search for: sg_phys

...@@ -145,42 +145,54 @@ static inline int vring_add_indirect(struct vring_virtqueue *vq, > > i = 0; > > for (n = 0; n < out_sgs; n++) { > > for (sg = sgs[n]; sg; sg = next(sg, &total_out)) { > > - desc[i].flags = VRING_DESC_F_NEXT; > > - desc[i].addr = sg_phys(sg); > > - desc[i].len = sg->length; > > - desc[i].next = i+1; > > + desc[i].flags = cpu_to_virtio16(vq->vq.vdev, > > + VRING_DESC_F_NEXT); > > + desc[i].addr = cpu_to_virtio64(vq->vq.vdev, > > + sg_phys(sg)); > > + desc[i]...

...@@ -145,42 +145,54 @@ static inline int vring_add_indirect(struct vring_virtqueue *vq, > > i = 0; > > for (n = 0; n < out_sgs; n++) { > > for (sg = sgs[n]; sg; sg = next(sg, &total_out)) { > > - desc[i].flags = VRING_DESC_F_NEXT; > > - desc[i].addr = sg_phys(sg); > > - desc[i].len = sg->length; > > - desc[i].next = i+1; > > + desc[i].flags = cpu_to_virtio16(vq->vq.vdev, > > + VRING_DESC_F_NEXT); > > + desc[i].addr = cpu_to_virtio64(vq->vq.vdev, > > + sg_phys(sg)); > > + desc[i]...

...o/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -145,42 +145,54 @@ static inline int vring_add_indirect(struct vring_virtqueue *vq, i = 0; for (n = 0; n < out_sgs; n++) { for (sg = sgs[n]; sg; sg = next(sg, &total_out)) { - desc[i].flags = VRING_DESC_F_NEXT; - desc[i].addr = sg_phys(sg); - desc[i].len = sg->length; - desc[i].next = i+1; + desc[i].flags = cpu_to_virtio_u16(vq->vq.vdev, + VRING_DESC_F_NEXT); + desc[i].addr = cpu_to_virtio_u64(vq->vq.vdev, + sg_phys(sg)); + desc[i].len = cpu_to_virtio_u32(vq->vq.vdev, + sg->length); +...

...o/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -145,42 +145,54 @@ static inline int vring_add_indirect(struct vring_virtqueue *vq, i = 0; for (n = 0; n < out_sgs; n++) { for (sg = sgs[n]; sg; sg = next(sg, &total_out)) { - desc[i].flags = VRING_DESC_F_NEXT; - desc[i].addr = sg_phys(sg); - desc[i].len = sg->length; - desc[i].next = i+1; + desc[i].flags = cpu_to_virtio_u16(vq->vq.vdev, + VRING_DESC_F_NEXT); + desc[i].addr = cpu_to_virtio_u64(vq->vq.vdev, + sg_phys(sg)); + desc[i].len = cpu_to_virtio_u32(vq->vq.vdev, + sg->length); +...

...malloc(total_sg * sizeof(struct vring_desc), gfp); - if (!desc) - return -ENOMEM; - - /* Transfer entries from the sg lists into the indirect page */ - i = 0; - for (n = 0; n < out_sgs; n++) { - for (sg = sgs[n]; sg; sg = sg_next(sg)) { - desc[i].flags = VRING_DESC_F_NEXT; - desc[i].addr = sg_phys(sg); - desc[i].len = sg->length; - desc[i].next = i+1; - i++; - } - } - for (; n < (out_sgs + in_sgs); n++) { - for (sg = sgs[n]; sg; sg = sg_next(sg)) { - desc[i].flags = VRING_DESC_F_NEXT|VRING_DESC_F_WRITE; - desc[i].addr = sg_phys(sg); - desc[i].len = sg->length; - desc...

