[Qemu-devel] [PATCH v8 11/20] virtio: add endian-ambivalent support to VirtIODevice

[Greg Kurz <gkurz@linux.vnet.ibm.com>]

Some CPU families can dynamically change their endianness. This means we
can have little endian ppc or big endian arm guests for example. This has
an impact on legacy virtio data structures since they are target endian.
We hence introduce a new property to track the endianness of each virtio
device. It is reasonnably assumed that endianness won't change while the
device is in use : we hence capture the device endianness when it gets
reset.

We migrate this property in a subsection, after the device descriptor. This
means the load code must not rely on it until it is restored. As a consequence,
the vring sanity checks had to be moved after the call to vmstate_load_state().
We enforce paranoia by poisoning the property at the begining of virtio_load().

Signed-off-by: Greg Kurz <gkurz@linux.vnet.ibm.com>
---

 Changes since last version (virtio migration RFC):
 - endianness cached at device reset time
 - reworked migration support

 hw/virtio/virtio-pci.c     |    8 ++--
 hw/virtio/virtio.c         |  100 +++++++++++++++++++++++++++++++++++++++-----
 include/hw/virtio/virtio.h |   12 ++++-
 3 files changed, 102 insertions(+), 18 deletions(-)

diff --git a/hw/virtio/virtio-pci.c b/hw/virtio/virtio-pci.c
index 390c8d2..2ffceb8 100644
--- a/hw/virtio/virtio-pci.c
+++ b/hw/virtio/virtio-pci.c
@@ -406,13 +406,13 @@ static uint64_t virtio_pci_config_read(void *opaque, hwaddr addr,
         break;
     case 2:
         val = virtio_config_readw(vdev, addr);
-        if (virtio_is_big_endian()) {
+        if (virtio_is_big_endian(vdev)) {
             val = bswap16(val);
         }
         break;
     case 4:
         val = virtio_config_readl(vdev, addr);
-        if (virtio_is_big_endian()) {
+        if (virtio_is_big_endian(vdev)) {
             val = bswap32(val);
         }
         break;
@@ -440,13 +440,13 @@ static void virtio_pci_config_write(void *opaque, hwaddr addr,
         virtio_config_writeb(vdev, addr, val);
         break;
     case 2:
-        if (virtio_is_big_endian()) {
+        if (virtio_is_big_endian(vdev)) {
             val = bswap16(val);
         }
         virtio_config_writew(vdev, addr, val);
         break;
     case 4:
-        if (virtio_is_big_endian()) {
+        if (virtio_is_big_endian(vdev)) {
             val = bswap32(val);
         }
         virtio_config_writel(vdev, addr, val);
diff --git a/hw/virtio/virtio.c b/hw/virtio/virtio.c
index 16b73d9..6235df8 100644
--- a/hw/virtio/virtio.c
+++ b/hw/virtio/virtio.c
@@ -545,6 +545,24 @@ void virtio_set_status(VirtIODevice *vdev, uint8_t val)
     vdev->status = val;
 }
 
+static void virtio_set_endian_target_default(VirtIODevice *vdev)
+{
+#ifdef TARGET_WORDS_BIGENDIAN
+    vdev->device_endian = VIRTIO_DEVICE_ENDIAN_BIG;
+#else
+    vdev->device_endian = VIRTIO_DEVICE_ENDIAN_LITTLE;
+#endif
+}
+
+static void virtio_set_endian_cpu(VirtIODevice *vdev, CPUState *cpu)
+{
+    if (cpu_virtio_is_big_endian(cpu)) {
+        vdev->device_endian = VIRTIO_DEVICE_ENDIAN_BIG;
+    } else {
+        vdev->device_endian = VIRTIO_DEVICE_ENDIAN_LITTLE;
+    }
+}
+
 void virtio_reset(void *opaque)
 {
     VirtIODevice *vdev = opaque;
@@ -552,6 +570,13 @@ void virtio_reset(void *opaque)
     int i;
 
     virtio_set_status(vdev, 0);
+    if (current_cpu) {
+        /* Guest initiated reset */
+        virtio_set_endian_cpu(vdev, current_cpu);
+    } else {
+        /* System reset */
+        virtio_set_endian_target_default(vdev);
+    }
 
     if (k->reset) {
         k->reset(vdev);
@@ -840,6 +865,28 @@ void virtio_notify_config(VirtIODevice *vdev)
     virtio_notify_vector(vdev, vdev->config_vector);
 }
 
+static bool virtio_device_endian_needed(void *opaque)
+{
+    VirtIODevice *vdev = opaque;
+
+    assert(vdev->device_endian != VIRTIO_DEVICE_ENDIAN_UNKNOWN);
+#ifdef TARGET_WORDS_BIGENDIAN
+    return vdev->device_endian == VIRTIO_DEVICE_ENDIAN_LITTLE;
+#else
+    return vdev->device_endian == VIRTIO_DEVICE_ENDIAN_BIG;
+#endif
+}
+
+static const VMStateDescription vmstate_virtio_device_endian = {
+    .name = "virtio/device_endian",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .fields = (VMStateField[]) {
+        VMSTATE_UINT8(device_endian, VirtIODevice),
+        VMSTATE_END_OF_LIST()
+    }
+};
+
 static const VMStateDescription vmstate_virtio = {
     .name = "virtio",
     .version_id = 1,
@@ -847,6 +894,13 @@ static const VMStateDescription vmstate_virtio = {
     .minimum_version_id_old = 1,
     .fields = (VMStateField[]) {
         VMSTATE_END_OF_LIST()
+    },
+    .subsections = (VMStateSubsection[]) {
+        {
+            .vmsd = &vmstate_virtio_device_endian,
+            .needed = &virtio_device_endian_needed
+        },
+        { 0 }
     }
 };
 
