*/
#include <qemu-common.h>
-#include <sysemu.h>
+#include "qemu-error.h"
+#include "trace.h"
+#include "blockdev.h"
#include "virtio-blk.h"
-#include "block_int.h"
#ifdef __linux__
# include <scsi/sg.h>
#endif
BlockDriverState *bs;
VirtQueue *vq;
void *rq;
+ QEMUBH *bh;
+ BlockConf *conf;
+ unsigned short sector_mask;
+ char sn[BLOCK_SERIAL_STRLEN];
+ DeviceState *qdev;
} VirtIOBlock;
static VirtIOBlock *to_virtio_blk(VirtIODevice *vdev)
{
VirtIOBlock *s = req->dev;
+ trace_virtio_blk_req_complete(req, status);
+
req->in->status = status;
virtqueue_push(s->vq, &req->elem, req->qiov.size + sizeof(*req->in));
virtio_notify(&s->vdev, s->vq);
qemu_free(req);
}
-static int virtio_blk_handle_write_error(VirtIOBlockReq *req, int error)
+static int virtio_blk_handle_rw_error(VirtIOBlockReq *req, int error,
+ int is_read)
{
- BlockInterfaceErrorAction action = drive_get_onerror(req->dev->bs);
+ BlockErrorAction action = bdrv_get_on_error(req->dev->bs, is_read);
VirtIOBlock *s = req->dev;
- if (action == BLOCK_ERR_IGNORE)
+ if (action == BLOCK_ERR_IGNORE) {
+ bdrv_mon_event(s->bs, BDRV_ACTION_IGNORE, is_read);
return 0;
+ }
if ((error == ENOSPC && action == BLOCK_ERR_STOP_ENOSPC)
|| action == BLOCK_ERR_STOP_ANY) {
req->next = s->rq;
s->rq = req;
+ bdrv_mon_event(s->bs, BDRV_ACTION_STOP, is_read);
vm_stop(0);
} else {
virtio_blk_req_complete(req, VIRTIO_BLK_S_IOERR);
+ bdrv_mon_event(s->bs, BDRV_ACTION_REPORT, is_read);
}
return 1;
{
VirtIOBlockReq *req = opaque;
- if (ret && (req->out->type & VIRTIO_BLK_T_OUT)) {
- if (virtio_blk_handle_write_error(req, -ret))
+ trace_virtio_blk_rw_complete(req, ret);
+
+ if (ret) {
+ int is_read = !(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);
}
+static void virtio_blk_flush_complete(void *opaque, int ret)
+{
+ VirtIOBlockReq *req = opaque;
+
+ virtio_blk_req_complete(req, ret ? VIRTIO_BLK_S_IOERR : VIRTIO_BLK_S_OK);
+}
+
static VirtIOBlockReq *virtio_blk_alloc_request(VirtIOBlock *s)
{
- VirtIOBlockReq *req = qemu_mallocz(sizeof(*req));
+ VirtIOBlockReq *req = qemu_malloc(sizeof(*req));
req->dev = s;
+ req->qiov.size = 0;
+ req->next = NULL;
return req;
}
static void virtio_blk_handle_scsi(VirtIOBlockReq *req)
{
struct sg_io_hdr hdr;
- int ret, size = 0;
+ int ret;
int status;
int i;
* before the regular inhdr.
*/
req->scsi = (void *)req->elem.in_sg[req->elem.in_num - 2].iov_base;
- size = sizeof(*req->in) + sizeof(*req->scsi);
memset(&hdr, 0, sizeof(struct sg_io_hdr));
hdr.interface_id = 'S';
hdr.dxfer_len += req->elem.in_sg[i].iov_len;
hdr.dxferp = req->elem.in_sg;
- size += hdr.dxfer_len;
} else {
/*
* Some SCSI commands don't actually transfer any data.
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;
- size += hdr.mx_sb_len;
ret = bdrv_ioctl(req->dev->bs, SG_IO, &hdr);
if (ret) {
}
#endif /* __linux__ */
-static void virtio_blk_handle_write(VirtIOBlockReq *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)
+{
+ BlockDriverAIOCB *acb;
+
+ /*
+ * Make sure all outstanding writes are posted to the backing device.
