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

Daniel Borkmann says:

====================
pull-request: bpf-next 2018-08-13

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

The main changes are:

1) Add driver XDP support for veth. This can be used in conjunction with
   redirect of another XDP program e.g. sitting on NIC so the xdp_frame
   can be forwarded to the peer veth directly without modification,
   from Toshiaki.

2) Add a new BPF map type REUSEPORT_SOCKARRAY and prog type SK_REUSEPORT
   in order to provide more control and visibility on where a SO_REUSEPORT
   sk should be located, and the latter enables to directly select a sk
   from the bpf map. This also enables map-in-map for application migration
   use cases, from Martin.

3) Add a new BPF helper bpf_skb_ancestor_cgroup_id() that returns the id
   of cgroup v2 that is the ancestor of the cgroup associated with the
   skb at the ancestor_level, from Andrey.

4) Implement BPF fs map pretty-print support based on BTF data for regular
   hash table and LRU map, from Yonghong.

5) Decouple the ability to attach BTF for a map from the key and value
   pretty-printer in BPF fs, and enable further support of BTF for maps for
   percpu and LPM trie, from Daniel.

6) Implement a better BPF sample of using XDP's CPU redirect feature for
   load balancing SKB processing to remote CPU. The sample implements the
   same XDP load balancing as Suricata does which is symmetric hash based
   on IP and L4 protocol, from Jesper.

7) Revert adding NULL pointer check with WARN_ON_ONCE() in __xdp_return()'s
   critical path as it is ensured that the allocator is present, from Björn.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

9 files changed, 482 insertions, 88 deletions

diff --git a/net/core/filter.c b/net/core/filter.c
index 587bbfbd7db3..15b9d2df92ca 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -1453,30 +1453,6 @@ static int __sk_attach_prog(struct bpf_prog *prog, struct sock *sk)
 	return 0;
 }
 
-static int __reuseport_attach_prog(struct bpf_prog *prog, struct sock *sk)
-{
-	struct bpf_prog *old_prog;
-	int err;
-
-	if (bpf_prog_size(prog->len) > sysctl_optmem_max)
-		return -ENOMEM;
-
-	if (sk_unhashed(sk) && sk->sk_reuseport) {
-		err = reuseport_alloc(sk);
-		if (err)
-			return err;
-	} else if (!rcu_access_pointer(sk->sk_reuseport_cb)) {
-		/* The socket wasn't bound with SO_REUSEPORT */
-		return -EINVAL;
-	}
-
-	old_prog = reuseport_attach_prog(sk, prog);
-	if (old_prog)
-		bpf_prog_destroy(old_prog);
-
-	return 0;
-}
-
 static
 struct bpf_prog *__get_filter(struct sock_fprog *fprog, struct sock *sk)
 {
@@ -1550,13 +1526,15 @@ int sk_reuseport_attach_filter(struct sock_fprog *fprog, struct sock *sk)
 	if (IS_ERR(prog))
 		return PTR_ERR(prog);
 
-	err = __reuseport_attach_prog(prog, sk);
-	if (err < 0) {
+	if (bpf_prog_size(prog->len) > sysctl_optmem_max)
+		err = -ENOMEM;
+	else
+		err = reuseport_attach_prog(sk, prog);
+
+	if (err)
 		__bpf_prog_release(prog);
-		return err;
-	}
 
-	return 0;
+	return err;
 }
 
 static struct bpf_prog *__get_bpf(u32 ufd, struct sock *sk)
@@ -1586,19 +1564,58 @@ int sk_attach_bpf(u32 ufd, struct sock *sk)
 
 int sk_reuseport_attach_bpf(u32 ufd, struct sock *sk)
 {
-	struct bpf_prog *prog = __get_bpf(ufd, sk);
+	struct bpf_prog *prog;
 	int err;
 
+	if (sock_flag(sk, SOCK_FILTER_LOCKED))
+		return -EPERM;
+
+	prog = bpf_prog_get_type(ufd, BPF_PROG_TYPE_SOCKET_FILTER);
+	if (IS_ERR(prog) && PTR_ERR(prog) == -EINVAL)
+		prog = bpf_prog_get_type(ufd, BPF_PROG_TYPE_SK_REUSEPORT);
 	if (IS_ERR(prog))
 		return PTR_ERR(prog);
 
