Displaying 20 results from an estimated 27 matches for "avail_used_flags".
2023 Mar 22
1
[PATCH vhost v4 02/11] virtio_ring: packed: separate dma codes
...tic inline int virtqueue_add_packed(struct virtqueue *_vq,
struct vring_virtqueue *vq = to_vvq(_vq);
struct vring_packed_desc *desc;
struct scatterlist *sg;
- unsigned int i, n, c, descs_used, err_idx;
+ unsigned int i, n, c, descs_used;
__le16 head_flags, flags;
- u16 head, id, prev, curr, avail_used_flags;
+ u16 head, id, prev, curr;
int err;
START_USE(vq);
@@ -1461,7 +1461,6 @@ static inline int virtqueue_add_packed(struct virtqueue *_vq,
}
head = vq->packed.next_avail_idx;
- avail_used_flags = vq->packed.avail_used_flags;
WARN_ON_ONCE(total_sg > vq->packed.vring.num &am...
2023 Mar 02
1
[PATCH vhost v1 06/12] virtio_ring: packed: separate DMA codes
...q,
@@ -1498,15 +1483,14 @@ static inline int virtqueue_add_vring_packed(struct vring_virtqueue *vq,
{
struct vring_packed_desc *desc;
struct scatterlist *sg;
- unsigned int i, n, c, descs_used, err_idx;
+ unsigned int i, n, c, descs_used;
__le16 head_flags, flags;
- u16 head, id, prev, curr, avail_used_flags;
+ u16 head, id, prev, curr;
desc = vq->packed.vring.desc;
head = vq->packed.next_avail_idx;
i = head;
descs_used = total_sg;
- avail_used_flags = vq->packed.avail_used_flags;
id = vq->free_head;
BUG_ON(id == vq->packed.vring.num);
@@ -1515,11 +1499,6 @@ static inline...
2018 Dec 07
0
[RFC 3/3] virtio_ring: use new vring flags
...+1038,9 @@ static int virtqueue_add_indirect_packed(struct vring_virtqueue *vq,
vq->packed.desc_extra[id].addr = addr;
vq->packed.desc_extra[id].len = total_sg *
sizeof(struct vring_packed_desc);
- vq->packed.desc_extra[id].flags = VRING_DESC_F_INDIRECT |
- vq->packed.avail_used_flags;
+ vq->packed.desc_extra[id].flags =
+ BIT(VRING_PACKED_DESC_F_INDIRECT) |
+ vq->packed.avail_used_flags;
}
/*
@@ -1035,8 +1049,9 @@ static int virtqueue_add_indirect_packed(struct vring_virtqueue *vq,
* the list are made available.
*/
virtio_wmb(vq->weak_barriers);
-...
2018 Dec 07
7
[RFC 0/3] virtio_ring: define flags as shifts consistently
This is a follow up of the discussion in this thread:
https://patchwork.ozlabs.org/patch/1001015/#2042353
Tiwei Bie (3):
virtio_ring: define flags as shifts consistently
virtio_ring: add VIRTIO_RING_NO_LEGACY
virtio_ring: use new vring flags
drivers/virtio/virtio_ring.c | 100 ++++++++++++++++++-------------
include/uapi/linux/virtio_ring.h | 61 +++++++++++++------
2 files changed,
2018 Dec 07
7
[RFC 0/3] virtio_ring: define flags as shifts consistently
This is a follow up of the discussion in this thread:
https://patchwork.ozlabs.org/patch/1001015/#2042353
Tiwei Bie (3):
virtio_ring: define flags as shifts consistently
virtio_ring: add VIRTIO_RING_NO_LEGACY
virtio_ring: use new vring flags
drivers/virtio/virtio_ring.c | 100 ++++++++++++++++++-------------
include/uapi/linux/virtio_ring.h | 61 +++++++++++++------
2 files changed,
2023 Mar 02
12
[PATCH vhost v1 00/12] virtio core prepares for AF_XDP
XDP socket(AF_XDP) is an excellent bypass kernel network framework. The zero
copy feature of xsk (XDP socket) needs to be supported by the driver. The
performance of zero copy is very good.
ENV: Qemu with vhost.
vhost cpu | Guest APP CPU |Guest Softirq CPU | PPS
-----------------------------|---------------|------------------|------------
xmit by sockperf: 90% | 100%
2023 Mar 21
11
[PATCH vhost v3 00/11] virtio core prepares for AF_XDP
XDP socket(AF_XDP) is an excellent bypass kernel network framework. The zero
copy feature of xsk (XDP socket) needs to be supported by the driver. The
performance of zero copy is very good.
ENV: Qemu with vhost.
vhost cpu | Guest APP CPU |Guest Softirq CPU | PPS
-----------------------------|---------------|------------------|------------
xmit by sockperf: 90% | 100%
2023 Mar 22
11
[PATCH vhost v4 00/11] virtio core prepares for AF_XDP
XDP socket(AF_XDP) is an excellent bypass kernel network framework. The zero
copy feature of xsk (XDP socket) needs to be supported by the driver. The
performance of zero copy is very good.
ENV: Qemu with vhost.
vhost cpu | Guest APP CPU |Guest Softirq CPU | PPS
-----------------------------|---------------|------------------|------------
xmit by sockperf: 90% | 100%
2023 Mar 24
11
[PATCH vhost v5 00/11] virtio core prepares for AF_XDP
XDP socket(AF_XDP) is an excellent bypass kernel network framework. The zero
copy feature of xsk (XDP socket) needs to be supported by the driver. The
performance of zero copy is very good.
