#define VIRTNET_SQ_STATS_LEN ARRAY_SIZE(virtnet_sq_stats_desc)
#define VIRTNET_RQ_STATS_LEN ARRAY_SIZE(virtnet_rq_stats_desc)
+/* The dma information of pages allocated at a time. */
+struct virtnet_rq_dma {
+ dma_addr_t addr;
+ u32 ref;
+ u16 len;
+ u16 need_sync;
+};
+
/* Internal representation of a send virtqueue */
struct send_queue {
/* Virtqueue associated with this send _queue */
char name[16];
struct xdp_rxq_info xdp_rxq;
+
+ /* Record the last dma info to free after new pages is allocated. */
+ struct virtnet_rq_dma *last_dma;
+
+ /* Do dma by self */
+ bool do_dma;
};
/* This structure can contain rss message with maximum settings for indirection table and keysize
return skb;
}
+static void virtnet_rq_unmap(struct receive_queue *rq, void *buf, u32 len)
+{
+ struct page *page = virt_to_head_page(buf);
+ struct virtnet_rq_dma *dma;
+ void *head;
+ int offset;
+
+ head = page_address(page);
+
+ dma = head;
+
+ --dma->ref;
+
+ if (dma->ref) {
+ if (dma->need_sync && len) {
+ offset = buf - (head + sizeof(*dma));
+
+ virtqueue_dma_sync_single_range_for_cpu(rq->vq, dma->addr, offset,
+ len, DMA_FROM_DEVICE);
+ }
+
+ return;
+ }
+
+ virtqueue_dma_unmap_single_attrs(rq->vq, dma->addr, dma->len,
+ DMA_FROM_DEVICE, DMA_ATTR_SKIP_CPU_SYNC);
+ put_page(page);
+}
+
+static void *virtnet_rq_get_buf(struct receive_queue *rq, u32 *len, void **ctx)
+{
+ void *buf;
+
+ buf = virtqueue_get_buf_ctx(rq->vq, len, ctx);
+ if (buf && rq->do_dma)
+ virtnet_rq_unmap(rq, buf, *len);
+
+ return buf;
+}
+
+static void *virtnet_rq_detach_unused_buf(struct receive_queue *rq)
+{
+ void *buf;
+
+ buf = virtqueue_detach_unused_buf(rq->vq);
+ if (buf && rq->do_dma)
+ virtnet_rq_unmap(rq, buf, 0);
+
+ return buf;
+}
+
+static void virtnet_rq_init_one_sg(struct receive_queue *rq, void *buf, u32 len)
+{
+ struct virtnet_rq_dma *dma;
+ dma_addr_t addr;
+ u32 offset;
+ void *head;
+
+ if (!rq->do_dma) {
+ sg_init_one(rq->sg, buf, len);
+ return;
+ }
+
+ head = page_address(rq->alloc_frag.page);
+
+ offset = buf - head;
+
+ dma = head;
+
+ addr = dma->addr - sizeof(*dma) + offset;
+
+ sg_init_table(rq->sg, 1);
+ rq->sg[0].dma_address = addr;
+ rq->sg[0].length = len;
+}
+
+static void *virtnet_rq_alloc(struct receive_queue *rq, u32 size, gfp_t gfp)
+{
+ struct page_frag *alloc_frag = &rq->alloc_frag;
+ struct virtnet_rq_dma *dma;
+ void *buf, *head;
+ dma_addr_t addr;
+
+ if (unlikely(!skb_page_frag_refill(size, alloc_frag, gfp)))
+ return NULL;
+
+ head = page_address(alloc_frag->page);
+
+ if (rq->do_dma) {
+ dma = head;
+
+ /* new pages */
+ if (!alloc_frag->offset) {
+ if (rq->last_dma) {
+ /* Now, the new page is allocated, the last dma
+ * will not be used. So the dma can be unmapped
+ * if the ref is 0.
