@@ -63,6 +63,20 @@ static size_t vub_iov_size(const struct iovec *iov,
return len;
}
+static size_t vub_iov_to_buf(const struct iovec *iov,
+ const unsigned int iov_cnt, void *buf)
+{
+ size_t len;
+ unsigned int i;
+
+ len = 0;
+ for (i = 0; i < iov_cnt; i++) {
+ memcpy(buf + len, iov[i].iov_base, iov[i].iov_len);
+ len += iov[i].iov_len;
+ }
+ return len;
+}
+
static void vub_panic_cb(VuDev *vu_dev, const char *buf)
{
VugDev *gdev;
@@ -161,6 +175,38 @@ vub_writev(VubReq *req, struct iovec *iov, uint32_t iovcnt)
return rc;
}
+static int
+vub_discard_write_zeroes(VubReq *req, struct iovec *iov, uint32_t iovcnt,
+ uint32_t type)
+{
+ struct virtio_blk_discard_write_zeroes desc;
+ ssize_t size;
+
+ size = vub_iov_size(iov, iovcnt);
+ if (size != sizeof(desc)) {
+ fprintf(stderr, "Invalid size %zd, expect %zu\n", size, sizeof(desc));
+ return -1;
+ }
+ vub_iov_to_buf(iov, iovcnt, &desc);
+
+ #if defined(__linux__) && defined(BLKDISCARD) && defined(BLKZEROOUT)
+ VubDev *vdev_blk = req->vdev_blk;
+ uint64_t range[2] = { le64toh(desc.sector) << 9,
+ le32toh(desc.num_sectors) << 9 };
+ if (type == VIRTIO_BLK_T_DISCARD) {
+ if (ioctl(vdev_blk->blk_fd, BLKDISCARD, range) == 0) {
+ return 0;
+ }
+ } else if (type == VIRTIO_BLK_T_WRITE_ZEROES) {
+ if (ioctl(vdev_blk->blk_fd, BLKZEROOUT, range) == 0) {
+ return 0;
+ }
+ }
+ #endif
+
+ return -1;
+}
+
static void
vub_flush(VubReq *req)
{
@@ -216,44 +262,55 @@ static int vub_virtio_process_req(VubDev *vdev_blk,
in_num--;
type = le32toh(req->out->type);
- switch (type & ~(VIRTIO_BLK_T_OUT | VIRTIO_BLK_T_BARRIER)) {
- case VIRTIO_BLK_T_IN: {
- ssize_t ret = 0;
- bool is_write = type & VIRTIO_BLK_T_OUT;
- req->sector_num = le64toh(req->out->sector);
- if (is_write) {
- ret = vub_writev(req, &elem->out_sg[1], out_num);
- } else {
- ret = vub_readv(req, &elem->in_sg[0], in_num);
- }
- if (ret >= 0) {
- req->in->status = VIRTIO_BLK_S_OK;
- } else {
- req->in->status = VIRTIO_BLK_S_IOERR;
- }
- vub_req_complete(req);
- break;
+ switch (type & ~VIRTIO_BLK_T_BARRIER) {
+ case VIRTIO_BLK_T_IN:
+ case VIRTIO_BLK_T_OUT: {
+ ssize_t ret = 0;
+ bool is_write = type & VIRTIO_BLK_T_OUT;
+ req->sector_num = le64toh(req->out->sector);
+ if (is_write) {
+ ret = vub_writev(req, &elem->out_sg[1], out_num);
+ } else {
+ ret = vub_readv(req, &elem->in_sg[0], in_num);
}
- case VIRTIO_BLK_T_FLUSH: {
- vub_flush(req);
+ if (ret >= 0) {
req->in->status = VIRTIO_BLK_S_OK;
- vub_req_complete(req);
- break;
+ } else {
+ req->in->status = VIRTIO_BLK_S_IOERR;
}
- case VIRTIO_BLK_T_GET_ID: {
- size_t size = MIN(vub_iov_size(&elem->in_sg[0], in_num),
- VIRTIO_BLK_ID_BYTES);
- snprintf(elem->in_sg[0].iov_base, size, "%s", "vhost_user_blk");
+ vub_req_complete(req);
+ break;
+ }
+ case VIRTIO_BLK_T_FLUSH:
+ vub_flush(req);
+ req->in->status = VIRTIO_BLK_S_OK;
+ vub_req_complete(req);
+ break;
+ case VIRTIO_BLK_T_GET_ID: {
+ size_t size = MIN(vub_iov_size(&elem->in_sg[0], in_num),
+ VIRTIO_BLK_ID_BYTES);
