#include <inttypes.h>
+#include "trace.h"
+#include "qemu-error.h"
#include "virtio.h"
-#include "sysemu.h"
-
-//#define VIRTIO_ZERO_COPY
-
-/* from Linux's linux/virtio_pci.h */
-
-/* A 32-bit r/o bitmask of the features supported by the host */
-#define VIRTIO_PCI_HOST_FEATURES 0
-
-/* A 32-bit r/w bitmask of features activated by the guest */
-#define VIRTIO_PCI_GUEST_FEATURES 4
-
-/* A 32-bit r/w PFN for the currently selected queue */
-#define VIRTIO_PCI_QUEUE_PFN 8
-
-/* A 16-bit r/o queue size for the currently selected queue */
-#define VIRTIO_PCI_QUEUE_NUM 12
-
-/* A 16-bit r/w queue selector */
-#define VIRTIO_PCI_QUEUE_SEL 14
-
-/* A 16-bit r/w queue notifier */
-#define VIRTIO_PCI_QUEUE_NOTIFY 16
-
-/* An 8-bit device status register. */
-#define VIRTIO_PCI_STATUS 18
-
-/* An 8-bit r/o interrupt status register. Reading the value will return the
- * current contents of the ISR and will also clear it. This is effectively
- * a read-and-acknowledge. */
-#define VIRTIO_PCI_ISR 19
-
-#define VIRTIO_PCI_CONFIG 20
-
-/* Virtio ABI version, if we increment this, we break the guest driver. */
-#define VIRTIO_PCI_ABI_VERSION 0
-
-/* How many bits to shift physical queue address written to QUEUE_PFN.
- * 12 is historical, and due to x86 page size. */
-#define VIRTIO_PCI_QUEUE_ADDR_SHIFT 12
/* The alignment to use between consumer and producer parts of vring.
* x86 pagesize again. */
/* QEMU doesn't strictly need write barriers since everything runs in
* lock-step. We'll leave the calls to wmb() in though to make it obvious for
* KVM or if kqemu gets SMP support.
+ * In any case, we must prevent the compiler from reordering the code.
+ * TODO: we likely need some rmb()/mb() as well.
*/
-#define wmb() do { } while (0)
+
+#define wmb() __asm__ __volatile__("": : :"memory")
typedef struct VRingDesc
{
struct VirtQueue
{
VRing vring;
- uint32_t pfn;
+ 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;
+ EventNotifier guest_notifier;
+ EventNotifier host_notifier;
};
-#define VIRTIO_PCI_QUEUE_MAX 16
-
/* virt queue functions */
-#ifdef VIRTIO_ZERO_COPY
-static void *virtio_map_gpa(target_phys_addr_t addr, size_t size)
+static void virtqueue_init(VirtQueue *vq)
{
- ram_addr_t off;
- target_phys_addr_t addr1;
+ target_phys_addr_t pa = vq->pa;
- off = cpu_get_physical_page_desc(addr);
- if ((off & ~TARGET_PAGE_MASK) != IO_MEM_RAM) {
- fprintf(stderr, "virtio DMA to IO ram\n");
- exit(1);
- }
-
- off = (off & TARGET_PAGE_MASK) | (addr & ~TARGET_PAGE_MASK);
-
- for (addr1 = addr + TARGET_PAGE_SIZE;
- addr1 < TARGET_PAGE_ALIGN(addr + size);
- addr1 += TARGET_PAGE_SIZE) {
- ram_addr_t off1;
-
- off1 = cpu_get_physical_page_desc(addr1);
- if ((off1 & ~TARGET_PAGE_MASK) != IO_MEM_RAM) {
- fprintf(stderr, "virtio DMA to IO ram\n");
- exit(1);
- }
-
- off1 = (off1 & TARGET_PAGE_MASK) | (addr1 & ~TARGET_PAGE_MASK);
-
- if (off1 != (off + (addr1 - addr))) {
- fprintf(stderr, "discontigous virtio memory\n");
- exit(1);
- }
- }
-
- return phys_ram_base + off;
-}
-#endif
-
-static void virtqueue_init(VirtQueue *vq, target_phys_addr_t pa)
-{
vq->vring.desc = pa;
vq->vring.avail = pa + vq->vring.num * sizeof(VRingDesc);
