1 files changed, 161 insertions, 17 deletions

diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index 396bc1c204e6..9352dad58996 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c
@@ -20,6 +20,7 @@
 #include <linux/vmalloc.h>
 #include <linux/rtnetlink.h>
 #include <linux/prefetch.h>
+#include <linux/filter.h>
 
 #include <asm/sync_bitops.h>
 #include <asm/mshyperv.h>
@@ -153,9 +154,18 @@ static void free_netvsc_device(struct rcu_head *head)
 	int i;
 
 	kfree(nvdev->extension);
-	vfree(nvdev->recv_buf);
-	vfree(nvdev->send_buf);
-	kfree(nvdev->send_section_map);
+
+	if (nvdev->recv_original_buf)
+		vfree(nvdev->recv_original_buf);
+	else
+		vfree(nvdev->recv_buf);
+
+	if (nvdev->send_original_buf)
+		vfree(nvdev->send_original_buf);
+	else
+		vfree(nvdev->send_buf);
+
+	bitmap_free(nvdev->send_section_map);
 
 	for (i = 0; i < VRSS_CHANNEL_MAX; i++) {
 		xdp_rxq_info_unreg(&nvdev->chan_table[i].xdp_rxq);
@@ -336,8 +346,8 @@ static int netvsc_init_buf(struct hv_device *device,
 	struct net_device *ndev = hv_get_drvdata(device);
 	struct nvsp_message *init_packet;
 	unsigned int buf_size;
-	size_t map_words;
 	int i, ret = 0;
+	void *vaddr;
 
 	/* Get receive buffer area. */
 	buf_size = device_info->recv_sections * device_info->recv_section_size;
@@ -373,6 +383,17 @@ static int netvsc_init_buf(struct hv_device *device,
 		goto cleanup;
 	}
 
+	if (hv_isolation_type_snp()) {
+		vaddr = hv_map_memory(net_device->recv_buf, buf_size);
+		if (!vaddr) {
+			ret = -ENOMEM;
+			goto cleanup;
+		}
+
+		net_device->recv_original_buf = net_device->recv_buf;
+		net_device->recv_buf = vaddr;
+	}
+
 	/* Notify the NetVsp of the gpadl handle */
 	init_packet = &net_device->channel_init_pkt;
 	memset(init_packet, 0, sizeof(struct nvsp_message));
@@ -476,6 +497,17 @@ static int netvsc_init_buf(struct hv_device *device,
 		goto cleanup;
 	}
 
+	if (hv_isolation_type_snp()) {
+		vaddr = hv_map_memory(net_device->send_buf, buf_size);
+		if (!vaddr) {
+			ret = -ENOMEM;
+			goto cleanup;
+		}
+
+		net_device->send_original_buf = net_device->send_buf;
+		net_device->send_buf = vaddr;
+	}
+
 	/* Notify the NetVsp of the gpadl handle */
 	init_packet = &net_device->channel_init_pkt;
 	memset(init_packet, 0, sizeof(struct nvsp_message));
@@ -528,10 +560,9 @@ static int netvsc_init_buf(struct hv_device *device,
 		   net_device->send_section_size, net_device->send_section_cnt);
 
 	/* Setup state for managing the send buffer. */
-	map_words = DIV_ROUND_UP(net_device->send_section_cnt, BITS_PER_LONG);
-
-	net_device->send_section_map = kcalloc(map_words, sizeof(ulong), GFP_KERNEL);
-	if (net_device->send_section_map == NULL) {
+	net_device->send_section_map = bitmap_zalloc(net_device->send_section_cnt,
+						     GFP_KERNEL);
+	if (!net_device->send_section_map) {
 		ret = -ENOMEM;
 		goto cleanup;
 	}
@@ -731,6 +762,12 @@ void netvsc_device_remove(struct hv_device *device)
 		netvsc_teardown_send_gpadl(device, net_device, ndev);
 	}
 
+	if (net_device->recv_original_buf)
+		hv_unmap_memory(net_device->recv_buf);
+
+	if (net_device->send_original_buf)
+		hv_unmap_memory(net_device->send_buf);
+
 	/* Release all resources */
 	free_netvsc_device_rcu(net_device);
 }
@@ -756,9 +793,9 @@ static void netvsc_send_tx_complete(struct net_device *ndev,
 	int queue_sends;
 	u64 cmd_rqst;
 
-	cmd_rqst = channel->request_addr_callback(channel, (u64)desc->trans_id);
+	cmd_rqst = channel->request_addr_callback(channel, desc->trans_id);
 	if (cmd_rqst == VMBUS_RQST_ERROR) {
-		netdev_err(ndev, "Incorrect transaction id\n");
+		netdev_err(ndev, "Invalid transaction ID %llx\n", desc->trans_id);
 		return;
 	}
 
