[PATCH iproute2 0/4] iproute: Support for remote checksum offload

[PATCH iproute2 0/4] iproute: Support for remote checksum offload

[Tom Herbert]

Also, updated man pages for remote checksum offload options,
and added a section on setting FOU/GUE encapsulation with IP tunnels.

Tom Herbert (4):
  ip link: Add support for remote checksum offload to IP tunnels
  vxlan: Add support for remote checksum offload
  iproute: Description of new options for VXLAN in ip-link man pages
  iproute: Descriptions of fou and gue options in ip-link man pages

 include/linux/if_link.h |  2 ++
 ip/iplink_vxlan.c       | 21 ++++++++++++
 ip/link_gre.c           | 11 ++++++-
 ip/link_iptnl.c         | 11 ++++++-
 man/man8/ip-link.8.in   | 86 ++++++++++++++++++++++++++++++++++++++++++++++++-
 5 files changed, 128 insertions(+), 3 deletions(-)

-- 
2.2.0.rc0.207.ga3a616c

[PATCH iproute2 1/4] ip link: Add support for remote checksum offload to IP tunnels

[Tom Herbert]

This patch adds support to remote checksum checksum offload
confinguration for IPIP, SIT, and GRE tunnels. This patch
adds a [no]encap-remcsum to ip link command which applicable
when configured tunnels that use GUE.

http://tools.ietf.org/html/draft-herbert-remotecsumoffload-00

Example:

ip link add name tun1 type gre remote 192.168.1.1 local 192.168.1.2 \
   ttl 225 encap fou encap-sport auto encap-dport 7777 encap-csum \
   encap-remcsum

This would create an GRE tunnel in GUE encapsulation where the source
port is automatically selected (based on hash of inner packet),
checksums in the encapsulating UDP header are enabled (needed.for
remote checksum offload), and remote checksum ffload is configured to
be used on the tunnel (affects TX side).

Signed-off-by: Tom Herbert <therbert@google.com>
---
 ip/link_gre.c   | 11 ++++++++++-
 ip/link_iptnl.c | 11 ++++++++++-
 2 files changed, 20 insertions(+), 2 deletions(-)

diff --git a/ip/link_gre.c b/ip/link_gre.c
index 47b64cb..1d78387 100644
--- a/ip/link_gre.c
+++ b/ip/link_gre.c
@@ -31,7 +31,7 @@ static void print_usage(FILE *f)
 	fprintf(f, "          [ ttl TTL ] [ tos TOS ] [ [no]pmtudisc ] [ dev PHYS_DEV ]\n");
 	fprintf(f, "          [ noencap ] [ encap { fou | gue | none } ]\n");
 	fprintf(f, "          [ encap-sport PORT ] [ encap-dport PORT ]\n");
-	fprintf(f, "          [ [no]encap-csum ] [ [no]encap-csum6 ]\n");
+	fprintf(f, "          [ [no]encap-csum ] [ [no]encap-csum6 ] [ [no]encap-remcsum ]\n");
 	fprintf(f, "\n");
 	fprintf(f, "Where: NAME := STRING\n");
 	fprintf(f, "       ADDR := { IP_ADDRESS | any }\n");
@@ -287,6 +287,10 @@ get_failed:
 			encapflags |= TUNNEL_ENCAP_FLAG_CSUM6;
 		} else if (strcmp(*argv, "noencap-udp6-csum") == 0) {
 			encapflags |= ~TUNNEL_ENCAP_FLAG_CSUM6;
+		} else if (strcmp(*argv, "encap-remcsum") == 0) {
+			encapflags |= TUNNEL_ENCAP_FLAG_REMCSUM;
+		} else if (strcmp(*argv, "noencap-remcsum") == 0) {
+			encapflags |= ~TUNNEL_ENCAP_FLAG_REMCSUM;
 		} else
 			usage();
 		argc--; argv++;
@@ -445,6 +449,11 @@ static void gre_print_opt(struct link_util *lu, FILE *f, struct rtattr *tb[])
 			fputs("encap-csum6 ", f);
 		else
 			fputs("noencap-csum6 ", f);
+
+		if (flags & TUNNEL_ENCAP_FLAG_REMCSUM)
+			fputs("encap-remcsum ", f);
+		else
+			fputs("noencap-remcsum ", f);
 	}
 }
 
