Merge branch 'ipv6-ioam'

Justin Iurman says: ==================== Support for the IOAM Pre-allocated Trace with IPv6 v5: - Refine types, min/max and default values for new sysctls - Introduce a "_wide" sysctl for each "ioam6_id" sysctl - Add more validation on headers before processing data - RCU for sc <> ns pointers + appropriate accessors - Generic Netlink policies are now per op, not per family anymore - Address other comments/remarks from Jakub (thanks again) - Revert "__packed" to "__attribute__((packed))" for uapi headers - Add tests to cover the functionality added, as requested by David Ahern v4: - Address warnings from checkpatch (ignore errors related to unnamed bitfields in the first patch) - Use of hweight32 (thanks Jakub) - Remove inline keyword from static functions in C files and let the compiler decide what to do (thanks Jakub) v3: - Fix warning "unused label 'out_unregister_genl'" by adding conditional macro - Fix lwtunnel output redirect bug: dst cache useless in this case, use orig_output instead v2: - Fix warning with static for __ioam6_fill_trace_data - Fix sparse warning with __force when casting __be64 to __be32 - Fix unchecked dereference when removing IOAM namespaces or schemas - exthdrs.c: Don't drop by default (now: ignore) to match the act bits "00" - Add control plane support for the inline insertion (lwtunnel) - Provide uapi structures - Use __net_timestamp if skb->tstamp is empty - Add note about the temporary IANA allocation - Remove support for "removable" TLVs - Remove support for virtual/anonymous tunnel decapsulation In-situ Operations, Administration, and Maintenance (IOAM) records operational and telemetry information in a packet while it traverses a path between two points in an IOAM domain. It is defined in draft-ietf-ippm-ioam-data [1]. IOAM data fields can be encapsulated into a variety of protocols. The IPv6 encapsulation is defined in draft-ietf-ippm-ioam-ipv6-options [2], via extension headers. IOAM can be used to complement OAM mechanisms based on e.g. ICMP or other types of probe packets. This patchset implements support for the Pre-allocated Trace, carried by a Hop-by-Hop. Therefore, a new IPv6 Hop-by-Hop TLV option is introduced, see IANA [3]. The three other IOAM options are not included in this patchset (Incremental Trace, Proof-of-Transit and Edge-to-Edge). The main idea behind the IOAM Pre-allocated Trace is that a node pre-allocates some room in packets for IOAM data. Then, each IOAM node on the path will insert its data. There exist several interesting use- cases, e.g. Fast failure detection/isolation or Smart service selection. Another killer use-case is what we have called Cross-Layer Telemetry, see the demo video on its repository [4], that aims to make the entire stack (L2/L3 -> L7) visible for distributed tracing tools (e.g. Jaeger), instead of the current L5 -> L7 limited view. So, basically, this is a nice feature for the Linux Kernel. This patchset also provides support for the control plane part, but only for the inline insertion (host-to-host use case), through lightweight tunnels. Indeed, for in-transit traffic, the solution is to have an IPv6-in-IPv6 encapsulation, which brings some difficulties and still requires a little bit of work and discussion (ie anonymous tunnel decapsulation and multi egress resolution). - Patch 1: IPv6 IOAM headers definition - Patch 2: Data plane support for Pre-allocated Trace - Patch 3: IOAM Generic Netlink API - Patch 4: Support for IOAM injection with lwtunnels - Patch 5: Documentation for new IOAM sysctls - Patch 6: Test for the IOAM insertion with IPv6 [1] https://tools.ietf.org/html/draft-ietf-ippm-ioam-data [2] https://tools.ietf.org/html/draft-ietf-ippm-ioam-ipv6-options [3] https://www.iana.org/assignments/ipv6-parameters/ipv6-parameters.xhtml#ipv6-parameters-2 [4] https://github.com/iurmanj/cross-layer-telemetry ==================== Signed-off-by: David S. Miller <davem@davemloft.net>
torvalds · Jul 21, 2021 · 7c804e9 · 7c804e9
2 parents 71f4f89 + 968691c
commit 7c804e9
Show file tree

