linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
* [PATCH net-next v8] net: openvswitch: IPv6: Add IPv6 extension header support
@ 2021-10-29 18:20 Toms Atteka
  2021-11-02 18:39 ` Jakub Kicinski
  0 siblings, 1 reply; 12+ messages in thread
From: Toms Atteka @ 2021-10-29 18:20 UTC (permalink / raw)
  To: netdev, pshelar, davem, kuba, dev, linux-kernel; +Cc: Toms Atteka

This change adds a new OpenFlow field OFPXMT_OFB_IPV6_EXTHDR and
packets can be filtered using ipv6_ext flag.

Signed-off-by: Toms Atteka <cpp.code.lv@gmail.com>
---
 include/uapi/linux/openvswitch.h |   6 ++
 net/openvswitch/flow.c           | 140 +++++++++++++++++++++++++++++++
 net/openvswitch/flow.h           |  14 ++++
 net/openvswitch/flow_netlink.c   |  26 +++++-
 4 files changed, 184 insertions(+), 2 deletions(-)

diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h
index a87b44cd5590..43790f07e4a2 100644
--- a/include/uapi/linux/openvswitch.h
+++ b/include/uapi/linux/openvswitch.h
@@ -342,6 +342,7 @@ enum ovs_key_attr {
 	OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4,   /* struct ovs_key_ct_tuple_ipv4 */
 	OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6,   /* struct ovs_key_ct_tuple_ipv6 */
 	OVS_KEY_ATTR_NSH,       /* Nested set of ovs_nsh_key_* */
+	OVS_KEY_ATTR_IPV6_EXTHDRS,  /* struct ovs_key_ipv6_exthdr */
 
 #ifdef __KERNEL__
 	OVS_KEY_ATTR_TUNNEL_INFO,  /* struct ip_tunnel_info */
@@ -421,6 +422,11 @@ struct ovs_key_ipv6 {
 	__u8   ipv6_frag;	/* One of OVS_FRAG_TYPE_*. */
 };
 
+/* separate structure to support backward compatibility with older user space */
+struct ovs_key_ipv6_exthdrs {
+	__u16  hdrs;
+};
+
 struct ovs_key_tcp {
 	__be16 tcp_src;
 	__be16 tcp_dst;
diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index 9d375e74b607..28acb40437ca 100644
--- a/net/openvswitch/flow.c
+++ b/net/openvswitch/flow.c
@@ -239,6 +239,144 @@ static bool icmphdr_ok(struct sk_buff *skb)
 				  sizeof(struct icmphdr));
 }
 
+/**
+ * get_ipv6_ext_hdrs() - Parses packet and sets IPv6 extension header flags.
+ *
+ * @skb: buffer where extension header data starts in packet
+ * @nh: ipv6 header
+ * @ext_hdrs: flags are stored here
+ *
+ * OFPIEH12_UNREP is set if more than one of a given IPv6 extension header
+ * is unexpectedly encountered. (Two destination options headers may be
+ * expected and would not cause this bit to be set.)
+ *
+ * OFPIEH12_UNSEQ is set if IPv6 extension headers were not in the order
+ * preferred (but not required) by RFC 2460:
+ *
+ * When more than one extension header is used in the same packet, it is
+ * recommended that those headers appear in the following order:
+ *      IPv6 header
+ *      Hop-by-Hop Options header
+ *      Destination Options header
+ *      Routing header
+ *      Fragment header
+ *      Authentication header
+ *      Encapsulating Security Payload header
+ *      Destination Options header
+ *      upper-layer header
+ */
+static void get_ipv6_ext_hdrs(struct sk_buff *skb, struct ipv6hdr *nh,
+			      u16 *ext_hdrs)
+{
+	u8 next_type = nh->nexthdr;
+	unsigned int start = skb_network_offset(skb) + sizeof(struct ipv6hdr);
+	int dest_options_header_count = 0;
+
+	*ext_hdrs = 0;
+
+	while (ipv6_ext_hdr(next_type)) {
+		struct ipv6_opt_hdr _hdr, *hp;
+
+		switch (next_type) {
+		case IPPROTO_NONE:
+			*ext_hdrs |= OFPIEH12_NONEXT;
+			/* stop parsing */
+			return;
+
+		case IPPROTO_ESP:
+			if (*ext_hdrs & OFPIEH12_ESP)
+				*ext_hdrs |= OFPIEH12_UNREP;
+			if ((*ext_hdrs & ~(OFPIEH12_HOP | OFPIEH12_DEST |
+					   OFPIEH12_ROUTER | IPPROTO_FRAGMENT |
+					   OFPIEH12_AUTH | OFPIEH12_UNREP)) ||
+			    dest_options_header_count >= 2) {
+				*ext_hdrs |= OFPIEH12_UNSEQ;
+			}
+			*ext_hdrs |= OFPIEH12_ESP;
+			break;
+
+		case IPPROTO_AH:
+			if (*ext_hdrs & OFPIEH12_AUTH)
+				*ext_hdrs |= OFPIEH12_UNREP;
+			if ((*ext_hdrs &
+			     ~(OFPIEH12_HOP | OFPIEH12_DEST | OFPIEH12_ROUTER |
+			       IPPROTO_FRAGMENT | OFPIEH12_UNREP)) ||
+			    dest_options_header_count >= 2) {
+				*ext_hdrs |= OFPIEH12_UNSEQ;
+			}
+			*ext_hdrs |= OFPIEH12_AUTH;
+			break;
+
+		case IPPROTO_DSTOPTS:
+			if (dest_options_header_count == 0) {
+				if (*ext_hdrs &
+				    ~(OFPIEH12_HOP | OFPIEH12_UNREP))
+					*ext_hdrs |= OFPIEH12_UNSEQ;
+				*ext_hdrs |= OFPIEH12_DEST;
+			} else if (dest_options_header_count == 1) {
+				if (*ext_hdrs &
+				    ~(OFPIEH12_HOP | OFPIEH12_DEST |
+				      OFPIEH12_ROUTER | OFPIEH12_FRAG |
+				      OFPIEH12_AUTH | OFPIEH12_ESP |
+				      OFPIEH12_UNREP)) {
+					*ext_hdrs |= OFPIEH12_UNSEQ;
+				}
+			} else {
+				*ext_hdrs |= OFPIEH12_UNREP;
+			}
+			dest_options_header_count++;
+			break;
+
+		case IPPROTO_FRAGMENT:
+			if (*ext_hdrs & OFPIEH12_FRAG)
+				*ext_hdrs |= OFPIEH12_UNREP;
+			if ((*ext_hdrs & ~(OFPIEH12_HOP |
+					   OFPIEH12_DEST |
+					   OFPIEH12_ROUTER |
+					   OFPIEH12_UNREP)) ||
+			    dest_options_header_count >= 2) {
+				*ext_hdrs |= OFPIEH12_UNSEQ;
+			}
+			*ext_hdrs |= OFPIEH12_FRAG;
+			break;
+
+		case IPPROTO_ROUTING:
+			if (*ext_hdrs & OFPIEH12_ROUTER)
+				*ext_hdrs |= OFPIEH12_UNREP;
+			if ((*ext_hdrs & ~(OFPIEH12_HOP |
+					   OFPIEH12_DEST |
+					   OFPIEH12_UNREP)) ||
+			    dest_options_header_count >= 2) {
+				*ext_hdrs |= OFPIEH12_UNSEQ;
+			}
+			*ext_hdrs |= OFPIEH12_ROUTER;
+			break;
+
+		case IPPROTO_HOPOPTS:
+			if (*ext_hdrs & OFPIEH12_HOP)
+				*ext_hdrs |= OFPIEH12_UNREP;
+			/* OFPIEH12_HOP is set to 1 if a hop-by-hop IPv6
+			 * extension header is present as the first
+			 * extension header in the packet.
+			 */
+			if (*ext_hdrs == 0)
+				*ext_hdrs |= OFPIEH12_HOP;
+			else
+				*ext_hdrs |= OFPIEH12_UNSEQ;
+			break;
+
+		default:
+			return;
+		}
+
+		hp = skb_header_pointer(skb, start, sizeof(_hdr), &_hdr);
+		if (!hp)
+			break;
+		next_type = hp->nexthdr;
+		start += ipv6_optlen(hp);
+	};
+}
+
 static int parse_ipv6hdr(struct sk_buff *skb, struct sw_flow_key *key)
 {
 	unsigned short frag_off;
@@ -254,6 +392,8 @@ static int parse_ipv6hdr(struct sk_buff *skb, struct sw_flow_key *key)
 
 	nh = ipv6_hdr(skb);
 
+	get_ipv6_ext_hdrs(skb, nh, &key->ipv6.exthdrs);
+
 	key->ip.proto = NEXTHDR_NONE;
 	key->ip.tos = ipv6_get_dsfield(nh);
 	key->ip.ttl = nh->hop_limit;
diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h
index 758a8c77f736..073ab73ffeaa 100644
--- a/net/openvswitch/flow.h
+++ b/net/openvswitch/flow.h
@@ -32,6 +32,19 @@ enum sw_flow_mac_proto {
 #define SW_FLOW_KEY_INVALID	0x80
 #define MPLS_LABEL_DEPTH       3
 
+/* Bit definitions for IPv6 Extension Header pseudo-field. */
+enum ofp12_ipv6exthdr_flags {
+	OFPIEH12_NONEXT = 1 << 0,   /* "No next header" encountered. */
+	OFPIEH12_ESP    = 1 << 1,   /* Encrypted Sec Payload header present. */
+	OFPIEH12_AUTH   = 1 << 2,   /* Authentication header present. */
+	OFPIEH12_DEST   = 1 << 3,   /* 1 or 2 dest headers present. */
+	OFPIEH12_FRAG   = 1 << 4,   /* Fragment header present. */
+	OFPIEH12_ROUTER = 1 << 5,   /* Router header present. */
+	OFPIEH12_HOP    = 1 << 6,   /* Hop-by-hop header present. */
+	OFPIEH12_UNREP  = 1 << 7,   /* Unexpected repeats encountered. */
+	OFPIEH12_UNSEQ  = 1 << 8    /* Unexpected sequencing encountered. */
+};
+
 /* Store options at the end of the array if they are less than the
  * maximum size. This allows us to get the benefits of variable length
  * matching for small options.
@@ -121,6 +134,7 @@ struct sw_flow_key {
 				struct in6_addr dst;	/* IPv6 destination address. */
 			} addr;
 			__be32 label;			/* IPv6 flow label. */
+			u16 exthdrs;	/* IPv6 extension header flags */
 			union {
 				struct {
 					struct in6_addr src;
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index 65c2e3458ff5..0aeaf28594ce 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -344,7 +344,7 @@ size_t ovs_key_attr_size(void)
 	/* Whenever adding new OVS_KEY_ FIELDS, we should consider
 	 * updating this function.
 	 */
-	BUILD_BUG_ON(OVS_KEY_ATTR_TUNNEL_INFO != 29);
+	BUILD_BUG_ON(OVS_KEY_ATTR_TUNNEL_INFO != 30);
 
 	return    nla_total_size(4)   /* OVS_KEY_ATTR_PRIORITY */
 		+ nla_total_size(0)   /* OVS_KEY_ATTR_TUNNEL */
@@ -367,7 +367,8 @@ size_t ovs_key_attr_size(void)
 		+ nla_total_size(2)   /* OVS_KEY_ATTR_ETHERTYPE */
 		+ nla_total_size(40)  /* OVS_KEY_ATTR_IPV6 */
 		+ nla_total_size(2)   /* OVS_KEY_ATTR_ICMPV6 */
-		+ nla_total_size(28); /* OVS_KEY_ATTR_ND */
+		+ nla_total_size(28)  /* OVS_KEY_ATTR_ND */
+		+ nla_total_size(2);  /* OVS_KEY_ATTR_IPV6_EXTHDRS */
 }
 
 static const struct ovs_len_tbl ovs_vxlan_ext_key_lens[OVS_VXLAN_EXT_MAX + 1] = {
@@ -435,6 +436,8 @@ static const struct ovs_len_tbl ovs_key_lens[OVS_KEY_ATTR_MAX + 1] = {
 		.len = sizeof(struct ovs_key_ct_tuple_ipv6) },
 	[OVS_KEY_ATTR_NSH]       = { .len = OVS_ATTR_NESTED,
 				     .next = ovs_nsh_key_attr_lens, },
+	[OVS_KEY_ATTR_IPV6_EXTHDRS] = {
+		.len = sizeof(struct ovs_key_ipv6_exthdrs) },
 };
 
 static bool check_attr_len(unsigned int attr_len, unsigned int expected_len)
@@ -1595,6 +1598,17 @@ static int ovs_key_from_nlattrs(struct net *net, struct sw_flow_match *match,
 		attrs &= ~(1 << OVS_KEY_ATTR_IPV6);
 	}
 