diff --git a/ip/link_iptnl.c b/ip/link_iptnl.c
index 9487117..cab174f 100644
--- a/ip/link_iptnl.c
+++ b/ip/link_iptnl.c
@@ -31,7 +31,7 @@ static void print_usage(FILE *f, int sit)
 	fprintf(f, "          [ 6rd-prefix ADDR ] [ 6rd-relay_prefix ADDR ] [ 6rd-reset ]\n");
 	fprintf(f, "          [ noencap ] [ encap { fou | gue | none } ]\n");
 	fprintf(f, "          [ encap-sport PORT ] [ encap-dport PORT ]\n");
-	fprintf(f, "          [ [no]encap-csum ] [ [no]encap-csum6 ]\n");
+	fprintf(f, "          [ [no]encap-csum ] [ [no]encap-csum6 ] [ [no]encap-remcsum ]\n");
 	if (sit) {
 		fprintf(f, "          [ mode { ip6ip | ipip | any } ]\n");
 		fprintf(f, "          [ isatap ]\n");
@@ -256,6 +256,10 @@ get_failed:
 			encapflags |= TUNNEL_ENCAP_FLAG_CSUM6;
 		} else if (strcmp(*argv, "noencap-udp6-csum") == 0) {
 			encapflags &= ~TUNNEL_ENCAP_FLAG_CSUM6;
+		} else if (strcmp(*argv, "encap-remcsum") == 0) {
+			encapflags |= TUNNEL_ENCAP_FLAG_REMCSUM;
+		} else if (strcmp(*argv, "noencap-remcsum") == 0) {
+			encapflags &= ~TUNNEL_ENCAP_FLAG_REMCSUM;
 		} else if (strcmp(*argv, "6rd-prefix") == 0) {
 			inet_prefix prefix;
 			NEXT_ARG();
@@ -438,6 +442,11 @@ static void iptunnel_print_opt(struct link_util *lu, FILE *f, struct rtattr *tb[
 			fputs("encap-csum6 ", f);
 		else
 			fputs("noencap-csum6 ", f);
+
+		if (flags & TUNNEL_ENCAP_FLAG_REMCSUM)
+			fputs("encap-remcsum ", f);
+		else
+			fputs("noencap-remcsum ", f);
 	}
 }
 
-- 
2.2.0.rc0.207.ga3a616c

Re: [PATCH iproute2 1/4] ip link: Add support for remote checksum offload to IP tunnels

[Stephen Hemminger]

On Thu, 29 Jan 2015 08:51:58 -0800
Tom Herbert <therbert@google.com> wrote:

> This patch adds support to remote checksum checksum offload
> confinguration for IPIP, SIT, and GRE tunnels. This patch
> adds a [no]encap-remcsum to ip link command which applicable
> when configured tunnels that use GUE.
> 
> http://tools.ietf.org/html/draft-herbert-remotecsumoffload-00
> 
> Example:
> 
> ip link add name tun1 type gre remote 192.168.1.1 local 192.168.1.2 \
>    ttl 225 encap fou encap-sport auto encap-dport 7777 encap-csum \
>    encap-remcsum
> 
> This would create an GRE tunnel in GUE encapsulation where the source
> port is automatically selected (based on hash of inner packet),
> checksums in the encapsulating UDP header are enabled (needed.for
> remote checksum offload), and remote checksum ffload is configured to
> be used on the tunnel (affects TX side).
> 
> Signed-off-by: Tom Herbert <therbert@google.com>

Applied to master since this does not depend on any net-next features.

[PATCH iproute2 2/4] vxlan: Add support for remote checksum offload

[Tom Herbert]

This patch adds support to remote checksum checksum offload
to VXLAN. This patch adds remcsumtx and remcsumrx to ip vxlan
configuration to enable remote checksum offload for transmit
and receive on the VXLAN tunnel.

https://tools.ietf.org/html/draft-herbert-vxlan-rco-00

Example:

ip link add name vxlan0 type vxlan id 42 group 239.1.1.1 dev eth0 \
    udpcsum remcsumtx remcsumrx