+ */
+ virtnet_rq_unmap(rq, rq->last_dma, 0);
+ rq->last_dma = NULL;
+ }
+
+ dma->len = alloc_frag->size - sizeof(*dma);
+
+ addr = virtqueue_dma_map_single_attrs(rq->vq, dma + 1,
+ dma->len, DMA_FROM_DEVICE, 0);
+ if (virtqueue_dma_mapping_error(rq->vq, addr))
+ return NULL;
+
+ dma->addr = addr;
+ dma->need_sync = virtqueue_dma_need_sync(rq->vq, addr);
+
+ /* Add a reference to dma to prevent the entire dma from
+ * being released during error handling. This reference
+ * will be freed after the pages are no longer used.
+ */
+ get_page(alloc_frag->page);
+ dma->ref = 1;
+ alloc_frag->offset = sizeof(*dma);
+
+ rq->last_dma = dma;
+ }
+
+ ++dma->ref;
+ }
+
+ buf = head + alloc_frag->offset;
+
+ get_page(alloc_frag->page);
+ alloc_frag->offset += size;
+
+ return buf;
+}
+
+static void virtnet_rq_set_premapped(struct virtnet_info *vi)
+{
+ int i;
+
+ /* disable for big mode */
+ if (!vi->mergeable_rx_bufs && vi->big_packets)
+ return;
+
+ for (i = 0; i < vi->max_queue_pairs; i++) {
+ if (virtqueue_set_dma_premapped(vi->rq[i].vq))
+ continue;
+
+ vi->rq[i].do_dma = true;
+ }
+}
+
static void free_old_xmit_skbs(struct send_queue *sq, bool in_napi)
{
unsigned int len;
void *buf;
int off;
- buf = virtqueue_get_buf(rq->vq, &buflen);
+ buf = virtnet_rq_get_buf(rq, &buflen, NULL);
if (unlikely(!buf))
goto err_buf;
int len;
while (num_buf-- > 1) {
- buf = virtqueue_get_buf(rq->vq, &len);
+ buf = virtnet_rq_get_buf(rq, &len, NULL);
if (unlikely(!buf)) {
pr_debug("%s: rx error: %d buffers missing\n",
dev->name, num_buf);
return -EINVAL;
while (--*num_buf > 0) {
- buf = virtqueue_get_buf_ctx(rq->vq, &len, &ctx);
+ buf = virtnet_rq_get_buf(rq, &len, &ctx);
if (unlikely(!buf)) {
pr_debug("%s: rx error: %d buffers out of %d missing\n",
dev->name, *num_buf,
while (--num_buf) {
int num_skb_frags;
- buf = virtqueue_get_buf_ctx(rq->vq, &len, &ctx);
+ buf = virtnet_rq_get_buf(rq, &len, &ctx);
if (unlikely(!buf)) {
pr_debug("%s: rx error: %d buffers out of %d missing\n",
dev->name, num_buf,
static int add_recvbuf_small(struct virtnet_info *vi, struct receive_queue *rq,
gfp_t gfp)
{
- struct page_frag *alloc_frag = &rq->alloc_frag;
char *buf;
unsigned int xdp_headroom = virtnet_get_headroom(vi);
void *ctx = (void *)(unsigned long)xdp_headroom;
len = SKB_DATA_ALIGN(len) +
SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
- if (unlikely(!skb_page_frag_refill(len, alloc_frag, gfp)))
+
+ buf = virtnet_rq_alloc(rq, len, gfp);
+ if (unlikely(!buf))
return -ENOMEM;
- buf = (char *)page_address(alloc_frag->page) + alloc_frag->offset;
- get_page(alloc_frag->page);
- alloc_frag->offset += len;
- sg_init_one(rq->sg, buf + VIRTNET_RX_PAD + xdp_headroom,
- vi->hdr_len + GOOD_PACKET_LEN);
+ virtnet_rq_init_one_sg(rq, buf + VIRTNET_RX_PAD + xdp_headroom,
+ vi->hdr_len + GOOD_PACKET_LEN);
+
err = virtqueue_add_inbuf_ctx(rq->vq, rq->sg, 1, buf, ctx, gfp);
- if (err < 0)
+ if (err < 0) {
+ if (rq->do_dma)
+ virtnet_rq_unmap(rq, buf, 0);
put_page(virt_to_head_page(buf));
+ }
+
return err;
}
unsigned int headroom = virtnet_get_headroom(vi);
unsigned int tailroom = headroom ? sizeof(struct skb_shared_info) : 0;
unsigned int room = SKB_DATA_ALIGN(headroom + tailroom);
- char *buf;
+ unsigned int len, hole;
void *ctx;
+ char *buf;
int err;
- unsigned int len, hole;
/* Extra tailroom is needed to satisfy XDP's assumption. This
* means rx frags coalescing won't work, but consider we've
* disabled GSO for XDP, it won't be a big issue.
