linux-sg2042/fs/xfs/libxfs/xfs_da_btree.h

207 lines
7.5 KiB
C
Raw Normal View History

// 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;
struct zone;
xfs: abstract the differences in dir2/dir3 via an ops vector Lots of the dir code now goes through switches to determine what is the correct on-disk format to parse. It generally involves a "xfs_sbversion_hasfoo" check, deferencing the superblock version and feature fields and hence touching several cache lines per operation in the process. Some operations do multiple checks because they nest conditional operations and they don't pass the information in a direct fashion between each other. Hence, add an ops vector to the xfs_inode structure that is configured when the inode is initialised to point to all the correct decode and encoding operations. This will significantly reduce the branchiness and cacheline footprint of the directory object decoding and encoding. This is the first patch in a series of conversion patches. It will introduce the ops structure, the setup of it and add the first operation to the vector. Subsequent patches will convert directory ops one at a time to keep the changes simple and obvious. Just this patch shows the benefit of such an approach on code size. Just converting the two shortform dir operations as this patch does decreases the built binary size by ~1500 bytes: $ size fs/xfs/xfs.o.orig fs/xfs/xfs.o.p1 text data bss dec hex filename 794490 96802 1096 892388 d9de4 fs/xfs/xfs.o.orig 792986 96802 1096 890884 d9804 fs/xfs/xfs.o.p1 $ That's a significant decrease in the instruction cache footprint of the directory code for such a simple change, and indicates that this approach is definitely worth pursuing further. Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Ben Myers <bpm@sgi.com>
2013-10-29 19:11:46 +08:00
struct xfs_dir_ops;
/*
* 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 {
int blksize; /* da block size in bytes */
int fsbcount; /* da block size in filesystem blocks */
uint8_t fsblog; /* log2 of _filesystem_ block size */
uint8_t blklog; /* log2 of da block size */
uint node_ents; /* # of entries in a danode */
int magicpct; /* 37% of block size in bytes */
xfs_dablk_t datablk; /* blockno of dir data v2 */
xfs_dablk_t leafblk; /* blockno of leaf data v2 */
xfs_dablk_t freeblk; /* blockno of free data v2 */
};
/*========================================================================
* 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 */
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 */
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: remote attribute overwrite causes transaction overrun Commit e461fcb ("xfs: remote attribute lookups require the value length") passes the remote attribute length in the xfs_da_args structure on lookup so that CRC calculations and validity checking can be performed correctly by related code. This, unfortunately has the side effect of changing the args->valuelen parameter in cases where it shouldn't. That is, when we replace a remote attribute, the incoming replacement stores the value and length in args->value and args->valuelen, but then the lookup which finds the existing remote attribute overwrites args->valuelen with the length of the remote attribute being replaced. Hence when we go to create the new attribute, we create it of the size of the existing remote attribute, not the size it is supposed to be. When the new attribute is much smaller than the old attribute, this results in a transaction overrun and an ASSERT() failure on a debug kernel: XFS: Assertion failed: tp->t_blk_res_used <= tp->t_blk_res, file: fs/xfs/xfs_trans.c, line: 331 Fix this by keeping the remote attribute value length separate to the attribute value length in the xfs_da_args structure. The enables us to pass the length of the remote attribute to be removed without overwriting the new attribute's length. Also, ensure that when we save remote block contexts for a later rename we zero the original state variables so that we don't confuse the state of the attribute to be removes with the state of the new attribute that we just added. [Spotted by Brain Foster.] Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Brian Foster <bfoster@redhat.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
2014-05-06 05:37:31 +08:00
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 */
xfs: remote attribute overwrite causes transaction overrun Commit e461fcb ("xfs: remote attribute lookups require the value length") passes the remote attribute length in the xfs_da_args structure on lookup so that CRC calculations and validity checking can be performed correctly by related code. This, unfortunately has the side effect of changing the args->valuelen parameter in cases where it shouldn't. That is, when we replace a remote attribute, the incoming replacement stores the value and length in args->value and args->valuelen, but then the lookup which finds the existing remote attribute overwrites args->valuelen with the length of the remote attribute being replaced. Hence when we go to create the new attribute, we create it of the size of the existing remote attribute, not the size it is supposed to be. When the new attribute is much smaller than the old attribute, this results in a transaction overrun and an ASSERT() failure on a debug kernel: XFS: Assertion failed: tp->t_blk_res_used <= tp->t_blk_res, file: fs/xfs/xfs_trans.c, line: 331 Fix this by keeping the remote attribute value length separate to the attribute value length in the xfs_da_args structure. The enables us to pass the length of the remote attribute to be removed without overwriting the new attribute's length. Also, ensure that when we save remote block contexts for a later rename we zero the original state variables so that we don't confuse the state of the attribute to be removes with the state of the new attribute that we just added. [Spotted by Brain Foster.] Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Brian Foster <bfoster@redhat.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
2014-05-06 05:37:31 +08:00
int rmtvaluelen2; /* remote attr value length in bytes */
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 */
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);
/*
* 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);
int xfs_da_reada_buf(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__ */