Message-ID: <1486458851-4920-6-git-send-email-steffen.klassert@secunet.com>
Date:   Tue, 7 Feb 2017 10:14:11 +0100
From:   Steffen Klassert <steffen.klassert@...unet.com>
To:     <netdev@...r.kernel.org>
CC:     Steffen Klassert <steffen.klassert@...unet.com>,
        David Miller <davem@...emloft.net>,
        Eric Dumazet <eric.dumazet@...il.com>,
        "Sowmini Varadhan" <sowmini.varadhan@...cle.com>,
        Ilan Tayari <ilant@...lanox.com>
Subject: [PATCH RFC ipsec-next 5/5] esp: Add a software GRO codepath

This patch adds GRO ifrastructure and callbacks for ESP on
ipv4 and ipv6.

In case the GRO layer detects an ESP packet, the
esp{4,6}_gro_receive() function does a xfrm state lookup
and calls the xfrm input layer if it finds a matching state.
The packet will be decapsulated and reinjected it into layer 2.

Signed-off-by: Steffen Klassert <steffen.klassert@...unet.com>
---
 include/net/xfrm.h              | 18 +++++++-
 net/ipv4/Kconfig                | 13 ++++++
 net/ipv4/Makefile               |  1 +
 net/ipv4/esp4_offload.c         | 96 ++++++++++++++++++++++++++++++++++++++++
 net/ipv4/xfrm4_input.c          |  6 +++
 net/ipv4/xfrm4_mode_transport.c |  3 +-
 net/ipv6/Kconfig                | 13 ++++++
 net/ipv6/Makefile               |  1 +
 net/ipv6/esp6_offload.c         | 98 +++++++++++++++++++++++++++++++++++++++++
 net/ipv6/xfrm6_input.c          |  5 +++
 net/ipv6/xfrm6_mode_transport.c |  3 +-
 net/xfrm/xfrm_input.c           | 32 +++++++++++---
 12 files changed, 280 insertions(+), 9 deletions(-)
 create mode 100644 net/ipv4/esp4_offload.c
 create mode 100644 net/ipv6/esp6_offload.c

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 8acea1e..8c94ef3 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -606,11 +606,25 @@ struct xfrm_mgr {
 int xfrm_register_km(struct xfrm_mgr *km);
 int xfrm_unregister_km(struct xfrm_mgr *km);
 
-struct xfrm_tunnel_skb_cb {
+/*
+ * This structure is used if we get the packet from the gro layer.
+ */
+struct xfrm_gro_skb_cb {
 	union {
 		struct inet_skb_parm h4;
 		struct inet6_skb_parm h6;
-	} header;
+
+		struct {
+			__be32 seq;
+			bool skb_is_gro;
+		} input;
+	} gro;
+};
+
+#define XFRM_GRO_SKB_CB(__skb) ((struct xfrm_gro_skb_cb *)&((__skb)->cb[0]))
+
+struct xfrm_tunnel_skb_cb {
+	struct xfrm_gro_skb_cb header;
 
 	union {
 		struct ip_tunnel *ip4;
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index 6e7baaf..e0878c3 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -360,6 +360,19 @@ config INET_ESP
 
 	  If unsure, say Y.
 