*/
len = get_mergeable_buf_len(rq, &rq->mrg_avg_pkt_len, room);
- if (unlikely(!skb_page_frag_refill(len + room, alloc_frag, gfp)))
+
+ buf = virtnet_rq_alloc(rq, len + room, gfp);
+ if (unlikely(!buf))
return -ENOMEM;
- buf = (char *)page_address(alloc_frag->page) + alloc_frag->offset;
buf += headroom; /* advance address leaving hole at front of pkt */
- get_page(alloc_frag->page);
- alloc_frag->offset += len + room;
hole = alloc_frag->size - alloc_frag->offset;
if (hole < len + room) {
/* To avoid internal fragmentation, if there is very likely not
alloc_frag->offset += hole;
}
- sg_init_one(rq->sg, buf, len);
+ virtnet_rq_init_one_sg(rq, buf, len);
+
ctx = mergeable_len_to_ctx(len + room, headroom);
err = virtqueue_add_inbuf_ctx(rq->vq, rq->sg, 1, buf, ctx, gfp);
- if (err < 0)
+ if (err < 0) {
+ if (rq->do_dma)
+ virtnet_rq_unmap(rq, buf, 0);
put_page(virt_to_head_page(buf));
+ }
return err;
}
void *ctx;
while (stats.packets < budget &&
- (buf = virtqueue_get_buf_ctx(rq->vq, &len, &ctx))) {
+ (buf = virtnet_rq_get_buf(rq, &len, &ctx))) {
receive_buf(vi, rq, buf, len, ctx, xdp_xmit, &stats);
stats.packets++;
}
} else {
while (stats.packets < budget &&
- (buf = virtqueue_get_buf(rq->vq, &len)) != NULL) {
+ (buf = virtnet_rq_get_buf(rq, &len, NULL)) != NULL) {
receive_buf(vi, rq, buf, len, NULL, xdp_xmit, &stats);
stats.packets++;
}
{
int i;
for (i = 0; i < vi->max_queue_pairs; i++)
- if (vi->rq[i].alloc_frag.page)
+ if (vi->rq[i].alloc_frag.page) {
+ if (vi->rq[i].do_dma && vi->rq[i].last_dma)
+ virtnet_rq_unmap(&vi->rq[i], vi->rq[i].last_dma, 0);
put_page(vi->rq[i].alloc_frag.page);
+ }
}
static void virtnet_sq_free_unused_buf(struct virtqueue *vq, void *buf)
}
for (i = 0; i < vi->max_queue_pairs; i++) {
- struct virtqueue *vq = vi->rq[i].vq;
- while ((buf = virtqueue_detach_unused_buf(vq)) != NULL)
- virtnet_rq_free_unused_buf(vq, buf);
+ struct receive_queue *rq = &vi->rq[i];
+
+ while ((buf = virtnet_rq_detach_unused_buf(rq)) != NULL)
+ virtnet_rq_free_unused_buf(rq->vq, buf);
cond_resched();
}
}
if (ret)
goto err_free;
+ virtnet_rq_set_premapped(vi);
+
cpus_read_lock();
virtnet_set_affinity(vi);
cpus_read_unlock();