-	err = __reuseport_attach_prog(prog, sk);
-	if (err < 0) {
-		bpf_prog_put(prog);
-		return err;
+	if (prog->type == BPF_PROG_TYPE_SK_REUSEPORT) {
+		/* Like other non BPF_PROG_TYPE_SOCKET_FILTER
+		 * bpf prog (e.g. sockmap).  It depends on the
+		 * limitation imposed by bpf_prog_load().
+		 * Hence, sysctl_optmem_max is not checked.
+		 */
+		if ((sk->sk_type != SOCK_STREAM &&
+		     sk->sk_type != SOCK_DGRAM) ||
+		    (sk->sk_protocol != IPPROTO_UDP &&
+		     sk->sk_protocol != IPPROTO_TCP) ||
+		    (sk->sk_family != AF_INET &&
+		     sk->sk_family != AF_INET6)) {
+			err = -ENOTSUPP;
+			goto err_prog_put;
+		}
+	} else {
+		/* BPF_PROG_TYPE_SOCKET_FILTER */
+		if (bpf_prog_size(prog->len) > sysctl_optmem_max) {
+			err = -ENOMEM;
+			goto err_prog_put;
+		}
 	}
 
-	return 0;
+	err = reuseport_attach_prog(sk, prog);
+err_prog_put:
+	if (err)
+		bpf_prog_put(prog);
+
+	return err;
+}
+
+void sk_reuseport_prog_free(struct bpf_prog *prog)
+{
+	if (!prog)
+		return;
+
+	if (prog->type == BPF_PROG_TYPE_SK_REUSEPORT)
+		bpf_prog_put(prog);
+	else
+		bpf_prog_destroy(prog);
 }
 
 struct bpf_scratchpad {
@@ -2082,19 +2099,12 @@ static const struct bpf_func_proto bpf_clone_redirect_proto = {
 	.arg3_type      = ARG_ANYTHING,
 };
 
-struct redirect_info {
-	u32 ifindex;
-	u32 flags;
-	struct bpf_map *map;
-	struct bpf_map *map_to_flush;
-	unsigned long   map_owner;
-};
-
-static DEFINE_PER_CPU(struct redirect_info, redirect_info);
+DEFINE_PER_CPU(struct bpf_redirect_info, bpf_redirect_info);
+EXPORT_PER_CPU_SYMBOL_GPL(bpf_redirect_info);
 
 BPF_CALL_2(bpf_redirect, u32, ifindex, u64, flags)
 {
-	struct redirect_info *ri = this_cpu_ptr(&redirect_info);
+	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
 
 	if (unlikely(flags & ~(BPF_F_INGRESS)))
 		return TC_ACT_SHOT;
@@ -2107,7 +2117,7 @@ BPF_CALL_2(bpf_redirect, u32, ifindex, u64, flags)
 
 int skb_do_redirect(struct sk_buff *skb)
 {
-	struct redirect_info *ri = this_cpu_ptr(&redirect_info);
+	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
 	struct net_device *dev;
 
 	dev = dev_get_by_index_rcu(dev_net(skb->dev), ri->ifindex);
@@ -3200,7 +3210,7 @@ static int __bpf_tx_xdp_map(struct net_device *dev_rx, void *fwd,
 
 void xdp_do_flush_map(void)
 {
-	struct redirect_info *ri = this_cpu_ptr(&redirect_info);
+	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
 	struct bpf_map *map = ri->map_to_flush;
 
