qemu/hw/virtio-blk.c

730 lines
20 KiB
C
Raw Normal View History

/*
* 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.
*
*/
#include "qemu-common.h"
#include "qemu/error-report.h"
#include "trace.h"
#include "hw/block-common.h"
#include "sysemu/blockdev.h"
#include "hw/virtio-blk.h"
#include "hw/scsi-defs.h"
#ifdef __linux__
# include <scsi/sg.h>
#endif
#include "hw/virtio-bus.h"
typedef struct VirtIOBlockReq
{
VirtIOBlock *dev;
VirtQueueElement elem;
struct virtio_blk_inhdr *in;
struct virtio_blk_outhdr *out;
struct virtio_scsi_inhdr *scsi;
QEMUIOVector qiov;
struct VirtIOBlockReq *next;
BlockAcctCookie acct;
} VirtIOBlockReq;
static void virtio_blk_req_complete(VirtIOBlockReq *req, int status)
{
VirtIOBlock *s = req->dev;
VirtIODevice *vdev = VIRTIO_DEVICE(s);
trace_virtio_blk_req_complete(req, status);
stb_p(&req->in->status, status);
virtqueue_push(s->vq, &req->elem, req->qiov.size + sizeof(*req->in));
virtio_notify(vdev, s->vq);
}
static int virtio_blk_handle_rw_error(VirtIOBlockReq *req, int error,
bool is_read)
{
BlockErrorAction action = bdrv_get_error_action(req->dev->bs, is_read, error);
VirtIOBlock *s = req->dev;
if (action == BDRV_ACTION_STOP) {
req->next = s->rq;
s->rq = req;
} else if (action == BDRV_ACTION_REPORT) {
virtio_blk_req_complete(req, VIRTIO_BLK_S_IOERR);
bdrv_acct_done(s->bs, &req->acct);
g_free(req);
}
bdrv_error_action(s->bs, action, is_read, error);
return action != BDRV_ACTION_IGNORE;
}
static void virtio_blk_rw_complete(void *opaque, int ret)
{
VirtIOBlockReq *req = opaque;
trace_virtio_blk_rw_complete(req, ret);
if (ret) {
bool is_read = !(ldl_p(&req->out->type) & VIRTIO_BLK_T_OUT);
if (virtio_blk_handle_rw_error(req, -ret, is_read))
return;
}
virtio_blk_req_complete(req, VIRTIO_BLK_S_OK);
bdrv_acct_done(req->dev->bs, &req->acct);
g_free(req);
}
static void virtio_blk_flush_complete(void *opaque, int ret)
{
VirtIOBlockReq *req = opaque;
if (ret) {
if (virtio_blk_handle_rw_error(req, -ret, 0)) {
return;
}
}
virtio_blk_req_complete(req, VIRTIO_BLK_S_OK);
bdrv_acct_done(req->dev->bs, &req->acct);
g_free(req);
}
static VirtIOBlockReq *virtio_blk_alloc_request(VirtIOBlock *s)
{
VirtIOBlockReq *req = g_malloc(sizeof(*req));
req->dev = s;
req->qiov.size = 0;
req->next = NULL;
return req;
}
static VirtIOBlockReq *virtio_blk_get_request(VirtIOBlock *s)
{
VirtIOBlockReq *req = virtio_blk_alloc_request(s);
if (req != NULL) {
if (!virtqueue_pop(s->vq, &req->elem)) {
g_free(req);
return NULL;
}
}
return req;
}
static void virtio_blk_handle_scsi(VirtIOBlockReq *req)
{
#ifdef __linux__
int ret;
int i;
#endif
int status = VIRTIO_BLK_S_OK;
/*
* We require at least one output segment each for the virtio_blk_outhdr
* and the SCSI command block.
*
* We also at least require the virtio_blk_inhdr, the virtio_scsi_inhdr
* and the sense buffer pointer in the input segments.
*/
if (req->elem.out_num < 2 || req->elem.in_num < 3) {
virtio_blk_req_complete(req, VIRTIO_BLK_S_IOERR);
g_free(req);
return;
}
/*
* The scsi inhdr is placed in the second-to-last input segment, just
* before the regular inhdr.
*/
req->scsi = (void *)req->elem.in_sg[req->elem.in_num - 2].iov_base;
if (!req->dev->blk.scsi) {
status = VIRTIO_BLK_S_UNSUPP;
goto fail;
}
/*
* No support for bidirection commands yet.
