Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Daniel Borkmann says:

====================
The following pull-request contains BPF updates for your *net-next* tree.

There is a small merge conflict in libbpf (Cc Andrii so he's in the loop
as well):

        for (i = 1; i <= btf__get_nr_types(btf); i++) {
                t = (struct btf_type *)btf__type_by_id(btf, i);

                if (!has_datasec && btf_is_var(t)) {
                        /* replace VAR with INT */
                        t->info = BTF_INFO_ENC(BTF_KIND_INT, 0, 0);
  <<<<<<< HEAD
                        /*
                         * using size = 1 is the safest choice, 4 will be too
                         * big and cause kernel BTF validation failure if
                         * original variable took less than 4 bytes
                         */
                        t->size = 1;
                        *(int *)(t+1) = BTF_INT_ENC(0, 0, 8);
                } else if (!has_datasec && kind == BTF_KIND_DATASEC) {
  =======
                        t->size = sizeof(int);
                        *(int *)(t + 1) = BTF_INT_ENC(0, 0, 32);
                } else if (!has_datasec && btf_is_datasec(t)) {
  >>>>>>> 72ef80b5ee
                        /* replace DATASEC with STRUCT */

Conflict is between the two commits 1d4126c4e1 ("libbpf: sanitize VAR to
conservative 1-byte INT") and b03bc6853c ("libbpf: convert libbpf code to
use new btf helpers"), so we need to pick the sanitation fixup as well as
use the new btf_is_datasec() helper and the whitespace cleanup. Looks like
the following:

  [...]
                if (!has_datasec && btf_is_var(t)) {
                        /* replace VAR with INT */
                        t->info = BTF_INFO_ENC(BTF_KIND_INT, 0, 0);
                        /*
                         * using size = 1 is the safest choice, 4 will be too
                         * big and cause kernel BTF validation failure if
                         * original variable took less than 4 bytes
                         */
                        t->size = 1;
                        *(int *)(t + 1) = BTF_INT_ENC(0, 0, 8);
                } else if (!has_datasec && btf_is_datasec(t)) {
                        /* replace DATASEC with STRUCT */
  [...]

The main changes are:

1) Addition of core parts of compile once - run everywhere (co-re) effort,
   that is, relocation of fields offsets in libbpf as well as exposure of
   kernel's own BTF via sysfs and loading through libbpf, from Andrii.

   More info on co-re: http://vger.kernel.org/bpfconf2019.html#session-2
   and http://vger.kernel.org/lpc-bpf2018.html#session-2

2) Enable passing input flags to the BPF flow dissector to customize parsing
   and allowing it to stop early similar to the C based one, from Stanislav.

3) Add a BPF helper function that allows generating SYN cookies from XDP and
   tc BPF, from Petar.

4) Add devmap hash-based map type for more flexibility in device lookup for
   redirects, from Toke.

5) Improvements to XDP forwarding sample code now utilizing recently enabled
   devmap lookups, from Jesper.

6) Add support for reporting the effective cgroup progs in bpftool, from Jakub
   and Takshak.

7) Fix reading kernel config from bpftool via /proc/config.gz, from Peter.

8) Fix AF_XDP umem pages mapping for 32 bit architectures, from Ivan.

9) Follow-up to add two more BPF loop tests for the selftest suite, from Alexei.

10) Add perf event output helper also for other skb-based program types, from Allan.

11) Fix a co-re related compilation error in selftests, from Yonghong.
====================

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>

Documentation/ABI/testing/sysfs-kernel-btf

@@ -0,0 +1,17 @@
+What:		/sys/kernel/btf
+Date:		Aug 2019
+KernelVersion:	5.5
+Contact:	bpf@vger.kernel.org
+Description:
+		Contains BTF type information and related data for kernel and
+		kernel modules.
+
+What:		/sys/kernel/btf/vmlinux
+Date:		Aug 2019
+KernelVersion:	5.5
+Contact:	bpf@vger.kernel.org
+Description:
+		Read-only binary attribute exposing kernel's own BTF type
+		information with description of all internal kernel types. See
+		Documentation/bpf/btf.rst for detailed description of format
+		itself.

Documentation/bpf/prog_flow_dissector.rst

@@ -26,6 +26,7 @@ The inputs are:
   * ``nhoff`` - initial offset of the networking header
   * ``thoff`` - initial offset of the transport header, initialized to nhoff
   * ``n_proto`` - L3 protocol type, parsed out of L2 header
+  * ``flags`` - optional flags
 
 Flow dissector BPF program should fill out the rest of the ``struct
 bpf_flow_keys`` fields. Input arguments ``nhoff/thoff/n_proto`` should be
@@ -101,6 +102,23 @@ can be called for both cases and would have to be written carefully to
 handle both cases.
 
 
+Flags
+=====
+
+``flow_keys->flags`` might contain optional input flags that work as follows:
+
+* ``BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG`` - tells BPF flow dissector to
+  continue parsing first fragment; the default expected behavior is that
+  flow dissector returns as soon as it finds out that the packet is fragmented;
+  used by ``eth_get_headlen`` to estimate length of all headers for GRO.
+* ``BPF_FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL`` - tells BPF flow dissector to
+  stop parsing as soon as it reaches IPv6 flow label; used by
+  ``___skb_get_hash`` and ``__skb_get_hash_symmetric`` to get flow hash.
+* ``BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP`` - tells BPF flow dissector to stop
+  parsing as soon as it reaches encapsulated headers; used by routing
+  infrastructure.
+
+
 Reference Implementation
 ========================
 

include/linux/bpf.h

@@ -713,7 +713,7 @@ struct xdp_buff;
 struct sk_buff;
 
 struct bpf_dtab_netdev *__dev_map_lookup_elem(struct bpf_map *map, u32 key);
-void __dev_map_insert_ctx(struct bpf_map *map, u32 index);
+struct bpf_dtab_netdev *__dev_map_hash_lookup_elem(struct bpf_map *map, u32 key);
 void __dev_map_flush(struct bpf_map *map);
 int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
 		    struct net_device *dev_rx);
@@ -721,7 +721,6 @@ int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb,
 			     struct bpf_prog *xdp_prog);
 
 struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key);
-void __cpu_map_insert_ctx(struct bpf_map *map, u32 index);
 void __cpu_map_flush(struct bpf_map *map);
 int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp,
 		    struct net_device *dev_rx);
@@ -801,8 +800,10 @@ static inline struct net_device  *__dev_map_lookup_elem(struct bpf_map *map,
 	return NULL;
 }
 
-static inline void __dev_map_insert_ctx(struct bpf_map *map, u32 index)
+static inline struct net_device  *__dev_map_hash_lookup_elem(struct bpf_map *map,
+							     u32 key)
 {
+	return NULL;
 }
 
 static inline void __dev_map_flush(struct bpf_map *map)
@@ -834,10 +835,6 @@ struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key)
 	return NULL;
 }
 
-static inline void __cpu_map_insert_ctx(struct bpf_map *map, u32 index)
-{
-}
-
 static inline void __cpu_map_flush(struct bpf_map *map)
 {
 }

include/linux/bpf_types.h

@@ -62,6 +62,7 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY_OF_MAPS, array_of_maps_map_ops)
 BPF_MAP_TYPE(BPF_MAP_TYPE_HASH_OF_MAPS, htab_of_maps_map_ops)
 #ifdef CONFIG_NET
 BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP, dev_map_ops)
+BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP_HASH, dev_map_hash_ops)
 BPF_MAP_TYPE(BPF_MAP_TYPE_SK_STORAGE, sk_storage_map_ops)
 #if defined(CONFIG_BPF_STREAM_PARSER)
 BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKMAP, sock_map_ops)

include/linux/skbuff.h

@@ -1271,7 +1271,7 @@ static inline int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr)
 
 struct bpf_flow_dissector;
 bool bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx,
-		      __be16 proto, int nhoff, int hlen);
+		      __be16 proto, int nhoff, int hlen, unsigned int flags);
 
 bool __skb_flow_dissect(const struct net *net,
 			const struct sk_buff *skb,

include/net/tcp.h

@@ -414,6 +414,16 @@ void tcp_parse_options(const struct net *net, const struct sk_buff *skb,
 		       int estab, struct tcp_fastopen_cookie *foc);
 const u8 *tcp_parse_md5sig_option(const struct tcphdr *th);
 
+/*
+ *	BPF SKB-less helpers
+ */
+u16 tcp_v4_get_syncookie(struct sock *sk, struct iphdr *iph,
+			 struct tcphdr *th, u32 *cookie);
+u16 tcp_v6_get_syncookie(struct sock *sk, struct ipv6hdr *iph,
+			 struct tcphdr *th, u32 *cookie);
+u16 tcp_get_syncookie_mss(struct request_sock_ops *rsk_ops,
+			  const struct tcp_request_sock_ops *af_ops,
+			  struct sock *sk, struct tcphdr *th);
 /*
  *	TCP v4 functions exported for the inet6 API
  */

include/trace/events/xdp.h

@@ -175,7 +175,8 @@ struct _bpf_dtab_netdev {
 #endif /* __DEVMAP_OBJ_TYPE */
 
 #define devmap_ifindex(fwd, map)				\
-	((map->map_type == BPF_MAP_TYPE_DEVMAP) ?		\
+	((map->map_type == BPF_MAP_TYPE_DEVMAP ||		\
+	  map->map_type == BPF_MAP_TYPE_DEVMAP_HASH) ?		\
 	  ((struct _bpf_dtab_netdev *)fwd)->dev->ifindex : 0)
 
 #define _trace_xdp_redirect_map(dev, xdp, fwd, map, idx)		\

include/uapi/linux/bpf.h

@@ -134,6 +134,7 @@ enum bpf_map_type {
 	BPF_MAP_TYPE_QUEUE,
 	BPF_MAP_TYPE_STACK,
 	BPF_MAP_TYPE_SK_STORAGE,
+	BPF_MAP_TYPE_DEVMAP_HASH,
 };
 
 /* Note that tracing related programs such as
@@ -2713,6 +2714,33 @@ union bpf_attr {
  *		**-EPERM** if no permission to send the *sig*.
  *
  *		**-EAGAIN** if bpf program can try again.
+ *
+ * s64 bpf_tcp_gen_syncookie(struct bpf_sock *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len)
+ *	Description
+ *		Try to issue a SYN cookie for the packet with corresponding
+ *		IP/TCP headers, *iph* and *th*, on the listening socket in *sk*.
+ *
+ *		*iph* points to the start of the IPv4 or IPv6 header, while
+ *		*iph_len* contains **sizeof**\ (**struct iphdr**) or
+ *		**sizeof**\ (**struct ip6hdr**).
+ *
+ *		*th* points to the start of the TCP header, while *th_len*
+ *		contains the length of the TCP header.
+ *
+ *	Return
+ *		On success, lower 32 bits hold the generated SYN cookie in
+ *		followed by 16 bits which hold the MSS value for that cookie,
+ *		and the top 16 bits are unused.
+ *
+ *		On failure, the returned value is one of the following:
+ *
+ *		**-EINVAL** SYN cookie cannot be issued due to error
+ *
+ *		**-ENOENT** SYN cookie should not be issued (no SYN flood)
+ *
+ *		**-EOPNOTSUPP** kernel configuration does not enable SYN cookies
+ *
+ *		**-EPROTONOSUPPORT** IP packet version is not 4 or 6
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -2824,7 +2852,8 @@ union bpf_attr {
 	FN(strtoul),			\
 	FN(sk_storage_get),		\
 	FN(sk_storage_delete),		\
-	FN(send_signal),
+	FN(send_signal),		\
+	FN(tcp_gen_syncookie),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
@@ -3507,6 +3536,10 @@ enum bpf_task_fd_type {
 	BPF_FD_TYPE_URETPROBE,		/* filename + offset */
 };
 
+#define BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG		(1U << 0)
+#define BPF_FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL		(1U << 1)
+#define BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP		(1U << 2)
+
 struct bpf_flow_keys {
 	__u16	nhoff;
 	__u16	thoff;
@@ -3528,6 +3561,8 @@ struct bpf_flow_keys {
 			__u32	ipv6_dst[4];	/* in6_addr; network order */
 		};
 	};
+	__u32	flags;
+	__be32	flow_label;
 };
 
 struct bpf_func_info {

kernel/bpf/Makefile

@@ -22,3 +22,6 @@ obj-$(CONFIG_CGROUP_BPF) += cgroup.o
 ifeq ($(CONFIG_INET),y)
 obj-$(CONFIG_BPF_SYSCALL) += reuseport_array.o
 endif
+ifeq ($(CONFIG_SYSFS),y)
+obj-$(CONFIG_DEBUG_INFO_BTF) += sysfs_btf.o
+endif

kernel/bpf/cgroup.c

@@ -964,7 +964,6 @@ static int sockopt_alloc_buf(struct bpf_sockopt_kern *ctx, int max_optlen)
 		return -ENOMEM;
 
 	ctx->optval_end = ctx->optval + max_optlen;
-	ctx->optlen = max_optlen;
 
 	return 0;
 }
@@ -984,7 +983,7 @@ int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level,
 		.level = *level,
 		.optname = *optname,
 	};
-	int ret;
+	int ret, max_optlen;
 
 	/* Opportunistic check to see whether we have any BPF program
 	 * attached to the hook so we don't waste time allocating
@@ -994,10 +993,18 @@ int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level,
 	    __cgroup_bpf_prog_array_is_empty(cgrp, BPF_CGROUP_SETSOCKOPT))
 		return 0;
 
-	ret = sockopt_alloc_buf(&ctx, *optlen);
+	/* Allocate a bit more than the initial user buffer for
+	 * BPF program. The canonical use case is overriding
+	 * TCP_CONGESTION(nv) to TCP_CONGESTION(cubic).
+	 */
+	max_optlen = max_t(int, 16, *optlen);
+
+	ret = sockopt_alloc_buf(&ctx, max_optlen);
 	if (ret)
 		return ret;
 
+	ctx.optlen = *optlen;
+
 	if (copy_from_user(ctx.optval, optval, *optlen) != 0) {
 		ret = -EFAULT;
 		goto out;
@@ -1016,7 +1023,7 @@ int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level,
 	if (ctx.optlen == -1) {
 		/* optlen set to -1, bypass kernel */
 		ret = 1;
-	} else if (ctx.optlen > *optlen || ctx.optlen < -1) {
+	} else if (ctx.optlen > max_optlen || ctx.optlen < -1) {
 		/* optlen is out of bounds */
 		ret = -EFAULT;
 	} else {
@@ -1063,6 +1070,8 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level,
 	if (ret)
 		return ret;
 
+	ctx.optlen = max_optlen;
+
 	if (!retval) {
 		/* If kernel getsockopt finished successfully,
 		 * copy whatever was returned to the user back

kernel/bpf/devmap.c

@@ -37,6 +37,12 @@
  * notifier hook walks the map we know that new dev references can not be
  * added by the user because core infrastructure ensures dev_get_by_index()
  * calls will fail at this point.
+ *
+ * The devmap_hash type is a map type which interprets keys as ifindexes and
+ * indexes these using a hashmap. This allows maps that use ifindex as key to be
+ * densely packed instead of having holes in the lookup array for unused
+ * ifindexes. The setup and packet enqueue/send code is shared between the two
+ * types of devmap; only the lookup and insertion is different.
  */
 #include <linux/bpf.h>
 #include <net/xdp.h>
@@ -59,10 +65,11 @@ struct xdp_bulk_queue {
 
 struct bpf_dtab_netdev {
 	struct net_device *dev; /* must be first member, due to tracepoint */
+	struct hlist_node index_hlist;
 	struct bpf_dtab *dtab;
-	unsigned int bit;
 	struct xdp_bulk_queue __percpu *bulkq;
 	struct rcu_head rcu;
+	unsigned int idx; /* keep track of map index for tracepoint */
 };
 
 struct bpf_dtab {
@@ -70,33 +77,45 @@ struct bpf_dtab {
 	struct bpf_dtab_netdev **netdev_map;
 	struct list_head __percpu *flush_list;
 	struct list_head list;
+
+	/* these are only used for DEVMAP_HASH type maps */
+	struct hlist_head *dev_index_head;
+	spinlock_t index_lock;
+	unsigned int items;
+	u32 n_buckets;
 };
 
 static DEFINE_SPINLOCK(dev_map_lock);
 static LIST_HEAD(dev_map_list);
 
-static struct bpf_map *dev_map_alloc(union bpf_attr *attr)
+static struct hlist_head *dev_map_create_hash(unsigned int entries)
+{
+	int i;
+	struct hlist_head *hash;
+
+	hash = kmalloc_array(entries, sizeof(*hash), GFP_KERNEL);
+	if (hash != NULL)
+		for (i = 0; i < entries; i++)
+			INIT_HLIST_HEAD(&hash[i]);
+
+	return hash;
+}
+
+static int dev_map_init_map(struct bpf_dtab *dtab, union bpf_attr *attr)
 {
-	struct bpf_dtab *dtab;
 	int err, cpu;
 	u64 cost;
 
-	if (!capable(CAP_NET_ADMIN))
-		return ERR_PTR(-EPERM);
-
 	/* check sanity of attributes */
 	if (attr->max_entries == 0 || attr->key_size != 4 ||
 	    attr->value_size != 4 || attr->map_flags & ~DEV_CREATE_FLAG_MASK)
-		return ERR_PTR(-EINVAL);
+		return -EINVAL;
 
 	/* Lookup returns a pointer straight to dev->ifindex, so make sure the
 	 * verifier prevents writes from the BPF side
 	 */
 	attr->map_flags |= BPF_F_RDONLY_PROG;
 
-	dtab = kzalloc(sizeof(*dtab), GFP_USER);
-	if (!dtab)
-		return ERR_PTR(-ENOMEM);
 
 	bpf_map_init_from_attr(&dtab->map, attr);
 
@@ -104,12 +123,18 @@ static struct bpf_map *dev_map_alloc(union bpf_attr *attr)
 	cost = (u64) dtab->map.max_entries * sizeof(struct bpf_dtab_netdev *);
 	cost += sizeof(struct list_head) * num_possible_cpus();
 
+	if (attr->map_type == BPF_MAP_TYPE_DEVMAP_HASH) {
+		dtab->n_buckets = roundup_pow_of_two(dtab->map.max_entries);
+
+		if (!dtab->n_buckets) /* Overflow check */
+			return -EINVAL;
+		cost += sizeof(struct hlist_head) * dtab->n_buckets;
+	}
+
 	/* if map size is larger than memlock limit, reject it */
 	err = bpf_map_charge_init(&dtab->map.memory, cost);
 	if (err)
-		goto free_dtab;
+		return -EINVAL;
-
-	err = -ENOMEM;
 
 	dtab->flush_list = alloc_percpu(struct list_head);
 	if (!dtab->flush_list)
@@ -124,19 +149,48 @@ static struct bpf_map *dev_map_alloc(union bpf_attr *attr)
 	if (!dtab->netdev_map)
 		goto free_percpu;
 
+	if (attr->map_type == BPF_MAP_TYPE_DEVMAP_HASH) {
+		dtab->dev_index_head = dev_map_create_hash(dtab->n_buckets);
+		if (!dtab->dev_index_head)
+			goto free_map_area;
+
+		spin_lock_init(&dtab->index_lock);
+	}
+
+	return 0;
+
+free_map_area:
+	bpf_map_area_free(dtab->netdev_map);
+free_percpu:
+	free_percpu(dtab->flush_list);
+free_charge:
+	bpf_map_charge_finish(&dtab->map.memory);
+	return -ENOMEM;
+}
+
+static struct bpf_map *dev_map_alloc(union bpf_attr *attr)
+{
+	struct bpf_dtab *dtab;
+	int err;
+
+	if (!capable(CAP_NET_ADMIN))
+		return ERR_PTR(-EPERM);
+
+	dtab = kzalloc(sizeof(*dtab), GFP_USER);
+	if (!dtab)
+		return ERR_PTR(-ENOMEM);
+
+	err = dev_map_init_map(dtab, attr);
+	if (err) {
+		kfree(dtab);
+		return ERR_PTR(err);
+	}
+
 	spin_lock(&dev_map_lock);
 	list_add_tail_rcu(&dtab->list, &dev_map_list);
 	spin_unlock(&dev_map_lock);
 
 	return &dtab->map;
-
-free_percpu:
-	free_percpu(dtab->flush_list);
-free_charge:
-	bpf_map_charge_finish(&dtab->map.memory);
-free_dtab:
-	kfree(dtab);
-	return ERR_PTR(err);
 }
 
 static void dev_map_free(struct bpf_map *map)
@@ -188,6 +242,7 @@ static void dev_map_free(struct bpf_map *map)
 
 	free_percpu(dtab->flush_list);
 	bpf_map_area_free(dtab->netdev_map);
+	kfree(dtab->dev_index_head);
 	kfree(dtab);
 }
 
@@ -208,6 +263,70 @@ static int dev_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
 	return 0;
 }
 
+static inline struct hlist_head *dev_map_index_hash(struct bpf_dtab *dtab,
+						    int idx)
+{
+	return &dtab->dev_index_head[idx & (dtab->n_buckets - 1)];
+}
+
+struct bpf_dtab_netdev *__dev_map_hash_lookup_elem(struct bpf_map *map, u32 key)
+{
+	struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
+	struct hlist_head *head = dev_map_index_hash(dtab, key);
+	struct bpf_dtab_netdev *dev;
+
+	hlist_for_each_entry_rcu(dev, head, index_hlist)
+		if (dev->idx == key)
+			return dev;
+
+	return NULL;
+}
+
+static int dev_map_hash_get_next_key(struct bpf_map *map, void *key,
+				    void *next_key)
+{
+	struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
+	u32 idx, *next = next_key;
+	struct bpf_dtab_netdev *dev, *next_dev;
+	struct hlist_head *head;
+	int i = 0;
+
+	if (!key)
+		goto find_first;
+
+	idx = *(u32 *)key;
+
+	dev = __dev_map_hash_lookup_elem(map, idx);
+	if (!dev)
+		goto find_first;
+
+	next_dev = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(&dev->index_hlist)),
+				    struct bpf_dtab_netdev, index_hlist);
+
+	if (next_dev) {
+		*next = next_dev->idx;
+		return 0;
+	}
+
+	i = idx & (dtab->n_buckets - 1);
+	i++;
+
+ find_first:
+	for (; i < dtab->n_buckets; i++) {
+		head = dev_map_index_hash(dtab, i);
+
+		next_dev = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(head)),
+					    struct bpf_dtab_netdev,
+					    index_hlist);
+		if (next_dev) {
+			*next = next_dev->idx;
+			return 0;
+		}
+	}
+
+	return -ENOENT;
+}
+
 static int bq_xmit_all(struct xdp_bulk_queue *bq, u32 flags,
 		       bool in_napi_ctx)
 {
@@ -235,7 +354,7 @@ static int bq_xmit_all(struct xdp_bulk_queue *bq, u32 flags,
 out:
 	bq->count = 0;
 
-	trace_xdp_devmap_xmit(&obj->dtab->map, obj->bit,
+	trace_xdp_devmap_xmit(&obj->dtab->map, obj->idx,
 			      sent, drops, bq->dev_rx, dev, err);
 	bq->dev_rx = NULL;
 	__list_del_clearprev(&bq->flush_node);
@@ -363,6 +482,15 @@ static void *dev_map_lookup_elem(struct bpf_map *map, void *key)
 	return dev ? &dev->ifindex : NULL;
 }
 
+static void *dev_map_hash_lookup_elem(struct bpf_map *map, void *key)
+{
+	struct bpf_dtab_netdev *obj = __dev_map_hash_lookup_elem(map,
+								*(u32 *)key);
+	struct net_device *dev = obj ? obj->dev : NULL;
+
+	return dev ? &dev->ifindex : NULL;
+}
+
 static void dev_map_flush_old(struct bpf_dtab_netdev *dev)
 {
 	if (dev->dev->netdev_ops->ndo_xdp_xmit) {
@@ -412,17 +540,74 @@ static int dev_map_delete_elem(struct bpf_map *map, void *key)
 	return 0;
 }
 
-static int dev_map_update_elem(struct bpf_map *map, void *key, void *value,
+static int dev_map_hash_delete_elem(struct bpf_map *map, void *key)
-				u64 map_flags)
 {
 	struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
-	struct net *net = current->nsproxy->net_ns;
+	struct bpf_dtab_netdev *old_dev;
+	int k = *(u32 *)key;
+	unsigned long flags;
+	int ret = -ENOENT;
+
+	spin_lock_irqsave(&dtab->index_lock, flags);
+
+	old_dev = __dev_map_hash_lookup_elem(map, k);
+	if (old_dev) {
+		dtab->items--;
+		hlist_del_init_rcu(&old_dev->index_hlist);
+		call_rcu(&old_dev->rcu, __dev_map_entry_free);
+		ret = 0;
+	}
+	spin_unlock_irqrestore(&dtab->index_lock, flags);
+
+	return ret;
+}
+
+static struct bpf_dtab_netdev *__dev_map_alloc_node(struct net *net,
+						    struct bpf_dtab *dtab,
+						    u32 ifindex,
+						    unsigned int idx)
+{
 	gfp_t gfp = GFP_ATOMIC | __GFP_NOWARN;
+	struct bpf_dtab_netdev *dev;
+	struct xdp_bulk_queue *bq;
+	int cpu;
+
+	dev = kmalloc_node(sizeof(*dev), gfp, dtab->map.numa_node);
+	if (!dev)
+		return ERR_PTR(-ENOMEM);
+
+	dev->bulkq = __alloc_percpu_gfp(sizeof(*dev->bulkq),
+					sizeof(void *), gfp);
+	if (!dev->bulkq) {
+		kfree(dev);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	for_each_possible_cpu(cpu) {
+		bq = per_cpu_ptr(dev->bulkq, cpu);
+		bq->obj = dev;
+	}
+
+	dev->dev = dev_get_by_index(net, ifindex);
+	if (!dev->dev) {
+		free_percpu(dev->bulkq);
+		kfree(dev);
+		return ERR_PTR(-EINVAL);
+	}
+
+	dev->idx = idx;
+	dev->dtab = dtab;
+
+	return dev;
+}
+
+static int __dev_map_update_elem(struct net *net, struct bpf_map *map,
+				 void *key, void *value, u64 map_flags)
+{
+	struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
 	struct bpf_dtab_netdev *dev, *old_dev;
 	u32 ifindex = *(u32 *)value;
-	struct xdp_bulk_queue *bq;
 	u32 i = *(u32 *)key;
-	int cpu;
 
 	if (unlikely(map_flags > BPF_EXIST))
 		return -EINVAL;
@@ -434,31 +619,9 @@ static int dev_map_update_elem(struct bpf_map *map, void *key, void *value,
 	if (!ifindex) {
 		dev = NULL;
 	} else {
-		dev = kmalloc_node(sizeof(*dev), gfp, map->numa_node);
+		dev = __dev_map_alloc_node(net, dtab, ifindex, i);
-		if (!dev)
+		if (IS_ERR(dev))
-			return -ENOMEM;
+			return PTR_ERR(dev);
-
-		dev->bulkq = __alloc_percpu_gfp(sizeof(*dev->bulkq),
-						sizeof(void *), gfp);
-		if (!dev->bulkq) {
-			kfree(dev);
-			return -ENOMEM;
-		}
-
-		for_each_possible_cpu(cpu) {
-			bq = per_cpu_ptr(dev->bulkq, cpu);
-			bq->obj = dev;
-		}
-
-		dev->dev = dev_get_by_index(net, ifindex);
-		if (!dev->dev) {
-			free_percpu(dev->bulkq);
-			kfree(dev);
-			return -EINVAL;
-		}
-
-		dev->bit = i;
-		dev->dtab = dtab;
 	}
 
 	/* Use call_rcu() here to ensure rcu critical sections have completed
@@ -472,6 +635,63 @@ static int dev_map_update_elem(struct bpf_map *map, void *key, void *value,
 	return 0;
 }
 
+static int dev_map_update_elem(struct bpf_map *map, void *key, void *value,
+			       u64 map_flags)
+{
+	return __dev_map_update_elem(current->nsproxy->net_ns,
+				     map, key, value, map_flags);
+}
+
+static int __dev_map_hash_update_elem(struct net *net, struct bpf_map *map,
+				     void *key, void *value, u64 map_flags)
+{
+	struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
+	struct bpf_dtab_netdev *dev, *old_dev;
+	u32 ifindex = *(u32 *)value;
+	u32 idx = *(u32 *)key;
+	unsigned long flags;
+
+	if (unlikely(map_flags > BPF_EXIST || !ifindex))
+		return -EINVAL;
+
+	old_dev = __dev_map_hash_lookup_elem(map, idx);
+	if (old_dev && (map_flags & BPF_NOEXIST))
+		return -EEXIST;
+
+	dev = __dev_map_alloc_node(net, dtab, ifindex, idx);
+	if (IS_ERR(dev))
+		return PTR_ERR(dev);
+
+	spin_lock_irqsave(&dtab->index_lock, flags);
+
+	if (old_dev) {
+		hlist_del_rcu(&old_dev->index_hlist);
+	} else {
+		if (dtab->items >= dtab->map.max_entries) {
+			spin_unlock_irqrestore(&dtab->index_lock, flags);
+			call_rcu(&dev->rcu, __dev_map_entry_free);
+			return -E2BIG;
+		}
+		dtab->items++;
+	}
+
+	hlist_add_head_rcu(&dev->index_hlist,
+			   dev_map_index_hash(dtab, idx));
+	spin_unlock_irqrestore(&dtab->index_lock, flags);
+
+	if (old_dev)
+		call_rcu(&old_dev->rcu, __dev_map_entry_free);
+
+	return 0;
+}
+
+static int dev_map_hash_update_elem(struct bpf_map *map, void *key, void *value,
+				   u64 map_flags)
+{
+	return __dev_map_hash_update_elem(current->nsproxy->net_ns,
+					 map, key, value, map_flags);
+}
+
 const struct bpf_map_ops dev_map_ops = {
 	.map_alloc = dev_map_alloc,
 	.map_free = dev_map_free,
@@ -482,6 +702,16 @@ const struct bpf_map_ops dev_map_ops = {
 	.map_check_btf = map_check_no_btf,
 };
 