+	if (attrs & (1ULL << OVS_KEY_ATTR_IPV6_EXTHDRS)) {
+		const struct ovs_key_ipv6_exthdrs *ipv6_exthdrs_key;
+
+		ipv6_exthdrs_key = nla_data(a[OVS_KEY_ATTR_IPV6_EXTHDRS]);
+
+		SW_FLOW_KEY_PUT(match, ipv6.exthdrs,
+				ipv6_exthdrs_key->hdrs, is_mask);
+
+		attrs &= ~(1ULL << OVS_KEY_ATTR_IPV6_EXTHDRS);
+	}
+
 	if (attrs & (1 << OVS_KEY_ATTR_ARP)) {
 		const struct ovs_key_arp *arp_key;
 
@@ -2097,6 +2111,7 @@ static int __ovs_nla_put_key(const struct sw_flow_key *swkey,
 		ipv4_key->ipv4_frag = output->ip.frag;
 	} else if (swkey->eth.type == htons(ETH_P_IPV6)) {
 		struct ovs_key_ipv6 *ipv6_key;
+		struct ovs_key_ipv6_exthdrs *ipv6_exthdrs_key;
 
 		nla = nla_reserve(skb, OVS_KEY_ATTR_IPV6, sizeof(*ipv6_key));
 		if (!nla)
@@ -2111,6 +2126,13 @@ static int __ovs_nla_put_key(const struct sw_flow_key *swkey,
 		ipv6_key->ipv6_tclass = output->ip.tos;
 		ipv6_key->ipv6_hlimit = output->ip.ttl;
 		ipv6_key->ipv6_frag = output->ip.frag;
+
+		nla = nla_reserve(skb, OVS_KEY_ATTR_IPV6_EXTHDRS,
+				  sizeof(*ipv6_exthdrs_key));
+		if (!nla)
+			goto nla_put_failure;
+		ipv6_exthdrs_key = nla_data(nla);
+		ipv6_exthdrs_key->hdrs = output->ipv6.exthdrs;
 	} else if (swkey->eth.type == htons(ETH_P_NSH)) {
 		if (nsh_key_to_nlattr(&output->nsh, is_mask, skb))
 			goto nla_put_failure;
-- 
2.25.1


^ permalink raw reply related	[flat|nested] 12+ messages in thread

* Re: [PATCH net-next v8] net: openvswitch: IPv6: Add IPv6 extension header support
  2021-10-29 18:20 [PATCH net-next v8] net: openvswitch: IPv6: Add IPv6 extension header support Toms Atteka
@ 2021-11-02 18:39 ` Jakub Kicinski
  0 siblings, 0 replies; 12+ messages in thread
From: Jakub Kicinski @ 2021-11-02 18:39 UTC (permalink / raw)
  To: Toms Atteka; +Cc: netdev, pshelar, davem, dev, linux-kernel

On Fri, 29 Oct 2021 11:20:08 -0700 Toms Atteka wrote:
> This change adds a new OpenFlow field OFPXMT_OFB_IPV6_EXTHDR and
> packets can be filtered using ipv6_ext flag.
> 
> Signed-off-by: Toms Atteka <cpp.code.lv@gmail.com>

Hi! This patch didn't get reviewed in time for the v5.16 merge window,
please continue the work but you'll have to repost in two weeks after
v5.16-rc1 has been cut. If you repost before that point please use RFC
designation.

^ permalink raw reply	[flat|nested] 12+ messages in thread

* Re: [PATCH net-next v8] net: openvswitch: IPv6: Add IPv6 extension header support
  2022-02-24  0:54 Toms Atteka
@ 2022-02-25 10:40 ` patchwork-bot+netdevbpf
  0 siblings, 0 replies; 12+ messages in thread
From: patchwork-bot+netdevbpf @ 2022-02-25 10:40 UTC (permalink / raw)
  To: Toms Atteka; +Cc: netdev, pshelar, davem, kuba, dev, linux-kernel

Hello:

This patch was applied to netdev/net-next.git (master)
by David S. Miller <davem@davemloft.net>:

On Wed, 23 Feb 2022 16:54:09 -0800 you wrote:
> This change adds a new OpenFlow field OFPXMT_OFB_IPV6_EXTHDR and
> packets can be filtered using ipv6_ext flag.
> 
> Signed-off-by: Toms Atteka <cpp.code.lv@gmail.com>
> Acked-by: Pravin B Shelar <pshelar@ovn.org>
> ---
>  include/uapi/linux/openvswitch.h |   6 ++
>  net/openvswitch/flow.c           | 140 +++++++++++++++++++++++++++++++
>  net/openvswitch/flow.h           |  14 ++++
>  net/openvswitch/flow_netlink.c   |  26 +++++-
>  4 files changed, 184 insertions(+), 2 deletions(-)

Here is the summary with links:
  - [net-next,v8] net: openvswitch: IPv6: Add IPv6 extension header support
    https://git.kernel.org/netdev/net-next/c/28a3f0601727

You are awesome, thank you!
-- 
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/patchwork/pwbot.html



^ permalink raw reply	[flat|nested] 12+ messages in thread

* [PATCH net-next v8] net: openvswitch: IPv6: Add IPv6 extension header support
@ 2022-02-24  0:54 Toms Atteka
  2022-02-25 10:40 ` patchwork-bot+netdevbpf
  0 siblings, 1 reply; 12+ messages in thread
From: Toms Atteka @ 2022-02-24  0:54 UTC (permalink / raw)
  To: netdev, pshelar, davem, kuba, dev, linux-kernel; +Cc: Toms Atteka

This change adds a new OpenFlow field OFPXMT_OFB_IPV6_EXTHDR and
packets can be filtered using ipv6_ext flag.

Signed-off-by: Toms Atteka <cpp.code.lv@gmail.com>
Acked-by: Pravin B Shelar <pshelar@ovn.org>
---
 include/uapi/linux/openvswitch.h |   6 ++
 net/openvswitch/flow.c           | 140 +++++++++++++++++++++++++++++++
 net/openvswitch/flow.h           |  14 ++++
 net/openvswitch/flow_netlink.c   |  26 +++++-
 4 files changed, 184 insertions(+), 2 deletions(-)

diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h
index 150bcff49b1c..9d1710f20505 100644
--- a/include/uapi/linux/openvswitch.h
+++ b/include/uapi/linux/openvswitch.h
@@ -351,6 +351,7 @@ enum ovs_key_attr {
 	OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4,   /* struct ovs_key_ct_tuple_ipv4 */
 	OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6,   /* struct ovs_key_ct_tuple_ipv6 */
 	OVS_KEY_ATTR_NSH,       /* Nested set of ovs_nsh_key_* */
+	OVS_KEY_ATTR_IPV6_EXTHDRS,  /* struct ovs_key_ipv6_exthdr */
 
 #ifdef __KERNEL__
 	OVS_KEY_ATTR_TUNNEL_INFO,  /* struct ip_tunnel_info */
@@ -430,6 +431,11 @@ struct ovs_key_ipv6 {
 	__u8   ipv6_frag;	/* One of OVS_FRAG_TYPE_*. */
 };
 
+/* separate structure to support backward compatibility with older user space */
+struct ovs_key_ipv6_exthdrs {
+	__u16  hdrs;
+};
+
 struct ovs_key_tcp {
 	__be16 tcp_src;
 	__be16 tcp_dst;
diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index f6cd24fd530c..8df73d86b968 100644
--- a/net/openvswitch/flow.c
+++ b/net/openvswitch/flow.c
@@ -241,6 +241,144 @@ static bool icmphdr_ok(struct sk_buff *skb)
 				  sizeof(struct icmphdr));
 }
 
