#include "trace.h"
#include "qemu-error.h"
#include "virtio.h"
-#include "sysemu.h"
/* The alignment to use between consumer and producer parts of vring.
* x86 pagesize again. */
VRing vring;
target_phys_addr_t pa;
uint16_t last_avail_idx;
+ /* Last used index value we have signalled on */
+ uint16_t signalled_used;
+
+ /* Last used index value we have signalled on */
+ bool signalled_used_valid;
+
+ /* Notification enabled? */
+ bool notification;
+
int inuse;
+
uint16_t vector;
void (*handle_output)(VirtIODevice *vdev, VirtQueue *vq);
VirtIODevice *vdev;
return lduw_phys(pa);
}
+static inline uint16_t vring_used_event(VirtQueue *vq)
+{
+ return vring_avail_ring(vq, vq->vring.num);
+}
+
static inline void vring_used_ring_id(VirtQueue *vq, int i, uint32_t val)
{
target_phys_addr_t pa;
return lduw_phys(pa);
}
-static inline void vring_used_idx_increment(VirtQueue *vq, uint16_t val)
+static inline void vring_used_idx_set(VirtQueue *vq, uint16_t val)
{
target_phys_addr_t pa;
pa = vq->vring.used + offsetof(VRingUsed, idx);
- stw_phys(pa, vring_used_idx(vq) + val);
+ stw_phys(pa, val);
}
static inline void vring_used_flags_set_bit(VirtQueue *vq, int mask)
stw_phys(pa, lduw_phys(pa) & ~mask);
}
+static inline void vring_avail_event(VirtQueue *vq, uint16_t val)
+{
+ target_phys_addr_t pa;
+ if (!vq->notification) {
+ return;
+ }
+ pa = vq->vring.used + offsetof(VRingUsed, ring[vq->vring.num]);
+ stw_phys(pa, val);
+}
+
void virtio_queue_set_notification(VirtQueue *vq, int enable)
{
- if (enable)
+ vq->notification = enable;
+ if (vq->vdev->guest_features & (1 << VIRTIO_RING_F_EVENT_IDX)) {
+ vring_avail_event(vq, vring_avail_idx(vq));
+ } else if (enable) {
vring_used_flags_unset_bit(vq, VRING_USED_F_NO_NOTIFY);
- else
+ } else {
vring_used_flags_set_bit(vq, VRING_USED_F_NO_NOTIFY);
+ }
}
int virtio_queue_ready(VirtQueue *vq)
void virtqueue_flush(VirtQueue *vq, unsigned int count)
{
+ uint16_t old, new;
/* Make sure buffer is written before we update index. */
wmb();
trace_virtqueue_flush(vq, count);
- vring_used_idx_increment(vq, count);
+ old = vring_used_idx(vq);
+ new = old + count;
+ vring_used_idx_set(vq, new);
vq->inuse -= count;
+ if (unlikely((int16_t)(new - vq->signalled_used) < (uint16_t)(new - old)))
+ vq->signalled_used_valid = false;
}
void virtqueue_push(VirtQueue *vq, const VirtQueueElement *elem,
max = vq->vring.num;
i = head = virtqueue_get_head(vq, vq->last_avail_idx++);
+ if (vq->vdev->guest_features & (1 << VIRTIO_RING_F_EVENT_IDX)) {
+ vring_avail_event(vq, vring_avail_idx(vq));
+ }
if (vring_desc_flags(desc_pa, i) & VRING_DESC_F_INDIRECT) {
if (vring_desc_len(desc_pa, i) % sizeof(VRingDesc)) {
struct iovec *sg;
if (vring_desc_flags(desc_pa, i) & VRING_DESC_F_WRITE) {
+ if (elem->in_num >= ARRAY_SIZE(elem->in_sg)) {
+ error_report("Too many write descriptors in indirect table");
+ exit(1);
+ }
elem->in_addr[elem->in_num] = vring_desc_addr(desc_pa, i);
sg = &elem->in_sg[elem->in_num++];
} else {
+ if (elem->out_num >= ARRAY_SIZE(elem->out_sg)) {
+ error_report("Too many read descriptors in indirect table");
+ exit(1);
+ }
elem->out_addr[elem->out_num] = vring_desc_addr(desc_pa, i);
sg = &elem->out_sg[elem->out_num++];
}
vdev->vq[i].last_avail_idx = 0;
vdev->vq[i].pa = 0;
vdev->vq[i].vector = VIRTIO_NO_VECTOR;
+ vdev->vq[i].signalled_used = 0;
+ vdev->vq[i].signalled_used_valid = false;
+ vdev->vq[i].notification = true;
}
}
return vdev->vq[n].vring.num;
}
-void virtio_queue_notify(VirtIODevice *vdev, int n)
+void virtio_queue_notify_vq(VirtQueue *vq)
{
- if (n < VIRTIO_PCI_QUEUE_MAX && vdev->vq[n].vring.desc) {
- trace_virtio_queue_notify(vdev, n, &vdev->vq[n]);
- vdev->vq[n].handle_output(vdev, &vdev->vq[n]);
+ if (vq->vring.desc) {
+ VirtIODevice *vdev = vq->vdev;
+ trace_virtio_queue_notify(vdev, vq - vdev->vq, vq);
+ vq->handle_output(vdev, vq);
}
}
+void virtio_queue_notify(VirtIODevice *vdev, int n)
+{
+ virtio_queue_notify_vq(&vdev->vq[n]);
+}
+
uint16_t virtio_queue_vector(VirtIODevice *vdev, int n)
{
return n < VIRTIO_PCI_QUEUE_MAX ? vdev->vq[n].vector :
virtio_notify_vector(vq->vdev, vq->vector);
}
-void virtio_notify(VirtIODevice *vdev, VirtQueue *vq)
+/* Assuming a given event_idx value from the other size, if
+ * we have just incremented index from old to new_idx,
+ * should we trigger an event? */
+static inline int vring_need_event(uint16_t event, uint16_t new, uint16_t old)
{
+ /* Note: Xen has similar logic for notification hold-off
+ * in include/xen/interface/io/ring.h with req_event and req_prod
+ * corresponding to event_idx + 1 and new respectively.