+ snprintf(elem->in_sg[0].iov_base, size, "%s", "vhost_user_blk");
+ req->in->status = VIRTIO_BLK_S_OK;
+ req->size = elem->in_sg[0].iov_len;
+ vub_req_complete(req);
+ break;
+ }
+ case VIRTIO_BLK_T_DISCARD:
+ case VIRTIO_BLK_T_WRITE_ZEROES: {
+ int rc;
+ rc = vub_discard_write_zeroes(req, &elem->out_sg[1], out_num, type);
+ if (rc == 0) {
req->in->status = VIRTIO_BLK_S_OK;
- req->size = elem->in_sg[0].iov_len;
- vub_req_complete(req);
- break;
- }
- default: {
- req->in->status = VIRTIO_BLK_S_UNSUPP;
- vub_req_complete(req);
- break;
+ } else {
+ req->in->status = VIRTIO_BLK_S_IOERR;
}
+ vub_req_complete(req);
+ break;
+ }
+ default:
+ req->in->status = VIRTIO_BLK_S_UNSUPP;
+ vub_req_complete(req);
+ break;
}
return 0;
@@ -317,6 +374,10 @@ vub_get_features(VuDev *dev)
1ull << VIRTIO_BLK_F_TOPOLOGY |
1ull << VIRTIO_BLK_F_BLK_SIZE |
1ull << VIRTIO_BLK_F_FLUSH |
+ #if defined(__linux__) && defined(BLKDISCARD) && defined(BLKZEROOUT)
+ 1ull << VIRTIO_BLK_F_DISCARD |
+ 1ull << VIRTIO_BLK_F_WRITE_ZEROES |
+ #endif
1ull << VIRTIO_BLK_F_CONFIG_WCE |
1ull << VIRTIO_F_VERSION_1 |
1ull << VHOST_USER_F_PROTOCOL_FEATURES;
@@ -478,6 +539,13 @@ vub_initialize_config(int fd, struct virtio_blk_config *config)
config->min_io_size = 1;
config->opt_io_size = 1;
config->num_queues = 1;
+ #if defined(__linux__) && defined(BLKDISCARD) && defined(BLKZEROOUT)
+ config->max_discard_sectors = 32768;
+ config->max_discard_seg = 1;
+ config->discard_sector_alignment = config->blk_size >> 9;
+ config->max_write_zeroes_sectors = 32768;
+ config->max_write_zeroes_seg = 1;
+ #endif
}
static VubDev *
@@ -38,6 +38,8 @@ static const int user_feature_bits[] = {
VIRTIO_BLK_F_RO,
VIRTIO_BLK_F_FLUSH,
VIRTIO_BLK_F_CONFIG_WCE,
+ VIRTIO_BLK_F_DISCARD,
+ VIRTIO_BLK_F_WRITE_ZEROES,
VIRTIO_F_VERSION_1,
VIRTIO_RING_F_INDIRECT_DESC,
VIRTIO_RING_F_EVENT_IDX,
@@ -204,6 +206,8 @@ static uint64_t vhost_user_blk_get_features(VirtIODevice *vdev,
virtio_add_feature(&features, VIRTIO_BLK_F_BLK_SIZE);
virtio_add_feature(&features, VIRTIO_BLK_F_FLUSH);
virtio_add_feature(&features, VIRTIO_BLK_F_RO);
+ virtio_add_feature(&features, VIRTIO_BLK_F_DISCARD);
+ virtio_add_feature(&features, VIRTIO_BLK_F_WRITE_ZEROES);
if (s->config_wce) {
virtio_add_feature(&features, VIRTIO_BLK_F_CONFIG_WCE);
@@ -38,6 +38,8 @@
#define VIRTIO_BLK_F_BLK_SIZE 6 /* Block size of disk is available*/
#define VIRTIO_BLK_F_TOPOLOGY 10 /* Topology information is available */
#define VIRTIO_BLK_F_MQ 12 /* support more than one vq */
+#define VIRTIO_BLK_F_DISCARD 13 /* DISCARD is supported */
+#define VIRTIO_BLK_F_WRITE_ZEROES 14 /* WRITE ZEROES is supported */
/* Legacy feature bits */
#ifndef VIRTIO_BLK_NO_LEGACY
@@ -84,6 +86,39 @@ struct virtio_blk_config {
/* number of vqs, only available when VIRTIO_BLK_F_MQ is set */
uint16_t num_queues;
+
+ /* the next 3 entries are guarded by VIRTIO_BLK_F_DISCARD */
+ /*
+ * The maximum discard sectors (in 512-byte sectors) for
+ * one segment.
