Sometimes we need to coalesce the rx frags to avoid frag list. One example is
virtio-net driver which tries to use small frags for both MTU sized packet and
GSO packet. So this patch introduce skb_coalesce_rx_frag() to do this.
Cc: Rusty Russell <[email protected]>
Cc: Michael S. Tsirkin <[email protected]>
Cc: Michael Dalton <[email protected]>
Cc: Eric Dumazet <[email protected]>
Signed-off-by: Jason Wang <[email protected]>
---
include/linux/skbuff.h | 3 +++
net/core/skbuff.c | 13 +++++++++++++
2 files changed, 16 insertions(+)
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 2c15497..e34652b 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1372,6 +1372,9 @@ static inline void skb_fill_page_desc(struct sk_buff *skb, int i,
void skb_add_rx_frag(struct sk_buff *skb, int i, struct page *page, int off,
int size, unsigned int truesize);
+void skb_coalesce_rx_frag(struct sk_buff *skb, int i, int off, int size,
+ unsigned int truesize);
+
#define SKB_PAGE_ASSERT(skb) BUG_ON(skb_shinfo(skb)->nr_frags)
#define SKB_FRAG_ASSERT(skb) BUG_ON(skb_has_frag_list(skb))
#define SKB_LINEAR_ASSERT(skb) BUG_ON(skb_is_nonlinear(skb))
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 0ab32fa..fdef994 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -476,6 +476,19 @@ void skb_add_rx_frag(struct sk_buff *skb, int i, struct page *page, int off,
}
EXPORT_SYMBOL(skb_add_rx_frag);
+void skb_coalesce_rx_frag(struct sk_buff *skb, int i, int off, int size,
+ unsigned int truesize)
+{
+ skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+
+ skb_frag_size_add(frag, size);
+ skb->len += size;
+ skb->data_len += size;
+ skb->truesize += truesize;
+ skb_frag_unref(skb, i);
+}
+EXPORT_SYMBOL(skb_coalesce_rx_frag);
+
static void skb_drop_list(struct sk_buff **listp)
{
kfree_skb_list(*listp);
--
1.8.1.2
Commit 2613af0ed18a11d5c566a81f9a6510b73180660a (virtio_net: migrate mergeable
rx buffers to page frag allocators) try to increase the payload/truesize for
MTU-sized traffic. But this will introduce the extra overhead for GSO packets
received because of the frag list. This commit tries to reduce this issue by
coalesce the possible rx frags when possible during rx. Test result shows the
about 15% improvement on full size GSO packet receiving (and even better than
commit 2613af0ed18a11d5c566a81f9a6510b73180660a).
Before this commit:
./netperf -H 192.168.100.4
MIGRATED TCP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 192.168.100.4
() port 0 AF_INET : demo
Recv Send Send
Socket Socket Message Elapsed
Size Size Size Time Throughput
bytes bytes bytes secs. 10^6bits/sec
87380 16384 16384 10.00 20303.87
After this commit:
./netperf -H 192.168.100.4
MIGRATED TCP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 192.168.100.4 () port 0 AF_INET : demo
Recv Send Send
Socket Socket Message Elapsed
Size Size Size Time Throughput
bytes bytes bytes secs. 10^6bits/sec
87380 16384 16384 10.00 23841.26
Cc: Rusty Russell <[email protected]>
Cc: Michael S. Tsirkin <[email protected]>
Cc: Michael Dalton <[email protected]>
Cc: Eric Dumazet <[email protected]>
Signed-off-by: Jason Wang <[email protected]>
---
drivers/net/virtio_net.c | 14 ++++++++++----
1 file changed, 10 insertions(+), 4 deletions(-)
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 113ee93..4ff4f78 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -305,7 +305,7 @@ static int receive_mergeable(struct receive_queue *rq, struct sk_buff *head_skb)
struct sk_buff *curr_skb = head_skb;
char *buf;
struct page *page;
- int num_buf, len;
+ int num_buf, len, offset;
num_buf = hdr->mhdr.num_buffers;
while (--num_buf) {
@@ -342,9 +342,15 @@ static int receive_mergeable(struct receive_queue *rq, struct sk_buff *head_skb)
head_skb->truesize += MAX_PACKET_LEN;
}
page = virt_to_head_page(buf);
- skb_add_rx_frag(curr_skb, num_skb_frags, page,
- buf - (char *)page_address(page), len,
- MAX_PACKET_LEN);
+ offset = buf - (char *)page_address(page);
+ if (skb_can_coalesce(curr_skb, num_skb_frags, page, offset)) {
+ skb_coalesce_rx_frag(curr_skb, num_skb_frags - 1,
+ offset, len, MAX_PACKET_LEN);
+ } else {
+ skb_add_rx_frag(curr_skb, num_skb_frags, page,
+ offset, len,
+ MAX_PACKET_LEN);
+ }
--rq->num;
}
return 0;
--
1.8.1.2
On Thu, Oct 31, 2013 at 6:28 PM, Jason Wang <[email protected]> wrote:
> Sometimes we need to coalesce the rx frags to avoid frag list. One example is
> virtio-net driver which tries to use small frags for both MTU sized packet and
> GSO packet. So this patch introduce skb_coalesce_rx_frag() to do this.
