freebsd-skq/sys/sys/bio.h

146 lines
5.3 KiB
C
Raw Normal View History

/*-
1994-05-24 10:09:53 +00:00
* Copyright (c) 1982, 1986, 1989, 1993
* The Regents of the University of California. All rights reserved.
* (c) UNIX System Laboratories, Inc.
* All or some portions of this file are derived from material licensed
* to the University of California by American Telephone and Telegraph
* Co. or Unix System Laboratories, Inc. and are reproduced herein with
* the permission of UNIX System Laboratories, Inc.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
* 4. Neither the name of the University nor the names of its contributors
* may be used to endorse or promote products derived from this software
* without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
* ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE.
*
* @(#)buf.h 8.9 (Berkeley) 3/30/95
1999-08-28 01:08:13 +00:00
* $FreeBSD$
1994-05-24 10:09:53 +00:00
*/
#ifndef _SYS_BIO_H_
#define _SYS_BIO_H_
1994-05-24 10:09:53 +00:00
#include <sys/queue.h>
/* bio_cmd */
#define BIO_READ 0x01
#define BIO_WRITE 0x02
#define BIO_DELETE 0x04
#define BIO_GETATTR 0x08
#define BIO_FLUSH 0x10
#define BIO_CMD0 0x20 /* Available for local hacks */
#define BIO_CMD1 0x40 /* Available for local hacks */
#define BIO_CMD2 0x80 /* Available for local hacks */
/* bio_flags */
#define BIO_ERROR 0x01
#define BIO_DONE 0x02
#define BIO_ONQUEUE 0x04
Correct bioq_disksort so that bioq_insert_tail() offers barrier semantic. Add the BIO_ORDERED flag for struct bio and update bio clients to use it. The barrier semantics of bioq_insert_tail() were broken in two ways: o In bioq_disksort(), an added bio could be inserted at the head of the queue, even when a barrier was present, if the sort key for the new entry was less than that of the last queued barrier bio. o The last_offset used to generate the sort key for newly queued bios did not stay at the position of the barrier until either the barrier was de-queued, or a new barrier (which updates last_offset) was queued. When a barrier is in effect, we know that the disk will pass through the barrier position just before the "blocked bios" are released, so using the barrier's offset for last_offset is the optimal choice. sys/geom/sched/subr_disk.c: sys/kern/subr_disk.c: o Update last_offset in bioq_insert_tail(). o Only update last_offset in bioq_remove() if the removed bio is at the head of the queue (typically due to a call via bioq_takefirst()) and no barrier is active. o In bioq_disksort(), if we have a barrier (insert_point is non-NULL), set prev to the barrier and cur to it's next element. Now that last_offset is kept at the barrier position, this change isn't strictly necessary, but since we have to take a decision branch anyway, it does avoid one, no-op, loop iteration in the while loop that immediately follows. o In bioq_disksort(), bypass the normal sort for bios with the BIO_ORDERED attribute and instead insert them into the queue with bioq_insert_tail(). bioq_insert_tail() not only gives the desired command order during insertion, but also provides barrier semantics so that commands disksorted in the future cannot pass the just enqueued transaction. sys/sys/bio.h: Add BIO_ORDERED as bit 4 of the bio_flags field in struct bio. sys/cam/ata/ata_da.c: sys/cam/scsi/scsi_da.c Use an ordered command for SCSI/ATA-NCQ commands issued in response to bios with the BIO_ORDERED flag set. sys/cam/scsi/scsi_da.c Use an ordered tag when issuing a synchronize cache command. Wrap some lines to 80 columns. sys/cddl/contrib/opensolaris/uts/common/fs/zfs/vdev_geom.c sys/geom/geom_io.c Mark bios with the BIO_FLUSH command as BIO_ORDERED. Sponsored by: Spectra Logic Corporation MFC after: 1 month
2010-09-02 19:40:28 +00:00
#define BIO_ORDERED 0x08
#ifdef _KERNEL
struct disk;
struct bio;
/* Empty classifier tag, to prevent further classification. */
#define BIO_NOTCLASSIFIED (void *)(~0UL)
typedef void bio_task_t(void *);
/*
* The bio structure describes an I/O operation in the kernel.