...virtio/virtio_ring.c > @@ -145,42 +145,54 @@ static inline int vring_add_indirect(struct vring_virtqueue *vq, > i = 0; > for (n = 0; n < out_sgs; n++) { > for (sg = sgs[n]; sg; sg = next(sg, &total_out)) { > - desc[i].flags = VRING_DESC_F_NEXT; > - desc[i].addr = sg_phys(sg); > - desc[i].len = sg->length; > - desc[i].next = i+1; > + desc[i].flags = cpu_to_virtio16(vq->vq.vdev, > + VRING_DESC_F_NEXT); > + desc[i].addr = cpu_to_virtio64(vq->vq.vdev, > + sg_phys(sg)); > + desc[i].len = cpu_to_virtio32(vq->vq.vd...

I resurrected these patches after prompting from Andy Lutomirski's recent patches. I put them on the back-burner because vring_bench had a 15% slowdown on my laptop: pktgen testing revealed a speedup, if anything, so I've cleaned them up. Rusty Russell (3): virtio_net: pass well-formed sgs to virtqueue_add_*() virtio_ring: assume sgs are always well-formed. virtio_ring: unify

I resurrected these patches after prompting from Andy Lutomirski's recent patches. I put them on the back-burner because vring_bench had a 15% slowdown on my laptop: pktgen testing revealed a speedup, if anything, so I've cleaned them up. Rusty Russell (3): virtio_net: pass well-formed sgs to virtqueue_add_*() virtio_ring: assume sgs are always well-formed. virtio_ring: unify

OK, so I've spent a few days benchmarking. Turns out 80% of virtio_add_buf cases are uni-directional (including the always-performance-sensitive networking code), and that gets no performance penalty (though tests with real networking would be appreciated!). I'm not reposting all the "convert driver to virtio_add_outbuf()" patches: just the scsi one which I didn't have

OK, so I've spent a few days benchmarking. Turns out 80% of virtio_add_buf cases are uni-directional (including the always-performance-sensitive networking code), and that gets no performance penalty (though tests with real networking would be appreciated!). I'm not reposting all the "convert driver to virtio_add_outbuf()" patches: just the scsi one which I didn't have

...of(struct vring_desc)); @@ -206,7 +207,7 @@ static inline int virtqueue_add(struct virtqueue *_vq, for (n = 0; n < out_sgs; n++) { for (sg = sgs[n]; sg; sg = sg_next(sg)) { desc[i].flags = cpu_to_virtio16(_vq->vdev, VRING_DESC_F_NEXT); - desc[i].addr = cpu_to_virtio64(_vq->vdev, sg_phys(sg)); + desc[i].addr = cpu_to_virtio_addr(_vq->vdev, sg_phys(sg)); desc[i].len = cpu_to_virtio32(_vq->vdev, sg->length); prev = i; i = virtio16_to_cpu(_vq->vdev, desc[i].next); @@ -215,7 +216,7 @@ static inline int virtqueue_add(struct virtqueue *_vq, for (; n < (out_...

...vq, /* Transfer entries from the sg lists into the indirect page */ i = 0; for (n = 0; n < out_sgs; n++) { - for (sg = sgs[n]; sg; sg = next(sg, &total_out)) { + for_each_sg(sgs[n], sg, total_out, j) { + if (!sg) + break; desc[i].flags = VRING_DESC_F_NEXT; desc[i].addr = sg_phys(sg); desc[i].len = sg->length; @@ -153,7 +139,9 @@ static inline int vring_add_indirect(struct vring_virtqueue *vq, } } for (; n < (out_sgs + in_sgs); n++) { - for (sg = sgs[n]; sg; sg = next(sg, &total_in)) { + for_each_sg(sgs[n], sg, total_in, j) { + if (!sg) + break;...

This fixes virtio on Xen guests as well as on any other platform on which physical addresses don't match bus addresses. This can be tested with: virtme-run --xen xen --kimg arch/x86/boot/bzImage --console using virtme from here: https://git.kernel.org/cgit/utils/kernel/virtme/virtme.git Without these patches, the guest hangs forever. With these patches, everything works. There

This fixes virtio on Xen guests as well as on any other platform on which physical addresses don't match bus addresses. This can be tested with: virtme-run --xen xen --kimg arch/x86/boot/bzImage --console using virtme from here: https://git.kernel.org/cgit/utils/kernel/virtme/virtme.git Without these patches, the guest hangs forever. With these patches, everything works. There

