Add new message to send multiple writes to server
Signed-off-by: John G Johnson <john.g.john...@oracle.com>
Signed-off-by: Elena Ufimtseva <elena.ufimts...@oracle.com>
Signed-off-by: Jagannathan Raman <jag.ra...@oracle.com>
---
hw/vfio/user-protocol.h | 21 ++++++++
hw/vfio/user.c | 128 +++++++++++++++++++++++++++++++++++++++++++++++-
hw/vfio/user.h | 7 +++
3 files changed, 154 insertions(+), 2 deletions(-)
diff --git a/hw/vfio/user-protocol.h b/hw/vfio/user-protocol.h
index 6afd090..ffa222b 100644
--- a/hw/vfio/user-protocol.h
+++ b/hw/vfio/user-protocol.h
@@ -40,6 +40,7 @@ enum vfio_user_command {
VFIO_USER_DMA_WRITE = 12,
VFIO_USER_DEVICE_RESET = 13,
VFIO_USER_DIRTY_PAGES = 14,
+ VFIO_USER_REGION_WRITE_MULTI = 15,
VFIO_USER_MAX,
};
@@ -73,6 +74,7 @@ typedef struct {
#define VFIO_USER_CAP_PGSIZES "pgsizes"
#define VFIO_USER_CAP_MAP_MAX "max_dma_maps"
#define VFIO_USER_CAP_MIGR "migration"
+#define VFIO_USER_CAP_MULTI "write_multiple"
/* "migration" members */
#define VFIO_USER_CAP_PGSIZE "pgsize"
@@ -220,4 +222,23 @@ typedef struct {
char data[];
} VFIOUserBitmap;
+/*
+ * VFIO_USER_REGION_WRITE_MULTI
+ */
+#define VFIO_USER_MULTI_DATA 8
+#define VFIO_USER_MULTI_MAX 200
+
+typedef struct {
+ uint64_t offset;
+ uint32_t region;
+ uint32_t count;
+ char data[VFIO_USER_MULTI_DATA];
+} VFIOUserWROne;
+
+typedef struct {
+ VFIOUserHdr hdr;
+ uint64_t wr_cnt;
+ VFIOUserWROne wrs[VFIO_USER_MULTI_MAX];
+} VFIOUserWRMulti;
+
#endif /* VFIO_USER_PROTOCOL_H */
diff --git a/hw/vfio/user.c b/hw/vfio/user.c
index a9e6cf5..4ed305b 100644
--- a/hw/vfio/user.c
+++ b/hw/vfio/user.c
@@ -66,6 +66,7 @@ static void vfio_user_send_wait(VFIOProxy *proxy, VFIOUserHdr
*hdr,
static void vfio_user_wait_reqs(VFIOProxy *proxy);
static void vfio_user_request_msg(VFIOUserHdr *hdr, uint16_t cmd,
uint32_t size, uint32_t flags);
+static void vfio_user_flush_multi(VFIOProxy *proxy);
static inline void vfio_user_set_error(VFIOUserHdr *hdr, uint32_t err)
{
@@ -461,6 +462,11 @@ static void vfio_user_send(void *opaque)
}
qio_channel_set_aio_fd_handler(proxy->ioc, proxy->ctx,
vfio_user_recv, NULL, proxy);
+
+ /* queue empty - send any pending multi write msgs */
+ if (proxy->wr_multi != NULL) {
+ vfio_user_flush_multi(proxy);
+ }
}
}
@@ -481,6 +487,7 @@ static int vfio_user_send_one(VFIOProxy *proxy)
}
QTAILQ_REMOVE(&proxy->outgoing, msg, next);
+ proxy->num_outgoing--;
if (msg->type == VFIO_MSG_ASYNC) {
vfio_user_recycle(proxy, msg);
} else {
@@ -587,11 +594,18 @@ static int vfio_user_send_queued(VFIOProxy *proxy,
VFIOUserMsg *msg)
{
int ret;
+ /* older coalesced writes go first */
+ if (proxy->wr_multi != NULL &&
+ ((msg->hdr->flags & VFIO_USER_TYPE) == VFIO_USER_REQUEST)) {
+ vfio_user_flush_multi(proxy);
+ }
+
/*
* Unsent outgoing msgs - add to tail
*/
