X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=lib%2Fvhost%2Fvhost_user.c;h=f99692bdc1d3d8f89cdfda0090069daa5897fa90;hb=8974b6c730a1f8e9cd64d327e3df53d2b86fb2a4;hp=5a894ca0cc75124c9a5767092f03152da598b5c0;hpb=e7cb7fdf5471d96edd586dd318511d8a892c41ca;p=dpdk.git

diff --git a/lib/vhost/vhost_user.c b/lib/vhost/vhost_user.c
index 5a894ca0cc..f99692bdc1 100644
--- a/lib/vhost/vhost_user.c
+++ b/lib/vhost/vhost_user.c
@@ -45,6 +45,8 @@
 #include <rte_common.h>
 #include <rte_malloc.h>
 #include <rte_log.h>
+#include <rte_vfio.h>
+#include <rte_errno.h>
 
 #include "iotlb.h"
 #include "vhost.h"
@@ -141,6 +143,59 @@ get_blk_size(int fd)
 	return ret == -1 ? (uint64_t)-1 : (uint64_t)stat.st_blksize;
 }
 
+static int
+async_dma_map(struct rte_vhost_mem_region *region, bool do_map)
+{
+	uint64_t host_iova;
+	int ret = 0;
+
+	host_iova = rte_mem_virt2iova((void *)(uintptr_t)region->host_user_addr);
+	if (do_map) {
+		/* Add mapped region into the default container of DPDK. */
+		ret = rte_vfio_container_dma_map(RTE_VFIO_DEFAULT_CONTAINER_FD,
+						 region->host_user_addr,
+						 host_iova,
+						 region->size);
+		if (ret) {
+			/*
+			 * DMA device may bind with kernel driver, in this case,
+			 * we don't need to program IOMMU manually. However, if no
+			 * device is bound with vfio/uio in DPDK, and vfio kernel
+			 * module is loaded, the API will still be called and return
+			 * with ENODEV/ENOSUP.
+			 *
+			 * DPDK vfio only returns ENODEV/ENOSUP in very similar
+			 * situations(vfio either unsupported, or supported
+			 * but no devices found). Either way, no mappings could be
+			 * performed. We treat it as normal case in async path.
+			 */
+			if (rte_errno == ENODEV || rte_errno == ENOTSUP)
+				return 0;
+
+			VHOST_LOG_CONFIG(ERR, "DMA engine map failed\n");
+			/* DMA mapping errors won't stop VHST_USER_SET_MEM_TABLE. */
+			return 0;
+		}
+
+	} else {
+		/* Remove mapped region from the default container of DPDK. */
+		ret = rte_vfio_container_dma_unmap(RTE_VFIO_DEFAULT_CONTAINER_FD,
+						   region->host_user_addr,
+						   host_iova,
+						   region->size);
+		if (ret) {
+			/* like DMA map, ignore the kernel driver case when unmap. */
+			if (rte_errno == EINVAL)
+				return 0;
+
+			VHOST_LOG_CONFIG(ERR, "DMA engine unmap failed\n");
+			return ret;
+		}
+	}
+
+	return ret;
+}
+
 static void
 free_mem_region(struct virtio_net *dev)
 {
@@ -153,6 +208,9 @@ free_mem_region(struct virtio_net *dev)
 	for (i = 0; i < dev->mem->nregions; i++) {
 		reg = &dev->mem->regions[i];
 		if (reg->host_user_addr) {
+			if (dev->async_copy && rte_vfio_is_enabled("vfio"))
+				async_dma_map(reg, false);
+
 			munmap(reg->mmap_addr, reg->mmap_size);
 			close(reg->fd);
 		}
@@ -915,6 +973,11 @@ vhost_user_set_vring_base(struct virtio_net **pdev,
 		vq->last_avail_idx = msg->payload.state.num;
 	}
 
+	VHOST_LOG_CONFIG(INFO,
+		"(%s) vring base idx:%u last_used_idx:%u last_avail_idx:%u.\n",
+		dev->ifname, msg->payload.state.index, vq->last_used_idx,
+		vq->last_avail_idx);
+
 	return RTE_VHOST_MSG_RESULT_OK;
 }
 
@@ -1057,7 +1120,7 @@ vhost_user_postcopy_region_register(struct virtio_net *dev,
 	struct uffdio_register reg_struct;
 
 	/*
-	 * Let's register all the mmap'ed area to ensure
+	 * Let's register all the mmapped area to ensure
 	 * alignment on page boundary.
 	 */
 	reg_struct.range.start = (uint64_t)(uintptr_t)reg->mmap_addr;
@@ -1119,7 +1182,7 @@ vhost_user_postcopy_register(struct virtio_net *dev, int main_fd,
 	msg->fd_num = 0;
 	send_vhost_reply(main_fd, msg);
 
-	/* Wait for qemu to acknolwedge it's got the addresses
+	/* Wait for qemu to acknowledge it got the addresses
 	 * we've got to wait before we're allowed to generate faults.
 	 */
 	if (read_vhost_message(main_fd, &ack_msg) <= 0) {
@@ -1157,6 +1220,7 @@ vhost_user_mmap_region(struct virtio_net *dev,
 	uint64_t mmap_size;
 	uint64_t alignment;
 	int populate;
+	int ret;
 
 	/* Check for memory_size + mmap_offset overflow */
 	if (mmap_offset >= -region->size) {
@@ -1210,13 +1274,21 @@ vhost_user_mmap_region(struct virtio_net *dev,
 	region->mmap_size = mmap_size;
 	region->host_user_addr = (uint64_t)(uintptr_t)mmap_addr + mmap_offset;
 
-	if (dev->async_copy)
+	if (dev->async_copy) {
 		if (add_guest_pages(dev, region, alignment) < 0) {
-			VHOST_LOG_CONFIG(ERR,
-					"adding guest pages to region failed.\n");
+			VHOST_LOG_CONFIG(ERR, "adding guest pages to region failed.\n");
 			return -1;
 		}
 
+		if (rte_vfio_is_enabled("vfio")) {
+			ret = async_dma_map(region, true);
+			if (ret) {
+				VHOST_LOG_CONFIG(ERR, "Configure IOMMU for DMA engine failed\n");
+				return -1;
+			}
+		}
+	}
+
 	VHOST_LOG_CONFIG(INFO,
 			"guest memory region size: 0x%" PRIx64 "\n"
 			"\t guest physical addr: 0x%" PRIx64 "\n"
@@ -1393,6 +1465,7 @@ free_mem_table:
 	free_mem_region(dev);
 	rte_free(dev->mem);
 	dev->mem = NULL;
+
 free_guest_pages:
 	rte_free(dev->guest_pages);
 	dev->guest_pages = NULL;
@@ -2140,8 +2213,8 @@ vhost_user_set_vring_enable(struct virtio_net **pdev,
 		"set queue enable: %d to qp idx: %d\n",
 		enable, index);
 
-	if (enable && dev->virtqueue[index]->async_registered) {
-		if (dev->virtqueue[index]->async_pkts_inflight_n) {
+	if (enable && dev->virtqueue[index]->async) {
+		if (dev->virtqueue[index]->async->pkts_inflight_n) {
 			VHOST_LOG_CONFIG(ERR, "failed to enable vring. "
 			"async inflight packets must be completed first\n");
 			return RTE_VHOST_MSG_RESULT_ERR;