+const struct bpf_map_ops dev_map_hash_ops = {
+	.map_alloc = dev_map_alloc,
+	.map_free = dev_map_free,
+	.map_get_next_key = dev_map_hash_get_next_key,
+	.map_lookup_elem = dev_map_hash_lookup_elem,
+	.map_update_elem = dev_map_hash_update_elem,
+	.map_delete_elem = dev_map_hash_delete_elem,
+	.map_check_btf = map_check_no_btf,
+};
+
 static int dev_map_notification(struct notifier_block *notifier,
 				ulong event, void *ptr)
 {

kernel/bpf/sysfs_btf.c

@@ -0,0 +1,51 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Provide kernel BTF information for introspection and use by eBPF tools.
+ */
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/kobject.h>
+#include <linux/init.h>
+#include <linux/sysfs.h>
+
+/* See scripts/link-vmlinux.sh, gen_btf() func for details */
+extern char __weak _binary__btf_vmlinux_bin_start[];
+extern char __weak _binary__btf_vmlinux_bin_end[];
+
+static ssize_t
+btf_vmlinux_read(struct file *file, struct kobject *kobj,
+		 struct bin_attribute *bin_attr,
+		 char *buf, loff_t off, size_t len)
+{
+	memcpy(buf, _binary__btf_vmlinux_bin_start + off, len);
+	return len;
+}
+
+static struct bin_attribute bin_attr_btf_vmlinux __ro_after_init = {
+	.attr = { .name = "vmlinux", .mode = 0444, },
+	.read = btf_vmlinux_read,
+};
+
+static struct kobject *btf_kobj;
+
+static int __init btf_vmlinux_init(void)
+{
+	int err;
+
+	if (!_binary__btf_vmlinux_bin_start)
+		return 0;
+
+	btf_kobj = kobject_create_and_add("btf", kernel_kobj);
+	if (IS_ERR(btf_kobj)) {
+		err = PTR_ERR(btf_kobj);
+		btf_kobj = NULL;
+		return err;
+	}
+
+	bin_attr_btf_vmlinux.size = _binary__btf_vmlinux_bin_end -
+				    _binary__btf_vmlinux_bin_start;
+
+	return sysfs_create_bin_file(btf_kobj, &bin_attr_btf_vmlinux);
+}
+
+subsys_initcall(btf_vmlinux_init);

kernel/bpf/verifier.c

@@ -3457,6 +3457,7 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
 			goto error;
 		break;
 	case BPF_MAP_TYPE_DEVMAP:
+	case BPF_MAP_TYPE_DEVMAP_HASH:
 		if (func_id != BPF_FUNC_redirect_map &&
 		    func_id != BPF_FUNC_map_lookup_elem)
 			goto error;
@@ -3539,6 +3540,7 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
 		break;
 	case BPF_FUNC_redirect_map:
 		if (map->map_type != BPF_MAP_TYPE_DEVMAP &&
+		    map->map_type != BPF_MAP_TYPE_DEVMAP_HASH &&
 		    map->map_type != BPF_MAP_TYPE_CPUMAP &&
 		    map->map_type != BPF_MAP_TYPE_XSKMAP)
 			goto error;

net/bpf/test_run.c

@@ -377,6 +377,22 @@ out:
 	return ret;
 }
 
+static int verify_user_bpf_flow_keys(struct bpf_flow_keys *ctx)
+{
+	/* make sure the fields we don't use are zeroed */
+	if (!range_is_zero(ctx, 0, offsetof(struct bpf_flow_keys, flags)))
+		return -EINVAL;
+
+	/* flags is allowed */
+
+	if (!range_is_zero(ctx, offsetof(struct bpf_flow_keys, flags) +
+			   FIELD_SIZEOF(struct bpf_flow_keys, flags),
+			   sizeof(struct bpf_flow_keys)))
+		return -EINVAL;
+
+	return 0;
+}
+
 int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog,
 				     const union bpf_attr *kattr,
 				     union bpf_attr __user *uattr)
@@ -384,9 +400,11 @@ int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog,
 	u32 size = kattr->test.data_size_in;
 	struct bpf_flow_dissector ctx = {};
 	u32 repeat = kattr->test.repeat;
+	struct bpf_flow_keys *user_ctx;
 	struct bpf_flow_keys flow_keys;
 	u64 time_start, time_spent = 0;
 	const struct ethhdr *eth;
+	unsigned int flags = 0;
 	u32 retval, duration;
 	void *data;
 	int ret;
@@ -395,9 +413,6 @@ int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog,
 	if (prog->type != BPF_PROG_TYPE_FLOW_DISSECTOR)
 		return -EINVAL;
 
-	if (kattr->test.ctx_in || kattr->test.ctx_out)
-		return -EINVAL;
-
 	if (size < ETH_HLEN)
 		return -EINVAL;
 
@@ -410,6 +425,18 @@ int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog,
 	if (!repeat)
 		repeat = 1;
 
+	user_ctx = bpf_ctx_init(kattr, sizeof(struct bpf_flow_keys));
+	if (IS_ERR(user_ctx)) {
+		kfree(data);
+		return PTR_ERR(user_ctx);
+	}
+	if (user_ctx) {
+		ret = verify_user_bpf_flow_keys(user_ctx);
+		if (ret)
+			goto out;
+		flags = user_ctx->flags;
+	}
+
 	ctx.flow_keys = &flow_keys;
 	ctx.data = data;
 	ctx.data_end = (__u8 *)data + size;
@@ -419,7 +446,7 @@ int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog,
 	time_start = ktime_get_ns();
 	for (i = 0; i < repeat; i++) {
 		retval = bpf_flow_dissect(prog, &ctx, eth->h_proto, ETH_HLEN,
-					  size);
+					  size, flags);
 
 		if (signal_pending(current)) {
 			preempt_enable();
@@ -450,8 +477,12 @@ int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog,
 
 	ret = bpf_test_finish(kattr, uattr, &flow_keys, sizeof(flow_keys),
 			      retval, duration);
+	if (!ret)
+		ret = bpf_ctx_finish(kattr, uattr, user_ctx,
+				     sizeof(struct bpf_flow_keys));
 
 out:
+	kfree(user_ctx);
 	kfree(data);
 	return ret;
 }

net/core/filter.c

@@ -3517,7 +3517,8 @@ static int __bpf_tx_xdp_map(struct net_device *dev_rx, void *fwd,
 	int err;
 
 	switch (map->map_type) {
-	case BPF_MAP_TYPE_DEVMAP: {
+	case BPF_MAP_TYPE_DEVMAP:
+	case BPF_MAP_TYPE_DEVMAP_HASH: {
 		struct bpf_dtab_netdev *dst = fwd;
 
 		err = dev_map_enqueue(dst, xdp, dev_rx);
@@ -3554,6 +3555,7 @@ void xdp_do_flush_map(void)
 	if (map) {
 		switch (map->map_type) {
 		case BPF_MAP_TYPE_DEVMAP:
+		case BPF_MAP_TYPE_DEVMAP_HASH:
 			__dev_map_flush(map);
 			break;
 		case BPF_MAP_TYPE_CPUMAP:
@@ -3574,6 +3576,8 @@ static inline void *__xdp_map_lookup_elem(struct bpf_map *map, u32 index)
 	switch (map->map_type) {
 	case BPF_MAP_TYPE_DEVMAP:
 		return __dev_map_lookup_elem(map, index);
+	case BPF_MAP_TYPE_DEVMAP_HASH:
+		return __dev_map_hash_lookup_elem(map, index);
 	case BPF_MAP_TYPE_CPUMAP:
 		return __cpu_map_lookup_elem(map, index);
 	case BPF_MAP_TYPE_XSKMAP:
@@ -3655,7 +3659,8 @@ static int xdp_do_generic_redirect_map(struct net_device *dev,
 	ri->tgt_value = NULL;
 	WRITE_ONCE(ri->map, NULL);
 
-	if (map->map_type == BPF_MAP_TYPE_DEVMAP) {
+	if (map->map_type == BPF_MAP_TYPE_DEVMAP ||
+	    map->map_type == BPF_MAP_TYPE_DEVMAP_HASH) {
 		struct bpf_dtab_netdev *dst = fwd;
 
 		err = dev_map_generic_redirect(dst, skb, xdp_prog);
@@ -5850,6 +5855,75 @@ static const struct bpf_func_proto bpf_tcp_check_syncookie_proto = {
 	.arg5_type	= ARG_CONST_SIZE,
 };
 
+BPF_CALL_5(bpf_tcp_gen_syncookie, struct sock *, sk, void *, iph, u32, iph_len,
+	   struct tcphdr *, th, u32, th_len)
+{
+#ifdef CONFIG_SYN_COOKIES
+	u32 cookie;
+	u16 mss;
+
+	if (unlikely(th_len < sizeof(*th) || th_len != th->doff * 4))
+		return -EINVAL;
+
+	if (sk->sk_protocol != IPPROTO_TCP || sk->sk_state != TCP_LISTEN)
+		return -EINVAL;
+
+	if (!sock_net(sk)->ipv4.sysctl_tcp_syncookies)
+		return -ENOENT;
+
+	if (!th->syn || th->ack || th->fin || th->rst)
+		return -EINVAL;
+
+	if (unlikely(iph_len < sizeof(struct iphdr)))
+		return -EINVAL;
+
+	/* Both struct iphdr and struct ipv6hdr have the version field at the
+	 * same offset so we can cast to the shorter header (struct iphdr).
+	 */
+	switch (((struct iphdr *)iph)->version) {
+	case 4:
+		if (sk->sk_family == AF_INET6 && sk->sk_ipv6only)
+			return -EINVAL;
+
+		mss = tcp_v4_get_syncookie(sk, iph, th, &cookie);
+		break;
+
+#if IS_BUILTIN(CONFIG_IPV6)
+	case 6:
+		if (unlikely(iph_len < sizeof(struct ipv6hdr)))
+			return -EINVAL;
+
+		if (sk->sk_family != AF_INET6)
+			return -EINVAL;
+
+		mss = tcp_v6_get_syncookie(sk, iph, th, &cookie);
+		break;
+#endif /* CONFIG_IPV6 */
+
+	default:
+		return -EPROTONOSUPPORT;
+	}
+	if (mss <= 0)
+		return -ENOENT;
+
+	return cookie | ((u64)mss << 32);
+#else
+	return -EOPNOTSUPP;
+#endif /* CONFIG_SYN_COOKIES */
+}
+
+static const struct bpf_func_proto bpf_tcp_gen_syncookie_proto = {
+	.func		= bpf_tcp_gen_syncookie,
+	.gpl_only	= true, /* __cookie_v*_init_sequence() is GPL */
+	.pkt_access	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_SOCK_COMMON,
+	.arg2_type	= ARG_PTR_TO_MEM,
+	.arg3_type	= ARG_CONST_SIZE,
+	.arg4_type	= ARG_PTR_TO_MEM,
+	.arg5_type	= ARG_CONST_SIZE,
+};
+
 #endif /* CONFIG_INET */
 
 bool bpf_helper_changes_pkt_data(void *func)
@@ -5999,6 +6073,8 @@ sk_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_get_socket_cookie_proto;
 	case BPF_FUNC_get_socket_uid:
 		return &bpf_get_socket_uid_proto;
+	case BPF_FUNC_perf_event_output:
+		return &bpf_skb_event_output_proto;
 	default:
 		return bpf_base_func_proto(func_id);
 	}
@@ -6019,6 +6095,8 @@ cg_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_sk_storage_get_proto;
 	case BPF_FUNC_sk_storage_delete:
 		return &bpf_sk_storage_delete_proto;
+	case BPF_FUNC_perf_event_output:
+		return &bpf_skb_event_output_proto;
 #ifdef CONFIG_SOCK_CGROUP_DATA
 	case BPF_FUNC_skb_cgroup_id:
 		return &bpf_skb_cgroup_id_proto;
@@ -6135,6 +6213,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_tcp_check_syncookie_proto;
 	case BPF_FUNC_skb_ecn_set_ce:
 		return &bpf_skb_ecn_set_ce_proto;
+	case BPF_FUNC_tcp_gen_syncookie:
+		return &bpf_tcp_gen_syncookie_proto;
 #endif
 	default:
 		return bpf_base_func_proto(func_id);
@@ -6174,6 +6254,8 @@ xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_xdp_skc_lookup_tcp_proto;
 	case BPF_FUNC_tcp_check_syncookie:
 		return &bpf_tcp_check_syncookie_proto;
+	case BPF_FUNC_tcp_gen_syncookie:
+		return &bpf_tcp_gen_syncookie_proto;
 #endif
 	default:
 		return bpf_base_func_proto(func_id);
@@ -6267,6 +6349,8 @@ sk_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_sk_redirect_map_proto;
 	case BPF_FUNC_sk_redirect_hash:
 		return &bpf_sk_redirect_hash_proto;
+	case BPF_FUNC_perf_event_output:
+		return &bpf_skb_event_output_proto;
 #ifdef CONFIG_INET
 	case BPF_FUNC_sk_lookup_tcp:
 		return &bpf_sk_lookup_tcp_proto;

net/core/flow_dissector.c

@@ -737,6 +737,7 @@ static void __skb_flow_bpf_to_target(const struct bpf_flow_keys *flow_keys,
 	struct flow_dissector_key_basic *key_basic;
 	struct flow_dissector_key_addrs *key_addrs;
 	struct flow_dissector_key_ports *key_ports;
+	struct flow_dissector_key_tags *key_tags;
 
 	key_control = skb_flow_dissector_target(flow_dissector,
 						FLOW_DISSECTOR_KEY_CONTROL,
@@ -781,10 +782,18 @@ static void __skb_flow_bpf_to_target(const struct bpf_flow_keys *flow_keys,
 		key_ports->src = flow_keys->sport;
 		key_ports->dst = flow_keys->dport;
 	}
+
+	if (dissector_uses_key(flow_dissector,
+			       FLOW_DISSECTOR_KEY_FLOW_LABEL)) {
+		key_tags = skb_flow_dissector_target(flow_dissector,
+						     FLOW_DISSECTOR_KEY_FLOW_LABEL,
+						     target_container);
+		key_tags->flow_label = ntohl(flow_keys->flow_label);
+	}
 }
 
 bool bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx,
-		      __be16 proto, int nhoff, int hlen)
+		      __be16 proto, int nhoff, int hlen, unsigned int flags)
 {
 	struct bpf_flow_keys *flow_keys = ctx->flow_keys;
 	u32 result;
@@ -795,6 +804,14 @@ bool bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx,
 	flow_keys->nhoff = nhoff;
 	flow_keys->thoff = flow_keys->nhoff;
 
+	BUILD_BUG_ON((int)BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG !=
+		     (int)FLOW_DISSECTOR_F_PARSE_1ST_FRAG);
+	BUILD_BUG_ON((int)BPF_FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL !=
+		     (int)FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL);
+	BUILD_BUG_ON((int)BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP !=
+		     (int)FLOW_DISSECTOR_F_STOP_AT_ENCAP);
+	flow_keys->flags = flags;
+
 	preempt_disable();
 	result = BPF_PROG_RUN(prog, ctx);
 	preempt_enable();
@@ -914,7 +931,7 @@ bool __skb_flow_dissect(const struct net *net,
 			}
 
 			ret = bpf_flow_dissect(attached, &ctx, n_proto, nhoff,
-					       hlen);
+					       hlen, flags);
 			__skb_flow_bpf_to_target(&flow_keys, flow_dissector,
 						 target_container);
 			rcu_read_unlock();

net/ipv4/tcp_input.c

@@ -3782,6 +3782,49 @@ static void smc_parse_options(const struct tcphdr *th,
 #endif
 }
 
+/* Try to parse the MSS option from the TCP header. Return 0 on failure, clamped
+ * value on success.
+ */
+static u16 tcp_parse_mss_option(const struct tcphdr *th, u16 user_mss)
+{
+	const unsigned char *ptr = (const unsigned char *)(th + 1);
+	int length = (th->doff * 4) - sizeof(struct tcphdr);
+	u16 mss = 0;
+
+	while (length > 0) {
+		int opcode = *ptr++;
+		int opsize;
+
+		switch (opcode) {
+		case TCPOPT_EOL:
+			return mss;
+		case TCPOPT_NOP:	/* Ref: RFC 793 section 3.1 */
+			length--;
+			continue;
+		default:
+			if (length < 2)
+				return mss;
+			opsize = *ptr++;
+			if (opsize < 2) /* "silly options" */
+				return mss;
+			if (opsize > length)
+				return mss;	/* fail on partial options */
+			if (opcode == TCPOPT_MSS && opsize == TCPOLEN_MSS) {
+				u16 in_mss = get_unaligned_be16(ptr);
+
+				if (in_mss) {
+					if (user_mss && user_mss < in_mss)
+						in_mss = user_mss;
+					mss = in_mss;
+				}
+			}
+			ptr += opsize - 2;
+			length -= opsize;
+		}
+	}
+	return mss;
+}
+
 /* Look for tcp options. Normally only called on SYN and SYNACK packets.
  * But, this can also be called on packets in the established flow when
  * the fast version below fails.
@@ -6422,9 +6465,7 @@ EXPORT_SYMBOL(inet_reqsk_alloc);
 /*
  * Return true if a syncookie should be sent
  */
-static bool tcp_syn_flood_action(const struct sock *sk,
+static bool tcp_syn_flood_action(const struct sock *sk, const char *proto)
-				 const struct sk_buff *skb,
-				 const char *proto)
 {
 	struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue;
 	const char *msg = "Dropping request";
@@ -6444,7 +6485,7 @@ static bool tcp_syn_flood_action(const struct sock *sk,
 	    net->ipv4.sysctl_tcp_syncookies != 2 &&
 	    xchg(&queue->synflood_warned, 1) == 0)
 		net_info_ratelimited("%s: Possible SYN flooding on port %d. %s.  Check SNMP counters.\n",
-				     proto, ntohs(tcp_hdr(skb)->dest), msg);
+				     proto, sk->sk_num, msg);
 
 	return want_cookie;
 }
@@ -6466,6 +6507,36 @@ static void tcp_reqsk_record_syn(const struct sock *sk,
 	}
 }
 
+/* If a SYN cookie is required and supported, returns a clamped MSS value to be
+ * used for SYN cookie generation.
+ */
+u16 tcp_get_syncookie_mss(struct request_sock_ops *rsk_ops,
+			  const struct tcp_request_sock_ops *af_ops,
+			  struct sock *sk, struct tcphdr *th)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+	u16 mss;
+
+	if (sock_net(sk)->ipv4.sysctl_tcp_syncookies != 2 &&
+	    !inet_csk_reqsk_queue_is_full(sk))
+		return 0;
+
+	if (!tcp_syn_flood_action(sk, rsk_ops->slab_name))
+		return 0;
+
+	if (sk_acceptq_is_full(sk)) {
+		NET_INC_STATS(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS);
+		return 0;
+	}
+
+	mss = tcp_parse_mss_option(th, tp->rx_opt.user_mss);
+	if (!mss)
+		mss = af_ops->mss_clamp;
+
+	return mss;
+}
+EXPORT_SYMBOL_GPL(tcp_get_syncookie_mss);
+
 int tcp_conn_request(struct request_sock_ops *rsk_ops,
 		     const struct tcp_request_sock_ops *af_ops,
 		     struct sock *sk, struct sk_buff *skb)
@@ -6487,7 +6558,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 	 */
 	if ((net->ipv4.sysctl_tcp_syncookies == 2 ||
 	     inet_csk_reqsk_queue_is_full(sk)) && !isn) {
-		want_cookie = tcp_syn_flood_action(sk, skb, rsk_ops->slab_name);
+		want_cookie = tcp_syn_flood_action(sk, rsk_ops->slab_name);
 		if (!want_cookie)
 			goto drop;
 	}

net/ipv4/tcp_ipv4.c

@@ -1515,6 +1515,21 @@ static struct sock *tcp_v4_cookie_check(struct sock *sk, struct sk_buff *skb)
 	return sk;
 }
 
+u16 tcp_v4_get_syncookie(struct sock *sk, struct iphdr *iph,
+			 struct tcphdr *th, u32 *cookie)
+{
+	u16 mss = 0;
+#ifdef CONFIG_SYN_COOKIES
+	mss = tcp_get_syncookie_mss(&tcp_request_sock_ops,
+				    &tcp_request_sock_ipv4_ops, sk, th);
+	if (mss) {
+		*cookie = __cookie_v4_init_sequence(iph, th, &mss);
+		tcp_synq_overflow(sk);
+	}
+#endif
+	return mss;
+}
+
 /* The socket must have it's spinlock held when we get
  * here, unless it is a TCP_LISTEN socket.
  *

net/ipv6/tcp_ipv6.c

@@ -1063,6 +1063,21 @@ static struct sock *tcp_v6_cookie_check(struct sock *sk, struct sk_buff *skb)
 	return sk;
 }
 
+u16 tcp_v6_get_syncookie(struct sock *sk, struct ipv6hdr *iph,
+			 struct tcphdr *th, u32 *cookie)
+{
+	u16 mss = 0;
+#ifdef CONFIG_SYN_COOKIES
+	mss = tcp_get_syncookie_mss(&tcp6_request_sock_ops,
+				    &tcp_request_sock_ipv6_ops, sk, th);
+	if (mss) {
+		*cookie = __cookie_v6_init_sequence(iph, th, &mss);
+		tcp_synq_overflow(sk);
+	}
+#endif
+	return mss;
+}
+
 static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
 {
 	if (skb->protocol == htons(ETH_P_IP))

net/xdp/xdp_umem.c

@@ -14,6 +14,7 @@
 #include <linux/netdevice.h>
 #include <linux/rtnetlink.h>
 #include <linux/idr.h>
+#include <linux/highmem.h>
 
 #include "xdp_umem.h"
 #include "xsk_queue.h"
@@ -164,6 +165,14 @@ void xdp_umem_clear_dev(struct xdp_umem *umem)
 	umem->zc = false;
 }
 
+static void xdp_umem_unmap_pages(struct xdp_umem *umem)
+{
+	unsigned int i;
+
+	for (i = 0; i < umem->npgs; i++)
+		kunmap(umem->pgs[i]);
+}
+
 static void xdp_umem_unpin_pages(struct xdp_umem *umem)
 {
 	unsigned int i;
@@ -207,6 +216,7 @@ static void xdp_umem_release(struct xdp_umem *umem)
 
 	xsk_reuseq_destroy(umem);
 
+	xdp_umem_unmap_pages(umem);
 	xdp_umem_unpin_pages(umem);
 
 	kfree(umem->pages);
@@ -369,7 +379,7 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
 	}
 
 	for (i = 0; i < umem->npgs; i++)
-		umem->pages[i].addr = page_address(umem->pgs[i]);
+		umem->pages[i].addr = kmap(umem->pgs[i]);
 
 	return 0;
 

samples/bpf/trace_output_user.c

@@ -18,9 +18,6 @@
 #include <libbpf.h>
 #include "bpf_load.h"
 #include "perf-sys.h"
-#include "trace_helpers.h"
-
-static int pmu_fd;
 
 static __u64 time_get_ns(void)
 {
@@ -31,12 +28,12 @@ static __u64 time_get_ns(void)
 }
 
 static __u64 start_time;
+static __u64 cnt;
 
 #define MAX_CNT 100000ll
 
-static int print_bpf_output(void *data, int size)
+static void print_bpf_output(void *ctx, int cpu, void *data, __u32 size)
 {
-	static __u64 cnt;
 	struct {
 		__u64 pid;
 		__u64 cookie;
@@ -45,7 +42,7 @@ static int print_bpf_output(void *data, int size)
 	if (e->cookie != 0x12345678) {
 		printf("BUG pid %llx cookie %llx sized %d\n",
 		       e->pid, e->cookie, size);
-		return LIBBPF_PERF_EVENT_ERROR;
+		return;
 	}
 
 	cnt++;
@@ -53,30 +50,14 @@ static int print_bpf_output(void *data, int size)
 	if (cnt == MAX_CNT) {
 		printf("recv %lld events per sec\n",
 		       MAX_CNT * 1000000000ll / (time_get_ns() - start_time));
-		return LIBBPF_PERF_EVENT_DONE;
+		return;
 	}
-
-	return LIBBPF_PERF_EVENT_CONT;
-}
-
-static void test_bpf_perf_event(void)
-{
-	struct perf_event_attr attr = {
-		.sample_type = PERF_SAMPLE_RAW,
-		.type = PERF_TYPE_SOFTWARE,
-		.config = PERF_COUNT_SW_BPF_OUTPUT,
-	};
-	int key = 0;
-
-	pmu_fd = sys_perf_event_open(&attr, -1/*pid*/, 0/*cpu*/, -1/*group_fd*/, 0);
-
-	assert(pmu_fd >= 0);
-	assert(bpf_map_update_elem(map_fd[0], &key, &pmu_fd, BPF_ANY) == 0);
-	ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0);
 }
 
 int main(int argc, char **argv)
 {
+	struct perf_buffer_opts pb_opts = {};
+	struct perf_buffer *pb;
 	char filename[256];
 	FILE *f;
 	int ret;
@@ -88,16 +69,20 @@ int main(int argc, char **argv)
 		return 1;
 	}
 
-	test_bpf_perf_event();
+	pb_opts.sample_cb = print_bpf_output;
-
+	pb = perf_buffer__new(map_fd[0], 8, &pb_opts);
-	if (perf_event_mmap(pmu_fd) < 0)
+	ret = libbpf_get_error(pb);
+	if (ret) {
+		printf("failed to setup perf_buffer: %d\n", ret);
 		return 1;
+	}
 
 	f = popen("taskset 1 dd if=/dev/zero of=/dev/null", "r");
 	(void) f;
 
 	start_time = time_get_ns();
-	ret = perf_event_poller(pmu_fd, print_bpf_output);
+	while ((ret = perf_buffer__poll(pb, 1000)) >= 0 && cnt < MAX_CNT) {
+	}
 	kill(0, SIGINT);
 	return ret;
 }

samples/bpf/xdp_fwd_kern.c

@@ -23,7 +23,8 @@
 
 #define IPV6_FLOWINFO_MASK              cpu_to_be32(0x0FFFFFFF)
 
-struct bpf_map_def SEC("maps") tx_port = {
+/* For TX-traffic redirect requires net_device ifindex to be in this devmap */
+struct bpf_map_def SEC("maps") xdp_tx_ports = {
 	.type = BPF_MAP_TYPE_DEVMAP,
 	.key_size = sizeof(int),
 	.value_size = sizeof(int),
@@ -102,14 +103,34 @@ static __always_inline int xdp_fwd_flags(struct xdp_md *ctx, u32 flags)
 	fib_params.ifindex = ctx->ingress_ifindex;
 
 	rc = bpf_fib_lookup(ctx, &fib_params, sizeof(fib_params), flags);
-
+	/*
-	/* verify egress index has xdp support
+	 * Some rc (return codes) from bpf_fib_lookup() are important,
-	 * TO-DO bpf_map_lookup_elem(&tx_port, &key) fails with
+	 * to understand how this XDP-prog interacts with network stack.
-	 *       cannot pass map_type 14 into func bpf_map_lookup_elem#1:
+	 *
-	 * NOTE: without verification that egress index supports XDP
+	 * BPF_FIB_LKUP_RET_NO_NEIGH:
-	 *       forwarding packets are dropped.
+	 *  Even if route lookup was a success, then the MAC-addresses are also
+	 *  needed.  This is obtained from arp/neighbour table, but if table is
+	 *  (still) empty then BPF_FIB_LKUP_RET_NO_NEIGH is returned.  To avoid
+	 *  doing ARP lookup directly from XDP, then send packet to normal
+	 *  network stack via XDP_PASS and expect it will do ARP resolution.
+	 *
+	 * BPF_FIB_LKUP_RET_FWD_DISABLED:
+	 *  The bpf_fib_lookup respect sysctl net.ipv{4,6}.conf.all.forwarding
+	 *  setting, and will return BPF_FIB_LKUP_RET_FWD_DISABLED if not
+	 *  enabled this on ingress device.
 	 */
-	if (rc == 0) {
+	if (rc == BPF_FIB_LKUP_RET_SUCCESS) {
+		/* Verify egress index has been configured as TX-port.
+		 * (Note: User can still have inserted an egress ifindex that
+		 * doesn't support XDP xmit, which will result in packet drops).
+		 *
+		 * Note: lookup in devmap supported since 0cdbb4b09a0.
+		 * If not supported will fail with:
+		 *  cannot pass map_type 14 into func bpf_map_lookup_elem#1:
+		 */
+		if (!bpf_map_lookup_elem(&xdp_tx_ports, &fib_params.ifindex))
+			return XDP_PASS;
+
 		if (h_proto == htons(ETH_P_IP))
 			ip_decrease_ttl(iph);
 		else if (h_proto == htons(ETH_P_IPV6))
@@ -117,7 +138,7 @@ static __always_inline int xdp_fwd_flags(struct xdp_md *ctx, u32 flags)
 
 		memcpy(eth->h_dest, fib_params.dmac, ETH_ALEN);
 		memcpy(eth->h_source, fib_params.smac, ETH_ALEN);
-		return bpf_redirect_map(&tx_port, fib_params.ifindex, 0);
+		return bpf_redirect_map(&xdp_tx_ports, fib_params.ifindex, 0);
 	}
 
 	return XDP_PASS;

samples/bpf/xdp_fwd_user.c

@@ -27,14 +27,20 @@
 #include "libbpf.h"
 #include <bpf/bpf.h>
 
-
+static int do_attach(int idx, int prog_fd, int map_fd, const char *name)
-static int do_attach(int idx, int fd, const char *name)
 {
 	int err;
 