+/**
+ * get_ipv6_ext_hdrs() - Parses packet and sets IPv6 extension header flags.
+ *
+ * @skb: buffer where extension header data starts in packet
+ * @nh: ipv6 header
+ * @ext_hdrs: flags are stored here
+ *
+ * OFPIEH12_UNREP is set if more than one of a given IPv6 extension header
+ * is unexpectedly encountered. (Two destination options headers may be
+ * expected and would not cause this bit to be set.)
+ *
+ * OFPIEH12_UNSEQ is set if IPv6 extension headers were not in the order
+ * preferred (but not required) by RFC 2460:
+ *
+ * When more than one extension header is used in the same packet, it is
+ * recommended that those headers appear in the following order:
+ *      IPv6 header
+ *      Hop-by-Hop Options header
+ *      Destination Options header
+ *      Routing header
+ *      Fragment header
+ *      Authentication header
+ *      Encapsulating Security Payload header
+ *      Destination Options header
+ *      upper-layer header
+ */
+static void get_ipv6_ext_hdrs(struct sk_buff *skb, struct ipv6hdr *nh,
+			      u16 *ext_hdrs)
+{
+	u8 next_type = nh->nexthdr;
+	unsigned int start = skb_network_offset(skb) + sizeof(struct ipv6hdr);
+	int dest_options_header_count = 0;
+
+	*ext_hdrs = 0;
+
+	while (ipv6_ext_hdr(next_type)) {
+		struct ipv6_opt_hdr _hdr, *hp;
+
+		switch (next_type) {
+		case IPPROTO_NONE:
+			*ext_hdrs |= OFPIEH12_NONEXT;
+			/* stop parsing */
+			return;
+
+		case IPPROTO_ESP:
+			if (*ext_hdrs & OFPIEH12_ESP)
+				*ext_hdrs |= OFPIEH12_UNREP;
+			if ((*ext_hdrs & ~(OFPIEH12_HOP | OFPIEH12_DEST |
+					   OFPIEH12_ROUTER | IPPROTO_FRAGMENT |
+					   OFPIEH12_AUTH | OFPIEH12_UNREP)) ||
+			    dest_options_header_count >= 2) {
+				*ext_hdrs |= OFPIEH12_UNSEQ;
+			}
+			*ext_hdrs |= OFPIEH12_ESP;
+			break;
+
+		case IPPROTO_AH:
+			if (*ext_hdrs & OFPIEH12_AUTH)
+				*ext_hdrs |= OFPIEH12_UNREP;
+			if ((*ext_hdrs &
+			     ~(OFPIEH12_HOP | OFPIEH12_DEST | OFPIEH12_ROUTER |
+			       IPPROTO_FRAGMENT | OFPIEH12_UNREP)) ||
+			    dest_options_header_count >= 2) {
+				*ext_hdrs |= OFPIEH12_UNSEQ;
+			}
+			*ext_hdrs |= OFPIEH12_AUTH;
+			break;
+
+		case IPPROTO_DSTOPTS:
+			if (dest_options_header_count == 0) {
+				if (*ext_hdrs &
+				    ~(OFPIEH12_HOP | OFPIEH12_UNREP))
+					*ext_hdrs |= OFPIEH12_UNSEQ;
+				*ext_hdrs |= OFPIEH12_DEST;
+			} else if (dest_options_header_count == 1) {
+				if (*ext_hdrs &
+				    ~(OFPIEH12_HOP | OFPIEH12_DEST |
+				      OFPIEH12_ROUTER | OFPIEH12_FRAG |
+				      OFPIEH12_AUTH | OFPIEH12_ESP |
+				      OFPIEH12_UNREP)) {
+					*ext_hdrs |= OFPIEH12_UNSEQ;
+				}
+			} else {
+				*ext_hdrs |= OFPIEH12_UNREP;
+			}
+			dest_options_header_count++;
+			break;
+
+		case IPPROTO_FRAGMENT:
+			if (*ext_hdrs & OFPIEH12_FRAG)
+				*ext_hdrs |= OFPIEH12_UNREP;
+			if ((*ext_hdrs & ~(OFPIEH12_HOP |
+					   OFPIEH12_DEST |
+					   OFPIEH12_ROUTER |
+					   OFPIEH12_UNREP)) ||
+			    dest_options_header_count >= 2) {
+				*ext_hdrs |= OFPIEH12_UNSEQ;
+			}
+			*ext_hdrs |= OFPIEH12_FRAG;
+			break;
+
+		case IPPROTO_ROUTING:
+			if (*ext_hdrs & OFPIEH12_ROUTER)
+				*ext_hdrs |= OFPIEH12_UNREP;
+			if ((*ext_hdrs & ~(OFPIEH12_HOP |
+					   OFPIEH12_DEST |
+					   OFPIEH12_UNREP)) ||
+			    dest_options_header_count >= 2) {
+				*ext_hdrs |= OFPIEH12_UNSEQ;
+			}
+			*ext_hdrs |= OFPIEH12_ROUTER;
+			break;
+
+		case IPPROTO_HOPOPTS:
+			if (*ext_hdrs & OFPIEH12_HOP)
+				*ext_hdrs |= OFPIEH12_UNREP;
+			/* OFPIEH12_HOP is set to 1 if a hop-by-hop IPv6
+			 * extension header is present as the first
+			 * extension header in the packet.
+			 */
+			if (*ext_hdrs == 0)
+				*ext_hdrs |= OFPIEH12_HOP;
+			else
+				*ext_hdrs |= OFPIEH12_UNSEQ;
+			break;
+
+		default:
+			return;
+		}
+
+		hp = skb_header_pointer(skb, start, sizeof(_hdr), &_hdr);
+		if (!hp)
+			break;
+		next_type = hp->nexthdr;
+		start += ipv6_optlen(hp);
+	};
+}
+
 static int parse_ipv6hdr(struct sk_buff *skb, struct sw_flow_key *key)
 {
 	unsigned short frag_off;
@@ -256,6 +394,8 @@ static int parse_ipv6hdr(struct sk_buff *skb, struct sw_flow_key *key)
 
 	nh = ipv6_hdr(skb);
 
+	get_ipv6_ext_hdrs(skb, nh, &key->ipv6.exthdrs);
+
 	key->ip.proto = NEXTHDR_NONE;
 	key->ip.tos = ipv6_get_dsfield(nh);
 	key->ip.ttl = nh->hop_limit;
diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h
index 758a8c77f736..073ab73ffeaa 100644
--- a/net/openvswitch/flow.h
+++ b/net/openvswitch/flow.h
@@ -32,6 +32,19 @@ enum sw_flow_mac_proto {
 #define SW_FLOW_KEY_INVALID	0x80
 #define MPLS_LABEL_DEPTH       3
 
+/* Bit definitions for IPv6 Extension Header pseudo-field. */
+enum ofp12_ipv6exthdr_flags {
+	OFPIEH12_NONEXT = 1 << 0,   /* "No next header" encountered. */
+	OFPIEH12_ESP    = 1 << 1,   /* Encrypted Sec Payload header present. */
+	OFPIEH12_AUTH   = 1 << 2,   /* Authentication header present. */
+	OFPIEH12_DEST   = 1 << 3,   /* 1 or 2 dest headers present. */
+	OFPIEH12_FRAG   = 1 << 4,   /* Fragment header present. */
+	OFPIEH12_ROUTER = 1 << 5,   /* Router header present. */
+	OFPIEH12_HOP    = 1 << 6,   /* Hop-by-hop header present. */
+	OFPIEH12_UNREP  = 1 << 7,   /* Unexpected repeats encountered. */
+	OFPIEH12_UNSEQ  = 1 << 8    /* Unexpected sequencing encountered. */
+};
+
 /* Store options at the end of the array if they are less than the
  * maximum size. This allows us to get the benefits of variable length
  * matching for small options.
@@ -121,6 +134,7 @@ struct sw_flow_key {
 				struct in6_addr dst;	/* IPv6 destination address. */
 			} addr;
 			__be32 label;			/* IPv6 flow label. */
+			u16 exthdrs;	/* IPv6 extension header flags */
 			union {
 				struct {
 					struct in6_addr src;
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index fd1f809e9bc1..8b4124820f7d 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -346,7 +346,7 @@ size_t ovs_key_attr_size(void)
 	/* Whenever adding new OVS_KEY_ FIELDS, we should consider
 	 * updating this function.
 	 */
-	BUILD_BUG_ON(OVS_KEY_ATTR_TUNNEL_INFO != 29);
+	BUILD_BUG_ON(OVS_KEY_ATTR_TUNNEL_INFO != 30);
 
 	return    nla_total_size(4)   /* OVS_KEY_ATTR_PRIORITY */
 		+ nla_total_size(0)   /* OVS_KEY_ATTR_TUNNEL */
@@ -369,7 +369,8 @@ size_t ovs_key_attr_size(void)
 		+ nla_total_size(2)   /* OVS_KEY_ATTR_ETHERTYPE */
 		+ nla_total_size(40)  /* OVS_KEY_ATTR_IPV6 */
 		+ nla_total_size(2)   /* OVS_KEY_ATTR_ICMPV6 */
-		+ nla_total_size(28); /* OVS_KEY_ATTR_ND */
+		+ nla_total_size(28)  /* OVS_KEY_ATTR_ND */
+		+ nla_total_size(2);  /* OVS_KEY_ATTR_IPV6_EXTHDRS */
 }
 
 static const struct ovs_len_tbl ovs_vxlan_ext_key_lens[OVS_VXLAN_EXT_MAX + 1] = {
@@ -437,6 +438,8 @@ static const struct ovs_len_tbl ovs_key_lens[OVS_KEY_ATTR_MAX + 1] = {
 		.len = sizeof(struct ovs_key_ct_tuple_ipv6) },
 	[OVS_KEY_ATTR_NSH]       = { .len = OVS_ATTR_NESTED,
 				     .next = ovs_nsh_key_attr_lens, },
+	[OVS_KEY_ATTR_IPV6_EXTHDRS] = {
+		.len = sizeof(struct ovs_key_ipv6_exthdrs) },
 };
 
 static bool check_attr_len(unsigned int attr_len, unsigned int expected_len)
@@ -1597,6 +1600,17 @@ static int ovs_key_from_nlattrs(struct net *net, struct sw_flow_match *match,
 		attrs &= ~(1 << OVS_KEY_ATTR_IPV6);
 	}
 
+	if (attrs & (1ULL << OVS_KEY_ATTR_IPV6_EXTHDRS)) {
+		const struct ovs_key_ipv6_exthdrs *ipv6_exthdrs_key;
+
+		ipv6_exthdrs_key = nla_data(a[OVS_KEY_ATTR_IPV6_EXTHDRS]);
+
+		SW_FLOW_KEY_PUT(match, ipv6.exthdrs,
+				ipv6_exthdrs_key->hdrs, is_mask);
+
+		attrs &= ~(1ULL << OVS_KEY_ATTR_IPV6_EXTHDRS);
+	}
+
 	if (attrs & (1 << OVS_KEY_ATTR_ARP)) {
 		const struct ovs_key_arp *arp_key;
 
@@ -2099,6 +2113,7 @@ static int __ovs_nla_put_key(const struct sw_flow_key *swkey,
 		ipv4_key->ipv4_frag = output->ip.frag;
 	} else if (swkey->eth.type == htons(ETH_P_IPV6)) {
 		struct ovs_key_ipv6 *ipv6_key;
+		struct ovs_key_ipv6_exthdrs *ipv6_exthdrs_key;
 
 		nla = nla_reserve(skb, OVS_KEY_ATTR_IPV6, sizeof(*ipv6_key));
 		if (!nla)
@@ -2113,6 +2128,13 @@ static int __ovs_nla_put_key(const struct sw_flow_key *swkey,
 		ipv6_key->ipv6_tclass = output->ip.tos;
 		ipv6_key->ipv6_hlimit = output->ip.ttl;
 		ipv6_key->ipv6_frag = output->ip.frag;
+
+		nla = nla_reserve(skb, OVS_KEY_ATTR_IPV6_EXTHDRS,
+				  sizeof(*ipv6_exthdrs_key));
+		if (!nla)
+			goto nla_put_failure;
+		ipv6_exthdrs_key = nla_data(nla);
+		ipv6_exthdrs_key->hdrs = output->ipv6.exthdrs;
 	} else if (swkey->eth.type == htons(ETH_P_NSH)) {
 		if (nsh_key_to_nlattr(&output->nsh, is_mask, skb))
 			goto nla_put_failure;
-- 
2.25.1


^ permalink raw reply related	[flat|nested] 12+ messages in thread

* Re: [PATCH net-next v8] net: openvswitch: IPv6: Add IPv6 extension header support
  2022-02-09 20:46           ` Cpp Code
@ 2022-02-10  0:58             ` Jakub Kicinski
  0 siblings, 0 replies; 12+ messages in thread
From: Jakub Kicinski @ 2022-02-10  0:58 UTC (permalink / raw)
  To: Cpp Code
  Cc: Pravin Shelar, Linux Kernel Network Developers, David S. Miller,
	ovs dev, LKML

On Wed, 9 Feb 2022 12:46:01 -0800 Cpp Code wrote:
> > ok, I see advantage of using skb_header_pointer() in this case, but
> > replacing all check_header() with skb_header_pointer() would add lot
> > of copy operation in flow extract. Anyways for this use case
> > skb_header_pointer() is fine.
> >
> > Acked-by: Pravin B Shelar <pshelar@ovn.org>  
> 
> Could this be applied please.

Please repost with Pravin's ack included.