vq->vring.used = vring_align(vq->vring.avail +
VIRTIO_PCI_VRING_ALIGN);
}
-static inline uint64_t vring_desc_addr(VirtQueue *vq, int i)
+static inline uint64_t vring_desc_addr(target_phys_addr_t desc_pa, int i)
{
target_phys_addr_t pa;
- pa = vq->vring.desc + sizeof(VRingDesc) * i + offsetof(VRingDesc, addr);
+ pa = desc_pa + sizeof(VRingDesc) * i + offsetof(VRingDesc, addr);
return ldq_phys(pa);
}
-static inline uint32_t vring_desc_len(VirtQueue *vq, int i)
+static inline uint32_t vring_desc_len(target_phys_addr_t desc_pa, int i)
{
target_phys_addr_t pa;
- pa = vq->vring.desc + sizeof(VRingDesc) * i + offsetof(VRingDesc, len);
+ pa = desc_pa + sizeof(VRingDesc) * i + offsetof(VRingDesc, len);
return ldl_phys(pa);
}
-static inline uint16_t vring_desc_flags(VirtQueue *vq, int i)
+static inline uint16_t vring_desc_flags(target_phys_addr_t desc_pa, int i)
{
target_phys_addr_t pa;
- pa = vq->vring.desc + sizeof(VRingDesc) * i + offsetof(VRingDesc, flags);
+ pa = desc_pa + sizeof(VRingDesc) * i + offsetof(VRingDesc, flags);
return lduw_phys(pa);
}
-static inline uint16_t vring_desc_next(VirtQueue *vq, int i)
+static inline uint16_t vring_desc_next(target_phys_addr_t desc_pa, int i)
{
target_phys_addr_t pa;
- pa = vq->vring.desc + sizeof(VRingDesc) * i + offsetof(VRingDesc, next);
+ pa = desc_pa + sizeof(VRingDesc) * i + offsetof(VRingDesc, next);
return lduw_phys(pa);
}
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)
unsigned int offset;
int i;
-#ifndef VIRTIO_ZERO_COPY
- for (i = 0; i < elem->out_num; i++)
- qemu_free(elem->out_sg[i].iov_base);
-#endif
+ trace_virtqueue_fill(vq, elem, len, idx);
offset = 0;
for (i = 0; i < elem->in_num; i++) {
size_t size = MIN(len - offset, elem->in_sg[i].iov_len);
-#ifdef VIRTIO_ZERO_COPY
- if (size) {
- ram_addr_t addr = (uint8_t *)elem->in_sg[i].iov_base - phys_ram_base;
- ram_addr_t off;
+ cpu_physical_memory_unmap(elem->in_sg[i].iov_base,
+ elem->in_sg[i].iov_len,
+ 1, size);
- for (off = 0; off < size; off += TARGET_PAGE_SIZE)
- cpu_physical_memory_set_dirty(addr + off);
- }
-#else
- if (size)
- cpu_physical_memory_write(elem->in_addr[i],
- elem->in_sg[i].iov_base,
- size);
-
- qemu_free(elem->in_sg[i].iov_base);
-#endif
-
- offset += size;
+ offset += elem->in_sg[i].iov_len;
}
+ for (i = 0; i < elem->out_num; i++)
+ cpu_physical_memory_unmap(elem->out_sg[i].iov_base,
+ elem->out_sg[i].iov_len,
+ 0, elem->out_sg[i].iov_len);
+
idx = (idx + vring_used_idx(vq)) % vq->vring.num;
/* Get a pointer to the next entry in the used ring. */
void virtqueue_flush(VirtQueue *vq, unsigned int count)
{
+ uint16_t old, new;
/* Make sure buffer is written before we update index. */
wmb();
- vring_used_idx_increment(vq, count);
+ trace_virtqueue_flush(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,
/* Check it isn't doing very strange things with descriptor numbers. */
if (num_heads > vq->vring.num) {
- fprintf(stderr, "Guest moved used index from %u to %u",
- idx, vring_avail_idx(vq));
+ error_report("Guest moved used index from %u to %u",
+ idx, vring_avail_idx(vq));
exit(1);
}
/* If their number is silly, that's a fatal mistake. */
if (head >= vq->vring.num) {