*/
struct bio {
uint8_t bio_cmd; /* I/O operation. */
uint8_t bio_flags; /* General flags. */
uint8_t bio_cflags; /* Private use by the consumer. */
uint8_t bio_pflags; /* Private use by the provider. */
struct cdev *bio_dev; /* Device to do I/O on. */
struct disk *bio_disk; /* Valid below geom_disk.c only */
off_t bio_offset; /* Offset into file. */
long bio_bcount; /* Valid bytes in buffer. */
caddr_t bio_data; /* Memory, superblocks, indirect etc. */
int bio_error; /* Errno for BIO_ERROR. */
long bio_resid; /* Remaining I/O in bytes. */
2002-03-19 20:18:42 +00:00
void (*bio_done)(struct bio *);
void *bio_driver1; /* Private use by the provider. */
void *bio_driver2; /* Private use by the provider. */
void *bio_caller1; /* Private use by the consumer. */
void *bio_caller2; /* Private use by the consumer. */
TAILQ_ENTRY(bio) bio_queue; /* Disksort queue. */
const char *bio_attribute; /* Attribute for BIO_[GS]ETATTR */
struct g_consumer *bio_from; /* GEOM linkage */
struct g_provider *bio_to; /* GEOM linkage */
off_t bio_length; /* Like bio_bcount */
off_t bio_completed; /* Inverse of bio_resid */
u_int bio_children; /* Number of spawned bios */
u_int bio_inbed; /* Children safely home by now */
struct bio *bio_parent; /* Pointer to parent */
struct bintime bio_t0; /* Time request started */
bio_task_t *bio_task; /* Task_queue handler */
void *bio_task_arg; /* Argument to above */
void *bio_classifier1; /* Classifier tag. */
void *bio_classifier2; /* Classifier tag. */
#ifdef DIAGNOSTIC
void *_bio_caller1;
void *_bio_caller2;
uint8_t _bio_cflags;
#endif
/* XXX: these go away when bio chaining is introduced */
daddr_t bio_pblkno; /* physical block number */
};
struct uio;
struct devstat;
struct bio_queue_head {
TAILQ_HEAD(bio_queue, bio) queue;
off_t last_offset;
struct bio *insert_point;
};
void biodone(struct bio *bp);
void biofinish(struct bio *bp, struct devstat *stat, int error);
int biowait(struct bio *bp, const char *wchan);
void bioq_disksort(struct bio_queue_head *ap, struct bio *bp);
struct bio *bioq_first(struct bio_queue_head *head);
struct bio *bioq_takefirst(struct bio_queue_head *head);
2003-04-01 12:49:40 +00:00
void bioq_flush(struct bio_queue_head *head, struct devstat *stp, int error);
void bioq_init(struct bio_queue_head *head);
void bioq_insert_head(struct bio_queue_head *head, struct bio *bp);
void bioq_insert_tail(struct bio_queue_head *head, struct bio *bp);
void bioq_remove(struct bio_queue_head *head, struct bio *bp);
void bio_taskqueue(struct bio *bp, bio_task_t *fund, void *arg);
int physio(struct cdev *dev, struct uio *uio, int ioflag);
#define physread physio
#define physwrite physio
The VFS/BIO subsystem contained a number of hacks in order to optimize piecemeal, middle-of-file writes for NFS. These hacks have caused no end of trouble, especially when combined with mmap(). I've removed them. Instead, NFS will issue a read-before-write to fully instantiate the struct buf containing the write. NFS does, however, optimize piecemeal appends to files. For most common file operations, you will not notice the difference. The sole remaining fragment in the VFS/BIO system is b_dirtyoff/end, which NFS uses to avoid cache coherency issues with read-merge-write style operations. NFS also optimizes the write-covers-entire-buffer case by avoiding the read-before-write. There is quite a bit of room for further optimization in these areas. The VM system marks pages fully-valid (AKA vm_page_t->valid = VM_PAGE_BITS_ALL) in several places, most noteably in vm_fault. This is not correct operation. The vm_pager_get_pages() code is now responsible for marking VM pages all-valid. A number of VM helper routines have been added to aid in zeroing-out the invalid portions of a VM page prior to the page being marked all-valid. This operation is necessary to properly support mmap(). The zeroing occurs most often when dealing with file-EOF situations. Several bugs have been fixed in the NFS subsystem, including bits handling file and directory EOF situations and buf->b_flags consistancy issues relating to clearing B_ERROR & B_INVAL, and handling B_DONE. getblk() and allocbuf() have been rewritten. B_CACHE operation is now formally defined in comments and more straightforward in implementation. B_CACHE for VMIO buffers is based on the validity of the backing store. B_CACHE for non-VMIO buffers is based simply on whether the buffer is B_INVAL or not (B_CACHE set if B_INVAL clear, and vise-versa). biodone() is now responsible for setting B_CACHE when a successful read completes. B_CACHE is also set when a bdwrite() is initiated and when a bwrite() is initiated. VFS VOP_BWRITE routines (there are only two - nfs_bwrite() and bwrite()) are now expected to set B_CACHE. This means that bowrite() and bawrite() also set B_CACHE indirectly. There are a number of places in the code which were previously using buf->b_bufsize (which is DEV_BSIZE aligned) when they should have been using buf->b_bcount. These have been fixed. getblk() now clears B_DONE on return because the rest of the system is so bad about dealing with B_DONE. Major fixes to NFS/TCP have been made. A server-side bug could cause requests to be lost by the server due to nfs_realign() overwriting other rpc's in the same TCP mbuf chain. The server's kernel must be recompiled to get the benefit of the fixes. Submitted by: Matthew Dillon <dillon@apollo.backplane.com>
1999-05-02 23:57:16 +00:00
#endif /* _KERNEL */
#endif /* !_SYS_BIO_H_ */