if (!QTAILQ_EMPTY(&proxy->outgoing)) {
QTAILQ_INSERT_TAIL(&proxy->outgoing, msg, next);
+ proxy->num_outgoing++;
return 0;
}
@@ -605,6 +619,7 @@ static int vfio_user_send_queued(VFIOProxy *proxy,
VFIOUserMsg *msg)
}
if (ret == QIO_CHANNEL_ERR_BLOCK) {
QTAILQ_INSERT_HEAD(&proxy->outgoing, msg, next);
+ proxy->num_outgoing = 1;
qio_channel_set_aio_fd_handler(proxy->ioc, proxy->ctx,
vfio_user_recv, vfio_user_send,
proxy);
@@ -1145,12 +1160,27 @@ static int check_migr(VFIOProxy *proxy, QObject *qobj,
Error **errp)
return caps_parse(proxy, qdict, caps_migr, errp);
}
+static int check_multi(VFIOProxy *proxy, QObject *qobj, Error **errp)
+{
+ QBool *qb = qobject_to(QBool, qobj);
+
+ if (qb == NULL) {
+ error_setg(errp, "malformed %s", VFIO_USER_CAP_MULTI);
+ return -1;
+ }
+ if (qbool_get_bool(qb)) {
+ proxy->flags |= VFIO_PROXY_USE_MULTI;
+ }
+ return 0;
+}
+
static struct cap_entry caps_cap[] = {
{ VFIO_USER_CAP_MAX_FDS, check_max_fds },
{ VFIO_USER_CAP_MAX_XFER, check_max_xfer },
{ VFIO_USER_CAP_PGSIZES, check_pgsizes },
{ VFIO_USER_CAP_MAP_MAX, check_max_dma },
{ VFIO_USER_CAP_MIGR, check_migr },
+ { VFIO_USER_CAP_MULTI, check_multi },
{ NULL }
};
@@ -1209,6 +1239,7 @@ static GString *caps_json(void)
qdict_put_int(capdict, VFIO_USER_CAP_MAX_XFER, VFIO_USER_DEF_MAX_XFER);
qdict_put_int(capdict, VFIO_USER_CAP_PGSIZES, VFIO_USER_DEF_PGSIZE);
qdict_put_int(capdict, VFIO_USER_CAP_MAP_MAX, VFIO_USER_DEF_MAP_MAX);
+ qdict_put_bool(capdict, VFIO_USER_CAP_MULTI, true);
qdict_put_obj(dict, VFIO_USER_CAP, QOBJECT(capdict));
@@ -1547,18 +1578,111 @@ static int vfio_user_region_read(VFIOProxy *proxy,
uint8_t index, off_t offset,
return msgp->count;
}
+static void vfio_user_flush_multi(VFIOProxy *proxy)
+{
+ VFIOUserMsg *msg;
+ VFIOUserWRMulti *wm = proxy->wr_multi;
+ int ret;
+
+ proxy->wr_multi = NULL;
+
+ /* adjust size for actual # of writes */
+ wm->hdr.size -= (VFIO_USER_MULTI_MAX - wm->wr_cnt) * sizeof(VFIOUserWROne);
+
+ msg = vfio_user_getmsg(proxy, &wm->hdr, NULL);
+ msg->id = wm->hdr.id;
+ msg->rsize = 0;
+ msg->type = VFIO_MSG_ASYNC;
+
+ ret = vfio_user_send_queued(proxy, msg);
+ if (ret < 0) {
+ vfio_user_recycle(proxy, msg);
+ }
+}
+
+static void vfio_user_create_multi(VFIOProxy *proxy)
+{
+ VFIOUserWRMulti *wm;
+
+ wm = g_malloc0(sizeof(*wm));
+ vfio_user_request_msg(&wm->hdr, VFIO_USER_REGION_WRITE_MULTI,
+ sizeof(*wm), VFIO_USER_NO_REPLY);
+ proxy->wr_multi = wm;
+}
+
+static void vfio_user_add_multi(VFIOProxy *proxy, uint8_t index, off_t offset,
+ uint32_t count, void *data)
+{
+ VFIOUserWRMulti *wm = proxy->wr_multi;
+ VFIOUserWROne *w1 = &wm->wrs[wm->wr_cnt];
+
+ w1->offset = offset;
+ w1->region = index;
+ w1->count = count;
+ memcpy(&w1->data, data, count);
+
+ wm->wr_cnt++;
+ if (wm->wr_cnt == VFIO_USER_MULTI_MAX ||