^ permalink raw reply	[flat|nested] 12+ messages in thread

* Re: [PATCH net-next v8] net: openvswitch: IPv6: Add IPv6 extension header support
  2021-12-10  7:36         ` Pravin Shelar
@ 2022-02-09 20:46           ` Cpp Code
  2022-02-10  0:58             ` Jakub Kicinski
  0 siblings, 1 reply; 12+ messages in thread
From: Cpp Code @ 2022-02-09 20:46 UTC (permalink / raw)
  To: Pravin Shelar
  Cc: Linux Kernel Network Developers, David S. Miller, Jakub Kicinski,
	ovs dev, LKML

On Thu, Dec 9, 2021 at 11:36 PM Pravin Shelar <pravin.ovn@gmail.com> wrote:
>
> ()
>
> On Mon, Dec 6, 2021 at 3:00 PM Cpp Code <cpp.code.lv@gmail.com> wrote:
> >
> > On Thu, Dec 2, 2021 at 9:28 PM Pravin Shelar <pravin.ovn@gmail.com> wrote:
> > >
> > > On Thu, Dec 2, 2021 at 12:20 PM Cpp Code <cpp.code.lv@gmail.com> wrote:
> > > >
> > > > On Wed, Dec 1, 2021 at 11:34 PM Pravin Shelar <pravin.ovn@gmail.com> wrote:
> > > > >
> > > > > On Wed, Nov 24, 2021 at 11:33 AM Toms Atteka <cpp.code.lv@gmail.com> wrote:
> > > > > >
> > > > > > This change adds a new OpenFlow field OFPXMT_OFB_IPV6_EXTHDR and
> > > > > > packets can be filtered using ipv6_ext flag.
> > > > > >
> > > > > > Signed-off-by: Toms Atteka <cpp.code.lv@gmail.com>
> > > > > > ---
> > > > > >  include/uapi/linux/openvswitch.h |   6 ++
> > > > > >  net/openvswitch/flow.c           | 140 +++++++++++++++++++++++++++++++
> > > > > >  net/openvswitch/flow.h           |  14 ++++
> > > > > >  net/openvswitch/flow_netlink.c   |  26 +++++-
> > > > > >  4 files changed, 184 insertions(+), 2 deletions(-)
> > > > > >
> > > > > > diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h
> > > > > > index a87b44cd5590..43790f07e4a2 100644
> > > > > > --- a/include/uapi/linux/openvswitch.h
> > > > > > +++ b/include/uapi/linux/openvswitch.h
> > > > > > @@ -342,6 +342,7 @@ enum ovs_key_attr {
> > > > > >         OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4,   /* struct ovs_key_ct_tuple_ipv4 */
> > > > > >         OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6,   /* struct ovs_key_ct_tuple_ipv6 */
> > > > > >         OVS_KEY_ATTR_NSH,       /* Nested set of ovs_nsh_key_* */
> > > > > > +       OVS_KEY_ATTR_IPV6_EXTHDRS,  /* struct ovs_key_ipv6_exthdr */
> > > > > >
> > > > > >  #ifdef __KERNEL__
> > > > > >         OVS_KEY_ATTR_TUNNEL_INFO,  /* struct ip_tunnel_info */
> > > > > > @@ -421,6 +422,11 @@ struct ovs_key_ipv6 {
> > > > > >         __u8   ipv6_frag;       /* One of OVS_FRAG_TYPE_*. */
> > > > > >  };
> > > > > >
> > > > > > +/* separate structure to support backward compatibility with older user space */
> > > > > > +struct ovs_key_ipv6_exthdrs {
> > > > > > +       __u16  hdrs;
> > > > > > +};
> > > > > > +
> > > > > >  struct ovs_key_tcp {
> > > > > >         __be16 tcp_src;
> > > > > >         __be16 tcp_dst;
> > > > > > diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
> > > > > > index 9d375e74b607..28acb40437ca 100644
> > > > > > --- a/net/openvswitch/flow.c
> > > > > > +++ b/net/openvswitch/flow.c
> > > > > > @@ -239,6 +239,144 @@ static bool icmphdr_ok(struct sk_buff *skb)
> > > > > >                                   sizeof(struct icmphdr));
> > > > > >  }
> > > > > >
> > > > > > +/**
> > > > > > + * get_ipv6_ext_hdrs() - Parses packet and sets IPv6 extension header flags.
> > > > > > + *
> > > > > > + * @skb: buffer where extension header data starts in packet
> > > > > > + * @nh: ipv6 header
> > > > > > + * @ext_hdrs: flags are stored here
> > > > > > + *
> > > > > > + * OFPIEH12_UNREP is set if more than one of a given IPv6 extension header
> > > > > > + * is unexpectedly encountered. (Two destination options headers may be
> > > > > > + * expected and would not cause this bit to be set.)
> > > > > > + *
> > > > > > + * OFPIEH12_UNSEQ is set if IPv6 extension headers were not in the order
> > > > > > + * preferred (but not required) by RFC 2460:
> > > > > > + *
> > > > > > + * When more than one extension header is used in the same packet, it is
> > > > > > + * recommended that those headers appear in the following order:
> > > > > > + *      IPv6 header
> > > > > > + *      Hop-by-Hop Options header
> > > > > > + *      Destination Options header
> > > > > > + *      Routing header
> > > > > > + *      Fragment header
> > > > > > + *      Authentication header
> > > > > > + *      Encapsulating Security Payload header
> > > > > > + *      Destination Options header
> > > > > > + *      upper-layer header
> > > > > > + */
> > > > > > +static void get_ipv6_ext_hdrs(struct sk_buff *skb, struct ipv6hdr *nh,
> > > > > > +                             u16 *ext_hdrs)
> > > > > > +{
> > > > > > +       u8 next_type = nh->nexthdr;
> > > > > > +       unsigned int start = skb_network_offset(skb) + sizeof(struct ipv6hdr);
> > > > > > +       int dest_options_header_count = 0;
> > > > > > +
> > > > > > +       *ext_hdrs = 0;
> > > > > > +
> > > > > > +       while (ipv6_ext_hdr(next_type)) {
> > > > > > +               struct ipv6_opt_hdr _hdr, *hp;
> > > > > > +
> > > > > > +               switch (next_type) {
> > > > > > +               case IPPROTO_NONE:
> > > > > > +                       *ext_hdrs |= OFPIEH12_NONEXT;
> > > > > > +                       /* stop parsing */
> > > > > > +                       return;
> > > > > > +
> > > > > > +               case IPPROTO_ESP:
> > > > > > +                       if (*ext_hdrs & OFPIEH12_ESP)
> > > > > > +                               *ext_hdrs |= OFPIEH12_UNREP;
> > > > > > +                       if ((*ext_hdrs & ~(OFPIEH12_HOP | OFPIEH12_DEST |
> > > > > > +                                          OFPIEH12_ROUTER | IPPROTO_FRAGMENT |
> > > > > > +                                          OFPIEH12_AUTH | OFPIEH12_UNREP)) ||
> > > > > > +                           dest_options_header_count >= 2) {
> > > > > > +                               *ext_hdrs |= OFPIEH12_UNSEQ;
> > > > > > +                       }
> > > > > > +                       *ext_hdrs |= OFPIEH12_ESP;
> > > > > > +                       break;
> > > > > you need to check_header() before looking into each extension header.
> > > >
> > > > Could you elaborate why I need to add check_header(),
> > > > skb_header_pointer() is doing sanitization.
> > >
> > > I mean check_header() would allow you to read the header without
> > > copying the bits, it is used in ovs flow extraction so its usual
> > > check.
> >
> > But check_header() will call *__pskb_pull_tail which in turn will copy
> > bits if data will be fragmented.
> >
> OVS flow extract uses this function to extract flow upto L4, so
> skb_header_pointer() is not saving any copy operation.
>
> > /* Moves tail of skb head forward, copying data from fragmented part,
> >  * when it is necessary.
> >  * 1. It may fail due to malloc failure.
> >  * 2. It may change skb pointers.
> >  *
> >  * It is pretty complicated. Luckily, it is called only in exceptional cases.
> >  */
> > void *__pskb_pull_tail(struct sk_buff *skb, int delta)
> >
> > as well I noticed that for example commit
> > 4a06fa67c4da20148803525151845276cdb995c1 is moving from
> > pskb_may_pull() to skb_header_pointer()
> ok, I see advantage of using skb_header_pointer() in this case, but
> replacing all check_header() with skb_header_pointer() would add lot
> of copy operation in flow extract. Anyways for this use case
> skb_header_pointer() is fine.
>
> Acked-by: Pravin B Shelar <pshelar@ovn.org>

Hi,

Could this be applied please.

Thanks,
Tom

^ permalink raw reply	[flat|nested] 12+ messages in thread

* Re: [PATCH net-next v8] net: openvswitch: IPv6: Add IPv6 extension header support
  2021-12-06 23:00       ` Cpp Code
@ 2021-12-10  7:36         ` Pravin Shelar
  2022-02-09 20:46           ` Cpp Code
  0 siblings, 1 reply; 12+ messages in thread
From: Pravin Shelar @ 2021-12-10  7:36 UTC (permalink / raw)
  To: Cpp Code
  Cc: Linux Kernel Network Developers, David S. Miller, Jakub Kicinski,
	ovs dev, LKML

()