 	ri->map_to_flush = NULL;
@@ -3245,7 +3255,7 @@ static inline bool xdp_map_invalid(const struct bpf_prog *xdp_prog,
 static int xdp_do_redirect_map(struct net_device *dev, struct xdp_buff *xdp,
 			       struct bpf_prog *xdp_prog)
 {
-	struct redirect_info *ri = this_cpu_ptr(&redirect_info);
+	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
 	unsigned long map_owner = ri->map_owner;
 	struct bpf_map *map = ri->map;
 	u32 index = ri->ifindex;
@@ -3285,7 +3295,7 @@ err:
 int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp,
 		    struct bpf_prog *xdp_prog)
 {
-	struct redirect_info *ri = this_cpu_ptr(&redirect_info);
+	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
 	struct net_device *fwd;
 	u32 index = ri->ifindex;
 	int err;
@@ -3317,7 +3327,7 @@ static int xdp_do_generic_redirect_map(struct net_device *dev,
 				       struct xdp_buff *xdp,
 				       struct bpf_prog *xdp_prog)
 {
-	struct redirect_info *ri = this_cpu_ptr(&redirect_info);
+	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
 	unsigned long map_owner = ri->map_owner;
 	struct bpf_map *map = ri->map;
 	u32 index = ri->ifindex;
@@ -3368,7 +3378,7 @@ err:
 int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb,
 			    struct xdp_buff *xdp, struct bpf_prog *xdp_prog)
 {
-	struct redirect_info *ri = this_cpu_ptr(&redirect_info);
+	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
 	u32 index = ri->ifindex;
 	struct net_device *fwd;
 	int err = 0;
@@ -3399,7 +3409,7 @@ EXPORT_SYMBOL_GPL(xdp_do_generic_redirect);
 
 BPF_CALL_2(bpf_xdp_redirect, u32, ifindex, u64, flags)
 {
-	struct redirect_info *ri = this_cpu_ptr(&redirect_info);
+	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
 
 	if (unlikely(flags))
 		return XDP_ABORTED;
@@ -3423,7 +3433,7 @@ static const struct bpf_func_proto bpf_xdp_redirect_proto = {
 BPF_CALL_4(bpf_xdp_redirect_map, struct bpf_map *, map, u32, ifindex, u64, flags,
 	   unsigned long, map_owner)
 {
-	struct redirect_info *ri = this_cpu_ptr(&redirect_info);
+	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
 
 	if (unlikely(flags))
 		return XDP_ABORTED;
@@ -3768,6 +3778,32 @@ static const struct bpf_func_proto bpf_skb_cgroup_id_proto = {
 	.ret_type       = RET_INTEGER,
 	.arg1_type      = ARG_PTR_TO_CTX,
 };
+
+BPF_CALL_2(bpf_skb_ancestor_cgroup_id, const struct sk_buff *, skb, int,
+	   ancestor_level)
+{
+	struct sock *sk = skb_to_full_sk(skb);
+	struct cgroup *ancestor;
+	struct cgroup *cgrp;
+
+	if (!sk || !sk_fullsock(sk))
+		return 0;
+
+	cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
+	ancestor = cgroup_ancestor(cgrp, ancestor_level);
+	if (!ancestor)
+		return 0;
+
+	return ancestor->kn->id.id;
+}
+
+static const struct bpf_func_proto bpf_skb_ancestor_cgroup_id_proto = {
+	.func           = bpf_skb_ancestor_cgroup_id,
+	.gpl_only       = false,
+	.ret_type       = RET_INTEGER,
+	.arg1_type      = ARG_PTR_TO_CTX,
+	.arg2_type      = ARG_ANYTHING,
+};
 #endif
 
