netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Tom Herbert <therbert@google.com>
To: davem@davemloft.net, netdev@vger.kernel.org
Subject: [PATCH v2 net-next 7/7] gue: Receive side of remote checksum offload
Date: Tue,  4 Nov 2014 09:06:57 -0800	[thread overview]
Message-ID: <1415120817-2105-8-git-send-email-therbert@google.com> (raw)
In-Reply-To: <1415120817-2105-1-git-send-email-therbert@google.com>

Add processing of the remote checksum offload option in both the normal
path as well as the GRO path. The implements patching the affected
checksum to derive the offloaded checksum.

Signed-off-by: Tom Herbert <therbert@google.com>
---
 net/ipv4/fou.c | 170 ++++++++++++++++++++++++++++++++++++++++++++++++++++++---
 1 file changed, 161 insertions(+), 9 deletions(-)

diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index fb0db99..740ae09 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -63,6 +63,59 @@ static int fou_udp_recv(struct sock *sk, struct sk_buff *skb)
 	return -fou->protocol;
 }
 
+static struct guehdr *gue_remcsum(struct sk_buff *skb, struct guehdr *guehdr,
+				  void *data, int hdrlen, u8 ipproto)
+{
+	__be16 *pd = data;
+	u16 start = ntohs(pd[0]);
+	u16 offset = ntohs(pd[1]);
+	u16 poffset = 0;
+	u16 plen;
+	__wsum csum, delta;
+	__sum16 *psum;
+
+	if (skb->remcsum_offload) {
+		/* Already processed in GRO path */
+		skb->remcsum_offload = 0;
+		return guehdr;
+	}
+
+	if (start > skb->len - hdrlen ||
+	    offset > skb->len - hdrlen - sizeof(u16))
+		return NULL;
+
+	if (unlikely(skb->ip_summed != CHECKSUM_COMPLETE))
+		__skb_checksum_complete(skb);
+
+	plen = hdrlen + offset + sizeof(u16);
+	if (!pskb_may_pull(skb, plen))
+		return NULL;
+	guehdr = (struct guehdr *)&udp_hdr(skb)[1];
+
+	if (ipproto == IPPROTO_IP && sizeof(struct iphdr) < plen) {
+		struct iphdr *ip = (struct iphdr *)(skb->data + hdrlen);
+
+		/* If next header happens to be IP we can skip that for the
+		 * checksum calculation since the IP header checksum is zero
+		 * if correct.
+		 */
+		poffset = ip->ihl * 4;
+	}
+
+	csum = csum_sub(skb->csum, skb_checksum(skb, poffset + hdrlen,
+						start - poffset - hdrlen, 0));
+
+	/* Set derived checksum in packet */
+	psum = (__sum16 *)(skb->data + hdrlen + offset);
+	delta = csum_sub(csum_fold(csum), *psum);
+	*psum = csum_fold(csum);
+
+	/* Adjust skb->csum since we changed the packet */
+	skb->csum = csum_add(skb->csum, delta);
+
+	return guehdr;
+}
+
 static int gue_control_message(struct sk_buff *skb, struct guehdr *guehdr)
 {
 	/* No support yet */
@@ -76,6 +129,7 @@ static int gue_udp_recv(struct sock *sk, struct sk_buff *skb)
 	size_t len, optlen, hdrlen;
 	struct guehdr *guehdr;
 	void *data;
+	u16 doffset = 0;
 
 	if (!fou)
 		return 1;
@@ -100,20 +154,43 @@ static int gue_udp_recv(struct sock *sk, struct sk_buff *skb)
 	if (guehdr->version != 0 || validate_gue_flags(guehdr, optlen))
 		goto drop;
 
-	/* Pull UDP and GUE headers */
-	fou_recv_pull(skb, len);
+	hdrlen = sizeof(struct guehdr) + optlen;
+
+	ip_hdr(skb)->tot_len = htons(ntohs(ip_hdr(skb)->tot_len) - len);
+
+	/* Pull UDP header now, skb->data points to guehdr */
+	__skb_pull(skb, sizeof(struct udphdr));
+
+	/* Pull csum through the guehdr now . This can be used if
+	 * there is a remote checksum offload.
+	 */
+	skb_postpull_rcsum(skb, udp_hdr(skb), len);
 
 	data = &guehdr[1];
 
 	if (guehdr->flags & GUE_FLAG_PRIV) {
-		data += GUE_LEN_PRIV;
+		__be32 flags = *(__be32 *)(data + doffset);
+
+		doffset += GUE_LEN_PRIV;
 
-		/* Process private flags */
+		if (flags & GUE_PFLAG_REMCSUM) {
+			guehdr = gue_remcsum(skb, guehdr, data + doffset,
+					     hdrlen, guehdr->proto_ctype);
+			if (!guehdr)
+				goto drop;
+
+			data = &guehdr[1];
+
+			doffset += GUE_PLEN_REMCSUM;
+		}
 	}
 
 	if (unlikely(guehdr->control))
 		return gue_control_message(skb, guehdr);
 
