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 <rusty@rustcorp.com.au> Signed-off-by: David S. Miller <davem@davemloft.net>
This commit is contained in:
Rusty Russell
David S. Miller
parent
a58354409a
commit
eeebf9b1fc
|
|
@ -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,
|
|||
|
||||
head = i = vq->free_head;
|
||||
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)) {
|
||||
vq->vring.desc[i].flags = VRING_DESC_F_NEXT;
|
||||
vq->vring.desc[i].addr = sg_phys(sg);
|
||||
vq->vring.desc[i].len = sg->length;
|
||||
|
|
@ -263,7 +239,7 @@ static inline int virtqueue_add(struct 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)) {
|
||||
vq->vring.desc[i].flags = VRING_DESC_F_NEXT|VRING_DESC_F_WRITE;
|
||||
vq->vring.desc[i].addr = sg_phys(sg);
|
||||
vq->vring.desc[i].len = sg->length;
|
||||
|
|
@ -324,29 +300,23 @@ int virtqueue_add_sgs(struct virtqueue *_vq,
|
|||
void *data,
|
||||
gfp_t gfp)
|
||||
{
|
||||
unsigned int i, total_out, total_in;
|
||||
unsigned int i, total_sg = 0;
|
||||
|
||||
/* Count them first. */
|
||||
for (i = total_out = total_in = 0; i < out_sgs; i++) {
|
||||
for (i = 0; i < out_sgs + in_sgs; i++) {
|
||||
struct scatterlist *sg;
|
||||
for (sg = sgs[i]; sg; sg = sg_next(sg))
|
||||
total_out++;
|
||||
total_sg++;
|
||||
}
|
||||
for (; i < out_sgs + in_sgs; i++) {
|
||||
struct scatterlist *sg;
|
||||
for (sg = sgs[i]; sg; sg = sg_next(sg))
|
||||
total_in++;
|
||||
}
|
||||
return virtqueue_add(_vq, sgs, sg_next_chained,
|
||||
total_out, total_in, out_sgs, in_sgs, data, gfp);
|
||||
return virtqueue_add(_vq, sgs, total_sg, out_sgs, in_sgs, data, gfp);
|
||||
}
|
||||
EXPORT_SYMBOL_GPL(virtqueue_add_sgs);
|
||||
|
||||
/**
|
||||
* virtqueue_add_outbuf - expose output buffers to other end
|
||||
* @vq: the struct virtqueue we're talking about.
|
||||
* @sgs: array of scatterlists (need not be terminated!)
|
||||
* @num: the number of scatterlists readable by other side
|
||||
* @sg: scatterlist (must be well-formed and terminated!)
|
||||
* @num: the number of entries in @sg readable by other side
|
||||
* @data: the token identifying the buffer.
|
||||
* @gfp: how to do memory allocations (if necessary).
|
||||
*
|
||||
|
|
@ -356,19 +326,19 @@ EXPORT_SYMBOL_GPL(virtqueue_add_sgs);
|
|||
* Returns zero or a negative error (ie. ENOSPC, ENOMEM, EIO).
|
||||
*/
|
||||
int virtqueue_add_outbuf(struct virtqueue *vq,
|
||||
struct scatterlist sg[], unsigned int num,
|
||||
struct scatterlist *sg, unsigned int num,
|
||||
void *data,
|
||||
gfp_t gfp)
|
||||
{
|
||||
return virtqueue_add(vq, &sg, sg_next_arr, num, 0, 1, 0, data, gfp);
|
||||
return virtqueue_add(vq, &sg, num, 1, 0, data, gfp);
|
||||
}
|
||||
EXPORT_SYMBOL_GPL(virtqueue_add_outbuf);
|
||||
|
||||
/**
|
||||
* virtqueue_add_inbuf - expose input buffers to other end
|
||||
* @vq: the struct virtqueue we're talking about.
|
||||
* @sgs: array of scatterlists (need not be terminated!)
|
||||
* @num: the number of scatterlists writable by other side
|
||||
* @sg: scatterlist (must be well-formed and terminated!)
|
||||
* @num: the number of entries in @sg writable by other side
|
||||
* @data: the token identifying the buffer.
|
||||
* @gfp: how to do memory allocations (if necessary).
|
||||
*
|
||||
|
|
@ -378,11 +348,11 @@ EXPORT_SYMBOL_GPL(virtqueue_add_outbuf);
|
|||
* Returns zero or a negative error (ie. ENOSPC, ENOMEM, EIO).
|
||||
*/
|
||||
int virtqueue_add_inbuf(struct virtqueue *vq,
|
||||
struct scatterlist sg[], unsigned int num,
|
||||
struct scatterlist *sg, unsigned int num,
|
||||
void *data,
|
||||
gfp_t gfp)
|
||||
{
|
||||
return virtqueue_add(vq, &sg, sg_next_arr, 0, num, 0, 1, data, gfp);
|
||||
return virtqueue_add(vq, &sg, num, 0, 1, data, gfp);
|
||||
}
|
||||
EXPORT_SYMBOL_GPL(virtqueue_add_inbuf);
|
||||
|
||||
|
|
|
|||
Loading…
Reference in New Issue