#include <rte_memcpy.h>
#include <rte_ether.h>
#include <rte_ip.h>
-#include <rte_virtio_net.h>
+#include <rte_vhost.h>
#include <rte_tcp.h>
#include <rte_udp.h>
#include <rte_sctp.h>
#include "vhost.h"
#define MAX_PKT_BURST 32
-#define VHOST_LOG_PAGE 4096
-
-static inline void __attribute__((always_inline))
-vhost_log_page(uint8_t *log_base, uint64_t page)
-{
- log_base[page / 8] |= 1 << (page % 8);
-}
-
-static inline void __attribute__((always_inline))
-vhost_log_write(struct virtio_net *dev, uint64_t addr, uint64_t len)
-{
- uint64_t page;
-
- if (likely(((dev->features & (1ULL << VHOST_F_LOG_ALL)) == 0) ||
- !dev->log_base || !len))
- return;
-
- if (unlikely(dev->log_size <= ((addr + len - 1) / VHOST_LOG_PAGE / 8)))
- return;
-
- /* To make sure guest memory updates are committed before logging */
- rte_smp_wmb();
-
- page = addr / VHOST_LOG_PAGE;
- while (page * VHOST_LOG_PAGE < addr + len) {
- vhost_log_page((uint8_t *)(uintptr_t)dev->log_base, page);
- page += 1;
- }
-}
-
-static inline void __attribute__((always_inline))
-vhost_log_used_vring(struct virtio_net *dev, struct vhost_virtqueue *vq,
- uint64_t offset, uint64_t len)
-{
- vhost_log_write(dev, vq->log_guest_addr + offset, len);
-}
static bool
-is_valid_virt_queue_idx(uint32_t idx, int is_tx, uint32_t qp_nb)
+is_valid_virt_queue_idx(uint32_t idx, int is_tx, uint32_t nr_vring)
{
- return (is_tx ^ (idx & 1)) == 0 && idx < qp_nb * VIRTIO_QNUM;
+ return (is_tx ^ (idx & 1)) == 0 && idx < nr_vring;
}
-static inline void __attribute__((always_inline))
+static __rte_always_inline void
do_flush_shadow_used_ring(struct virtio_net *dev, struct vhost_virtqueue *vq,
uint16_t to, uint16_t from, uint16_t size)
{
size * sizeof(struct vring_used_elem));
}
-static inline void __attribute__((always_inline))
+static __rte_always_inline void
flush_shadow_used_ring(struct virtio_net *dev, struct vhost_virtqueue *vq)
{
uint16_t used_idx = vq->last_used_idx & (vq->size - 1);
sizeof(vq->used->idx));
}
-static inline void __attribute__((always_inline))
+static __rte_always_inline void
update_shadow_used_ring(struct vhost_virtqueue *vq,
uint16_t desc_idx, uint16_t len)
{
vq->shadow_used_ring[i].len = len;
}
+/* avoid write operation when necessary, to lessen cache issues */
+#define ASSIGN_UNLESS_EQUAL(var, val) do { \
+ if ((var) != (val)) \
+ (var) = (val); \
+} while (0)
+
static void
virtio_enqueue_offload(struct rte_mbuf *m_buf, struct virtio_net_hdr *net_hdr)
{
cksum));
break;
}
+ } else {
+ ASSIGN_UNLESS_EQUAL(net_hdr->csum_start, 0);
+ ASSIGN_UNLESS_EQUAL(net_hdr->csum_offset, 0);
+ ASSIGN_UNLESS_EQUAL(net_hdr->flags, 0);
}
if (m_buf->ol_flags & PKT_TX_TCP_SEG) {
net_hdr->gso_size = m_buf->tso_segsz;
net_hdr->hdr_len = m_buf->l2_len + m_buf->l3_len
+ m_buf->l4_len;
+ } else {
+ ASSIGN_UNLESS_EQUAL(net_hdr->gso_type, 0);
+ ASSIGN_UNLESS_EQUAL(net_hdr->gso_size, 0);
+ ASSIGN_UNLESS_EQUAL(net_hdr->hdr_len, 0);
}
}
-static inline void
-copy_virtio_net_hdr(struct virtio_net *dev, uint64_t desc_addr,
- struct virtio_net_hdr_mrg_rxbuf hdr)
-{
- if (dev->vhost_hlen == sizeof(struct virtio_net_hdr_mrg_rxbuf))
- *(struct virtio_net_hdr_mrg_rxbuf *)(uintptr_t)desc_addr = hdr;
- else