Hide file tree

Showing 27 changed files with 2,393 additions and 1 deletion.
diff --git a/Documentation/networking/ioam6-sysctl.rst b/Documentation/networking/ioam6-sysctl.rst
@@ -0,0 +1,26 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=====================
+IOAM6 Sysfs variables
+=====================
+
+
+/proc/sys/net/conf/<iface>/ioam6_* variables:
+=============================================
+
+ioam6_enabled - BOOL
+        Accept (= enabled) or ignore (= disabled) IPv6 IOAM options on ingress
+        for this interface.
+
+        * 0 - disabled (default)
+        * 1 - enabled
+
+ioam6_id - SHORT INTEGER
+        Define the IOAM id of this interface.
+
+        Default is ~0.
+
+ioam6_id_wide - INTEGER
+        Define the wide IOAM id of this interface.
+
+        Default is ~0.
diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst
@@ -1926,6 +1926,23 @@ fib_notify_on_flag_change - INTEGER
         - 1 - Emit notifications.
         - 2 - Emit notifications only for RTM_F_OFFLOAD_FAILED flag change.
 
+ioam6_id - INTEGER
+        Define the IOAM id of this node. Uses only 24 bits out of 32 in total.
+
+        Min: 0
+        Max: 0xFFFFFF
+
+        Default: 0xFFFFFF
+
+ioam6_id_wide - LONG INTEGER
+        Define the wide IOAM id of this node. Uses only 56 bits out of 64 in
+        total. Can be different from ioam6_id.
+
+        Min: 0
+        Max: 0xFFFFFFFFFFFFFF
+
+        Default: 0xFFFFFFFFFFFFFF
+
 IPv6 Fragmentation:
 
 ip6frag_high_thresh - INTEGER

diff --git a/include/linux/ioam6.h b/include/linux/ioam6.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ *  IPv6 IOAM
+ *
+ *  Author:
+ *  Justin Iurman <justin.iurman@uliege.be>
+ */
+#ifndef _LINUX_IOAM6_H
+#define _LINUX_IOAM6_H
+
+#include <uapi/linux/ioam6.h>
+
+#endif /* _LINUX_IOAM6_H */
diff --git a/include/linux/ioam6_genl.h b/include/linux/ioam6_genl.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ *  IPv6 IOAM Generic Netlink API
+ *
+ *  Author:
+ *  Justin Iurman <justin.iurman@uliege.be>
+ */
+#ifndef _LINUX_IOAM6_GENL_H
+#define _LINUX_IOAM6_GENL_H
+
+#include <uapi/linux/ioam6_genl.h>
+
+#endif /* _LINUX_IOAM6_GENL_H */
diff --git a/include/linux/ioam6_iptunnel.h b/include/linux/ioam6_iptunnel.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ *  IPv6 IOAM Lightweight Tunnel API
+ *
+ *  Author:
+ *  Justin Iurman <justin.iurman@uliege.be>
+ */
+#ifndef _LINUX_IOAM6_IPTUNNEL_H
+#define _LINUX_IOAM6_IPTUNNEL_H
+
+#include <uapi/linux/ioam6_iptunnel.h>
+
+#endif /* _LINUX_IOAM6_IPTUNNEL_H */
diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
@@ -76,6 +76,9 @@ struct ipv6_devconf {
 	__s32		disable_policy;
 	__s32           ndisc_tclass;
 	__s32		rpl_seg_enabled;
+	__u32		ioam6_id;
+	__u32		ioam6_id_wide;
+	__u8		ioam6_enabled;
 
 	struct ctl_table_header *sysctl_header;
 };

