X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=lib%2Flibrte_vhost%2Fvhost.c;h=afded4952f947b9450173beb122ed921b218a271;hb=2017bc33561af8e9880f077cef541ea947a06de0;hp=f0ed7290a25683c0619725002a286e158cd353f4;hpb=ab4d7b9f1afcc70719b0a3040efcc11950ccfa75;p=dpdk.git

diff --git a/lib/librte_vhost/vhost.c b/lib/librte_vhost/vhost.c
index f0ed7290a2..afded4952f 100644
--- a/lib/librte_vhost/vhost.c
+++ b/lib/librte_vhost/vhost.c
@@ -1,34 +1,5 @@
-/*-
- *   BSD LICENSE
- *
- *   Copyright(c) 2010-2016 Intel Corporation. All rights reserved.
- *   All rights reserved.
- *
- *   Redistribution and use in source and binary forms, with or without
- *   modification, are permitted provided that the following conditions
- *   are met:
- *
- *     * Redistributions of source code must retain the above copyright
- *       notice, this list of conditions and the following disclaimer.
- *     * Redistributions in binary form must reproduce the above copyright
- *       notice, this list of conditions and the following disclaimer in
- *       the documentation and/or other materials provided with the
- *       distribution.
- *     * Neither the name of Intel Corporation nor the names of its
- *       contributors may be used to endorse or promote products derived
- *       from this software without specific prior written permission.
- *
- *   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- *   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- *   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- *   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- *   OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- *   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- *   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- *   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- *   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- *   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- *   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2010-2017 Intel Corporation
  */
 
 #include <linux/vhost.h>
@@ -40,31 +11,64 @@
 #include <numaif.h>
 #endif
 
+#include <rte_errno.h>
 #include <rte_ethdev.h>
 #include <rte_log.h>
 #include <rte_string_fns.h>
 #include <rte_memory.h>
 #include <rte_malloc.h>
-#include <rte_virtio_net.h>
+#include <rte_vhost.h>
+#include <rte_rwlock.h>
 
+#include "iotlb.h"
 #include "vhost.h"
+#include "vhost_user.h"
 
 struct virtio_net *vhost_devices[MAX_VHOST_DEVICE];
 
-struct virtio_net *
-get_device(int vid)
+/* Called with iotlb_lock read-locked */
+uint64_t
+__vhost_iova_to_vva(struct virtio_net *dev, struct vhost_virtqueue *vq,
+		    uint64_t iova, uint64_t *size, uint8_t perm)
 {
-	struct virtio_net *dev = vhost_devices[vid];
+	uint64_t vva, tmp_size;
 
-	if (unlikely(!dev)) {
-		RTE_LOG(ERR, VHOST_CONFIG,
-			"(%d) device not found.\n", vid);
+	if (unlikely(!*size))
+		return 0;
+
+	tmp_size = *size;
+
+	vva = vhost_user_iotlb_cache_find(vq, iova, &tmp_size, perm);
+	if (tmp_size == *size)
+		return vva;
+
+	iova += tmp_size;
+
+	if (!vhost_user_iotlb_pending_miss(vq, iova, perm)) {
+		/*
+		 * iotlb_lock is read-locked for a full burst,
+		 * but it only protects the iotlb cache.
+		 * In case of IOTLB miss, we might block on the socket,
+		 * which could cause a deadlock with QEMU if an IOTLB update
+		 * is being handled. We can safely unlock here to avoid it.
+		 */
+		vhost_user_iotlb_rd_unlock(vq);
+
+		vhost_user_iotlb_pending_insert(vq, iova, perm);
+		if (vhost_user_iotlb_miss(dev, iova, perm)) {
+			RTE_LOG(ERR, VHOST_CONFIG,
+				"IOTLB miss req failed for IOVA 0x%" PRIx64 "\n",
+				iova);
+			vhost_user_iotlb_pending_remove(vq, iova, 1, perm);
+		}
+
+		vhost_user_iotlb_rd_lock(vq);
 	}
 
