netdev - [PATCH vhost v7 04/11] virtio_ring: split: support premapped

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20230425073613.8839-5-xuanzhuo@linux.alibaba.com>
Date:   Tue, 25 Apr 2023 15:36:06 +0800
From:   Xuan Zhuo <xuanzhuo@...ux.alibaba.com>
To:     virtualization@...ts.linux-foundation.org
Cc:     "Michael S. Tsirkin" <mst@...hat.com>,
        Jason Wang <jasowang@...hat.com>,
        Xuan Zhuo <xuanzhuo@...ux.alibaba.com>,
        Alexei Starovoitov <ast@...nel.org>,
        Daniel Borkmann <daniel@...earbox.net>,
        "David S. Miller" <davem@...emloft.net>,
        Jesper Dangaard Brouer <hawk@...nel.org>,
        John Fastabend <john.fastabend@...il.com>,
        netdev@...r.kernel.org, bpf@...r.kernel.org,
        Christoph Hellwig <hch@...radead.org>,
        Jakub Kicinski <kuba@...nel.org>,
        Alexander Lobakin <aleksander.lobakin@...el.com>
Subject: [PATCH vhost v7 04/11] virtio_ring: split: support premapped

virtio core only supports virtual addresses, dma is completed in virtio
core.

In some scenarios (such as the AF_XDP), the memory is allocated
and DMA mapping is completed in advance, so it is necessary for us to
support passing the DMA address to virtio core.

Drives can use sg->dma_address to pass the mapped dma address to virtio
core. If one sg->dma_address is used then all sgs must use
sg->dma_address, otherwise all must be null when passing it to the APIs
of virtio.

Signed-off-by: Xuan Zhuo <xuanzhuo@...ux.alibaba.com>
---
 drivers/virtio/virtio_ring.c | 31 +++++++++++++++++++++++--------
 1 file changed, 23 insertions(+), 8 deletions(-)

diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index 62db16a15ae7..055c1c069fff 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -67,9 +67,13 @@
 #define LAST_ADD_TIME_INVALID(vq)
 #endif
 
+#define VRING_STATE_F_MAP_INTERNAL BIT(0)
+
 struct vring_desc_state_split {
 	void *data;			/* Data for callback. */
 	struct vring_desc *indir_desc;	/* Indirect descriptor, if any. */
+	u32 flags;			/* State flags. */
+	u32 padding;
 };
 
 struct vring_desc_state_packed {
@@ -448,7 +452,7 @@ static void vring_unmap_one_split_indirect(const struct vring_virtqueue *vq,
 }
 
 static unsigned int vring_unmap_one_split(const struct vring_virtqueue *vq,
-					  unsigned int i)
+					  unsigned int i, bool dma_map_internal)
 {
 	struct vring_desc_extra *extra = vq->split.desc_extra;
 	u16 flags;
@@ -465,6 +469,9 @@ static unsigned int vring_unmap_one_split(const struct vring_virtqueue *vq,
 				 (flags & VRING_DESC_F_WRITE) ?
 				 DMA_FROM_DEVICE : DMA_TO_DEVICE);
 	} else {
+		if (!dma_map_internal)
+			goto out;
+
 		dma_unmap_page(vring_dma_dev(vq),
 			       extra[i].addr,
 			       extra[i].len,
@@ -615,7 +622,7 @@ static inline int virtqueue_add_split(struct virtqueue *_vq,
 	struct scatterlist *sg;
 	struct vring_desc *desc;
 	unsigned int i, n, avail, descs_used, prev;
-	bool indirect;
+	bool indirect, dma_map_internal;
 	int head;
 
 	START_USE(vq);
@@ -668,7 +675,8 @@ static inline int virtqueue_add_split(struct virtqueue *_vq,
 		return -ENOSPC;
 	}
 
-	if (virtqueue_map_sgs(vq, sgs, total_sg, out_sgs, in_sgs))
+	dma_map_internal = !sgs[0]->dma_address;
+	if (dma_map_internal && virtqueue_map_sgs(vq, sgs, total_sg, out_sgs, in_sgs))
 		goto err_map;
 
 	for (n = 0; n < out_sgs; n++) {
@@ -735,6 +743,8 @@ static inline int virtqueue_add_split(struct virtqueue *_vq,
 	else
 		vq->split.desc_state[head].indir_desc = ctx;
 
+	vq->split.desc_state[head].flags = dma_map_internal ? VRING_STATE_F_MAP_INTERNAL : 0;
+
 	/* Put entry in available array (but don't update avail->idx until they
 	 * do sync). */
 	avail = vq->split.avail_idx_shadow & (vq->split.vring.num - 1);
@@ -759,7 +769,8 @@ static inline int virtqueue_add_split(struct virtqueue *_vq,
 	return 0;
 
 unmap_release:
-	virtqueue_unmap_sgs(vq, sgs, total_sg, out_sgs, in_sgs);
+	if (dma_map_internal)
+		virtqueue_unmap_sgs(vq, sgs, total_sg, out_sgs, in_sgs);
 
 err_map:
 	if (indirect)
@@ -805,20 +816,22 @@ static void detach_buf_split(struct vring_virtqueue *vq, unsigned int head,
 {
 	unsigned int i, j;
 	__virtio16 nextflag = cpu_to_virtio16(vq->vq.vdev, VRING_DESC_F_NEXT);
+	bool dma_map_internal;
 
 	/* Clear data ptr. */
 	vq->split.desc_state[head].data = NULL;
+	dma_map_internal = !!(vq->split.desc_state[head].flags & VRING_STATE_F_MAP_INTERNAL);
 
 	/* Put back on free list: unmap first-level descriptors and find end */
 	i = head;
 
 	while (vq->split.vring.desc[i].flags & nextflag) {
-		vring_unmap_one_split(vq, i);
+		vring_unmap_one_split(vq, i, dma_map_internal);
 		i = vq->split.desc_extra[i].next;
 		vq->vq.num_free++;
 	}
 
-	vring_unmap_one_split(vq, i);
+	vring_unmap_one_split(vq, i, dma_map_internal);
 	vq->split.desc_extra[i].next = vq->free_head;
 	vq->free_head = head;
 
@@ -840,8 +853,10 @@ static void detach_buf_split(struct vring_virtqueue *vq, unsigned int head,
 				VRING_DESC_F_INDIRECT));
 		BUG_ON(len == 0 || len % sizeof(struct vring_desc));
 
-		for (j = 0; j < len / sizeof(struct vring_desc); j++)
-			vring_unmap_one_split_indirect(vq, &indir_desc[j]);
+		if (dma_map_internal) {
+			for (j = 0; j < len / sizeof(struct vring_desc); j++)
+				vring_unmap_one_split_indirect(vq, &indir_desc[j]);
+		}
 
 		kfree(indir_desc);
 		vq->split.desc_state[head].indir_desc = NULL;
-- 
2.32.0.3.g01195cf9f