+	__skb_pull(skb, hdrlen);
+	skb_reset_transport_header(skb);
+
 	return -guehdr->proto_ctype;
 
 drop:
@@ -164,6 +241,66 @@ out_unlock:
 	return err;
 }
 
+static struct guehdr *gue_gro_remcsum(struct sk_buff *skb, unsigned int off,
+				      struct guehdr *guehdr, void *data,
+				      size_t hdrlen, u8 ipproto)
+{
+	__be16 *pd = data;
+	u16 start = ntohs(pd[0]);
+	u16 offset = ntohs(pd[1]);
+	u16 poffset = 0;
+	u16 plen;
+	void *ptr;
+	__wsum csum, delta;
+	__sum16 *psum;
+
+	if (skb->remcsum_offload)
+		return guehdr;
+
+	if (start > skb_gro_len(skb) - hdrlen ||
+	    offset > skb_gro_len(skb) - hdrlen - sizeof(u16) ||
+	    !NAPI_GRO_CB(skb)->csum_valid || skb->remcsum_offload)
+		return NULL;
+
+	plen = hdrlen + offset + sizeof(u16);
+
+	/* Pull checksum that will be written */
+	if (skb_gro_header_hard(skb, off + plen)) {
+		guehdr = skb_gro_header_slow(skb, off + plen, off);
+		if (!guehdr)
+			return NULL;
+	}
+
+	ptr = (void *)guehdr + hdrlen;
+
+	if (ipproto == IPPROTO_IP &&
+	    (hdrlen + sizeof(struct iphdr) < plen)) {
+		struct iphdr *ip = (struct iphdr *)(ptr + hdrlen);
+
+		/* If next header happens to be IP we can skip
+		 * that for the checksum calculation since the
+		 * IP header checksum is zero if correct.
+		 */
+		poffset = ip->ihl * 4;
+	}
+
+	csum = csum_sub(NAPI_GRO_CB(skb)->csum,
+			csum_partial(ptr + poffset, start - poffset, 0));
+
+	/* Set derived checksum in packet */
+	psum = (__sum16 *)(ptr + offset);
+	delta = csum_sub(csum_fold(csum), *psum);
+	*psum = csum_fold(csum);
+
+	/* Adjust skb->csum since we changed the packet */
+	skb->csum = csum_add(skb->csum, delta);
+	NAPI_GRO_CB(skb)->csum = csum_add(NAPI_GRO_CB(skb)->csum, delta);
+
+	skb->remcsum_offload = 1;
+
+	return guehdr;
+}
+
 static struct sk_buff **gue_gro_receive(struct sk_buff **head,
 					struct sk_buff *skb)
 {
@@ -174,6 +311,7 @@ static struct sk_buff **gue_gro_receive(struct sk_buff **head,
 	struct guehdr *guehdr;
 	size_t len, optlen, hdrlen, off;
 	void *data;
+	u16 doffset = 0;
 	int flush = 1;
 
 	off = skb_gro_offset(skb);
@@ -201,19 +339,33 @@ static struct sk_buff **gue_gro_receive(struct sk_buff **head,
 
 	hdrlen = sizeof(*guehdr) + optlen;
 
-	skb_gro_pull(skb, hdrlen);
-
-	/* Adjusted NAPI_GRO_CB(skb)->csum after skb_gro_pull()*/
+	/* Adjust NAPI_GRO_CB(skb)->csum to account for guehdr,
+	 * this is needed if there is a remote checkcsum offload.
+	 */
 	skb_gro_postpull_rcsum(skb, guehdr, hdrlen);
 
 	data = &guehdr[1];
 
 	if (guehdr->flags & GUE_FLAG_PRIV) {
-		data += GUE_LEN_PRIV;
+		__be32 flags = *(__be32 *)(data + doffset);
 
-		/* Process private flags */
+		doffset += GUE_LEN_PRIV;
+
+		if (flags & GUE_PFLAG_REMCSUM) {
+			guehdr = gue_gro_remcsum(skb, off, guehdr,
+						 data + doffset, hdrlen,
+						 guehdr->proto_ctype);
+			if (!guehdr)
+				goto out;
+
+			data = &guehdr[1];
+
+			doffset += GUE_PLEN_REMCSUM;
+		}
 	}
 
+	skb_gro_pull(skb, hdrlen);
+
 	flush = 0;
 
 	for (p = *head; p; p = p->next) {
-- 
2.1.0.rc2.206.gedb03e5

  parent reply	other threads:[~2014-11-04 17:07 UTC|newest]

Thread overview: 9+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-11-04 17:06 [PATCH v2 net-next 0/7] gue: Remote checksum offload Tom Herbert
2014-11-04 17:06 ` [PATCH v2 net-next 1/7] net: Move fou_build_header into fou.c and refactor Tom Herbert
2014-11-04 17:06 ` [PATCH v2 net-next 2/7] udp: Offload outer UDP tunnel csum if available Tom Herbert
2014-11-04 17:06 ` [PATCH v2 net-next 3/7] gue: Add infrastructure for flags and options Tom Herbert
2014-11-04 17:06 ` [PATCH v2 net-next 4/7] udp: Changes to udp_offload to support remote checksum offload Tom Herbert
2014-11-04 17:06 ` [PATCH v2 net-next 5/7] gue: Protocol constants for " Tom Herbert
2014-11-04 17:06 ` [PATCH v2 net-next 6/7] gue: TX support for using remote checksum offload option Tom Herbert
2014-11-04 17:06 ` Tom Herbert [this message]
2014-11-05 21:44 ` [PATCH v2 net-next 0/7] gue: Remote checksum offload David Miller

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1415120817-2105-8-git-send-email-therbert@google.com \
    --to=therbert@google.com \
    --cc=davem@davemloft.net \
    --cc=netdev@vger.kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).