+ */
+ virtio_submit_multiwrite(req->dev->bs, mrb);
+
+ acb = bdrv_aio_flush(req->dev->bs, virtio_blk_flush_complete, req);
+ if (!acb) {
+ virtio_blk_req_complete(req, VIRTIO_BLK_S_IOERR);
+ }
+}
+
+static void virtio_blk_handle_write(VirtIOBlockReq *req, MultiReqBuffer *mrb)
{
- bdrv_aio_writev(req->dev->bs, req->out->sector, &req->qiov,
- req->qiov.size / 512, virtio_blk_rw_complete, req);
+ BlockRequest *blkreq;
+
+ trace_virtio_blk_handle_write(req, req->out->sector, req->qiov.size / 512);
+
+ if (req->out->sector & req->dev->sector_mask) {
+ 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 = req->out->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)
{
- bdrv_aio_readv(req->dev->bs, req->out->sector, &req->qiov,
- req->qiov.size / 512, virtio_blk_rw_complete, req);
+ BlockDriverAIOCB *acb;
+
+ if (req->out->sector & req->dev->sector_mask) {
+ virtio_blk_rw_complete(req, -EIO);
+ return;
+ }
+
+ acb = bdrv_aio_readv(req->dev->bs, req->out->sector, &req->qiov,
+ req->qiov.size / BDRV_SECTOR_SIZE,
+ virtio_blk_rw_complete, req);
+ if (!acb) {
+ virtio_blk_rw_complete(req, -EIO);
+ }
+}
+
+static void virtio_blk_handle_request(VirtIOBlockReq *req,
+ MultiReqBuffer *mrb)
+{
+ if (req->elem.out_num < 1 || req->elem.in_num < 1) {
+ fprintf(stderr, "virtio-blk missing headers\n");
+ 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)) {
+ fprintf(stderr, "virtio-blk header not in correct element\n");
+ 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;
+
+ if (req->out->type & VIRTIO_BLK_T_FLUSH) {
+ virtio_blk_handle_flush(req, mrb);
+ } else if (req->out->type & VIRTIO_BLK_T_SCSI_CMD) {
+ virtio_blk_handle_scsi(req);
+ } else if (req->out->type & VIRTIO_BLK_T_GET_ID) {
+ VirtIOBlock *s = req->dev;
+
+ memcpy(req->elem.in_sg[0].iov_base, s->sn,
+ MIN(req->elem.in_sg[0].iov_len, sizeof(s->sn)));
+ virtio_blk_req_complete(req, VIRTIO_BLK_S_OK);
+ } else if (req->out->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 {
+ qemu_iovec_init_external(&req->qiov, &req->elem.in_sg[0],
+ req->elem.in_num - 1);
+ virtio_blk_handle_read(req);
+ }
}
static void virtio_blk_handle_output(VirtIODevice *vdev, VirtQueue *vq)
{
VirtIOBlock *s = to_virtio_blk(vdev);
VirtIOBlockReq *req;
+ MultiReqBuffer mrb = {
+ .num_writes = 0,
+ };
while ((req = virtio_blk_get_request(s))) {
- if (req->elem.out_num < 1 || req->elem.in_num < 1) {
- fprintf(stderr, "virtio-blk missing headers\n");
- exit(1);
- }
+ virtio_blk_handle_request(req, &mrb);
+ }
- 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)) {
- fprintf(stderr, "virtio-blk header not in correct element\n");
- exit(1);
- }
+ virtio_submit_multiwrite(s->bs, &mrb);
- req->out = (void *)req->elem.out_sg[0].iov_base;
- req->in = (void *)req->elem.in_sg[req->elem.in_num - 1].iov_base;
-
- if (req->out->type & VIRTIO_BLK_T_SCSI_CMD) {
- virtio_blk_handle_scsi(req);
- } else if (req->out->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);
- } else {
- qemu_iovec_init_external(&req->qiov, &req->elem.in_sg[0],
- req->elem.in_num - 1);
- virtio_blk_handle_read(req);
- }
- }
/*
* FIXME: Want to check for completions before returning to guest mode,
* so cached reads and writes are reported as quickly as possible. But
*/
}
-static void virtio_blk_dma_restart_cb(void *opaque, int running, int reason)
+static void virtio_blk_dma_restart_bh(void *opaque)
{
VirtIOBlock *s = opaque;
VirtIOBlockReq *req = s->rq;
+ MultiReqBuffer mrb = {
+ .num_writes = 0,
+ };
- if (!running)
- return;
+ qemu_bh_delete(s->bh);
+ s->bh = NULL;
s->rq = NULL;
while (req) {
- virtio_blk_handle_write(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, int reason)
+{
+ VirtIOBlock *s = opaque;
+
+ if (!running)
+ return;
+
+ 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)
qemu_aio_flush();
