kvm tools: Separate virtio-pci layer out of virtio-net

Signed-off-by: Sasha Levin <levinsasha928@gmail.com>
Signed-off-by: Pekka Enberg <penberg@kernel.org>
This commit is contained in:
Sasha Levin
2015-06-01 16:39:47 +01:00
committed by Will Deacon
parent 53cbeb9b7c
commit 78a2a3e20a
+101 -245
View File
@@ -1,19 +1,19 @@
#include "kvm/virtio-pci-dev.h"
#include "kvm/virtio-net.h"
#include "kvm/virtio.h"
#include "kvm/ioport.h"
#include "kvm/types.h"
#include "kvm/mutex.h"
#include "kvm/util.h"
#include "kvm/kvm.h"
#include "kvm/pci.h"
#include "kvm/irq.h"
#include "kvm/uip.h"
#include "kvm/ioeventfd.h"
#include "kvm/guest_compat.h"
#include "kvm/virtio-pci.h"
#include <linux/virtio_net.h>
#include <linux/if_tun.h>
#include <linux/types.h>
#include <arpa/inet.h>
#include <net/if.h>
@@ -32,18 +32,10 @@
#define VIRTIO_NET_RX_QUEUE 0
#define VIRTIO_NET_TX_QUEUE 1
static struct pci_device_header pci_header = {
.vendor_id = PCI_VENDOR_ID_REDHAT_QUMRANET,
.device_id = PCI_DEVICE_ID_VIRTIO_NET,
.header_type = PCI_HEADER_TYPE_NORMAL,
.revision_id = 0,
.class = 0x020000,
.subsys_vendor_id = PCI_SUBSYSTEM_VENDOR_ID_REDHAT_QUMRANET,
.subsys_id = VIRTIO_ID_NET,
};
struct net_dev;
extern struct kvm *kvm;
struct net_dev_operations {
int (*rx)(struct iovec *iov, u16 in, struct net_dev *ndev);
int (*tx)(struct iovec *iov, u16 in, struct net_dev *ndev);
@@ -51,21 +43,12 @@ struct net_dev_operations {
struct net_dev {
pthread_mutex_t mutex;
struct virtio_pci vpci;
struct virt_queue vqs[VIRTIO_NET_NUM_QUEUES];
struct virtio_net_config config;
u32 host_features;
u32 guest_features;
u16 config_vector;
u8 status;
u8 isr;
u16 queue_selector;
u16 base_addr;
u32 vq_vector[VIRTIO_NET_NUM_QUEUES];
u32 gsis[VIRTIO_NET_NUM_QUEUES];
u32 msix_io_block;
u32 features;
int compat_id;
bool msix_enabled;
pthread_t io_rx_thread;
pthread_mutex_t io_rx_lock;
@@ -90,14 +73,6 @@ static struct net_dev ndev = {
.config = {
.status = VIRTIO_NET_S_LINK_UP,
},
.host_features = 1UL << VIRTIO_NET_F_MAC
| 1UL << VIRTIO_NET_F_CSUM
| 1UL << VIRTIO_NET_F_HOST_UFO
| 1UL << VIRTIO_NET_F_HOST_TSO4
| 1UL << VIRTIO_NET_F_HOST_TSO6
| 1UL << VIRTIO_NET_F_GUEST_UFO
| 1UL << VIRTIO_NET_F_GUEST_TSO4
| 1UL << VIRTIO_NET_F_GUEST_TSO6,
.info = {
.buf_nr = 20,
}
@@ -131,7 +106,7 @@ static void *virtio_net_rx_thread(void *p)
virt_queue__set_used_elem(vq, head, len);
/* We should interrupt guest right now, otherwise latency is huge. */
kvm__irq_trigger(kvm, ndev.gsis[VIRTIO_NET_RX_QUEUE]);
virtio_pci__signal_vq(kvm, &ndev.vpci, VIRTIO_NET_RX_QUEUE);
}
}
@@ -168,7 +143,7 @@ static void *virtio_net_tx_thread(void *p)
virt_queue__set_used_elem(vq, head, len);
}
kvm__irq_trigger(kvm, ndev.gsis[VIRTIO_NET_TX_QUEUE]);
virtio_pci__signal_vq(kvm, &ndev.vpci, VIRTIO_NET_TX_QUEUE);
}
pthread_exit(NULL);
