vfio-user: add coalesced posted writes

Add new message to send multiple writes to server in a single message.
Prevents the outgoing queue from overflowing when a long latency
operation is followed by a series of posted writes.

Originally-by: John Johnson <john.g.johnson@oracle.com>
Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
Signed-off-by: John Levon <john.levon@nutanix.com>
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Link: https://lore.kernel.org/qemu-devel/20250625193012.2316242-18-john.levon@nutanix.com
Signed-off-by: Cédric Le Goater <clg@redhat.com>

1 files changed, 40 insertions, 0 deletions

diff --git a/hw/vfio-user/device.c b/hw/vfio-user/device.c
index aa07eac330..0609a7dc25 100644
--- a/hw/vfio-user/device.c
+++ b/hw/vfio-user/device.c
@@ -9,6 +9,8 @@
 #include "qemu/osdep.h"
 #include "qapi/error.h"
 #include "qemu/error-report.h"
+#include "qemu/lockable.h"
+#include "qemu/thread.h"
 
 #include "hw/vfio-user/device.h"
 #include "hw/vfio-user/trace.h"
@@ -337,6 +339,7 @@ static int vfio_user_device_io_region_write(VFIODevice *vbasedev, uint8_t index,
     VFIOUserProxy *proxy = vbasedev->proxy;
     int size = sizeof(*msgp) + count;
     Error *local_err = NULL;
+    bool can_multi;
     int flags = 0;
     int ret;
 
@@ -352,6 +355,43 @@ static int vfio_user_device_io_region_write(VFIODevice *vbasedev, uint8_t index,
         flags |= VFIO_USER_NO_REPLY;
     }
 
+    /* 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, off, 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, off, count, data);
+                return count;
+            }
+        }
+    }
+
     msgp = g_malloc0(size);
     vfio_user_request_msg(&msgp->hdr, VFIO_USER_REGION_WRITE, size, flags);
     msgp->offset = off;