+ * Note also that req_event and req_prod in Xen start at 1,
+ * event indexes in virtio start at 0. */
+ return (uint16_t)(new - event - 1) < (uint16_t)(new - old);
+}
+
+static bool vring_notify(VirtIODevice *vdev, VirtQueue *vq)
+{
+ uint16_t old, new;
+ bool v;
/* Always notify when queue is empty (when feature acknowledge) */
- if ((vring_avail_flags(vq) & VRING_AVAIL_F_NO_INTERRUPT) &&
- (!(vdev->guest_features & (1 << VIRTIO_F_NOTIFY_ON_EMPTY)) ||
- (vq->inuse || vring_avail_idx(vq) != vq->last_avail_idx)))
+ if (((vdev->guest_features & (1 << VIRTIO_F_NOTIFY_ON_EMPTY)) &&
+ !vq->inuse && vring_avail_idx(vq) == vq->last_avail_idx)) {
+ return true;
+ }
+
+ if (!(vdev->guest_features & (1 << VIRTIO_RING_F_EVENT_IDX))) {
+ return !(vring_avail_flags(vq) & VRING_AVAIL_F_NO_INTERRUPT);
+ }
+
+ v = vq->signalled_used_valid;
+ vq->signalled_used_valid = true;
+ old = vq->signalled_used;
+ new = vq->signalled_used = vring_used_idx(vq);
+ return !v || vring_need_event(vring_used_event(vq), new, old);
+}
+
+void virtio_notify(VirtIODevice *vdev, VirtQueue *vq)
+{
+ if (!vring_notify(vdev, vq)) {
return;
+ }
trace_virtio_notify(vdev, vq);
vdev->isr |= 0x01;
uint32_t features;
uint32_t supported_features =
vdev->binding->get_features(vdev->binding_opaque);
- uint16_t num_heads;
if (vdev->binding->load_config) {
ret = vdev->binding->load_config(vdev->binding_opaque, f);
vdev->vq[i].vring.num = qemu_get_be32(f);
vdev->vq[i].pa = qemu_get_be64(f);
qemu_get_be16s(f, &vdev->vq[i].last_avail_idx);
+ vdev->vq[i].signalled_used_valid = false;
+ vdev->vq[i].notification = true;
if (vdev->vq[i].pa) {
+ uint16_t nheads;
virtqueue_init(&vdev->vq[i]);
- }
- num_heads = vring_avail_idx(&vdev->vq[i]) - vdev->vq[i].last_avail_idx;
- /* Check it isn't doing very strange things with descriptor numbers. */
- if (num_heads > 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, num_heads);
- return -1;
+ 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",
+ i, vdev->vq[i].last_avail_idx);
+ return -1;
}
if (vdev->binding->load_queue) {
ret = vdev->binding->load_queue(vdev->binding_opaque, i, f);
void virtio_cleanup(VirtIODevice *vdev)
{
+ qemu_del_vm_change_state_handler(vdev->vmstate);
if (vdev->config)
qemu_free(vdev->config);
qemu_free(vdev->vq);
}
+static void virtio_vmstate_change(void *opaque, int running, int reason)
+{
+ VirtIODevice *vdev = opaque;
+ bool backend_run = running && (vdev->status & VIRTIO_CONFIG_S_DRIVER_OK);
+ vdev->vm_running = running;
+
+ if (backend_run) {
+ virtio_set_status(vdev, vdev->status);
+ }
+
+ if (vdev->binding->vmstate_change) {
+ vdev->binding->vmstate_change(vdev->binding_opaque, backend_run);
+ }
+
+ if (!backend_run) {
+ virtio_set_status(vdev, vdev->status);
+ }
+}
+
VirtIODevice *virtio_common_init(const char *name, uint16_t device_id,
size_t config_size, size_t struct_size)
{
vdev->queue_sel = 0;
vdev->config_vector = VIRTIO_NO_VECTOR;
vdev->vq = qemu_mallocz(sizeof(VirtQueue) * VIRTIO_PCI_QUEUE_MAX);
+ vdev->vm_running = vm_running;
for(i = 0; i < VIRTIO_PCI_QUEUE_MAX; i++) {
vdev->vq[i].vector = VIRTIO_NO_VECTOR;
vdev->vq[i].vdev = vdev;
else
vdev->config = NULL;
+ vdev->vmstate = qemu_add_vm_change_state_handler(virtio_vmstate_change, vdev);
+
return vdev;
}