diff --git a/include/net/ioam6.h b/include/net/ioam6.h
@@ -0,0 +1,67 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ *  IPv6 IOAM implementation
+ *
+ *  Author:
+ *  Justin Iurman <justin.iurman@uliege.be>
+ */
+
+#ifndef _NET_IOAM6_H
+#define _NET_IOAM6_H
+
+#include <linux/net.h>
+#include <linux/ipv6.h>
+#include <linux/ioam6.h>
+#include <linux/rhashtable-types.h>
+
+struct ioam6_namespace {
+	struct rhash_head head;
+	struct rcu_head rcu;
+
+	struct ioam6_schema __rcu *schema;
+
+	__be16 id;
+	__be32 data;
+	__be64 data_wide;
+};
+
+struct ioam6_schema {
+	struct rhash_head head;
+	struct rcu_head rcu;
+
+	struct ioam6_namespace __rcu *ns;
+
+	u32 id;
+	int len;
+	__be32 hdr;
+
+	u8 data[0];
+};
+
+struct ioam6_pernet_data {
+	struct mutex lock;
+	struct rhashtable namespaces;
+	struct rhashtable schemas;
+};
+
+static inline struct ioam6_pernet_data *ioam6_pernet(struct net *net)
+{
+#if IS_ENABLED(CONFIG_IPV6)
+	return net->ipv6.ioam6_data;
+#else
+	return NULL;
+#endif
+}
+
+struct ioam6_namespace *ioam6_namespace(struct net *net, __be16 id);
+void ioam6_fill_trace_data(struct sk_buff *skb,
+			   struct ioam6_namespace *ns,
+			   struct ioam6_trace_hdr *trace);
+
+int ioam6_init(void);
+void ioam6_exit(void);
+
+int ioam6_iptunnel_init(void);
+void ioam6_iptunnel_exit(void);
+
+#endif /* _NET_IOAM6_H */
diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h
@@ -51,6 +51,8 @@ struct netns_sysctl_ipv6 {
 	int max_dst_opts_len;
 	int max_hbh_opts_len;
 	int seg6_flowlabel;
+	u32 ioam6_id;
+	u64 ioam6_id_wide;
 	bool skip_notify_on_dev_down;
 	u8 fib_notify_on_flag_change;
 };
@@ -110,6 +112,7 @@ struct netns_ipv6 {
 		spinlock_t	lock;
 		u32		seq;
 	} ip6addrlbl_table;
+	struct ioam6_pernet_data *ioam6_data;
 };
 
 #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)

diff --git a/include/uapi/linux/in6.h b/include/uapi/linux/in6.h
@@ -145,6 +145,7 @@ struct in6_flowlabel_req {
 #define IPV6_TLV_PADN		1
 #define IPV6_TLV_ROUTERALERT	5
 #define IPV6_TLV_CALIPSO	7	/* RFC 5570 */
+#define IPV6_TLV_IOAM		49	/* TEMPORARY IANA allocation for IOAM */
 #define IPV6_TLV_JUMBO		194
 #define IPV6_TLV_HAO		201	/* home address option */
 

