2008-12-05 03:52:44 +08:00
|
|
|
/*
|
|
|
|
* Virtio Block Device
|
|
|
|
*
|
|
|
|
* Copyright IBM, Corp. 2007
|
|
|
|
*
|
|
|
|
* Authors:
|
|
|
|
* Anthony Liguori <aliguori@us.ibm.com>
|
|
|
|
*
|
|
|
|
* This work is licensed under the terms of the GNU GPL, version 2. See
|
|
|
|
* the COPYING file in the top-level directory.
|
|
|
|
*
|
|
|
|
*/
|
|
|
|
|
|
|
|
#ifndef _QEMU_VIRTIO_BLK_H
|
|
|
|
#define _QEMU_VIRTIO_BLK_H
|
|
|
|
|
2013-02-06 00:06:20 +08:00
|
|
|
#include "hw/virtio/virtio.h"
|
|
|
|
#include "hw/block/block.h"
|
2014-03-03 18:30:08 +08:00
|
|
|
#include "sysemu/iothread.h"
|
2014-06-11 12:11:42 +08:00
|
|
|
#include "block/block.h"
|
2008-12-05 03:52:44 +08:00
|
|
|
|
2013-04-09 18:04:48 +08:00
|
|
|
#define TYPE_VIRTIO_BLK "virtio-blk-device"
|
2013-03-19 00:37:22 +08:00
|
|
|
#define VIRTIO_BLK(obj) \
|
|
|
|
OBJECT_CHECK(VirtIOBlock, (obj), TYPE_VIRTIO_BLK)
|
|
|
|
|
2008-12-05 03:52:44 +08:00
|
|
|
/* from Linux's linux/virtio_blk.h */
|
|
|
|
|
|
|
|
/* The ID for virtio_block */
|
|
|
|
#define VIRTIO_ID_BLOCK 2
|
|
|
|
|
|
|
|
/* Feature bits */
|
|
|
|
#define VIRTIO_BLK_F_BARRIER 0 /* Does host support barriers? */
|
|
|
|
#define VIRTIO_BLK_F_SIZE_MAX 1 /* Indicates maximum segment size */
|
|
|
|
#define VIRTIO_BLK_F_SEG_MAX 2 /* Indicates maximum # of segments */
|
|
|
|
#define VIRTIO_BLK_F_GEOMETRY 4 /* Indicates support of legacy geometry */
|
2009-04-27 16:29:14 +08:00
|
|
|
#define VIRTIO_BLK_F_RO 5 /* Disk is read-only */
|
|
|
|
#define VIRTIO_BLK_F_BLK_SIZE 6 /* Block size of disk is available*/
|
|
|
|
#define VIRTIO_BLK_F_SCSI 7 /* Supports scsi command passthru */
|
2010-02-11 06:36:49 +08:00
|
|
|
/* #define VIRTIO_BLK_F_IDENTIFY 8 ATA IDENTIFY supported, DEPRECATED */
|
2012-08-09 22:07:19 +08:00
|
|
|
#define VIRTIO_BLK_F_WCE 9 /* write cache enabled */
|
2010-02-11 06:37:25 +08:00
|
|
|
#define VIRTIO_BLK_F_TOPOLOGY 10 /* Topology information is available */
|
2012-08-09 22:07:19 +08:00
|
|
|
#define VIRTIO_BLK_F_CONFIG_WCE 11 /* write cache configurable */
|
2009-06-23 02:26:51 +08:00
|
|
|
|
2011-06-20 17:35:18 +08:00
|
|
|
#define VIRTIO_BLK_ID_BYTES 20 /* ID string length */
|
|
|
|
|
2008-12-05 03:52:44 +08:00
|
|
|
struct virtio_blk_config
|
|
|
|
{
|
|
|
|
uint64_t capacity;
|
|
|
|
uint32_t size_max;
|
|
|
|
uint32_t seg_max;
|
|
|
|
uint16_t cylinders;
|
|
|
|
uint8_t heads;
|
|
|
|
uint8_t sectors;
|
2010-03-04 21:20:17 +08:00
|
|
|
uint32_t blk_size;
|
2010-02-11 06:37:25 +08:00