+ */
+ uint32_t max_discard_sectors;
+ /*
+ * The maximum number of discard segments in a
+ * discard command.
+ */
+ uint32_t max_discard_seg;
+ /* Discard commands must be aligned to this number of sectors. */
+ uint32_t discard_sector_alignment;
+
+ /* the next 3 entries are guarded by VIRTIO_BLK_F_WRITE_ZEROES */
+ /*
+ * The maximum number of write zeroes sectors (in 512-byte sectors) in
+ * one segment.
+ */
+ uint32_t max_write_zeroes_sectors;
+ /*
+ * The maximum number of segments in a write zeroes
+ * command.
+ */
+ uint32_t max_write_zeroes_seg;
+ /*
+ * Set if a VIRTIO_BLK_T_WRITE_ZEROES request may result in the
+ * deallocation of one or more of the sectors.
+ */
+ uint8_t write_zeroes_may_unmap;
+
+ uint8_t unused1[3];
} QEMU_PACKED;
/*
@@ -112,6 +147,12 @@ struct virtio_blk_config {
/* Get device ID command */
#define VIRTIO_BLK_T_GET_ID 8
+/* Discard command */
+#define VIRTIO_BLK_T_DISCARD 11
+
+/* Write zeroes command */
+#define VIRTIO_BLK_T_WRITE_ZEROES 13
+
#ifndef VIRTIO_BLK_NO_LEGACY
/* Barrier before this op. */
#define VIRTIO_BLK_T_BARRIER 0x80000000
@@ -131,6 +172,19 @@ struct virtio_blk_outhdr {
__virtio64 sector;
};
+/* Unmap this range (only valid for write zeroes command) */
+#define VIRTIO_BLK_WRITE_ZEROES_FLAG_UNMAP 0x00000001
+
+/* Discard/write zeroes range for each request. */
+struct virtio_blk_discard_write_zeroes {
+ /* discard/write zeroes start sector */
+ uint64_t sector;
+ /* number of discard/write zeroes sectors */
+ uint32_t num_sectors;
+ /* flags for this range */
+ uint32_t flags;
+};
+
#ifndef VIRTIO_BLK_NO_LEGACY
struct virtio_scsi_inhdr {
__virtio32 errors;
Linux commit 1f23816b8 "virtio_blk: add discard and write zeroes support" added the support in the Guest kernel, while here also enable the features support with vhost-user-blk driver. Also enable the test example utility with DISCARD and WRITE ZEROES commands. Signed-off-by: Changpeng Liu <changpeng.liu@intel.com> --- contrib/vhost-user-blk/vhost-user-blk.c | 134 +++++++++++++++++++++------- hw/block/vhost-user-blk.c | 4 + include/standard-headers/linux/virtio_blk.h | 54 +++++++++++ 3 files changed, 159 insertions(+), 33 deletions(-)