-	err = bpf_set_link_xdp_fd(idx, fd, 0);
+	err = bpf_set_link_xdp_fd(idx, prog_fd, 0);
-	if (err < 0)
+	if (err < 0) {
 		printf("ERROR: failed to attach program to %s\n", name);
+		return err;
+	}
+
+	/* Adding ifindex as a possible egress TX port */
+	err = bpf_map_update_elem(map_fd, &idx, &idx, 0);
+	if (err)
+		printf("ERROR: failed using device %s as TX-port\n", name);
 
 	return err;
 }
@@ -47,6 +53,9 @@ static int do_detach(int idx, const char *name)
 	if (err < 0)
 		printf("ERROR: failed to detach program from %s\n", name);
 
+	/* TODO: Remember to cleanup map, when adding use of shared map
+	 *  bpf_map_delete_elem((map_fd, &idx);
+	 */
 	return err;
 }
 
@@ -67,10 +76,10 @@ int main(int argc, char **argv)
 	};
 	const char *prog_name = "xdp_fwd";
 	struct bpf_program *prog;
+	int prog_fd, map_fd = -1;
 	char filename[PATH_MAX];
 	struct bpf_object *obj;
 	int opt, i, idx, err;
-	int prog_fd, map_fd;
 	int attach = 1;
 	int ret = 0;
 
@@ -103,8 +112,14 @@ int main(int argc, char **argv)
 			return 1;
 		}
 
-		if (bpf_prog_load_xattr(&prog_load_attr, &obj, &prog_fd))
+		err = bpf_prog_load_xattr(&prog_load_attr, &obj, &prog_fd);
+		if (err) {
+			printf("Does kernel support devmap lookup?\n");
+			/* If not, the error message will be:
+			 *  "cannot pass map_type 14 into func bpf_map_lookup_elem#1"
+			 */
 			return 1;
+		}
 
 		prog = bpf_object__find_program_by_title(obj, prog_name);
 		prog_fd = bpf_program__fd(prog);
@@ -113,16 +128,12 @@ int main(int argc, char **argv)
 			return 1;
 		}
 		map_fd = bpf_map__fd(bpf_object__find_map_by_name(obj,
-								  "tx_port"));
+							"xdp_tx_ports"));
 		if (map_fd < 0) {
 			printf("map not found: %s\n", strerror(map_fd));
 			return 1;
 		}
 	}
-	if (attach) {
-		for (i = 1; i < 64; ++i)
-			bpf_map_update_elem(map_fd, &i, &i, 0);
-	}
 
 	for (i = optind; i < argc; ++i) {
 		idx = if_nametoindex(argv[i]);
@@ -138,7 +149,7 @@ int main(int argc, char **argv)
 			if (err)
 				ret = err;
 		} else {
-			err = do_attach(idx, prog_fd, argv[i]);
+			err = do_attach(idx, prog_fd, map_fd, argv[i]);
 			if (err)
 				ret = err;
 		}

samples/bpf/xdp_sample_pkts_user.c

@@ -17,14 +17,13 @@
 #include <linux/if_link.h>
 
 #include "perf-sys.h"
-#include "trace_helpers.h"
 
 #define MAX_CPUS 128
-static int pmu_fds[MAX_CPUS], if_idx;
+static int if_idx;
-static struct perf_event_mmap_page *headers[MAX_CPUS];
 static char *if_name;
 static __u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
 static __u32 prog_id;
+static struct perf_buffer *pb = NULL;
 
 static int do_attach(int idx, int fd, const char *name)
 {
@@ -73,7 +72,7 @@ static int do_detach(int idx, const char *name)
 
 #define SAMPLE_SIZE 64
 
-static int print_bpf_output(void *data, int size)
+static void print_bpf_output(void *ctx, int cpu, void *data, __u32 size)
 {
 	struct {
 		__u16 cookie;
@@ -83,45 +82,20 @@ static int print_bpf_output(void *data, int size)
 	int i;
 
 	if (e->cookie != 0xdead) {
-		printf("BUG cookie %x sized %d\n",
+		printf("BUG cookie %x sized %d\n", e->cookie, size);
-		       e->cookie, size);
+		return;
-		return LIBBPF_PERF_EVENT_ERROR;
 	}
 
 	printf("Pkt len: %-5d bytes. Ethernet hdr: ", e->pkt_len);
 	for (i = 0; i < 14 && i < e->pkt_len; i++)
 		printf("%02x ", e->pkt_data[i]);
 	printf("\n");
-
-	return LIBBPF_PERF_EVENT_CONT;
-}
-
-static void test_bpf_perf_event(int map_fd, int num)
-{
-	struct perf_event_attr attr = {
-		.sample_type = PERF_SAMPLE_RAW,
-		.type = PERF_TYPE_SOFTWARE,
-		.config = PERF_COUNT_SW_BPF_OUTPUT,
-		.wakeup_events = 1, /* get an fd notification for every event */
-	};
-	int i;
-
-	for (i = 0; i < num; i++) {
-		int key = i;
-
-		pmu_fds[i] = sys_perf_event_open(&attr, -1/*pid*/, i/*cpu*/,
-						 -1/*group_fd*/, 0);
-
-		assert(pmu_fds[i] >= 0);
-		assert(bpf_map_update_elem(map_fd, &key,
-					   &pmu_fds[i], BPF_ANY) == 0);
-		ioctl(pmu_fds[i], PERF_EVENT_IOC_ENABLE, 0);
-	}
 }
 
 static void sig_handler(int signo)
 {
 	do_detach(if_idx, if_name);
+	perf_buffer__free(pb);
 	exit(0);
 }
 
@@ -140,13 +114,13 @@ int main(int argc, char **argv)
 	struct bpf_prog_load_attr prog_load_attr = {
 		.prog_type	= BPF_PROG_TYPE_XDP,
 	};
+	struct perf_buffer_opts pb_opts = {};
 	const char *optstr = "F";
 	int prog_fd, map_fd, opt;
 	struct bpf_object *obj;
 	struct bpf_map *map;
 	char filename[256];
-	int ret, err, i;
+	int ret, err;
-	int numcpus;
 
 	while ((opt = getopt(argc, argv, optstr)) != -1) {
 		switch (opt) {
@@ -169,10 +143,6 @@ int main(int argc, char **argv)
 		return 1;
 	}
 
-	numcpus = get_nprocs();
-	if (numcpus > MAX_CPUS)
-		numcpus = MAX_CPUS;
-
 	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
 	prog_load_attr.file = filename;
 
@@ -211,14 +181,17 @@ int main(int argc, char **argv)
 		return 1;
 	}
 
-	test_bpf_perf_event(map_fd, numcpus);
+	pb_opts.sample_cb = print_bpf_output;
+	pb = perf_buffer__new(map_fd, 8, &pb_opts);
+	err = libbpf_get_error(pb);
+	if (err) {
+		perror("perf_buffer setup failed");
+		return 1;
+	}
 
-	for (i = 0; i < numcpus; i++)
+	while ((ret = perf_buffer__poll(pb, 1000)) >= 0) {
-		if (perf_event_mmap_header(pmu_fds[i], &headers[i]) < 0)
+	}
-			return 1;
 
-	ret = perf_event_poller_multi(pmu_fds, headers, numcpus,
-				      print_bpf_output);
 	kill(0, SIGINT);
 	return ret;
 }

scripts/link-vmlinux.sh

@@ -56,8 +56,8 @@ modpost_link()
 }
 
 # Link of vmlinux
-# ${1} - optional extra .o files
+# ${1} - output file
-# ${2} - output file
+# ${@:2} - optional extra .o files
 vmlinux_link()
 {
 	local lds="${objtree}/${KBUILD_LDS}"
@@ -70,9 +70,9 @@ vmlinux_link()
 			--start-group				\
 			${KBUILD_VMLINUX_LIBS}			\
 			--end-group				\
-			${1}"
+			${@:2}"
 
-		${LD} ${KBUILD_LDFLAGS} ${LDFLAGS_vmlinux} -o ${2}	\
+		${LD} ${KBUILD_LDFLAGS} ${LDFLAGS_vmlinux} -o ${1}	\
 			-T ${lds} ${objects}
 	else
 		objects="-Wl,--whole-archive			\
@@ -81,9 +81,9 @@ vmlinux_link()
 			-Wl,--start-group			\
 			${KBUILD_VMLINUX_LIBS}			\
 			-Wl,--end-group				\
-			${1}"
+			${@:2}"
 
-		${CC} ${CFLAGS_vmlinux} -o ${2}			\
+		${CC} ${CFLAGS_vmlinux} -o ${1}			\
 			-Wl,-T,${lds}				\
 			${objects}				\
 			-lutil -lrt -lpthread
@@ -92,23 +92,34 @@ vmlinux_link()
 }
 
 # generate .BTF typeinfo from DWARF debuginfo
+# ${1} - vmlinux image
+# ${2} - file to dump raw BTF data into
 gen_btf()
 {
-	local pahole_ver;
+	local pahole_ver
+	local bin_arch
 
 	if ! [ -x "$(command -v ${PAHOLE})" ]; then
 		info "BTF" "${1}: pahole (${PAHOLE}) is not available"
-		return 0
+		return 1
 	fi
 
 	pahole_ver=$(${PAHOLE} --version | sed -E 's/v([0-9]+)\.([0-9]+)/\1\2/')
 	if [ "${pahole_ver}" -lt "113" ]; then
 		info "BTF" "${1}: pahole version $(${PAHOLE} --version) is too old, need at least v1.13"
-		return 0
+		return 1
 	fi
 
-	info "BTF" ${1}
+	info "BTF" ${2}
+	vmlinux_link ${1}
 	LLVM_OBJCOPY=${OBJCOPY} ${PAHOLE} -J ${1}
+
+	# dump .BTF section into raw binary file to link with final vmlinux
+	bin_arch=$(${OBJDUMP} -f ${1} | grep architecture | \
+		cut -d, -f1 | cut -d' ' -f2)
+	${OBJCOPY} --dump-section .BTF=.btf.vmlinux.bin ${1} 2>/dev/null
+	${OBJCOPY} -I binary -O ${CONFIG_OUTPUT_FORMAT} -B ${bin_arch} \
+		--rename-section .data=.BTF .btf.vmlinux.bin ${2}
 }
 
 # Create ${2} .o file with all symbols from the ${1} object file
@@ -153,6 +164,7 @@ sortextable()
 # Delete output files in case of error
 cleanup()
 {
+	rm -f .btf.*
 	rm -f .tmp_System.map
 	rm -f .tmp_kallsyms*
 	rm -f .tmp_vmlinux*
@@ -215,6 +227,13 @@ ${MAKE} -f "${srctree}/scripts/Makefile.modpost" MODPOST_VMLINUX=1
 info MODINFO modules.builtin.modinfo
 ${OBJCOPY} -j .modinfo -O binary vmlinux.o modules.builtin.modinfo
 
+btf_vmlinux_bin_o=""
+if [ -n "${CONFIG_DEBUG_INFO_BTF}" ]; then
+	if gen_btf .tmp_vmlinux.btf .btf.vmlinux.bin.o ; then
+		btf_vmlinux_bin_o=.btf.vmlinux.bin.o
+	fi
+fi
+
 kallsymso=""
 kallsyms_vmlinux=""
 if [ -n "${CONFIG_KALLSYMS}" ]; then
@@ -246,11 +265,11 @@ if [ -n "${CONFIG_KALLSYMS}" ]; then
 	kallsyms_vmlinux=.tmp_vmlinux2
 
 	# step 1
-	vmlinux_link "" .tmp_vmlinux1
+	vmlinux_link .tmp_vmlinux1 ${btf_vmlinux_bin_o}
 	kallsyms .tmp_vmlinux1 .tmp_kallsyms1.o
 
 	# step 2
-	vmlinux_link .tmp_kallsyms1.o .tmp_vmlinux2
+	vmlinux_link .tmp_vmlinux2 .tmp_kallsyms1.o ${btf_vmlinux_bin_o}
 	kallsyms .tmp_vmlinux2 .tmp_kallsyms2.o
 
 	# step 3
@@ -261,18 +280,13 @@ if [ -n "${CONFIG_KALLSYMS}" ]; then
 		kallsymso=.tmp_kallsyms3.o
 		kallsyms_vmlinux=.tmp_vmlinux3
 
-		vmlinux_link .tmp_kallsyms2.o .tmp_vmlinux3
+		vmlinux_link .tmp_vmlinux3 .tmp_kallsyms2.o ${btf_vmlinux_bin_o}
-
 		kallsyms .tmp_vmlinux3 .tmp_kallsyms3.o
 	fi
 fi
 
 info LD vmlinux
-vmlinux_link "${kallsymso}" vmlinux
+vmlinux_link vmlinux "${kallsymso}" "${btf_vmlinux_bin_o}"
-
-if [ -n "${CONFIG_DEBUG_INFO_BTF}" ]; then
-	gen_btf vmlinux
-fi
 
 if [ -n "${CONFIG_BUILDTIME_EXTABLE_SORT}" ]; then
 	info SORTEX vmlinux

tools/bpf/bpftool/Documentation/bpftool-cgroup.rst

@@ -20,8 +20,8 @@ SYNOPSIS
 CGROUP COMMANDS
 ===============
 
-|	**bpftool** **cgroup { show | list }** *CGROUP*
+|	**bpftool** **cgroup { show | list }** *CGROUP* [**effective**]
-|	**bpftool** **cgroup tree** [*CGROUP_ROOT*]
+|	**bpftool** **cgroup tree** [*CGROUP_ROOT*] [**effective**]
 |	**bpftool** **cgroup attach** *CGROUP* *ATTACH_TYPE* *PROG* [*ATTACH_FLAGS*]
 |	**bpftool** **cgroup detach** *CGROUP* *ATTACH_TYPE* *PROG*
 |	**bpftool** **cgroup help**
@@ -35,13 +35,17 @@ CGROUP COMMANDS
 
 DESCRIPTION
 ===========
-	**bpftool cgroup { show | list }** *CGROUP*
+	**bpftool cgroup { show | list }** *CGROUP* [**effective**]
 		  List all programs attached to the cgroup *CGROUP*.
 
 		  Output will start with program ID followed by attach type,
 		  attach flags and program name.
 
-	**bpftool cgroup tree** [*CGROUP_ROOT*]
+		  If **effective** is specified retrieve effective programs that
+		  will execute for events within a cgroup. This includes
+		  inherited along with attached ones.
+
+	**bpftool cgroup tree** [*CGROUP_ROOT*] [**effective**]
 		  Iterate over all cgroups in *CGROUP_ROOT* and list all
 		  attached programs. If *CGROUP_ROOT* is not specified,
 		  bpftool uses cgroup v2 mountpoint.
@@ -50,6 +54,10 @@ DESCRIPTION
 		  commands: it starts with absolute cgroup path, followed by
 		  program ID, attach type, attach flags and program name.
 
+		  If **effective** is specified retrieve effective programs that
+		  will execute for events within a cgroup. This includes
+		  inherited along with attached ones.
+
 	**bpftool cgroup attach** *CGROUP* *ATTACH_TYPE* *PROG* [*ATTACH_FLAGS*]
 		  Attach program *PROG* to the cgroup *CGROUP* with attach type
 		  *ATTACH_TYPE* and optional *ATTACH_FLAGS*.

tools/bpf/bpftool/Documentation/bpftool-map.rst

@@ -46,7 +46,7 @@ MAP COMMANDS
 |	*TYPE* := { **hash** | **array** | **prog_array** | **perf_event_array** | **percpu_hash**
 |		| **percpu_array** | **stack_trace** | **cgroup_array** | **lru_hash**
 |		| **lru_percpu_hash** | **lpm_trie** | **array_of_maps** | **hash_of_maps**
-|		| **devmap** | **sockmap** | **cpumap** | **xskmap** | **sockhash**
+|		| **devmap** | **devmap_hash** | **sockmap** | **cpumap** | **xskmap** | **sockhash**
 |		| **cgroup_storage** | **reuseport_sockarray** | **percpu_cgroup_storage**
 |		| **queue** | **stack** }
 

tools/bpf/bpftool/Makefile

@@ -52,14 +52,14 @@ ifneq ($(EXTRA_LDFLAGS),)
 LDFLAGS += $(EXTRA_LDFLAGS)
 endif
 
-LIBS = -lelf $(LIBBPF)
+LIBS = -lelf -lz $(LIBBPF)
 
 INSTALL ?= install
 RM ?= rm -f
 
 FEATURE_USER = .bpftool
-FEATURE_TESTS = libbfd disassembler-four-args reallocarray
+FEATURE_TESTS = libbfd disassembler-four-args reallocarray zlib
-FEATURE_DISPLAY = libbfd disassembler-four-args
+FEATURE_DISPLAY = libbfd disassembler-four-args zlib
 
 check_feat := 1
 NON_CHECK_FEAT_TARGETS := clean uninstall doc doc-clean doc-install doc-uninstall
@@ -111,6 +111,8 @@ OBJS = $(patsubst %.c,$(OUTPUT)%.o,$(SRCS)) $(OUTPUT)disasm.o
 $(OUTPUT)disasm.o: $(srctree)/kernel/bpf/disasm.c
 	$(QUIET_CC)$(COMPILE.c) -MMD -o $@ $<
 
+$(OUTPUT)feature.o: | zdep
+
 $(OUTPUT)bpftool: $(OBJS) $(LIBBPF)
 	$(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) -o $@ $^ $(LIBS)
 
@@ -149,6 +151,9 @@ doc-uninstall:
 
 FORCE:
 
-.PHONY: all FORCE clean install uninstall
+zdep:
+	@if [ "$(feature-zlib)" != "1" ]; then echo "No zlib found"; exit 1 ; fi
+
+.PHONY: all FORCE clean install uninstall zdep
 .PHONY: doc doc-clean doc-install doc-uninstall
 .DEFAULT_GOAL := all

tools/bpf/bpftool/bash-completion/bpftool

@@ -489,8 +489,8 @@ _bpftool()
                                 perf_event_array percpu_hash percpu_array \
                                 stack_trace cgroup_array lru_hash \
                                 lru_percpu_hash lpm_trie array_of_maps \
-                                hash_of_maps devmap sockmap cpumap xskmap \
+                                hash_of_maps devmap devmap_hash sockmap cpumap \
-                                sockhash cgroup_storage reuseport_sockarray \
+                                xskmap sockhash cgroup_storage reuseport_sockarray \
                                 percpu_cgroup_storage queue stack' -- \
                                                    "$cur" ) )
                             return 0
@@ -710,12 +710,15 @@ _bpftool()
             ;;
         cgroup)
             case $command in
-                show|list)
+                show|list|tree)
-                    _filedir
+                    case $cword in
-                    return 0
+                        3)
-                    ;;
+                            _filedir
-                tree)
+                            ;;
-                    _filedir
+                        4)
+                            COMPREPLY=( $( compgen -W 'effective' -- "$cur" ) )
+                            ;;
+                    esac
                     return 0
                     ;;
                 attach|detach)

tools/bpf/bpftool/cgroup.c

@@ -29,6 +29,8 @@
 	"                        recvmsg4 | recvmsg6 | sysctl |\n"	       \
 	"                        getsockopt | setsockopt }"
 
+static unsigned int query_flags;
+
 static const char * const attach_type_strings[] = {
 	[BPF_CGROUP_INET_INGRESS] = "ingress",
 	[BPF_CGROUP_INET_EGRESS] = "egress",
@@ -107,7 +109,8 @@ static int count_attached_bpf_progs(int cgroup_fd, enum bpf_attach_type type)
 	__u32 prog_cnt = 0;
 	int ret;
 
-	ret = bpf_prog_query(cgroup_fd, type, 0, NULL, NULL, &prog_cnt);
+	ret = bpf_prog_query(cgroup_fd, type, query_flags, NULL,
+			     NULL, &prog_cnt);
 	if (ret)
 		return -1;
 
@@ -125,8 +128,8 @@ static int show_attached_bpf_progs(int cgroup_fd, enum bpf_attach_type type,
 	int ret;
 
 	prog_cnt = ARRAY_SIZE(prog_ids);
-	ret = bpf_prog_query(cgroup_fd, type, 0, &attach_flags, prog_ids,
+	ret = bpf_prog_query(cgroup_fd, type, query_flags, &attach_flags,
-			     &prog_cnt);
+			     prog_ids, &prog_cnt);
 	if (ret)
 		return ret;
 
@@ -158,20 +161,34 @@ static int show_attached_bpf_progs(int cgroup_fd, enum bpf_attach_type type,
 static int do_show(int argc, char **argv)
 {
 	enum bpf_attach_type type;
+	const char *path;
 	int cgroup_fd;
 	int ret = -1;
 
-	if (argc < 1) {
+	query_flags = 0;
-		p_err("too few parameters for cgroup show");
+
-		goto exit;
+	if (!REQ_ARGS(1))
-	} else if (argc > 1) {
+		return -1;
-		p_err("too many parameters for cgroup show");
+	path = GET_ARG();
-		goto exit;
+
+	while (argc) {
+		if (is_prefix(*argv, "effective")) {
+			if (query_flags & BPF_F_QUERY_EFFECTIVE) {
+				p_err("duplicated argument: %s", *argv);
+				return -1;
+			}
+			query_flags |= BPF_F_QUERY_EFFECTIVE;
+			NEXT_ARG();
+		} else {
+			p_err("expected no more arguments, 'effective', got: '%s'?",
+			      *argv);
+			return -1;
+		}
 	}
 
-	cgroup_fd = open(argv[0], O_RDONLY);
+	cgroup_fd = open(path, O_RDONLY);
 	if (cgroup_fd < 0) {
-		p_err("can't open cgroup %s", argv[0]);
+		p_err("can't open cgroup %s", path);
 		goto exit;
 	}
 
@@ -294,25 +311,36 @@ static char *find_cgroup_root(void)
 
 static int do_show_tree(int argc, char **argv)
 {
-	char *cgroup_root;
+	char *cgroup_root, *cgroup_alloced = NULL;
 	int ret;
 
-	switch (argc) {
+	query_flags = 0;
-	case 0:
+
-		cgroup_root = find_cgroup_root();
+	if (!argc) {
-		if (!cgroup_root) {
+		cgroup_alloced = find_cgroup_root();
+		if (!cgroup_alloced) {
 			p_err("cgroup v2 isn't mounted");
 			return -1;
 		}
-		break;
+		cgroup_root = cgroup_alloced;
-	case 1:
+	} else {
-		cgroup_root = argv[0];
+		cgroup_root = GET_ARG();
-		break;
-	default:
-		p_err("too many parameters for cgroup tree");
-		return -1;
-	}
 
+		while (argc) {
+			if (is_prefix(*argv, "effective")) {
+				if (query_flags & BPF_F_QUERY_EFFECTIVE) {
+					p_err("duplicated argument: %s", *argv);
+					return -1;
+				}
+				query_flags |= BPF_F_QUERY_EFFECTIVE;
+				NEXT_ARG();
+			} else {
+				p_err("expected no more arguments, 'effective', got: '%s'?",
+				      *argv);
+				return -1;
+			}
+		}
+	}
 
 	if (json_output)
 		jsonw_start_array(json_wtr);
@@ -338,8 +366,7 @@ static int do_show_tree(int argc, char **argv)
 	if (json_output)
 		jsonw_end_array(json_wtr);
 
-	if (argc == 0)
+	free(cgroup_alloced);
-		free(cgroup_root);
 
 	return ret;
 }
@@ -459,8 +486,8 @@ static int do_help(int argc, char **argv)
 	}
 
 	fprintf(stderr,
-		"Usage: %s %s { show | list } CGROUP\n"
+		"Usage: %s %s { show | list } CGROUP [**effective**]\n"
-		"       %s %s tree [CGROUP_ROOT]\n"
+		"       %s %s tree [CGROUP_ROOT] [**effective**]\n"
 		"       %s %s attach CGROUP ATTACH_TYPE PROG [ATTACH_FLAGS]\n"
 		"       %s %s detach CGROUP ATTACH_TYPE PROG\n"
 		"       %s %s help\n"

tools/bpf/bpftool/feature.c

@@ -14,6 +14,7 @@
 
 #include <bpf.h>
 #include <libbpf.h>
+#include <zlib.h>
 
 #include "main.h"
 
@@ -284,34 +285,32 @@ static void probe_jit_limit(void)
 	}
 }
 
-static char *get_kernel_config_option(FILE *fd, const char *option)
+static bool read_next_kernel_config_option(gzFile file, char *buf, size_t n,
+					   char **value)
 {
-	size_t line_n = 0, optlen = strlen(option);
+	char *sep;
-	char *res, *strval, *line = NULL;
-	ssize_t n;
 
-	rewind(fd);
+	while (gzgets(file, buf, n)) {
-	while ((n = getline(&line, &line_n, fd)) > 0) {
+		if (strncmp(buf, "CONFIG_", 7))
-		if (strncmp(line, option, optlen))
 			continue;
-		/* Check we have at least '=', value, and '\n' */
+
-		if (strlen(line) < optlen + 3)
+		sep = strchr(buf, '=');
-			continue;
+		if (!sep)
-		if (*(line + optlen) != '=')
 			continue;
 
 		/* Trim ending '\n' */
-		line[strlen(line) - 1] = '\0';
+		buf[strlen(buf) - 1] = '\0';
 
-		/* Copy and return config option value */
+		/* Split on '=' and ensure that a value is present. */
-		strval = line + optlen + 1;
+		*sep = '\0';
-		res = strdup(strval);
+		if (!sep[1])
-		free(line);
+			continue;
-		return res;
+
+		*value = sep + 1;
+		return true;
 	}
-	free(line);
 
-	return NULL;
+	return false;
 }
 
 static void probe_kernel_image_config(void)
@@ -386,59 +385,61 @@ static void probe_kernel_image_config(void)
 		/* test_bpf module for BPF tests */
 		"CONFIG_TEST_BPF",
 	};
-	char *value, *buf = NULL;
+	char *values[ARRAY_SIZE(options)] = { };
 	struct utsname utsn;
 	char path[PATH_MAX];
-	size_t i, n;
+	gzFile file = NULL;
-	ssize_t ret;
+	char buf[4096];
-	FILE *fd;
+	char *value;
+	size_t i;
 
-	if (uname(&utsn))
+	if (!uname(&utsn)) {
-		goto no_config;
+		snprintf(path, sizeof(path), "/boot/config-%s", utsn.release);
 
-	snprintf(path, sizeof(path), "/boot/config-%s", utsn.release);
+		/* gzopen also accepts uncompressed files. */
-
+		file = gzopen(path, "r");
-	fd = fopen(path, "r");
-	if (!fd && errno == ENOENT) {
-		/* Some distributions put the config file at /proc/config, give
-		 * it a try.
-		 * Sometimes it is also at /proc/config.gz but we do not try
-		 * this one for now, it would require linking against libz.
-		 */
-		fd = fopen("/proc/config", "r");
 	}
-	if (!fd) {
+
+	if (!file) {
+		/* Some distributions build with CONFIG_IKCONFIG=y and put the
+		 * config file at /proc/config.gz.
+		 */
+		file = gzopen("/proc/config.gz", "r");
+	}
+	if (!file) {
 		p_info("skipping kernel config, can't open file: %s",
 		       strerror(errno));
-		goto no_config;
+		goto end_parse;
 	}
 	/* Sanity checks */
-	ret = getline(&buf, &n, fd);
+	if (!gzgets(file, buf, sizeof(buf)) ||
-	ret = getline(&buf, &n, fd);
+	    !gzgets(file, buf, sizeof(buf))) {
-	if (!buf || !ret) {
 		p_info("skipping kernel config, can't read from file: %s",
 		       strerror(errno));
-		free(buf);
+		goto end_parse;
-		goto no_config;
 	}
 	if (strcmp(buf, "# Automatically generated file; DO NOT EDIT.\n")) {
 		p_info("skipping kernel config, can't find correct file");
-		free(buf);
+		goto end_parse;
-		goto no_config;
 	}
-	free(buf);
+
+	while (read_next_kernel_config_option(file, buf, sizeof(buf), &value)) {
+		for (i = 0; i < ARRAY_SIZE(options); i++) {
+			if (values[i] || strcmp(buf, options[i]))
+				continue;
+
+			values[i] = strdup(value);
+		}
+	}
+
+end_parse:
+	if (file)
+		gzclose(file);
 
 	for (i = 0; i < ARRAY_SIZE(options); i++) {
-		value = get_kernel_config_option(fd, options[i]);
+		print_kernel_option(options[i], values[i]);
-		print_kernel_option(options[i], value);
+		free(values[i]);
-		free(value);
 	}
-	fclose(fd);
-	return;
-
-no_config:
-	for (i = 0; i < ARRAY_SIZE(options); i++)
-		print_kernel_option(options[i], NULL);
 }
 
 static bool probe_bpf_syscall(const char *define_prefix)

tools/bpf/bpftool/map.c

@@ -37,6 +37,7 @@ const char * const map_type_name[] = {
 	[BPF_MAP_TYPE_ARRAY_OF_MAPS]		= "array_of_maps",
 	[BPF_MAP_TYPE_HASH_OF_MAPS]		= "hash_of_maps",
 	[BPF_MAP_TYPE_DEVMAP]			= "devmap",
+	[BPF_MAP_TYPE_DEVMAP_HASH]		= "devmap_hash",
 	[BPF_MAP_TYPE_SOCKMAP]			= "sockmap",
 	[BPF_MAP_TYPE_CPUMAP]			= "cpumap",
 	[BPF_MAP_TYPE_XSKMAP]			= "xskmap",
@@ -1271,7 +1272,7 @@ static int do_help(int argc, char **argv)
 		"       TYPE := { hash | array | prog_array | perf_event_array | percpu_hash |\n"
 		"                 percpu_array | stack_trace | cgroup_array | lru_hash |\n"
 		"                 lru_percpu_hash | lpm_trie | array_of_maps | hash_of_maps |\n"
-		"                 devmap | sockmap | cpumap | xskmap | sockhash |\n"
+		"                 devmap | devmap_hash | sockmap | cpumap | xskmap | sockhash |\n"
 		"                 cgroup_storage | reuseport_sockarray | percpu_cgroup_storage }\n"
 		"       " HELP_SPEC_OPTIONS "\n"
 		"",

tools/include/uapi/linux/bpf.h

@@ -134,6 +134,7 @@ enum bpf_map_type {
 	BPF_MAP_TYPE_QUEUE,
 	BPF_MAP_TYPE_STACK,
 	BPF_MAP_TYPE_SK_STORAGE,
+	BPF_MAP_TYPE_DEVMAP_HASH,
 };
 