@@ -177,112 +152,6 @@ static void *virtio_net_tx_thread(void *p)
}
static bool virtio_net_pci_io_device_specific_out(struct kvm *kvm, void *data,
unsigned long offset, int size)
{
u8 *config_space = (u8 *)&ndev.config;
int type;
u32 config_offset;
type = virtio__get_dev_specific_field(offset - 20, ndev.msix_enabled, 0, &config_offset);
if (type == VIRTIO_PCI_O_MSIX) {
if (offset == VIRTIO_MSI_CONFIG_VECTOR) {
ndev.config_vector = ioport__read16(data);
} else {
u32 gsi;
u32 vec;
vec = ndev.vq_vector[ndev.queue_selector] = ioport__read16(data);
gsi = irq__add_msix_route(kvm,
pci_header.msix.table[vec].low,
pci_header.msix.table[vec].high,
pci_header.msix.table[vec].data);
ndev.gsis[ndev.queue_selector] = gsi;
}
return true;
}
if (size != 1)
return false;
if ((config_offset) > sizeof(struct virtio_net_config))
pr_error("config offset is too big: %u", config_offset);
config_space[config_offset] = *(u8 *)data;
return true;
}
static bool virtio_net_pci_io_device_specific_in(void *data, unsigned long offset, int size)
{
u8 *config_space = (u8 *)&ndev.config;
int type;
u32 config_offset;
type = virtio__get_dev_specific_field(offset - 20, ndev.msix_enabled, 0, &config_offset);
if (type == VIRTIO_PCI_O_MSIX) {
if (offset == VIRTIO_MSI_CONFIG_VECTOR)
ioport__write16(data, ndev.config_vector);
else
ioport__write16(data, ndev.vq_vector[ndev.queue_selector]);
return true;
}
if (size != 1)
return false;
if ((config_offset) > sizeof(struct virtio_net_config))
pr_error("config offset is too big: %u", config_offset);
ioport__write8(data, config_space[config_offset]);
return true;
}
static bool virtio_net_pci_io_in(struct ioport *ioport, struct kvm *kvm, u16 port, void *data, int size)
{
unsigned long offset = port - ndev.base_addr;
bool ret = true;
mutex_lock(&ndev.mutex);
switch (offset) {
case VIRTIO_PCI_HOST_FEATURES:
ioport__write32(data, ndev.host_features);
break;
case VIRTIO_PCI_GUEST_FEATURES:
ret = false;
break;
case VIRTIO_PCI_QUEUE_PFN:
ioport__write32(data, ndev.vqs[ndev.queue_selector].pfn);
break;
case VIRTIO_PCI_QUEUE_NUM:
ioport__write16(data, VIRTIO_NET_QUEUE_SIZE);
break;
case VIRTIO_PCI_QUEUE_SEL:
case VIRTIO_PCI_QUEUE_NOTIFY:
ret = false;
break;
case VIRTIO_PCI_STATUS:
ioport__write8(data, ndev.status);
break;
case VIRTIO_PCI_ISR:
ioport__write8(data, ndev.isr);
kvm__irq_line(kvm, pci_header.irq_line, VIRTIO_IRQ_LOW);
ndev.isr = VIRTIO_IRQ_LOW;
break;
default:
ret = virtio_net_pci_io_device_specific_in(data, offset, size);
};
mutex_unlock(&ndev.mutex);
return ret;
}
static void virtio_net_handle_callback(struct kvm *kvm, u16 queue_index)
{
switch (queue_index) {
@@ -301,76 +170,11 @@ static void virtio_net_handle_callback(struct kvm *kvm, u16 queue_index)
}
}
static bool virtio_net_pci_io_out(struct ioport *ioport, struct kvm *kvm, u16 port, void *data, int size)