- *(struct virtio_net_hdr *)(uintptr_t)desc_addr = hdr.hdr;
-}
-
-static inline int __attribute__((always_inline))
-copy_mbuf_to_desc(struct virtio_net *dev, struct vhost_virtqueue *vq,
- struct rte_mbuf *m, uint16_t desc_idx)
+static __rte_always_inline int
+copy_mbuf_to_desc(struct virtio_net *dev, struct vring_desc *descs,
+ struct rte_mbuf *m, uint16_t desc_idx, uint32_t size)
{
uint32_t desc_avail, desc_offset;
uint32_t mbuf_avail, mbuf_offset;
uint32_t cpy_len;
struct vring_desc *desc;
uint64_t desc_addr;
- struct virtio_net_hdr_mrg_rxbuf virtio_hdr = {{0, 0, 0, 0, 0, 0}, 0};
+ /* A counter to avoid desc dead loop chain */
+ uint16_t nr_desc = 1;
- desc = &vq->desc[desc_idx];
- desc_addr = gpa_to_vva(dev, desc->addr);
+ desc = &descs[desc_idx];
+ desc_addr = rte_vhost_gpa_to_vva(dev->mem, desc->addr);
/*
* Checking of 'desc_addr' placed outside of 'unlikely' macro to avoid
* performance issue with some versions of gcc (4.8.4 and 5.3.0) which
rte_prefetch0((void *)(uintptr_t)desc_addr);
- virtio_enqueue_offload(m, &virtio_hdr.hdr);
- copy_virtio_net_hdr(dev, desc_addr, virtio_hdr);
+ virtio_enqueue_offload(m, (struct virtio_net_hdr *)(uintptr_t)desc_addr);
vhost_log_write(dev, desc->addr, dev->vhost_hlen);
PRINT_PACKET(dev, (uintptr_t)desc_addr, dev->vhost_hlen, 0);
/* Room in vring buffer is not enough */
return -1;
}
- if (unlikely(desc->next >= vq->size))
+ if (unlikely(desc->next >= size || ++nr_desc > size))
return -1;
- desc = &vq->desc[desc->next];
- desc_addr = gpa_to_vva(dev, desc->addr);
+ desc = &descs[desc->next];
+ desc_addr = rte_vhost_gpa_to_vva(dev->mem, desc->addr);
if (unlikely(!desc_addr))
return -1;
/**
* This function adds buffers to the virtio devices RX virtqueue. Buffers can
* be received from the physical port or from another virtio device. A packet
- * count is returned to indicate the number of packets that are succesfully
+ * count is returned to indicate the number of packets that are successfully
* added to the RX queue. This function works when the mbuf is scattered, but
* it doesn't support the mergeable feature.
*/
-static inline uint32_t __attribute__((always_inline))
+static __rte_always_inline uint32_t
virtio_dev_rx(struct virtio_net *dev, uint16_t queue_id,
struct rte_mbuf **pkts, uint32_t count)
{
struct vhost_virtqueue *vq;
uint16_t avail_idx, free_entries, start_idx;
uint16_t desc_indexes[MAX_PKT_BURST];
+ struct vring_desc *descs;
uint16_t used_idx;
- uint32_t i;
+ uint32_t i, sz;
LOG_DEBUG(VHOST_DATA, "(%d) %s\n", dev->vid, __func__);
- if (unlikely(!is_valid_virt_queue_idx(queue_id, 0, dev->virt_qp_nb))) {
+ if (unlikely(!is_valid_virt_queue_idx(queue_id, 0, dev->nr_vring))) {
RTE_LOG(ERR, VHOST_DATA, "(%d) %s: invalid virtqueue idx %d.\n",
dev->vid, __func__, queue_id);
return 0;
uint16_t desc_idx = desc_indexes[i];
int err;
- err = copy_mbuf_to_desc(dev, vq, pkts[i], desc_idx);
+ if (vq->desc[desc_idx].flags & VRING_DESC_F_INDIRECT) {
+ descs = (struct vring_desc *)(uintptr_t)
+ rte_vhost_gpa_to_vva(dev->mem,
+ vq->desc[desc_idx].addr);
+ if (unlikely(!descs)) {
+ count = i;
+ break;
+ }
+
+ desc_idx = 0;
+ sz = vq->desc[desc_idx].len / sizeof(*descs);
+ } else {
+ descs = vq->desc;
+ sz = vq->size;
+ }
+