On Mon, Dec 6, 2021 at 3:00 PM Cpp Code <cpp.code.lv@gmail.com> wrote:
>
> On Thu, Dec 2, 2021 at 9:28 PM Pravin Shelar <pravin.ovn@gmail.com> wrote:
> >
> > On Thu, Dec 2, 2021 at 12:20 PM Cpp Code <cpp.code.lv@gmail.com> wrote:
> > >
> > > On Wed, Dec 1, 2021 at 11:34 PM Pravin Shelar <pravin.ovn@gmail.com> wrote:
> > > >
> > > > On Wed, Nov 24, 2021 at 11:33 AM Toms Atteka <cpp.code.lv@gmail.com> wrote:
> > > > >
> > > > > This change adds a new OpenFlow field OFPXMT_OFB_IPV6_EXTHDR and
> > > > > packets can be filtered using ipv6_ext flag.
> > > > >
> > > > > Signed-off-by: Toms Atteka <cpp.code.lv@gmail.com>
> > > > > ---
> > > > >  include/uapi/linux/openvswitch.h |   6 ++
> > > > >  net/openvswitch/flow.c           | 140 +++++++++++++++++++++++++++++++
> > > > >  net/openvswitch/flow.h           |  14 ++++
> > > > >  net/openvswitch/flow_netlink.c   |  26 +++++-
> > > > >  4 files changed, 184 insertions(+), 2 deletions(-)
> > > > >
> > > > > diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h
> > > > > index a87b44cd5590..43790f07e4a2 100644
> > > > > --- a/include/uapi/linux/openvswitch.h
> > > > > +++ b/include/uapi/linux/openvswitch.h
> > > > > @@ -342,6 +342,7 @@ enum ovs_key_attr {
> > > > >         OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4,   /* struct ovs_key_ct_tuple_ipv4 */
> > > > >         OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6,   /* struct ovs_key_ct_tuple_ipv6 */
> > > > >         OVS_KEY_ATTR_NSH,       /* Nested set of ovs_nsh_key_* */
> > > > > +       OVS_KEY_ATTR_IPV6_EXTHDRS,  /* struct ovs_key_ipv6_exthdr */
> > > > >
> > > > >  #ifdef __KERNEL__
> > > > >         OVS_KEY_ATTR_TUNNEL_INFO,  /* struct ip_tunnel_info */
> > > > > @@ -421,6 +422,11 @@ struct ovs_key_ipv6 {
> > > > >         __u8   ipv6_frag;       /* One of OVS_FRAG_TYPE_*. */
> > > > >  };
> > > > >
> > > > > +/* separate structure to support backward compatibility with older user space */
> > > > > +struct ovs_key_ipv6_exthdrs {
> > > > > +       __u16  hdrs;
> > > > > +};
> > > > > +
> > > > >  struct ovs_key_tcp {
> > > > >         __be16 tcp_src;
> > > > >         __be16 tcp_dst;
> > > > > diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
> > > > > index 9d375e74b607..28acb40437ca 100644
> > > > > --- a/net/openvswitch/flow.c
> > > > > +++ b/net/openvswitch/flow.c
> > > > > @@ -239,6 +239,144 @@ static bool icmphdr_ok(struct sk_buff *skb)
> > > > >                                   sizeof(struct icmphdr));
> > > > >  }
> > > > >
> > > > > +/**
> > > > > + * get_ipv6_ext_hdrs() - Parses packet and sets IPv6 extension header flags.
> > > > > + *
> > > > > + * @skb: buffer where extension header data starts in packet
> > > > > + * @nh: ipv6 header
> > > > > + * @ext_hdrs: flags are stored here
> > > > > + *
> > > > > + * OFPIEH12_UNREP is set if more than one of a given IPv6 extension header
> > > > > + * is unexpectedly encountered. (Two destination options headers may be
> > > > > + * expected and would not cause this bit to be set.)
> > > > > + *
> > > > > + * OFPIEH12_UNSEQ is set if IPv6 extension headers were not in the order
> > > > > + * preferred (but not required) by RFC 2460:
> > > > > + *
> > > > > + * When more than one extension header is used in the same packet, it is
> > > > > + * recommended that those headers appear in the following order:
> > > > > + *      IPv6 header
> > > > > + *      Hop-by-Hop Options header
> > > > > + *      Destination Options header
> > > > > + *      Routing header
> > > > > + *      Fragment header
> > > > > + *      Authentication header
> > > > > + *      Encapsulating Security Payload header
> > > > > + *      Destination Options header
> > > > > + *      upper-layer header
> > > > > + */
> > > > > +static void get_ipv6_ext_hdrs(struct sk_buff *skb, struct ipv6hdr *nh,
> > > > > +                             u16 *ext_hdrs)
> > > > > +{
> > > > > +       u8 next_type = nh->nexthdr;
> > > > > +       unsigned int start = skb_network_offset(skb) + sizeof(struct ipv6hdr);
> > > > > +       int dest_options_header_count = 0;
> > > > > +
> > > > > +       *ext_hdrs = 0;
> > > > > +
> > > > > +       while (ipv6_ext_hdr(next_type)) {
> > > > > +               struct ipv6_opt_hdr _hdr, *hp;
> > > > > +
> > > > > +               switch (next_type) {
> > > > > +               case IPPROTO_NONE:
> > > > > +                       *ext_hdrs |= OFPIEH12_NONEXT;
> > > > > +                       /* stop parsing */
> > > > > +                       return;
> > > > > +
> > > > > +               case IPPROTO_ESP:
> > > > > +                       if (*ext_hdrs & OFPIEH12_ESP)
> > > > > +                               *ext_hdrs |= OFPIEH12_UNREP;
> > > > > +                       if ((*ext_hdrs & ~(OFPIEH12_HOP | OFPIEH12_DEST |
> > > > > +                                          OFPIEH12_ROUTER | IPPROTO_FRAGMENT |
> > > > > +                                          OFPIEH12_AUTH | OFPIEH12_UNREP)) ||
> > > > > +                           dest_options_header_count >= 2) {
> > > > > +                               *ext_hdrs |= OFPIEH12_UNSEQ;
> > > > > +                       }
> > > > > +                       *ext_hdrs |= OFPIEH12_ESP;
> > > > > +                       break;
> > > > you need to check_header() before looking into each extension header.
> > >
> > > Could you elaborate why I need to add check_header(),
> > > skb_header_pointer() is doing sanitization.
> >
> > I mean check_header() would allow you to read the header without
> > copying the bits, it is used in ovs flow extraction so its usual
> > check.
>
> But check_header() will call *__pskb_pull_tail which in turn will copy
> bits if data will be fragmented.
>
OVS flow extract uses this function to extract flow upto L4, so
skb_header_pointer() is not saving any copy operation.

> /* Moves tail of skb head forward, copying data from fragmented part,
>  * when it is necessary.
>  * 1. It may fail due to malloc failure.
>  * 2. It may change skb pointers.
>  *
>  * It is pretty complicated. Luckily, it is called only in exceptional cases.
>  */
> void *__pskb_pull_tail(struct sk_buff *skb, int delta)
>
> as well I noticed that for example commit
> 4a06fa67c4da20148803525151845276cdb995c1 is moving from
> pskb_may_pull() to skb_header_pointer()
ok, I see advantage of using skb_header_pointer() in this case, but
replacing all check_header() with skb_header_pointer() would add lot
of copy operation in flow extract. Anyways for this use case
skb_header_pointer() is fine.

Acked-by: Pravin B Shelar <pshelar@ovn.org>

^ permalink raw reply	[flat|nested] 12+ messages in thread

* Re: [PATCH net-next v8] net: openvswitch: IPv6: Add IPv6 extension header support
  2021-12-03  5:28     ` Pravin Shelar
@ 2021-12-06 23:00       ` Cpp Code
  2021-12-10  7:36         ` Pravin Shelar
  0 siblings, 1 reply; 12+ messages in thread
From: Cpp Code @ 2021-12-06 23:00 UTC (permalink / raw)
  To: Pravin Shelar
  Cc: Linux Kernel Network Developers, David S. Miller, Jakub Kicinski,
	ovs dev, LKML

On Thu, Dec 2, 2021 at 9:28 PM Pravin Shelar <pravin.ovn@gmail.com> wrote:
>
> On Thu, Dec 2, 2021 at 12:20 PM Cpp Code <cpp.code.lv@gmail.com> wrote:
> >
> > On Wed, Dec 1, 2021 at 11:34 PM Pravin Shelar <pravin.ovn@gmail.com> wrote:
> > >
> > > On Wed, Nov 24, 2021 at 11:33 AM Toms Atteka <cpp.code.lv@gmail.com> wrote:
> > > >
> > > > This change adds a new OpenFlow field OFPXMT_OFB_IPV6_EXTHDR and
> > > > packets can be filtered using ipv6_ext flag.
> > > >
> > > > Signed-off-by: Toms Atteka <cpp.code.lv@gmail.com>
> > > > ---
> > > >  include/uapi/linux/openvswitch.h |   6 ++
> > > >  net/openvswitch/flow.c           | 140 +++++++++++++++++++++++++++++++
> > > >  net/openvswitch/flow.h           |  14 ++++
> > > >  net/openvswitch/flow_netlink.c   |  26 +++++-
> > > >  4 files changed, 184 insertions(+), 2 deletions(-)
> > > >
> > > > diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h
> > > > index a87b44cd5590..43790f07e4a2 100644
> > > > --- a/include/uapi/linux/openvswitch.h
> > > > +++ b/include/uapi/linux/openvswitch.h
> > > > @@ -342,6 +342,7 @@ enum ovs_key_attr {
> > > >         OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4,   /* struct ovs_key_ct_tuple_ipv4 */
> > > >         OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6,   /* struct ovs_key_ct_tuple_ipv6 */
> > > >         OVS_KEY_ATTR_NSH,       /* Nested set of ovs_nsh_key_* */
> > > > +       OVS_KEY_ATTR_IPV6_EXTHDRS,  /* struct ovs_key_ipv6_exthdr */
> > > >
> > > >  #ifdef __KERNEL__
> > > >         OVS_KEY_ATTR_TUNNEL_INFO,  /* struct ip_tunnel_info */
> > > > @@ -421,6 +422,11 @@ struct ovs_key_ipv6 {
> > > >         __u8   ipv6_frag;       /* One of OVS_FRAG_TYPE_*. */
> > > >  };
> > > >
> > > > +/* separate structure to support backward compatibility with older user space */
> > > > +struct ovs_key_ipv6_exthdrs {
> > > > +       __u16  hdrs;
> > > > +};
> > > > +
> > > >  struct ovs_key_tcp {
> > > >         __be16 tcp_src;
> > > >         __be16 tcp_dst;
> > > > diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
> > > > index 9d375e74b607..28acb40437ca 100644
> > > > --- a/net/openvswitch/flow.c
> > > > +++ b/net/openvswitch/flow.c
> > > > @@ -239,6 +239,144 @@ static bool icmphdr_ok(struct sk_buff *skb)
> > > >                                   sizeof(struct icmphdr));
> > > >  }
> > > >
> > > > +/**
> > > > + * get_ipv6_ext_hdrs() - Parses packet and sets IPv6 extension header flags.
> > > > + *
> > > > + * @skb: buffer where extension header data starts in packet
> > > > + * @nh: ipv6 header
> > > > + * @ext_hdrs: flags are stored here
> > > > + *
> > > > + * OFPIEH12_UNREP is set if more than one of a given IPv6 extension header
> > > > + * is unexpectedly encountered. (Two destination options headers may be
> > > > + * expected and would not cause this bit to be set.)
> > > > + *
> > > > + * OFPIEH12_UNSEQ is set if IPv6 extension headers were not in the order
> > > > + * preferred (but not required) by RFC 2460:
> > > > + *
> > > > + * When more than one extension header is used in the same packet, it is
> > > > + * recommended that those headers appear in the following order:
> > > > + *      IPv6 header
> > > > + *      Hop-by-Hop Options header
> > > > + *      Destination Options header
> > > > + *      Routing header
> > > > + *      Fragment header
> > > > + *      Authentication header
> > > > + *      Encapsulating Security Payload header
> > > > + *      Destination Options header
> > > > + *      upper-layer header
> > > > + */
> > > > +static void get_ipv6_ext_hdrs(struct sk_buff *skb, struct ipv6hdr *nh,
> > > > +                             u16 *ext_hdrs)
> > > > +{
> > > > +       u8 next_type = nh->nexthdr;
> > > > +       unsigned int start = skb_network_offset(skb) + sizeof(struct ipv6hdr);
> > > > +       int dest_options_header_count = 0;
> > > > +
> > > > +       *ext_hdrs = 0;
> > > > +
> > > > +       while (ipv6_ext_hdr(next_type)) {
> > > > +               struct ipv6_opt_hdr _hdr, *hp;
> > > > +
> > > > +               switch (next_type) {
> > > > +               case IPPROTO_NONE:
> > > > +                       *ext_hdrs |= OFPIEH12_NONEXT;
> > > > +                       /* stop parsing */
> > > > +                       return;
> > > > +
> > > > +               case IPPROTO_ESP:
> > > > +                       if (*ext_hdrs & OFPIEH12_ESP)
> > > > +                               *ext_hdrs |= OFPIEH12_UNREP;
> > > > +                       if ((*ext_hdrs & ~(OFPIEH12_HOP | OFPIEH12_DEST |
> > > > +                                          OFPIEH12_ROUTER | IPPROTO_FRAGMENT |
> > > > +                                          OFPIEH12_AUTH | OFPIEH12_UNREP)) ||
> > > > +                           dest_options_header_count >= 2) {
> > > > +                               *ext_hdrs |= OFPIEH12_UNSEQ;
> > > > +                       }
> > > > +                       *ext_hdrs |= OFPIEH12_ESP;
> > > > +                       break;
> > > you need to check_header() before looking into each extension header.
> >
> > Could you elaborate why I need to add check_header(),
> > skb_header_pointer() is doing sanitization.
>
> I mean check_header() would allow you to read the header without
> copying the bits, it is used in ovs flow extraction so its usual
> check.