 static unsigned long bpf_xdp_copy(void *dst_buff, const void *src_buff,
@@ -4956,6 +4992,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 #ifdef CONFIG_SOCK_CGROUP_DATA
 	case BPF_FUNC_skb_cgroup_id:
 		return &bpf_skb_cgroup_id_proto;
+	case BPF_FUNC_skb_ancestor_cgroup_id:
+		return &bpf_skb_ancestor_cgroup_id_proto;
 #endif
 	default:
 		return bpf_base_func_proto(func_id);
@@ -7020,3 +7058,270 @@ out:
 	release_sock(sk);
 	return ret;
 }
+
+#ifdef CONFIG_INET
+struct sk_reuseport_kern {
+	struct sk_buff *skb;
+	struct sock *sk;
+	struct sock *selected_sk;
+	void *data_end;
+	u32 hash;
+	u32 reuseport_id;
+	bool bind_inany;
+};
+
+static void bpf_init_reuseport_kern(struct sk_reuseport_kern *reuse_kern,
+				    struct sock_reuseport *reuse,
+				    struct sock *sk, struct sk_buff *skb,
+				    u32 hash)
+{
+	reuse_kern->skb = skb;
+	reuse_kern->sk = sk;
+	reuse_kern->selected_sk = NULL;
+	reuse_kern->data_end = skb->data + skb_headlen(skb);
+	reuse_kern->hash = hash;
+	reuse_kern->reuseport_id = reuse->reuseport_id;
+	reuse_kern->bind_inany = reuse->bind_inany;
+}
+
+struct sock *bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk,
+				  struct bpf_prog *prog, struct sk_buff *skb,
+				  u32 hash)
+{
+	struct sk_reuseport_kern reuse_kern;
+	enum sk_action action;
+
+	bpf_init_reuseport_kern(&reuse_kern, reuse, sk, skb, hash);
+	action = BPF_PROG_RUN(prog, &reuse_kern);
+
+	if (action == SK_PASS)
+		return reuse_kern.selected_sk;
+	else
+		return ERR_PTR(-ECONNREFUSED);
+}
+
+BPF_CALL_4(sk_select_reuseport, struct sk_reuseport_kern *, reuse_kern,
+	   struct bpf_map *, map, void *, key, u32, flags)
+{
+	struct sock_reuseport *reuse;
+	struct sock *selected_sk;
+
+	selected_sk = map->ops->map_lookup_elem(map, key);
+	if (!selected_sk)
+		return -ENOENT;
+
+	reuse = rcu_dereference(selected_sk->sk_reuseport_cb);
+	if (!reuse)
+		/* selected_sk is unhashed (e.g. by close()) after the
+		 * above map_lookup_elem().  Treat selected_sk has already
+		 * been removed from the map.
+		 */
+		return -ENOENT;
+
+	if (unlikely(reuse->reuseport_id != reuse_kern->reuseport_id)) {
+		struct sock *sk;
+
+		if (unlikely(!reuse_kern->reuseport_id))
+			/* There is a small race between adding the
+			 * sk to the map and setting the
+			 * reuse_kern->reuseport_id.
+			 * Treat it as the sk has not been added to
+			 * the bpf map yet.
+			 */
+			return -ENOENT;
+
+		sk = reuse_kern->sk;
+		if (sk->sk_protocol != selected_sk->sk_protocol)
+			return -EPROTOTYPE;
+		else if (sk->sk_family != selected_sk->sk_family)
+			return -EAFNOSUPPORT;
+
+		/* Catch all. Likely bound to a different sockaddr. */
+		return -EBADFD;
+	}
+
+	reuse_kern->selected_sk = selected_sk;
+
+	return 0;
+}
+
+static const struct bpf_func_proto sk_select_reuseport_proto = {
+	.func           = sk_select_reuseport,
+	.gpl_only       = false,
+	.ret_type       = RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type      = ARG_CONST_MAP_PTR,
+	.arg3_type      = ARG_PTR_TO_MAP_KEY,
+	.arg4_type	= ARG_ANYTHING,
+};
+
+BPF_CALL_4(sk_reuseport_load_bytes,
+	   const struct sk_reuseport_kern *, reuse_kern, u32, offset,
+	   void *, to, u32, len)
+{
+	return ____bpf_skb_load_bytes(reuse_kern->skb, offset, to, len);
+}
+
+static const struct bpf_func_proto sk_reuseport_load_bytes_proto = {
+	.func		= sk_reuseport_load_bytes,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_ANYTHING,
+	.arg3_type	= ARG_PTR_TO_UNINIT_MEM,
+	.arg4_type	= ARG_CONST_SIZE,
+};
+
+BPF_CALL_5(sk_reuseport_load_bytes_relative,
+	   const struct sk_reuseport_kern *, reuse_kern, u32, offset,
+	   void *, to, u32, len, u32, start_header)
+{
+	return ____bpf_skb_load_bytes_relative(reuse_kern->skb, offset, to,
+					       len, start_header);
+}
+
+static const struct bpf_func_proto sk_reuseport_load_bytes_relative_proto = {
+	.func		= sk_reuseport_load_bytes_relative,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_ANYTHING,
+	.arg3_type	= ARG_PTR_TO_UNINIT_MEM,
+	.arg4_type	= ARG_CONST_SIZE,
+	.arg5_type	= ARG_ANYTHING,
+};
+
+static const struct bpf_func_proto *
+sk_reuseport_func_proto(enum bpf_func_id func_id,
+			const struct bpf_prog *prog)
