[PATCH 2/3] virtio_ring: assume sgs are always well-formed.
We used to have several callers which just used arrays. They're gone, so we can use sg_next() everywhere, simplifying the code. On my laptop, this slowed down vring_bench by 15%: vring_bench before: 936153354-967745359(9.44739e+08+/-6.1e+06)ns vring_bench after: 1061485790-1104800648(1.08254e+09+/-6.6e+06)ns However, a more realistic test using pktgen on a AMD FX(tm)-8320 saw a few percent improvement: pktgen before: 767390-792966(785159+/-6.5e+03)pps 356-367(363.75+/-2.9)Mb/sec (356068960-367936224(3.64314e+08+/-3e+06)bps) errors: 0 pktgen after: 787781-796334(793165+/-2.4e+03)pps 365-369(367.5+/-1.2)Mb/sec (365530384-369498976(3.68028e+08+/-1.1e+06)bps) errors: 0 Signed-off-by: Rusty Russell --- drivers/virtio/virtio_ring.c | 68 +--- 1 file changed, 19 insertions(+), 49 deletions(-) diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index 4d08f45a9c29..374399c62080 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -99,28 +99,10 @@ struct vring_virtqueue #define to_vvq(_vq) container_of(_vq, struct vring_virtqueue, vq) -static inline struct scatterlist *sg_next_chained(struct scatterlist *sg, - unsigned int *count) -{ - return sg_next(sg); -} - -static inline struct scatterlist *sg_next_arr(struct scatterlist *sg, - unsigned int *count) -{ - if (--(*count) == 0) - return NULL; - return sg + 1; -} - /* Set up an indirect table of descriptors and add it to the queue. */ static inline int vring_add_indirect(struct vring_virtqueue *vq, struct scatterlist *sgs[], -struct scatterlist *(*next) - (struct scatterlist *, unsigned int *), unsigned int total_sg, -unsigned int total_out, -unsigned int total_in, unsigned int out_sgs, unsigned int in_sgs, gfp_t gfp) @@ -144,7 +126,7 @@ static inline int vring_add_indirect(struct 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, _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, _in)) { + 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; @@ -186,10 +168,7 @@ static inline int vring_add_indirect(struct vring_virtqueue *vq, static inline int virtqueue_add(struct virtqueue *_vq, struct scatterlist *sgs[], - struct scatterlist *(*next) - (struct scatterlist *, unsigned int *), - unsigned int total_out, - unsigned int total_in, + unsigned int total_sg, unsigned int out_sgs, unsigned int in_sgs, void *data, @@ -197,7 +176,7 @@ static inline int virtqueue_add(struct virtqueue *_vq, { struct vring_virtqueue *vq = to_vvq(_vq); struct scatterlist *sg; - unsigned int i, n, avail, uninitialized_var(prev), total_sg; + unsigned int i, n, avail, uninitialized_var(prev); int head; START_USE(vq); @@ -222,13 +201,10 @@ static inline int virtqueue_add(struct virtqueue *_vq, } #endif - total_sg = total_in + total_out; - /* If the host supports indirect descriptor tables, and we have multiple * buffers, then go indirect. FIXME: tune this threshold */ if (vq->indirect && total_sg > 1 && vq->vq.num_free) { - head = vring_add_indirect(vq, sgs, next, total_sg, total_out, - total_in, + head = vring_add_indirect(vq, sgs, total_sg, out_sgs, in_sgs, gfp); if (likely(head >= 0)) goto add_head; @@ -254,7 +230,7 @@ static inline int virtqueue_add(struct virtqueue *_vq, head = i =
[PATCH 2/3] virtio_ring: assume sgs are always well-formed.
We used to have several callers which just used arrays. They're gone, so we can use sg_next() everywhere, simplifying the code. On my laptop, this slowed down vring_bench by 15%: vring_bench before: 936153354-967745359(9.44739e+08+/-6.1e+06)ns vring_bench after: 1061485790-1104800648(1.08254e+09+/-6.6e+06)ns However, a more realistic test using pktgen on a AMD FX(tm)-8320 saw a few percent improvement: pktgen before: 767390-792966(785159+/-6.5e+03)pps 356-367(363.75+/-2.9)Mb/sec (356068960-367936224(3.64314e+08+/-3e+06)bps) errors: 0 pktgen after: 787781-796334(793165+/-2.4e+03)pps 365-369(367.5+/-1.2)Mb/sec (365530384-369498976(3.68028e+08+/-1.1e+06)bps) errors: 0 Signed-off-by: Rusty Russell ru...@rustcorp.com.au --- drivers/virtio/virtio_ring.c | 68 +--- 1 file changed, 19 insertions(+), 49 deletions(-) diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index 4d08f45a9c29..374399c62080 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -99,28 +99,10 @@ struct vring_virtqueue #define to_vvq(_vq) container_of(_vq, struct vring_virtqueue, vq) -static inline struct scatterlist *sg_next_chained(struct scatterlist *sg, - unsigned int *count) -{ - return sg_next(sg); -} - -static inline struct scatterlist *sg_next_arr(struct scatterlist *sg, - unsigned int *count) -{ - if (--(*count) == 0) - return NULL; - return sg + 1; -} - /* Set up an indirect table of descriptors and add it to the queue. */ static inline int vring_add_indirect(struct vring_virtqueue *vq, struct scatterlist *sgs[], -struct scatterlist *(*next) - (struct scatterlist *, unsigned int *), unsigned int total_sg, -unsigned int total_out, -unsigned int total_in, unsigned int out_sgs, unsigned int in_sgs, gfp_t gfp) @@ -144,7 +126,7 @@ static inline int vring_add_indirect(struct 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 = VRING_DESC_F_NEXT|VRING_DESC_F_WRITE; desc[i].addr = sg_phys(sg); desc[i].len = sg-length; @@ -186,10 +168,7 @@ static inline int vring_add_indirect(struct vring_virtqueue *vq, static inline int virtqueue_add(struct virtqueue *_vq, struct scatterlist *sgs[], - struct scatterlist *(*next) - (struct scatterlist *, unsigned int *), - unsigned int total_out, - unsigned int total_in, + unsigned int total_sg, unsigned int out_sgs, unsigned int in_sgs, void *data, @@ -197,7 +176,7 @@ static inline int virtqueue_add(struct virtqueue *_vq, { struct vring_virtqueue *vq = to_vvq(_vq); struct scatterlist *sg; - unsigned int i, n, avail, uninitialized_var(prev), total_sg; + unsigned int i, n, avail, uninitialized_var(prev); int head; START_USE(vq); @@ -222,13 +201,10 @@ static inline int virtqueue_add(struct virtqueue *_vq, } #endif - total_sg = total_in + total_out; - /* If the host supports indirect descriptor tables, and we have multiple * buffers, then go indirect. FIXME: tune this threshold */ if (vq-indirect total_sg 1 vq-vq.num_free) { - head = vring_add_indirect(vq, sgs, next, total_sg, total_out, - total_in, + head = vring_add_indirect(vq, sgs, total_sg, out_sgs, in_sgs, gfp); if (likely(head = 0)) goto add_head; @@ -254,7 +230,7 @@ static inline int virtqueue_add(struct virtqueue *_vq,