But check_header() will call *__pskb_pull_tail which in turn will copy
bits if data will be fragmented.

/* Moves tail of skb head forward, copying data from fragmented part,
 * when it is necessary.
 * 1. It may fail due to malloc failure.
 * 2. It may change skb pointers.
 *
 * It is pretty complicated. Luckily, it is called only in exceptional cases.
 */
void *__pskb_pull_tail(struct sk_buff *skb, int delta)

as well I noticed that for example commit
4a06fa67c4da20148803525151845276cdb995c1 is moving from
pskb_may_pull() to skb_header_pointer()

^ permalink raw reply	[flat|nested] 12+ messages in thread

* Re: [PATCH net-next v8] net: openvswitch: IPv6: Add IPv6 extension header support
  2021-12-02 20:20   ` Cpp Code
@ 2021-12-03  5:28     ` Pravin Shelar
  2021-12-06 23:00       ` Cpp Code
  0 siblings, 1 reply; 12+ messages in thread
From: Pravin Shelar @ 2021-12-03  5:28 UTC (permalink / raw)
  To: Cpp Code
  Cc: Linux Kernel Network Developers, David S. Miller, Jakub Kicinski,
	ovs dev, LKML

On Thu, Dec 2, 2021 at 12:20 PM Cpp Code <cpp.code.lv@gmail.com> wrote:
>
> On Wed, Dec 1, 2021 at 11:34 PM Pravin Shelar <pravin.ovn@gmail.com> wrote:
> >
> > On Wed, Nov 24, 2021 at 11:33 AM Toms Atteka <cpp.code.lv@gmail.com> wrote:
> > >
> > > This change adds a new OpenFlow field OFPXMT_OFB_IPV6_EXTHDR and
> > > packets can be filtered using ipv6_ext flag.
> > >
> > > Signed-off-by: Toms Atteka <cpp.code.lv@gmail.com>
> > > ---
> > >  include/uapi/linux/openvswitch.h |   6 ++
> > >  net/openvswitch/flow.c           | 140 +++++++++++++++++++++++++++++++
> > >  net/openvswitch/flow.h           |  14 ++++
> > >  net/openvswitch/flow_netlink.c   |  26 +++++-
> > >  4 files changed, 184 insertions(+), 2 deletions(-)
> > >
> > > diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h
> > > index a87b44cd5590..43790f07e4a2 100644
> > > --- a/include/uapi/linux/openvswitch.h
> > > +++ b/include/uapi/linux/openvswitch.h
> > > @@ -342,6 +342,7 @@ enum ovs_key_attr {
> > >         OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4,   /* struct ovs_key_ct_tuple_ipv4 */
> > >         OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6,   /* struct ovs_key_ct_tuple_ipv6 */
> > >         OVS_KEY_ATTR_NSH,       /* Nested set of ovs_nsh_key_* */
> > > +       OVS_KEY_ATTR_IPV6_EXTHDRS,  /* struct ovs_key_ipv6_exthdr */
> > >
> > >  #ifdef __KERNEL__
> > >         OVS_KEY_ATTR_TUNNEL_INFO,  /* struct ip_tunnel_info */
> > > @@ -421,6 +422,11 @@ struct ovs_key_ipv6 {
> > >         __u8   ipv6_frag;       /* One of OVS_FRAG_TYPE_*. */
> > >  };
> > >
> > > +/* separate structure to support backward compatibility with older user space */
> > > +struct ovs_key_ipv6_exthdrs {
> > > +       __u16  hdrs;
> > > +};
> > > +
> > >  struct ovs_key_tcp {
> > >         __be16 tcp_src;
> > >         __be16 tcp_dst;
> > > diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
> > > index 9d375e74b607..28acb40437ca 100644
> > > --- a/net/openvswitch/flow.c
> > > +++ b/net/openvswitch/flow.c
> > > @@ -239,6 +239,144 @@ static bool icmphdr_ok(struct sk_buff *skb)
> > >                                   sizeof(struct icmphdr));
> > >  }
> > >
> > > +/**
> > > + * get_ipv6_ext_hdrs() - Parses packet and sets IPv6 extension header flags.
> > > + *
> > > + * @skb: buffer where extension header data starts in packet
> > > + * @nh: ipv6 header
> > > + * @ext_hdrs: flags are stored here
> > > + *
> > > + * OFPIEH12_UNREP is set if more than one of a given IPv6 extension header
> > > + * is unexpectedly encountered. (Two destination options headers may be
> > > + * expected and would not cause this bit to be set.)
> > > + *
> > > + * OFPIEH12_UNSEQ is set if IPv6 extension headers were not in the order
> > > + * preferred (but not required) by RFC 2460:
> > > + *
> > > + * When more than one extension header is used in the same packet, it is
> > > + * recommended that those headers appear in the following order:
> > > + *      IPv6 header
> > > + *      Hop-by-Hop Options header
> > > + *      Destination Options header
> > > + *      Routing header
> > > + *      Fragment header
> > > + *      Authentication header
> > > + *      Encapsulating Security Payload header
> > > + *      Destination Options header
> > > + *      upper-layer header
> > > + */
> > > +static void get_ipv6_ext_hdrs(struct sk_buff *skb, struct ipv6hdr *nh,
> > > +                             u16 *ext_hdrs)
> > > +{
> > > +       u8 next_type = nh->nexthdr;
> > > +       unsigned int start = skb_network_offset(skb) + sizeof(struct ipv6hdr);
> > > +       int dest_options_header_count = 0;
> > > +
> > > +       *ext_hdrs = 0;
> > > +
> > > +       while (ipv6_ext_hdr(next_type)) {
> > > +               struct ipv6_opt_hdr _hdr, *hp;
> > > +
> > > +               switch (next_type) {
> > > +               case IPPROTO_NONE:
> > > +                       *ext_hdrs |= OFPIEH12_NONEXT;
> > > +                       /* stop parsing */
> > > +                       return;
> > > +
> > > +               case IPPROTO_ESP:
> > > +                       if (*ext_hdrs & OFPIEH12_ESP)
> > > +                               *ext_hdrs |= OFPIEH12_UNREP;
> > > +                       if ((*ext_hdrs & ~(OFPIEH12_HOP | OFPIEH12_DEST |
> > > +                                          OFPIEH12_ROUTER | IPPROTO_FRAGMENT |
> > > +                                          OFPIEH12_AUTH | OFPIEH12_UNREP)) ||
> > > +                           dest_options_header_count >= 2) {
> > > +                               *ext_hdrs |= OFPIEH12_UNSEQ;
> > > +                       }
> > > +                       *ext_hdrs |= OFPIEH12_ESP;
> > > +                       break;
> > you need to check_header() before looking into each extension header.
>
> Could you elaborate why I need to add check_header(),
> skb_header_pointer() is doing sanitization.

I mean check_header() would allow you to read the header without
copying the bits, it is used in ovs flow extraction so its usual
check.

^ permalink raw reply	[flat|nested] 12+ messages in thread

* Re: [PATCH net-next v8] net: openvswitch: IPv6: Add IPv6 extension header support
  2021-12-02  7:33 ` Pravin Shelar
@ 2021-12-02 20:20   ` Cpp Code
  2021-12-03  5:28     ` Pravin Shelar
  0 siblings, 1 reply; 12+ messages in thread
From: Cpp Code @ 2021-12-02 20:20 UTC (permalink / raw)
  To: Pravin Shelar
  Cc: Linux Kernel Network Developers, David S. Miller, Jakub Kicinski,
	ovs dev, LKML

On Wed, Dec 1, 2021 at 11:34 PM Pravin Shelar <pravin.ovn@gmail.com> wrote:
>
> On Wed, Nov 24, 2021 at 11:33 AM Toms Atteka <cpp.code.lv@gmail.com> wrote:
> >
> > This change adds a new OpenFlow field OFPXMT_OFB_IPV6_EXTHDR and
> > packets can be filtered using ipv6_ext flag.
> >
> > Signed-off-by: Toms Atteka <cpp.code.lv@gmail.com>
> > ---
> >  include/uapi/linux/openvswitch.h |   6 ++
> >  net/openvswitch/flow.c           | 140 +++++++++++++++++++++++++++++++
> >  net/openvswitch/flow.h           |  14 ++++
> >  net/openvswitch/flow_netlink.c   |  26 +++++-
> >  4 files changed, 184 insertions(+), 2 deletions(-)
> >
> > diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h
> > index a87b44cd5590..43790f07e4a2 100644
> > --- a/include/uapi/linux/openvswitch.h
> > +++ b/include/uapi/linux/openvswitch.h
> > @@ -342,6 +342,7 @@ enum ovs_key_attr {
> >         OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4,   /* struct ovs_key_ct_tuple_ipv4 */
> >         OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6,   /* struct ovs_key_ct_tuple_ipv6 */
> >         OVS_KEY_ATTR_NSH,       /* Nested set of ovs_nsh_key_* */
> > +       OVS_KEY_ATTR_IPV6_EXTHDRS,  /* struct ovs_key_ipv6_exthdr */
> >
> >  #ifdef __KERNEL__
> >         OVS_KEY_ATTR_TUNNEL_INFO,  /* struct ip_tunnel_info */
> > @@ -421,6 +422,11 @@ struct ovs_key_ipv6 {
> >         __u8   ipv6_frag;       /* One of OVS_FRAG_TYPE_*. */
> >  };
> >
> > +/* separate structure to support backward compatibility with older user space */
> > +struct ovs_key_ipv6_exthdrs {
> > +       __u16  hdrs;
> > +};
> > +
> >  struct ovs_key_tcp {
> >         __be16 tcp_src;
> >         __be16 tcp_dst;
> > diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
> > index 9d375e74b607..28acb40437ca 100644
> > --- a/net/openvswitch/flow.c
> > +++ b/net/openvswitch/flow.c
> > @@ -239,6 +239,144 @@ static bool icmphdr_ok(struct sk_buff *skb)
> >                                   sizeof(struct icmphdr));
> >  }
> >
> > +/**
> > + * get_ipv6_ext_hdrs() - Parses packet and sets IPv6 extension header flags.
> > + *
> > + * @skb: buffer where extension header data starts in packet
> > + * @nh: ipv6 header
> > + * @ext_hdrs: flags are stored here
> > + *
> > + * OFPIEH12_UNREP is set if more than one of a given IPv6 extension header
> > + * is unexpectedly encountered. (Two destination options headers may be
> > + * expected and would not cause this bit to be set.)
> > + *
> > + * OFPIEH12_UNSEQ is set if IPv6 extension headers were not in the order
> > + * preferred (but not required) by RFC 2460:
> > + *
> > + * When more than one extension header is used in the same packet, it is
> > + * recommended that those headers appear in the following order:
> > + *      IPv6 header
> > + *      Hop-by-Hop Options header
> > + *      Destination Options header
> > + *      Routing header
> > + *      Fragment header
> > + *      Authentication header
> > + *      Encapsulating Security Payload header
> > + *      Destination Options header
> > + *      upper-layer header
> > + */
> > +static void get_ipv6_ext_hdrs(struct sk_buff *skb, struct ipv6hdr *nh,
> > +                             u16 *ext_hdrs)
> > +{
> > +       u8 next_type = nh->nexthdr;
> > +       unsigned int start = skb_network_offset(skb) + sizeof(struct ipv6hdr);
> > +       int dest_options_header_count = 0;
> > +
> > +       *ext_hdrs = 0;
> > +
> > +       while (ipv6_ext_hdr(next_type)) {
> > +               struct ipv6_opt_hdr _hdr, *hp;
> > +
> > +               switch (next_type) {
> > +               case IPPROTO_NONE:
> > +                       *ext_hdrs |= OFPIEH12_NONEXT;
> > +                       /* stop parsing */
> > +                       return;
> > +
> > +               case IPPROTO_ESP:
> > +                       if (*ext_hdrs & OFPIEH12_ESP)
> > +                               *ext_hdrs |= OFPIEH12_UNREP;
> > +                       if ((*ext_hdrs & ~(OFPIEH12_HOP | OFPIEH12_DEST |
> > +                                          OFPIEH12_ROUTER | IPPROTO_FRAGMENT |
> > +                                          OFPIEH12_AUTH | OFPIEH12_UNREP)) ||
> > +                           dest_options_header_count >= 2) {
> > +                               *ext_hdrs |= OFPIEH12_UNSEQ;
> > +                       }
> > +                       *ext_hdrs |= OFPIEH12_ESP;
> > +                       break;
> you need to check_header() before looking into each extension header.

