/debug/tracing/events/xfs/xfs_ihold/enable or set more complex filters, etc. In Documentation/trace/events.txt all this is desctribed in more detail. To reads the events do a cat /sys/kernel/debug/tracing/trace Compared to the last posting this patch converts the tracing mostly to the one tracepoint per callsite model that other users of the new tracing facility also employ. This allows a very fine-grained control of the tracing, a cleaner output of the traces and also enables the perf tool to use each tracepoint as a virtual performance counter, allowing us to e.g. count how often certain workloads git various spots in XFS. Take a look at http://lwn.net/Articles/346470/ for some examples. Also the btree tracing isn't included at all yet, as it will require additional core tracing features not in mainline yet, I plan to deliver it later. And the really nice thing about this patch is that it actually removes many lines of code while adding this nice functionality: fs/xfs/Makefile | 8 fs/xfs/linux-2.6/xfs_acl.c | 1 fs/xfs/linux-2.6/xfs_aops.c | 52 - fs/xfs/linux-2.6/xfs_aops.h | 2 fs/xfs/linux-2.6/xfs_buf.c | 117 +-- fs/xfs/linux-2.6/xfs_buf.h | 33 fs/xfs/linux-2.6/xfs_fs_subr.c | 3 fs/xfs/linux-2.6/xfs_ioctl.c | 1 fs/xfs/linux-2.6/xfs_ioctl32.c | 1 fs/xfs/linux-2.6/xfs_iops.c | 1 fs/xfs/linux-2.6/xfs_linux.h | 1 fs/xfs/linux-2.6/xfs_lrw.c | 87 -- fs/xfs/linux-2.6/xfs_lrw.h | 45 - fs/xfs/linux-2.6/xfs_super.c | 104 --- fs/xfs/linux-2.6/xfs_super.h | 7 fs/xfs/linux-2.6/xfs_sync.c | 1 fs/xfs/linux-2.6/xfs_trace.c | 75 ++ fs/xfs/linux-2.6/xfs_trace.h | 1369 +++++++++++++++++++++++++++++++++++++++++ fs/xfs/linux-2.6/xfs_vnode.h | 4 fs/xfs/quota/xfs_dquot.c | 110 --- fs/xfs/quota/xfs_dquot.h | 21 fs/xfs/quota/xfs_qm.c | 40 - fs/xfs/quota/xfs_qm_syscalls.c | 4 fs/xfs/support/ktrace.c | 323 --------- fs/xfs/support/ktrace.h | 85 -- fs/xfs/xfs.h | 16 fs/xfs/xfs_ag.h | 14 fs/xfs/xfs_alloc.c | 230 +----- fs/xfs/xfs_alloc.h | 27 fs/xfs/xfs_alloc_btree.c | 1 fs/xfs/xfs_attr.c | 107 --- fs/xfs/xfs_attr.h | 10 fs/xfs/xfs_attr_leaf.c | 14 fs/xfs/xfs_attr_sf.h | 40 - fs/xfs/xfs_bmap.c | 507 +++------------ fs/xfs/xfs_bmap.h | 49 - fs/xfs/xfs_bmap_btree.c | 6 fs/xfs/xfs_btree.c | 5 fs/xfs/xfs_btree_trace.h | 17 fs/xfs/xfs_buf_item.c | 87 -- fs/xfs/xfs_buf_item.h | 20 fs/xfs/xfs_da_btree.c | 3 fs/xfs/xfs_da_btree.h | 7 fs/xfs/xfs_dfrag.c | 2 fs/xfs/xfs_dir2.c | 8 fs/xfs/xfs_dir2_block.c | 20 fs/xfs/xfs_dir2_leaf.c | 21 fs/xfs/xfs_dir2_node.c | 27 fs/xfs/xfs_dir2_sf.c | 26 fs/xfs/xfs_dir2_trace.c | 216 ------ fs/xfs/xfs_dir2_trace.h | 72 -- fs/xfs/xfs_filestream.c | 8 fs/xfs/xfs_fsops.c | 2 fs/xfs/xfs_iget.c | 111 --- fs/xfs/xfs_inode.c | 67 -- fs/xfs/xfs_inode.h | 76 -- fs/xfs/xfs_inode_item.c | 5 fs/xfs/xfs_iomap.c | 85 -- fs/xfs/xfs_iomap.h | 8 fs/xfs/xfs_log.c | 181 +---- fs/xfs/xfs_log_priv.h | 20 fs/xfs/xfs_log_recover.c | 1 fs/xfs/xfs_mount.c | 2 fs/xfs/xfs_quota.h | 8 fs/xfs/xfs_rename.c | 1 fs/xfs/xfs_rtalloc.c | 1 fs/xfs/xfs_rw.c | 3 fs/xfs/xfs_trans.h | 47 + fs/xfs/xfs_trans_buf.c | 62 - fs/xfs/xfs_vnodeops.c | 8 70 files changed, 2151 insertions(+), 2592 deletions(-) Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Alex Elder <aelder@sgi.com>
2009-12-15 07:14:59 +08:00
#define XFS_DA_OP_FLAGS \
{ XFS_DA_OP_JUSTCHECK, "JUSTCHECK" }, \
{ XFS_DA_OP_RENAME, "RENAME" }, \
{ XFS_DA_OP_ADDNAME, "ADDNAME" }, \
{ XFS_DA_OP_OKNOENT, "OKNOENT" }, \
{ XFS_DA_OP_CILOOKUP, "CILOOKUP" }
/*
* 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 */
unsigned int blocksize; /* logical block size */
unsigned int node_ents; /* how many entries in danode */
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;
/*
* 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)
/*
* Name ops for directory and/or attr name operations
*/
struct xfs_nameops {
xfs_dahash_t (*hashname)(struct xfs_name *);
enum xfs_dacmp (*compname)(struct xfs_da_args *,
const unsigned char *, int);
};
/*========================================================================
* 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, xfs_daddr_t mappedbno,
struct xfs_buf **bpp, int which_fork);
extern const struct xfs_buf_ops xfs_da3_node_buf_ops;
/*
* Utility routines.
*/
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, xfs_daddr_t mappedbno,
struct xfs_buf **bp, int whichfork);
int xfs_da_read_buf(struct xfs_trans *trans, struct xfs_inode *dp,
xfs_dablk_t bno, xfs_daddr_t mappedbno,
struct xfs_buf **bpp, int whichfork,
const struct xfs_buf_ops *ops);
xfs_daddr_t xfs_da_reada_buf(struct xfs_trans *trans, struct xfs_inode *dp,
xfs_dablk_t bno, xfs_daddr_t mapped_bno,
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);
xfs_da_state_t *xfs_da_state_alloc(void);
void xfs_da_state_free(xfs_da_state_t *state);
extern struct kmem_zone *xfs_da_state_zone;
extern const struct xfs_nameops xfs_default_nameops;
#endif /* __XFS_DA_BTREE_H__ */