}
+/* coalesce internal state, copy to pci i/o region 0
+ */
static void virtio_blk_update_config(VirtIODevice *vdev, uint8_t *config)
{
VirtIOBlock *s = to_virtio_blk(vdev);
bdrv_get_geometry(s->bs, &capacity);
bdrv_get_geometry_hint(s->bs, &cylinders, &heads, &secs);
+ memset(&blkcfg, 0, sizeof(blkcfg));
stq_raw(&blkcfg.capacity, capacity);
stl_raw(&blkcfg.seg_max, 128 - 2);
stw_raw(&blkcfg.cylinders, cylinders);
blkcfg.heads = heads;
- blkcfg.sectors = secs;
- memcpy(config, &blkcfg, sizeof(blkcfg));
+ blkcfg.sectors = secs & ~s->sector_mask;
+ blkcfg.blk_size = s->conf->logical_block_size;
+ blkcfg.size_max = 0;
+ blkcfg.physical_block_exp = get_physical_block_exp(s->conf);
+ blkcfg.alignment_offset = 0;
+ blkcfg.min_io_size = s->conf->min_io_size / blkcfg.blk_size;
+ blkcfg.opt_io_size = s->conf->opt_io_size / blkcfg.blk_size;
+ memcpy(config, &blkcfg, sizeof(struct virtio_blk_config));
}
-static uint32_t virtio_blk_get_features(VirtIODevice *vdev)
+static uint32_t virtio_blk_get_features(VirtIODevice *vdev, uint32_t features)
{
- uint32_t features = 0;
+ VirtIOBlock *s = to_virtio_blk(vdev);
features |= (1 << VIRTIO_BLK_F_SEG_MAX);
features |= (1 << VIRTIO_BLK_F_GEOMETRY);
-#ifdef __linux__
- features |= (1 << VIRTIO_BLK_F_SCSI);
-#endif
+ features |= (1 << VIRTIO_BLK_F_TOPOLOGY);
+ features |= (1 << VIRTIO_BLK_F_BLK_SIZE);
+
+ if (bdrv_enable_write_cache(s->bs))
+ features |= (1 << VIRTIO_BLK_F_WCACHE);
+
+ if (bdrv_is_read_only(s->bs))
+ features |= 1 << VIRTIO_BLK_F_RO;
return features;
}
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->next;
+ 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_init(PCIDevice *pci_dev)
+VirtIODevice *virtio_blk_init(DeviceState *dev, BlockConf *conf)
{
VirtIOBlock *s;
int cylinders, heads, secs;
static int virtio_blk_id;
- BlockDriverState *bs;
+ DriveInfo *dinfo;
+
+ if (!conf->bs) {
+ error_report("virtio-blk-pci: drive property not set");
+ return NULL;
+ }
+ if (!bdrv_is_inserted(conf->bs)) {
+ error_report("Device needs media, but drive is empty");
+ return NULL;
+ }
- s = (VirtIOBlock *)virtio_init_pci(pci_dev, "virtio-blk",
- PCI_VENDOR_ID_REDHAT_QUMRANET,
- PCI_DEVICE_ID_VIRTIO_BLOCK,
- PCI_VENDOR_ID_REDHAT_QUMRANET,
- VIRTIO_ID_BLOCK,
- PCI_CLASS_STORAGE_OTHER, 0x00,
- sizeof(struct virtio_blk_config));
+ s = (VirtIOBlock *)virtio_common_init("virtio-blk", VIRTIO_ID_BLOCK,
+ sizeof(struct virtio_blk_config),
+ sizeof(VirtIOBlock));
- bs = qdev_init_bdrv(&pci_dev->qdev, IF_VIRTIO);
s->vdev.get_config = virtio_blk_update_config;
s->vdev.get_features = virtio_blk_get_features;
s->vdev.reset = virtio_blk_reset;
- s->bs = bs;
+ s->bs = conf->bs;
+ s->conf = conf;
s->rq = NULL;
- bs->private = &s->vdev.pci_dev;
+ s->sector_mask = (s->conf->logical_block_size / BDRV_SECTOR_SIZE) - 1;
bdrv_guess_geometry(s->bs, &cylinders, &heads, &secs);
- bdrv_set_geometry_hint(s->bs, cylinders, heads, secs);
+
+ /* NB: per existing s/n string convention the string is terminated
+ * by '\0' only when less than sizeof (s->sn)
+ */
+ dinfo = drive_get_by_blockdev(s->bs);
+ strncpy(s->sn, dinfo->serial, sizeof (s->sn));
s->vq = virtio_add_queue(&s->vdev, 128, virtio_blk_handle_output);
qemu_add_vm_change_state_handler(virtio_blk_dma_restart_cb, s);
- register_savevm("virtio-blk", virtio_blk_id++, 2,
+ s->qdev = dev;
+ register_savevm(dev, "virtio-blk", virtio_blk_id++, 2,
virtio_blk_save, virtio_blk_load, s);
+ bdrv_set_removable(s->bs, 0);
+
+ return &s->vdev;
}
-static void virtio_blk_register_devices(void)
+void virtio_blk_exit(VirtIODevice *vdev)
{
- pci_qdev_register("virtio-blk", sizeof(VirtIOBlock), virtio_blk_init);
+ VirtIOBlock *s = to_virtio_blk(vdev);
+ unregister_savevm(s->qdev, "virtio-blk", s);
}
-
-device_init(virtio_blk_register_devices)
projects / qemu.git / blobdiff