-	return dev;
+	return 0;
 }
 
-static void
+void
 cleanup_vq(struct vhost_virtqueue *vq, int destroy)
 {
 	if ((vq->callfd >= 0) && (destroy != 0))
@@ -88,6 +92,15 @@ cleanup_device(struct virtio_net *dev, int destroy)
 		cleanup_vq(dev->virtqueue[i], destroy);
 }
 
+void
+free_vq(struct vhost_virtqueue *vq)
+{
+	rte_free(vq->shadow_used_ring);
+	rte_free(vq->batch_copy_elems);
+	rte_mempool_free(vq->iotlb_pool);
+	rte_free(vq);
+}
+
 /*
  * Release virtqueues and device memory.
  */
@@ -95,46 +108,114 @@ static void
 free_device(struct virtio_net *dev)
 {
 	uint32_t i;
-	struct vhost_virtqueue *vq;
 
-	for (i = 0; i < dev->nr_vring; i++) {
-		vq = dev->virtqueue[i];
+	for (i = 0; i < dev->nr_vring; i++)
+		free_vq(dev->virtqueue[i]);
 
-		rte_free(vq->shadow_used_ring);
+	rte_free(dev);
+}
 
-		rte_free(vq);
-	}
+int
+vring_translate(struct virtio_net *dev, struct vhost_virtqueue *vq)
+{
+	uint64_t req_size, size;
 
-	rte_free(dev);
+	if (!(dev->features & (1ULL << VIRTIO_F_IOMMU_PLATFORM)))
+		goto out;
+
+	req_size = sizeof(struct vring_desc) * vq->size;
+	size = req_size;
+	vq->desc = (struct vring_desc *)(uintptr_t)vhost_iova_to_vva(dev, vq,
+						vq->ring_addrs.desc_user_addr,
+						&size, VHOST_ACCESS_RW);
+	if (!vq->desc || size != req_size)
+		return -1;
+
+	req_size = sizeof(struct vring_avail);
+	req_size += sizeof(uint16_t) * vq->size;
+	if (dev->features & (1ULL << VIRTIO_RING_F_EVENT_IDX))
+		req_size += sizeof(uint16_t);
+	size = req_size;
+	vq->avail = (struct vring_avail *)(uintptr_t)vhost_iova_to_vva(dev, vq,
+						vq->ring_addrs.avail_user_addr,
+						&size, VHOST_ACCESS_RW);
+	if (!vq->avail || size != req_size)
+		return -1;
+
+	req_size = sizeof(struct vring_used);
+	req_size += sizeof(struct vring_used_elem) * vq->size;
+	if (dev->features & (1ULL << VIRTIO_RING_F_EVENT_IDX))
+		req_size += sizeof(uint16_t);
+	size = req_size;
+	vq->used = (struct vring_used *)(uintptr_t)vhost_iova_to_vva(dev, vq,
+						vq->ring_addrs.used_user_addr,
+						&size, VHOST_ACCESS_RW);
+	if (!vq->used || size != req_size)
+		return -1;
+
+out:
+	vq->access_ok = 1;
+
+	return 0;
+}
+
+void
+vring_invalidate(struct virtio_net *dev, struct vhost_virtqueue *vq)
+{
+	if (dev->features & (1ULL << VIRTIO_F_IOMMU_PLATFORM))
+		vhost_user_iotlb_wr_lock(vq);
+
+	vq->access_ok = 0;
+	vq->desc = NULL;
+	vq->avail = NULL;
+	vq->used = NULL;
+
+	if (dev->features & (1ULL << VIRTIO_F_IOMMU_PLATFORM))
+		vhost_user_iotlb_wr_unlock(vq);
 }
 
 static void
-init_vring_queue(struct vhost_virtqueue *vq)
+init_vring_queue(struct virtio_net *dev, uint32_t vring_idx)
 {
+	struct vhost_virtqueue *vq;
+
+	if (vring_idx >= VHOST_MAX_VRING) {
+		RTE_LOG(ERR, VHOST_CONFIG,
+				"Failed not init vring, out of bound (%d)\n",
+				vring_idx);
+		return;
+	}
+
+	vq = dev->virtqueue[vring_idx];
+
 	memset(vq, 0, sizeof(struct vhost_virtqueue));
 
 	vq->kickfd = VIRTIO_UNINITIALIZED_EVENTFD;
 	vq->callfd = VIRTIO_UNINITIALIZED_EVENTFD;
 