@@ -766,10 +803,10 @@ static void netvsc_send_tx_complete(struct net_device *ndev,
 
 	/* Notify the layer above us */
 	if (likely(skb)) {
-		const struct hv_netvsc_packet *packet
+		struct hv_netvsc_packet *packet
 			= (struct hv_netvsc_packet *)skb->cb;
 		u32 send_index = packet->send_buf_index;
-		struct netvsc_stats *tx_stats;
+		struct netvsc_stats_tx *tx_stats;
 
 		if (send_index != NETVSC_INVALID_INDEX)
 			netvsc_free_send_slot(net_device, send_index);
@@ -782,6 +819,7 @@ static void netvsc_send_tx_complete(struct net_device *ndev,
 		tx_stats->bytes += packet->total_bytes;
 		u64_stats_update_end(&tx_stats->syncp);
 
+		netvsc_dma_unmap(ndev_ctx->device_ctx, packet);
 		napi_consume_skb(skb, budget);
 	}
 
@@ -817,9 +855,9 @@ static void netvsc_send_completion(struct net_device *ndev,
 	/* First check if this is a VMBUS completion without data payload */
 	if (!msglen) {
 		cmd_rqst = incoming_channel->request_addr_callback(incoming_channel,
-								   (u64)desc->trans_id);
+								   desc->trans_id);
 		if (cmd_rqst == VMBUS_RQST_ERROR) {
-			netdev_err(ndev, "Invalid transaction id\n");
+			netdev_err(ndev, "Invalid transaction ID %llx\n", desc->trans_id);
 			return;
 		}
 
@@ -946,6 +984,88 @@ static void netvsc_copy_to_send_buf(struct netvsc_device *net_device,
 		memset(dest, 0, padding);
 }
 
+void netvsc_dma_unmap(struct hv_device *hv_dev,
+		      struct hv_netvsc_packet *packet)
+{
+	u32 page_count = packet->cp_partial ?
+		packet->page_buf_cnt - packet->rmsg_pgcnt :
+		packet->page_buf_cnt;
+	int i;
+
+	if (!hv_is_isolation_supported())
+		return;
+
+	if (!packet->dma_range)
+		return;
+
+	for (i = 0; i < page_count; i++)
+		dma_unmap_single(&hv_dev->device, packet->dma_range[i].dma,
+				 packet->dma_range[i].mapping_size,
+				 DMA_TO_DEVICE);
+
+	kfree(packet->dma_range);
+}
+
+/* netvsc_dma_map - Map swiotlb bounce buffer with data page of
+ * packet sent by vmbus_sendpacket_pagebuffer() in the Isolation
+ * VM.
+ *
+ * In isolation VM, netvsc send buffer has been marked visible to
+ * host and so the data copied to send buffer doesn't need to use
+ * bounce buffer. The data pages handled by vmbus_sendpacket_pagebuffer()
+ * may not be copied to send buffer and so these pages need to be
+ * mapped with swiotlb bounce buffer. netvsc_dma_map() is to do
+ * that. The pfns in the struct hv_page_buffer need to be converted
+ * to bounce buffer's pfn. The loop here is necessary because the
+ * entries in the page buffer array are not necessarily full
+ * pages of data.  Each entry in the array has a separate offset and
+ * len that may be non-zero, even for entries in the middle of the
+ * array.  And the entries are not physically contiguous.  So each
+ * entry must be individually mapped rather than as a contiguous unit.
+ * So not use dma_map_sg() here.
+ */
+static int netvsc_dma_map(struct hv_device *hv_dev,
+			  struct hv_netvsc_packet *packet,
+			  struct hv_page_buffer *pb)
+{
+	u32 page_count =  packet->cp_partial ?
+		packet->page_buf_cnt - packet->rmsg_pgcnt :
+		packet->page_buf_cnt;
+	dma_addr_t dma;
+	int i;
+
+	if (!hv_is_isolation_supported())
+		return 0;
+
+	packet->dma_range = kcalloc(page_count,
+				    sizeof(*packet->dma_range),
+				    GFP_KERNEL);
+	if (!packet->dma_range)
+		return -ENOMEM;
+
+	for (i = 0; i < page_count; i++) {
+		char *src = phys_to_virt((pb[i].pfn << HV_HYP_PAGE_SHIFT)
+					 + pb[i].offset);
+		u32 len = pb[i].len;
+
+		dma = dma_map_single(&hv_dev->device, src, len,
+				     DMA_TO_DEVICE);
+		if (dma_mapping_error(&hv_dev->device, dma)) {
+			kfree(packet->dma_range);
+			return -ENOMEM;
+		}
+
+		/* pb[].offset and pb[].len are not changed during dma mapping
+		 * and so not reassign.
+		 */
+		packet->dma_range[i].dma = dma;
+		packet->dma_range[i].mapping_size = len;
+		pb[i].pfn = dma >> HV_HYP_PAGE_SHIFT;
+	}
+
+	return 0;
+}
+
 static inline int netvsc_send_pkt(
 	struct hv_device *device,
 	struct hv_netvsc_packet *packet,
@@ -986,14 +1106,24 @@ static inline int netvsc_send_pkt(
 