+{
+	switch (func_id) {
+	case BPF_FUNC_sk_select_reuseport:
+		return &sk_select_reuseport_proto;
+	case BPF_FUNC_skb_load_bytes:
+		return &sk_reuseport_load_bytes_proto;
+	case BPF_FUNC_skb_load_bytes_relative:
+		return &sk_reuseport_load_bytes_relative_proto;
+	default:
+		return bpf_base_func_proto(func_id);
+	}
+}
+
+static bool
+sk_reuseport_is_valid_access(int off, int size,
+			     enum bpf_access_type type,
+			     const struct bpf_prog *prog,
+			     struct bpf_insn_access_aux *info)
+{
+	const u32 size_default = sizeof(__u32);
+
+	if (off < 0 || off >= sizeof(struct sk_reuseport_md) ||
+	    off % size || type != BPF_READ)
+		return false;
+
+	switch (off) {
+	case offsetof(struct sk_reuseport_md, data):
+		info->reg_type = PTR_TO_PACKET;
+		return size == sizeof(__u64);
+
+	case offsetof(struct sk_reuseport_md, data_end):
+		info->reg_type = PTR_TO_PACKET_END;
+		return size == sizeof(__u64);
+
+	case offsetof(struct sk_reuseport_md, hash):
+		return size == size_default;
+
+	/* Fields that allow narrowing */
+	case offsetof(struct sk_reuseport_md, eth_protocol):
+		if (size < FIELD_SIZEOF(struct sk_buff, protocol))
+			return false;
+	case offsetof(struct sk_reuseport_md, ip_protocol):
+	case offsetof(struct sk_reuseport_md, bind_inany):
+	case offsetof(struct sk_reuseport_md, len):
+		bpf_ctx_record_field_size(info, size_default);
+		return bpf_ctx_narrow_access_ok(off, size, size_default);
+
+	default:
+		return false;
+	}
+}
+
+#define SK_REUSEPORT_LOAD_FIELD(F) ({					\
+	*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_reuseport_kern, F), \
+			      si->dst_reg, si->src_reg,			\
+			      bpf_target_off(struct sk_reuseport_kern, F, \
+					     FIELD_SIZEOF(struct sk_reuseport_kern, F), \
+					     target_size));		\
+	})
+
+#define SK_REUSEPORT_LOAD_SKB_FIELD(SKB_FIELD)				\
+	SOCK_ADDR_LOAD_NESTED_FIELD(struct sk_reuseport_kern,		\
+				    struct sk_buff,			\
+				    skb,				\
+				    SKB_FIELD)
+
+#define SK_REUSEPORT_LOAD_SK_FIELD_SIZE_OFF(SK_FIELD, BPF_SIZE, EXTRA_OFF) \
+	SOCK_ADDR_LOAD_NESTED_FIELD_SIZE_OFF(struct sk_reuseport_kern,	\
+					     struct sock,		\
+					     sk,			\
+					     SK_FIELD, BPF_SIZE, EXTRA_OFF)
+
+static u32 sk_reuseport_convert_ctx_access(enum bpf_access_type type,
+					   const struct bpf_insn *si,
+					   struct bpf_insn *insn_buf,
+					   struct bpf_prog *prog,
+					   u32 *target_size)
+{
+	struct bpf_insn *insn = insn_buf;
+
+	switch (si->off) {
+	case offsetof(struct sk_reuseport_md, data):
+		SK_REUSEPORT_LOAD_SKB_FIELD(data);
+		break;
+
+	case offsetof(struct sk_reuseport_md, len):
+		SK_REUSEPORT_LOAD_SKB_FIELD(len);
+		break;
+
+	case offsetof(struct sk_reuseport_md, eth_protocol):
+		SK_REUSEPORT_LOAD_SKB_FIELD(protocol);
+		break;
+
+	case offsetof(struct sk_reuseport_md, ip_protocol):
+		BUILD_BUG_ON(hweight_long(SK_FL_PROTO_MASK) != BITS_PER_BYTE);
+		SK_REUSEPORT_LOAD_SK_FIELD_SIZE_OFF(__sk_flags_offset,
+						    BPF_W, 0);
+		*insn++ = BPF_ALU32_IMM(BPF_AND, si->dst_reg, SK_FL_PROTO_MASK);
+		*insn++ = BPF_ALU32_IMM(BPF_RSH, si->dst_reg,
+					SK_FL_PROTO_SHIFT);
+		/* SK_FL_PROTO_MASK and SK_FL_PROTO_SHIFT are endian
+		 * aware.  No further narrowing or masking is needed.
+		 */
+		*target_size = 1;
+		break;
+
+	case offsetof(struct sk_reuseport_md, data_end):
+		SK_REUSEPORT_LOAD_FIELD(data_end);
+		break;
+
+	case offsetof(struct sk_reuseport_md, hash):
+		SK_REUSEPORT_LOAD_FIELD(hash);
+		break;
+
+	case offsetof(struct sk_reuseport_md, bind_inany):
+		SK_REUSEPORT_LOAD_FIELD(bind_inany);
+		break;
+	}
+
+	return insn - insn_buf;
+}
+
+const struct bpf_verifier_ops sk_reuseport_verifier_ops = {
+	.get_func_proto		= sk_reuseport_func_proto,
+	.is_valid_access	= sk_reuseport_is_valid_access,
+	.convert_ctx_access	= sk_reuseport_convert_ctx_access,
+};
+
+const struct bpf_prog_ops sk_reuseport_prog_ops = {
+};
+#endif /* CONFIG_INET */
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 8d574a88125d..c996c09d095f 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -1291,7 +1291,7 @@ struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask)
 }
 EXPORT_SYMBOL(skb_clone);
 