*/
if (req->elem.out_num > 2 && req->elem.in_num > 3) {
status = VIRTIO_BLK_S_UNSUPP;
goto fail;
}
#ifdef __linux__
struct sg_io_hdr hdr;
memset(&hdr, 0, sizeof(struct sg_io_hdr));
hdr.interface_id = 'S';
hdr.cmd_len = req->elem.out_sg[1].iov_len;
hdr.cmdp = req->elem.out_sg[1].iov_base;
hdr.dxfer_len = 0;
if (req->elem.out_num > 2) {
/*
* If there are more than the minimally required 2 output segments
* there is write payload starting from the third iovec.
*/
hdr.dxfer_direction = SG_DXFER_TO_DEV;
hdr.iovec_count = req->elem.out_num - 2;
for (i = 0; i < hdr.iovec_count; i++)
hdr.dxfer_len += req->elem.out_sg[i + 2].iov_len;
hdr.dxferp = req->elem.out_sg + 2;
} else if (req->elem.in_num > 3) {
/*
* If we have more than 3 input segments the guest wants to actually
* read data.
*/
hdr.dxfer_direction = SG_DXFER_FROM_DEV;
hdr.iovec_count = req->elem.in_num - 3;
for (i = 0; i < hdr.iovec_count; i++)
hdr.dxfer_len += req->elem.in_sg[i].iov_len;
hdr.dxferp = req->elem.in_sg;
} else {
/*
* Some SCSI commands don't actually transfer any data.
*/
hdr.dxfer_direction = SG_DXFER_NONE;
}
hdr.sbp = req->elem.in_sg[req->elem.in_num - 3].iov_base;
hdr.mx_sb_len = req->elem.in_sg[req->elem.in_num - 3].iov_len;
ret = bdrv_ioctl(req->dev->bs, SG_IO, &hdr);
if (ret) {
status = VIRTIO_BLK_S_UNSUPP;
goto fail;
}
/*
* From SCSI-Generic-HOWTO: "Some lower level drivers (e.g. ide-scsi)
* clear the masked_status field [hence status gets cleared too, see
* block/scsi_ioctl.c] even when a CHECK_CONDITION or COMMAND_TERMINATED
* status has occurred. However they do set DRIVER_SENSE in driver_status
* field. Also a (sb_len_wr > 0) indicates there is a sense buffer.
*/
if (hdr.status == 0 && hdr.sb_len_wr > 0) {
hdr.status = CHECK_CONDITION;
}
stl_p(&req->scsi->errors,
hdr.status | (hdr.msg_status << 8) |
(hdr.host_status << 16) | (hdr.driver_status << 24));
stl_p(&req->scsi->residual, hdr.resid);
stl_p(&req->scsi->sense_len, hdr.sb_len_wr);
stl_p(&req->scsi->data_len, hdr.dxfer_len);
virtio_blk_req_complete(req, status);
g_free(req);
return;
#else
abort();
#endif
fail:
/* Just put anything nonzero so that the ioctl fails in the guest. */
stl_p(&req->scsi->errors, 255);
virtio_blk_req_complete(req, status);
g_free(req);
}
typedef struct MultiReqBuffer {
BlockRequest blkreq[32];
unsigned int num_writes;
} MultiReqBuffer;
static void virtio_submit_multiwrite(BlockDriverState *bs, MultiReqBuffer *mrb)
{
int i, ret;
if (!mrb->num_writes) {
return;
}
ret = bdrv_aio_multiwrite(bs, mrb->blkreq, mrb->num_writes);
if (ret != 0) {
for (i = 0; i < mrb->num_writes; i++) {
if (mrb->blkreq[i].error) {
virtio_blk_rw_complete(mrb->blkreq[i].opaque, -EIO);
}
}
}
mrb->num_writes = 0;
}
static void virtio_blk_handle_flush(VirtIOBlockReq *req, MultiReqBuffer *mrb)
{
bdrv_acct_start(req->dev->bs, &req->acct, 0, BDRV_ACCT_FLUSH);
/*
* Make sure all outstanding writes are posted to the backing device.