- fprintf(stderr, "Guest says index %u is available", head);
+ error_report("Guest says index %u is available", head);
exit(1);
}
return head;
}
-static unsigned virtqueue_next_desc(VirtQueue *vq, unsigned int i)
+static unsigned virtqueue_next_desc(target_phys_addr_t desc_pa,
+ unsigned int i, unsigned int max)
{
unsigned int next;
/* If this descriptor says it doesn't chain, we're done. */
- if (!(vring_desc_flags(vq, i) & VRING_DESC_F_NEXT))
- return vq->vring.num;
+ if (!(vring_desc_flags(desc_pa, i) & VRING_DESC_F_NEXT))
+ return max;
/* Check they're not leading us off end of descriptors. */
- next = vring_desc_next(vq, i);
+ next = vring_desc_next(desc_pa, i);
/* Make sure compiler knows to grab that: we don't want it changing! */
wmb();
- if (next >= vq->vring.num) {
- fprintf(stderr, "Desc next is %u", next);
+ if (next >= max) {
+ error_report("Desc next is %u", next);
exit(1);
}
int virtqueue_avail_bytes(VirtQueue *vq, int in_bytes, int out_bytes)
{
unsigned int idx;
- int num_bufs, in_total, out_total;
+ int total_bufs, in_total, out_total;
idx = vq->last_avail_idx;
- num_bufs = in_total = out_total = 0;
+ total_bufs = in_total = out_total = 0;
while (virtqueue_num_heads(vq, idx)) {
+ unsigned int max, num_bufs, indirect = 0;
+ target_phys_addr_t desc_pa;
int i;
+ max = vq->vring.num;
+ num_bufs = total_bufs;
i = virtqueue_get_head(vq, idx++);
+ desc_pa = vq->vring.desc;
+
+ if (vring_desc_flags(desc_pa, i) & VRING_DESC_F_INDIRECT) {
+ if (vring_desc_len(desc_pa, i) % sizeof(VRingDesc)) {
+ error_report("Invalid size for indirect buffer table");
+ exit(1);
+ }
+
+ /* If we've got too many, that implies a descriptor loop. */
+ if (num_bufs >= max) {
+ error_report("Looped descriptor");
+ exit(1);
+ }
+
+ /* loop over the indirect descriptor table */
+ indirect = 1;
+ max = vring_desc_len(desc_pa, i) / sizeof(VRingDesc);
+ num_bufs = i = 0;
+ desc_pa = vring_desc_addr(desc_pa, i);
+ }
+
do {
/* If we've got too many, that implies a descriptor loop. */
- if (++num_bufs > vq->vring.num) {
- fprintf(stderr, "Looped descriptor");
+ if (++num_bufs > max) {
+ error_report("Looped descriptor");
exit(1);
}
- if (vring_desc_flags(vq, i) & VRING_DESC_F_WRITE) {
+ if (vring_desc_flags(desc_pa, i) & VRING_DESC_F_WRITE) {
if (in_bytes > 0 &&
- (in_total += vring_desc_len(vq, i)) >= in_bytes)
+ (in_total += vring_desc_len(desc_pa, i)) >= in_bytes)
return 1;
} else {
if (out_bytes > 0 &&
- (out_total += vring_desc_len(vq, i)) >= out_bytes)
+ (out_total += vring_desc_len(desc_pa, i)) >= out_bytes)
return 1;
}
- } while ((i = virtqueue_next_desc(vq, i)) != vq->vring.num);
+ } while ((i = virtqueue_next_desc(desc_pa, i, max)) != max);
+
+ if (!indirect)
+ total_bufs = num_bufs;
+ else
+ total_bufs++;
}
return 0;
}
+void virtqueue_map_sg(struct iovec *sg, target_phys_addr_t *addr,
+ size_t num_sg, int is_write)
+{
+ unsigned int i;
+ target_phys_addr_t len;
+
+ for (i = 0; i < num_sg; i++) {
+ len = sg[i].iov_len;
+ sg[i].iov_base = cpu_physical_memory_map(addr[i], &len, is_write);
+ if (sg[i].iov_base == NULL || len != sg[i].iov_len) {
+ error_report("virtio: trying to map MMIO memory");
+ exit(1);
+ }
+ }
+}
+