+config INET_ESP_OFFLOAD
+	tristate "IP: ESP transformation offload"
+	depends on INET_ESP
+	select XFRM_OFFLOAD
+	default n
+	---help---
+	  Support for ESP transformation offload. This makes sense
+	  only if this system really does IPsec and want to do it
+	  with high throughput. A typical desktop system does not
+	  need it, even if it does IPsec.
+
+	  If unsure, say N.
+
 config INET_IPCOMP
 	tristate "IP: IPComp transformation"
 	select INET_XFRM_TUNNEL
diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile
index 48af58a..c6d4238 100644
--- a/net/ipv4/Makefile
+++ b/net/ipv4/Makefile
@@ -29,6 +29,7 @@ obj-$(CONFIG_NET_IPVTI) += ip_vti.o
 obj-$(CONFIG_SYN_COOKIES) += syncookies.o
 obj-$(CONFIG_INET_AH) += ah4.o
 obj-$(CONFIG_INET_ESP) += esp4.o
+obj-$(CONFIG_INET_ESP_OFFLOAD) += esp4_offload.o
 obj-$(CONFIG_INET_IPCOMP) += ipcomp.o
 obj-$(CONFIG_INET_XFRM_TUNNEL) += xfrm4_tunnel.o
 obj-$(CONFIG_INET_XFRM_MODE_BEET) += xfrm4_mode_beet.o
diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c
new file mode 100644
index 0000000..2f26085
--- /dev/null
+++ b/net/ipv4/esp4_offload.c
@@ -0,0 +1,96 @@
+/*
+ * IPV4 GSO/GRO offload support
+ * Linux INET implementation
+ *
+ * Copyright (C) 2016 secunet Security Networks AG
+ * Author: Steffen Klassert <steffen.klassert@...unet.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * ESP GRO support
+ */
+
+#include <linux/skbuff.h>
+#include <linux/init.h>
+#include <net/protocol.h>
+#include <crypto/aead.h>
+#include <crypto/authenc.h>
+#include <linux/err.h>
+#include <linux/module.h>
+#include <net/ip.h>
+#include <net/xfrm.h>
+#include <net/esp.h>
+#include <linux/scatterlist.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <net/udp.h>
+
+static struct sk_buff **esp4_gro_receive(struct sk_buff **head,
+					 struct sk_buff *skb)
+{
+	int err;
+	__be32 seq;
+	__be32 spi;
+	struct xfrm_state *x;
+	int offset = skb_gro_offset(skb);
+
+	skb_pull(skb, offset);
+
+	if ((err = xfrm_parse_spi(skb, IPPROTO_ESP, &spi, &seq)) != 0)
+		goto out;
+
+	err = secpath_set(skb);
+	if (err)
+		goto out;
+
+	if (skb->sp->len == XFRM_MAX_DEPTH)
+		goto out;
+
+	x = xfrm_state_lookup(dev_net(skb->dev), skb->mark,
+			      (xfrm_address_t *)&ip_hdr(skb)->daddr,
+			      spi, IPPROTO_ESP, AF_INET);
+	if (!x)
+		goto out;
+
+	XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = NULL;
+	XFRM_SPI_SKB_CB(skb)->family = AF_INET;
+	XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr);
+	XFRM_GRO_SKB_CB(skb)->gro.input.seq = seq;
+	skb->sp->xvec[skb->sp->len++] = x;
+
+	/* We don't need to handle errors from xfrm_input, it does all
+	 * the error handling and frees the resources on error. */
+	xfrm_input(skb, IPPROTO_ESP, spi, -2);
+
+	return ERR_PTR(-EINPROGRESS);
+out:
+	skb_push(skb, offset);
+	NAPI_GRO_CB(skb)->same_flow = 0;
+	NAPI_GRO_CB(skb)->flush = 1;
+
+	return NULL;
+}
+
+static const struct net_offload esp4_offload = {
+	.callbacks = {
+		.gro_receive = esp4_gro_receive,
+	},
+};
+
+static int __init esp4_offload_init(void)
+{
+	return inet_add_offload(&esp4_offload, IPPROTO_ESP);
+}
+
+static void __exit esp4_offload_exit(void)
+{
+	inet_del_offload(&esp4_offload, IPPROTO_ESP);
+}
+
+module_init(esp4_offload_init);
+module_exit(esp4_offload_exit);
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Steffen Klassert <steffen.klassert@...unet.com>");
diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c
index 62e1e72..7554c95 100644
--- a/net/ipv4/xfrm4_input.c
+++ b/net/ipv4/xfrm4_input.c
@@ -53,6 +53,12 @@ int xfrm4_transport_finish(struct sk_buff *skb, int async)
 	iph->tot_len = htons(skb->len);
 	ip_send_check(iph);
 
+
+	if (XFRM_GRO_SKB_CB(skb)->gro.input.skb_is_gro) {
+		skb_mac_header_rebuild(skb);
+		return 0;
+	}
+
 	NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING,
 		dev_net(skb->dev), NULL, skb, skb->dev, NULL,
 		xfrm4_rcv_encap_finish);
diff --git a/net/ipv4/xfrm4_mode_transport.c b/net/ipv4/xfrm4_mode_transport.c
index fd840c7..3827f83 100644
--- a/net/ipv4/xfrm4_mode_transport.c
+++ b/net/ipv4/xfrm4_mode_transport.c
@@ -50,7 +50,8 @@ static int xfrm4_transport_input(struct xfrm_state *x, struct sk_buff *skb)
 		skb->network_header = skb->transport_header;
 	}
 	ip_hdr(skb)->tot_len = htons(skb->len + ihl);
-	skb_reset_transport_header(skb);
+	if (!(XFRM_GRO_SKB_CB(skb)->gro.input.skb_is_gro))
+		skb_reset_transport_header(skb);
 	return 0;
 }
 
diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig
index ec1267e..b2a85cc 100644
--- a/net/ipv6/Kconfig
+++ b/net/ipv6/Kconfig
@@ -75,6 +75,19 @@ config INET6_ESP
 
 	  If unsure, say Y.
 