{
unsigned long offset = port - ndev.base_addr;
bool ret = true;
mutex_lock(&ndev.mutex);
switch (offset) {
case VIRTIO_PCI_GUEST_FEATURES:
ndev.guest_features = ioport__read32(data);
break;
case VIRTIO_PCI_QUEUE_PFN: {
struct virt_queue *queue;
void *p;
assert(ndev.queue_selector < VIRTIO_NET_NUM_QUEUES);
compat__remove_message(ndev.compat_id);
queue = &ndev.vqs[ndev.queue_selector];
queue->pfn = ioport__read32(data);
p = guest_pfn_to_host(kvm, queue->pfn);
vring_init(&queue->vring, VIRTIO_NET_QUEUE_SIZE, p, VIRTIO_PCI_VRING_ALIGN);
break;
}
case VIRTIO_PCI_QUEUE_SEL:
ndev.queue_selector = ioport__read16(data);
break;
case VIRTIO_PCI_QUEUE_NOTIFY: {
u16 queue_index;
queue_index = ioport__read16(data);
virtio_net_handle_callback(kvm, queue_index);
break;
}
case VIRTIO_PCI_STATUS:
ndev.status = ioport__read8(data);
break;
default:
ret = virtio_net_pci_io_device_specific_out(kvm, data, offset, size);
};
mutex_unlock(&ndev.mutex);
return ret;
}
static void ioevent_callback(struct kvm *kvm, void *param)
{
virtio_net_handle_callback(kvm, (u64)(long)param);
}
static struct ioport_operations virtio_net_io_ops = {
.io_in = virtio_net_pci_io_in,
.io_out = virtio_net_pci_io_out,
};
static void callback_mmio(u64 addr, u8 *data, u32 len, u8 is_write, void *ptr)
{
void *table = pci_header.msix.table;
if (is_write)
memcpy(table + addr - ndev.msix_io_block, data, len);
else
memcpy(data, table + addr - ndev.msix_io_block, len);
ndev.msix_enabled = 1;
}
static bool virtio_net__tap_init(const struct virtio_net_parameters *params)
{
int sock = socket(AF_INET, SOCK_STREAM, 0);
@@ -495,23 +299,92 @@ static struct net_dev_operations uip_ops = {
.tx = uip_ops_tx,
};
static void set_config(struct kvm *kvm, void *dev, u8 data, u32 offset)
{
struct net_dev *ndev = dev;
((u8 *)(&ndev->config))[offset] = data;
}
static u8 get_config(struct kvm *kvm, void *dev, u32 offset)
{
struct net_dev *ndev = dev;
return ((u8 *)(&ndev->config))[offset];
}
static u32 get_host_features(struct kvm *kvm, void *dev)
{
return 1UL << VIRTIO_NET_F_MAC
| 1UL << VIRTIO_NET_F_CSUM
| 1UL << VIRTIO_NET_F_HOST_UFO
| 1UL << VIRTIO_NET_F_HOST_TSO4
| 1UL << VIRTIO_NET_F_HOST_TSO6
| 1UL << VIRTIO_NET_F_GUEST_UFO
| 1UL << VIRTIO_NET_F_GUEST_TSO4
| 1UL << VIRTIO_NET_F_GUEST_TSO6;
}
static void set_guest_features(struct kvm *kvm, void *dev, u32 features)
{
struct net_dev *ndev = dev;
ndev->features = features;
}
static int init_vq(struct kvm *kvm, void *dev, u32 vq, u32 pfn)
{
struct net_dev *ndev = dev;
struct virt_queue *queue;
void *p;
struct ioevent ioevent;
compat__remove_message(ndev->compat_id);
queue = &ndev->vqs[vq];
queue->pfn = pfn;
p = guest_pfn_to_host(kvm, queue->pfn);
vring_init(&queue->vring, VIRTIO_NET_QUEUE_SIZE, p, VIRTIO_PCI_VRING_ALIGN);