+ err = copy_mbuf_to_desc(dev, descs, pkts[i], desc_idx, sz);
if (unlikely(err)) {
used_idx = (start_idx + i) & (vq->size - 1);
vq->used->ring[used_idx].len = dev->vhost_hlen;
return count;
}
-static inline int __attribute__((always_inline))
-fill_vec_buf(struct vhost_virtqueue *vq, uint32_t avail_idx,
- uint32_t *vec_idx, struct buf_vector *buf_vec,
- uint16_t *desc_chain_head, uint16_t *desc_chain_len)
+static __rte_always_inline int
+fill_vec_buf(struct virtio_net *dev, struct vhost_virtqueue *vq,
+ uint32_t avail_idx, uint32_t *vec_idx,
+ struct buf_vector *buf_vec, uint16_t *desc_chain_head,
+ uint16_t *desc_chain_len)
{
uint16_t idx = vq->avail->ring[avail_idx & (vq->size - 1)];
uint32_t vec_id = *vec_idx;
uint32_t len = 0;
+ struct vring_desc *descs = vq->desc;
*desc_chain_head = idx;
+
+ if (vq->desc[idx].flags & VRING_DESC_F_INDIRECT) {
+ descs = (struct vring_desc *)(uintptr_t)
+ rte_vhost_gpa_to_vva(dev->mem, vq->desc[idx].addr);
+ if (unlikely(!descs))
+ return -1;
+
+ idx = 0;
+ }
+
while (1) {
if (unlikely(vec_id >= BUF_VECTOR_MAX || idx >= vq->size))
return -1;
- len += vq->desc[idx].len;
- buf_vec[vec_id].buf_addr = vq->desc[idx].addr;
- buf_vec[vec_id].buf_len = vq->desc[idx].len;
+ len += descs[idx].len;
+ buf_vec[vec_id].buf_addr = descs[idx].addr;
+ buf_vec[vec_id].buf_len = descs[idx].len;
buf_vec[vec_id].desc_idx = idx;
vec_id++;
- if ((vq->desc[idx].flags & VRING_DESC_F_NEXT) == 0)
+ if ((descs[idx].flags & VRING_DESC_F_NEXT) == 0)
break;
- idx = vq->desc[idx].next;
+ idx = descs[idx].next;
}
*desc_chain_len = len;
* Returns -1 on fail, 0 on success
*/
static inline int
-reserve_avail_buf_mergeable(struct vhost_virtqueue *vq, uint32_t size,
- struct buf_vector *buf_vec, uint16_t *num_buffers)
+reserve_avail_buf_mergeable(struct virtio_net *dev, struct vhost_virtqueue *vq,
+ uint32_t size, struct buf_vector *buf_vec,
+ uint16_t *num_buffers, uint16_t avail_head)
{
uint16_t cur_idx;
- uint16_t avail_idx;
uint32_t vec_idx = 0;
uint16_t tries = 0;
cur_idx = vq->last_avail_idx;
while (size > 0) {
- avail_idx = *((volatile uint16_t *)&vq->avail->idx);
- if (unlikely(cur_idx == avail_idx))
+ if (unlikely(cur_idx == avail_head))
return -1;
- if (unlikely(fill_vec_buf(vq, cur_idx, &vec_idx, buf_vec,
- &head_idx, &len) < 0))
+ if (unlikely(fill_vec_buf(dev, vq, cur_idx, &vec_idx, buf_vec,
+ &head_idx, &len) < 0))
return -1;
len = RTE_MIN(len, size);
update_shadow_used_ring(vq, head_idx, len);
return 0;
}
-static inline int __attribute__((always_inline))
+static __rte_always_inline int
copy_mbuf_to_desc_mergeable(struct virtio_net *dev, struct rte_mbuf *m,
struct buf_vector *buf_vec, uint16_t num_buffers)
{
- struct virtio_net_hdr_mrg_rxbuf virtio_hdr = {{0, 0, 0, 0, 0, 0}, 0};
uint32_t vec_idx = 0;
uint64_t desc_addr;
uint32_t mbuf_offset, mbuf_avail;
if (unlikely(m == NULL))
return -1;
- desc_addr = gpa_to_vva(dev, buf_vec[vec_idx].buf_addr);
+ desc_addr = rte_vhost_gpa_to_vva(dev->mem, buf_vec[vec_idx].buf_addr);
if (buf_vec[vec_idx].buf_len < dev->vhost_hlen || !desc_addr)
return -1;
hdr_phys_addr = buf_vec[vec_idx].buf_addr;
rte_prefetch0((void *)(uintptr_t)hdr_addr);
- virtio_hdr.num_buffers = num_buffers;