Signed-off-by: Tom Herbert <therbert@google.com>
---
 include/linux/if_link.h |  2 ++
 ip/iplink_vxlan.c       | 21 +++++++++++++++++++++
 2 files changed, 23 insertions(+)

diff --git a/include/linux/if_link.h b/include/linux/if_link.h
index 167ec34..11df025 100644
--- a/include/linux/if_link.h
+++ b/include/linux/if_link.h
@@ -368,6 +368,8 @@ enum {
 	IFLA_VXLAN_UDP_CSUM,
 	IFLA_VXLAN_UDP_ZERO_CSUM6_TX,
 	IFLA_VXLAN_UDP_ZERO_CSUM6_RX,
+	IFLA_VXLAN_REMCSUM_TX,
+	IFLA_VXLAN_REMCSUM_RX,
 	__IFLA_VXLAN_MAX
 };
 #define IFLA_VXLAN_MAX	(__IFLA_VXLAN_MAX - 1)
diff --git a/ip/iplink_vxlan.c b/ip/iplink_vxlan.c
index 9cc3ec3..8fb11df 100644
--- a/ip/iplink_vxlan.c
+++ b/ip/iplink_vxlan.c
@@ -30,6 +30,7 @@ static void print_explain(FILE *f)
 	fprintf(f, "                 [ [no]l2miss ] [ [no]l3miss ]\n");
 	fprintf(f, "                 [ ageing SECONDS ] [ maxaddress NUMBER ]\n");
 	fprintf(f, "                 [ [no]udpcsum ] [ [no]udp6zerocsumtx ] [ [no]udp6zerocsumrx ]\n");
+	fprintf(f, "                 [ [no]remcsumtx ] [ [no]remcsumrx ]\n");
 	fprintf(f, "\n");
 	fprintf(f, "Where: VNI := 0-16777215\n");
 	fprintf(f, "       ADDR := { IP_ADDRESS | any }\n");
@@ -68,6 +69,8 @@ static int vxlan_parse_opt(struct link_util *lu, int argc, char **argv,
 	__u8 udpcsum = 0;
 	__u8 udp6zerocsumtx = 0;
 	__u8 udp6zerocsumrx = 0;
+	__u8 remcsumtx = 0;
+	__u8 remcsumrx = 0;
 	int dst_port_set = 0;
 	struct ifla_vxlan_port_range range = { 0, 0 };
 
@@ -197,6 +200,14 @@ static int vxlan_parse_opt(struct link_util *lu, int argc, char **argv,
 			udp6zerocsumrx = 1;
 		} else if (!matches(*argv, "noudp6zerocsumrx")) {
 			udp6zerocsumrx = 0;
+		} else if (!matches(*argv, "remcsumtx")) {
+			remcsumtx = 1;
+		} else if (!matches(*argv, "noremcsumtx")) {
+			remcsumtx = 0;
+		} else if (!matches(*argv, "remcsumrx")) {
+			remcsumrx = 1;
+		} else if (!matches(*argv, "noremcsumrx")) {
+			remcsumrx = 0;
 		} else if (matches(*argv, "help") == 0) {
 			explain();
 			return -1;
@@ -255,6 +266,8 @@ static int vxlan_parse_opt(struct link_util *lu, int argc, char **argv,
 	addattr8(n, 1024, IFLA_VXLAN_UDP_CSUM, udpcsum);
 	addattr8(n, 1024, IFLA_VXLAN_UDP_ZERO_CSUM6_TX, udp6zerocsumtx);
 	addattr8(n, 1024, IFLA_VXLAN_UDP_ZERO_CSUM6_RX, udp6zerocsumrx);
+	addattr8(n, 1024, IFLA_VXLAN_REMCSUM_TX, remcsumtx);
+	addattr8(n, 1024, IFLA_VXLAN_REMCSUM_RX, remcsumrx);
 
 	if (noage)
 		addattr32(n, 1024, IFLA_VXLAN_AGEING, 0);
@@ -398,6 +411,14 @@ static void vxlan_print_opt(struct link_util *lu, FILE *f, struct rtattr *tb[])
 	if (tb[IFLA_VXLAN_UDP_ZERO_CSUM6_RX] &&
 	    rta_getattr_u8(tb[IFLA_VXLAN_UDP_ZERO_CSUM6_RX]))
 		fputs("udp6zerocsumrx ", f);
+
+	if (tb[IFLA_VXLAN_REMCSUM_TX] &&
+	    rta_getattr_u8(tb[IFLA_VXLAN_REMCSUM_TX]))
+		fputs("remcsumtx ", f);
+
+	if (tb[IFLA_VXLAN_REMCSUM_RX] &&
+	    rta_getattr_u8(tb[IFLA_VXLAN_REMCSUM_RX]))
+		fputs("remcsumrx ", f);
 }
 
 static void vxlan_print_help(struct link_util *lu, int argc, char **argv,
-- 
2.2.0.rc0.207.ga3a616c