+	vhost_user_iotlb_init(dev, vring_idx);
 	/* Backends are set to -1 indicating an inactive device. */
 	vq->backend = -1;
 
-	/*
-	 * always set the vq to enabled; this is to keep compatibility
-	 * with the old QEMU, whereas there is no SET_VRING_ENABLE message.
-	 */
-	vq->enabled = 1;
-
 	TAILQ_INIT(&vq->zmbuf_list);
 }
 
 static void
-reset_vring_queue(struct vhost_virtqueue *vq)
+reset_vring_queue(struct virtio_net *dev, uint32_t vring_idx)
 {
+	struct vhost_virtqueue *vq;
 	int callfd;
 
+	if (vring_idx >= VHOST_MAX_VRING) {
+		RTE_LOG(ERR, VHOST_CONFIG,
+				"Failed not init vring, out of bound (%d)\n",
+				vring_idx);
+		return;
+	}
+
+	vq = dev->virtqueue[vring_idx];
 	callfd = vq->callfd;
-	init_vring_queue(vq);
+	init_vring_queue(dev, vring_idx);
 	vq->callfd = callfd;
 }
 
@@ -151,7 +232,8 @@ alloc_vring_queue(struct virtio_net *dev, uint32_t vring_idx)
 	}
 
 	dev->virtqueue[vring_idx] = vq;
-	init_vring_queue(vq);
+	init_vring_queue(dev, vring_idx);
+	rte_spinlock_init(&vq->access_lock);
 
 	dev->nr_vring += 1;
 
@@ -170,10 +252,10 @@ reset_device(struct virtio_net *dev)
 
 	dev->features = 0;
 	dev->protocol_features = 0;
-	dev->flags = 0;
+	dev->flags &= VIRTIO_DEV_BUILTIN_VIRTIO_NET;
 
 	for (i = 0; i < dev->nr_vring; i++)
-		reset_vring_queue(dev->virtqueue[i]);
+		reset_vring_queue(dev, i);
 }
 
 /*
@@ -206,6 +288,9 @@ vhost_new_device(void)
 
 	vhost_devices[i] = dev;
 	dev->vid = i;
+	dev->flags = VIRTIO_DEV_BUILTIN_VIRTIO_NET;
+	dev->slave_req_fd = -1;
+	dev->vdpa_dev_id = -1;
 
 	return i;
 }
@@ -218,11 +303,17 @@ void
 vhost_destroy_device(int vid)
 {
 	struct virtio_net *dev = get_device(vid);
+	struct rte_vdpa_device *vdpa_dev;
+	int did = -1;
 
 	if (dev == NULL)
 		return;
 
 	if (dev->flags & VIRTIO_DEV_RUNNING) {
+		did = dev->vdpa_dev_id;
+		vdpa_dev = rte_vdpa_get_device(did);
+		if (vdpa_dev && vdpa_dev->ops->dev_close)
+			vdpa_dev->ops->dev_close(dev->vid);
 		dev->flags &= ~VIRTIO_DEV_RUNNING;
 		dev->notify_ops->destroy_device(vid);
 	}
@@ -233,6 +324,31 @@ vhost_destroy_device(int vid)
 	vhost_devices[vid] = NULL;
 }
 
+void
+vhost_attach_vdpa_device(int vid, int did)
+{
+	struct virtio_net *dev = get_device(vid);
+
+	if (dev == NULL)
+		return;
+
+	if (rte_vdpa_get_device(did) == NULL)
+		return;
+
+	dev->vdpa_dev_id = did;
+}
+
+void
+vhost_detach_vdpa_device(int vid)
+{
+	struct virtio_net *dev = get_device(vid);
+
+	if (dev == NULL)
+		return;
+
+	dev->vdpa_dev_id = -1;
+}
+
 void
 vhost_set_ifname(int vid, const char *if_name, unsigned int if_len)
 {
@@ -261,6 +377,20 @@ vhost_enable_dequeue_zero_copy(int vid)
 	dev->dequeue_zero_copy = 1;
 }
 