@@ -925,6 +979,12 @@ int virtio_load(VirtIODevice *vdev, QEMUFile *f, int version_id)
     VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus);
     VirtioDeviceClass *vdc = VIRTIO_DEVICE_GET_CLASS(vdev);
 
+    /*
+     * We poison the endianness to ensure it does not get used before
+     * subsections have been loaded.
+     */
+    vdev->device_endian = VIRTIO_DEVICE_ENDIAN_UNKNOWN;
+
     if (k->load_config) {
         ret = k->load_config(qbus->parent, f);
         if (ret)
@@ -971,18 +1031,7 @@ int virtio_load(VirtIODevice *vdev, QEMUFile *f, int version_id)
         vdev->vq[i].notification = true;
 
         if (vdev->vq[i].pa) {
-            uint16_t nheads;
             virtqueue_init(&vdev->vq[i]);
-            nheads = vring_avail_idx(&vdev->vq[i]) - vdev->vq[i].last_avail_idx;
-            /* Check it isn't doing very strange things with descriptor numbers. */
-            if (nheads > vdev->vq[i].vring.num) {
-                error_report("VQ %d size 0x%x Guest index 0x%x "
-                             "inconsistent with Host index 0x%x: delta 0x%x",
-                             i, vdev->vq[i].vring.num,
-                             vring_avail_idx(&vdev->vq[i]),
-                             vdev->vq[i].last_avail_idx, nheads);
-                return -1;
-            }
         } else if (vdev->vq[i].last_avail_idx) {
             error_report("VQ %d address 0x0 "
                          "inconsistent with Host index 0x%x",
@@ -1005,7 +1054,33 @@ int virtio_load(VirtIODevice *vdev, QEMUFile *f, int version_id)
         }
     }
 
-    return vmstate_load_state(f, &vmstate_virtio, vdev, 1);
+    /* Subsections */
+    ret = vmstate_load_state(f, &vmstate_virtio, vdev, 1);
+    if (ret) {
+        return ret;
+    }
+
+    if (vdev->device_endian == VIRTIO_DEVICE_ENDIAN_UNKNOWN) {
+        virtio_set_endian_target_default(vdev);
+    }
+
+    for (i = 0; i < num; i++) {
+        if (vdev->vq[i].pa) {
+            uint16_t nheads;
+            nheads = vring_avail_idx(&vdev->vq[i]) - vdev->vq[i].last_avail_idx;
+            /* Check it isn't doing strange things with descriptor numbers. */
+            if (nheads > vdev->vq[i].vring.num) {
+                error_report("VQ %d size 0x%x Guest index 0x%x "
+                             "inconsistent with Host index 0x%x: delta 0x%x",
+                             i, vdev->vq[i].vring.num,
+                             vring_avail_idx(&vdev->vq[i]),
+                             vdev->vq[i].last_avail_idx, nheads);
+                return -1;
+            }
+        }
+    }
+
+    return 0;
 }
 
 void virtio_cleanup(VirtIODevice *vdev)
@@ -1062,6 +1137,7 @@ void virtio_init(VirtIODevice *vdev, const char *name,
     }
     vdev->vmstate = qemu_add_vm_change_state_handler(virtio_vmstate_change,
                                                      vdev);
+    virtio_set_endian_target_default(vdev);
 }
 
 hwaddr virtio_queue_get_desc_addr(VirtIODevice *vdev, int n)
diff --git a/include/hw/virtio/virtio.h b/include/hw/virtio/virtio.h
index daf0bb2..a60104c 100644
--- a/include/hw/virtio/virtio.h
+++ b/include/hw/virtio/virtio.h
@@ -104,6 +104,12 @@ typedef struct VirtQueueElement
 #define VIRTIO_DEVICE(obj) \
         OBJECT_CHECK(VirtIODevice, (obj), TYPE_VIRTIO_DEVICE)
 
+enum virtio_device_endian {
+    VIRTIO_DEVICE_ENDIAN_UNKNOWN,
+    VIRTIO_DEVICE_ENDIAN_LITTLE,
+    VIRTIO_DEVICE_ENDIAN_BIG,
+};
+
 struct VirtIODevice
 {
     DeviceState parent_obj;
@@ -121,6 +127,7 @@ struct VirtIODevice
     bool vm_running;
     VMChangeStateEntry *vmstate;
     char *bus_name;
+    uint8_t device_endian;
 };
 
 typedef struct VirtioDeviceClass {
@@ -256,8 +263,9 @@ void virtio_queue_set_host_notifier_fd_handler(VirtQueue *vq, bool assign,
 void virtio_queue_notify_vq(VirtQueue *vq);
 void virtio_irq(VirtQueue *vq);
 
-static inline bool virtio_is_big_endian(void)
+static inline bool virtio_is_big_endian(VirtIODevice *vdev)
 {
-    return target_words_bigendian();
+    assert(vdev->device_endian != VIRTIO_DEVICE_ENDIAN_UNKNOWN);
+    return vdev->device_endian == VIRTIO_DEVICE_ENDIAN_BIG;
 }
 #endif