int virtqueue_pop(VirtQueue *vq, VirtQueueElement *elem)
{
- unsigned int i, head;
+ unsigned int i, head, max;
+ target_phys_addr_t desc_pa = vq->vring.desc;
if (!virtqueue_num_heads(vq, vq->last_avail_idx))
return 0;
/* When we start there are none of either input nor output. */
elem->out_num = elem->in_num = 0;
+ 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)) {
+ error_report("Invalid size for indirect buffer table");
+ exit(1);
+ }
+
+ /* loop over the indirect descriptor table */
+ max = vring_desc_len(desc_pa, i) / sizeof(VRingDesc);
+ desc_pa = vring_desc_addr(desc_pa, i);
+ i = 0;
+ }
+
+ /* Collect all the descriptors */
do {
struct iovec *sg;
- if (vring_desc_flags(vq, i) & VRING_DESC_F_WRITE) {
- elem->in_addr[elem->in_num] = vring_desc_addr(vq, i);
+ 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
+ } 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++];
-
- /* Grab the first descriptor, and check it's OK. */
- sg->iov_len = vring_desc_len(vq, i);
-
-#ifdef VIRTIO_ZERO_COPY
- sg->iov_base = virtio_map_gpa(vring_desc_addr(vq, i), sg->iov_len);
-#else
- /* cap individual scatter element size to prevent unbounded allocations
- of memory from the guest. Practically speaking, no virtio driver
- will ever pass more than a page in each element. We set the cap to
- be 2MB in case for some reason a large page makes it way into the
- sg list. When we implement a zero copy API, this limitation will
- disappear */
- if (sg->iov_len > (2 << 20))
- sg->iov_len = 2 << 20;
-
- sg->iov_base = qemu_malloc(sg->iov_len);
- if (sg->iov_base &&
- !(vring_desc_flags(vq, i) & VRING_DESC_F_WRITE)) {
- cpu_physical_memory_read(vring_desc_addr(vq, i),
- sg->iov_base,
- sg->iov_len);
- }
-#endif
- if (sg->iov_base == NULL) {
- fprintf(stderr, "Invalid mapping\n");
- exit(1);
}
+ sg->iov_len = vring_desc_len(desc_pa, i);
+
/* If we've got too many, that implies a descriptor loop. */
- if ((elem->in_num + elem->out_num) > vq->vring.num) {
- fprintf(stderr, "Looped descriptor");
+ if ((elem->in_num + elem->out_num) > max) {
+ error_report("Looped descriptor");
exit(1);
}
- } while ((i = virtqueue_next_desc(vq, i)) != vq->vring.num);
+ } while ((i = virtqueue_next_desc(desc_pa, i, max)) != max);
+
+ /* Now map what we have collected */
+ virtqueue_map_sg(elem->in_sg, elem->in_addr, elem->in_num, 1);
+ virtqueue_map_sg(elem->out_sg, elem->out_addr, elem->out_num, 0);
elem->index = head;
vq->inuse++;
+ trace_virtqueue_pop(vq, elem, elem->in_num, elem->out_num);
return elem->in_num + elem->out_num;
}
/* virtio device */
-
-static VirtIODevice *to_virtio_device(PCIDevice *pci_dev)
+static void virtio_notify_vector(VirtIODevice *vdev, uint16_t vector)
{
- return (VirtIODevice *)pci_dev;
+ if (vdev->binding->notify) {
+ vdev->binding->notify(vdev->binding_opaque, vector);
+ }
}
-static void virtio_update_irq(VirtIODevice *vdev)
+void virtio_update_irq(VirtIODevice *vdev)
{
- qemu_set_irq(vdev->pci_dev.irq[0], vdev->isr & 1);
+ virtio_notify_vector(vdev, VIRTIO_NO_VECTOR);
}
-static void virtio_reset(void *opaque)
+void virtio_reset(void *opaque)
{
VirtIODevice *vdev = opaque;
int i;
+ virtio_set_status(vdev, 0);
+