Could you elaborate why I need to add check_header(),
skb_header_pointer() is doing sanitization.

^ permalink raw reply	[flat|nested] 12+ messages in thread

* Re: [PATCH net-next v8] net: openvswitch: IPv6: Add IPv6 extension header support
  2021-11-24 19:33 Toms Atteka
@ 2021-12-02  7:33 ` Pravin Shelar
  2021-12-02 20:20   ` Cpp Code
  0 siblings, 1 reply; 12+ messages in thread
From: Pravin Shelar @ 2021-12-02  7:33 UTC (permalink / raw)
  To: Toms Atteka
  Cc: Linux Kernel Network Developers, David S. Miller, Jakub Kicinski,
	ovs dev, LKML

On Wed, Nov 24, 2021 at 11:33 AM Toms Atteka <cpp.code.lv@gmail.com> wrote:
>
> This change adds a new OpenFlow field OFPXMT_OFB_IPV6_EXTHDR and
> packets can be filtered using ipv6_ext flag.
>
> Signed-off-by: Toms Atteka <cpp.code.lv@gmail.com>
> ---
>  include/uapi/linux/openvswitch.h |   6 ++
>  net/openvswitch/flow.c           | 140 +++++++++++++++++++++++++++++++
>  net/openvswitch/flow.h           |  14 ++++
>  net/openvswitch/flow_netlink.c   |  26 +++++-
>  4 files changed, 184 insertions(+), 2 deletions(-)
>
> diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h
> index a87b44cd5590..43790f07e4a2 100644
> --- a/include/uapi/linux/openvswitch.h
> +++ b/include/uapi/linux/openvswitch.h
> @@ -342,6 +342,7 @@ enum ovs_key_attr {
>         OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4,   /* struct ovs_key_ct_tuple_ipv4 */
>         OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6,   /* struct ovs_key_ct_tuple_ipv6 */
>         OVS_KEY_ATTR_NSH,       /* Nested set of ovs_nsh_key_* */
> +       OVS_KEY_ATTR_IPV6_EXTHDRS,  /* struct ovs_key_ipv6_exthdr */
>
>  #ifdef __KERNEL__
>         OVS_KEY_ATTR_TUNNEL_INFO,  /* struct ip_tunnel_info */
> @@ -421,6 +422,11 @@ struct ovs_key_ipv6 {
>         __u8   ipv6_frag;       /* One of OVS_FRAG_TYPE_*. */
>  };
>
> +/* separate structure to support backward compatibility with older user space */
> +struct ovs_key_ipv6_exthdrs {
> +       __u16  hdrs;
> +};
> +
>  struct ovs_key_tcp {
>         __be16 tcp_src;
>         __be16 tcp_dst;
> diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
> index 9d375e74b607..28acb40437ca 100644
> --- a/net/openvswitch/flow.c
> +++ b/net/openvswitch/flow.c
> @@ -239,6 +239,144 @@ static bool icmphdr_ok(struct sk_buff *skb)
>                                   sizeof(struct icmphdr));
>  }
>
> +/**
> + * get_ipv6_ext_hdrs() - Parses packet and sets IPv6 extension header flags.
> + *
> + * @skb: buffer where extension header data starts in packet
> + * @nh: ipv6 header
> + * @ext_hdrs: flags are stored here
> + *
> + * OFPIEH12_UNREP is set if more than one of a given IPv6 extension header
> + * is unexpectedly encountered. (Two destination options headers may be
> + * expected and would not cause this bit to be set.)
> + *
> + * OFPIEH12_UNSEQ is set if IPv6 extension headers were not in the order
> + * preferred (but not required) by RFC 2460:
> + *
> + * When more than one extension header is used in the same packet, it is
> + * recommended that those headers appear in the following order:
> + *      IPv6 header
> + *      Hop-by-Hop Options header
> + *      Destination Options header
> + *      Routing header
> + *      Fragment header
> + *      Authentication header
> + *      Encapsulating Security Payload header
> + *      Destination Options header
> + *      upper-layer header
> + */
> +static void get_ipv6_ext_hdrs(struct sk_buff *skb, struct ipv6hdr *nh,
> +                             u16 *ext_hdrs)
> +{
> +       u8 next_type = nh->nexthdr;
> +       unsigned int start = skb_network_offset(skb) + sizeof(struct ipv6hdr);
> +       int dest_options_header_count = 0;
> +
> +       *ext_hdrs = 0;
> +
> +       while (ipv6_ext_hdr(next_type)) {
> +               struct ipv6_opt_hdr _hdr, *hp;
> +
> +               switch (next_type) {
> +               case IPPROTO_NONE:
> +                       *ext_hdrs |= OFPIEH12_NONEXT;
> +                       /* stop parsing */
> +                       return;
> +
> +               case IPPROTO_ESP:
> +                       if (*ext_hdrs & OFPIEH12_ESP)
> +                               *ext_hdrs |= OFPIEH12_UNREP;
> +                       if ((*ext_hdrs & ~(OFPIEH12_HOP | OFPIEH12_DEST |
> +                                          OFPIEH12_ROUTER | IPPROTO_FRAGMENT |
> +                                          OFPIEH12_AUTH | OFPIEH12_UNREP)) ||
> +                           dest_options_header_count >= 2) {
> +                               *ext_hdrs |= OFPIEH12_UNSEQ;
> +                       }
> +                       *ext_hdrs |= OFPIEH12_ESP;
> +                       break;
you need to check_header() before looking into each extension header.

^ permalink raw reply	[flat|nested] 12+ messages in thread

* [PATCH net-next v8] net: openvswitch: IPv6: Add IPv6 extension header support
@ 2021-11-24 19:33 Toms Atteka
  2021-12-02  7:33 ` Pravin Shelar
  0 siblings, 1 reply; 12+ messages in thread
From: Toms Atteka @ 2021-11-24 19:33 UTC (permalink / raw)
  To: netdev, pshelar, davem, kuba, dev, linux-kernel; +Cc: Toms Atteka

This change adds a new OpenFlow field OFPXMT_OFB_IPV6_EXTHDR and
packets can be filtered using ipv6_ext flag.

Signed-off-by: Toms Atteka <cpp.code.lv@gmail.com>
---
 include/uapi/linux/openvswitch.h |   6 ++
 net/openvswitch/flow.c           | 140 +++++++++++++++++++++++++++++++
 net/openvswitch/flow.h           |  14 ++++
 net/openvswitch/flow_netlink.c   |  26 +++++-
 4 files changed, 184 insertions(+), 2 deletions(-)

diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h
index a87b44cd5590..43790f07e4a2 100644
--- a/include/uapi/linux/openvswitch.h
+++ b/include/uapi/linux/openvswitch.h
@@ -342,6 +342,7 @@ enum ovs_key_attr {
 	OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4,   /* struct ovs_key_ct_tuple_ipv4 */
 	OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6,   /* struct ovs_key_ct_tuple_ipv6 */
 	OVS_KEY_ATTR_NSH,       /* Nested set of ovs_nsh_key_* */
+	OVS_KEY_ATTR_IPV6_EXTHDRS,  /* struct ovs_key_ipv6_exthdr */
 
 #ifdef __KERNEL__
 	OVS_KEY_ATTR_TUNNEL_INFO,  /* struct ip_tunnel_info */
@@ -421,6 +422,11 @@ struct ovs_key_ipv6 {
 	__u8   ipv6_frag;	/* One of OVS_FRAG_TYPE_*. */
 };
 
+/* separate structure to support backward compatibility with older user space */
+struct ovs_key_ipv6_exthdrs {
+	__u16  hdrs;
+};
+
 struct ovs_key_tcp {
 	__be16 tcp_src;
 	__be16 tcp_dst;
diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index 9d375e74b607..28acb40437ca 100644
--- a/net/openvswitch/flow.c
+++ b/net/openvswitch/flow.c
@@ -239,6 +239,144 @@ static bool icmphdr_ok(struct sk_buff *skb)
 				  sizeof(struct icmphdr));
 }
 