diff --git a/include/uapi/linux/ioam6.h b/include/uapi/linux/ioam6.h
@@ -0,0 +1,133 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/*
+ *  IPv6 IOAM implementation
+ *
+ *  Author:
+ *  Justin Iurman <justin.iurman@uliege.be>
+ */
+
+#ifndef _UAPI_LINUX_IOAM6_H
+#define _UAPI_LINUX_IOAM6_H
+
+#include <asm/byteorder.h>
+#include <linux/types.h>
+
+#define IOAM6_U16_UNAVAILABLE U16_MAX
+#define IOAM6_U32_UNAVAILABLE U32_MAX
+#define IOAM6_U64_UNAVAILABLE U64_MAX
+
+#define IOAM6_DEFAULT_ID (IOAM6_U32_UNAVAILABLE >> 8)
+#define IOAM6_DEFAULT_ID_WIDE (IOAM6_U64_UNAVAILABLE >> 8)
+#define IOAM6_DEFAULT_IF_ID IOAM6_U16_UNAVAILABLE
+#define IOAM6_DEFAULT_IF_ID_WIDE IOAM6_U32_UNAVAILABLE
+
+/*
+ * IPv6 IOAM Option Header
+ */
+struct ioam6_hdr {
+	__u8 opt_type;
+	__u8 opt_len;
+	__u8 :8;				/* reserved */
+#define IOAM6_TYPE_PREALLOC 0
+	__u8 type;
+} __attribute__((packed));
+
+/*
+ * IOAM Trace Header
+ */
+struct ioam6_trace_hdr {
+	__be16	namespace_id;
+
+#if defined(__LITTLE_ENDIAN_BITFIELD)
+
+	__u8	:1,				/* unused */
+		:1,				/* unused */
+		overflow:1,
+		nodelen:5;
+
+	__u8	remlen:7,
+		:1;				/* unused */
+
+	union {
+		__be32 type_be32;
+
+		struct {
+			__u32	bit7:1,
+				bit6:1,
+				bit5:1,
+				bit4:1,
+				bit3:1,
+				bit2:1,
+				bit1:1,
+				bit0:1,
+				bit15:1,	/* unused */
+				bit14:1,	/* unused */
+				bit13:1,	/* unused */
+				bit12:1,	/* unused */
+				bit11:1,
+				bit10:1,
+				bit9:1,
+				bit8:1,
+				bit23:1,	/* reserved */
+				bit22:1,
+				bit21:1,	/* unused */
+				bit20:1,	/* unused */
+				bit19:1,	/* unused */
+				bit18:1,	/* unused */
+				bit17:1,	/* unused */
+				bit16:1,	/* unused */
+				:8;		/* reserved */
+		} type;
+	};
+
+#elif defined(__BIG_ENDIAN_BITFIELD)
+
+	__u8	nodelen:5,
+		overflow:1,
+		:1,				/* unused */
+		:1;				/* unused */
+
+	__u8	:1,				/* unused */
+		remlen:7;
+
+	union {
+		__be32 type_be32;
+
+		struct {
+			__u32	bit0:1,
+				bit1:1,
+				bit2:1,
+				bit3:1,
+				bit4:1,
+				bit5:1,
+				bit6:1,
+				bit7:1,
+				bit8:1,
+				bit9:1,
+				bit10:1,
+				bit11:1,
+				bit12:1,	/* unused */
+				bit13:1,	/* unused */
+				bit14:1,	/* unused */
+				bit15:1,	/* unused */
+				bit16:1,	/* unused */
+				bit17:1,	/* unused */
+				bit18:1,	/* unused */
+				bit19:1,	/* unused */
+				bit20:1,	/* unused */
+				bit21:1,	/* unused */
+				bit22:1,
+				bit23:1,	/* reserved */
+				:8;		/* reserved */
+		} type;
+	};
+
+#else
+#error "Please fix <asm/byteorder.h>"
+#endif
+
+#define IOAM6_TRACE_DATA_SIZE_MAX 244
+	__u8	data[0];
+} __attribute__((packed));
+
+#endif /* _UAPI_LINUX_IOAM6_H */
diff --git a/include/uapi/linux/ioam6_genl.h b/include/uapi/linux/ioam6_genl.h
@@ -0,0 +1,52 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/*
+ *  IPv6 IOAM Generic Netlink API
+ *
+ *  Author:
+ *  Justin Iurman <justin.iurman@uliege.be>
+ */
+
+#ifndef _UAPI_LINUX_IOAM6_GENL_H
+#define _UAPI_LINUX_IOAM6_GENL_H
+
+#define IOAM6_GENL_NAME "IOAM6"
+#define IOAM6_GENL_VERSION 0x1
+
+enum {
+	IOAM6_ATTR_UNSPEC,
+
+	IOAM6_ATTR_NS_ID,	/* u16 */
+	IOAM6_ATTR_NS_DATA,	/* u32 */
+	IOAM6_ATTR_NS_DATA_WIDE,/* u64 */
+
+#define IOAM6_MAX_SCHEMA_DATA_LEN (255 * 4)
+	IOAM6_ATTR_SC_ID,	/* u32 */
+	IOAM6_ATTR_SC_DATA,	/* Binary */
+	IOAM6_ATTR_SC_NONE,	/* Flag */
+
+	IOAM6_ATTR_PAD,
+
+	__IOAM6_ATTR_MAX,
+};
+
+#define IOAM6_ATTR_MAX (__IOAM6_ATTR_MAX - 1)
+
+enum {
+	IOAM6_CMD_UNSPEC,
+
+	IOAM6_CMD_ADD_NAMESPACE,
+	IOAM6_CMD_DEL_NAMESPACE,
+	IOAM6_CMD_DUMP_NAMESPACES,
+
+	IOAM6_CMD_ADD_SCHEMA,
+	IOAM6_CMD_DEL_SCHEMA,
+	IOAM6_CMD_DUMP_SCHEMAS,
+
+	IOAM6_CMD_NS_SET_SCHEMA,
+
+	__IOAM6_CMD_MAX,
+};
+
+#define IOAM6_CMD_MAX (__IOAM6_CMD_MAX - 1)
+
+#endif /* _UAPI_LINUX_IOAM6_GENL_H */