VIRTIO CORE, NET AND BLOCK DRIVERS
M: "Michael S. Tsirkin" <mst@redhat.com>
+M: Jason Wang <jasowang@redhat.com>
L: virtualization@lists.linux-foundation.org
S: Maintained
F: Documentation/devicetree/bindings/virtio/
VIRTIO HOST (VHOST)
M: "Michael S. Tsirkin" <mst@redhat.com>
+M: Jason Wang <jasowang@redhat.com>
L: kvm@vger.kernel.org
L: virtualization@lists.linux-foundation.org
L: netdev@vger.kernel.org
static int init_vq(struct virtio_blk *vblk)
{
- int err = 0;
+ int err;
int i;
vq_callback_t **callbacks;
const char **names;
if (err)
num_vqs = 1;
- vblk->vqs = kmalloc(sizeof(*vblk->vqs) * num_vqs, GFP_KERNEL);
+ vblk->vqs = kmalloc_array(num_vqs, sizeof(*vblk->vqs), GFP_KERNEL);
if (!vblk->vqs)
return -ENOMEM;
- names = kmalloc(sizeof(*names) * num_vqs, GFP_KERNEL);
- callbacks = kmalloc(sizeof(*callbacks) * num_vqs, GFP_KERNEL);
- vqs = kmalloc(sizeof(*vqs) * num_vqs, GFP_KERNEL);
+ names = kmalloc_array(num_vqs, sizeof(*names), GFP_KERNEL);
+ callbacks = kmalloc_array(num_vqs, sizeof(*callbacks), GFP_KERNEL);
+ vqs = kmalloc_array(num_vqs, sizeof(*vqs), GFP_KERNEL);
if (!names || !callbacks || !vqs) {
err = -ENOMEM;
goto out;
spin_lock_irq(&port->inbuf_lock);
/* Remove unused data this port might have received. */
discard_port_data(port);
+ spin_unlock_irq(&port->inbuf_lock);
/* Remove buffers we queued up for the Host to send us data in. */
- while ((buf = virtqueue_detach_unused_buf(port->in_vq)))
- free_buf(buf, true);
- spin_unlock_irq(&port->inbuf_lock);
+ do {
+ spin_lock_irq(&port->inbuf_lock);
+ buf = virtqueue_detach_unused_buf(port->in_vq);
+ spin_unlock_irq(&port->inbuf_lock);
+ if (buf)
+ free_buf(buf, true);
+ } while (buf);
spin_lock_irq(&port->outvq_lock);
reclaim_consumed_buffers(port);
+ spin_unlock_irq(&port->outvq_lock);
/* Free pending buffers from the out-queue. */
- while ((buf = virtqueue_detach_unused_buf(port->out_vq)))
- free_buf(buf, true);
- spin_unlock_irq(&port->outvq_lock);
+ do {
+ spin_lock_irq(&port->outvq_lock);
+ buf = virtqueue_detach_unused_buf(port->out_vq);
+ spin_unlock_irq(&port->outvq_lock);
+ if (buf)
+ free_buf(buf, true);
+ } while (buf);
}
/*
+++ /dev/null
-/* Configuration space parsing helpers for virtio.
- *
- * The configuration is [type][len][... len bytes ...] fields.
- *
- * Copyright 2007 Rusty Russell, IBM Corporation.
- * GPL v2 or later.
- */
-#include <linux/err.h>
-#include <linux/virtio.h>
-#include <linux/virtio_config.h>
-#include <linux/bug.h>
-
virtio_device_ready(vdev);
+ if (towards_target(vb))
+ virtballoon_changed(vdev);
return 0;
out_del_vqs:
return -ENODEV;
}
- rc = dma_set_mask_and_coherent(&pci_dev->dev, DMA_BIT_MASK(64));
- if (rc)
- rc = dma_set_mask_and_coherent(&pci_dev->dev,
- DMA_BIT_MASK(32));
+ rc = dma_set_mask(&pci_dev->dev, DMA_BIT_MASK(64));
+ if (rc) {
+ rc = dma_set_mask_and_coherent(&pci_dev->dev, DMA_BIT_MASK(32));
+ } else {
+ /*
+ * The virtio ring base address is expressed as a 32-bit PFN,
+ * with a page size of 1 << VIRTIO_PCI_QUEUE_ADDR_SHIFT.