ENV: Qemu with vhost.
vhost cpu | Guest APP CPU |Guest Softirq CPU | PPS
-----------------------------|---------------|------------------|------------
xmit by sockperf: 90% | 100%
2023 Mar 27
11
[PATCH vhost v6 00/11] virtio core prepares for AF_XDP
XDP socket(AF_XDP) is an excellent bypass kernel network framework. The zero
copy feature of xsk (XDP socket) needs to be supported by the driver. The
performance of zero copy is very good.
ENV: Qemu with vhost.
vhost cpu | Guest APP CPU |Guest Softirq CPU | PPS
-----------------------------|---------------|------------------|------------
xmit by sockperf: 90% | 100%
2023 May 17
12
[PATCH vhost v9 00/12] virtio core prepares for AF_XDP
## About DMA APIs
Now, virtio may can not work with DMA APIs when virtio features do not have
VIRTIO_F_ACCESS_PLATFORM.
1. I tried to let DMA APIs return phy address by virtio-device. But DMA APIs just
work with the "real" devices.
2. I tried to let xsk support callballs to get phy address from virtio-net
driver as the dma address. But the maintainers of xsk may want to use
2023 May 09
12
[PATCH vhost v8 00/12] virtio core prepares for AF_XDP
## About DMA APIs
Now, virtio may can not work with DMA APIs when virtio features do not have
VIRTIO_F_ACCESS_PLATFORM.
1. I tried to let DMA APIs return phy address by virtio-device. But DMA APIs just
work with the "real" devices.
2. I tried to let xsk support callballs to get phy address from virtio-net
driver as the dma address. But the maintainers of xsk may want to use
2023 May 17
2
[PATCH vhost v9 01/12] virtio_ring: put mapping error check in vring_map_one_sg
...g(vq, sg, n < out_sgs ?
- DMA_TO_DEVICE : DMA_FROM_DEVICE);
- if (vring_mapping_error(vq, addr))
+ dma_addr_t addr;
+
+ if (vring_map_one_sg(vq, sg, n < out_sgs ?
+ DMA_TO_DEVICE : DMA_FROM_DEVICE, &addr))
goto unmap_release;
flags = cpu_to_le16(vq->packed.avail_used_flags |
--
2.32.0.3.g01195cf9f
2023 Apr 25
12
[PATCH vhost v7 00/11] virtio core prepares for AF_XDP
## About DMA APIs
Now, virtio may can not work with DMA APIs when virtio features do not have
VIRTIO_F_ACCESS_PLATFORM.
1. I tried to let DMA APIs return phy address by virtio-device. But DMA APIs just
work with the "real" devices.
2. I tried to let xsk support callballs to get phy address from virtio-net
driver as the dma address. But the maintainers of xsk may want to use
2023 Feb 14
11
[PATCH vhost 00/10] virtio core prepares for AF_XDP
XDP socket(AF_XDP) is an excellent bypass kernel network framework. The zero
copy feature of xsk (XDP socket) needs to be supported by the driver. The
performance of zero copy is very good.
ENV: Qemu with vhost.
vhost cpu | Guest APP CPU |Guest Softirq CPU | PPS
-----------------------------|---------------|------------------|------------
xmit by sockperf: 90% | 100%
2023 Jun 02
12
[PATCH vhost v10 00/10] virtio core prepares for AF_XDP
## About DMA APIs
Now, virtio may can not work with DMA APIs when virtio features do not have
VIRTIO_F_ACCESS_PLATFORM.
1. I tried to let DMA APIs return phy address by virtio-device. But DMA APIs just
work with the "real" devices.
2. I tried to let xsk support callballs to get phy address from virtio-net
driver as the dma address. But the maintainers of xsk may want to use
2023 Jun 02
12
[PATCH vhost v10 00/10] virtio core prepares for AF_XDP
## About DMA APIs
Now, virtio may can not work with DMA APIs when virtio features do not have
VIRTIO_F_ACCESS_PLATFORM.
1. I tried to let DMA APIs return phy address by virtio-device. But DMA APIs just
work with the "real" devices.
2. I tried to let xsk support callballs to get phy address from virtio-net
driver as the dma address. But the maintainers of xsk may want to use
2023 May 26
1
[PATCH] virtio_ring: validate used buffer length
...+ if (vq->packed.buflen)
+ vq->packed.buflen[id] = buflen;
+
vq->num_added += 1;
pr_debug("Added buffer head %i to %p\n", head, vq);
@@ -1416,6 +1470,7 @@ static inline int virtqueue_add_packed(struct virtqueue *_vq,
__le16 head_flags, flags;
u16 head, id, prev, curr, avail_used_flags;
int err;
+ u32 buflen = 0;
START_USE(vq);
@@ -1498,6 +1553,8 @@ static inline int virtqueue_add_packed(struct virtqueue *_vq,
1 << VRING_PACKED_DESC_F_AVAIL |
1 << VRING_PACKED_DESC_F_USED;
}
+ if (n >= out_sgs)
+ buflen += sg->length;
}
}
@@ -...
2018 Nov 21
19
[PATCH net-next v3 00/13] virtio: support packed ring
Hi,
This patch set implements packed ring support in virtio driver.
A performance test between pktgen (pktgen_sample03_burst_single_flow.sh)
and DPDK vhost (testpmd/rxonly/vhost-PMD) has been done, I saw
~30% performance gain in packed ring in this case.
To make this patch set work with below patch set for vhost,
some hacks are needed to set the _F_NEXT flag in indirect
descriptors (this should
2018 Nov 21
19
[PATCH net-next v3 00/13] virtio: support packed ring
Hi,
This patch set implements packed ring support in virtio driver.
A performance test between pktgen (pktgen_sample03_burst_single_flow.sh)
and DPDK vhost (testpmd/rxonly/vhost-PMD) has been done, I saw
~30% performance gain in packed ring in this case.
To make this patch set work with below patch set for vhost,
some hacks are needed to set the _F_NEXT flag in indirect
descriptors (this should