if (vdev->reset)
vdev->reset(vdev);
- vdev->features = 0;
+ vdev->guest_features = 0;
vdev->queue_sel = 0;
vdev->status = 0;
vdev->isr = 0;
- virtio_update_irq(vdev);
+ vdev->config_vector = VIRTIO_NO_VECTOR;
+ virtio_notify_vector(vdev, vdev->config_vector);
for(i = 0; i < VIRTIO_PCI_QUEUE_MAX; i++) {
vdev->vq[i].vring.desc = 0;
vdev->vq[i].vring.avail = 0;
vdev->vq[i].vring.used = 0;
vdev->vq[i].last_avail_idx = 0;
- vdev->vq[i].pfn = 0;
- }
-}
-
-static void virtio_ioport_write(void *opaque, uint32_t addr, uint32_t val)
-{
- VirtIODevice *vdev = to_virtio_device(opaque);
- ram_addr_t pa;
-
- addr -= vdev->addr;
-
- switch (addr) {
- case VIRTIO_PCI_GUEST_FEATURES:
- if (vdev->set_features)
- vdev->set_features(vdev, val);
- vdev->features = val;
- break;
- case VIRTIO_PCI_QUEUE_PFN:
- pa = (ram_addr_t)val << VIRTIO_PCI_QUEUE_ADDR_SHIFT;
- vdev->vq[vdev->queue_sel].pfn = val;
- if (pa == 0) {
- virtio_reset(vdev);
- } else {
- virtqueue_init(&vdev->vq[vdev->queue_sel], pa);
- }
- break;
- case VIRTIO_PCI_QUEUE_SEL:
- if (val < VIRTIO_PCI_QUEUE_MAX)
- vdev->queue_sel = val;
- break;
- case VIRTIO_PCI_QUEUE_NOTIFY:
- if (val < VIRTIO_PCI_QUEUE_MAX && vdev->vq[val].vring.desc)
- vdev->vq[val].handle_output(vdev, &vdev->vq[val]);
- break;
- case VIRTIO_PCI_STATUS:
- vdev->status = val & 0xFF;
- if (vdev->status == 0)
- virtio_reset(vdev);
- break;
+ 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;
}
}
-static uint32_t virtio_ioport_read(void *opaque, uint32_t addr)
-{
- VirtIODevice *vdev = to_virtio_device(opaque);
- uint32_t ret = 0xFFFFFFFF;
-
- addr -= vdev->addr;
-
- switch (addr) {
- case VIRTIO_PCI_HOST_FEATURES:
- ret = vdev->get_features(vdev);
- ret |= (1 << VIRTIO_F_NOTIFY_ON_EMPTY);
- break;
- case VIRTIO_PCI_GUEST_FEATURES:
- ret = vdev->features;
- break;
- case VIRTIO_PCI_QUEUE_PFN:
- ret = vdev->vq[vdev->queue_sel].pfn;
- break;
- case VIRTIO_PCI_QUEUE_NUM:
- ret = vdev->vq[vdev->queue_sel].vring.num;
- break;
- case VIRTIO_PCI_QUEUE_SEL:
- ret = vdev->queue_sel;
- break;
- case VIRTIO_PCI_STATUS:
- ret = vdev->status;
- break;
- case VIRTIO_PCI_ISR:
- /* reading from the ISR also clears it. */
- ret = vdev->isr;
- vdev->isr = 0;
- virtio_update_irq(vdev);
- break;
- default:
- break;
- }
-
- return ret;
-}
-
-static uint32_t virtio_config_readb(void *opaque, uint32_t addr)
+uint32_t virtio_config_readb(VirtIODevice *vdev, uint32_t addr)
{
- VirtIODevice *vdev = opaque;
uint8_t val;
vdev->get_config(vdev, vdev->config);
- addr -= vdev->addr + VIRTIO_PCI_CONFIG;
if (addr > (vdev->config_len - sizeof(val)))
return (uint32_t)-1;
return val;
}
-static uint32_t virtio_config_readw(void *opaque, uint32_t addr)
+uint32_t virtio_config_readw(VirtIODevice *vdev, uint32_t addr)
{
- VirtIODevice *vdev = opaque;
uint16_t val;
vdev->get_config(vdev, vdev->config);
- addr -= vdev->addr + VIRTIO_PCI_CONFIG;
if (addr > (vdev->config_len - sizeof(val)))
return (uint32_t)-1;
return val;
}
-static uint32_t virtio_config_readl(void *opaque, uint32_t addr)
+uint32_t virtio_config_readl(VirtIODevice *vdev, uint32_t addr)
{
- VirtIODevice *vdev = opaque;
uint32_t val;
vdev->get_config(vdev, vdev->config);