+ */
+ dma_set_coherent_mask(&pci_dev->dev,
+ DMA_BIT_MASK(32 + VIRTIO_PCI_QUEUE_ADDR_SHIFT));
+ }
+
if (rc)
dev_warn(&pci_dev->dev, "Failed to enable 64-bit or 32-bit DMA. Trying to continue, but this might not work.\n");
* making all of the arch DMA ops work on the vring device itself
* is a mess. For now, we use the parent device for DMA ops.
*/
-static struct device *vring_dma_dev(const struct vring_virtqueue *vq)
+static inline struct device *vring_dma_dev(const struct vring_virtqueue *vq)
{
return vq->vq.vdev->dev.parent;
}
if (!(vq->avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT)) {
vq->avail_flags_shadow |= VRING_AVAIL_F_NO_INTERRUPT;
- vq->vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->avail_flags_shadow);
+ if (!vq->event)
+ vq->vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->avail_flags_shadow);
}
}
* entry. Always do both to keep code simple. */
if (vq->avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT) {
vq->avail_flags_shadow &= ~VRING_AVAIL_F_NO_INTERRUPT;
- vq->vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->avail_flags_shadow);
+ if (!vq->event)
+ vq->vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->avail_flags_shadow);
}
vring_used_event(&vq->vring) = cpu_to_virtio16(_vq->vdev, last_used_idx = vq->last_used_idx);
END_USE(vq);
* more to do. */
/* Depending on the VIRTIO_RING_F_USED_EVENT_IDX feature, we need to
* either clear the flags bit or point the event index at the next
- * entry. Always do both to keep code simple. */
+ * entry. Always update the event index to keep code simple. */
if (vq->avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT) {
vq->avail_flags_shadow &= ~VRING_AVAIL_F_NO_INTERRUPT;
- vq->vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->avail_flags_shadow);
+ if (!vq->event)
+ vq->vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->avail_flags_shadow);
}
/* TODO: tune this threshold */
bufs = (u16)(vq->avail_idx_shadow - vq->last_used_idx) * 3 / 4;
/* No callback? Tell other side not to bother us. */
if (!callback) {
vq->avail_flags_shadow |= VRING_AVAIL_F_NO_INTERRUPT;
- vq->vring.avail->flags = cpu_to_virtio16(vdev, vq->avail_flags_shadow);
+ if (!vq->event)
+ vq->vring.avail->flags = cpu_to_virtio16(vdev, vq->avail_flags_shadow);
}
/* Put everything in free lists. */
all: ring virtio_ring_0_9 virtio_ring_poll virtio_ring_inorder ptr_ring noring
CFLAGS += -Wall
-CFLAGS += -pthread -O2 -ggdb
-LDFLAGS += -pthread -O2 -ggdb
+CFLAGS += -pthread -O2 -ggdb -flto -fwhole-program
+LDFLAGS += -pthread -O2 -ggdb -flto -fwhole-program
main.o: main.c main.h
ring.o: ring.c main.h
assert(!ret);
}
-static void run_guest(void)
+void poll_used(void)
+{
+ while (used_empty())
+ busy_wait();
+}
+
+static void __attribute__((__flatten__)) run_guest(void)
{
int completed_before;
int completed = 0;
assert(completed <= bufs);
assert(started <= bufs);
if (do_sleep) {
- if (enable_call())
+ if (used_empty() && enable_call())
wait_for_call();
} else {
poll_used();
}
}
-static void run_host(void)
+void poll_avail(void)
+{
+ while (avail_empty())
+ busy_wait();
+}
+
+static void __attribute__((__flatten__)) run_host(void)
{
int completed_before;
int completed = 0;
for (;;) {
if (do_sleep) {
- if (enable_kick())
+ if (avail_empty() && enable_kick())
wait_for_kick();
} else {
poll_avail();
int add_inbuf(unsigned, void *, void *);
void *get_buf(unsigned *, void **);
void disable_call();
+bool used_empty();
bool enable_call();
void kick_available();
-void poll_used();
/* host side */
void disable_kick();
+bool avail_empty();
bool enable_kick();
bool use_buf(unsigned *, void **);
void call_used();
-void poll_avail();
/* implemented by main */
extern bool do_sleep;
return "Buffer";