LOG_DEBUG(VHOST_DATA, "(%d) RX: num merge buffers %d\n",
dev->vid, num_buffers);
/* done with current desc buf, get the next one */
if (desc_avail == 0) {
vec_idx++;
- desc_addr = gpa_to_vva(dev, buf_vec[vec_idx].buf_addr);
+ desc_addr = rte_vhost_gpa_to_vva(dev->mem,
+ buf_vec[vec_idx].buf_addr);
if (unlikely(!desc_addr))
return -1;
}
if (hdr_addr) {
- virtio_enqueue_offload(hdr_mbuf, &virtio_hdr.hdr);
- copy_virtio_net_hdr(dev, hdr_addr, virtio_hdr);
+ struct virtio_net_hdr_mrg_rxbuf *hdr;
+
+ hdr = (struct virtio_net_hdr_mrg_rxbuf *)(uintptr_t)
+ hdr_addr;
+ virtio_enqueue_offload(hdr_mbuf, &hdr->hdr);
+ ASSIGN_UNLESS_EQUAL(hdr->num_buffers, num_buffers);
+
vhost_log_write(dev, hdr_phys_addr, dev->vhost_hlen);
PRINT_PACKET(dev, (uintptr_t)hdr_addr,
dev->vhost_hlen, 0);
return 0;
}
-static inline uint32_t __attribute__((always_inline))
+static __rte_always_inline uint32_t
virtio_dev_merge_rx(struct virtio_net *dev, uint16_t queue_id,
struct rte_mbuf **pkts, uint32_t count)
{
uint32_t pkt_idx = 0;
uint16_t num_buffers;
struct buf_vector buf_vec[BUF_VECTOR_MAX];
+ uint16_t avail_head;
LOG_DEBUG(VHOST_DATA, "(%d) %s\n", dev->vid, __func__);
- if (unlikely(!is_valid_virt_queue_idx(queue_id, 0, dev->virt_qp_nb))) {
+ if (unlikely(!is_valid_virt_queue_idx(queue_id, 0, dev->nr_vring))) {
RTE_LOG(ERR, VHOST_DATA, "(%d) %s: invalid virtqueue idx %d.\n",
dev->vid, __func__, queue_id);
return 0;
rte_prefetch0(&vq->avail->ring[vq->last_avail_idx & (vq->size - 1)]);
vq->shadow_used_idx = 0;
+ avail_head = *((volatile uint16_t *)&vq->avail->idx);
for (pkt_idx = 0; pkt_idx < count; pkt_idx++) {
uint32_t pkt_len = pkts[pkt_idx]->pkt_len + dev->vhost_hlen;
- if (unlikely(reserve_avail_buf_mergeable(vq, pkt_len, buf_vec,
- &num_buffers) < 0)) {
+ if (unlikely(reserve_avail_buf_mergeable(dev, vq,
+ pkt_len, buf_vec, &num_buffers,
+ avail_head) < 0)) {
LOG_DEBUG(VHOST_DATA,
"(%d) failed to get enough desc from vring\n",
dev->vid);
switch (ethertype) {
case ETHER_TYPE_IPv4:
- ipv4_hdr = (struct ipv4_hdr *)l3_hdr;
+ ipv4_hdr = l3_hdr;
*l4_proto = ipv4_hdr->next_proto_id;
m->l3_len = (ipv4_hdr->version_ihl & 0x0f) * 4;
*l4_hdr = (char *)l3_hdr + m->l3_len;
m->ol_flags |= PKT_TX_IPV4;
break;
case ETHER_TYPE_IPv6:
- ipv6_hdr = (struct ipv6_hdr *)l3_hdr;
+ ipv6_hdr = l3_hdr;
*l4_proto = ipv6_hdr->proto;
m->l3_len = sizeof(struct ipv6_hdr);
*l4_hdr = (char *)l3_hdr + m->l3_len;
default:
m->l3_len = 0;
*l4_proto = 0;
+ *l4_hdr = NULL;
break;
}
}
-static inline void __attribute__((always_inline))
+static __rte_always_inline void
vhost_dequeue_offload(struct virtio_net_hdr *hdr, struct rte_mbuf *m)
{
uint16_t l4_proto = 0;
}
}
- if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) {
+ if (l4_hdr && hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) {
switch (hdr->gso_type & ~VIRTIO_NET_HDR_GSO_ECN) {
case VIRTIO_NET_HDR_GSO_TCPV4:
case VIRTIO_NET_HDR_GSO_TCPV6:
- tcp_hdr = (struct tcp_hdr *)l4_hdr;
+ tcp_hdr = l4_hdr;
m->ol_flags |= PKT_TX_TCP_SEG;
m->tso_segsz = hdr->gso_size;
m->l4_len = (tcp_hdr->data_off & 0xf0) >> 2;
return 0;
}
-static inline void __attribute__((always_inline))
+static __rte_always_inline void
put_zmbuf(struct zcopy_mbuf *zmbuf)
{
zmbuf->in_use = 0;