- addr -= vdev->addr + VIRTIO_PCI_CONFIG;
if (addr > (vdev->config_len - sizeof(val)))
return (uint32_t)-1;
return val;
}
-static void virtio_config_writeb(void *opaque, uint32_t addr, uint32_t data)
+void virtio_config_writeb(VirtIODevice *vdev, uint32_t addr, uint32_t data)
{
- VirtIODevice *vdev = opaque;
uint8_t val = data;
- addr -= vdev->addr + VIRTIO_PCI_CONFIG;
if (addr > (vdev->config_len - sizeof(val)))
return;
vdev->set_config(vdev, vdev->config);
}
-static void virtio_config_writew(void *opaque, uint32_t addr, uint32_t data)
+void virtio_config_writew(VirtIODevice *vdev, uint32_t addr, uint32_t data)
{
- VirtIODevice *vdev = opaque;
uint16_t val = data;
- addr -= vdev->addr + VIRTIO_PCI_CONFIG;
if (addr > (vdev->config_len - sizeof(val)))
return;
vdev->set_config(vdev, vdev->config);
}
-static void virtio_config_writel(void *opaque, uint32_t addr, uint32_t data)
+void virtio_config_writel(VirtIODevice *vdev, uint32_t addr, uint32_t data)
{
- VirtIODevice *vdev = opaque;
uint32_t val = data;
- addr -= vdev->addr + VIRTIO_PCI_CONFIG;
if (addr > (vdev->config_len - sizeof(val)))
return;
vdev->set_config(vdev, vdev->config);
}
-static void virtio_map(PCIDevice *pci_dev, int region_num,
- uint32_t addr, uint32_t size, int type)
+void virtio_queue_set_addr(VirtIODevice *vdev, int n, target_phys_addr_t addr)
{
- VirtIODevice *vdev = to_virtio_device(pci_dev);
- int i;
+ vdev->vq[n].pa = addr;
+ virtqueue_init(&vdev->vq[n]);
+}
- vdev->addr = addr;
- for (i = 0; i < 3; i++) {
- register_ioport_write(addr, 20, 1 << i, virtio_ioport_write, vdev);
- register_ioport_read(addr, 20, 1 << i, virtio_ioport_read, vdev);
- }
+target_phys_addr_t virtio_queue_get_addr(VirtIODevice *vdev, int n)
+{
+ return vdev->vq[n].pa;
+}
+
+int virtio_queue_get_num(VirtIODevice *vdev, int n)
+{
+ return vdev->vq[n].vring.num;
+}
- if (vdev->config_len) {
- register_ioport_write(addr + 20, vdev->config_len, 1,
- virtio_config_writeb, vdev);
- register_ioport_write(addr + 20, vdev->config_len, 2,
- virtio_config_writew, vdev);
- register_ioport_write(addr + 20, vdev->config_len, 4,
- virtio_config_writel, vdev);
- register_ioport_read(addr + 20, vdev->config_len, 1,
- virtio_config_readb, vdev);
- register_ioport_read(addr + 20, vdev->config_len, 2,
- virtio_config_readw, vdev);
- register_ioport_read(addr + 20, vdev->config_len, 4,
- virtio_config_readl, vdev);
-
- vdev->get_config(vdev, vdev->config);
+void virtio_queue_notify_vq(VirtQueue *vq)
+{
+ 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_NO_VECTOR;
+}
+
+void virtio_queue_set_vector(VirtIODevice *vdev, int n, uint16_t vector)
+{
+ if (n < VIRTIO_PCI_QUEUE_MAX)
+ vdev->vq[n].vector = vector;
+}
+
VirtQueue *virtio_add_queue(VirtIODevice *vdev, int queue_size,
void (*handle_output)(VirtIODevice *, VirtQueue *))
{
return &vdev->vq[i];
}
+void virtio_irq(VirtQueue *vq)
+{
+ trace_virtio_irq(vq);
+ vq->vdev->isr |= 0x01;
+ virtio_notify_vector(vq->vdev, vq->vector);
+}
+
+/* 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 (((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)
{
- /* Always notify when queue is empty */
- if ((vq->inuse || vring_avail_idx(vq) != vq->last_avail_idx) &&