+config INET6_ESP_OFFLOAD
+	tristate "IPv6: ESP transformation offload"
+	depends on INET6_ESP
+	select XFRM_OFFLOAD
+	default n
+	---help---
+	  Support for ESP transformation offload. This makes sense
+	  only if this system really does IPsec and want to do it
+	  with high throughput. A typical desktop system does not
+	  need it, even if it does IPsec.
+
+	  If unsure, say N.
+
 config INET6_IPCOMP
 	tristate "IPv6: IPComp transformation"
 	select INET6_XFRM_TUNNEL
diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile
index a9e9fec..217e9ff 100644
--- a/net/ipv6/Makefile
+++ b/net/ipv6/Makefile
@@ -30,6 +30,7 @@ ipv6-objs += $(ipv6-y)
 
 obj-$(CONFIG_INET6_AH) += ah6.o
 obj-$(CONFIG_INET6_ESP) += esp6.o
+obj-$(CONFIG_INET6_ESP_OFFLOAD) += esp6_offload.o
 obj-$(CONFIG_INET6_IPCOMP) += ipcomp6.o
 obj-$(CONFIG_INET6_XFRM_TUNNEL) += xfrm6_tunnel.o
 obj-$(CONFIG_INET6_TUNNEL) += tunnel6.o
diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c
new file mode 100644
index 0000000..f97d88b
--- /dev/null
+++ b/net/ipv6/esp6_offload.c
@@ -0,0 +1,98 @@
+/*
+ * IPV6 GSO/GRO offload support
+ * Linux INET implementation
+ *
+ * Copyright (C) 2016 secunet Security Networks AG
+ * Author: Steffen Klassert <steffen.klassert@...unet.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * ESP GRO support
+ */
+
+#include <linux/skbuff.h>
+#include <linux/init.h>
+#include <net/protocol.h>
+#include <crypto/aead.h>
+#include <crypto/authenc.h>
+#include <linux/err.h>
+#include <linux/module.h>
+#include <net/ip.h>
+#include <net/xfrm.h>
+#include <net/esp.h>
+#include <linux/scatterlist.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <net/ip6_route.h>
+#include <net/ipv6.h>
+#include <linux/icmpv6.h>
+
+static struct sk_buff **esp6_gro_receive(struct sk_buff **head,
+					 struct sk_buff *skb)
+{
+	int err;
+	__be32 seq;
+	__be32 spi;
+	struct xfrm_state *x;
+	int offset = skb_gro_offset(skb);
+
+	skb_pull(skb, offset);
+
+	if ((err = xfrm_parse_spi(skb, IPPROTO_ESP, &spi, &seq)) != 0)
+		goto out;
+
+	err = secpath_set(skb);
+	if (err)
+		goto out;
+
+	if (skb->sp->len == XFRM_MAX_DEPTH)
+		goto out;
+
+	x = xfrm_state_lookup(dev_net(skb->dev), skb->mark,
+			      (xfrm_address_t *)&ipv6_hdr(skb)->daddr,
+			      spi, IPPROTO_ESP, AF_INET6);
+	if (!x)
+		goto out;
+
+	XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = NULL;
+	XFRM_SPI_SKB_CB(skb)->family = AF_INET6;
+	XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct ipv6hdr, daddr);
+	XFRM_GRO_SKB_CB(skb)->gro.input.seq = seq;
+	skb->sp->xvec[skb->sp->len++] = x;
+
+	/* We don't need to handle errors from xfrm_input, it does all
+	 * the error handling and frees the resources on error. */
+	xfrm_input(skb, IPPROTO_ESP, spi, -2);
+
+	return ERR_PTR(-EINPROGRESS);
+out:
+	skb_push(skb, offset);
+	NAPI_GRO_CB(skb)->same_flow = 0;
+	NAPI_GRO_CB(skb)->flush = 1;
+
+	return NULL;
+}
+
+static const struct net_offload esp6_offload = {
+	.callbacks = {
+		.gro_receive = esp6_gro_receive,
+	},
+};
+
+static int __init esp6_offload_init(void)
+{
+	return inet6_add_offload(&esp6_offload, IPPROTO_ESP);
+}
+
+static void __exit esp6_offload_exit(void)
+{
+	inet6_del_offload(&esp6_offload, IPPROTO_ESP);
+}
+
+module_init(esp6_offload_init);
+module_exit(esp6_offload_exit);
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Steffen Klassert <steffen.klassert@...unet.com>");
diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c
index 662fb2c..43373be 100644
--- a/net/ipv6/xfrm6_input.c
+++ b/net/ipv6/xfrm6_input.c
@@ -44,6 +44,11 @@ int xfrm6_transport_finish(struct sk_buff *skb, int async)
 	ipv6_hdr(skb)->payload_len = htons(skb->len);
 	__skb_push(skb, skb->data - skb_network_header(skb));
 