+ proxy->num_outgoing < VFIO_USER_OUT_LOW) {
+ vfio_user_flush_multi(proxy);
+ }
+}
+
static int vfio_user_region_write(VFIOProxy *proxy, uint8_t index, off_t
offset,
uint32_t count, void *data, bool post)
{
VFIOUserRegionRW *msgp = NULL;
- int flags = post ? VFIO_USER_NO_REPLY : 0;
+ int flags;
int size = sizeof(*msgp) + count;
+ bool can_multi;
int ret;
if (count > proxy->max_xfer_size) {
return -EINVAL;
}
+ if (proxy->flags & VFIO_PROXY_NO_POST) {
+ post = false;
+ }
+
+ /* write eligible to be in a WRITE_MULTI msg ? */
+ can_multi = (proxy->flags & VFIO_PROXY_USE_MULTI) && post &&
+ count <= VFIO_USER_MULTI_DATA;
+
+ /*
+ * This should be a rare case, so first check without the lock,
+ * if we're wrong, vfio_send_queued() will flush any posted writes
+ * we missed here
+ */
+ if (proxy->wr_multi != NULL ||
+ (proxy->num_outgoing > VFIO_USER_OUT_HIGH && can_multi)) {
+
+ /*
+ * re-check with lock
+ *
+ * if already building a WRITE_MULTI msg,
+ * add this one if possible else flush pending before
+ * sending the current one
+ *
+ * else if outgoing queue is over the highwater,
+ * start a new WRITE_MULTI message
+ */
+ WITH_QEMU_LOCK_GUARD(&proxy->lock) {
+ if (proxy->wr_multi != NULL) {
+ if (can_multi) {
+ vfio_user_add_multi(proxy, index, offset, count, data);
+ return count;
+ }
+ vfio_user_flush_multi(proxy);
+ } else if (proxy->num_outgoing > VFIO_USER_OUT_HIGH && can_multi) {
+ vfio_user_create_multi(proxy);
+ vfio_user_add_multi(proxy, index, offset, count, data);
+ return count;
+ }
+ }
+ }
+
+ flags = post ? VFIO_USER_NO_REPLY : 0;
msgp = g_malloc0(size);
vfio_user_request_msg(&msgp->hdr, VFIO_USER_REGION_WRITE, size, flags);
msgp->offset = offset;
@@ -1567,7 +1691,7 @@ static int vfio_user_region_write(VFIOProxy *proxy,
uint8_t index, off_t offset,
memcpy(&msgp->data, data, count);
/* async send will free msg after it's sent */
- if (post && !(proxy->flags & VFIO_PROXY_NO_POST)) {
+ if (post) {
vfio_user_send_async(proxy, &msgp->hdr, NULL);
return count;
}
diff --git a/hw/vfio/user.h b/hw/vfio/user.h
index f711861..c96e74a 100644
--- a/hw/vfio/user.h
+++ b/hw/vfio/user.h
@@ -79,6 +79,8 @@ typedef struct VFIOProxy {
VFIOUserMsg *last_nowait;
VFIOUserMsg *part_recv;
size_t recv_left;
+ VFIOUserWRMulti *wr_multi;
+ int num_outgoing;
enum proxy_state state;
} VFIOProxy;
@@ -87,6 +89,11 @@ typedef struct VFIOProxy {
#define VFIO_PROXY_SECURE 0x2
#define VFIO_PROXY_FORCE_QUEUED 0x4
#define VFIO_PROXY_NO_POST 0x8
+#define VFIO_PROXY_USE_MULTI 0x10
+
+/* coalescing high and low water marks for VFIOProxy num_outgoing */
+#define VFIO_USER_OUT_HIGH 1024
+#define VFIO_USER_OUT_LOW 128
VFIOProxy *vfio_user_connect_dev(SocketAddress *addr, Error **errp);
void vfio_user_disconnect(VFIOProxy *proxy);
--
1.8.3.1