-static void skb_headers_offset_update(struct sk_buff *skb, int off)
+void skb_headers_offset_update(struct sk_buff *skb, int off)
 {
 	/* Only adjust this if it actually is csum_start rather than csum */
 	if (skb->ip_summed == CHECKSUM_PARTIAL)
@@ -1305,6 +1305,7 @@ static void skb_headers_offset_update(struct sk_buff *skb, int off)
 	skb->inner_network_header += off;
 	skb->inner_mac_header += off;
 }
+EXPORT_SYMBOL(skb_headers_offset_update);
 
 void skb_copy_header(struct sk_buff *new, const struct sk_buff *old)
 {
diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c
index 064acb04be0f..ba5cba56f574 100644
--- a/net/core/sock_reuseport.c
+++ b/net/core/sock_reuseport.c
@@ -8,11 +8,34 @@
 
 #include <net/sock_reuseport.h>
 #include <linux/bpf.h>
+#include <linux/idr.h>
+#include <linux/filter.h>
 #include <linux/rcupdate.h>
 
 #define INIT_SOCKS 128
 
-static DEFINE_SPINLOCK(reuseport_lock);
+DEFINE_SPINLOCK(reuseport_lock);
+
+#define REUSEPORT_MIN_ID 1
+static DEFINE_IDA(reuseport_ida);
+
+int reuseport_get_id(struct sock_reuseport *reuse)
+{
+	int id;
+
+	if (reuse->reuseport_id)
+		return reuse->reuseport_id;
+
+	id = ida_simple_get(&reuseport_ida, REUSEPORT_MIN_ID, 0,
+			    /* Called under reuseport_lock */
+			    GFP_ATOMIC);
+	if (id < 0)
+		return id;
+
+	reuse->reuseport_id = id;
+
+	return reuse->reuseport_id;
+}
 
 static struct sock_reuseport *__reuseport_alloc(unsigned int max_socks)
 {
@@ -29,7 +52,7 @@ static struct sock_reuseport *__reuseport_alloc(unsigned int max_socks)
 	return reuse;
 }
 
-int reuseport_alloc(struct sock *sk)
+int reuseport_alloc(struct sock *sk, bool bind_inany)
 {
 	struct sock_reuseport *reuse;
 
@@ -41,9 +64,17 @@ int reuseport_alloc(struct sock *sk)
 	/* Allocation attempts can occur concurrently via the setsockopt path
 	 * and the bind/hash path.  Nothing to do when we lose the race.
 	 */
-	if (rcu_dereference_protected(sk->sk_reuseport_cb,
-				      lockdep_is_held(&reuseport_lock)))
+	reuse = rcu_dereference_protected(sk->sk_reuseport_cb,
+					  lockdep_is_held(&reuseport_lock));
+	if (reuse) {
+		/* Only set reuse->bind_inany if the bind_inany is true.
+		 * Otherwise, it will overwrite the reuse->bind_inany
+		 * which was set by the bind/hash path.
+		 */
+		if (bind_inany)
+			reuse->bind_inany = bind_inany;
 		goto out;
+	}
 