 /* Note that tracing related programs such as
@@ -1571,8 +1572,11 @@ union bpf_attr {
  * 		but this is only implemented for native XDP (with driver
  * 		support) as of this writing).
  *
- * 		All values for *flags* are reserved for future usage, and must
+ * 		The lower two bits of *flags* are used as the return code if
- * 		be left at zero.
+ * 		the map lookup fails. This is so that the return value can be
+ * 		one of the XDP program return codes up to XDP_TX, as chosen by
+ * 		the caller. Any higher bits in the *flags* argument must be
+ * 		unset.
  *
  * 		When used to redirect packets to net devices, this helper
  * 		provides a high performance increase over **bpf_redirect**\ ().
@@ -2710,6 +2714,33 @@ union bpf_attr {
  *		**-EPERM** if no permission to send the *sig*.
  *
  *		**-EAGAIN** if bpf program can try again.
+ *
+ * s64 bpf_tcp_gen_syncookie(struct bpf_sock *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len)
+ *	Description
+ *		Try to issue a SYN cookie for the packet with corresponding
+ *		IP/TCP headers, *iph* and *th*, on the listening socket in *sk*.
+ *
+ *		*iph* points to the start of the IPv4 or IPv6 header, while
+ *		*iph_len* contains **sizeof**\ (**struct iphdr**) or
+ *		**sizeof**\ (**struct ip6hdr**).
+ *
+ *		*th* points to the start of the TCP header, while *th_len*
+ *		contains the length of the TCP header.
+ *
+ *	Return
+ *		On success, lower 32 bits hold the generated SYN cookie in
+ *		followed by 16 bits which hold the MSS value for that cookie,
+ *		and the top 16 bits are unused.
+ *
+ *		On failure, the returned value is one of the following:
+ *
+ *		**-EINVAL** SYN cookie cannot be issued due to error
+ *
+ *		**-ENOENT** SYN cookie should not be issued (no SYN flood)
+ *
+ *		**-EOPNOTSUPP** kernel configuration does not enable SYN cookies
+ *
+ *		**-EPROTONOSUPPORT** IP packet version is not 4 or 6
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -2821,7 +2852,8 @@ union bpf_attr {
 	FN(strtoul),			\
 	FN(sk_storage_get),		\
 	FN(sk_storage_delete),		\
-	FN(send_signal),
+	FN(send_signal),		\
+	FN(tcp_gen_syncookie),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
@@ -3504,6 +3536,10 @@ enum bpf_task_fd_type {
 	BPF_FD_TYPE_URETPROBE,		/* filename + offset */
 };
 
+#define BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG		(1U << 0)
+#define BPF_FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL		(1U << 1)
+#define BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP		(1U << 2)
+
 struct bpf_flow_keys {
 	__u16	nhoff;
 	__u16	thoff;
@@ -3525,6 +3561,8 @@ struct bpf_flow_keys {
 			__u32	ipv6_dst[4];	/* in6_addr; network order */
 		};
 	};
+	__u32	flags;
+	__be32	flow_label;
 };
 
 struct bpf_func_info {

tools/lib/bpf/btf.c

@@ -20,13 +20,6 @@
 #define BTF_MAX_NR_TYPES 0x7fffffff
 #define BTF_MAX_STR_OFFSET 0x7fffffff
 
-#define IS_MODIFIER(k) (((k) == BTF_KIND_TYPEDEF) || \
-		((k) == BTF_KIND_VOLATILE) || \
-		((k) == BTF_KIND_CONST) || \
-		((k) == BTF_KIND_RESTRICT))
-
-#define IS_VAR(k) ((k) == BTF_KIND_VAR)
-
 static struct btf_type btf_void;
 
 struct btf {
@@ -43,47 +36,6 @@ struct btf {
 	int fd;
 };
 
-struct btf_ext_info {
-	/*
-	 * info points to the individual info section (e.g. func_info and
-	 * line_info) from the .BTF.ext. It does not include the __u32 rec_size.
-	 */
-	void *info;
-	__u32 rec_size;
-	__u32 len;
-};
-
-struct btf_ext {
-	union {
-		struct btf_ext_header *hdr;
-		void *data;
-	};
-	struct btf_ext_info func_info;
-	struct btf_ext_info line_info;
-	__u32 data_size;
-};
-
-struct btf_ext_info_sec {
-	__u32	sec_name_off;
-	__u32	num_info;
-	/* Followed by num_info * record_size number of bytes */
-	__u8	data[0];
-};
-
-/* The minimum bpf_func_info checked by the loader */
-struct bpf_func_info_min {
-	__u32   insn_off;
-	__u32   type_id;
-};
-
-/* The minimum bpf_line_info checked by the loader */
-struct bpf_line_info_min {
-	__u32	insn_off;
-	__u32	file_name_off;
-	__u32	line_off;
-	__u32	line_col;
-};
-
 static inline __u64 ptr_to_u64(const void *ptr)
 {
 	return (__u64) (unsigned long) ptr;
@@ -193,9 +145,9 @@ static int btf_parse_str_sec(struct btf *btf)
 static int btf_type_size(struct btf_type *t)
 {
 	int base_size = sizeof(struct btf_type);
-	__u16 vlen = BTF_INFO_VLEN(t->info);
+	__u16 vlen = btf_vlen(t);
 
-	switch (BTF_INFO_KIND(t->info)) {
+	switch (btf_kind(t)) {
 	case BTF_KIND_FWD:
 	case BTF_KIND_CONST:
 	case BTF_KIND_VOLATILE:
@@ -220,7 +172,7 @@ static int btf_type_size(struct btf_type *t)
 	case BTF_KIND_DATASEC:
 		return base_size + vlen * sizeof(struct btf_var_secinfo);
 	default:
-		pr_debug("Unsupported BTF_KIND:%u\n", BTF_INFO_KIND(t->info));
+		pr_debug("Unsupported BTF_KIND:%u\n", btf_kind(t));
 		return -EINVAL;
 	}
 }
@@ -264,7 +216,7 @@ const struct btf_type *btf__type_by_id(const struct btf *btf, __u32 type_id)
 
 static bool btf_type_is_void(const struct btf_type *t)
 {
-	return t == &btf_void || BTF_INFO_KIND(t->info) == BTF_KIND_FWD;
+	return t == &btf_void || btf_is_fwd(t);
 }
 
 static bool btf_type_is_void_or_null(const struct btf_type *t)
@@ -285,7 +237,7 @@ __s64 btf__resolve_size(const struct btf *btf, __u32 type_id)
 	t = btf__type_by_id(btf, type_id);
 	for (i = 0; i < MAX_RESOLVE_DEPTH && !btf_type_is_void_or_null(t);
 	     i++) {
-		switch (BTF_INFO_KIND(t->info)) {
+		switch (btf_kind(t)) {
 		case BTF_KIND_INT:
 		case BTF_KIND_STRUCT:
 		case BTF_KIND_UNION:
@@ -304,7 +256,7 @@ __s64 btf__resolve_size(const struct btf *btf, __u32 type_id)
 			type_id = t->type;
 			break;
 		case BTF_KIND_ARRAY:
-			array = (const struct btf_array *)(t + 1);
+			array = btf_array(t);
 			if (nelems && array->nelems > UINT32_MAX / nelems)
 				return -E2BIG;
 			nelems *= array->nelems;
@@ -335,8 +287,7 @@ int btf__resolve_type(const struct btf *btf, __u32 type_id)
 	t = btf__type_by_id(btf, type_id);
 	while (depth < MAX_RESOLVE_DEPTH &&
 	       !btf_type_is_void_or_null(t) &&
-	       (IS_MODIFIER(BTF_INFO_KIND(t->info)) ||
+	       (btf_is_mod(t) || btf_is_typedef(t) || btf_is_var(t))) {
-		IS_VAR(BTF_INFO_KIND(t->info)))) {
 		type_id = t->type;
 		t = btf__type_by_id(btf, type_id);
 		depth++;
@@ -555,11 +506,11 @@ static int compare_vsi_off(const void *_a, const void *_b)
 static int btf_fixup_datasec(struct bpf_object *obj, struct btf *btf,
 			     struct btf_type *t)
 {
-	__u32 size = 0, off = 0, i, vars = BTF_INFO_VLEN(t->info);
+	__u32 size = 0, off = 0, i, vars = btf_vlen(t);
 	const char *name = btf__name_by_offset(btf, t->name_off);
 	const struct btf_type *t_var;
 	struct btf_var_secinfo *vsi;
-	struct btf_var *var;
+	const struct btf_var *var;
 	int ret;
 
 	if (!name) {
@@ -575,12 +526,11 @@ static int btf_fixup_datasec(struct bpf_object *obj, struct btf *btf,
 
 	t->size = size;
 
-	for (i = 0, vsi = (struct btf_var_secinfo *)(t + 1);
+	for (i = 0, vsi = btf_var_secinfos(t); i < vars; i++, vsi++) {
-	     i < vars; i++, vsi++) {
 		t_var = btf__type_by_id(btf, vsi->type);
-		var = (struct btf_var *)(t_var + 1);
+		var = btf_var(t_var);
 
-		if (BTF_INFO_KIND(t_var->info) != BTF_KIND_VAR) {
+		if (!btf_is_var(t_var)) {
 			pr_debug("Non-VAR type seen in section %s\n", name);
 			return -EINVAL;
 		}
@@ -596,7 +546,8 @@ static int btf_fixup_datasec(struct bpf_object *obj, struct btf *btf,
 
 		ret = bpf_object__variable_offset(obj, name, &off);
 		if (ret) {
-			pr_debug("No offset found in symbol table for VAR %s\n", name);
+			pr_debug("No offset found in symbol table for VAR %s\n",
+				 name);
 			return -ENOENT;
 		}
 
@@ -620,7 +571,7 @@ int btf__finalize_data(struct bpf_object *obj, struct btf *btf)
 		 * is section size and global variable offset. We use
 		 * the info from the ELF itself for this purpose.
 		 */
-		if (BTF_INFO_KIND(t->info) == BTF_KIND_DATASEC) {
+		if (btf_is_datasec(t)) {
 			err = btf_fixup_datasec(obj, btf, t);
 			if (err)
 				break;
@@ -775,14 +726,13 @@ int btf__get_map_kv_tids(const struct btf *btf, const char *map_name,
 		return -EINVAL;
 	}
 
-	if (BTF_INFO_KIND(container_type->info) != BTF_KIND_STRUCT ||
+	if (!btf_is_struct(container_type) || btf_vlen(container_type) < 2) {
-	    BTF_INFO_VLEN(container_type->info) < 2) {
 		pr_warning("map:%s container_name:%s is an invalid container struct\n",
 			   map_name, container_name);
 		return -EINVAL;
 	}
 
-	key = (struct btf_member *)(container_type + 1);
+	key = btf_members(container_type);
 	value = key + 1;
 
 	key_size = btf__resolve_size(btf, key->type);
@@ -832,6 +782,9 @@ static int btf_ext_setup_info(struct btf_ext *btf_ext,
 	/* The start of the info sec (including the __u32 record_size). */
 	void *info;
 
+	if (ext_sec->len == 0)
+		return 0;
+
 	if (ext_sec->off & 0x03) {
 		pr_debug(".BTF.ext %s section is not aligned to 4 bytes\n",
 		     ext_sec->desc);
@@ -935,11 +888,24 @@ static int btf_ext_setup_line_info(struct btf_ext *btf_ext)
 	return btf_ext_setup_info(btf_ext, &param);
 }
 
+static int btf_ext_setup_offset_reloc(struct btf_ext *btf_ext)
+{
+	struct btf_ext_sec_setup_param param = {
+		.off = btf_ext->hdr->offset_reloc_off,
+		.len = btf_ext->hdr->offset_reloc_len,
+		.min_rec_size = sizeof(struct bpf_offset_reloc),
+		.ext_info = &btf_ext->offset_reloc_info,
+		.desc = "offset_reloc",
+	};
+
+	return btf_ext_setup_info(btf_ext, &param);
+}
+
 static int btf_ext_parse_hdr(__u8 *data, __u32 data_size)
 {
 	const struct btf_ext_header *hdr = (struct btf_ext_header *)data;
 
-	if (data_size < offsetof(struct btf_ext_header, func_info_off) ||
+	if (data_size < offsetofend(struct btf_ext_header, hdr_len) ||
 	    data_size < hdr->hdr_len) {
 		pr_debug("BTF.ext header not found");
 		return -EINVAL;
@@ -997,6 +963,9 @@ struct btf_ext *btf_ext__new(__u8 *data, __u32 size)
 	}
 	memcpy(btf_ext->data, data, size);
 
+	if (btf_ext->hdr->hdr_len <
+	    offsetofend(struct btf_ext_header, line_info_len))
+		goto done;
 	err = btf_ext_setup_func_info(btf_ext);
 	if (err)
 		goto done;
@@ -1005,6 +974,13 @@ struct btf_ext *btf_ext__new(__u8 *data, __u32 size)
 	if (err)
 		goto done;
 
+	if (btf_ext->hdr->hdr_len <
+	    offsetofend(struct btf_ext_header, offset_reloc_len))
+		goto done;
+	err = btf_ext_setup_offset_reloc(btf_ext);
+	if (err)
+		goto done;
+
 done:
 	if (err) {
 		btf_ext__free(btf_ext);
@@ -1441,10 +1417,9 @@ static struct btf_dedup *btf_dedup_new(struct btf *btf, struct btf_ext *btf_ext,
 	d->map[0] = 0;
 	for (i = 1; i <= btf->nr_types; i++) {
 		struct btf_type *t = d->btf->types[i];
-		__u16 kind = BTF_INFO_KIND(t->info);
 
 		/* VAR and DATASEC are never deduped and are self-canonical */
-		if (kind == BTF_KIND_VAR || kind == BTF_KIND_DATASEC)
+		if (btf_is_var(t) || btf_is_datasec(t))
 			d->map[i] = i;
 		else
 			d->map[i] = BTF_UNPROCESSED_ID;
@@ -1485,11 +1460,11 @@ static int btf_for_each_str_off(struct btf_dedup *d, str_off_fn_t fn, void *ctx)
 		if (r)
 			return r;
 
-		switch (BTF_INFO_KIND(t->info)) {
+		switch (btf_kind(t)) {
 		case BTF_KIND_STRUCT:
 		case BTF_KIND_UNION: {
-			struct btf_member *m = (struct btf_member *)(t + 1);
+			struct btf_member *m = btf_members(t);
-			__u16 vlen = BTF_INFO_VLEN(t->info);
+			__u16 vlen = btf_vlen(t);
 
 			for (j = 0; j < vlen; j++) {
 				r = fn(&m->name_off, ctx);
@@ -1500,8 +1475,8 @@ static int btf_for_each_str_off(struct btf_dedup *d, str_off_fn_t fn, void *ctx)
 			break;
 		}
 		case BTF_KIND_ENUM: {
-			struct btf_enum *m = (struct btf_enum *)(t + 1);
+			struct btf_enum *m = btf_enum(t);
-			__u16 vlen = BTF_INFO_VLEN(t->info);
+			__u16 vlen = btf_vlen(t);
 
 			for (j = 0; j < vlen; j++) {
 				r = fn(&m->name_off, ctx);
@@ -1512,8 +1487,8 @@ static int btf_for_each_str_off(struct btf_dedup *d, str_off_fn_t fn, void *ctx)
 			break;
 		}
 		case BTF_KIND_FUNC_PROTO: {
-			struct btf_param *m = (struct btf_param *)(t + 1);
+			struct btf_param *m = btf_params(t);
-			__u16 vlen = BTF_INFO_VLEN(t->info);
+			__u16 vlen = btf_vlen(t);
 
 			for (j = 0; j < vlen; j++) {
 				r = fn(&m->name_off, ctx);
@@ -1802,16 +1777,16 @@ static long btf_hash_enum(struct btf_type *t)
 /* Check structural equality of two ENUMs. */
 static bool btf_equal_enum(struct btf_type *t1, struct btf_type *t2)
 {
-	struct btf_enum *m1, *m2;
+	const struct btf_enum *m1, *m2;
 	__u16 vlen;
 	int i;
 
 	if (!btf_equal_common(t1, t2))
 		return false;
 
-	vlen = BTF_INFO_VLEN(t1->info);
+	vlen = btf_vlen(t1);
-	m1 = (struct btf_enum *)(t1 + 1);
+	m1 = btf_enum(t1);
-	m2 = (struct btf_enum *)(t2 + 1);
+	m2 = btf_enum(t2);
 	for (i = 0; i < vlen; i++) {
 		if (m1->name_off != m2->name_off || m1->val != m2->val)
 			return false;
@@ -1823,8 +1798,7 @@ static bool btf_equal_enum(struct btf_type *t1, struct btf_type *t2)
 
 static inline bool btf_is_enum_fwd(struct btf_type *t)
 {
-	return BTF_INFO_KIND(t->info) == BTF_KIND_ENUM &&
+	return btf_is_enum(t) && btf_vlen(t) == 0;
-	       BTF_INFO_VLEN(t->info) == 0;
 }
 
 static bool btf_compat_enum(struct btf_type *t1, struct btf_type *t2)
@@ -1844,8 +1818,8 @@ static bool btf_compat_enum(struct btf_type *t1, struct btf_type *t2)
  */
 static long btf_hash_struct(struct btf_type *t)
 {
-	struct btf_member *member = (struct btf_member *)(t + 1);
+	const struct btf_member *member = btf_members(t);
-	__u32 vlen = BTF_INFO_VLEN(t->info);
+	__u32 vlen = btf_vlen(t);
 	long h = btf_hash_common(t);
 	int i;
 
@@ -1865,16 +1839,16 @@ static long btf_hash_struct(struct btf_type *t)
  */
 static bool btf_shallow_equal_struct(struct btf_type *t1, struct btf_type *t2)
 {
-	struct btf_member *m1, *m2;
+	const struct btf_member *m1, *m2;
 	__u16 vlen;
 	int i;
 
 	if (!btf_equal_common(t1, t2))
 		return false;
 
-	vlen = BTF_INFO_VLEN(t1->info);
+	vlen = btf_vlen(t1);
-	m1 = (struct btf_member *)(t1 + 1);
+	m1 = btf_members(t1);
-	m2 = (struct btf_member *)(t2 + 1);
+	m2 = btf_members(t2);
 	for (i = 0; i < vlen; i++) {
 		if (m1->name_off != m2->name_off || m1->offset != m2->offset)
 			return false;
@@ -1891,7 +1865,7 @@ static bool btf_shallow_equal_struct(struct btf_type *t1, struct btf_type *t2)
  */
 static long btf_hash_array(struct btf_type *t)
 {
-	struct btf_array *info = (struct btf_array *)(t + 1);
+	const struct btf_array *info = btf_array(t);
 	long h = btf_hash_common(t);
 
 	h = hash_combine(h, info->type);
@@ -1909,13 +1883,13 @@ static long btf_hash_array(struct btf_type *t)
  */
 static bool btf_equal_array(struct btf_type *t1, struct btf_type *t2)
 {
-	struct btf_array *info1, *info2;
+	const struct btf_array *info1, *info2;
 
 	if (!btf_equal_common(t1, t2))
 		return false;
 
-	info1 = (struct btf_array *)(t1 + 1);
+	info1 = btf_array(t1);
-	info2 = (struct btf_array *)(t2 + 1);
+	info2 = btf_array(t2);
 	return info1->type == info2->type &&
 	       info1->index_type == info2->index_type &&
 	       info1->nelems == info2->nelems;
@@ -1928,14 +1902,10 @@ static bool btf_equal_array(struct btf_type *t1, struct btf_type *t2)
  */
 static bool btf_compat_array(struct btf_type *t1, struct btf_type *t2)
 {
-	struct btf_array *info1, *info2;
-
 	if (!btf_equal_common(t1, t2))
 		return false;
 
-	info1 = (struct btf_array *)(t1 + 1);
+	return btf_array(t1)->nelems == btf_array(t2)->nelems;
-	info2 = (struct btf_array *)(t2 + 1);
-	return info1->nelems == info2->nelems;
 }
 
 /*
@@ -1945,8 +1915,8 @@ static bool btf_compat_array(struct btf_type *t1, struct btf_type *t2)
  */
 static long btf_hash_fnproto(struct btf_type *t)
 {
-	struct btf_param *member = (struct btf_param *)(t + 1);
+	const struct btf_param *member = btf_params(t);
-	__u16 vlen = BTF_INFO_VLEN(t->info);
+	__u16 vlen = btf_vlen(t);
 	long h = btf_hash_common(t);
 	int i;
 
@@ -1967,16 +1937,16 @@ static long btf_hash_fnproto(struct btf_type *t)
  */
 static bool btf_equal_fnproto(struct btf_type *t1, struct btf_type *t2)
 {
-	struct btf_param *m1, *m2;
+	const struct btf_param *m1, *m2;
 	__u16 vlen;
 	int i;
 
 	if (!btf_equal_common(t1, t2))
 		return false;
 
-	vlen = BTF_INFO_VLEN(t1->info);
+	vlen = btf_vlen(t1);
-	m1 = (struct btf_param *)(t1 + 1);
+	m1 = btf_params(t1);
-	m2 = (struct btf_param *)(t2 + 1);
+	m2 = btf_params(t2);
 	for (i = 0; i < vlen; i++) {
 		if (m1->name_off != m2->name_off || m1->type != m2->type)
 			return false;
@@ -1993,7 +1963,7 @@ static bool btf_equal_fnproto(struct btf_type *t1, struct btf_type *t2)
  */
 static bool btf_compat_fnproto(struct btf_type *t1, struct btf_type *t2)
 {
-	struct btf_param *m1, *m2;
+	const struct btf_param *m1, *m2;
 	__u16 vlen;
 	int i;
 
@@ -2001,9 +1971,9 @@ static bool btf_compat_fnproto(struct btf_type *t1, struct btf_type *t2)
 	if (t1->name_off != t2->name_off || t1->info != t2->info)
 		return false;
 
-	vlen = BTF_INFO_VLEN(t1->info);
+	vlen = btf_vlen(t1);
-	m1 = (struct btf_param *)(t1 + 1);
+	m1 = btf_params(t1);
-	m2 = (struct btf_param *)(t2 + 1);
+	m2 = btf_params(t2);
 	for (i = 0; i < vlen; i++) {
 		if (m1->name_off != m2->name_off)
 			return false;
@@ -2029,7 +1999,7 @@ static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id)
 	__u32 cand_id;
 	long h;
 
-	switch (BTF_INFO_KIND(t->info)) {
+	switch (btf_kind(t)) {
 	case BTF_KIND_CONST:
 	case BTF_KIND_VOLATILE:
 	case BTF_KIND_RESTRICT:
@@ -2142,13 +2112,13 @@ static uint32_t resolve_fwd_id(struct btf_dedup *d, uint32_t type_id)
 {
 	__u32 orig_type_id = type_id;
 
-	if (BTF_INFO_KIND(d->btf->types[type_id]->info) != BTF_KIND_FWD)
+	if (!btf_is_fwd(d->btf->types[type_id]))
 		return type_id;
 
 	while (is_type_mapped(d, type_id) && d->map[type_id] != type_id)
 		type_id = d->map[type_id];
 
-	if (BTF_INFO_KIND(d->btf->types[type_id]->info) != BTF_KIND_FWD)
+	if (!btf_is_fwd(d->btf->types[type_id]))
 		return type_id;
 
 	return orig_type_id;
@@ -2157,7 +2127,7 @@ static uint32_t resolve_fwd_id(struct btf_dedup *d, uint32_t type_id)
 
 static inline __u16 btf_fwd_kind(struct btf_type *t)
 {
-	return BTF_INFO_KFLAG(t->info) ? BTF_KIND_UNION : BTF_KIND_STRUCT;
+	return btf_kflag(t) ? BTF_KIND_UNION : BTF_KIND_STRUCT;
 }
 
 /*
@@ -2278,8 +2248,8 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id,
 
 	cand_type = d->btf->types[cand_id];
 	canon_type = d->btf->types[canon_id];
-	cand_kind = BTF_INFO_KIND(cand_type->info);
+	cand_kind = btf_kind(cand_type);
-	canon_kind = BTF_INFO_KIND(canon_type->info);
+	canon_kind = btf_kind(canon_type);
 
 	if (cand_type->name_off != canon_type->name_off)
 		return 0;
@@ -2328,12 +2298,12 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id,
 		return btf_dedup_is_equiv(d, cand_type->type, canon_type->type);
 
 	case BTF_KIND_ARRAY: {
-		struct btf_array *cand_arr, *canon_arr;
+		const struct btf_array *cand_arr, *canon_arr;
 
 		if (!btf_compat_array(cand_type, canon_type))
 			return 0;
-		cand_arr = (struct btf_array *)(cand_type + 1);
+		cand_arr = btf_array(cand_type);
-		canon_arr = (struct btf_array *)(canon_type + 1);
+		canon_arr = btf_array(canon_type);
 		eq = btf_dedup_is_equiv(d,
 			cand_arr->index_type, canon_arr->index_type);
 		if (eq <= 0)
@@ -2343,14 +2313,14 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id,
 
 	case BTF_KIND_STRUCT:
 	case BTF_KIND_UNION: {
-		struct btf_member *cand_m, *canon_m;
+		const struct btf_member *cand_m, *canon_m;
 		__u16 vlen;
 
 		if (!btf_shallow_equal_struct(cand_type, canon_type))
 			return 0;
-		vlen = BTF_INFO_VLEN(cand_type->info);
+		vlen = btf_vlen(cand_type);
-		cand_m = (struct btf_member *)(cand_type + 1);
+		cand_m = btf_members(cand_type);
-		canon_m = (struct btf_member *)(canon_type + 1);
+		canon_m = btf_members(canon_type);
 		for (i = 0; i < vlen; i++) {
 			eq = btf_dedup_is_equiv(d, cand_m->type, canon_m->type);
 			if (eq <= 0)
@@ -2363,7 +2333,7 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id,
 	}
 
 	case BTF_KIND_FUNC_PROTO: {
-		struct btf_param *cand_p, *canon_p;
+		const struct btf_param *cand_p, *canon_p;
 		__u16 vlen;
 
 		if (!btf_compat_fnproto(cand_type, canon_type))
@@ -2371,9 +2341,9 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id,
 		eq = btf_dedup_is_equiv(d, cand_type->type, canon_type->type);
 		if (eq <= 0)
 			return eq;
-		vlen = BTF_INFO_VLEN(cand_type->info);
+		vlen = btf_vlen(cand_type);
-		cand_p = (struct btf_param *)(cand_type + 1);
+		cand_p = btf_params(cand_type);
-		canon_p = (struct btf_param *)(canon_type + 1);
+		canon_p = btf_params(canon_type);
 		for (i = 0; i < vlen; i++) {
 			eq = btf_dedup_is_equiv(d, cand_p->type, canon_p->type);
 			if (eq <= 0)
@@ -2428,8 +2398,8 @@ static void btf_dedup_merge_hypot_map(struct btf_dedup *d)
 		targ_type_id = d->hypot_map[cand_type_id];
 		t_id = resolve_type_id(d, targ_type_id);
 		c_id = resolve_type_id(d, cand_type_id);
-		t_kind = BTF_INFO_KIND(d->btf->types[t_id]->info);
+		t_kind = btf_kind(d->btf->types[t_id]);
-		c_kind = BTF_INFO_KIND(d->btf->types[c_id]->info);
+		c_kind = btf_kind(d->btf->types[c_id]);
 		/*
 		 * Resolve FWD into STRUCT/UNION.
 		 * It's ok to resolve FWD into STRUCT/UNION that's not yet
@@ -2498,7 +2468,7 @@ static int btf_dedup_struct_type(struct btf_dedup *d, __u32 type_id)
 		return 0;
 
 	t = d->btf->types[type_id];
-	kind = BTF_INFO_KIND(t->info);
+	kind = btf_kind(t);
 
 	if (kind != BTF_KIND_STRUCT && kind != BTF_KIND_UNION)
 		return 0;
@@ -2593,7 +2563,7 @@ static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id)
 	t = d->btf->types[type_id];
 	d->map[type_id] = BTF_IN_PROGRESS_ID;
 
-	switch (BTF_INFO_KIND(t->info)) {
+	switch (btf_kind(t)) {
 	case BTF_KIND_CONST:
 	case BTF_KIND_VOLATILE:
 	case BTF_KIND_RESTRICT:
@@ -2617,7 +2587,7 @@ static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id)
 		break;
 
 	case BTF_KIND_ARRAY: {
-		struct btf_array *info = (struct btf_array *)(t + 1);
+		struct btf_array *info = btf_array(t);
 
 		ref_type_id = btf_dedup_ref_type(d, info->type);
 		if (ref_type_id < 0)
@@ -2651,8 +2621,8 @@ static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id)
 			return ref_type_id;
 		t->type = ref_type_id;
 
-		vlen = BTF_INFO_VLEN(t->info);
+		vlen = btf_vlen(t);
-		param = (struct btf_param *)(t + 1);
+		param = btf_params(t);
 		for (i = 0; i < vlen; i++) {
 			ref_type_id = btf_dedup_ref_type(d, param->type);
 			if (ref_type_id < 0)
@@ -2792,7 +2762,7 @@ static int btf_dedup_remap_type(struct btf_dedup *d, __u32 type_id)
 	struct btf_type *t = d->btf->types[type_id];
 	int i, r;
 