>
> Cc: Rusty Russell <[email protected]>
> Cc: Michael S. Tsirkin <[email protected]>
> Cc: Michael Dalton <[email protected]>
> Cc: Eric Dumazet <[email protected]>
> Signed-off-by: Jason Wang <[email protected]>
> ---
> include/linux/skbuff.h | 3 +++
> net/core/skbuff.c | 13 +++++++++++++
> 2 files changed, 16 insertions(+)
>
> diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
> index 2c15497..e34652b 100644
> --- a/include/linux/skbuff.h
> +++ b/include/linux/skbuff.h
> @@ -1372,6 +1372,9 @@ static inline void skb_fill_page_desc(struct sk_buff *skb, int i,
> void skb_add_rx_frag(struct sk_buff *skb, int i, struct page *page, int off,
> int size, unsigned int truesize);
>
> +void skb_coalesce_rx_frag(struct sk_buff *skb, int i, int off, int size,
> + unsigned int truesize);
> +
> #define SKB_PAGE_ASSERT(skb) BUG_ON(skb_shinfo(skb)->nr_frags)
> #define SKB_FRAG_ASSERT(skb) BUG_ON(skb_has_frag_list(skb))
> #define SKB_LINEAR_ASSERT(skb) BUG_ON(skb_is_nonlinear(skb))
> diff --git a/net/core/skbuff.c b/net/core/skbuff.c
> index 0ab32fa..fdef994 100644
> --- a/net/core/skbuff.c
> +++ b/net/core/skbuff.c
> @@ -476,6 +476,19 @@ void skb_add_rx_frag(struct sk_buff *skb, int i, struct page *page, int off,
> }
> EXPORT_SYMBOL(skb_add_rx_frag);
>
> +void skb_coalesce_rx_frag(struct sk_buff *skb, int i, int off, int size,
> + unsigned int truesize)
> +{
> + skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
> +
> + skb_frag_size_add(frag, size);
> + skb->len += size;
> + skb->data_len += size;
> + skb->truesize += truesize;
> + skb_frag_unref(skb, i);
> +}
I didn't see you use "off" in skb_coalesce_rx_frag.
> +EXPORT_SYMBOL(skb_coalesce_rx_frag);
> +
> static void skb_drop_list(struct sk_buff **listp)
> {
> kfree_skb_list(*listp);
> --
> 1.8.1.2
>
> --
> To unsubscribe from this list: send the line "unsubscribe netdev" in
> the body of a message to [email protected]
> More majordomo info at http://vger.kernel.org/majordomo-info.html
On 10/31/2013 07:05 PM, Kmindg G wrote:
> On Thu, Oct 31, 2013 at 6:28 PM, Jason Wang <[email protected]> wrote:
>> > Sometimes we need to coalesce the rx frags to avoid frag list. One example is
>> > virtio-net driver which tries to use small frags for both MTU sized packet and
>> > GSO packet. So this patch introduce skb_coalesce_rx_frag() to do this.