Re: [PATCH iproute2 2/4] vxlan: Add support for remote checksum offload

[Stephen Hemminger]

On Thu, 29 Jan 2015 08:51:59 -0800
Tom Herbert <therbert@google.com> wrote:

> This patch adds support to remote checksum checksum offload
> to VXLAN. This patch adds remcsumtx and remcsumrx to ip vxlan
> configuration to enable remote checksum offload for transmit
> and receive on the VXLAN tunnel.
> 
> https://tools.ietf.org/html/draft-herbert-vxlan-rco-00
> 
> Example:
> 
> ip link add name vxlan0 type vxlan id 42 group 239.1.1.1 dev eth0 \
>     udpcsum remcsumtx remcsumrx
> 
> Signed-off-by: Tom Herbert <therbert@google.com>

Does not apply to current iproute2 net-next branch because
the vxlan group policy extensions was applied first.

Please fix conflicts and resubmit.

[PATCH iproute2 3/4] iproute: Description of new options for VXLAN in ip-link man pages

[Tom Herbert]

Add description for UDP checksums and remote checksum offload.

Signed-off-by: Tom Herbert <therbert@google.com>
---
 man/man8/ip-link.8.in | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/man/man8/ip-link.8.in b/man/man8/ip-link.8.in
index 1209b55..a0be895 100644
--- a/man/man8/ip-link.8.in
+++ b/man/man8/ip-link.8.in
@@ -276,6 +276,12 @@ the following additional arguments are supported:
 .BI ageing " SECONDS "
 .R " ] [ "
 .BI maxaddress " NUMBER "
+.R " ] [ "
+.I "[no]udpcsum "
+.R " ] [ "
+.I "[no]remcsumtx "
+.R " ] [ "
+.I "[no]remcsumrx "
 .R " ]"
 
 .in +8
@@ -348,6 +354,18 @@ are entered into the VXLAN device forwarding database.
 .BI maxaddress " NUMBER"
 - specifies the maximum number of FDB entries.
 
+.sp
+.I [no]udpcsum
+- specifies if UDP checksum is enabled in the outer header.
+
+.sp
+.I [no]remcsumtx
+- specifies if remote checksum option is tranmitted.
+
+.sp
+.I [no]remcsumrx
+- specifies if remote checksum option is allowed to be received.
+
 .in -8
 
 .TP
-- 
2.2.0.rc0.207.ga3a616c

Re: [PATCH iproute2 3/4] iproute: Description of new options for VXLAN in ip-link man pages

[Nikolay Aleksandrov]

On 01/29/2015 05:52 PM, Tom Herbert wrote:
> Add description for UDP checksums and remote checksum offload.
> 
> Signed-off-by: Tom Herbert <therbert@google.com>
> ---
>  man/man8/ip-link.8.in | 18 ++++++++++++++++++
>  1 file changed, 18 insertions(+)
> 
> diff --git a/man/man8/ip-link.8.in b/man/man8/ip-link.8.in
> index 1209b55..a0be895 100644
> --- a/man/man8/ip-link.8.in
> +++ b/man/man8/ip-link.8.in
> @@ -276,6 +276,12 @@ the following additional arguments are supported:
>  .BI ageing " SECONDS "
>  .R " ] [ "
>  .BI maxaddress " NUMBER "
> +.R " ] [ "
> +.I "[no]udpcsum "
> +.R " ] [ "
> +.I "[no]remcsumtx "
> +.R " ] [ "
> +.I "[no]remcsumrx "
>  .R " ]"
>  
>  .in +8
> @@ -348,6 +354,18 @@ are entered into the VXLAN device forwarding database.
>  .BI maxaddress " NUMBER"
>  - specifies the maximum number of FDB entries.
>  
> +.sp
> +.I [no]udpcsum
> +- specifies if UDP checksum is enabled in the outer header.
> +
> +.sp
> +.I [no]remcsumtx
> +- specifies if remote checksum option is tranmitted.
                                            ^^^^^^^^^^
transmitted

> +
> +.sp
> +.I [no]remcsumrx
> +- specifies if remote checksum option is allowed to be received.
> +
>  .in -8
>  
>  .TP
> 

Re: [PATCH iproute2 3/4] iproute: Description of new options for VXLAN in ip-link man pages

[Stephen Hemminger]

On Thu, 29 Jan 2015 08:52:00 -0800
Tom Herbert <therbert@google.com> wrote:

> Add description for UDP checksums and remote checksum offload.
> 
> Signed-off-by: Tom Herbert <therbert@google.com>

Resubmit this when you fix up patch #2

[PATCH iproute2 4/4] iproute: Descriptions of fou and gue options in ip-link man pages

[Tom Herbert]

Add section for additional arguments to GRE, IPIP, and SIT types
that are related to Foo-over-UDP and Generic UDP Encapsulation.
Also, added an example GUE configuration in the examples section.