-	switch (BTF_INFO_KIND(t->info)) {
+	switch (btf_kind(t)) {
 	case BTF_KIND_INT:
 	case BTF_KIND_ENUM:
 		break;
@@ -2812,7 +2782,7 @@ static int btf_dedup_remap_type(struct btf_dedup *d, __u32 type_id)
 		break;
 
 	case BTF_KIND_ARRAY: {
-		struct btf_array *arr_info = (struct btf_array *)(t + 1);
+		struct btf_array *arr_info = btf_array(t);
 
 		r = btf_dedup_remap_type_id(d, arr_info->type);
 		if (r < 0)
@@ -2827,8 +2797,8 @@ static int btf_dedup_remap_type(struct btf_dedup *d, __u32 type_id)
 
 	case BTF_KIND_STRUCT:
 	case BTF_KIND_UNION: {
-		struct btf_member *member = (struct btf_member *)(t + 1);
+		struct btf_member *member = btf_members(t);
-		__u16 vlen = BTF_INFO_VLEN(t->info);
+		__u16 vlen = btf_vlen(t);
 
 		for (i = 0; i < vlen; i++) {
 			r = btf_dedup_remap_type_id(d, member->type);
@@ -2841,8 +2811,8 @@ static int btf_dedup_remap_type(struct btf_dedup *d, __u32 type_id)
 	}
 
 	case BTF_KIND_FUNC_PROTO: {
-		struct btf_param *param = (struct btf_param *)(t + 1);
+		struct btf_param *param = btf_params(t);
-		__u16 vlen = BTF_INFO_VLEN(t->info);
+		__u16 vlen = btf_vlen(t);
 
 		r = btf_dedup_remap_type_id(d, t->type);
 		if (r < 0)
@@ -2860,8 +2830,8 @@ static int btf_dedup_remap_type(struct btf_dedup *d, __u32 type_id)
 	}
 
 	case BTF_KIND_DATASEC: {
-		struct btf_var_secinfo *var = (struct btf_var_secinfo *)(t + 1);
+		struct btf_var_secinfo *var = btf_var_secinfos(t);
-		__u16 vlen = BTF_INFO_VLEN(t->info);
+		__u16 vlen = btf_vlen(t);
 
 		for (i = 0; i < vlen; i++) {
 			r = btf_dedup_remap_type_id(d, var->type);

tools/lib/bpf/btf.h

@@ -5,6 +5,7 @@
 #define __LIBBPF_BTF_H
 
 #include <stdarg.h>
+#include <linux/btf.h>
 #include <linux/types.h>
 
 #ifdef __cplusplus
@@ -57,6 +58,10 @@ struct btf_ext_header {
 	__u32	func_info_len;
 	__u32	line_info_off;
 	__u32	line_info_len;
+
+	/* optional part of .BTF.ext header */
+	__u32	offset_reloc_off;
+	__u32	offset_reloc_len;
 };
 
 LIBBPF_API void btf__free(struct btf *btf);
@@ -120,6 +125,183 @@ LIBBPF_API void btf_dump__free(struct btf_dump *d);
 
 LIBBPF_API int btf_dump__dump_type(struct btf_dump *d, __u32 id);
 
+/*
+ * A set of helpers for easier BTF types handling
+ */
+static inline __u16 btf_kind(const struct btf_type *t)
+{
+	return BTF_INFO_KIND(t->info);
+}
+
+static inline __u16 btf_vlen(const struct btf_type *t)
+{
+	return BTF_INFO_VLEN(t->info);
+}
+
+static inline bool btf_kflag(const struct btf_type *t)
+{
+	return BTF_INFO_KFLAG(t->info);
+}
+
+static inline bool btf_is_int(const struct btf_type *t)
+{
+	return btf_kind(t) == BTF_KIND_INT;
+}
+
+static inline bool btf_is_ptr(const struct btf_type *t)
+{
+	return btf_kind(t) == BTF_KIND_PTR;
+}
+
+static inline bool btf_is_array(const struct btf_type *t)
+{
+	return btf_kind(t) == BTF_KIND_ARRAY;
+}
+
+static inline bool btf_is_struct(const struct btf_type *t)
+{
+	return btf_kind(t) == BTF_KIND_STRUCT;
+}
+
+static inline bool btf_is_union(const struct btf_type *t)
+{
+	return btf_kind(t) == BTF_KIND_UNION;
+}
+
+static inline bool btf_is_composite(const struct btf_type *t)
+{
+	__u16 kind = btf_kind(t);
+
+	return kind == BTF_KIND_STRUCT || kind == BTF_KIND_UNION;
+}
+
+static inline bool btf_is_enum(const struct btf_type *t)
+{
+	return btf_kind(t) == BTF_KIND_ENUM;
+}
+
+static inline bool btf_is_fwd(const struct btf_type *t)
+{
+	return btf_kind(t) == BTF_KIND_FWD;
+}
+
+static inline bool btf_is_typedef(const struct btf_type *t)
+{
+	return btf_kind(t) == BTF_KIND_TYPEDEF;
+}
+
+static inline bool btf_is_volatile(const struct btf_type *t)
+{
+	return btf_kind(t) == BTF_KIND_VOLATILE;
+}
+
+static inline bool btf_is_const(const struct btf_type *t)
+{
+	return btf_kind(t) == BTF_KIND_CONST;
+}
+
+static inline bool btf_is_restrict(const struct btf_type *t)
+{
+	return btf_kind(t) == BTF_KIND_RESTRICT;
+}
+
+static inline bool btf_is_mod(const struct btf_type *t)
+{
+	__u16 kind = btf_kind(t);
+
+	return kind == BTF_KIND_VOLATILE ||
+	       kind == BTF_KIND_CONST ||
+	       kind == BTF_KIND_RESTRICT;
+}
+
+static inline bool btf_is_func(const struct btf_type *t)
+{
+	return btf_kind(t) == BTF_KIND_FUNC;
+}
+
+static inline bool btf_is_func_proto(const struct btf_type *t)
+{
+	return btf_kind(t) == BTF_KIND_FUNC_PROTO;
+}
+
+static inline bool btf_is_var(const struct btf_type *t)
+{
+	return btf_kind(t) == BTF_KIND_VAR;
+}
+
+static inline bool btf_is_datasec(const struct btf_type *t)
+{
+	return btf_kind(t) == BTF_KIND_DATASEC;
+}
+
+static inline __u8 btf_int_encoding(const struct btf_type *t)
+{
+	return BTF_INT_ENCODING(*(__u32 *)(t + 1));
+}
+
+static inline __u8 btf_int_offset(const struct btf_type *t)
+{
+	return BTF_INT_OFFSET(*(__u32 *)(t + 1));
+}
+
+static inline __u8 btf_int_bits(const struct btf_type *t)
+{
+	return BTF_INT_BITS(*(__u32 *)(t + 1));
+}
+
+static inline struct btf_array *btf_array(const struct btf_type *t)
+{
+	return (struct btf_array *)(t + 1);
+}
+
+static inline struct btf_enum *btf_enum(const struct btf_type *t)
+{
+	return (struct btf_enum *)(t + 1);
+}
+
+static inline struct btf_member *btf_members(const struct btf_type *t)
+{
+	return (struct btf_member *)(t + 1);
+}
+
+/* Get bit offset of a member with specified index. */
+static inline __u32 btf_member_bit_offset(const struct btf_type *t,
+					  __u32 member_idx)
+{
+	const struct btf_member *m = btf_members(t) + member_idx;
+	bool kflag = btf_kflag(t);
+
+	return kflag ? BTF_MEMBER_BIT_OFFSET(m->offset) : m->offset;
+}
+/*
+ * Get bitfield size of a member, assuming t is BTF_KIND_STRUCT or
+ * BTF_KIND_UNION. If member is not a bitfield, zero is returned.
+ */
+static inline __u32 btf_member_bitfield_size(const struct btf_type *t,
+					     __u32 member_idx)
+{
+	const struct btf_member *m = btf_members(t) + member_idx;
+	bool kflag = btf_kflag(t);
+
+	return kflag ? BTF_MEMBER_BITFIELD_SIZE(m->offset) : 0;
+}
+
+static inline struct btf_param *btf_params(const struct btf_type *t)
+{
+	return (struct btf_param *)(t + 1);
+}
+
+static inline struct btf_var *btf_var(const struct btf_type *t)
+{
+	return (struct btf_var *)(t + 1);
+}
+
+static inline struct btf_var_secinfo *
+btf_var_secinfos(const struct btf_type *t)
+{
+	return (struct btf_var_secinfo *)(t + 1);
+}
+
 #ifdef __cplusplus
 } /* extern "C" */
 #endif

tools/lib/bpf/btf_dump.c

@@ -100,21 +100,6 @@ static bool str_equal_fn(const void *a, const void *b, void *ctx)
 	return strcmp(a, b) == 0;
 }
 
-static __u16 btf_kind_of(const struct btf_type *t)
-{
-	return BTF_INFO_KIND(t->info);
-}
-
-static __u16 btf_vlen_of(const struct btf_type *t)
-{
-	return BTF_INFO_VLEN(t->info);
-}
-
-static bool btf_kflag_of(const struct btf_type *t)
-{
-	return BTF_INFO_KFLAG(t->info);
-}
-
 static const char *btf_name_of(const struct btf_dump *d, __u32 name_off)
 {
 	return btf__name_by_offset(d->btf, name_off);
@@ -349,7 +334,7 @@ static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr)
 	 */
 	struct btf_dump_type_aux_state *tstate = &d->type_states[id];
 	const struct btf_type *t;
-	__u16 kind, vlen;
+	__u16 vlen;
 	int err, i;
 
 	/* return true, letting typedefs know that it's ok to be emitted */
@@ -357,18 +342,16 @@ static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr)
 		return 1;
 
 	t = btf__type_by_id(d->btf, id);
-	kind = btf_kind_of(t);
 
 	if (tstate->order_state == ORDERING) {
 		/* type loop, but resolvable through fwd declaration */
-		if ((kind == BTF_KIND_STRUCT || kind == BTF_KIND_UNION) &&
+		if (btf_is_composite(t) && through_ptr && t->name_off != 0)
-		    through_ptr && t->name_off != 0)
 			return 0;
 		pr_warning("unsatisfiable type cycle, id:[%u]\n", id);
 		return -ELOOP;
 	}
 
-	switch (kind) {
+	switch (btf_kind(t)) {
 	case BTF_KIND_INT:
 		tstate->order_state = ORDERED;
 		return 0;
@@ -378,14 +361,12 @@ static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr)
 		tstate->order_state = ORDERED;
 		return err;
 
-	case BTF_KIND_ARRAY: {
+	case BTF_KIND_ARRAY:
-		const struct btf_array *a = (void *)(t + 1);
+		return btf_dump_order_type(d, btf_array(t)->type, through_ptr);
 
-		return btf_dump_order_type(d, a->type, through_ptr);
-	}
 	case BTF_KIND_STRUCT:
 	case BTF_KIND_UNION: {
-		const struct btf_member *m = (void *)(t + 1);
+		const struct btf_member *m = btf_members(t);
 		/*
 		 * struct/union is part of strong link, only if it's embedded
 		 * (so no ptr in a path) or it's anonymous (so has to be
@@ -396,7 +377,7 @@ static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr)
 
 		tstate->order_state = ORDERING;
 
-		vlen = btf_vlen_of(t);
+		vlen = btf_vlen(t);
 		for (i = 0; i < vlen; i++, m++) {
 			err = btf_dump_order_type(d, m->type, false);
 			if (err < 0)
@@ -447,7 +428,7 @@ static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr)
 		return btf_dump_order_type(d, t->type, through_ptr);
 
 	case BTF_KIND_FUNC_PROTO: {
-		const struct btf_param *p = (void *)(t + 1);
+		const struct btf_param *p = btf_params(t);
 		bool is_strong;
 
 		err = btf_dump_order_type(d, t->type, through_ptr);
@@ -455,7 +436,7 @@ static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr)
 			return err;
 		is_strong = err > 0;
 
-		vlen = btf_vlen_of(t);
+		vlen = btf_vlen(t);
 		for (i = 0; i < vlen; i++, p++) {
 			err = btf_dump_order_type(d, p->type, through_ptr);
 			if (err < 0)
@@ -553,7 +534,7 @@ static void btf_dump_emit_type(struct btf_dump *d, __u32 id, __u32 cont_id)
 		return;
 
 	t = btf__type_by_id(d->btf, id);
-	kind = btf_kind_of(t);
+	kind = btf_kind(t);
 
 	if (top_level_def && t->name_off == 0) {
 		pr_warning("unexpected nameless definition, id:[%u]\n", id);
@@ -618,12 +599,9 @@ static void btf_dump_emit_type(struct btf_dump *d, __u32 id, __u32 cont_id)
 	case BTF_KIND_RESTRICT:
 		btf_dump_emit_type(d, t->type, cont_id);
 		break;
-	case BTF_KIND_ARRAY: {
+	case BTF_KIND_ARRAY:
-		const struct btf_array *a = (void *)(t + 1);
+		btf_dump_emit_type(d, btf_array(t)->type, cont_id);
-
-		btf_dump_emit_type(d, a->type, cont_id);
 		break;
-	}
 	case BTF_KIND_FWD:
 		btf_dump_emit_fwd_def(d, id, t);
 		btf_dump_printf(d, ";\n\n");
@@ -656,8 +634,8 @@ static void btf_dump_emit_type(struct btf_dump *d, __u32 id, __u32 cont_id)
 		 * applicable
 		 */
 		if (top_level_def || t->name_off == 0) {
-			const struct btf_member *m = (void *)(t + 1);
+			const struct btf_member *m = btf_members(t);
-			__u16 vlen = btf_vlen_of(t);
+			__u16 vlen = btf_vlen(t);
 			int i, new_cont_id;
 
 			new_cont_id = t->name_off == 0 ? cont_id : id;
@@ -678,8 +656,8 @@ static void btf_dump_emit_type(struct btf_dump *d, __u32 id, __u32 cont_id)
 		}
 		break;
 	case BTF_KIND_FUNC_PROTO: {
-		const struct btf_param *p = (void *)(t + 1);
+		const struct btf_param *p = btf_params(t);
-		__u16 vlen = btf_vlen_of(t);
+		__u16 vlen = btf_vlen(t);
 		int i;
 
 		btf_dump_emit_type(d, t->type, cont_id);
@@ -696,7 +674,7 @@ static void btf_dump_emit_type(struct btf_dump *d, __u32 id, __u32 cont_id)
 static int btf_align_of(const struct btf *btf, __u32 id)
 {
 	const struct btf_type *t = btf__type_by_id(btf, id);
-	__u16 kind = btf_kind_of(t);
+	__u16 kind = btf_kind(t);
 
 	switch (kind) {
 	case BTF_KIND_INT:
@@ -709,15 +687,12 @@ static int btf_align_of(const struct btf *btf, __u32 id)
 	case BTF_KIND_CONST:
 	case BTF_KIND_RESTRICT:
 		return btf_align_of(btf, t->type);
-	case BTF_KIND_ARRAY: {
+	case BTF_KIND_ARRAY:
-		const struct btf_array *a = (void *)(t + 1);
+		return btf_align_of(btf, btf_array(t)->type);
-
-		return btf_align_of(btf, a->type);
-	}
 	case BTF_KIND_STRUCT:
 	case BTF_KIND_UNION: {
-		const struct btf_member *m = (void *)(t + 1);
+		const struct btf_member *m = btf_members(t);
-		__u16 vlen = btf_vlen_of(t);
+		__u16 vlen = btf_vlen(t);
 		int i, align = 1;
 
 		for (i = 0; i < vlen; i++, m++)
@@ -726,7 +701,7 @@ static int btf_align_of(const struct btf *btf, __u32 id)
 		return align;
 	}
 	default:
-		pr_warning("unsupported BTF_KIND:%u\n", btf_kind_of(t));
+		pr_warning("unsupported BTF_KIND:%u\n", btf_kind(t));
 		return 1;
 	}
 }
@@ -737,20 +712,18 @@ static bool btf_is_struct_packed(const struct btf *btf, __u32 id,
 	const struct btf_member *m;
 	int align, i, bit_sz;
 	__u16 vlen;
-	bool kflag;
 
 	align = btf_align_of(btf, id);
 	/* size of a non-packed struct has to be a multiple of its alignment*/
 	if (t->size % align)
 		return true;
 
-	m = (void *)(t + 1);
+	m = btf_members(t);
-	kflag = btf_kflag_of(t);
+	vlen = btf_vlen(t);
-	vlen = btf_vlen_of(t);
 	/* all non-bitfield fields have to be naturally aligned */
 	for (i = 0; i < vlen; i++, m++) {
 		align = btf_align_of(btf, m->type);
-		bit_sz = kflag ? BTF_MEMBER_BITFIELD_SIZE(m->offset) : 0;
+		bit_sz = btf_member_bitfield_size(t, i);
 		if (bit_sz == 0 && m->offset % (8 * align) != 0)
 			return true;
 	}
@@ -807,7 +780,7 @@ static void btf_dump_emit_struct_fwd(struct btf_dump *d, __u32 id,
 				     const struct btf_type *t)
 {
 	btf_dump_printf(d, "%s %s",
-			btf_kind_of(t) == BTF_KIND_STRUCT ? "struct" : "union",
+			btf_is_struct(t) ? "struct" : "union",
 			btf_dump_type_name(d, id));
 }
 
@@ -816,12 +789,11 @@ static void btf_dump_emit_struct_def(struct btf_dump *d,
 				     const struct btf_type *t,
 				     int lvl)
 {
-	const struct btf_member *m = (void *)(t + 1);
+	const struct btf_member *m = btf_members(t);
-	bool kflag = btf_kflag_of(t), is_struct;
+	bool is_struct = btf_is_struct(t);
 	int align, i, packed, off = 0;
-	__u16 vlen = btf_vlen_of(t);
+	__u16 vlen = btf_vlen(t);
 
-	is_struct = btf_kind_of(t) == BTF_KIND_STRUCT;
 	packed = is_struct ? btf_is_struct_packed(d->btf, id, t) : 0;
 	align = packed ? 1 : btf_align_of(d->btf, id);
 
@@ -835,8 +807,8 @@ static void btf_dump_emit_struct_def(struct btf_dump *d,
 		int m_off, m_sz;
 
 		fname = btf_name_of(d, m->name_off);
-		m_sz = kflag ? BTF_MEMBER_BITFIELD_SIZE(m->offset) : 0;
+		m_sz = btf_member_bitfield_size(t, i);
-		m_off = kflag ? BTF_MEMBER_BIT_OFFSET(m->offset) : m->offset;
+		m_off = btf_member_bit_offset(t, i);
 		align = packed ? 1 : btf_align_of(d->btf, m->type);
 
 		btf_dump_emit_bit_padding(d, off, m_off, m_sz, align, lvl + 1);
@@ -870,8 +842,8 @@ static void btf_dump_emit_enum_def(struct btf_dump *d, __u32 id,
 				   const struct btf_type *t,
 				   int lvl)
 {
-	const struct btf_enum *v = (void *)(t+1);
+	const struct btf_enum *v = btf_enum(t);
-	__u16 vlen = btf_vlen_of(t);
+	__u16 vlen = btf_vlen(t);
 	const char *name;
 	size_t dup_cnt;
 	int i;
@@ -905,7 +877,7 @@ static void btf_dump_emit_fwd_def(struct btf_dump *d, __u32 id,
 {
 	const char *name = btf_dump_type_name(d, id);
 
-	if (btf_kflag_of(t))
+	if (btf_kflag(t))
 		btf_dump_printf(d, "union %s", name);
 	else
 		btf_dump_printf(d, "struct %s", name);
@@ -987,7 +959,6 @@ static void btf_dump_emit_type_decl(struct btf_dump *d, __u32 id,
 	struct id_stack decl_stack;
 	const struct btf_type *t;
 	int err, stack_start;
-	__u16 kind;
 
 	stack_start = d->decl_stack_cnt;
 	for (;;) {
@@ -1008,8 +979,7 @@ static void btf_dump_emit_type_decl(struct btf_dump *d, __u32 id,
 			break;
 
 		t = btf__type_by_id(d->btf, id);
-		kind = btf_kind_of(t);
+		switch (btf_kind(t)) {
-		switch (kind) {
 		case BTF_KIND_PTR:
 		case BTF_KIND_VOLATILE:
 		case BTF_KIND_CONST:
@@ -1017,12 +987,9 @@ static void btf_dump_emit_type_decl(struct btf_dump *d, __u32 id,
 		case BTF_KIND_FUNC_PROTO:
 			id = t->type;
 			break;
-		case BTF_KIND_ARRAY: {
+		case BTF_KIND_ARRAY:
-			const struct btf_array *a = (void *)(t + 1);
+			id = btf_array(t)->type;
-
-			id = a->type;
 			break;
-		}
 		case BTF_KIND_INT:
 		case BTF_KIND_ENUM:
 		case BTF_KIND_FWD:
@@ -1032,7 +999,7 @@ static void btf_dump_emit_type_decl(struct btf_dump *d, __u32 id,
 			goto done;
 		default:
 			pr_warning("unexpected type in decl chain, kind:%u, id:[%u]\n",
-				   kind, id);
+				   btf_kind(t), id);
 			goto done;
 		}
 	}
@@ -1070,7 +1037,7 @@ static void btf_dump_emit_mods(struct btf_dump *d, struct id_stack *decl_stack)
 		id = decl_stack->ids[decl_stack->cnt - 1];
 		t = btf__type_by_id(d->btf, id);
 
-		switch (btf_kind_of(t)) {
+		switch (btf_kind(t)) {
 		case BTF_KIND_VOLATILE:
 			btf_dump_printf(d, "volatile ");
 			break;
@@ -1087,20 +1054,6 @@ static void btf_dump_emit_mods(struct btf_dump *d, struct id_stack *decl_stack)
 	}
 }
 
-static bool btf_is_mod_kind(const struct btf *btf, __u32 id)
-{
-	const struct btf_type *t = btf__type_by_id(btf, id);
-
-	switch (btf_kind_of(t)) {
-	case BTF_KIND_VOLATILE:
-	case BTF_KIND_CONST:
-	case BTF_KIND_RESTRICT:
-		return true;
-	default:
-		return false;
-	}
-}
-
 static void btf_dump_emit_name(const struct btf_dump *d,
 			       const char *name, bool last_was_ptr)
 {
@@ -1139,7 +1092,7 @@ static void btf_dump_emit_type_chain(struct btf_dump *d,
 		}
 
 		t = btf__type_by_id(d->btf, id);
-		kind = btf_kind_of(t);
+		kind = btf_kind(t);
 
 		switch (kind) {
 		case BTF_KIND_INT:
@@ -1185,7 +1138,7 @@ static void btf_dump_emit_type_chain(struct btf_dump *d,
 			btf_dump_printf(d, " restrict");
 			break;
 		case BTF_KIND_ARRAY: {
-			const struct btf_array *a = (void *)(t + 1);
+			const struct btf_array *a = btf_array(t);
 			const struct btf_type *next_t;
 			__u32 next_id;
 			bool multidim;
@@ -1201,7 +1154,8 @@ static void btf_dump_emit_type_chain(struct btf_dump *d,
 			 */
 			while (decls->cnt) {
 				next_id = decls->ids[decls->cnt - 1];
-				if (btf_is_mod_kind(d->btf, next_id))
+				next_t = btf__type_by_id(d->btf, next_id);
+				if (btf_is_mod(next_t))
 					decls->cnt--;
 				else
 					break;
@@ -1214,7 +1168,7 @@ static void btf_dump_emit_type_chain(struct btf_dump *d,
 			}
 
 			next_t = btf__type_by_id(d->btf, next_id);
-			multidim = btf_kind_of(next_t) == BTF_KIND_ARRAY;
+			multidim = btf_is_array(next_t);
 			/* we need space if we have named non-pointer */
 			if (fname[0] && !last_was_ptr)
 				btf_dump_printf(d, " ");
@@ -1228,8 +1182,8 @@ static void btf_dump_emit_type_chain(struct btf_dump *d,
 			return;
 		}
 		case BTF_KIND_FUNC_PROTO: {
-			const struct btf_param *p = (void *)(t + 1);
+			const struct btf_param *p = btf_params(t);
-			__u16 vlen = btf_vlen_of(t);
+			__u16 vlen = btf_vlen(t);
 			int i;
 
 			btf_dump_emit_mods(d, decls);

tools/lib/bpf/libbpf.h

@@ -57,7 +57,7 @@ enum libbpf_print_level {
 typedef int (*libbpf_print_fn_t)(enum libbpf_print_level level,
 				 const char *, va_list ap);
 
-LIBBPF_API void libbpf_set_print(libbpf_print_fn_t fn);
+LIBBPF_API libbpf_print_fn_t libbpf_set_print(libbpf_print_fn_t fn);
 
 /* Hide internal to user */
 struct bpf_object;
@@ -92,6 +92,7 @@ LIBBPF_API void bpf_object__close(struct bpf_object *object);
 struct bpf_object_load_attr {
 	struct bpf_object *obj;
 	int log_level;
+	const char *target_btf_path;
 };
 
 /* Load/unload object into/from kernel */

tools/lib/bpf/libbpf_internal.h

@@ -29,6 +29,10 @@
 #ifndef max
 # define max(x, y) ((x) < (y) ? (y) : (x))
 #endif
+#ifndef offsetofend
+# define offsetofend(TYPE, FIELD) \
+	(offsetof(TYPE, FIELD) + sizeof(((TYPE *)0)->FIELD))
+#endif
 
 extern void libbpf_print(enum libbpf_print_level level,
 			 const char *format, ...)
@@ -46,4 +50,105 @@ do {				\
 int libbpf__load_raw_btf(const char *raw_types, size_t types_len,
 			 const char *str_sec, size_t str_len);
 
+struct btf_ext_info {
+	/*
+	 * info points to the individual info section (e.g. func_info and
+	 * line_info) from the .BTF.ext. It does not include the __u32 rec_size.
+	 */
+	void *info;
+	__u32 rec_size;
+	__u32 len;
+};
+
+#define for_each_btf_ext_sec(seg, sec)					\
+	for (sec = (seg)->info;						\
+	     (void *)sec < (seg)->info + (seg)->len;			\
+	     sec = (void *)sec + sizeof(struct btf_ext_info_sec) +	\
+		   (seg)->rec_size * sec->num_info)
+
+#define for_each_btf_ext_rec(seg, sec, i, rec)				\
+	for (i = 0, rec = (void *)&(sec)->data;				\
+	     i < (sec)->num_info;					\
+	     i++, rec = (void *)rec + (seg)->rec_size)
+
+struct btf_ext {
+	union {
+		struct btf_ext_header *hdr;
+		void *data;
+	};
+	struct btf_ext_info func_info;
+	struct btf_ext_info line_info;
+	struct btf_ext_info offset_reloc_info;
+	__u32 data_size;
+};
+
+struct btf_ext_info_sec {
+	__u32	sec_name_off;
+	__u32	num_info;
+	/* Followed by num_info * record_size number of bytes */
+	__u8	data[0];
+};
+
+/* The minimum bpf_func_info checked by the loader */
+struct bpf_func_info_min {
+	__u32   insn_off;
+	__u32   type_id;
+};
+
+/* The minimum bpf_line_info checked by the loader */
+struct bpf_line_info_min {
+	__u32	insn_off;
+	__u32	file_name_off;
+	__u32	line_off;
+	__u32	line_col;
+};
+
+/* The minimum bpf_offset_reloc checked by the loader
+ *
+ * Offset relocation captures the following data:
+ * - insn_off - instruction offset (in bytes) within a BPF program that needs
+ *   its insn->imm field to be relocated with actual offset;
+ * - type_id - BTF type ID of the "root" (containing) entity of a relocatable
+ *   offset;
+ * - access_str_off - offset into corresponding .BTF string section. String
+ *   itself encodes an accessed field using a sequence of field and array
+ *   indicies, separated by colon (:). It's conceptually very close to LLVM's
+ *   getelementptr ([0]) instruction's arguments for identifying offset to 
+ *   a field.
+ *
+ * Example to provide a better feel.
+ *
+ *   struct sample {
+ *       int a;
+ *       struct {
+ *           int b[10];
+ *       };
+ *   };
+ *
+ *   struct sample *s = ...;
+ *   int x = &s->a;     // encoded as "0:0" (a is field #0)
+ *   int y = &s->b[5];  // encoded as "0:1:0:5" (anon struct is field #1, 
+ *                      // b is field #0 inside anon struct, accessing elem #5)
+ *   int z = &s[10]->b; // encoded as "10:1" (ptr is used as an array)
+ *
+ * type_id for all relocs in this example  will capture BTF type id of
+ * `struct sample`.
+ *
+ * Such relocation is emitted when using __builtin_preserve_access_index()
+ * Clang built-in, passing expression that captures field address, e.g.:
+ *
+ * bpf_probe_read(&dst, sizeof(dst),
+ *		  __builtin_preserve_access_index(&src->a.b.c));
+ *
+ * In this case Clang will emit offset relocation recording necessary data to
+ * be able to find offset of embedded `a.b.c` field within `src` struct.
+ *
+ *   [0] https://llvm.org/docs/LangRef.html#getelementptr-instruction
+ */
+struct bpf_offset_reloc {
+	__u32   insn_off;
+	__u32   type_id;
+	__u32   access_str_off;
+};
+
 #endif /* __LIBBPF_LIBBPF_INTERNAL_H */

tools/lib/bpf/libbpf_probes.c

@@ -244,6 +244,7 @@ bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex)
 	case BPF_MAP_TYPE_ARRAY_OF_MAPS:
 	case BPF_MAP_TYPE_HASH_OF_MAPS:
 	case BPF_MAP_TYPE_DEVMAP:
+	case BPF_MAP_TYPE_DEVMAP_HASH:
 	case BPF_MAP_TYPE_SOCKMAP:
 	case BPF_MAP_TYPE_CPUMAP:
 	case BPF_MAP_TYPE_XSKMAP:

tools/testing/selftests/bpf/Makefile

@@ -236,18 +236,12 @@ PROG_TESTS_H := $(PROG_TESTS_DIR)/tests.h
 PROG_TESTS_FILES := $(wildcard prog_tests/*.c)
 test_progs.c: $(PROG_TESTS_H)
 $(OUTPUT)/test_progs: CFLAGS += $(TEST_PROGS_CFLAGS)
-$(OUTPUT)/test_progs: test_progs.c $(PROG_TESTS_H) $(PROG_TESTS_FILES)
+$(OUTPUT)/test_progs: test_progs.c $(PROG_TESTS_FILES) | $(PROG_TESTS_H)
 $(PROG_TESTS_H): $(PROG_TESTS_FILES) | $(PROG_TESTS_DIR)
 	$(shell ( cd prog_tests/; \
 		  echo '/* Generated header, do not edit */'; \
-		  echo '#ifdef DECLARE'; \
 		  ls *.c 2> /dev/null | \
-			sed -e 's@\([^\.]*\)\.c@extern void test_\1(void);@'; \
+			sed -e 's@\([^\.]*\)\.c@DEFINE_TEST(\1)@'; \
-		  echo '#endif'; \
-		  echo '#ifdef CALL'; \
-		  ls *.c 2> /dev/null | \
-			sed -e 's@\([^\.]*\)\.c@test_\1();@'; \
-		  echo '#endif' \
 		 ) > $(PROG_TESTS_H))
 