...truct vring_virtqueue *vq, /* Transfer entries from the sg lists into the indirect page */ i = 0; for (n = 0; n < out_sgs; n++) { - for (sg = sgs[n]; sg; sg = next(sg, &total_out)) { + for (sg = sgs[n]; sg; sg = sg_next(sg)) { desc[i].flags = VRING_DESC_F_NEXT; desc[i].addr = sg_phys(sg); desc[i].len = sg->length; @@ -153,7 +135,7 @@ static inline int vring_add_indirect(struct vring_virtqueue *vq, } } for (; n < (out_sgs + in_sgs); n++) { - for (sg = sgs[n]; sg; sg = next(sg, &total_in)) { + for (sg = sgs[n]; sg; sg = sg_next(sg)) { desc[i].flags = VR...

...remoteproc on the ZynqMP (arm64) but I'm hitting a DMA/mm error. The issue was discussed here: http://lists.infradead.org/pipermail/linux-arm-kernel/2015-March/333050.html Russel King pointed out that the arm64 is not doing anything wrong by returning vmapped memory (which is incompatible with sg_phys()). Hence this RFC series that tries to illustrate/fix the problem in rpmsg/virtio. Is this going in the right direction? Any ideas or suggestions on how to better fix this? Something that worries me a little is that it would be nice if the DMA capability for virtio protocols was not hardcoded li...

...remoteproc on the ZynqMP (arm64) but I'm hitting a DMA/mm error. The issue was discussed here: http://lists.infradead.org/pipermail/linux-arm-kernel/2015-March/333050.html Russel King pointed out that the arm64 is not doing anything wrong by returning vmapped memory (which is incompatible with sg_phys()). Hence this RFC series that tries to illustrate/fix the problem in rpmsg/virtio. Is this going in the right direction? Any ideas or suggestions on how to better fix this? Something that worries me a little is that it would be nice if the DMA capability for virtio protocols was not hardcoded li...

...irection, static dma_addr_t *addr) { if (!vq->use_dma_api) { /* @@ -366,7 +365,8 @@ static dma_addr_t vring_map_one_sg(const struct vring_virtqueue *vq, * depending on the direction. */ kmsan_handle_dma(sg_page(sg), sg->offset, sg->length, direction); - return (dma_addr_t)sg_phys(sg); + *addr = (dma_addr_t)sg_phys(sg); + return 0; } /* @@ -374,9 +374,14 @@ static dma_addr_t vring_map_one_sg(const struct vring_virtqueue *vq, * the way it expects (we don't guarantee that the scatterlist * will exist for the lifetime of the mapping). */ - return dma_map_pa...

...tatic inline int vring_add_indirect(struct vring_virtqueue *vq, > struct scatterlist *sgs[], > @@ -132,7 +172,11 @@ static inline int vring_add_indirect(struct vring_virtqueue *vq, > if (!sg) > break; > desc[i].flags = VRING_DESC_F_NEXT; > - desc[i].addr = sg_phys(sg); > + desc[i].addr = > + dma_map_one_sg(vq, sg, DMA_TO_DEVICE); > + if (dma_mapping_error(vq->vq.vdev->dev.parent, > + desc[i].addr)) > + goto unmap_free; > desc[i].len = sg->length; > desc[i].next = i+1; > i++; > @@ -143,7 +187...

...tatic inline int vring_add_indirect(struct vring_virtqueue *vq, > struct scatterlist *sgs[], > @@ -132,7 +172,11 @@ static inline int vring_add_indirect(struct vring_virtqueue *vq, > if (!sg) > break; > desc[i].flags = VRING_DESC_F_NEXT; > - desc[i].addr = sg_phys(sg); > + desc[i].addr = > + dma_map_one_sg(vq, sg, DMA_TO_DEVICE); > + if (dma_mapping_error(vq->vq.vdev->dev.parent, > + desc[i].addr)) > + goto unmap_free; > desc[i].len = sg->length; > desc[i].next = i+1; > i++; > @@ -143,7 +187...