Signed-off-by: Tom Herbert <therbert@google.com>
---
 man/man8/ip-link.8.in | 68 ++++++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 67 insertions(+), 1 deletion(-)

diff --git a/man/man8/ip-link.8.in b/man/man8/ip-link.8.in
index a0be895..2634590 100644
--- a/man/man8/ip-link.8.in
+++ b/man/man8/ip-link.8.in
@@ -369,6 +369,63 @@ are entered into the VXLAN device forwarding database.
 .in -8
 
 .TP
+GRE, IPIP, SIT Type Support
+For a link of types
+.I GRE/IPIP/SIT
+the following additional arguments are supported:
+
+.BI "ip link add " DEVICE
+.BR type " { gre | ipip | sit } "
+.BI " remote " ADDR " local " ADDR
+.R " [ "
+.BR encap " { fou | gue | none } "
+.R " ] [ "
+.BI "encap-sport { " PORT " | auto } "
+.R " ] [ "
+.BI "encap-dport " PORT
+.R " ] [ "
+.I " [no]encap-csum "
+.R " ] [ "
+.I " [no]encap-remcsum "
+.R " ]"
+
+.in +8
+.sp
+.BI  remote " ADDR "
+- specifies the remote address of the tunnel.
+
+.sp
+.BI  local " ADDR "
+- specifies the fixed local address for tunneled packets.
+It must be an address on another interface on this host.
+
+.sp
+.BR encap " { fou | gue | none } "
+- specifies type of secondary UDP encapsulation. "fou" indicates
+Foo-Over-UDP, "gue" indicates Generic UDP Encapsulation.
+
+.sp
+.BI "encap-sport { " PORT " | auto } "
+- specifies the source port in UDP encapsulation.
+.IR PORT
+indicates the port by number, "auto"
+indicates that the port number should be chosen automatically
+(the kernel picks a flow based on the flow hash of the
+encapsulated packet).
+
+.sp
+.I [no]encap-csum
+- specifies if UDP checksums are enabled in the secondary
+encapsulation.
+
+.sp
+.I [no]encap-remcsum
+- specifies if Remote Checksum Offload is enabled. This is only
+applicable for Generic UDP Encapsulation.
+
+.in -8
+
+.TP
 IP6GRE/IP6GRETAP Type Support
 For a link of type
 .I IP6GRE/IP6GRETAP
@@ -404,7 +461,7 @@ the following additional arguments are supported:
 .sp
 .BI  local " ADDR "
 - specifies the fixed local IPv6 address for tunneled packets.
-It must be and address on another interface on this host.
+It must be an address on another interface on this host.
 
 .sp
 .BI  [i|o]seq
@@ -781,6 +838,15 @@ ip link help gre
 .RS 4
 Display help for the gre link type.
 .RE
+.PP
+ip link add name tun1 type ipip remote 192.168.1.1
+local 192.168.1.2 ttl 225 encap gue encap-sport auto
+encap-dport 5555 encap-csum encap-remcsum
+.RS 4
+Creates an IPIP that is encapsulated with Generic UDP Encapsulation,
+and the outer UDP checksum and remote checksum offload are enabled.
+
+.RE
 
 .SH SEE ALSO
 .br
-- 
2.2.0.rc0.207.ga3a616c

Re: [PATCH iproute2 4/4] iproute: Descriptions of fou and gue options in ip-link man pages

[Stephen Hemminger]

On Thu, 29 Jan 2015 08:52:01 -0800
Tom Herbert <therbert@google.com> wrote:

> Add section for additional arguments to GRE, IPIP, and SIT types
> that are related to Foo-over-UDP and Generic UDP Encapsulation.
> Also, added an example GUE configuration in the examples section.
> 
> Signed-off-by: Tom Herbert <therbert@google.com>

Applied to master branch.