 MAP_TESTS_DIR = $(OUTPUT)/map_tests
@@ -257,7 +251,7 @@ MAP_TESTS_H := $(MAP_TESTS_DIR)/tests.h
 MAP_TESTS_FILES := $(wildcard map_tests/*.c)
 test_maps.c: $(MAP_TESTS_H)
 $(OUTPUT)/test_maps: CFLAGS += $(TEST_MAPS_CFLAGS)
-$(OUTPUT)/test_maps: test_maps.c $(MAP_TESTS_H) $(MAP_TESTS_FILES)
+$(OUTPUT)/test_maps: test_maps.c $(MAP_TESTS_FILES) | $(MAP_TESTS_H)
 $(MAP_TESTS_H): $(MAP_TESTS_FILES) | $(MAP_TESTS_DIR)
 	$(shell ( cd map_tests/; \
 		  echo '/* Generated header, do not edit */'; \
@@ -278,7 +272,7 @@ VERIFIER_TESTS_H := $(VERIFIER_TESTS_DIR)/tests.h
 VERIFIER_TEST_FILES := $(wildcard verifier/*.c)
 test_verifier.c: $(VERIFIER_TESTS_H)
 $(OUTPUT)/test_verifier: CFLAGS += $(TEST_VERIFIER_CFLAGS)
-$(OUTPUT)/test_verifier: test_verifier.c $(VERIFIER_TESTS_H)
+$(OUTPUT)/test_verifier: test_verifier.c | $(VERIFIER_TEST_FILES) $(VERIFIER_TESTS_H)
 $(VERIFIER_TESTS_H): $(VERIFIER_TEST_FILES) | $(VERIFIER_TESTS_DIR)
 	$(shell ( cd verifier/; \
 		  echo '/* Generated header, do not edit */'; \

tools/testing/selftests/bpf/bpf_helpers.h

@@ -228,6 +228,9 @@ static void *(*bpf_sk_storage_get)(void *map, struct bpf_sock *sk,
 static int (*bpf_sk_storage_delete)(void *map, struct bpf_sock *sk) =
 	(void *)BPF_FUNC_sk_storage_delete;
 static int (*bpf_send_signal)(unsigned sig) = (void *)BPF_FUNC_send_signal;
+static long long (*bpf_tcp_gen_syncookie)(struct bpf_sock *sk, void *ip,
+					  int ip_len, void *tcp, int tcp_len) =
+	(void *) BPF_FUNC_tcp_gen_syncookie;
 
 /* llvm builtin functions that eBPF C program may use to
  * emit BPF_LD_ABS and BPF_LD_IND instructions
@@ -501,4 +504,24 @@ struct pt_regs;
 				(void *)(PT_REGS_FP(ctx) + sizeof(ip))); })
 #endif
 
+/*
+ * BPF_CORE_READ abstracts away bpf_probe_read() call and captures offset
+ * relocation for source address using __builtin_preserve_access_index()
+ * built-in, provided by Clang.
+ *
+ * __builtin_preserve_access_index() takes as an argument an expression of
+ * taking an address of a field within struct/union. It makes compiler emit
+ * a relocation, which records BTF type ID describing root struct/union and an
+ * accessor string which describes exact embedded field that was used to take
+ * an address. See detailed description of this relocation format and
+ * semantics in comments to struct bpf_offset_reloc in libbpf_internal.h.
+ *
+ * This relocation allows libbpf to adjust BPF instruction to use correct
+ * actual field offset, based on target kernel BTF type that matches original
+ * (local) BTF, used to record relocation.
+ */
+#define BPF_CORE_READ(dst, src)						\
+	bpf_probe_read((dst), sizeof(*(src)),				\
+		       __builtin_preserve_access_index(src))
+
 #endif

tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c

@@ -106,8 +106,8 @@ void test_bpf_obj_id(void)
 		if (CHECK(err ||
 			  prog_infos[i].type != BPF_PROG_TYPE_SOCKET_FILTER ||
 			  info_len != sizeof(struct bpf_prog_info) ||
-			  (jit_enabled && !prog_infos[i].jited_prog_len) ||
+			  (env.jit_enabled && !prog_infos[i].jited_prog_len) ||
-			  (jit_enabled &&
+			  (env.jit_enabled &&
 			   !memcmp(jited_insns, zeros, sizeof(zeros))) ||
 			  !prog_infos[i].xlated_prog_len ||
 			  !memcmp(xlated_insns, zeros, sizeof(zeros)) ||
@@ -121,7 +121,7 @@ void test_bpf_obj_id(void)
 			  err, errno, i,
 			  prog_infos[i].type, BPF_PROG_TYPE_SOCKET_FILTER,
 			  info_len, sizeof(struct bpf_prog_info),
-			  jit_enabled,
+			  env.jit_enabled,
 			  prog_infos[i].jited_prog_len,
 			  prog_infos[i].xlated_prog_len,
 			  !!memcmp(jited_insns, zeros, sizeof(zeros)),

tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c

@@ -4,12 +4,15 @@
 static int libbpf_debug_print(enum libbpf_print_level level,
 			      const char *format, va_list args)
 {
-	if (level != LIBBPF_DEBUG)
+	if (level != LIBBPF_DEBUG) {
-		return vfprintf(stderr, format, args);
+		vprintf(format, args);
+		return 0;
+	}
 
 	if (!strstr(format, "verifier log"))
 		return 0;
-	return vfprintf(stderr, "%s", args);
+	vprintf("%s", args);
+	return 0;
 }
 
 static int check_load(const char *file, enum bpf_prog_type type)
@@ -30,14 +33,25 @@ static int check_load(const char *file, enum bpf_prog_type type)
 	return err;
 }
 
+struct scale_test_def {
+	const char *file;
+	enum bpf_prog_type attach_type;
+	bool fails;
+};
+
 void test_bpf_verif_scale(void)
 {
-	const char *sched_cls[] = {
+	struct scale_test_def tests[] = {
-		"./test_verif_scale1.o", "./test_verif_scale2.o", "./test_verif_scale3.o",
+		{ "loop3.o", BPF_PROG_TYPE_RAW_TRACEPOINT, true /* fails */ },
-	};
+
-	const char *raw_tp[] = {
+		{ "test_verif_scale1.o", BPF_PROG_TYPE_SCHED_CLS },
+		{ "test_verif_scale2.o", BPF_PROG_TYPE_SCHED_CLS },
+		{ "test_verif_scale3.o", BPF_PROG_TYPE_SCHED_CLS },
+
 		/* full unroll by llvm */
-		"./pyperf50.o",	"./pyperf100.o", "./pyperf180.o",
+		{ "pyperf50.o", BPF_PROG_TYPE_RAW_TRACEPOINT },
+		{ "pyperf100.o", BPF_PROG_TYPE_RAW_TRACEPOINT },
+		{ "pyperf180.o", BPF_PROG_TYPE_RAW_TRACEPOINT },
 
 		/* partial unroll. llvm will unroll loop ~150 times.
 		 * C loop count -> 600.
@@ -45,7 +59,7 @@ void test_bpf_verif_scale(void)
 		 * 16k insns in loop body.
 		 * Total of 5 such loops. Total program size ~82k insns.
 		 */
-		"./pyperf600.o",
+		{ "pyperf600.o", BPF_PROG_TYPE_RAW_TRACEPOINT },
 
 		/* no unroll at all.
 		 * C loop count -> 600.
@@ -53,48 +67,52 @@ void test_bpf_verif_scale(void)
 		 * ~110 insns in loop body.
 		 * Total of 5 such loops. Total program size ~1500 insns.
 		 */
-		"./pyperf600_nounroll.o",
+		{ "pyperf600_nounroll.o", BPF_PROG_TYPE_RAW_TRACEPOINT },
 
-		"./loop1.o", "./loop2.o",
+		{ "loop1.o", BPF_PROG_TYPE_RAW_TRACEPOINT },
+		{ "loop2.o", BPF_PROG_TYPE_RAW_TRACEPOINT },
+		{ "loop4.o", BPF_PROG_TYPE_SCHED_CLS },
+		{ "loop5.o", BPF_PROG_TYPE_SCHED_CLS },
 
 		/* partial unroll. 19k insn in a loop.
 		 * Total program size 20.8k insn.
 		 * ~350k processed_insns
 		 */
-		"./strobemeta.o",
+		{ "strobemeta.o", BPF_PROG_TYPE_RAW_TRACEPOINT },
 
 		/* no unroll, tiny loops */
-		"./strobemeta_nounroll1.o",
+		{ "strobemeta_nounroll1.o", BPF_PROG_TYPE_RAW_TRACEPOINT },
-		"./strobemeta_nounroll2.o",
+		{ "strobemeta_nounroll2.o", BPF_PROG_TYPE_RAW_TRACEPOINT },
-	};
+
-	const char *cg_sysctl[] = {
+		{ "test_sysctl_loop1.o", BPF_PROG_TYPE_CGROUP_SYSCTL },
-		"./test_sysctl_loop1.o", "./test_sysctl_loop2.o",
+		{ "test_sysctl_loop2.o", BPF_PROG_TYPE_CGROUP_SYSCTL },
+
+		{ "test_xdp_loop.o", BPF_PROG_TYPE_XDP },
+		{ "test_seg6_loop.o", BPF_PROG_TYPE_LWT_SEG6LOCAL },
 	};
+	libbpf_print_fn_t old_print_fn = NULL;
 	int err, i;
 
-	if (verifier_stats)
+	if (env.verifier_stats) {
-		libbpf_set_print(libbpf_debug_print);
+		test__force_log();
-
+		old_print_fn = libbpf_set_print(libbpf_debug_print);
-	err = check_load("./loop3.o", BPF_PROG_TYPE_RAW_TRACEPOINT);
-	printf("test_scale:loop3:%s\n", err ? (error_cnt--, "OK") : "FAIL");
-
-	for (i = 0; i < ARRAY_SIZE(sched_cls); i++) {
-		err = check_load(sched_cls[i], BPF_PROG_TYPE_SCHED_CLS);
-		printf("test_scale:%s:%s\n", sched_cls[i], err ? "FAIL" : "OK");
 	}
 
-	for (i = 0; i < ARRAY_SIZE(raw_tp); i++) {
+	for (i = 0; i < ARRAY_SIZE(tests); i++) {
-		err = check_load(raw_tp[i], BPF_PROG_TYPE_RAW_TRACEPOINT);
+		const struct scale_test_def *test = &tests[i];
-		printf("test_scale:%s:%s\n", raw_tp[i], err ? "FAIL" : "OK");
+
+		if (!test__start_subtest(test->file))
+			continue;
+
+		err = check_load(test->file, test->attach_type);
+		if (test->fails) { /* expected to fail */
+			if (err)
+				error_cnt--;
+			else
+				error_cnt++;
+		}
 	}
 
-	for (i = 0; i < ARRAY_SIZE(cg_sysctl); i++) {
+	if (env.verifier_stats)
-		err = check_load(cg_sysctl[i], BPF_PROG_TYPE_CGROUP_SYSCTL);
+		libbpf_set_print(old_print_fn);
-		printf("test_scale:%s:%s\n", cg_sysctl[i], err ? "FAIL" : "OK");
-	}
-	err = check_load("./test_xdp_loop.o", BPF_PROG_TYPE_XDP);
-	printf("test_scale:test_xdp_loop:%s\n", err ? "FAIL" : "OK");
-
-	err = check_load("./test_seg6_loop.o", BPF_PROG_TYPE_LWT_SEG6LOCAL);
-	printf("test_scale:test_seg6_loop:%s\n", err ? "FAIL" : "OK");
 }

tools/testing/selftests/bpf/prog_tests/core_reloc.c

@@ -0,0 +1,385 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+#include "progs/core_reloc_types.h"
+
+#define STRUCT_TO_CHAR_PTR(struct_name) (const char *)&(struct struct_name)
+
+#define FLAVORS_DATA(struct_name) STRUCT_TO_CHAR_PTR(struct_name) {	\
+	.a = 42,							\
+	.b = 0xc001,							\
+	.c = 0xbeef,							\
+}
+
+#define FLAVORS_CASE_COMMON(name)					\
+	.case_name = #name,						\
+	.bpf_obj_file = "test_core_reloc_flavors.o",			\
+	.btf_src_file = "btf__core_reloc_" #name ".o"			\
+
+#define FLAVORS_CASE(name) {						\
+	FLAVORS_CASE_COMMON(name),					\
+	.input = FLAVORS_DATA(core_reloc_##name),			\
+	.input_len = sizeof(struct core_reloc_##name),			\
+	.output = FLAVORS_DATA(core_reloc_flavors),			\
+	.output_len = sizeof(struct core_reloc_flavors),		\
+}
+
+#define FLAVORS_ERR_CASE(name) {					\
+	FLAVORS_CASE_COMMON(name),					\
+	.fails = true,							\
+}
+
+#define NESTING_DATA(struct_name) STRUCT_TO_CHAR_PTR(struct_name) {	\
+	.a = { .a = { .a = 42 } },					\
+	.b = { .b = { .b = 0xc001 } },					\
+}
+
+#define NESTING_CASE_COMMON(name)					\
+	.case_name = #name,						\
+	.bpf_obj_file = "test_core_reloc_nesting.o",			\
+	.btf_src_file = "btf__core_reloc_" #name ".o"
+
+#define NESTING_CASE(name) {						\
+	NESTING_CASE_COMMON(name),					\
+	.input = NESTING_DATA(core_reloc_##name),			\
+	.input_len = sizeof(struct core_reloc_##name),			\
+	.output = NESTING_DATA(core_reloc_nesting),			\
+	.output_len = sizeof(struct core_reloc_nesting)			\
+}
+
+#define NESTING_ERR_CASE(name) {					\
+	NESTING_CASE_COMMON(name),					\
+	.fails = true,							\
+}
+
+#define ARRAYS_DATA(struct_name) STRUCT_TO_CHAR_PTR(struct_name) {	\
+	.a = { [2] = 1 },						\
+	.b = { [1] = { [2] = { [3] = 2 } } },				\
+	.c = { [1] = { .c =  3 } },					\
+	.d = { [0] = { [0] = { .d = 4 } } },				\
+}
+
+#define ARRAYS_CASE_COMMON(name)					\
+	.case_name = #name,						\
+	.bpf_obj_file = "test_core_reloc_arrays.o",			\
+	.btf_src_file = "btf__core_reloc_" #name ".o"
+
+#define ARRAYS_CASE(name) {						\
+	ARRAYS_CASE_COMMON(name),					\
+	.input = ARRAYS_DATA(core_reloc_##name),			\
+	.input_len = sizeof(struct core_reloc_##name),			\
+	.output = STRUCT_TO_CHAR_PTR(core_reloc_arrays_output) {	\
+		.a2   = 1,						\
+		.b123 = 2,						\
+		.c1c  = 3,						\
+		.d00d = 4,						\
+	},								\
+	.output_len = sizeof(struct core_reloc_arrays_output)		\
+}
+
+#define ARRAYS_ERR_CASE(name) {						\
+	ARRAYS_CASE_COMMON(name),					\
+	.fails = true,							\
+}
+
+#define PRIMITIVES_DATA(struct_name) STRUCT_TO_CHAR_PTR(struct_name) {	\
+	.a = 1,								\
+	.b = 2,								\
+	.c = 3,								\
+	.d = (void *)4,							\
+	.f = (void *)5,							\
+}
+
+#define PRIMITIVES_CASE_COMMON(name)					\
+	.case_name = #name,						\
+	.bpf_obj_file = "test_core_reloc_primitives.o",			\
+	.btf_src_file = "btf__core_reloc_" #name ".o"
+
+#define PRIMITIVES_CASE(name) {						\
+	PRIMITIVES_CASE_COMMON(name),					\
+	.input = PRIMITIVES_DATA(core_reloc_##name),			\
+	.input_len = sizeof(struct core_reloc_##name),			\
+	.output = PRIMITIVES_DATA(core_reloc_primitives),		\
+	.output_len = sizeof(struct core_reloc_primitives),		\
+}
+
+#define PRIMITIVES_ERR_CASE(name) {					\
+	PRIMITIVES_CASE_COMMON(name),					\
+	.fails = true,							\
+}
+
+#define MODS_CASE(name) {						\
+	.case_name = #name,						\
+	.bpf_obj_file = "test_core_reloc_mods.o",			\
+	.btf_src_file = "btf__core_reloc_" #name ".o",			\
+	.input = STRUCT_TO_CHAR_PTR(core_reloc_##name) {		\
+		.a = 1,							\
+		.b = 2,							\
+		.c = (void *)3,						\
+		.d = (void *)4,						\
+		.e = { [2] = 5 },					\
+		.f = { [1] = 6 },					\
+		.g = { .x = 7 },					\
+		.h = { .y = 8 },					\
+	},								\
+	.input_len = sizeof(struct core_reloc_##name),			\
+	.output = STRUCT_TO_CHAR_PTR(core_reloc_mods_output) {		\
+		.a = 1, .b = 2, .c = 3, .d = 4,				\
+		.e = 5, .f = 6, .g = 7, .h = 8,				\
+	},								\
+	.output_len = sizeof(struct core_reloc_mods_output),		\
+}
+
+#define PTR_AS_ARR_CASE(name) {						\
+	.case_name = #name,						\
+	.bpf_obj_file = "test_core_reloc_ptr_as_arr.o",			\
+	.btf_src_file = "btf__core_reloc_" #name ".o",			\
+	.input = (const char *)&(struct core_reloc_##name []){		\
+		{ .a = 1 },						\
+		{ .a = 2 },						\
+		{ .a = 3 },						\
+	},								\
+	.input_len = 3 * sizeof(struct core_reloc_##name),		\
+	.output = STRUCT_TO_CHAR_PTR(core_reloc_ptr_as_arr) {		\
+		.a = 3,							\
+	},								\
+	.output_len = sizeof(struct core_reloc_ptr_as_arr),		\
+}
+
+#define INTS_DATA(struct_name) STRUCT_TO_CHAR_PTR(struct_name) {	\
+	.u8_field = 1,							\
+	.s8_field = 2,							\
+	.u16_field = 3,							\
+	.s16_field = 4,							\
+	.u32_field = 5,							\
+	.s32_field = 6,							\
+	.u64_field = 7,							\
+	.s64_field = 8,							\
+}
+
+#define INTS_CASE_COMMON(name)						\
+	.case_name = #name,						\
+	.bpf_obj_file = "test_core_reloc_ints.o",			\
+	.btf_src_file = "btf__core_reloc_" #name ".o"
+
+#define INTS_CASE(name) {						\
+	INTS_CASE_COMMON(name),						\
+	.input = INTS_DATA(core_reloc_##name),				\
+	.input_len = sizeof(struct core_reloc_##name),			\
+	.output = INTS_DATA(core_reloc_ints),				\
+	.output_len = sizeof(struct core_reloc_ints),			\
+}
+
+#define INTS_ERR_CASE(name) {						\
+	INTS_CASE_COMMON(name),						\
+	.fails = true,							\
+}
+
+struct core_reloc_test_case {
+	const char *case_name;
+	const char *bpf_obj_file;
+	const char *btf_src_file;
+	const char *input;
+	int input_len;
+	const char *output;
+	int output_len;
+	bool fails;
+};
+
+static struct core_reloc_test_case test_cases[] = {
+	/* validate we can find kernel image and use its BTF for relocs */
+	{
+		.case_name = "kernel",
+		.bpf_obj_file = "test_core_reloc_kernel.o",
+		.btf_src_file = NULL, /* load from /lib/modules/$(uname -r) */
+		.input = "",
+		.input_len = 0,
+		.output = "\1", /* true */
+		.output_len = 1,
+	},
+
+	/* validate BPF program can use multiple flavors to match against
+	 * single target BTF type
+	 */
+	FLAVORS_CASE(flavors),
+
+	FLAVORS_ERR_CASE(flavors__err_wrong_name),
+
+	/* various struct/enum nesting and resolution scenarios */
+	NESTING_CASE(nesting),
+	NESTING_CASE(nesting___anon_embed),
+	NESTING_CASE(nesting___struct_union_mixup),
+	NESTING_CASE(nesting___extra_nesting),
+	NESTING_CASE(nesting___dup_compat_types),
+
+	NESTING_ERR_CASE(nesting___err_missing_field),
+	NESTING_ERR_CASE(nesting___err_array_field),
+	NESTING_ERR_CASE(nesting___err_missing_container),
+	NESTING_ERR_CASE(nesting___err_nonstruct_container),
+	NESTING_ERR_CASE(nesting___err_array_container),
+	NESTING_ERR_CASE(nesting___err_dup_incompat_types),
+	NESTING_ERR_CASE(nesting___err_partial_match_dups),
+	NESTING_ERR_CASE(nesting___err_too_deep),
+
+	/* various array access relocation scenarios */
+	ARRAYS_CASE(arrays),
+	ARRAYS_CASE(arrays___diff_arr_dim),
+	ARRAYS_CASE(arrays___diff_arr_val_sz),
+
+	ARRAYS_ERR_CASE(arrays___err_too_small),
+	ARRAYS_ERR_CASE(arrays___err_too_shallow),
+	ARRAYS_ERR_CASE(arrays___err_non_array),
+	ARRAYS_ERR_CASE(arrays___err_wrong_val_type1),
+	ARRAYS_ERR_CASE(arrays___err_wrong_val_type2),
+
+	/* enum/ptr/int handling scenarios */
+	PRIMITIVES_CASE(primitives),
+	PRIMITIVES_CASE(primitives___diff_enum_def),
+	PRIMITIVES_CASE(primitives___diff_func_proto),
+	PRIMITIVES_CASE(primitives___diff_ptr_type),
+
+	PRIMITIVES_ERR_CASE(primitives___err_non_enum),
+	PRIMITIVES_ERR_CASE(primitives___err_non_int),
+	PRIMITIVES_ERR_CASE(primitives___err_non_ptr),
+
+	/* const/volatile/restrict and typedefs scenarios */
+	MODS_CASE(mods),
+	MODS_CASE(mods___mod_swap),
+	MODS_CASE(mods___typedefs),
+
+	/* handling "ptr is an array" semantics */
+	PTR_AS_ARR_CASE(ptr_as_arr),
+	PTR_AS_ARR_CASE(ptr_as_arr___diff_sz),
+
+	/* int signedness/sizing/bitfield handling */
+	INTS_CASE(ints),
+	INTS_CASE(ints___bool),
+	INTS_CASE(ints___reverse_sign),
+
+	INTS_ERR_CASE(ints___err_bitfield),
+	INTS_ERR_CASE(ints___err_wrong_sz_8),
+	INTS_ERR_CASE(ints___err_wrong_sz_16),
+	INTS_ERR_CASE(ints___err_wrong_sz_32),
+	INTS_ERR_CASE(ints___err_wrong_sz_64),
+	
+	/* validate edge cases of capturing relocations */
+	{
+		.case_name = "misc",
+		.bpf_obj_file = "test_core_reloc_misc.o",
+		.btf_src_file = "btf__core_reloc_misc.o",
+		.input = (const char *)&(struct core_reloc_misc_extensible[]){
+			{ .a = 1 },
+			{ .a = 2 }, /* not read */
+			{ .a = 3 },
+		},
+		.input_len = 4 * sizeof(int),
+		.output = STRUCT_TO_CHAR_PTR(core_reloc_misc_output) {
+			.a = 1,
+			.b = 1,
+			.c = 0, /* BUG in clang, should be 3 */
+		},
+		.output_len = sizeof(struct core_reloc_misc_output),
+	},
+};
+
+struct data {
+	char in[256];
+	char out[256];
+};
+
+void test_core_reloc(void)
+{
+	const char *probe_name = "raw_tracepoint/sys_enter";
+	struct bpf_object_load_attr load_attr = {};
+	struct core_reloc_test_case *test_case;
+	int err, duration = 0, i, equal;
+	struct bpf_link *link = NULL;
+	struct bpf_map *data_map;
+	struct bpf_program *prog;
+	struct bpf_object *obj;
+	const int zero = 0;
+	struct data data;
+
+	for (i = 0; i < ARRAY_SIZE(test_cases); i++) {
+		test_case = &test_cases[i];
+
+		if (!test__start_subtest(test_case->case_name))
+			continue;
+
+		obj = bpf_object__open(test_case->bpf_obj_file);
+		if (CHECK(IS_ERR_OR_NULL(obj), "obj_open",
+			  "failed to open '%s': %ld\n",
+			  test_case->bpf_obj_file, PTR_ERR(obj)))
+			continue;
+
+		prog = bpf_object__find_program_by_title(obj, probe_name);
+		if (CHECK(!prog, "find_probe",
+			  "prog '%s' not found\n", probe_name))
+			goto cleanup;
+		bpf_program__set_type(prog, BPF_PROG_TYPE_RAW_TRACEPOINT);
+
+		load_attr.obj = obj;
+		load_attr.log_level = 0;
+		load_attr.target_btf_path = test_case->btf_src_file;
+		err = bpf_object__load_xattr(&load_attr);
+		if (test_case->fails) {
+			CHECK(!err, "obj_load_fail",
+			      "should fail to load prog '%s'\n", probe_name);
+			goto cleanup;
+		} else {
+			if (CHECK(err, "obj_load",
+				  "failed to load prog '%s': %d\n",
+				  probe_name, err))
+				goto cleanup;
+		}
+
+		link = bpf_program__attach_raw_tracepoint(prog, "sys_enter");
+		if (CHECK(IS_ERR(link), "attach_raw_tp", "err %ld\n",
+			  PTR_ERR(link)))
+			goto cleanup;
+
+		data_map = bpf_object__find_map_by_name(obj, "test_cor.bss");
+		if (CHECK(!data_map, "find_data_map", "data map not found\n"))
+			goto cleanup;
+
+		memset(&data, 0, sizeof(data));
+		memcpy(data.in, test_case->input, test_case->input_len);
+
+		err = bpf_map_update_elem(bpf_map__fd(data_map),
+					  &zero, &data, 0);
+		if (CHECK(err, "update_data_map",
+			  "failed to update .data map: %d\n", err))
+			goto cleanup;
+
+		/* trigger test run */
+		usleep(1);
+
+		err = bpf_map_lookup_elem(bpf_map__fd(data_map), &zero, &data);
+		if (CHECK(err, "get_result",
+			  "failed to get output data: %d\n", err))
+			goto cleanup;
+
+		equal = memcmp(data.out, test_case->output,
+			       test_case->output_len) == 0;
+		if (CHECK(!equal, "check_result",
+			  "input/output data don't match\n")) {
+			int j;
+
+			for (j = 0; j < test_case->input_len; j++) {
+				printf("input byte #%d: 0x%02hhx\n",
+				       j, test_case->input[j]);
+			}
+			for (j = 0; j < test_case->output_len; j++) {
+				printf("output byte #%d: EXP 0x%02hhx GOT 0x%02hhx\n",
+				       j, test_case->output[j], data.out[j]);
+			}
+			goto cleanup;
+		}
+
+cleanup:
+		if (!IS_ERR_OR_NULL(link)) {
+			bpf_link__destroy(link);
+			link = NULL;
+		}
+		bpf_object__close(obj);
+	}
+}

tools/testing/selftests/bpf/prog_tests/flow_dissector.c

@@ -5,6 +5,10 @@
 #include <linux/if_tun.h>
 #include <sys/uio.h>
 
+#ifndef IP_MF
+#define IP_MF 0x2000
+#endif
+
 #define CHECK_FLOW_KEYS(desc, got, expected)				\
 	CHECK_ATTR(memcmp(&got, &expected, sizeof(got)) != 0,		\
 	      desc,							\
@@ -16,6 +20,7 @@
 	      "is_encap=%u/%u "						\
 	      "ip_proto=0x%x/0x%x "					\
 	      "n_proto=0x%x/0x%x "					\
+	      "flow_label=0x%x/0x%x "					\
 	      "sport=%u/%u "						\
 	      "dport=%u/%u\n",						\
 	      got.nhoff, expected.nhoff,				\
@@ -26,6 +31,7 @@
 	      got.is_encap, expected.is_encap,				\
 	      got.ip_proto, expected.ip_proto,				\
 	      got.n_proto, expected.n_proto,				\
+	      got.flow_label, expected.flow_label,			\
 	      got.sport, expected.sport,				\
 	      got.dport, expected.dport)
 
@@ -35,6 +41,13 @@ struct ipv4_pkt {
 	struct tcphdr tcp;
 } __packed;
 
+struct ipip_pkt {
+	struct ethhdr eth;
+	struct iphdr iph;
+	struct iphdr iph_inner;
+	struct tcphdr tcp;
+} __packed;
+
 struct svlan_ipv4_pkt {
 	struct ethhdr eth;
 	__u16 vlan_tci;
@@ -49,6 +62,18 @@ struct ipv6_pkt {
 	struct tcphdr tcp;
 } __packed;
 