>> >
>> > Cc: Rusty Russell <[email protected]>
>> > Cc: Michael S. Tsirkin <[email protected]>
>> > Cc: Michael Dalton <[email protected]>
>> > Cc: Eric Dumazet <[email protected]>
>> > Signed-off-by: Jason Wang <[email protected]>
>> > ---
>> > include/linux/skbuff.h | 3 +++
>> > net/core/skbuff.c | 13 +++++++++++++
>> > 2 files changed, 16 insertions(+)
>> >
>> > diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
>> > index 2c15497..e34652b 100644
>> > --- a/include/linux/skbuff.h
>> > +++ b/include/linux/skbuff.h
>> > @@ -1372,6 +1372,9 @@ static inline void skb_fill_page_desc(struct sk_buff *skb, int i,
>> > void skb_add_rx_frag(struct sk_buff *skb, int i, struct page *page, int off,
>> > int size, unsigned int truesize);
>> >
>> > +void skb_coalesce_rx_frag(struct sk_buff *skb, int i, int off, int size,
>> > + unsigned int truesize);
>> > +
>> > #define SKB_PAGE_ASSERT(skb) BUG_ON(skb_shinfo(skb)->nr_frags)
>> > #define SKB_FRAG_ASSERT(skb) BUG_ON(skb_has_frag_list(skb))
>> > #define SKB_LINEAR_ASSERT(skb) BUG_ON(skb_is_nonlinear(skb))
>> > diff --git a/net/core/skbuff.c b/net/core/skbuff.c
>> > index 0ab32fa..fdef994 100644
>> > --- a/net/core/skbuff.c
>> > +++ b/net/core/skbuff.c
>> > @@ -476,6 +476,19 @@ void skb_add_rx_frag(struct sk_buff *skb, int i, struct page *page, int off,
>> > }
>> > EXPORT_SYMBOL(skb_add_rx_frag);
>> >
>> > +void skb_coalesce_rx_frag(struct sk_buff *skb, int i, int off, int size,
>> > + unsigned int truesize)
>> > +{
>> > + skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
>> > +
>> > + skb_frag_size_add(frag, size);
>> > + skb->len += size;
>> > + skb->data_len += size;
>> > + skb->truesize += truesize;
>> > + skb_frag_unref(skb, i);
>> > +}
> I didn't see you use "off" in skb_coalesce_rx_frag.
>
Ture, it's useless. Will post V2.
Thanks
On Thu, Oct 31, 2013 at 06:28:32PM +0800, Jason Wang wrote:
> Sometimes we need to coalesce the rx frags to avoid frag list. One example is
> virtio-net driver which tries to use small frags for both MTU sized packet and
> GSO packet. So this patch introduce skb_coalesce_rx_frag() to do this.
>
> Cc: Rusty Russell <[email protected]>
> Cc: Michael S. Tsirkin <[email protected]>
> Cc: Michael Dalton <[email protected]>
> Cc: Eric Dumazet <[email protected]>
> Signed-off-by: Jason Wang <[email protected]>
Acked-by: Michael S. Tsirkin <[email protected]>
> ---
> include/linux/skbuff.h | 3 +++
> net/core/skbuff.c | 13 +++++++++++++
> 2 files changed, 16 insertions(+)
>
> diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
> index 2c15497..e34652b 100644
> --- a/include/linux/skbuff.h
> +++ b/include/linux/skbuff.h
> @@ -1372,6 +1372,9 @@ static inline void skb_fill_page_desc(struct sk_buff *skb, int i,
> void skb_add_rx_frag(struct sk_buff *skb, int i, struct page *page, int off,
> int size, unsigned int truesize);
>
> +void skb_coalesce_rx_frag(struct sk_buff *skb, int i, int off, int size,
> + unsigned int truesize);
> +
> #define SKB_PAGE_ASSERT(skb) BUG_ON(skb_shinfo(skb)->nr_frags)
> #define SKB_FRAG_ASSERT(skb) BUG_ON(skb_has_frag_list(skb))
> #define SKB_LINEAR_ASSERT(skb) BUG_ON(skb_is_nonlinear(skb))
> diff --git a/net/core/skbuff.c b/net/core/skbuff.c
> index 0ab32fa..fdef994 100644
> --- a/net/core/skbuff.c
> +++ b/net/core/skbuff.c
> @@ -476,6 +476,19 @@ void skb_add_rx_frag(struct sk_buff *skb, int i, struct page *page, int off,
> }
> EXPORT_SYMBOL(skb_add_rx_frag);
>
> +void skb_coalesce_rx_frag(struct sk_buff *skb, int i, int off, int size,
> + unsigned int truesize)
> +{
> + skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
> +
> + skb_frag_size_add(frag, size);
> + skb->len += size;
> + skb->data_len += size;
> + skb->truesize += truesize;
> + skb_frag_unref(skb, i);
> +}
> +EXPORT_SYMBOL(skb_coalesce_rx_frag);
> +
> static void skb_drop_list(struct sk_buff **listp)
> {
> kfree_skb_list(*listp);
> --
> 1.8.1.2
On Thu, Oct 31, 2013 at 06:28:33PM +0800, Jason Wang wrote:
> Commit 2613af0ed18a11d5c566a81f9a6510b73180660a (virtio_net: migrate mergeable
> rx buffers to page frag allocators) try to increase the payload/truesize for
> MTU-sized traffic. But this will introduce the extra overhead for GSO packets
> received because of the frag list. This commit tries to reduce this issue by
> coalesce the possible rx frags when possible during rx. Test result shows the
> about 15% improvement on full size GSO packet receiving (and even better than
> commit 2613af0ed18a11d5c566a81f9a6510b73180660a).