*/
virtio_submit_multiwrite(req->dev->bs, mrb);
bdrv_aio_flush(req->dev->bs, virtio_blk_flush_complete, req);
}
static void virtio_blk_handle_write(VirtIOBlockReq *req, MultiReqBuffer *mrb)
{
BlockRequest *blkreq;
uint64_t sector;
sector = ldq_p(&req->out->sector);
bdrv_acct_start(req->dev->bs, &req->acct, req->qiov.size, BDRV_ACCT_WRITE);
trace_virtio_blk_handle_write(req, sector, req->qiov.size / 512);
if (sector & req->dev->sector_mask) {
virtio_blk_rw_complete(req, -EIO);
return;
}
if (req->qiov.size % req->dev->conf->logical_block_size) {
virtio_blk_rw_complete(req, -EIO);
return;
}
if (mrb->num_writes == 32) {
virtio_submit_multiwrite(req->dev->bs, mrb);
}
blkreq = &mrb->blkreq[mrb->num_writes];
blkreq->sector = sector;
blkreq->nb_sectors = req->qiov.size / BDRV_SECTOR_SIZE;
blkreq->qiov = &req->qiov;
blkreq->cb = virtio_blk_rw_complete;
blkreq->opaque = req;
blkreq->error = 0;
mrb->num_writes++;
}
static void virtio_blk_handle_read(VirtIOBlockReq *req)
{
uint64_t sector;
sector = ldq_p(&req->out->sector);
bdrv_acct_start(req->dev->bs, &req->acct, req->qiov.size, BDRV_ACCT_READ);
trace_virtio_blk_handle_read(req, sector, req->qiov.size / 512);
if (sector & req->dev->sector_mask) {
virtio_blk_rw_complete(req, -EIO);
return;
}
if (req->qiov.size % req->dev->conf->logical_block_size) {
virtio_blk_rw_complete(req, -EIO);
return;
}
bdrv_aio_readv(req->dev->bs, sector, &req->qiov,
req->qiov.size / BDRV_SECTOR_SIZE,
virtio_blk_rw_complete, req);
}
static void virtio_blk_handle_request(VirtIOBlockReq *req,
MultiReqBuffer *mrb)
{
uint32_t type;
if (req->elem.out_num < 1 || req->elem.in_num < 1) {
error_report("virtio-blk missing headers");
exit(1);
}
if (req->elem.out_sg[0].iov_len < sizeof(*req->out) ||
req->elem.in_sg[req->elem.in_num - 1].iov_len < sizeof(*req->in)) {
error_report("virtio-blk header not in correct element");
exit(1);
}
req->out = (void *)req->elem.out_sg[0].iov_base;
req->in = (void *)req->elem.in_sg[req->elem.in_num - 1].iov_base;
type = ldl_p(&req->out->type);
if (type & VIRTIO_BLK_T_FLUSH) {
virtio_blk_handle_flush(req, mrb);
} else if (type & VIRTIO_BLK_T_SCSI_CMD) {
virtio_blk_handle_scsi(req);
} else if (type & VIRTIO_BLK_T_GET_ID) {
VirtIOBlock *s = req->dev;
/*
* NB: per existing s/n string convention the string is
* terminated by '\0' only when shorter than buffer.
*/
strncpy(req->elem.in_sg[0].iov_base,
s->blk.serial ? s->blk.serial : "",
MIN(req->elem.in_sg[0].iov_len, VIRTIO_BLK_ID_BYTES));
virtio_blk_req_complete(req, VIRTIO_BLK_S_OK);
g_free(req);
} else if (type & VIRTIO_BLK_T_OUT) {
qemu_iovec_init_external(&req->qiov, &req->elem.out_sg[1],
req->elem.out_num - 1);
virtio_blk_handle_write(req, mrb);
} else if (type == VIRTIO_BLK_T_IN || type == VIRTIO_BLK_T_BARRIER) {
/* VIRTIO_BLK_T_IN is 0, so we can't just & it. */
qemu_iovec_init_external(&req->qiov, &req->elem.in_sg[0],
req->elem.in_num - 1);
virtio_blk_handle_read(req);
} else {
virtio_blk_req_complete(req, VIRTIO_BLK_S_UNSUPP);
g_free(req);
}
}
static void virtio_blk_handle_output(VirtIODevice *vdev, VirtQueue *vq)
{
VirtIOBlock *s = VIRTIO_BLK(vdev);
VirtIOBlockReq *req;
MultiReqBuffer mrb = {
.num_writes = 0,
};
#ifdef CONFIG_VIRTIO_BLK_DATA_PLANE
/* Some guests kick before setting VIRTIO_CONFIG_S_DRIVER_OK so start
* dataplane here instead of waiting for .set_status().
*/
if (s->dataplane) {
virtio_blk_data_plane_start(s->dataplane);
return;
}
#endif
while ((req = virtio_blk_get_request(s))) {
virtio_blk_handle_request(req, &mrb);
}
virtio_submit_multiwrite(s->bs, &mrb);
/*
* FIXME: Want to check for completions before returning to guest mode,
* so cached reads and writes are reported as quickly as possible. But
* that should be done in the generic block layer.