 	reuse = __reuseport_alloc(INIT_SOCKS);
 	if (!reuse) {
@@ -53,6 +84,7 @@ int reuseport_alloc(struct sock *sk)
 
 	reuse->socks[0] = sk;
 	reuse->num_socks = 1;
+	reuse->bind_inany = bind_inany;
 	rcu_assign_pointer(sk->sk_reuseport_cb, reuse);
 
 out:
@@ -78,9 +110,12 @@ static struct sock_reuseport *reuseport_grow(struct sock_reuseport *reuse)
 	more_reuse->max_socks = more_socks_size;
 	more_reuse->num_socks = reuse->num_socks;
 	more_reuse->prog = reuse->prog;
+	more_reuse->reuseport_id = reuse->reuseport_id;
+	more_reuse->bind_inany = reuse->bind_inany;
 
 	memcpy(more_reuse->socks, reuse->socks,
 	       reuse->num_socks * sizeof(struct sock *));
+	more_reuse->synq_overflow_ts = READ_ONCE(reuse->synq_overflow_ts);
 
 	for (i = 0; i < reuse->num_socks; ++i)
 		rcu_assign_pointer(reuse->socks[i]->sk_reuseport_cb,
@@ -99,8 +134,9 @@ static void reuseport_free_rcu(struct rcu_head *head)
 	struct sock_reuseport *reuse;
 
 	reuse = container_of(head, struct sock_reuseport, rcu);
-	if (reuse->prog)
-		bpf_prog_destroy(reuse->prog);
+	sk_reuseport_prog_free(rcu_dereference_protected(reuse->prog, 1));
+	if (reuse->reuseport_id)
+		ida_simple_remove(&reuseport_ida, reuse->reuseport_id);
 	kfree(reuse);
 }
 
@@ -110,12 +146,12 @@ static void reuseport_free_rcu(struct rcu_head *head)
  *  @sk2: Socket belonging to the existing reuseport group.
  *  May return ENOMEM and not add socket to group under memory pressure.
  */
-int reuseport_add_sock(struct sock *sk, struct sock *sk2)
+int reuseport_add_sock(struct sock *sk, struct sock *sk2, bool bind_inany)
 {
 	struct sock_reuseport *old_reuse, *reuse;
 
 	if (!rcu_access_pointer(sk2->sk_reuseport_cb)) {
-		int err = reuseport_alloc(sk2);
+		int err = reuseport_alloc(sk2, bind_inany);
 
 		if (err)
 			return err;
@@ -160,6 +196,14 @@ void reuseport_detach_sock(struct sock *sk)
 	spin_lock_bh(&reuseport_lock);
 	reuse = rcu_dereference_protected(sk->sk_reuseport_cb,
 					  lockdep_is_held(&reuseport_lock));
+
+	/* At least one of the sk in this reuseport group is added to
+	 * a bpf map.  Notify the bpf side.  The bpf map logic will
+	 * remove the sk if it is indeed added to a bpf map.
+	 */
+	if (reuse->reuseport_id)
+		bpf_sk_reuseport_detach(sk);
+
 	rcu_assign_pointer(sk->sk_reuseport_cb, NULL);
 
 	for (i = 0; i < reuse->num_socks; i++) {
@@ -175,9 +219,9 @@ void reuseport_detach_sock(struct sock *sk)
 }
 EXPORT_SYMBOL(reuseport_detach_sock);
 
-static struct sock *run_bpf(struct sock_reuseport *reuse, u16 socks,
-			    struct bpf_prog *prog, struct sk_buff *skb,
-			    int hdr_len)
+static struct sock *run_bpf_filter(struct sock_reuseport *reuse, u16 socks,
+				   struct bpf_prog *prog, struct sk_buff *skb,
+				   int hdr_len)
 {
 	struct sk_buff *nskb = NULL;
 	u32 index;
@@ -238,9 +282,15 @@ struct sock *reuseport_select_sock(struct sock *sk,
 		/* paired with smp_wmb() in reuseport_add_sock() */
 		smp_rmb();
 
-		if (prog && skb)
-			sk2 = run_bpf(reuse, socks, prog, skb, hdr_len);
+		if (!prog || !skb)
+			goto select_by_hash;
+
+		if (prog->type == BPF_PROG_TYPE_SK_REUSEPORT)
+			sk2 = bpf_run_sk_reuseport(reuse, sk, prog, skb, hash);
+		else
+			sk2 = run_bpf_filter(reuse, socks, prog, skb, hdr_len);
 