>
> Before this commit:
> ./netperf -H 192.168.100.4
> MIGRATED TCP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 192.168.100.4
> () port 0 AF_INET : demo
> Recv Send Send
> Socket Socket Message Elapsed
> Size Size Size Time Throughput
> bytes bytes bytes secs. 10^6bits/sec
>
> 87380 16384 16384 10.00 20303.87
>
> After this commit:
> ./netperf -H 192.168.100.4
> MIGRATED TCP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 192.168.100.4 () port 0 AF_INET : demo
> Recv Send Send
> Socket Socket Message Elapsed
> Size Size Size Time Throughput
> bytes bytes bytes secs. 10^6bits/sec
>
> 87380 16384 16384 10.00 23841.26
>
> Cc: Rusty Russell <[email protected]>
> Cc: Michael S. Tsirkin <[email protected]>
> Cc: Michael Dalton <[email protected]>
> Cc: Eric Dumazet <[email protected]>
> Signed-off-by: Jason Wang <[email protected]>
Good idea.
Acked-by: Michael S. Tsirkin <[email protected]>
> ---
> drivers/net/virtio_net.c | 14 ++++++++++----
> 1 file changed, 10 insertions(+), 4 deletions(-)
>
> diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
> index 113ee93..4ff4f78 100644
> --- a/drivers/net/virtio_net.c
> +++ b/drivers/net/virtio_net.c
> @@ -305,7 +305,7 @@ static int receive_mergeable(struct receive_queue *rq, struct sk_buff *head_skb)
> struct sk_buff *curr_skb = head_skb;
> char *buf;
> struct page *page;
> - int num_buf, len;
> + int num_buf, len, offset;
>
> num_buf = hdr->mhdr.num_buffers;
> while (--num_buf) {
> @@ -342,9 +342,15 @@ static int receive_mergeable(struct receive_queue *rq, struct sk_buff *head_skb)
> head_skb->truesize += MAX_PACKET_LEN;
> }
> page = virt_to_head_page(buf);
> - skb_add_rx_frag(curr_skb, num_skb_frags, page,
> - buf - (char *)page_address(page), len,
> - MAX_PACKET_LEN);
> + offset = buf - (char *)page_address(page);
> + if (skb_can_coalesce(curr_skb, num_skb_frags, page, offset)) {
> + skb_coalesce_rx_frag(curr_skb, num_skb_frags - 1,
> + offset, len, MAX_PACKET_LEN);
> + } else {
> + skb_add_rx_frag(curr_skb, num_skb_frags, page,
> + offset, len,
> + MAX_PACKET_LEN);
> + }
> --rq->num;
> }
> return 0;
> --
> 1.8.1.2
Jason Wang <[email protected]> writes:
> Commit 2613af0ed18a11d5c566a81f9a6510b73180660a (virtio_net: migrate mergeable
> rx buffers to page frag allocators) try to increase the payload/truesize for
> MTU-sized traffic. But this will introduce the extra overhead for GSO packets
> received because of the frag list. This commit tries to reduce this issue by
> coalesce the possible rx frags when possible during rx. Test result shows the
> about 15% improvement on full size GSO packet receiving (and even better than
> commit 2613af0ed18a11d5c566a81f9a6510b73180660a).
I don't know about the other users of skb_add_rx_frag, but should
this coalesce-if-possible code be built into that?
Thanks,
Rusty.