|
|
|
uint8_t physical_block_exp;
|
|
|
|
uint8_t alignment_offset;
|
|
|
|
uint16_t min_io_size;
|
|
|
|
uint32_t opt_io_size;
|
2012-08-09 22:07:19 +08:00
|
|
|
uint8_t wce;
|
2011-08-31 18:38:01 +08:00
|
|
|
} QEMU_PACKED;
|
2008-12-05 03:52:44 +08:00
|
|
|
|
|
|
|
/* These two define direction. */
|
|
|
|
#define VIRTIO_BLK_T_IN 0
|
|
|
|
#define VIRTIO_BLK_T_OUT 1
|
|
|
|
|
|
|
|
/* This bit says it's a scsi command, not an actual read or write. */
|
|
|
|
#define VIRTIO_BLK_T_SCSI_CMD 2
|
|
|
|
|
2009-09-05 01:02:23 +08:00
|
|
|
/* Flush the volatile write cache */
|
|
|
|
#define VIRTIO_BLK_T_FLUSH 4
|
|
|
|
|
2010-07-03 01:44:25 +08:00
|
|
|
/* return the device ID string */
|
|
|
|
#define VIRTIO_BLK_T_GET_ID 8
|
|
|
|
|
2008-12-05 03:52:44 +08:00
|
|
|
/* Barrier before this op. */
|
|
|
|
#define VIRTIO_BLK_T_BARRIER 0x80000000
|
|
|
|
|
|
|
|
/* This is the first element of the read scatter-gather list. */
|
|
|
|
struct virtio_blk_outhdr
|
|
|
|
{
|
|
|
|
/* VIRTIO_BLK_T* */
|
|
|
|
uint32_t type;
|
|
|
|
/* io priority. */
|
|
|
|
uint32_t ioprio;
|
|
|
|
/* Sector (ie. 512 byte offset) */
|
|
|
|
uint64_t sector;
|
|
|
|
};
|
|
|
|
|
|
|
|
#define VIRTIO_BLK_S_OK 0
|
|
|
|
#define VIRTIO_BLK_S_IOERR 1
|
|
|
|
#define VIRTIO_BLK_S_UNSUPP 2
|
|
|
|
|
2009-04-23 18:58:51 +08:00
|
|
|
/* This is the last element of the write scatter-gather list */
|
2008-12-05 03:52:44 +08:00
|
|
|
struct virtio_blk_inhdr
|
|
|
|
{
|
|
|
|
unsigned char status;
|
|
|
|
};
|
|
|
|
|
2009-04-27 16:29:14 +08:00
|
|
|
/* SCSI pass-through header */
|
|
|
|
struct virtio_scsi_inhdr
|
|
|
|
{
|
|
|
|
uint32_t errors;
|
|
|
|
uint32_t data_len;
|
|
|
|
uint32_t sense_len;
|
|
|
|
uint32_t residual;
|
|
|
|
};
|
|
|
|
|
2012-05-16 18:54:05 +08:00
|
|
|
struct VirtIOBlkConf
|
|
|
|
{
|
|
|
|
BlockConf conf;
|
2014-03-03 18:30:08 +08:00
|
|
|
IOThread *iothread;
|
2012-05-16 18:54:05 +08:00
|
|
|
char *serial;
|
virtio-blk: always enable VIRTIO_BLK_F_SCSI
VIRTIO_BLK_F_SCSI is supposed to mean whether the host can *parse*
SCSI requests, not *execute* them. You could run QEMU with scsi=on
and a file-backed disk, and QEMU would fail all SCSI requests even
though it advertises VIRTIO_BLK_F_SCSI.
Because we need to do this to fix a migration compatibility problem
related to how QEMU is invoked by management, we must do this
unconditionally even on older machine types. This more or less assumes
that no one ever invoked QEMU with scsi=off.