- (vring_avail_flags(vq) & VRING_AVAIL_F_NO_INTERRUPT))
+ if (!vring_notify(vdev, vq)) {
return;
+ }
+ trace_virtio_notify(vdev, vq);
vdev->isr |= 0x01;
- virtio_update_irq(vdev);
+ virtio_notify_vector(vdev, vq->vector);
}
void virtio_notify_config(VirtIODevice *vdev)
{
+ if (!(vdev->status & VIRTIO_CONFIG_S_DRIVER_OK))
+ return;
+
vdev->isr |= 0x03;
- virtio_update_irq(vdev);
+ virtio_notify_vector(vdev, vdev->config_vector);
}
void virtio_save(VirtIODevice *vdev, QEMUFile *f)
{
int i;
- pci_device_save(&vdev->pci_dev, f);
+ if (vdev->binding->save_config)
+ vdev->binding->save_config(vdev->binding_opaque, f);
- qemu_put_be32s(f, &vdev->addr);
qemu_put_8s(f, &vdev->status);
qemu_put_8s(f, &vdev->isr);
qemu_put_be16s(f, &vdev->queue_sel);
- qemu_put_be32s(f, &vdev->features);
+ qemu_put_be32s(f, &vdev->guest_features);
qemu_put_be32(f, vdev->config_len);
qemu_put_buffer(f, vdev->config, vdev->config_len);
break;
qemu_put_be32(f, vdev->vq[i].vring.num);
- qemu_put_be32s(f, &vdev->vq[i].pfn);
+ qemu_put_be64(f, vdev->vq[i].pa);
qemu_put_be16s(f, &vdev->vq[i].last_avail_idx);
+ if (vdev->binding->save_queue)
+ vdev->binding->save_queue(vdev->binding_opaque, i, f);
}
}
-void virtio_load(VirtIODevice *vdev, QEMUFile *f)
+int virtio_load(VirtIODevice *vdev, QEMUFile *f)
{
- int num, i;
+ int num, i, ret;
+ uint32_t features;
+ uint32_t supported_features =
+ vdev->binding->get_features(vdev->binding_opaque);
- pci_device_load(&vdev->pci_dev, f);
+ if (vdev->binding->load_config) {
+ ret = vdev->binding->load_config(vdev->binding_opaque, f);
+ if (ret)
+ return ret;
+ }
- qemu_get_be32s(f, &vdev->addr);
qemu_get_8s(f, &vdev->status);
qemu_get_8s(f, &vdev->isr);
qemu_get_be16s(f, &vdev->queue_sel);
- qemu_get_be32s(f, &vdev->features);
+ qemu_get_be32s(f, &features);
+ if (features & ~supported_features) {
+ error_report("Features 0x%x unsupported. Allowed features: 0x%x",
+ features, supported_features);
+ return -1;
+ }
+ if (vdev->set_features)
+ vdev->set_features(vdev, features);
+ vdev->guest_features = features;
vdev->config_len = qemu_get_be32(f);
qemu_get_buffer(f, vdev->config, vdev->config_len);
for (i = 0; i < num; i++) {
vdev->vq[i].vring.num = qemu_get_be32(f);
- qemu_get_be32s(f, &vdev->vq[i].pfn);
+ 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]);
+ 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);
+ if (ret)
+ return ret;
+ }
+ }
- if (vdev->vq[i].pfn) {
- target_phys_addr_t pa;
+ virtio_notify_vector(vdev, VIRTIO_NO_VECTOR);
+ return 0;
+}
- pa = (ram_addr_t)vdev->vq[i].pfn << VIRTIO_PCI_QUEUE_ADDR_SHIFT;
- virtqueue_init(&vdev->vq[i], pa);
- }
+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);
}
- virtio_update_irq(vdev);
+ if (!backend_run) {
+ virtio_set_status(vdev, vdev->status);
+ }
}
-VirtIODevice *virtio_init_pci(PCIBus *bus, const char *name,
- uint16_t vendor, uint16_t device,
- uint16_t subvendor, uint16_t subdevice,
- uint8_t class_code, uint8_t subclass_code,
- uint8_t pif, size_t config_size,
- size_t struct_size)
+VirtIODevice *virtio_common_init(const char *name, uint16_t device_id,
+ size_t config_size, size_t struct_size)
{