+	if (XFRM_GRO_SKB_CB(skb)->gro.input.skb_is_gro) {
+		skb_mac_header_rebuild(skb);
+		return -1;
+	}
+
 	NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING,
 		dev_net(skb->dev), NULL, skb, skb->dev, NULL,
 		ip6_rcv_finish);
diff --git a/net/ipv6/xfrm6_mode_transport.c b/net/ipv6/xfrm6_mode_transport.c
index 4e34410..11a6186 100644
--- a/net/ipv6/xfrm6_mode_transport.c
+++ b/net/ipv6/xfrm6_mode_transport.c
@@ -55,7 +55,8 @@ static int xfrm6_transport_input(struct xfrm_state *x, struct sk_buff *skb)
 	}
 	ipv6_hdr(skb)->payload_len = htons(skb->len + ihl -
 					   sizeof(struct ipv6hdr));
-	skb_reset_transport_header(skb);
+	if (!(XFRM_GRO_SKB_CB(skb)->gro.input.skb_is_gro))
+		skb_reset_transport_header(skb);
 	return 0;
 }
 
diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
index 538d338..762547e 100644
--- a/net/xfrm/xfrm_input.c
+++ b/net/xfrm/xfrm_input.c
@@ -215,14 +215,24 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
 	unsigned int family;
 	int decaps = 0;
 	int async = 0;
+	bool xfrm_gro = false;
 
-	/* A negative encap_type indicates async resumption. */
 	if (encap_type < 0) {
-		async = 1;
 		x = xfrm_input_state(skb);
-		seq = XFRM_SKB_CB(skb)->seq.input.low;
 		family = x->outer_mode->afinfo->family;
-		goto resume;
+
+		/* An encap_type of -1 indicates async resumption. */
+		if (encap_type == -1) {
+			async = 1;
+			seq = XFRM_SKB_CB(skb)->seq.input.low;
+			xfrm_gro = XFRM_GRO_SKB_CB(skb)->gro.input.skb_is_gro;
+			goto resume;
+		}
+		/* encap_type < -1 indicates a GRO call. */
+		xfrm_gro = true;
+		encap_type = 0;
+		seq = XFRM_GRO_SKB_CB(skb)->gro.input.seq;
+		goto lock;
 	}
 
 	daddr = (xfrm_address_t *)(skb_network_header(skb) +
@@ -268,6 +278,7 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
 
 		skb->sp->xvec[skb->sp->len++] = x;
 
+lock:
 		spin_lock(&x->lock);
 
 		if (unlikely(x->km.state != XFRM_STATE_VALID)) {
@@ -305,6 +316,10 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
 
 		XFRM_SKB_CB(skb)->seq.input.low = seq;
 		XFRM_SKB_CB(skb)->seq.input.hi = seq_hi;
+		XFRM_GRO_SKB_CB(skb)->gro.input.skb_is_gro = false;
+
+		if (xfrm_gro)
+			XFRM_GRO_SKB_CB(skb)->gro.input.skb_is_gro = true;
 
 		skb_dst_force(skb);
 		dev_hold(skb->dev);
@@ -389,7 +404,14 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
 		gro_cells_receive(&gro_cells, skb);
 		return 0;
 	} else {
-		return x->inner_mode->afinfo->transport_finish(skb, async);
+		err = x->inner_mode->afinfo->transport_finish(skb, async);
+		if (xfrm_gro) {
+			skb_dst_drop(skb);
+			gro_cells_receive(&gro_cells, skb);
+			return err;
+		}
+
+		return err;
 	}
 
 drop_unlock:
-- 
1.9.1

Powered by blists - more mailing lists