+struct ipv6_frag_pkt {
+	struct ethhdr eth;
+	struct ipv6hdr iph;
+	struct frag_hdr {
+		__u8 nexthdr;
+		__u8 reserved;
+		__be16 frag_off;
+		__be32 identification;
+	} ipf;
+	struct tcphdr tcp;
+} __packed;
+
 struct dvlan_ipv6_pkt {
 	struct ethhdr eth;
 	__u16 vlan_tci;
@@ -64,10 +89,13 @@ struct test {
 	union {
 		struct ipv4_pkt ipv4;
 		struct svlan_ipv4_pkt svlan_ipv4;
+		struct ipip_pkt ipip;
 		struct ipv6_pkt ipv6;
+		struct ipv6_frag_pkt ipv6_frag;
 		struct dvlan_ipv6_pkt dvlan_ipv6;
 	} pkt;
 	struct bpf_flow_keys keys;
+	__u32 flags;
 };
 
 #define VLAN_HLEN	4
@@ -81,6 +109,8 @@ struct test tests[] = {
 			.iph.protocol = IPPROTO_TCP,
 			.iph.tot_len = __bpf_constant_htons(MAGIC_BYTES),
 			.tcp.doff = 5,
+			.tcp.source = 80,
+			.tcp.dest = 8080,
 		},
 		.keys = {
 			.nhoff = ETH_HLEN,
@@ -88,6 +118,8 @@ struct test tests[] = {
 			.addr_proto = ETH_P_IP,
 			.ip_proto = IPPROTO_TCP,
 			.n_proto = __bpf_constant_htons(ETH_P_IP),
+			.sport = 80,
+			.dport = 8080,
 		},
 	},
 	{
@@ -97,6 +129,8 @@ struct test tests[] = {
 			.iph.nexthdr = IPPROTO_TCP,
 			.iph.payload_len = __bpf_constant_htons(MAGIC_BYTES),
 			.tcp.doff = 5,
+			.tcp.source = 80,
+			.tcp.dest = 8080,
 		},
 		.keys = {
 			.nhoff = ETH_HLEN,
@@ -104,6 +138,8 @@ struct test tests[] = {
 			.addr_proto = ETH_P_IPV6,
 			.ip_proto = IPPROTO_TCP,
 			.n_proto = __bpf_constant_htons(ETH_P_IPV6),
+			.sport = 80,
+			.dport = 8080,
 		},
 	},
 	{
@@ -115,6 +151,8 @@ struct test tests[] = {
 			.iph.protocol = IPPROTO_TCP,
 			.iph.tot_len = __bpf_constant_htons(MAGIC_BYTES),
 			.tcp.doff = 5,
+			.tcp.source = 80,
+			.tcp.dest = 8080,
 		},
 		.keys = {
 			.nhoff = ETH_HLEN + VLAN_HLEN,
@@ -122,6 +160,8 @@ struct test tests[] = {
 			.addr_proto = ETH_P_IP,
 			.ip_proto = IPPROTO_TCP,
 			.n_proto = __bpf_constant_htons(ETH_P_IP),
+			.sport = 80,
+			.dport = 8080,
 		},
 	},
 	{
@@ -133,6 +173,8 @@ struct test tests[] = {
 			.iph.nexthdr = IPPROTO_TCP,
 			.iph.payload_len = __bpf_constant_htons(MAGIC_BYTES),
 			.tcp.doff = 5,
+			.tcp.source = 80,
+			.tcp.dest = 8080,
 		},
 		.keys = {
 			.nhoff = ETH_HLEN + VLAN_HLEN * 2,
@@ -141,8 +183,206 @@ struct test tests[] = {
 			.addr_proto = ETH_P_IPV6,
 			.ip_proto = IPPROTO_TCP,
 			.n_proto = __bpf_constant_htons(ETH_P_IPV6),
+			.sport = 80,
+			.dport = 8080,
 		},
 	},
+	{
+		.name = "ipv4-frag",
+		.pkt.ipv4 = {
+			.eth.h_proto = __bpf_constant_htons(ETH_P_IP),
+			.iph.ihl = 5,
+			.iph.protocol = IPPROTO_TCP,
+			.iph.tot_len = __bpf_constant_htons(MAGIC_BYTES),
+			.iph.frag_off = __bpf_constant_htons(IP_MF),
+			.tcp.doff = 5,
+			.tcp.source = 80,
+			.tcp.dest = 8080,
+		},
+		.keys = {
+			.flags = BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG,
+			.nhoff = ETH_HLEN,
+			.thoff = ETH_HLEN + sizeof(struct iphdr),
+			.addr_proto = ETH_P_IP,
+			.ip_proto = IPPROTO_TCP,
+			.n_proto = __bpf_constant_htons(ETH_P_IP),
+			.is_frag = true,
+			.is_first_frag = true,
+			.sport = 80,
+			.dport = 8080,
+		},
+		.flags = BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG,
+	},
+	{
+		.name = "ipv4-no-frag",
+		.pkt.ipv4 = {
+			.eth.h_proto = __bpf_constant_htons(ETH_P_IP),
+			.iph.ihl = 5,
+			.iph.protocol = IPPROTO_TCP,
+			.iph.tot_len = __bpf_constant_htons(MAGIC_BYTES),
+			.iph.frag_off = __bpf_constant_htons(IP_MF),
+			.tcp.doff = 5,
+			.tcp.source = 80,
+			.tcp.dest = 8080,
+		},
+		.keys = {
+			.nhoff = ETH_HLEN,
+			.thoff = ETH_HLEN + sizeof(struct iphdr),
+			.addr_proto = ETH_P_IP,
+			.ip_proto = IPPROTO_TCP,
+			.n_proto = __bpf_constant_htons(ETH_P_IP),
+			.is_frag = true,
+			.is_first_frag = true,
+		},
+	},
+	{
+		.name = "ipv6-frag",
+		.pkt.ipv6_frag = {
+			.eth.h_proto = __bpf_constant_htons(ETH_P_IPV6),
+			.iph.nexthdr = IPPROTO_FRAGMENT,
+			.iph.payload_len = __bpf_constant_htons(MAGIC_BYTES),
+			.ipf.nexthdr = IPPROTO_TCP,
+			.tcp.doff = 5,
+			.tcp.source = 80,
+			.tcp.dest = 8080,
+		},
+		.keys = {
+			.flags = BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG,
+			.nhoff = ETH_HLEN,
+			.thoff = ETH_HLEN + sizeof(struct ipv6hdr) +
+				sizeof(struct frag_hdr),
+			.addr_proto = ETH_P_IPV6,
+			.ip_proto = IPPROTO_TCP,
+			.n_proto = __bpf_constant_htons(ETH_P_IPV6),
+			.is_frag = true,
+			.is_first_frag = true,
+			.sport = 80,
+			.dport = 8080,
+		},
+		.flags = BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG,
+	},
+	{
+		.name = "ipv6-no-frag",
+		.pkt.ipv6_frag = {
+			.eth.h_proto = __bpf_constant_htons(ETH_P_IPV6),
+			.iph.nexthdr = IPPROTO_FRAGMENT,
+			.iph.payload_len = __bpf_constant_htons(MAGIC_BYTES),
+			.ipf.nexthdr = IPPROTO_TCP,
+			.tcp.doff = 5,
+			.tcp.source = 80,
+			.tcp.dest = 8080,
+		},
+		.keys = {
+			.nhoff = ETH_HLEN,
+			.thoff = ETH_HLEN + sizeof(struct ipv6hdr) +
+				sizeof(struct frag_hdr),
+			.addr_proto = ETH_P_IPV6,
+			.ip_proto = IPPROTO_TCP,
+			.n_proto = __bpf_constant_htons(ETH_P_IPV6),
+			.is_frag = true,
+			.is_first_frag = true,
+		},
+	},
+	{
+		.name = "ipv6-flow-label",
+		.pkt.ipv6 = {
+			.eth.h_proto = __bpf_constant_htons(ETH_P_IPV6),
+			.iph.nexthdr = IPPROTO_TCP,
+			.iph.payload_len = __bpf_constant_htons(MAGIC_BYTES),
+			.iph.flow_lbl = { 0xb, 0xee, 0xef },
+			.tcp.doff = 5,
+			.tcp.source = 80,
+			.tcp.dest = 8080,
+		},
+		.keys = {
+			.nhoff = ETH_HLEN,
+			.thoff = ETH_HLEN + sizeof(struct ipv6hdr),
+			.addr_proto = ETH_P_IPV6,
+			.ip_proto = IPPROTO_TCP,
+			.n_proto = __bpf_constant_htons(ETH_P_IPV6),
+			.sport = 80,
+			.dport = 8080,
+			.flow_label = __bpf_constant_htonl(0xbeeef),
+		},
+	},
+	{
+		.name = "ipv6-no-flow-label",
+		.pkt.ipv6 = {
+			.eth.h_proto = __bpf_constant_htons(ETH_P_IPV6),
+			.iph.nexthdr = IPPROTO_TCP,
+			.iph.payload_len = __bpf_constant_htons(MAGIC_BYTES),
+			.iph.flow_lbl = { 0xb, 0xee, 0xef },
+			.tcp.doff = 5,
+			.tcp.source = 80,
+			.tcp.dest = 8080,
+		},
+		.keys = {
+			.flags = BPF_FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL,
+			.nhoff = ETH_HLEN,
+			.thoff = ETH_HLEN + sizeof(struct ipv6hdr),
+			.addr_proto = ETH_P_IPV6,
+			.ip_proto = IPPROTO_TCP,
+			.n_proto = __bpf_constant_htons(ETH_P_IPV6),
+			.flow_label = __bpf_constant_htonl(0xbeeef),
+		},
+		.flags = BPF_FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL,
+	},
+	{
+		.name = "ipip-encap",
+		.pkt.ipip = {
+			.eth.h_proto = __bpf_constant_htons(ETH_P_IP),
+			.iph.ihl = 5,
+			.iph.protocol = IPPROTO_IPIP,
+			.iph.tot_len = __bpf_constant_htons(MAGIC_BYTES),
+			.iph_inner.ihl = 5,
+			.iph_inner.protocol = IPPROTO_TCP,
+			.iph_inner.tot_len =
+				__bpf_constant_htons(MAGIC_BYTES) -
+				sizeof(struct iphdr),
+			.tcp.doff = 5,
+			.tcp.source = 80,
+			.tcp.dest = 8080,
+		},
+		.keys = {
+			.nhoff = 0,
+			.nhoff = ETH_HLEN,
+			.thoff = ETH_HLEN + sizeof(struct iphdr) +
+				sizeof(struct iphdr),
+			.addr_proto = ETH_P_IP,
+			.ip_proto = IPPROTO_TCP,
+			.n_proto = __bpf_constant_htons(ETH_P_IP),
+			.is_encap = true,
+			.sport = 80,
+			.dport = 8080,
+		},
+	},
+	{
+		.name = "ipip-no-encap",
+		.pkt.ipip = {
+			.eth.h_proto = __bpf_constant_htons(ETH_P_IP),
+			.iph.ihl = 5,
+			.iph.protocol = IPPROTO_IPIP,
+			.iph.tot_len = __bpf_constant_htons(MAGIC_BYTES),
+			.iph_inner.ihl = 5,
+			.iph_inner.protocol = IPPROTO_TCP,
+			.iph_inner.tot_len =
+				__bpf_constant_htons(MAGIC_BYTES) -
+				sizeof(struct iphdr),
+			.tcp.doff = 5,
+			.tcp.source = 80,
+			.tcp.dest = 8080,
+		},
+		.keys = {
+			.flags = BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP,
+			.nhoff = ETH_HLEN,
+			.thoff = ETH_HLEN + sizeof(struct iphdr),
+			.addr_proto = ETH_P_IP,
+			.ip_proto = IPPROTO_IPIP,
+			.n_proto = __bpf_constant_htons(ETH_P_IP),
+			.is_encap = true,
+		},
+		.flags = BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP,
+	},
 };
 
 static int create_tap(const char *ifname)
@@ -225,6 +465,13 @@ void test_flow_dissector(void)
 			.data_size_in = sizeof(tests[i].pkt),
 			.data_out = &flow_keys,
 		};
+		static struct bpf_flow_keys ctx = {};
+
+		if (tests[i].flags) {
+			tattr.ctx_in = &ctx;
+			tattr.ctx_size_in = sizeof(ctx);
+			ctx.flags = tests[i].flags;
+		}
 
 		err = bpf_prog_test_run_xattr(&tattr);
 		CHECK_ATTR(tattr.data_size_out != sizeof(flow_keys) ||
@@ -251,9 +498,20 @@ void test_flow_dissector(void)
 	CHECK(err, "ifup", "err %d errno %d\n", err, errno);
 
 	for (i = 0; i < ARRAY_SIZE(tests); i++) {
-		struct bpf_flow_keys flow_keys = {};
+		/* Keep in sync with 'flags' from eth_get_headlen. */
+		__u32 eth_get_headlen_flags =
+			BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG;
 		struct bpf_prog_test_run_attr tattr = {};
-		__u32 key = 0;
+		struct bpf_flow_keys flow_keys = {};
+		__u32 key = (__u32)(tests[i].keys.sport) << 16 |
+			    tests[i].keys.dport;
+
+		/* For skb-less case we can't pass input flags; run
+		 * only the tests that have a matching set of flags.
+		 */
+
+		if (tests[i].flags != eth_get_headlen_flags)
+			continue;
 
 		err = tx_tap(tap_fd, &tests[i].pkt, sizeof(tests[i].pkt));
 		CHECK(err < 0, "tx_tap", "err %d errno %d\n", err, errno);
@@ -263,6 +521,9 @@ void test_flow_dissector(void)
 
 		CHECK_ATTR(err, tests[i].name, "skb-less err %d\n", err);
 		CHECK_FLOW_KEYS(tests[i].name, flow_keys, tests[i].keys);
+
+		err = bpf_map_delete_elem(keys_fd, &key);
+		CHECK_ATTR(err, tests[i].name, "bpf_map_delete_elem %d\n", err);
 	}
 
 	bpf_prog_detach(prog_fd, BPF_FLOW_DISSECTOR);

tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c

@@ -1,8 +1,15 @@
 // SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+#include <pthread.h>
+#include <sched.h>
+#include <sys/socket.h>
 #include <test_progs.h>
 
 #define MAX_CNT_RAWTP	10ull
 #define MAX_STACK_RAWTP	100
+
+static int duration = 0;
+
 struct get_stack_trace_t {
 	int pid;
 	int kern_stack_size;
@@ -13,7 +20,7 @@ struct get_stack_trace_t {
 	struct bpf_stack_build_id user_stack_buildid[MAX_STACK_RAWTP];
 };
 
-static int get_stack_print_output(void *data, int size)
+static void get_stack_print_output(void *ctx, int cpu, void *data, __u32 size)
 {
 	bool good_kern_stack = false, good_user_stack = false;
 	const char *nonjit_func = "___bpf_prog_run";
@@ -34,7 +41,7 @@ static int get_stack_print_output(void *data, int size)
 		 * just assume it is good if the stack is not empty.
 		 * This could be improved in the future.
 		 */
-		if (jit_enabled) {
+		if (env.jit_enabled) {
 			found = num_stack > 0;
 		} else {
 			for (i = 0; i < num_stack; i++) {
@@ -51,7 +58,7 @@ static int get_stack_print_output(void *data, int size)
 		}
 	} else {
 		num_stack = e->kern_stack_size / sizeof(__u64);
-		if (jit_enabled) {
+		if (env.jit_enabled) {
 			good_kern_stack = num_stack > 0;
 		} else {
 			for (i = 0; i < num_stack; i++) {
@@ -65,75 +72,76 @@ static int get_stack_print_output(void *data, int size)
 		if (e->user_stack_size > 0 && e->user_stack_buildid_size > 0)
 			good_user_stack = true;
 	}
-	if (!good_kern_stack || !good_user_stack)
-		return LIBBPF_PERF_EVENT_ERROR;
 
-	if (cnt == MAX_CNT_RAWTP)
+	if (!good_kern_stack)
-		return LIBBPF_PERF_EVENT_DONE;
+	    CHECK(!good_kern_stack, "kern_stack", "corrupted kernel stack\n");
-
+	if (!good_user_stack)
-	return LIBBPF_PERF_EVENT_CONT;
+	    CHECK(!good_user_stack, "user_stack", "corrupted user stack\n");
 }
 
 void test_get_stack_raw_tp(void)
 {
 	const char *file = "./test_get_stack_rawtp.o";
-	int i, efd, err, prog_fd, pmu_fd, perfmap_fd;
+	const char *prog_name = "raw_tracepoint/sys_enter";
-	struct perf_event_attr attr = {};
+	int i, err, prog_fd, exp_cnt = MAX_CNT_RAWTP;
+	struct perf_buffer_opts pb_opts = {};
+	struct perf_buffer *pb = NULL;
+	struct bpf_link *link = NULL;
 	struct timespec tv = {0, 10};
-	__u32 key = 0, duration = 0;
+	struct bpf_program *prog;
 	struct bpf_object *obj;
+	struct bpf_map *map;
+	cpu_set_t cpu_set;
 
 	err = bpf_prog_load(file, BPF_PROG_TYPE_RAW_TRACEPOINT, &obj, &prog_fd);
 	if (CHECK(err, "prog_load raw tp", "err %d errno %d\n", err, errno))
 		return;
 
-	efd = bpf_raw_tracepoint_open("sys_enter", prog_fd);
+	prog = bpf_object__find_program_by_title(obj, prog_name);
-	if (CHECK(efd < 0, "raw_tp_open", "err %d errno %d\n", efd, errno))
+	if (CHECK(!prog, "find_probe", "prog '%s' not found\n", prog_name))
 		goto close_prog;
 
-	perfmap_fd = bpf_find_map(__func__, obj, "perfmap");
+	map = bpf_object__find_map_by_name(obj, "perfmap");
-	if (CHECK(perfmap_fd < 0, "bpf_find_map", "err %d errno %d\n",
+	if (CHECK(!map, "bpf_find_map", "not found\n"))
-		  perfmap_fd, errno))
 		goto close_prog;
 
 	err = load_kallsyms();
 	if (CHECK(err < 0, "load_kallsyms", "err %d errno %d\n", err, errno))
 		goto close_prog;
 
-	attr.sample_type = PERF_SAMPLE_RAW;
+	CPU_ZERO(&cpu_set);
-	attr.type = PERF_TYPE_SOFTWARE;
+	CPU_SET(0, &cpu_set);
-	attr.config = PERF_COUNT_SW_BPF_OUTPUT;
+	err = pthread_setaffinity_np(pthread_self(), sizeof(cpu_set), &cpu_set);
-	pmu_fd = syscall(__NR_perf_event_open, &attr, getpid()/*pid*/, -1/*cpu*/,
+	if (CHECK(err, "set_affinity", "err %d, errno %d\n", err, errno))
-			 -1/*group_fd*/, 0);
-	if (CHECK(pmu_fd < 0, "perf_event_open", "err %d errno %d\n", pmu_fd,
-		  errno))
 		goto close_prog;
 
-	err = bpf_map_update_elem(perfmap_fd, &key, &pmu_fd, BPF_ANY);
+	link = bpf_program__attach_raw_tracepoint(prog, "sys_enter");
-	if (CHECK(err < 0, "bpf_map_update_elem", "err %d errno %d\n", err,
+	if (CHECK(IS_ERR(link), "attach_raw_tp", "err %ld\n", PTR_ERR(link)))
-		  errno))
 		goto close_prog;
 
-	err = ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0);
+	pb_opts.sample_cb = get_stack_print_output;
-	if (CHECK(err < 0, "ioctl PERF_EVENT_IOC_ENABLE", "err %d errno %d\n",
+	pb = perf_buffer__new(bpf_map__fd(map), 8, &pb_opts);
-		  err, errno))
+	if (CHECK(IS_ERR(pb), "perf_buf__new", "err %ld\n", PTR_ERR(pb)))
-		goto close_prog;
-
-	err = perf_event_mmap(pmu_fd);
-	if (CHECK(err < 0, "perf_event_mmap", "err %d errno %d\n", err, errno))
 		goto close_prog;
 
 	/* trigger some syscall action */
 	for (i = 0; i < MAX_CNT_RAWTP; i++)
 		nanosleep(&tv, NULL);
 
-	err = perf_event_poller(pmu_fd, get_stack_print_output);
+	while (exp_cnt > 0) {
-	if (CHECK(err < 0, "perf_event_poller", "err %d errno %d\n", err, errno))
+		err = perf_buffer__poll(pb, 100);
-		goto close_prog;
+		if (err < 0 && CHECK(err < 0, "pb__poll", "err %d\n", err))
+			goto close_prog;
+		exp_cnt -= err;
+	}
 
 	goto close_prog_noerr;
 close_prog:
 	error_cnt++;
 close_prog_noerr:
+	if (!IS_ERR_OR_NULL(link))
+		bpf_link__destroy(link);
+	if (!IS_ERR_OR_NULL(pb))
+		perf_buffer__free(pb);
 	bpf_object__close(obj);
 }

tools/testing/selftests/bpf/prog_tests/reference_tracking.c

@@ -1,15 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <test_progs.h>
 
-static int libbpf_debug_print(enum libbpf_print_level level,
-			      const char *format, va_list args)
-{
-	if (level == LIBBPF_DEBUG)
-		return 0;
-
-	return vfprintf(stderr, format, args);
-}
-
 void test_reference_tracking(void)
 {
 	const char *file = "./test_sk_lookup_kern.o";
@@ -36,9 +27,11 @@ void test_reference_tracking(void)
 
 		/* Expect verifier failure if test name has 'fail' */
 		if (strstr(title, "fail") != NULL) {
-			libbpf_set_print(NULL);
+			libbpf_print_fn_t old_print_fn;
+
+			old_print_fn = libbpf_set_print(NULL);
 			err = !bpf_program__load(prog, "GPL", 0);
-			libbpf_set_print(libbpf_debug_print);
+			libbpf_set_print(old_print_fn);
 		} else {
 			err = bpf_program__load(prog, "GPL", 0);
 		}

tools/testing/selftests/bpf/prog_tests/send_signal.c

@@ -203,7 +203,7 @@ static int test_send_signal_nmi(void)
 	if (pmu_fd == -1) {
 		if (errno == ENOENT) {
 			printf("%s:SKIP:no PERF_COUNT_HW_CPU_CYCLES\n",
-				__func__);
+			       __func__);
 			return 0;
 		}
 		/* Let the test fail with a more informative message */
@@ -219,11 +219,10 @@ void test_send_signal(void)
 {
 	int ret = 0;
 
-	ret |= test_send_signal_tracepoint();
+	if (test__start_subtest("send_signal_tracepoint"))
-	ret |= test_send_signal_perf();
+		ret |= test_send_signal_tracepoint();
-	ret |= test_send_signal_nmi();
+	if (test__start_subtest("send_signal_perf"))
-	if (!ret)
+		ret |= test_send_signal_perf();
-		printf("test_send_signal:OK\n");
+	if (test__start_subtest("send_signal_nmi"))
-	else
+		ret |= test_send_signal_nmi();
-		printf("test_send_signal:FAIL\n");
 }

tools/testing/selftests/bpf/prog_tests/xdp_noinline.c

@@ -75,7 +75,8 @@ void test_xdp_noinline(void)
 	}
 	if (bytes != MAGIC_BYTES * NUM_ITER * 2 || pkts != NUM_ITER * 2) {
 		error_cnt++;
-		printf("test_xdp_noinline:FAIL:stats %lld %lld\n", bytes, pkts);
+		printf("test_xdp_noinline:FAIL:stats %lld %lld\n",
+		       bytes, pkts);
 	}
 out:
 	bpf_object__close(obj);

tools/testing/selftests/bpf/progs/bpf_flow.c

@@ -65,8 +65,8 @@ struct {
 } jmp_table SEC(".maps");
 
 struct {
-	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(type, BPF_MAP_TYPE_HASH);
-	__uint(max_entries, 1);
+	__uint(max_entries, 1024);
 	__type(key, __u32);
 	__type(value, struct bpf_flow_keys);
 } last_dissection SEC(".maps");
@@ -74,15 +74,20 @@ struct {
 static __always_inline int export_flow_keys(struct bpf_flow_keys *keys,
 					    int ret)
 {
-	struct bpf_flow_keys *val;
+	__u32 key = (__u32)(keys->sport) << 16 | keys->dport;
-	__u32 key = 0;
+	struct bpf_flow_keys val;
 
-	val = bpf_map_lookup_elem(&last_dissection, &key);
+	memcpy(&val, keys, sizeof(val));
-	if (val)
+	bpf_map_update_elem(&last_dissection, &key, &val, BPF_ANY);
-		memcpy(val, keys, sizeof(*val));
 	return ret;
 }
 
+#define IPV6_FLOWLABEL_MASK		__bpf_constant_htonl(0x000FFFFF)
+static inline __be32 ip6_flowlabel(const struct ipv6hdr *hdr)
+{
+	return *(__be32 *)hdr & IPV6_FLOWLABEL_MASK;
+}
+
 static __always_inline void *bpf_flow_dissect_get_header(struct __sk_buff *skb,
 							 __u16 hdr_size,
 							 void *buffer)
@@ -153,7 +158,6 @@ static __always_inline int parse_ip_proto(struct __sk_buff *skb, __u8 proto)
 	struct tcphdr *tcp, _tcp;
 	struct udphdr *udp, _udp;
 
-	keys->ip_proto = proto;
 	switch (proto) {
 	case IPPROTO_ICMP:
 		icmp = bpf_flow_dissect_get_header(skb, sizeof(*icmp), &_icmp);
@@ -162,9 +166,15 @@ static __always_inline int parse_ip_proto(struct __sk_buff *skb, __u8 proto)
 		return export_flow_keys(keys, BPF_OK);
 	case IPPROTO_IPIP:
 		keys->is_encap = true;
+		if (keys->flags & BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP)
+			return export_flow_keys(keys, BPF_OK);
+
 		return parse_eth_proto(skb, bpf_htons(ETH_P_IP));
 	case IPPROTO_IPV6:
 		keys->is_encap = true;
+		if (keys->flags & BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP)
+			return export_flow_keys(keys, BPF_OK);
+
 		return parse_eth_proto(skb, bpf_htons(ETH_P_IPV6));
 	case IPPROTO_GRE:
 		gre = bpf_flow_dissect_get_header(skb, sizeof(*gre), &_gre);
@@ -184,6 +194,8 @@ static __always_inline int parse_ip_proto(struct __sk_buff *skb, __u8 proto)
 			keys->thoff += 4; /* Step over sequence number */
 
 		keys->is_encap = true;
+		if (keys->flags & BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP)
+			return export_flow_keys(keys, BPF_OK);
 
 		if (gre->proto == bpf_htons(ETH_P_TEB)) {
 			eth = bpf_flow_dissect_get_header(skb, sizeof(*eth),
@@ -231,7 +243,6 @@ static __always_inline int parse_ipv6_proto(struct __sk_buff *skb, __u8 nexthdr)
 {
 	struct bpf_flow_keys *keys = skb->flow_keys;
 
-	keys->ip_proto = nexthdr;
 	switch (nexthdr) {
 	case IPPROTO_HOPOPTS:
 	case IPPROTO_DSTOPTS:
@@ -266,6 +277,7 @@ PROG(IP)(struct __sk_buff *skb)
 	keys->addr_proto = ETH_P_IP;
 	keys->ipv4_src = iph->saddr;
 	keys->ipv4_dst = iph->daddr;
+	keys->ip_proto = iph->protocol;
 
 	keys->thoff += iph->ihl << 2;
 	if (data + keys->thoff > data_end)
@@ -273,13 +285,20 @@ PROG(IP)(struct __sk_buff *skb)
 
 	if (iph->frag_off & bpf_htons(IP_MF | IP_OFFSET)) {
 		keys->is_frag = true;
-		if (iph->frag_off & bpf_htons(IP_OFFSET))
+		if (iph->frag_off & bpf_htons(IP_OFFSET)) {
 			/* From second fragment on, packets do not have headers
 			 * we can parse.
 			 */
 			done = true;
-		else
+		} else {
 			keys->is_first_frag = true;
+			/* No need to parse fragmented packet unless
+			 * explicitly asked for.
+			 */
+			if (!(keys->flags &
+			      BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG))
+				done = true;
+		}
 	}
 
 	if (done)
@@ -301,6 +320,11 @@ PROG(IPV6)(struct __sk_buff *skb)
 	memcpy(&keys->ipv6_src, &ip6h->saddr, 2*sizeof(ip6h->saddr));
 
 	keys->thoff += sizeof(struct ipv6hdr);
+	keys->ip_proto = ip6h->nexthdr;
+	keys->flow_label = ip6_flowlabel(ip6h);
+
+	if (keys->flags & BPF_FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL)
+		return export_flow_keys(keys, BPF_OK);
 
 	return parse_ipv6_proto(skb, ip6h->nexthdr);
 }
@@ -317,7 +341,8 @@ PROG(IPV6OP)(struct __sk_buff *skb)
 	/* hlen is in 8-octets and does not include the first 8 bytes
 	 * of the header
 	 */
-	skb->flow_keys->thoff += (1 + ip6h->hdrlen) << 3;
+	keys->thoff += (1 + ip6h->hdrlen) << 3;
+	keys->ip_proto = ip6h->nexthdr;
 
 	return parse_ipv6_proto(skb, ip6h->nexthdr);
 }
@@ -333,9 +358,18 @@ PROG(IPV6FR)(struct __sk_buff *skb)
 
 	keys->thoff += sizeof(*fragh);
 	keys->is_frag = true;
-	if (!(fragh->frag_off & bpf_htons(IP6_OFFSET)))
+	keys->ip_proto = fragh->nexthdr;
+
+	if (!(fragh->frag_off & bpf_htons(IP6_OFFSET))) {
 		keys->is_first_frag = true;
 