 	trace_nvsp_send_pkt(ndev, out_channel, rpkt);
 
+	packet->dma_range = NULL;
 	if (packet->page_buf_cnt) {
 		if (packet->cp_partial)
 			pb += packet->rmsg_pgcnt;
 
+		ret = netvsc_dma_map(ndev_ctx->device_ctx, packet, pb);
+		if (ret) {
+			ret = -EAGAIN;
+			goto exit;
+		}
+
 		ret = vmbus_sendpacket_pagebuffer(out_channel,
 						  pb, packet->page_buf_cnt,
 						  &nvmsg, sizeof(nvmsg),
 						  req_id);
+
+		if (ret)
+			netvsc_dma_unmap(ndev_ctx->device_ctx, packet);
 	} else {
 		ret = vmbus_sendpacket(out_channel,
 				       &nvmsg, sizeof(nvmsg),
@@ -1001,6 +1131,7 @@ static inline int netvsc_send_pkt(
 				       VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
 	}
 
+exit:
 	if (ret == 0) {
 		atomic_inc_return(&nvchan->queue_sends);
 
@@ -1449,6 +1580,10 @@ static void netvsc_send_vf(struct net_device *ndev,
 
 	net_device_ctx->vf_alloc = nvmsg->msg.v4_msg.vf_assoc.allocated;
 	net_device_ctx->vf_serial = nvmsg->msg.v4_msg.vf_assoc.serial;
+
+	if (net_device_ctx->vf_alloc)
+		complete(&net_device_ctx->vf_add);
+
 	netdev_info(ndev, "VF slot %u %s\n",
 		    net_device_ctx->vf_serial,
 		    net_device_ctx->vf_alloc ? "added" : "removed");
@@ -1500,7 +1635,6 @@ static int netvsc_process_raw_pkt(struct hv_device *device,
 
 	case VM_PKT_DATA_USING_XFER_PAGES:
 		return netvsc_receive(ndev, net_device, nvchan, desc);
-		break;
 
 	case VM_PKT_DATA_INBAND:
 		netvsc_receive_inband(ndev, net_device, desc);
@@ -1541,12 +1675,17 @@ int netvsc_poll(struct napi_struct *napi, int budget)
 	if (!nvchan->desc)
 		nvchan->desc = hv_pkt_iter_first(channel);
 
+	nvchan->xdp_flush = false;
+
 	while (nvchan->desc && work_done < budget) {
 		work_done += netvsc_process_raw_pkt(device, nvchan, net_device,
 						    ndev, nvchan->desc, budget);
 		nvchan->desc = hv_pkt_iter_next(channel, nvchan->desc);
 	}
 
+	if (nvchan->xdp_flush)
+		xdp_do_flush();
+
 	/* Send any pending receive completions */
 	ret = send_recv_completions(ndev, net_device, nvchan);
 
@@ -1644,8 +1783,7 @@ struct netvsc_device *netvsc_device_add(struct hv_device *device,
 	}
 
 	/* Enable NAPI handler before init callbacks */
-	netif_napi_add(ndev, &net_device->chan_table[0].napi,
-		       netvsc_poll, NAPI_POLL_WEIGHT);
+	netif_napi_add(ndev, &net_device->chan_table[0].napi, netvsc_poll);
 
 	/* Open the channel */
 	device->channel->next_request_id_callback = vmbus_next_request_id;
@@ -1693,6 +1831,12 @@ cleanup:
 	netif_napi_del(&net_device->chan_table[0].napi);
 
 cleanup2:
+	if (net_device->recv_original_buf)
+		hv_unmap_memory(net_device->recv_buf);
+
+	if (net_device->send_original_buf)
+		hv_unmap_memory(net_device->send_buf);
+
 	free_netvsc_device(&net_device->rcu);
 
 	return ERR_PTR(ret);