[PATCH QEMU HCI-8.0 v8 07/14] usb-host: re-issue drained URBs if CPR is aborted #VSTOR-137800

[Andrey Drobyshev <andrey.drobyshev@virtuozzo.com>]

If CPR fails, the source VM resumes with the drained packets still owned
by the host controller as in-flight, and nothing left to complete them.

Remember the packets suppressed during the drain on a list, and re-issue
them on the preserved fd from the vm-state handler's resume branch -- it
runs on any resume but only acts once we have actually drained
(cpr_drained).  Control transfers cannot be reconstructed from the packet
alone, so complete those as errors and let the guest driver retry.

A re-issued transfer is replayed from the start of the TD, so a partial
transfer loses its progress -- an OUT fragment already consumed by the
device may be sent twice.  Only the paused-VM .pre_save() fallback queues
partial transfers for re-issue; the normal running-VM drain delivers them
as short transfers and is unaffected.

Signed-off-by: Andrey Drobyshev <andrey.drobyshev@virtuozzo.com>
---
 hw/usb/host-libusb.c | 79 ++++++++++++++++++++++++++++++++++++++++++++++++----
 1 file changed, 74 insertions(+), 5 deletions(-)

diff --git a/hw/usb/host-libusb.c b/hw/usb/host-libusb.c
index 413ddc12ee4..9cc7d72aa63 100644
--- a/hw/usb/host-libusb.c
+++ b/hw/usb/host-libusb.c
@@ -124,6 +124,7 @@ struct USBHostDevice {
     /* CPR migration */
     Error                            *cpr_blocker;
     VMChangeStateEntry               *cpr_vmse;
+    GSList                           *cpr_inflight;
     bool                             cpr_drained;
     bool                             cpr_replay_all;
 
@@ -169,6 +170,7 @@ static void usb_host_release_interfaces(USBHostDevice *s);
 static void usb_host_nodev(USBHostDevice *s);
 static void usb_host_detach_kernel(USBHostDevice *s);
 static void usb_host_attach_kernel(USBHostDevice *s);
+static void usb_host_handle_data(USBDevice *udev, USBPacket *p);
 
 /* ------------------------------------------------------------------------ */
 
@@ -433,9 +435,10 @@ static USBHostRequest *usb_host_req_find(USBHostDevice *s, USBPacket *p)
 /*
  * Classify a reap during the CPR drain (r->p is still set).  The paused-VM
  * fallback (cpr_replay_all) can't deliver completions, so it suppresses every
- * reap for the target to replay; otherwise one that moved no data is suppressed
- * and one that moved some is kept as a short transfer.  Returns true if
- * suppressed, so the caller frees the request.
+ * reap; otherwise one that moved no data is suppressed and one that moved some
+ * is kept as a short transfer.  Suppressed packets are queued on cpr_inflight
+ * for the target to replay.  Returns true if suppressed, so the caller frees
+ * the request.
  */
 static bool usb_host_req_cpr_replay(USBHostRequest *r,
                                     struct libusb_transfer *xfer)
@@ -462,6 +465,9 @@ static bool usb_host_req_cpr_replay(USBHostRequest *r,
             return false;
         }
     }
+    if (r->p->state == USB_PACKET_ASYNC) {
+        r->host->cpr_inflight = g_slist_append(r->host->cpr_inflight, r->p);
+    }
     return true;
 }
 
@@ -1284,16 +1290,74 @@ static int usb_host_cpr_quiesce(USBHostDevice *s, MigMode mode)
     return 0;
 }
 
+/*
+ * If CPR is aborted the source resumes with the drained packets still owned
+ * by the controller as in-flight; re-issue them on the preserved fd.  Control
+ * transfers can't be reconstructed from the packet, so error those out.
+ */
+static void usb_host_cpr_reissue(USBHostDevice *s)
+{
+    USBDevice *udev = USB_DEVICE(s);
+    GSList *it;
+    USBPacket *p;
+
+    if (!s->cpr_drained) {
+        return;
+    }
+
+    for (it = s->cpr_inflight; it; it = it->next) {
+        p = it->data;
+        /*
+         * Replay from the start of the TD.  A transfer that already moved some
+         * data is re-run in full, so an OUT fragment the device consumed may be
+         * sent twice.  Only the paused-VM pre_save fallback queues such partial
+         * transfers here; the normal drain delivers them as short transfers.
+         */
+        p->actual_length = 0;
+        if (p->ep->nr == 0) {
+            /* control endpoint: can't be reconstructed, so error it out */
+            p->status = USB_RET_IOERROR;
+            usb_generic_async_ctrl_complete(udev, p);
+        } else {
+            usb_host_handle_data(udev, p);
+            if (p->status != USB_RET_ASYNC) {
+                /* completed synchronously with an error */
+                if (usb_host_use_combining(p->ep)) {
+                    usb_combined_input_packet_complete(udev, p);
+                } else {
+                    usb_packet_complete(udev, p);
+                }
+            }
+        }
+    }
+    g_slist_free(s->cpr_inflight);
+    s->cpr_inflight = NULL;
+    s->cpr_replay_all = false;
+    s->cpr_drained = false;
+}
+
 /*
  * Run the CPR quiesce from the vm-state handler, on the stop-for-CPR
- * transition before the device/irqchip snapshot.
+ * transition before the device/irqchip snapshot, and re-issue the drained
+ * packets on resume if CPR was aborted.
  */
 static void usb_host_cpr_vm_state(void *opaque, bool running, RunState state)
 {
     USBHostDevice *s = opaque;
     MigMode mode;
 
-    if (running || !s->dh || state != RUN_STATE_FINISH_MIGRATE) {
+    if (running) {
+        /*
+         * Resume: re-issue drained packets and reset state, even if the
+         * device was lost between the drain and now (dh == NULL).
+         */
+        usb_host_cpr_reissue(s);
+        return;
+    }
+    if (!s->dh) {
+        return;
+    }
+    if (state != RUN_STATE_FINISH_MIGRATE) {
         return;
     }
     mode = migrate_mode();
@@ -1499,6 +1563,8 @@ static void usb_host_unrealize(USBDevice *udev)
     if (s->cpr_vmse) {
         qemu_del_vm_change_state_handler(s->cpr_vmse);
     }
+    g_slist_free(s->cpr_inflight);
+    s->cpr_inflight = NULL;
 }
 
 static void usb_host_cancel_packet(USBDevice *udev, USBPacket *p)
@@ -1506,6 +1572,9 @@ static void usb_host_cancel_packet(USBDevice *udev, USBPacket *p)
     USBHostDevice *s = USB_HOST_DEVICE(udev);
     USBHostRequest *r;
 
+    /* Packet is being cancelled -> it mustn't be re-issued on failed CPR */
+    s->cpr_inflight = g_slist_remove(s->cpr_inflight, p);
+
     if (p->combined) {
         usb_combined_packet_cancel(udev, p);
         return;

-- 
2.47.1