*/
}
Fix VM state change handlers running out of order When a VM state change handler changes VM state, other VM state change handlers can see the state transitions out of order. bmdma_map(), scsi_disk_init() and virtio_blk_init() install VM state change handlers to restart DMA. These handlers can vm_stop() by running into a write error on a drive with werror=stop. This throws the VM state change handler callback into disarray. Here's an example case I observed: 0. The virtual IDE drive goes south. All future writes return errors. 1. Something encounters a write error, and duly stops the VM with vm_stop(). 2. vm_stop() calls vm_state_notify(0). 3. vm_state_notify() runs the callbacks in list vm_change_state_head. It contains ide_dma_restart_cb() installed by bmdma_map(). It also contains audio_vm_change_state_handler() installed by audio_init(). 4. audio_vm_change_state_handler() stops audio stuff. 5. User continues VM with monitor command "c". This runs vm_start(). 6. vm_start() calls vm_state_notify(1). 7. vm_state_notify() runs the callbacks in vm_change_state_head. 8. ide_dma_restart_cb() happens to come first. It does its work, runs into a write error, and duly stops the VM with vm_stop(). 9. vm_stop() runs vm_state_notify(0). 10. vm_state_notify() runs the callbacks in vm_change_state_head. 11. audio_vm_change_state_handler() stops audio stuff. Which isn't running. 12. vm_stop() finishes, ide_dma_restart_cb() finishes, step 7's vm_state_notify() resumes running handlers. 13. audio_vm_change_state_handler() starts audio stuff. Oopsie. Fix this by moving the actual write from each VM state change handler into a new bottom half (suggested by Gleb Natapov). Signed-off-by: Markus Armbruster <armbru@redhat.com> Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
2009-07-28 18:33:41 +00:00
static void virtio_blk_dma_restart_bh(void *opaque)
{
VirtIOBlock *s = opaque;
VirtIOBlockReq *req = s->rq;
MultiReqBuffer mrb = {
.num_writes = 0,
};
Fix VM state change handlers running out of order When a VM state change handler changes VM state, other VM state change handlers can see the state transitions out of order. bmdma_map(), scsi_disk_init() and virtio_blk_init() install VM state change handlers to restart DMA. These handlers can vm_stop() by running into a write error on a drive with werror=stop. This throws the VM state change handler callback into disarray. Here's an example case I observed: 0. The virtual IDE drive goes south. All future writes return errors. 1. Something encounters a write error, and duly stops the VM with vm_stop(). 2. vm_stop() calls vm_state_notify(0). 3. vm_state_notify() runs the callbacks in list vm_change_state_head. It contains ide_dma_restart_cb() installed by bmdma_map(). It also contains audio_vm_change_state_handler() installed by audio_init(). 4. audio_vm_change_state_handler() stops audio stuff. 5. User continues VM with monitor command "c". This runs vm_start(). 6. vm_start() calls vm_state_notify(1). 7. vm_state_notify() runs the callbacks in vm_change_state_head. 8. ide_dma_restart_cb() happens to come first. It does its work, runs into a write error, and duly stops the VM with vm_stop(). 9. vm_stop() runs vm_state_notify(0). 10. vm_state_notify() runs the callbacks in vm_change_state_head. 11. audio_vm_change_state_handler() stops audio stuff. Which isn't running. 12. vm_stop() finishes, ide_dma_restart_cb() finishes, step 7's vm_state_notify() resumes running handlers. 13. audio_vm_change_state_handler() starts audio stuff. Oopsie. Fix this by moving the actual write from each VM state change handler into a new bottom half (suggested by Gleb Natapov). Signed-off-by: Markus Armbruster <armbru@redhat.com> Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
2009-07-28 18:33:41 +00:00
qemu_bh_delete(s->bh);
s->bh = NULL;
s->rq = NULL;
while (req) {
virtio_blk_handle_request(req, &mrb);
req = req->next;
}
virtio_submit_multiwrite(s->bs, &mrb);
}
static void virtio_blk_dma_restart_cb(void *opaque, int running,
RunState state)
Fix VM state change handlers running out of order When a VM state change handler changes VM state, other VM state change handlers can see the state transitions out of order. bmdma_map(), scsi_disk_init() and virtio_blk_init() install VM state change handlers to restart DMA. These handlers can vm_stop() by running into a write error on a drive with werror=stop. This throws the VM state change handler callback into disarray. Here's an example case I observed: 0. The virtual IDE drive goes south. All future writes return errors. 1. Something encounters a write error, and duly stops the VM with vm_stop(). 2. vm_stop() calls vm_state_notify(0). 3. vm_state_notify() runs the callbacks in list vm_change_state_head. It contains ide_dma_restart_cb() installed by bmdma_map(). It also contains audio_vm_change_state_handler() installed by audio_init(). 4. audio_vm_change_state_handler() stops audio stuff. 