ioevent = (struct ioevent) {
.io_addr = ndev->vpci.base_addr + VIRTIO_PCI_QUEUE_NOTIFY,
.io_len = sizeof(u16),
.fn = ioevent_callback,
.fn_ptr = (void *)(u64)vq,
.datamatch = vq,
.fn_kvm = kvm,
.fd = eventfd(0, 0),
};
ioeventfd__add_event(&ioevent);
return 0;
}
static int notify_vq(struct kvm *kvm, void *dev, u32 vq)
{
virtio_net_handle_callback(kvm, vq);
return 0;
}
static int get_pfn_vq(struct kvm *kvm, void *dev, u32 vq)
{
struct net_dev *ndev = dev;
return ndev->vqs[vq].pfn;
}
static int get_size_vq(struct kvm *kvm, void *dev, u32 vq)
{
return VIRTIO_NET_QUEUE_SIZE;
}
void virtio_net__init(const struct virtio_net_parameters *params)
{
struct ioevent ioevent;
u8 dev, line, pin;
u16 net_base_addr;
int i;
if (irq__register_device(VIRTIO_ID_NET, &dev, &pin, &line) < 0)
return;
pci_header.irq_pin = pin;
pci_header.irq_line = line;
net_base_addr = ioport__register(IOPORT_EMPTY, &virtio_net_io_ops, IOPORT_SIZE, NULL);
pci_header.bar[0] = net_base_addr | PCI_BASE_ADDRESS_SPACE_IO;
ndev.base_addr = net_base_addr;
pci__register(&pci_header, dev);
for (i = 0 ; i < 6 ; i++) {
ndev.config.mac[i] = params->guest_mac[i];
ndev.info.guest_mac.addr[i] = params->guest_mac[i];
@@ -530,37 +403,20 @@ void virtio_net__init(const struct virtio_net_parameters *params)
ndev.ops = &uip_ops;
}
ndev.msix_io_block = pci_get_io_space_block();
kvm__register_mmio(params->kvm, ndev.msix_io_block, 0x100, callback_mmio, NULL);
pci_header.bar[1] = ndev.msix_io_block |
PCI_BASE_ADDRESS_SPACE_MEMORY |
PCI_BASE_ADDRESS_MEM_TYPE_64;
/* bar[2] is the continuation of bar[1] for 64bit addressing */
pci_header.bar[2] = 0;
pci_header.status = PCI_STATUS_CAP_LIST;
pci_header.capabilities = (void *)&pci_header.msix - (void *)&pci_header;
pci_header.msix.cap = PCI_CAP_ID_MSIX;
pci_header.msix.next = 0;
pci_header.msix.table_size = (VIRTIO_NET_NUM_QUEUES + 1) | PCI_MSIX_FLAGS_ENABLE;
pci_header.msix.table_offset = 1; /* Use BAR 1 */
virtio_pci__init(kvm, &ndev.vpci, &ndev, PCI_DEVICE_ID_VIRTIO_NET, VIRTIO_ID_NET);
ndev.vpci.ops = (struct virtio_pci_ops) {
.set_config = set_config,
.get_config = get_config,
.get_host_features = get_host_features,
.set_guest_features = set_guest_features,
.init_vq = init_vq,
.notify_vq = notify_vq,
.get_pfn_vq = get_pfn_vq,
.get_size_vq = get_size_vq,
};
virtio_net__io_thread_init(params->kvm);
for (i = 0; i < VIRTIO_NET_NUM_QUEUES; i++) {
ioevent = (struct ioevent) {
.io_addr = net_base_addr + VIRTIO_PCI_QUEUE_NOTIFY,
.io_len = sizeof(u16),
.fn = ioevent_callback,
.datamatch = i,
.fn_ptr = (void *)(long)i,
.fn_kvm = params->kvm,
.fd = eventfd(0, 0),
};
ioeventfd__add_event(&ioevent);
}
ndev.compat_id = compat__add_message("virtio-net device was not detected",
"While you have requested a virtio-net device, "
"the guest kernel didn't seem to detect it.\n"