+void
+vhost_set_builtin_virtio_net(int vid, bool enable)
+{
+	struct virtio_net *dev = get_device(vid);
+
+	if (dev == NULL)
+		return;
+
+	if (enable)
+		dev->flags |= VIRTIO_DEV_BUILTIN_VIRTIO_NET;
+	else
+		dev->flags &= ~VIRTIO_DEV_BUILTIN_VIRTIO_NET;
+}
+
 int
 rte_vhost_get_mtu(int vid, uint16_t *mtu)
 {
@@ -272,7 +402,7 @@ rte_vhost_get_mtu(int vid, uint16_t *mtu)
 	if (!(dev->flags & VIRTIO_DEV_READY))
 		return -EAGAIN;
 
-	if (!(dev->features & VIRTIO_NET_F_MTU))
+	if (!(dev->features & (1ULL << VIRTIO_NET_F_MTU)))
 		return -ENOTSUP;
 
 	*mtu = dev->mtu;
@@ -295,7 +425,8 @@ rte_vhost_get_numa_node(int vid)
 			    MPOL_F_NODE | MPOL_F_ADDR);
 	if (ret < 0) {
 		RTE_LOG(ERR, VHOST_CONFIG,
-			"(%d) failed to query numa node: %d\n", vid, ret);
+			"(%d) failed to query numa node: %s\n",
+			vid, rte_strerror(errno));
 		return -1;
 	}
 
@@ -317,6 +448,17 @@ rte_vhost_get_queue_num(int vid)
 	return dev->nr_vring / 2;
 }
 
+uint16_t
+rte_vhost_get_vring_num(int vid)
+{
+	struct virtio_net *dev = get_device(vid);
+
+	if (dev == NULL)
+		return 0;
+
+	return dev->nr_vring;
+}
+
 int
 rte_vhost_get_ifname(int vid, char *buf, size_t len)
 {
@@ -358,7 +500,7 @@ rte_vhost_get_mem_table(int vid, struct rte_vhost_memory **mem)
 		return -1;
 
 	size = dev->mem->nregions * sizeof(struct rte_vhost_mem_region);
-	m = malloc(size);
+	m = malloc(sizeof(struct rte_vhost_memory) + size);
 	if (!m)
 		return -1;
 
@@ -399,6 +541,27 @@ rte_vhost_get_vhost_vring(int vid, uint16_t vring_idx,
 	return 0;
 }
 
+int
+rte_vhost_vring_call(int vid, uint16_t vring_idx)
+{
+	struct virtio_net *dev;
+	struct vhost_virtqueue *vq;
+
+	dev = get_device(vid);
+	if (!dev)
+		return -1;
+
+	if (vring_idx >= VHOST_MAX_VRING)
+		return -1;
+
+	vq = dev->virtqueue[vring_idx];
+	if (!vq)
+		return -1;
+
+	vhost_vring_call(dev, vq);
+	return 0;
+}
+
 uint16_t
 rte_vhost_avail_entries(int vid, uint16_t queue_id)
 {
@@ -421,15 +584,143 @@ rte_vhost_enable_guest_notification(int vid, uint16_t queue_id, int enable)
 {
 	struct virtio_net *dev = get_device(vid);
 