5. User continues VM with monitor command "c". This runs vm_start(). 6. vm_start() calls vm_state_notify(1). 7. vm_state_notify() runs the callbacks in vm_change_state_head. 8. ide_dma_restart_cb() happens to come first. It does its work, runs into a write error, and duly stops the VM with vm_stop(). 9. vm_stop() runs vm_state_notify(0). 10. vm_state_notify() runs the callbacks in vm_change_state_head. 11. audio_vm_change_state_handler() stops audio stuff. Which isn't running. 12. vm_stop() finishes, ide_dma_restart_cb() finishes, step 7's vm_state_notify() resumes running handlers. 13. audio_vm_change_state_handler() starts audio stuff. Oopsie. Fix this by moving the actual write from each VM state change handler into a new bottom half (suggested by Gleb Natapov). Signed-off-by: Markus Armbruster <armbru@redhat.com> Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
2009-07-28 18:33:41 +00:00
{
VirtIOBlock *s = opaque;
if (!running) {
Fix VM state change handlers running out of order When a VM state change handler changes VM state, other VM state change handlers can see the state transitions out of order. bmdma_map(), scsi_disk_init() and virtio_blk_init() install VM state change handlers to restart DMA. These handlers can vm_stop() by running into a write error on a drive with werror=stop. This throws the VM state change handler callback into disarray. Here's an example case I observed: 0. The virtual IDE drive goes south. All future writes return errors. 1. Something encounters a write error, and duly stops the VM with vm_stop(). 2. vm_stop() calls vm_state_notify(0). 3. vm_state_notify() runs the callbacks in list vm_change_state_head. It contains ide_dma_restart_cb() installed by bmdma_map(). It also contains audio_vm_change_state_handler() installed by audio_init(). 4. audio_vm_change_state_handler() stops audio stuff. 5. User continues VM with monitor command "c". This runs vm_start(). 6. vm_start() calls vm_state_notify(1). 7. vm_state_notify() runs the callbacks in vm_change_state_head. 8. ide_dma_restart_cb() happens to come first. It does its work, runs into a write error, and duly stops the VM with vm_stop(). 9. vm_stop() runs vm_state_notify(0). 10. vm_state_notify() runs the callbacks in vm_change_state_head. 11. audio_vm_change_state_handler() stops audio stuff. Which isn't running. 12. vm_stop() finishes, ide_dma_restart_cb() finishes, step 7's vm_state_notify() resumes running handlers. 13. audio_vm_change_state_handler() starts audio stuff. Oopsie. Fix this by moving the actual write from each VM state change handler into a new bottom half (suggested by Gleb Natapov). Signed-off-by: Markus Armbruster <armbru@redhat.com> Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
2009-07-28 18:33:41 +00:00
return;
}
Fix VM state change handlers running out of order When a VM state change handler changes VM state, other VM state change handlers can see the state transitions out of order. bmdma_map(), scsi_disk_init() and virtio_blk_init() install VM state change handlers to restart DMA. These handlers can vm_stop() by running into a write error on a drive with werror=stop. This throws the VM state change handler callback into disarray. Here's an example case I observed: 0. The virtual IDE drive goes south. All future writes return errors. 1. Something encounters a write error, and duly stops the VM with vm_stop(). 2. vm_stop() calls vm_state_notify(0). 3. vm_state_notify() runs the callbacks in list vm_change_state_head. It contains ide_dma_restart_cb() installed by bmdma_map(). It also contains audio_vm_change_state_handler() installed by audio_init(). 4. audio_vm_change_state_handler() stops audio stuff. 5. User continues VM with monitor command "c". This runs vm_start(). 6. vm_start() calls vm_state_notify(1). 7. vm_state_notify() runs the callbacks in vm_change_state_head. 8. ide_dma_restart_cb() happens to come first. It does its work, runs into a write error, and duly stops the VM with vm_stop(). 9. vm_stop() runs vm_state_notify(0). 10. vm_state_notify() runs the callbacks in vm_change_state_head. 11. audio_vm_change_state_handler() stops audio stuff. Which isn't running. 12. vm_stop() finishes, ide_dma_restart_cb() finishes, step 7's vm_state_notify() resumes running handlers. 13. audio_vm_change_state_handler() starts audio stuff. Oopsie. Fix this by moving the actual write from each VM state change handler into a new bottom half (suggested by Gleb Natapov). Signed-off-by: Markus Armbruster <armbru@redhat.com> Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
2009-07-28 18:33:41 +00:00
if (!s->bh) {
s->bh = qemu_bh_new(virtio_blk_dma_restart_bh, s);
qemu_bh_schedule(s->bh);
}
}
static void virtio_blk_reset(VirtIODevice *vdev)
{
#ifdef CONFIG_VIRTIO_BLK_DATA_PLANE
VirtIOBlock *s = VIRTIO_BLK(vdev);
if (s->dataplane) {
virtio_blk_data_plane_stop(s->dataplane);
}
#endif
/*
* This should cancel pending requests, but can't do nicely until there
* are per-device request lists.