}
-static inline int __attribute__((always_inline))
+static __rte_always_inline int
copy_desc_to_mbuf(struct virtio_net *dev, struct vring_desc *descs,
uint16_t max_desc, struct rte_mbuf *m, uint16_t desc_idx,
struct rte_mempool *mbuf_pool)
(desc->flags & VRING_DESC_F_INDIRECT))
return -1;
- desc_addr = gpa_to_vva(dev, desc->addr);
+ desc_addr = rte_vhost_gpa_to_vva(dev->mem, desc->addr);
if (unlikely(!desc_addr))
return -1;
if (unlikely(desc->flags & VRING_DESC_F_INDIRECT))
return -1;
- desc_addr = gpa_to_vva(dev, desc->addr);
+ desc_addr = rte_vhost_gpa_to_vva(dev->mem, desc->addr);
if (unlikely(!desc_addr))
return -1;
if (unlikely(desc->flags & VRING_DESC_F_INDIRECT))
return -1;
- desc_addr = gpa_to_vva(dev, desc->addr);
+ desc_addr = rte_vhost_gpa_to_vva(dev->mem, desc->addr);
if (unlikely(!desc_addr))
return -1;
"allocate memory for mbuf.\n");
return -1;
}
+ if (unlikely(dev->dequeue_zero_copy))
+ rte_mbuf_refcnt_update(cur, 1);
prev->next = cur;
prev->data_len = mbuf_offset;
return 0;
}
-static inline void __attribute__((always_inline))
+static __rte_always_inline void
update_used_ring(struct virtio_net *dev, struct vhost_virtqueue *vq,
uint32_t used_idx, uint32_t desc_idx)
{
sizeof(vq->used->ring[used_idx]));
}
-static inline void __attribute__((always_inline))
+static __rte_always_inline void
update_used_idx(struct virtio_net *dev, struct vhost_virtqueue *vq,
uint32_t count)
{
eventfd_write(vq->callfd, (eventfd_t)1);
}
-static inline struct zcopy_mbuf *__attribute__((always_inline))
+static __rte_always_inline struct zcopy_mbuf *
get_zmbuf(struct vhost_virtqueue *vq)
{
uint16_t i;
return NULL;
}
-static inline bool __attribute__((always_inline))
+static __rte_always_inline bool
mbuf_is_consumed(struct rte_mbuf *m)
{
while (m) {
if (!dev)
return 0;
- if (unlikely(!is_valid_virt_queue_idx(queue_id, 1, dev->virt_qp_nb))) {
+ if (unlikely(!is_valid_virt_queue_idx(queue_id, 1, dev->nr_vring))) {
RTE_LOG(ERR, VHOST_DATA, "(%d) %s: invalid virtqueue idx %d.\n",
dev->vid, __func__, queue_id);
return 0;
* array, to looks like that guest actually send such packet.
*
* Check user_send_rarp() for more information.
+ *
+ * broadcast_rarp shares a cacheline in the virtio_net structure
+ * with some fields that are accessed during enqueue and
+ * rte_atomic16_cmpset() causes a write if using cmpxchg. This could
+ * result in false sharing between enqueue and dequeue.
+ *
+ * Prevent unnecessary false sharing by reading broadcast_rarp first
+ * and only performing cmpset if the read indicates it is likely to
+ * be set.
*/
- if (unlikely(rte_atomic16_cmpset((volatile uint16_t *)
- &dev->broadcast_rarp.cnt, 1, 0))) {
+
+ if (unlikely(rte_atomic16_read(&dev->broadcast_rarp) &&
+ rte_atomic16_cmpset((volatile uint16_t *)
+ &dev->broadcast_rarp.cnt, 1, 0))) {
+
rarp_mbuf = rte_pktmbuf_alloc(mbuf_pool);
if (rarp_mbuf == NULL) {
RTE_LOG(ERR, VHOST_DATA,
rte_prefetch0(&vq->desc[desc_indexes[i + 1]]);
if (vq->desc[desc_indexes[i]].flags & VRING_DESC_F_INDIRECT) {
- desc = (struct vring_desc *)(uintptr_t)gpa_to_vva(dev,
+ desc = (struct vring_desc *)(uintptr_t)
+ rte_vhost_gpa_to_vva(dev->mem,
vq->desc[desc_indexes[i]].addr);
if (unlikely(!desc))
break;