+	if (!dev)
+		return -1;
+
+	if (enable)
+		dev->virtqueue[queue_id]->used->flags &=
+			~VRING_USED_F_NO_NOTIFY;
+	else
+		dev->virtqueue[queue_id]->used->flags |= VRING_USED_F_NO_NOTIFY;
+	return 0;
+}
+
+void
+rte_vhost_log_write(int vid, uint64_t addr, uint64_t len)
+{
+	struct virtio_net *dev = get_device(vid);
+
+	if (dev == NULL)
+		return;
+
+	vhost_log_write(dev, addr, len);
+}
+
+void
+rte_vhost_log_used_vring(int vid, uint16_t vring_idx,
+			 uint64_t offset, uint64_t len)
+{
+	struct virtio_net *dev;
+	struct vhost_virtqueue *vq;
+
+	dev = get_device(vid);
+	if (dev == NULL)
+		return;
+
+	if (vring_idx >= VHOST_MAX_VRING)
+		return;
+	vq = dev->virtqueue[vring_idx];
+	if (!vq)
+		return;
+
+	vhost_log_used_vring(dev, vq, offset, len);
+}
+
+uint32_t
+rte_vhost_rx_queue_count(int vid, uint16_t qid)
+{
+	struct virtio_net *dev;
+	struct vhost_virtqueue *vq;
+
+	dev = get_device(vid);
+	if (dev == NULL)
+		return 0;
+
+	if (unlikely(qid >= dev->nr_vring || (qid & 1) == 0)) {
+		RTE_LOG(ERR, VHOST_DATA, "(%d) %s: invalid virtqueue idx %d.\n",
+			dev->vid, __func__, qid);
+		return 0;
+	}
+
+	vq = dev->virtqueue[qid];
+	if (vq == NULL)
+		return 0;
+
+	if (unlikely(vq->enabled == 0 || vq->avail == NULL))
+		return 0;
+
+	return *((volatile uint16_t *)&vq->avail->idx) - vq->last_avail_idx;
+}
+
+int rte_vhost_get_vdpa_device_id(int vid)
+{
+	struct virtio_net *dev = get_device(vid);
+
 	if (dev == NULL)
 		return -1;
 
-	if (enable) {
-		RTE_LOG(ERR, VHOST_CONFIG,
-			"guest notification isn't supported.\n");
+	return dev->vdpa_dev_id;
+}
+
+int rte_vhost_get_log_base(int vid, uint64_t *log_base,
+		uint64_t *log_size)
+{
+	struct virtio_net *dev = get_device(vid);
+
+	if (!dev)
+		return -1;
+
+	if (unlikely(!(dev->flags & VIRTIO_DEV_BUILTIN_VIRTIO_NET))) {
+		RTE_LOG(ERR, VHOST_DATA,
+			"(%d) %s: built-in vhost net backend is disabled.\n",
+			dev->vid, __func__);
+		return -1;
+	}
+
+	*log_base = dev->log_base;
+	*log_size = dev->log_size;
+
+	return 0;
+}
+
+int rte_vhost_get_vring_base(int vid, uint16_t queue_id,
+		uint16_t *last_avail_idx, uint16_t *last_used_idx)
+{
+	struct virtio_net *dev = get_device(vid);
+
+	if (!dev)
+		return -1;
+
+	if (unlikely(!(dev->flags & VIRTIO_DEV_BUILTIN_VIRTIO_NET))) {
+		RTE_LOG(ERR, VHOST_DATA,
+			"(%d) %s: built-in vhost net backend is disabled.\n",
+			dev->vid, __func__);
+		return -1;
+	}
+
+	*last_avail_idx = dev->virtqueue[queue_id]->last_avail_idx;
+	*last_used_idx = dev->virtqueue[queue_id]->last_used_idx;
+
+	return 0;
+}
+
+int rte_vhost_set_vring_base(int vid, uint16_t queue_id,
+		uint16_t last_avail_idx, uint16_t last_used_idx)
+{
+	struct virtio_net *dev = get_device(vid);
+
+	if (!dev)
+		return -1;
+
+	if (unlikely(!(dev->flags & VIRTIO_DEV_BUILTIN_VIRTIO_NET))) {
+		RTE_LOG(ERR, VHOST_DATA,
+			"(%d) %s: built-in vhost net backend is disabled.\n",
+			dev->vid, __func__);
 		return -1;
 	}
 
-	dev->virtqueue[queue_id]->used->flags = VRING_USED_F_NO_NOTIFY;
+	dev->virtqueue[queue_id]->last_avail_idx = last_avail_idx;
+	dev->virtqueue[queue_id]->last_used_idx = last_used_idx;
+
 	return 0;
 }