*/
bdrv_drain_all();
}
/* coalesce internal state, copy to pci i/o region 0
*/
static void virtio_blk_update_config(VirtIODevice *vdev, uint8_t *config)
{
VirtIOBlock *s = VIRTIO_BLK(vdev);
struct virtio_blk_config blkcfg;
uint64_t capacity;
int blk_size = s->conf->logical_block_size;
bdrv_get_geometry(s->bs, &capacity);
memset(&blkcfg, 0, sizeof(blkcfg));
stq_raw(&blkcfg.capacity, capacity);
stl_raw(&blkcfg.seg_max, 128 - 2);
stw_raw(&blkcfg.cylinders, s->conf->cyls);
stl_raw(&blkcfg.blk_size, blk_size);
stw_raw(&blkcfg.min_io_size, s->conf->min_io_size / blk_size);
stw_raw(&blkcfg.opt_io_size, s->conf->opt_io_size / blk_size);
blkcfg.heads = s->conf->heads;
/*
* We must ensure that the block device capacity is a multiple of
* the logical block size. If that is not the case, lets use
* sector_mask to adopt the geometry to have a correct picture.
* For those devices where the capacity is ok for the given geometry
* we dont touch the sector value of the geometry, since some devices
* (like s390 dasd) need a specific value. Here the capacity is already
* cyls*heads*secs*blk_size and the sector value is not block size
* divided by 512 - instead it is the amount of blk_size blocks
* per track (cylinder).
*/
if (bdrv_getlength(s->bs) / s->conf->heads / s->conf->secs % blk_size) {
blkcfg.sectors = s->conf->secs & ~s->sector_mask;
} else {
blkcfg.sectors = s->conf->secs;
}
blkcfg.size_max = 0;
blkcfg.physical_block_exp = get_physical_block_exp(s->conf);
blkcfg.alignment_offset = 0;
blkcfg.wce = bdrv_enable_write_cache(s->bs);
memcpy(config, &blkcfg, sizeof(struct virtio_blk_config));
}
static void virtio_blk_set_config(VirtIODevice *vdev, const uint8_t *config)
{
VirtIOBlock *s = VIRTIO_BLK(vdev);
struct virtio_blk_config blkcfg;
memcpy(&blkcfg, config, sizeof(blkcfg));
bdrv_set_enable_write_cache(s->bs, blkcfg.wce != 0);
}
static uint32_t virtio_blk_get_features(VirtIODevice *vdev, uint32_t features)
{
VirtIOBlock *s = VIRTIO_BLK(vdev);
features |= (1 << VIRTIO_BLK_F_SEG_MAX);
features |= (1 << VIRTIO_BLK_F_GEOMETRY);
features |= (1 << VIRTIO_BLK_F_TOPOLOGY);
features |= (1 << VIRTIO_BLK_F_BLK_SIZE);
features |= (1 << VIRTIO_BLK_F_SCSI);
if (s->blk.config_wce) {
features |= (1 << VIRTIO_BLK_F_CONFIG_WCE);
}
if (bdrv_enable_write_cache(s->bs))
features |= (1 << VIRTIO_BLK_F_WCE);
if (bdrv_is_read_only(s->bs))
features |= 1 << VIRTIO_BLK_F_RO;
return features;
}
static void virtio_blk_set_status(VirtIODevice *vdev, uint8_t status)
{
VirtIOBlock *s = VIRTIO_BLK(vdev);
uint32_t features;
#ifdef CONFIG_VIRTIO_BLK_DATA_PLANE
if (s->dataplane && !(status & (VIRTIO_CONFIG_S_DRIVER |
VIRTIO_CONFIG_S_DRIVER_OK))) {
virtio_blk_data_plane_stop(s->dataplane);
}
#endif
if (!(status & VIRTIO_CONFIG_S_DRIVER_OK)) {
return;
}
features = vdev->guest_features;
bdrv_set_enable_write_cache(s->bs, !!(features & (1 << VIRTIO_BLK_F_WCE)));
}
static void virtio_blk_save(QEMUFile *f, void *opaque)
{
VirtIOBlock *s = opaque;
VirtIODevice *vdev = VIRTIO_DEVICE(s);
VirtIOBlockReq *req = s->rq;
virtio_save(vdev, f);