+/**
+ * get_ipv6_ext_hdrs() - Parses packet and sets IPv6 extension header flags.
+ *
+ * @skb: buffer where extension header data starts in packet
+ * @nh: ipv6 header
+ * @ext_hdrs: flags are stored here
+ *
+ * OFPIEH12_UNREP is set if more than one of a given IPv6 extension header
+ * is unexpectedly encountered. (Two destination options headers may be
+ * expected and would not cause this bit to be set.)
+ *
+ * OFPIEH12_UNSEQ is set if IPv6 extension headers were not in the order
+ * preferred (but not required) by RFC 2460:
+ *
+ * When more than one extension header is used in the same packet, it is
+ * recommended that those headers appear in the following order:
+ *      IPv6 header
+ *      Hop-by-Hop Options header
+ *      Destination Options header
+ *      Routing header
+ *      Fragment header
+ *      Authentication header
+ *      Encapsulating Security Payload header
+ *      Destination Options header
+ *      upper-layer header
+ */
+static void get_ipv6_ext_hdrs(struct sk_buff *skb, struct ipv6hdr *nh,
+			      u16 *ext_hdrs)
+{
+	u8 next_type = nh->nexthdr;
+	unsigned int start = skb_network_offset(skb) + sizeof(struct ipv6hdr);
+	int dest_options_header_count = 0;
+
+	*ext_hdrs = 0;
+
+	while (ipv6_ext_hdr(next_type)) {
+		struct ipv6_opt_hdr _hdr, *hp;
+
+		switch (next_type) {
+		case IPPROTO_NONE:
+			*ext_hdrs |= OFPIEH12_NONEXT;
+			/* stop parsing */
+			return;
+
+		case IPPROTO_ESP:
+			if (*ext_hdrs & OFPIEH12_ESP)
+				*ext_hdrs |= OFPIEH12_UNREP;
+			if ((*ext_hdrs & ~(OFPIEH12_HOP | OFPIEH12_DEST |
+					   OFPIEH12_ROUTER | IPPROTO_FRAGMENT |
+					   OFPIEH12_AUTH | OFPIEH12_UNREP)) ||
+			    dest_options_header_count >= 2) {
+				*ext_hdrs |= OFPIEH12_UNSEQ;
+			}
+			*ext_hdrs |= OFPIEH12_ESP;
+			break;
+
+		case IPPROTO_AH:
+			if (*ext_hdrs & OFPIEH12_AUTH)
+				*ext_hdrs |= OFPIEH12_UNREP;
+			if ((*ext_hdrs &
+			     ~(OFPIEH12_HOP | OFPIEH12_DEST | OFPIEH12_ROUTER |
+			       IPPROTO_FRAGMENT | OFPIEH12_UNREP)) ||
+			    dest_options_header_count >= 2) {
+				*ext_hdrs |= OFPIEH12_UNSEQ;
+			}
+			*ext_hdrs |= OFPIEH12_AUTH;
+			break;
+
+		case IPPROTO_DSTOPTS:
+			if (dest_options_header_count == 0) {
+				if (*ext_hdrs &
+				    ~(OFPIEH12_HOP | OFPIEH12_UNREP))
+					*ext_hdrs |= OFPIEH12_UNSEQ;
+				*ext_hdrs |= OFPIEH12_DEST;
+			} else if (dest_options_header_count == 1) {
+				if (*ext_hdrs &
+				    ~(OFPIEH12_HOP | OFPIEH12_DEST |
+				      OFPIEH12_ROUTER | OFPIEH12_FRAG |
+				      OFPIEH12_AUTH | OFPIEH12_ESP |
+				      OFPIEH12_UNREP)) {
+					*ext_hdrs |= OFPIEH12_UNSEQ;
+				}
+			} else {
+				*ext_hdrs |= OFPIEH12_UNREP;
+			}
+			dest_options_header_count++;
+			break;
+
+		case IPPROTO_FRAGMENT:
+			if (*ext_hdrs & OFPIEH12_FRAG)
+				*ext_hdrs |= OFPIEH12_UNREP;
+			if ((*ext_hdrs & ~(OFPIEH12_HOP |
+					   OFPIEH12_DEST |
+					   OFPIEH12_ROUTER |
+					   OFPIEH12_UNREP)) ||
+			    dest_options_header_count >= 2) {
+				*ext_hdrs |= OFPIEH12_UNSEQ;
+			}
+			*ext_hdrs |= OFPIEH12_FRAG;
+			break;
+
+		case IPPROTO_ROUTING:
+			if (*ext_hdrs & OFPIEH12_ROUTER)
+				*ext_hdrs |= OFPIEH12_UNREP;
+			if ((*ext_hdrs & ~(OFPIEH12_HOP |
+					   OFPIEH12_DEST |
+					   OFPIEH12_UNREP)) ||
+			    dest_options_header_count >= 2) {
+				*ext_hdrs |= OFPIEH12_UNSEQ;
+			}
+			*ext_hdrs |= OFPIEH12_ROUTER;
+			break;
+
+		case IPPROTO_HOPOPTS:
+			if (*ext_hdrs & OFPIEH12_HOP)
+				*ext_hdrs |= OFPIEH12_UNREP;
+			/* OFPIEH12_HOP is set to 1 if a hop-by-hop IPv6
+			 * extension header is present as the first
+			 * extension header in the packet.
+			 */
+			if (*ext_hdrs == 0)
+				*ext_hdrs |= OFPIEH12_HOP;
+			else
+				*ext_hdrs |= OFPIEH12_UNSEQ;
+			break;
+
+		default:
+			return;
+		}
+
+		hp = skb_header_pointer(skb, start, sizeof(_hdr), &_hdr);
+		if (!hp)
+			break;
+		next_type = hp->nexthdr;
+		start += ipv6_optlen(hp);
+	};
+}
+
 static int parse_ipv6hdr(struct sk_buff *skb, struct sw_flow_key *key)
 {
 	unsigned short frag_off;
@@ -254,6 +392,8 @@ static int parse_ipv6hdr(struct sk_buff *skb, struct sw_flow_key *key)
 
 	nh = ipv6_hdr(skb);
 
+	get_ipv6_ext_hdrs(skb, nh, &key->ipv6.exthdrs);
+
 	key->ip.proto = NEXTHDR_NONE;
 	key->ip.tos = ipv6_get_dsfield(nh);
 	key->ip.ttl = nh->hop_limit;
diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h
index 758a8c77f736..073ab73ffeaa 100644
--- a/net/openvswitch/flow.h
+++ b/net/openvswitch/flow.h
@@ -32,6 +32,19 @@ enum sw_flow_mac_proto {
 #define SW_FLOW_KEY_INVALID	0x80
 #define MPLS_LABEL_DEPTH       3
 
+/* Bit definitions for IPv6 Extension Header pseudo-field. */
+enum ofp12_ipv6exthdr_flags {
+	OFPIEH12_NONEXT = 1 << 0,   /* "No next header" encountered. */
+	OFPIEH12_ESP    = 1 << 1,   /* Encrypted Sec Payload header present. */
+	OFPIEH12_AUTH   = 1 << 2,   /* Authentication header present. */
+	OFPIEH12_DEST   = 1 << 3,   /* 1 or 2 dest headers present. */
+	OFPIEH12_FRAG   = 1 << 4,   /* Fragment header present. */
+	OFPIEH12_ROUTER = 1 << 5,   /* Router header present. */
+	OFPIEH12_HOP    = 1 << 6,   /* Hop-by-hop header present. */
+	OFPIEH12_UNREP  = 1 << 7,   /* Unexpected repeats encountered. */
+	OFPIEH12_UNSEQ  = 1 << 8    /* Unexpected sequencing encountered. */
+};
+
 /* Store options at the end of the array if they are less than the
  * maximum size. This allows us to get the benefits of variable length
  * matching for small options.
@@ -121,6 +134,7 @@ struct sw_flow_key {
 				struct in6_addr dst;	/* IPv6 destination address. */
 			} addr;
 			__be32 label;			/* IPv6 flow label. */
+			u16 exthdrs;	/* IPv6 extension header flags */
 			union {
 				struct {
 					struct in6_addr src;
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index 65c2e3458ff5..0aeaf28594ce 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -344,7 +344,7 @@ size_t ovs_key_attr_size(void)
 	/* Whenever adding new OVS_KEY_ FIELDS, we should consider
 	 * updating this function.
 	 */
-	BUILD_BUG_ON(OVS_KEY_ATTR_TUNNEL_INFO != 29);
+	BUILD_BUG_ON(OVS_KEY_ATTR_TUNNEL_INFO != 30);
 
 	return    nla_total_size(4)   /* OVS_KEY_ATTR_PRIORITY */
 		+ nla_total_size(0)   /* OVS_KEY_ATTR_TUNNEL */
@@ -367,7 +367,8 @@ size_t ovs_key_attr_size(void)
 		+ nla_total_size(2)   /* OVS_KEY_ATTR_ETHERTYPE */
 		+ nla_total_size(40)  /* OVS_KEY_ATTR_IPV6 */
 		+ nla_total_size(2)   /* OVS_KEY_ATTR_ICMPV6 */
-		+ nla_total_size(28); /* OVS_KEY_ATTR_ND */
+		+ nla_total_size(28)  /* OVS_KEY_ATTR_ND */
+		+ nla_total_size(2);  /* OVS_KEY_ATTR_IPV6_EXTHDRS */
 }
 
 static const struct ovs_len_tbl ovs_vxlan_ext_key_lens[OVS_VXLAN_EXT_MAX + 1] = {
@@ -435,6 +436,8 @@ static const struct ovs_len_tbl ovs_key_lens[OVS_KEY_ATTR_MAX + 1] = {
 		.len = sizeof(struct ovs_key_ct_tuple_ipv6) },
 	[OVS_KEY_ATTR_NSH]       = { .len = OVS_ATTR_NESTED,
 				     .next = ovs_nsh_key_attr_lens, },
+	[OVS_KEY_ATTR_IPV6_EXTHDRS] = {
+		.len = sizeof(struct ovs_key_ipv6_exthdrs) },
 };
 
 static bool check_attr_len(unsigned int attr_len, unsigned int expected_len)
@@ -1595,6 +1598,17 @@ static int ovs_key_from_nlattrs(struct net *net, struct sw_flow_match *match,
 		attrs &= ~(1 << OVS_KEY_ATTR_IPV6);
 	}
 
+	if (attrs & (1ULL << OVS_KEY_ATTR_IPV6_EXTHDRS)) {
+		const struct ovs_key_ipv6_exthdrs *ipv6_exthdrs_key;
+
+		ipv6_exthdrs_key = nla_data(a[OVS_KEY_ATTR_IPV6_EXTHDRS]);
+
+		SW_FLOW_KEY_PUT(match, ipv6.exthdrs,
+				ipv6_exthdrs_key->hdrs, is_mask);
+
+		attrs &= ~(1ULL << OVS_KEY_ATTR_IPV6_EXTHDRS);
+	}
+
 	if (attrs & (1 << OVS_KEY_ATTR_ARP)) {
 		const struct ovs_key_arp *arp_key;
 
@@ -2097,6 +2111,7 @@ static int __ovs_nla_put_key(const struct sw_flow_key *swkey,
 		ipv4_key->ipv4_frag = output->ip.frag;
 	} else if (swkey->eth.type == htons(ETH_P_IPV6)) {
 		struct ovs_key_ipv6 *ipv6_key;
+		struct ovs_key_ipv6_exthdrs *ipv6_exthdrs_key;
 
 		nla = nla_reserve(skb, OVS_KEY_ATTR_IPV6, sizeof(*ipv6_key));
 		if (!nla)
@@ -2111,6 +2126,13 @@ static int __ovs_nla_put_key(const struct sw_flow_key *swkey,
 		ipv6_key->ipv6_tclass = output->ip.tos;
 		ipv6_key->ipv6_hlimit = output->ip.ttl;
 		ipv6_key->ipv6_frag = output->ip.frag;
+
+		nla = nla_reserve(skb, OVS_KEY_ATTR_IPV6_EXTHDRS,
+				  sizeof(*ipv6_exthdrs_key));
+		if (!nla)
+			goto nla_put_failure;
+		ipv6_exthdrs_key = nla_data(nla);
+		ipv6_exthdrs_key->hdrs = output->ipv6.exthdrs;
 	} else if (swkey->eth.type == htons(ETH_P_NSH)) {
 		if (nsh_key_to_nlattr(&output->nsh, is_mask, skb))
 			goto nla_put_failure;
-- 
2.25.1


^ permalink raw reply related	[flat|nested] 12+ messages in thread

end of thread, other threads:[~2022-02-25 10:40 UTC | newest]

Thread overview: 12+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2021-10-29 18:20 [PATCH net-next v8] net: openvswitch: IPv6: Add IPv6 extension header support Toms Atteka
2021-11-02 18:39 ` Jakub Kicinski
2021-11-24 19:33 Toms Atteka
2021-12-02  7:33 ` Pravin Shelar
2021-12-02 20:20   ` Cpp Code
2021-12-03  5:28     ` Pravin Shelar
2021-12-06 23:00       ` Cpp Code
2021-12-10  7:36         ` Pravin Shelar
2022-02-09 20:46           ` Cpp Code
2022-02-10  0:58             ` Jakub Kicinski
2022-02-24  0:54 Toms Atteka
2022-02-25 10:40 ` patchwork-bot+netdevbpf

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).