}
-void poll_used(void)
+bool used_empty()
{
+ return false;
}
void disable_call()
assert(0);
}
-void poll_avail(void)
+bool avail_empty()
{
+ return false;
}
bool use_buf(unsigned *lenp, void **bufp)
return datap;
}
-void poll_used(void)
+bool used_empty()
{
- void *b;
-
- do {
- if (tailcnt == headcnt || __ptr_ring_full(&array)) {
- b = NULL;
- barrier();
- } else {
- b = "Buffer\n";
- }
- } while (!b);
+ return (tailcnt == headcnt || __ptr_ring_full(&array));
}
void disable_call()
assert(0);
}
-void poll_avail(void)
+bool avail_empty()
{
- void *b;
-
- do {
- barrier();
- b = __ptr_ring_peek(&array);
- } while (!b);
+ return !__ptr_ring_peek(&array);
}
bool use_buf(unsigned *lenp, void **bufp)
return datap;
}
-void poll_used(void)
+bool used_empty()
{
unsigned head = (ring_size - 1) & guest.last_used_idx;
- while (ring[head].flags & DESC_HW)
- busy_wait();
+ return (ring[head].flags & DESC_HW);
}
void disable_call()
bool enable_call()
{
- unsigned head = (ring_size - 1) & guest.last_used_idx;
-
event->call_index = guest.last_used_idx;
/* Flush call index write */
/* Barrier D (for pairing) */
smp_mb();
- return ring[head].flags & DESC_HW;
+ return used_empty();
}
void kick_available(void)
bool enable_kick()
{
- unsigned head = (ring_size - 1) & host.used_idx;
-
event->kick_index = host.used_idx;
/* Barrier C (for pairing) */
smp_mb();
- return !(ring[head].flags & DESC_HW);
+ return avail_empty();
}
-void poll_avail(void)
+bool avail_empty()
{
unsigned head = (ring_size - 1) & host.used_idx;
- while (!(ring[head].flags & DESC_HW))
- busy_wait();
+ return !(ring[head].flags & DESC_HW);
}
bool use_buf(unsigned *lenp, void **bufp)
return datap;
}
-void poll_used(void)
+bool used_empty()
{
+ unsigned short last_used_idx = guest.last_used_idx;
#ifdef RING_POLL
- unsigned head = (ring_size - 1) & guest.last_used_idx;
+ unsigned short head = last_used_idx & (ring_size - 1);
+ unsigned index = ring.used->ring[head].id;
- for (;;) {
- unsigned index = ring.used->ring[head].id;
-
- if ((index ^ guest.last_used_idx ^ 0x8000) & ~(ring_size - 1))
- busy_wait();
- else
- break;
- }
+ return (index ^ last_used_idx ^ 0x8000) & ~(ring_size - 1);
#else
- unsigned head = guest.last_used_idx;
-
- while (ring.used->idx == head)
- busy_wait();
+ return ring.used->idx == last_used_idx;
#endif
}
bool enable_call()
{
- unsigned short last_used_idx;
-
- vring_used_event(&ring) = (last_used_idx = guest.last_used_idx);
+ vring_used_event(&ring) = guest.last_used_idx;
/* Flush call index write */
/* Barrier D (for pairing) */
smp_mb();
-#ifdef RING_POLL
- {
- unsigned short head = last_used_idx & (ring_size - 1);
- unsigned index = ring.used->ring[head].id;
-
- return (index ^ last_used_idx ^ 0x8000) & ~(ring_size - 1);
- }
-#else
- return ring.used->idx == last_used_idx;
-#endif
+ return used_empty();
}
void kick_available(void)
bool enable_kick()
{
- unsigned head = host.used_idx;
-
- vring_avail_event(&ring) = head;
+ vring_avail_event(&ring) = host.used_idx;
/* Barrier C (for pairing) */
smp_mb();
-#ifdef RING_POLL
- {
- unsigned index = ring.avail->ring[head & (ring_size - 1)];
-
- return (index ^ head ^ 0x8000) & ~(ring_size - 1);
- }
-#else
- return head == ring.avail->idx;
-#endif
+ return avail_empty();
}
-void poll_avail(void)
+bool avail_empty()
{
unsigned head = host.used_idx;
#ifdef RING_POLL
- for (;;) {
- unsigned index = ring.avail->ring[head & (ring_size - 1)];
- if ((index ^ head ^ 0x8000) & ~(ring_size - 1))
- busy_wait();
- else
- break;
- }
+ unsigned index = ring.avail->ring[head & (ring_size - 1)];
+
+ return ((index ^ head ^ 0x8000) & ~(ring_size - 1));
#else
- while (ring.avail->idx == head)
- busy_wait();
+ return head == ring.avail->idx;
#endif
}