+		/* No need to parse fragmented packet unless
+		 * explicitly asked for.
+		 */
+		if (!(keys->flags & BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG))
+			return export_flow_keys(keys, BPF_OK);
+	}
+
 	return parse_ipv6_proto(skb, fragh->nexthdr);
 }
 

tools/testing/selftests/bpf/progs/btf__core_reloc_arrays.c

@@ -0,0 +1,3 @@
+#include "core_reloc_types.h"
+
+void f(struct core_reloc_arrays x) {}

tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___diff_arr_dim.c

@@ -0,0 +1,3 @@
+#include "core_reloc_types.h"
+
+void f(struct core_reloc_arrays___diff_arr_dim x) {}

tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___diff_arr_val_sz.c

@@ -0,0 +1,3 @@
+#include "core_reloc_types.h"
+
+void f(struct core_reloc_arrays___diff_arr_val_sz x) {}

tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_non_array.c

@@ -0,0 +1,3 @@
+#include "core_reloc_types.h"
+
+void f(struct core_reloc_arrays___err_non_array x) {}

tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_too_shallow.c

@@ -0,0 +1,3 @@
+#include "core_reloc_types.h"
+
+void f(struct core_reloc_arrays___err_too_shallow x) {}

tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_too_small.c

@@ -0,0 +1,3 @@
+#include "core_reloc_types.h"
+
+void f(struct core_reloc_arrays___err_too_small x) {}

tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_wrong_val_type1.c

@@ -0,0 +1,3 @@
+#include "core_reloc_types.h"
+
+void f(struct core_reloc_arrays___err_wrong_val_type1 x) {}

tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_wrong_val_type2.c

@@ -0,0 +1,3 @@
+#include "core_reloc_types.h"
+
+void f(struct core_reloc_arrays___err_wrong_val_type2 x) {}

tools/testing/selftests/bpf/progs/btf__core_reloc_flavors.c

@@ -0,0 +1,3 @@
+#include "core_reloc_types.h"
+
+void f(struct core_reloc_flavors x) {}

tools/testing/selftests/bpf/progs/btf__core_reloc_flavors__err_wrong_name.c

@@ -0,0 +1,3 @@
+#include "core_reloc_types.h"
+
+void f(struct core_reloc_flavors__err_wrong_name x) {}

tools/testing/selftests/bpf/progs/btf__core_reloc_ints.c

@@ -0,0 +1,3 @@
+#include "core_reloc_types.h"
+
+void f(struct core_reloc_ints x) {}

tools/testing/selftests/bpf/progs/btf__core_reloc_ints___bool.c

@@ -0,0 +1,3 @@
+#include "core_reloc_types.h"
+
+void f(struct core_reloc_ints___bool x) {}

tools/testing/selftests/bpf/progs/btf__core_reloc_ints___err_bitfield.c

@@ -0,0 +1,3 @@
+#include "core_reloc_types.h"
+
+void f(struct core_reloc_ints___err_bitfield x) {}

tools/testing/selftests/bpf/progs/btf__core_reloc_ints___err_wrong_sz_16.c

@@ -0,0 +1,3 @@
+#include "core_reloc_types.h"
+
+void f(struct core_reloc_ints___err_wrong_sz_16 x) {}

tools/testing/selftests/bpf/progs/btf__core_reloc_ints___err_wrong_sz_32.c

@@ -0,0 +1,3 @@
+#include "core_reloc_types.h"
+
+void f(struct core_reloc_ints___err_wrong_sz_32 x) {}

tools/testing/selftests/bpf/progs/btf__core_reloc_ints___err_wrong_sz_64.c

@@ -0,0 +1,3 @@
+#include "core_reloc_types.h"
+
+void f(struct core_reloc_ints___err_wrong_sz_64 x) {}

tools/testing/selftests/bpf/progs/btf__core_reloc_ints___err_wrong_sz_8.c

@@ -0,0 +1,3 @@
+#include "core_reloc_types.h"
+
+void f(struct core_reloc_ints___err_wrong_sz_8 x) {}

tools/testing/selftests/bpf/progs/btf__core_reloc_ints___reverse_sign.c

@@ -0,0 +1,3 @@
+#include "core_reloc_types.h"
+
+void f(struct core_reloc_ints___reverse_sign x) {}

tools/testing/selftests/bpf/progs/btf__core_reloc_misc.c

@@ -0,0 +1,5 @@
+#include "core_reloc_types.h"
+
+void f1(struct core_reloc_misc___a x) {}
+void f2(struct core_reloc_misc___b x) {}
+void f3(struct core_reloc_misc_extensible x) {}

tools/testing/selftests/bpf/progs/btf__core_reloc_mods.c

@@ -0,0 +1,3 @@
+#include "core_reloc_types.h"
+
+void f(struct core_reloc_mods x) {}

tools/testing/selftests/bpf/progs/btf__core_reloc_mods___mod_swap.c

@@ -0,0 +1,3 @@
+#include "core_reloc_types.h"
+
+void f(struct core_reloc_mods___mod_swap x) {}

tools/testing/selftests/bpf/progs/btf__core_reloc_mods___typedefs.c

@@ -0,0 +1,3 @@
+#include "core_reloc_types.h"
+
+void f(struct core_reloc_mods___typedefs x) {}

tools/testing/selftests/bpf/progs/btf__core_reloc_nesting.c

@@ -0,0 +1,3 @@
+#include "core_reloc_types.h"
+
+void f(struct core_reloc_nesting x) {}

tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___anon_embed.c

@@ -0,0 +1,3 @@
+#include "core_reloc_types.h"
+
+void f(struct core_reloc_nesting___anon_embed x) {}

tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___dup_compat_types.c

@@ -0,0 +1,5 @@
+#include "core_reloc_types.h"
+
+void f1(struct core_reloc_nesting___dup_compat_types x) {}
+void f2(struct core_reloc_nesting___dup_compat_types__2 x) {}
+void f3(struct core_reloc_nesting___dup_compat_types__3 x) {}

tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_array_container.c

@@ -0,0 +1,3 @@
+#include "core_reloc_types.h"
+
+void f(struct core_reloc_nesting___err_array_container x) {}

tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_array_field.c

@@ -0,0 +1,3 @@
+#include "core_reloc_types.h"
+
+void f(struct core_reloc_nesting___err_array_field x) {}

tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_dup_incompat_types.c

@@ -0,0 +1,4 @@
+#include "core_reloc_types.h"
+
+void f1(struct core_reloc_nesting___err_dup_incompat_types__1 x) {}
+void f2(struct core_reloc_nesting___err_dup_incompat_types__2 x) {}

tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_missing_container.c

@@ -0,0 +1,3 @@
+#include "core_reloc_types.h"
+
+void f(struct core_reloc_nesting___err_missing_container x) {}

tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_missing_field.c

@@ -0,0 +1,3 @@
+#include "core_reloc_types.h"
+
+void f(struct core_reloc_nesting___err_missing_field x) {}

tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_nonstruct_container.c

@@ -0,0 +1,3 @@
+#include "core_reloc_types.h"
+
+void f(struct core_reloc_nesting___err_nonstruct_container x) {}

tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_partial_match_dups.c

@@ -0,0 +1,4 @@
+#include "core_reloc_types.h"
+
+void f1(struct core_reloc_nesting___err_partial_match_dups__a x) {}
+void f2(struct core_reloc_nesting___err_partial_match_dups__b x) {}

tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_too_deep.c

@@ -0,0 +1,3 @@
+#include "core_reloc_types.h"
+
+void f(struct core_reloc_nesting___err_too_deep x) {}

tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___extra_nesting.c

@@ -0,0 +1,3 @@
+#include "core_reloc_types.h"
+
+void f(struct core_reloc_nesting___extra_nesting x) {}

tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___struct_union_mixup.c

@@ -0,0 +1,3 @@
+#include "core_reloc_types.h"
+
+void f(struct core_reloc_nesting___struct_union_mixup x) {}

tools/testing/selftests/bpf/progs/btf__core_reloc_primitives.c

@@ -0,0 +1,3 @@
+#include "core_reloc_types.h"
+
+void f(struct core_reloc_primitives x) {}

tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___diff_enum_def.c

@@ -0,0 +1,3 @@
+#include "core_reloc_types.h"
+
+void f(struct core_reloc_primitives___diff_enum_def x) {}

tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___diff_func_proto.c

@@ -0,0 +1,3 @@
+#include "core_reloc_types.h"
+
+void f(struct core_reloc_primitives___diff_func_proto x) {}

tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___diff_ptr_type.c

@@ -0,0 +1,3 @@
+#include "core_reloc_types.h"
+
+void f(struct core_reloc_primitives___diff_ptr_type x) {}

tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___err_non_enum.c

@@ -0,0 +1,3 @@
+#include "core_reloc_types.h"
+
+void f(struct core_reloc_primitives___err_non_enum x) {}

tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___err_non_int.c

@@ -0,0 +1,3 @@
+#include "core_reloc_types.h"
+
+void f(struct core_reloc_primitives___err_non_int x) {}

tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___err_non_ptr.c

@@ -0,0 +1,3 @@
+#include "core_reloc_types.h"
+
+void f(struct core_reloc_primitives___err_non_ptr x) {}

tools/testing/selftests/bpf/progs/btf__core_reloc_ptr_as_arr.c

@@ -0,0 +1,3 @@
+#include "core_reloc_types.h"
+
+void f(struct core_reloc_ptr_as_arr x) {}

tools/testing/selftests/bpf/progs/btf__core_reloc_ptr_as_arr___diff_sz.c

@@ -0,0 +1,3 @@
+#include "core_reloc_types.h"
+
+void f(struct core_reloc_ptr_as_arr___diff_sz x) {}

tools/testing/selftests/bpf/progs/core_reloc_types.h

@@ -0,0 +1,667 @@
+#include <stdint.h>
+#include <stdbool.h>
+
+/*
+ * FLAVORS
+ */
+struct core_reloc_flavors {
+	int a;
+	int b;
+	int c;
+};
+
+/* this is not a flavor, as it doesn't have triple underscore */
+struct core_reloc_flavors__err_wrong_name {
+	int a;
+	int b;
+	int c;
+};
+
+/*
+ * NESTING
+ */
+/* original set up, used to record relocations in BPF program */
+struct core_reloc_nesting_substruct {
+	int a;
+};
+
+union core_reloc_nesting_subunion {
+	int b;
+};
+
+struct core_reloc_nesting {
+	union {
+		struct core_reloc_nesting_substruct a;
+	} a;
+	struct {
+		union core_reloc_nesting_subunion b;
+	} b;
+};
+
+/* inlined anonymous struct/union instead of named structs in original */
+struct core_reloc_nesting___anon_embed {
+	int __just_for_padding;
+	union {
+		struct {
+			int a;
+		} a;
+	} a;
+	struct {
+		union {
+			int b;
+		} b;
+	} b;
+};
+
+/* different mix of nested structs/unions than in original */
+struct core_reloc_nesting___struct_union_mixup {
+	int __a;
+	struct {
+		int __a;
+		union {
+			char __a;
+			int a;
+		} a;
+	} a;
+	int __b;
+	union {
+		int __b;
+		union {
+			char __b;
+			int b;
+		} b;
+	} b;
+};
+
+/* extra anon structs/unions, but still valid a.a.a and b.b.b accessors */
+struct core_reloc_nesting___extra_nesting {
+	int __padding;
+	struct {
+		struct {
+			struct {
+				struct {
+					union {
+						int a;
+					} a;
+				};
+			};
+		} a;
+		int __some_more;
+		struct {
+			union {
+				union {
+					union {
+						struct {
+							int b;
+						};
+					} b;
+				};
+			} b;
+		};
+	};
+};
+
+/* three flavors of same struct with different structure but same layout for
+ * a.a.a and b.b.b, thus successfully resolved and relocatable */
+struct core_reloc_nesting___dup_compat_types {
+	char __just_for_padding;
+	/* 3 more bytes of padding */
+	struct {
+		struct {
+			int a; /* offset 4 */
+		} a;
+	} a;
+	long long __more_padding;
+	struct {
+		struct {
+			int b; /* offset 16 */
+		} b;
+	} b;
+};
+
+struct core_reloc_nesting___dup_compat_types__2 {
+	int __aligned_padding;
+	struct {
+		int __trickier_noop[0];
+		struct {
+			char __some_more_noops[0];
+			int a; /* offset 4 */
+		} a;
+	} a;
+	int __more_padding;
+	struct {
+		struct {
+			struct {
+				int __critical_padding;
+				int b; /* offset 16 */
+			} b;
+			int __does_not_matter;
+		};
+	} b;
+	int __more_irrelevant_stuff;
+};
+
+struct core_reloc_nesting___dup_compat_types__3 {
+	char __correct_padding[4];
+	struct {
+		struct {
+			int a; /* offset 4 */
+		} a;
+	} a;
+	/* 8 byte padding due to next struct's alignment */
+	struct {
+		struct {
+			int b;
+		} b;
+	} b __attribute__((aligned(16)));
+};
+
+/* b.b.b field is missing */
+struct core_reloc_nesting___err_missing_field {
+	struct {
+		struct {
+			int a;
+		} a;
+	} a;
+	struct {
+		struct {
+			int x;
+		} b;
+	} b;
+};
+
+/* b.b.b field is an array of integers instead of plain int */
+struct core_reloc_nesting___err_array_field {
+	struct {
+		struct {
+			int a;
+		} a;
+	} a;
+	struct {
+		struct {
+			int b[1];
+		} b;
+	} b;
+};
+
+/* middle b container is missing */
+struct core_reloc_nesting___err_missing_container {
+	struct {
+		struct {
+			int a;
+		} a;
+	} a;
+	struct {
+		int x;
+	} b;
+};
+
+/* middle b container is referenced through pointer instead of being embedded */
+struct core_reloc_nesting___err_nonstruct_container {
+	struct {
+		struct {
+			int a;
+		} a;
+	} a;
+	struct {
+		struct {
+			int b;
+		} *b;
+	} b;
+};
+
+/* middle b container is an array of structs instead of plain struct */
+struct core_reloc_nesting___err_array_container {
+	struct {
+		struct {
+			int a;
+		} a;
+	} a;
+	struct {
+		struct {
+			int b;
+		} b[1];
+	} b;
+};
+
+/* two flavors of same struct with incompatible layout for b.b.b */
+struct core_reloc_nesting___err_dup_incompat_types__1 {
+	struct {
+		struct {
+			int a; /* offset 0 */
+		} a;
+	} a;
+	struct {
+		struct {
+			int b; /* offset 4 */
+		} b;
+	} b;
+};
+
+struct core_reloc_nesting___err_dup_incompat_types__2 {
+	struct {
+		struct {
+			int a; /* offset 0 */
+		} a;
+	} a;
+	int __extra_padding;
+	struct {
+		struct {
+			int b; /* offset 8 (!) */
+		} b;
+	} b;
+};
+
+/* two flavors of same struct having one of a.a.a and b.b.b, but not both */
+struct core_reloc_nesting___err_partial_match_dups__a {
+	struct {
+		struct {
+			int a;
+		} a;
+	} a;
+};
+
+struct core_reloc_nesting___err_partial_match_dups__b {
+	struct {
+		struct {
+			int b;
+		} b;
+	} b;
+};
+
+struct core_reloc_nesting___err_too_deep {
+	struct {
+		struct {
+			int a;
+		} a;
+	} a;
+	/* 65 levels of nestedness for b.b.b */
+	struct {
+		struct {
+			struct { struct { struct { struct { struct {
+			struct { struct { struct { struct { struct {
+			struct { struct { struct { struct { struct {
+			struct { struct { struct { struct { struct {
+			struct { struct { struct { struct { struct {
+			struct { struct { struct { struct { struct {
+			struct { struct { struct { struct { struct {
+			struct { struct { struct { struct { struct {
+			struct { struct { struct { struct { struct {
+			struct { struct { struct { struct { struct {
+			struct { struct { struct { struct { struct {
+			struct { struct { struct { struct { struct {
+				/* this one is one too much */
+				struct {
+					int b;
+				};
+			}; }; }; }; };
+			}; }; }; }; };
+			}; }; }; }; };
+			}; }; }; }; };
+			}; }; }; }; };
+			}; }; }; }; };
+			}; }; }; }; };
+			}; }; }; }; };
+			}; }; }; }; };
+			}; }; }; }; };
+			}; }; }; }; };
+			}; }; }; }; };
+		} b;
+	} b;
+};
+
+/*
+ * ARRAYS
+ */
+struct core_reloc_arrays_output {
+	int a2;
+	char b123;
+	int c1c;
+	int d00d;
+};
+
+struct core_reloc_arrays_substruct {
+	int c;
+	int d;
+};
+
+struct core_reloc_arrays {
+	int a[5];
+	char b[2][3][4];
+	struct core_reloc_arrays_substruct c[3];
+	struct core_reloc_arrays_substruct d[1][2];
+};
+
+/* bigger array dimensions */
+struct core_reloc_arrays___diff_arr_dim {
+	int a[7];
+	char b[3][4][5];
+	struct core_reloc_arrays_substruct c[4];
+	struct core_reloc_arrays_substruct d[2][3];
+};
+
+/* different size of array's value (struct) */
+struct core_reloc_arrays___diff_arr_val_sz {
+	int a[5];
+	char b[2][3][4];
+	struct {
+		int __padding1;
+		int c;
+		int __padding2;
+	} c[3];
+	struct {
+		int __padding1;
+		int d;
+		int __padding2;
+	} d[1][2];
+};
+
+struct core_reloc_arrays___err_too_small {
+	int a[2]; /* this one is too small */
+	char b[2][3][4];
+	struct core_reloc_arrays_substruct c[3];
+	struct core_reloc_arrays_substruct d[1][2];
+};
+
+struct core_reloc_arrays___err_too_shallow {
+	int a[5];
+	char b[2][3]; /* this one lacks one dimension */
+	struct core_reloc_arrays_substruct c[3];
+	struct core_reloc_arrays_substruct d[1][2];
+};
+
+struct core_reloc_arrays___err_non_array {
+	int a; /* not an array */
+	char b[2][3][4];
+	struct core_reloc_arrays_substruct c[3];
+	struct core_reloc_arrays_substruct d[1][2];
+};
+
+struct core_reloc_arrays___err_wrong_val_type1 {
+	char a[5]; /* char instead of int */
+	char b[2][3][4];
+	struct core_reloc_arrays_substruct c[3];
+	struct core_reloc_arrays_substruct d[1][2];
+};
+
+struct core_reloc_arrays___err_wrong_val_type2 {
+	int a[5];
+	char b[2][3][4];
+	int c[3]; /* value is not a struct */
+	struct core_reloc_arrays_substruct d[1][2];
+};
+
+/*
+ * PRIMITIVES
+ */
+enum core_reloc_primitives_enum {
+	A = 0,
+	B = 1,
+};
+
+struct core_reloc_primitives {
+	char a;
+	int b;
+	enum core_reloc_primitives_enum c;
+	void *d;
+	int (*f)(const char *);
+};
+
+struct core_reloc_primitives___diff_enum_def {
+	char a;
+	int b;
+	void *d;
+	int (*f)(const char *);
+	enum {
+		X = 100,
+		Y = 200,
+	} c; /* inline enum def with differing set of values */
+};
+
+struct core_reloc_primitives___diff_func_proto {
+	void (*f)(int); /* incompatible function prototype */
+	void *d;
+	enum core_reloc_primitives_enum c;
+	int b;
+	char a;
+};
+
+struct core_reloc_primitives___diff_ptr_type {
+	const char * const d; /* different pointee type + modifiers */
+	char a;
+	int b;
+	enum core_reloc_primitives_enum c;
+	int (*f)(const char *);
+};
+
+struct core_reloc_primitives___err_non_enum {
+	char a[1];
+	int b;
+	int c; /* int instead of enum */
+	void *d;
+	int (*f)(const char *);
+};
+
+struct core_reloc_primitives___err_non_int {
+	char a[1];
+	int *b; /* ptr instead of int */
+	enum core_reloc_primitives_enum c;
+	void *d;
+	int (*f)(const char *);
+};
+
+struct core_reloc_primitives___err_non_ptr {
+	char a[1];
+	int b;
+	enum core_reloc_primitives_enum c;
+	int d; /* int instead of ptr */
+	int (*f)(const char *);
+};
+
+/*
+ * MODS
+ */
+struct core_reloc_mods_output {
+	int a, b, c, d, e, f, g, h;
+};
+
+typedef const int int_t;
+typedef const char *char_ptr_t;
+typedef const int arr_t[7];
+
+struct core_reloc_mods_substruct {
+	int x;
+	int y;
+};
+
+typedef struct {
+	int x;
+	int y;
+} core_reloc_mods_substruct_t;
+
+struct core_reloc_mods {
+	int a;
+	int_t b;
+	char *c;
+	char_ptr_t d;
+	int e[3];
+	arr_t f;
+	struct core_reloc_mods_substruct g;
+	core_reloc_mods_substruct_t h;
+};
+
+/* a/b, c/d, e/f, and g/h pairs are swapped */
+struct core_reloc_mods___mod_swap {
+	int b;
+	int_t a;
+	char *d;
+	char_ptr_t c;
+	int f[3];
+	arr_t e;
+	struct {
+		int y;
+		int x;
+	} h;
+	core_reloc_mods_substruct_t g;
+};
+
+typedef int int1_t;
+typedef int1_t int2_t;
+typedef int2_t int3_t;
+
+typedef int arr1_t[5];
+typedef arr1_t arr2_t;
+typedef arr2_t arr3_t;
+typedef arr3_t arr4_t;
+
+typedef const char * const volatile fancy_char_ptr_t;
+
+typedef core_reloc_mods_substruct_t core_reloc_mods_substruct_tt;
+
+/* we need more typedefs */
+struct core_reloc_mods___typedefs {
+	core_reloc_mods_substruct_tt g;
+	core_reloc_mods_substruct_tt h;
+	arr4_t f;
+	arr4_t e;
+	fancy_char_ptr_t d;
+	fancy_char_ptr_t c;
+	int3_t b;
+	int3_t a;
+};
+
+/*
+ * PTR_AS_ARR
+ */
+struct core_reloc_ptr_as_arr {
+	int a;
+};
+
+struct core_reloc_ptr_as_arr___diff_sz {
+	int :32; /* padding */
+	char __some_more_padding;
+	int a;
+};
+
+/*
+ * INTS
+ */
+struct core_reloc_ints {
+	uint8_t		u8_field;
+	int8_t		s8_field;
+	uint16_t	u16_field;
+	int16_t		s16_field;
+	uint32_t	u32_field;
+	int32_t		s32_field;
+	uint64_t	u64_field;
+	int64_t		s64_field;
+};
+
+/* signed/unsigned types swap */
+struct core_reloc_ints___reverse_sign {
+	int8_t		u8_field;
+	uint8_t		s8_field;
+	int16_t		u16_field;
+	uint16_t	s16_field;
+	int32_t		u32_field;
+	uint32_t	s32_field;
+	int64_t		u64_field;
+	uint64_t	s64_field;
+};
+
+struct core_reloc_ints___bool {
+	bool		u8_field; /* bool instead of uint8 */
+	int8_t		s8_field;
+	uint16_t	u16_field;
+	int16_t		s16_field;
+	uint32_t	u32_field;
+	int32_t		s32_field;
+	uint64_t	u64_field;
+	int64_t		s64_field;
+};
+
+struct core_reloc_ints___err_bitfield {
+	uint8_t		u8_field;
+	int8_t		s8_field;
+	uint16_t	u16_field;
+	int16_t		s16_field;
+	uint32_t	u32_field: 32; /* bitfields are not supported */
+	int32_t		s32_field;
+	uint64_t	u64_field;
+	int64_t		s64_field;
+};
+
+struct core_reloc_ints___err_wrong_sz_8 {
+	uint16_t	u8_field; /* not 8-bit anymore */
+	int16_t		s8_field; /* not 8-bit anymore */
+
+	uint16_t	u16_field;
+	int16_t		s16_field;
+	uint32_t	u32_field;
+	int32_t		s32_field;
+	uint64_t	u64_field;
+	int64_t		s64_field;
+};
+
+struct core_reloc_ints___err_wrong_sz_16 {
+	uint8_t		u8_field;
+	int8_t		s8_field;
+
+	uint32_t	u16_field; /* not 16-bit anymore */
+	int32_t		s16_field; /* not 16-bit anymore */
+
+	uint32_t	u32_field;
+	int32_t		s32_field;
+	uint64_t	u64_field;
+	int64_t		s64_field;
+};
+
+struct core_reloc_ints___err_wrong_sz_32 {
+	uint8_t		u8_field;
+	int8_t		s8_field;
+	uint16_t	u16_field;
+	int16_t		s16_field;
+
+	uint64_t	u32_field; /* not 32-bit anymore */
+	int64_t		s32_field; /* not 32-bit anymore */
+
+	uint64_t	u64_field;
+	int64_t		s64_field;
+};
+
+struct core_reloc_ints___err_wrong_sz_64 {
+	uint8_t		u8_field;
+	int8_t		s8_field;
+	uint16_t	u16_field;
+	int16_t		s16_field;
+	uint32_t	u32_field;
+	int32_t		s32_field;
+
+	uint32_t	u64_field; /* not 64-bit anymore */
+	int32_t		s64_field; /* not 64-bit anymore */
+};
+
+/*
+ * MISC
+ */
+struct core_reloc_misc_output {
+	int a, b, c;
+};
+
+struct core_reloc_misc___a {
+	int a1;
+	int a2;
+};
+
+struct core_reloc_misc___b {
+	int b1;
+	int b2;
+};
+
+/* this one extends core_reloc_misc_extensible struct from BPF prog */
+struct core_reloc_misc_extensible {
+	int a;
+	int b;
+	int c;
+	int d;
+};

tools/testing/selftests/bpf/progs/loop4.c

@@ -0,0 +1,18 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2019 Facebook
+#include <linux/bpf.h>
+#include "bpf_helpers.h"
+
+char _license[] SEC("license") = "GPL";
+
+SEC("socket")
+int combinations(volatile struct __sk_buff* skb)
+{
+	int ret = 0, i;
+
+#pragma nounroll
+	for (i = 0; i < 20; i++)
+		if (skb->len)
+			ret |= 1 << i;
+	return ret;
+}

tools/testing/selftests/bpf/progs/loop5.c

@@ -0,0 +1,32 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2019 Facebook
+#include <linux/bpf.h>
+#include "bpf_helpers.h"
+#define barrier() __asm__ __volatile__("": : :"memory")
+
+char _license[] SEC("license") = "GPL";
+
+SEC("socket")
+int while_true(volatile struct __sk_buff* skb)
+{
+	int i = 0;
+
+	while (1) {
+		if (skb->len)
+			i += 3;
+		else
+			i += 7;
+		if (i == 9)
+			break;
+		barrier();
+		if (i == 10)
+			break;
+		barrier();
+		if (i == 13)
+			break;
+		barrier();
+		if (i == 14)
+			break;
+	}
+	return i;
+}

tools/testing/selftests/bpf/progs/sockopt_sk.c

@@ -1,5 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <string.h>
 #include <netinet/in.h>
+#include <netinet/tcp.h>
 #include <linux/bpf.h>
 #include "bpf_helpers.h"
 
@@ -42,6 +44,14 @@ int _getsockopt(struct bpf_sockopt *ctx)
 		return 1;
 	}
 
+	if (ctx->level == SOL_TCP && ctx->optname == TCP_CONGESTION) {
+		/* Not interested in SOL_TCP:TCP_CONGESTION;
+		 * let next BPF program in the cgroup chain or kernel
+		 * handle it.
+		 */
+		return 1;
+	}
+
 	if (ctx->level != SOL_CUSTOM)
 		return 0; /* EPERM, deny everything except custom level */
 
@@ -91,6 +101,18 @@ int _setsockopt(struct bpf_sockopt *ctx)
 		return 1;
 	}
 
+	if (ctx->level == SOL_TCP && ctx->optname == TCP_CONGESTION) {
+		/* Always use cubic */
+
+		if (optval + 5 > optval_end)
+			return 0; /* EPERM, bounds check */
+
+		memcpy(optval, "cubic", 5);
+		ctx->optlen = 5;
+
+		return 1;
+	}
+
 	if (ctx->level != SOL_CUSTOM)
 		return 0; /* EPERM, deny everything except custom level */
 

tools/testing/selftests/bpf/progs/test_core_reloc_arrays.c

@@ -0,0 +1,55 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2019 Facebook
+
+#include <linux/bpf.h>
+#include <stdint.h>
+#include "bpf_helpers.h"
+
+char _license[] SEC("license") = "GPL";
+
+static volatile struct data {
+	char in[256];
+	char out[256];
+} data;
+
+struct core_reloc_arrays_output {
+	int a2;
+	char b123;
+	int c1c;
+	int d00d;
+};
+
+struct core_reloc_arrays_substruct {
+	int c;
+	int d;
+};
+
+struct core_reloc_arrays {
+	int a[5];
+	char b[2][3][4];
+	struct core_reloc_arrays_substruct c[3];
+	struct core_reloc_arrays_substruct d[1][2];
+};
+
+SEC("raw_tracepoint/sys_enter")
+int test_core_arrays(void *ctx)
+{
+	struct core_reloc_arrays *in = (void *)&data.in;
+	struct core_reloc_arrays_output *out = (void *)&data.out;
+
+	/* in->a[2] */
+	if (BPF_CORE_READ(&out->a2, &in->a[2]))
+		return 1;
+	/* in->b[1][2][3] */
+	if (BPF_CORE_READ(&out->b123, &in->b[1][2][3]))
+		return 1;
+	/* in->c[1].c */
+	if (BPF_CORE_READ(&out->c1c, &in->c[1].c))
+		return 1;
+	/* in->d[0][0].d */
+	if (BPF_CORE_READ(&out->d00d, &in->d[0][0].d))
+		return 1;
+
+	return 0;
+}
+