VirtIODevice *vdev;
- PCIDevice *pci_dev;
- uint8_t *config;
- uint32_t size;
-
- pci_dev = pci_register_device(bus, name, struct_size,
- -1, NULL, NULL);
- if (!pci_dev)
- return NULL;
+ int i;
- vdev = to_virtio_device(pci_dev);
+ vdev = qemu_mallocz(struct_size);
+ vdev->device_id = device_id;
vdev->status = 0;
vdev->isr = 0;
vdev->queue_sel = 0;
+ vdev->config_vector = VIRTIO_NO_VECTOR;
vdev->vq = qemu_mallocz(sizeof(VirtQueue) * VIRTIO_PCI_QUEUE_MAX);
-
- config = pci_dev->config;
- pci_config_set_vendor_id(config, vendor);
- pci_config_set_device_id(config, device);
-
- config[0x08] = VIRTIO_PCI_ABI_VERSION;
-
- config[0x09] = pif;
- config[0x0a] = subclass_code;
- config[0x0b] = class_code;
- config[0x0e] = 0x00;
-
- config[0x2c] = subvendor & 0xFF;
- config[0x2d] = (subvendor >> 8) & 0xFF;
- config[0x2e] = subdevice & 0xFF;
- config[0x2f] = (subdevice >> 8) & 0xFF;
-
- config[0x3d] = 1;
+ 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;
+ }
vdev->name = name;
vdev->config_len = config_size;
else
vdev->config = NULL;
- size = 20 + config_size;
- if (size & (size-1))
- size = 1 << qemu_fls(size);
-
- pci_register_io_region(pci_dev, 0, size, PCI_ADDRESS_SPACE_IO,
- virtio_map);
- qemu_register_reset(virtio_reset, vdev);
+ vdev->vmstate = qemu_add_vm_change_state_handler(virtio_vmstate_change, vdev);
return vdev;
}
+
+void virtio_bind_device(VirtIODevice *vdev, const VirtIOBindings *binding,
+ void *opaque)
+{
+ vdev->binding = binding;
+ vdev->binding_opaque = opaque;
+}
+
+target_phys_addr_t virtio_queue_get_desc_addr(VirtIODevice *vdev, int n)
+{
+ return vdev->vq[n].vring.desc;
+}
+
+target_phys_addr_t virtio_queue_get_avail_addr(VirtIODevice *vdev, int n)
+{
+ return vdev->vq[n].vring.avail;
+}
+
+target_phys_addr_t virtio_queue_get_used_addr(VirtIODevice *vdev, int n)
+{
+ return vdev->vq[n].vring.used;
+}
+
+target_phys_addr_t virtio_queue_get_ring_addr(VirtIODevice *vdev, int n)
+{
+ return vdev->vq[n].vring.desc;
+}
+
+target_phys_addr_t virtio_queue_get_desc_size(VirtIODevice *vdev, int n)
+{
+ return sizeof(VRingDesc) * vdev->vq[n].vring.num;
+}
+
+target_phys_addr_t virtio_queue_get_avail_size(VirtIODevice *vdev, int n)
+{
+ return offsetof(VRingAvail, ring) +
+ sizeof(uint64_t) * vdev->vq[n].vring.num;
+}
+
+target_phys_addr_t virtio_queue_get_used_size(VirtIODevice *vdev, int n)
+{
+ return offsetof(VRingUsed, ring) +
+ sizeof(VRingUsedElem) * vdev->vq[n].vring.num;
+}
+
+target_phys_addr_t virtio_queue_get_ring_size(VirtIODevice *vdev, int n)
+{
+ return vdev->vq[n].vring.used - vdev->vq[n].vring.desc +
+ virtio_queue_get_used_size(vdev, n);
+}
+
+uint16_t virtio_queue_get_last_avail_idx(VirtIODevice *vdev, int n)
+{
+ return vdev->vq[n].last_avail_idx;
+}
+
+void virtio_queue_set_last_avail_idx(VirtIODevice *vdev, int n, uint16_t idx)
+{
+ vdev->vq[n].last_avail_idx = idx;
+}
+
+VirtQueue *virtio_get_queue(VirtIODevice *vdev, int n)
+{
+ return vdev->vq + n;
+}
+
+EventNotifier *virtio_queue_get_guest_notifier(VirtQueue *vq)
+{
+ return &vq->guest_notifier;
+}
+EventNotifier *virtio_queue_get_host_notifier(VirtQueue *vq)
+{
+ return &vq->host_notifier;
+}
projects / qemu.git / blobdiff