Here is how testing goes:
- old QEMU, scsi=on -> new QEMU, scsi=on
- new QEMU, scsi=on -> old QEMU, scsi=on
- old QEMU, scsi=off -> new QEMU, scsi=on
- new QEMU, scsi=off -> old QEMU, scsi=on
ok (new QEMU has VIRTIO_BLK_F_SCSI, adding host features is fine)
- old QEMU, scsi=off -> new QEMU, scsi=off
ok (new QEMU has VIRTIO_BLK_F_SCSI, adding host features is fine)
- old QEMU, scsi=on -> new QEMU, scsi=off
ok, bug fixed
- new QEMU, scsi=on -> old QEMU, scsi=off
doesn't work (same as: old QEMU, scsi=on -> old QEMU, scsi=off)
- new QEMU, scsi=off -> old QEMU, scsi=off
broken by the patch
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
2012-05-16 18:54:06 +08:00
|
|
|
uint32_t scsi;
|
2012-12-10 20:14:39 +08:00
|
|
|
uint32_t config_wce;
|
2012-11-14 22:39:30 +08:00
|
|
|
uint32_t data_plane;
|
2012-05-16 18:54:05 +08:00
|
|
|
};
|
|
|
|
|
2013-02-06 00:06:20 +08:00
|
|
|
struct VirtIOBlockDataPlane;
|
|
|
|
|
2014-06-17 14:32:06 +08:00
|
|
|
struct VirtIOBlockReq;
|
2013-03-19 00:37:18 +08:00
|
|
|
typedef struct VirtIOBlock {
|
2013-03-19 00:37:27 +08:00
|
|
|
VirtIODevice parent_obj;
|
2013-03-19 00:37:18 +08:00
|
|
|
BlockDriverState *bs;
|
|
|
|
VirtQueue *vq;
|
|
|
|
void *rq;
|
|
|
|
QEMUBH *bh;
|
|
|
|
BlockConf *conf;
|
2013-03-19 00:37:21 +08:00
|
|
|
VirtIOBlkConf blk;
|
2013-03-19 00:37:18 +08:00
|
|
|
unsigned short sector_mask;
|
virtio-blk: do not relay a previous driver's WCE configuration to the current
The following sequence happens:
- the SeaBIOS virtio-blk driver does not support the WCE feature, which
causes QEMU to disable writeback caching
- the Linux virtio-blk driver resets the device, finds WCE is available
but writeback caching is disabled; tells block layer to not send cache
flush commands
- the Linux virtio-blk driver sets the DRIVER_OK bit, which causes
writeback caching to be re-enabled, but the Linux virtio-blk driver does
not know of this side effect and cache flushes remain disabled
The bug is at the third step. If the guest does know about CONFIG_WCE,
QEMU should ignore the WCE feature's state. The guest will control the
cache mode solely using configuration space. This change makes Linux
do flushes correctly, but Linux will keep SeaBIOS's writethrough mode.
Hence, whenever the guest is reset, the cache mode of the disk should
be reset to whatever was specified in the "-drive" option. With this
change, the Linux virtio-blk driver finds that writeback caching is
enabled, and tells the block layer to send cache flush commands
appropriately.
Reported-by: Rusty Russell <rusty@au1.ibm.com
Cc: qemu-stable@nongnu.org
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
2013-09-20 23:31:55 +08:00
|
|
|
bool original_wce;
|
2013-03-19 00:37:18 +08:00
|
|
|
VMChangeStateEntry *change;
|
2014-06-17 14:32:06 +08:00
|
|
|
/* Function to push to vq and notify guest */
|
|
|
|
void (*complete_request)(struct VirtIOBlockReq *req, unsigned char status);
|
2013-03-19 00:37:18 +08:00
|
|
|
#ifdef CONFIG_VIRTIO_BLK_DATA_PLANE
|
2013-07-29 21:01:59 +08:00
|
|
|
Notifier migration_state_notifier;
|
2013-02-06 00:06:20 +08:00
|
|
|
struct VirtIOBlockDataPlane *dataplane;
|
2013-03-19 00:37:18 +08:00
|
|
|
#endif
|
|
|
|
} VirtIOBlock;
|
|
|
|
|
2014-06-17 14:32:07 +08:00
|
|
|
typedef struct MultiReqBuffer {
|
|
|
|
BlockRequest blkreq[32];
|
|
|
|
unsigned int num_writes;
|
|
|
|
} MultiReqBuffer;
|
|
|
|
|
2014-06-11 12:11:42 +08:00
|
|
|
typedef struct VirtIOBlockReq {
|
|
|
|
VirtIOBlock *dev;
|
2014-06-11 12:11:43 +08:00
|
|
|
VirtQueueElement *elem;
|
2014-06-11 12:11:42 +08:00
|
|
|
struct virtio_blk_inhdr *in;
|
2014-06-11 12:11:48 +08:00
|
|
|
struct virtio_blk_outhdr out;
|
2014-06-11 12:11:42 +08:00
|
|
|
QEMUIOVector qiov;
|
|
|
|
struct VirtIOBlockReq *next;
|
|
|
|
BlockAcctCookie acct;
|
|
|
|
} VirtIOBlockReq;
|
|
|
|
|
2014-05-22 16:22:42 +08:00
|
|
|
int virtio_blk_handle_scsi_req(VirtIOBlock *blk,
|
|
|
|
VirtQueueElement *elem);
|
|
|
|
|
2014-06-17 14:32:07 +08:00
|
|
|
void virtio_blk_handle_request(VirtIOBlockReq *req, MultiReqBuffer *mrb);
|
|
|
|
|
|
|
|
void virtio_submit_multiwrite(BlockDriverState *bs, MultiReqBuffer *mrb);
|
|
|
|
|
2008-12-05 03:52:44 +08:00
|
|
|
#endif
|