while (req) {
qemu_put_sbyte(f, 1);
qemu_put_buffer(f, (unsigned char*)&req->elem, sizeof(req->elem));
req = req->next;
}
qemu_put_sbyte(f, 0);
}
static int virtio_blk_load(QEMUFile *f, void *opaque, int version_id)
{
VirtIOBlock *s = opaque;
VirtIODevice *vdev = VIRTIO_DEVICE(s);
int ret;
if (version_id != 2)
return -EINVAL;
ret = virtio_load(vdev, f);
if (ret) {
return ret;
}
while (qemu_get_sbyte(f)) {
VirtIOBlockReq *req = virtio_blk_alloc_request(s);
qemu_get_buffer(f, (unsigned char*)&req->elem, sizeof(req->elem));
req->next = s->rq;
s->rq = req;
virtqueue_map_sg(req->elem.in_sg, req->elem.in_addr,
req->elem.in_num, 1);
virtqueue_map_sg(req->elem.out_sg, req->elem.out_addr,
req->elem.out_num, 0);
}
return 0;
}
static void virtio_blk_resize(void *opaque)
{
VirtIODevice *vdev = VIRTIO_DEVICE(opaque);
virtio_notify_config(vdev);
}
static const BlockDevOps virtio_block_ops = {
.resize_cb = virtio_blk_resize,
};
void virtio_blk_set_conf(DeviceState *dev, VirtIOBlkConf *blk)
{
VirtIOBlock *s = VIRTIO_BLK(dev);
memcpy(&(s->blk), blk, sizeof(struct VirtIOBlkConf));
}
static int virtio_blk_device_init(VirtIODevice *vdev)
{
DeviceState *qdev = DEVICE(vdev);
VirtIOBlock *s = VIRTIO_BLK(vdev);
VirtIOBlkConf *blk = &(s->blk);
static int virtio_blk_id;
if (!blk->conf.bs) {
error_report("drive property not set");
return -1;
}
if (!bdrv_is_inserted(blk->conf.bs)) {
error_report("Device needs media, but drive is empty");
return -1;
}
blkconf_serial(&blk->conf, &blk->serial);
if (blkconf_geometry(&blk->conf, NULL, 65535, 255, 255) < 0) {
return -1;
}
virtio_init(vdev, "virtio-blk", VIRTIO_ID_BLOCK,
sizeof(struct virtio_blk_config));
vdev->get_config = virtio_blk_update_config;
vdev->set_config = virtio_blk_set_config;
vdev->get_features = virtio_blk_get_features;
vdev->set_status = virtio_blk_set_status;
vdev->reset = virtio_blk_reset;
s->bs = blk->conf.bs;
s->conf = &blk->conf;
memcpy(&(s->blk), blk, sizeof(struct VirtIOBlkConf));
s->rq = NULL;
s->sector_mask = (s->conf->logical_block_size / BDRV_SECTOR_SIZE) - 1;
s->vq = virtio_add_queue(vdev, 128, virtio_blk_handle_output);
#ifdef CONFIG_VIRTIO_BLK_DATA_PLANE
if (!virtio_blk_data_plane_create(vdev, blk, &s->dataplane)) {
virtio-blk: Do not segfault fault if failed to initialize dataplane $ ~/usr/bin/qemu-system-x86_64 -enable-kvm -m 1024 -drive if=none,id=drive0,cache=none,aio=native,format=raw,file=/root/Image/centos-6.4.raw -device virtio-blk-pci,drive=drive0,scsi=off,x-data-plane=on,config-wce=on # make dataplane fail to initialize qemu-system-x86_64: -device virtio-blk-pci,drive=drive0,scsi=off,x-data-plane=on,config-wce=on: device is incompatible with x-data-plane, use config-wce=off *** glibc detected *** /root/usr/bin/qemu-system-x86_64: free(): invalid pointer: 0x00007f001fef12f8 *** ======= Backtrace: ========= /lib64/libc.so.6(+0x7d776)[0x7f00153a5776] /root/usr/bin/qemu-system-x86_64(+0x2c34ec)[0x7f001cf5b4ec] /root/usr/bin/qemu-system-x86_64(+0x342f9a)[0x7f001cfdaf9a] /root/usr/bin/qemu-system-x86_64(+0x33694e)[0x7f001cfce94e] .................... (gdb) bt #0 0x00007f3bf3a12015 in raise () from /lib64/libc.so.6 #1 0x00007f3bf3a1348b in abort () from /lib64/libc.so.6 #2 0x00007f3bf3a51a4e in __libc_message () from /lib64/libc.so.6 #3 0x00007f3bf3a57776 in malloc_printerr () from /lib64/libc.so.6 #4 0x00007f3bfb60d4ec in free_and_trace (mem=0x7f3bfe0129f8) at vl.c:2786 #5 0x00007f3bfb68cf9a in virtio_cleanup (vdev=0x7f3bfe0129f8) at /root/Develop/QEMU/qemu/hw/virtio.c:900 #6 0x00007f3bfb68094e in virtio_blk_device_init (vdev=0x7f3bfe0129f8) at /root/Develop/QEMU/qemu/hw/virtio-blk.c:666 #7 0x00007f3bfb68dadf in virtio_device_init (qdev=0x7f3bfe0129f8) at /root/Develop/QEMU/qemu/hw/virtio.c:1092 #8 0x00007f3bfb50da46 in device_realize (dev=0x7f3bfe0129f8, err=0x7fff479c9258) at hw/qdev.c:176 ............................. In virtio_blk_device_init(), the memory which vdev point to is a static member of "struct VirtIOBlkPCI", not heap memory, and it does not get freed. So we shoule use virtio_common_cleanup() to clean this VirtIODevice rather than virtio_cleanup(), which attempts to free the vdev. This error was introduced by commit 05ff686536f408ba6e8426b1b54d25bd3379fda2 recently. Signed-off-by: Dunrong Huang <huangdr@cloud-times.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2013-03-19 08:27:29 +00:00
virtio_common_cleanup(vdev);
return -1;
}
#endif
s->change = qemu_add_vm_change_state_handler(virtio_blk_dma_restart_cb, s);
register_savevm(qdev, "virtio-blk", virtio_blk_id++, 2,
virtio_blk_save, virtio_blk_load, s);
bdrv_set_dev_ops(s->bs, &virtio_block_ops, s);
bdrv_set_buffer_alignment(s->bs, s->conf->logical_block_size);
bdrv_iostatus_enable(s->bs);
add_boot_device_path(s->conf->bootindex, qdev, "/disk@0,0");
return 0;
}
static int virtio_blk_device_exit(DeviceState *dev)
{
VirtIODevice *vdev = VIRTIO_DEVICE(dev);
VirtIOBlock *s = VIRTIO_BLK(dev);
#ifdef CONFIG_VIRTIO_BLK_DATA_PLANE
virtio_blk_data_plane_destroy(s->dataplane);
s->dataplane = NULL;
#endif
qemu_del_vm_change_state_handler(s->change);
unregister_savevm(dev, "virtio-blk", s);
blockdev_mark_auto_del(s->bs);
virtio_common_cleanup(vdev);
return 0;
}
static Property virtio_blk_properties[] = {
DEFINE_VIRTIO_BLK_PROPERTIES(VirtIOBlock, blk),
DEFINE_PROP_END_OF_LIST(),
};
static void virtio_blk_class_init(ObjectClass *klass, void *data)
{
DeviceClass *dc = DEVICE_CLASS(klass);
VirtioDeviceClass *vdc = VIRTIO_DEVICE_CLASS(klass);
dc->exit = virtio_blk_device_exit;
dc->props = virtio_blk_properties;
vdc->init = virtio_blk_device_init;
vdc->get_config = virtio_blk_update_config;
vdc->set_config = virtio_blk_set_config;
vdc->get_features = virtio_blk_get_features;
vdc->set_status = virtio_blk_set_status;
vdc->reset = virtio_blk_reset;
}
static const TypeInfo virtio_device_info = {
.name = TYPE_VIRTIO_BLK,
.parent = TYPE_VIRTIO_DEVICE,
.instance_size = sizeof(VirtIOBlock),
.class_init = virtio_blk_class_init,
};
static void virtio_register_types(void)
{
type_register_static(&virtio_device_info);
}
type_init(virtio_register_types)