+select_by_hash:
 		/* no bpf or invalid bpf result: fall back to hash usage */
 		if (!sk2)
 			sk2 = reuse->socks[reciprocal_scale(hash, socks)];
@@ -252,12 +302,21 @@ out:
 }
 EXPORT_SYMBOL(reuseport_select_sock);
 
-struct bpf_prog *
-reuseport_attach_prog(struct sock *sk, struct bpf_prog *prog)
+int reuseport_attach_prog(struct sock *sk, struct bpf_prog *prog)
 {
 	struct sock_reuseport *reuse;
 	struct bpf_prog *old_prog;
 
+	if (sk_unhashed(sk) && sk->sk_reuseport) {
+		int err = reuseport_alloc(sk, false);
+
+		if (err)
+			return err;
+	} else if (!rcu_access_pointer(sk->sk_reuseport_cb)) {
+		/* The socket wasn't bound with SO_REUSEPORT */
+		return -EINVAL;
+	}
+
 	spin_lock_bh(&reuseport_lock);
 	reuse = rcu_dereference_protected(sk->sk_reuseport_cb,
 					  lockdep_is_held(&reuseport_lock));
@@ -266,6 +325,7 @@ reuseport_attach_prog(struct sock *sk, struct bpf_prog *prog)
 	rcu_assign_pointer(reuse->prog, prog);
 	spin_unlock_bh(&reuseport_lock);
 
-	return old_prog;
+	sk_reuseport_prog_free(old_prog);
+	return 0;
 }
 EXPORT_SYMBOL(reuseport_attach_prog);
diff --git a/net/core/xdp.c b/net/core/xdp.c
index c013b836006b..3dd99e1c04f5 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -330,10 +330,12 @@ static void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct,
 		/* mem->id is valid, checked in xdp_rxq_info_reg_mem_model() */
 		xa = rhashtable_lookup(mem_id_ht, &mem->id, mem_id_rht_params);
 		page = virt_to_head_page(data);
-		if (xa)
+		if (xa) {
+			napi_direct &= !xdp_return_frame_no_direct();
 			page_pool_put_page(xa->page_pool, page, napi_direct);
-		else
+		} else {
 			put_page(page);
+		}
 		rcu_read_unlock();
 		break;
 	case MEM_TYPE_PAGE_SHARED:
@@ -348,8 +350,7 @@ static void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct,
 		rcu_read_lock();
 		/* mem->id is valid, checked in xdp_rxq_info_reg_mem_model() */
 		xa = rhashtable_lookup(mem_id_ht, &mem->id, mem_id_rht_params);
-		if (!WARN_ON_ONCE(!xa))
-			xa->zc_alloc->free(xa->zc_alloc, handle);
+		xa->zc_alloc->free(xa->zc_alloc, handle);
 		rcu_read_unlock();
 	default:
 		/* Not possible, checked in xdp_rxq_info_reg_mem_model() */
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 33a88e045efd..dfd5009f96ef 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -107,6 +107,15 @@ bool inet_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2,
 }
 EXPORT_SYMBOL(inet_rcv_saddr_equal);
 
+bool inet_rcv_saddr_any(const struct sock *sk)
+{
+#if IS_ENABLED(CONFIG_IPV6)
+	if (sk->sk_family == AF_INET6)
+		return ipv6_addr_any(&sk->sk_v6_rcv_saddr);
+#endif
+	return !sk->sk_rcv_saddr;
+}
+
 void inet_get_local_port_range(struct net *net, int *low, int *high)
 {
 	unsigned int seq;
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 3647167c8fa3..f5c9ef2586de 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -328,7 +328,7 @@ struct sock *__inet_lookup_listener(struct net *net,
 				    saddr, sport, daddr, hnum,
 				    dif, sdif);
 	if (result)
-		return result;
+		goto done;
 
 	/* Lookup lhash2 with INADDR_ANY */
 
@@ -337,9 +337,10 @@ struct sock *__inet_lookup_listener(struct net *net,
 	if (ilb2->count > ilb->count)
 		goto port_lookup;
 
-	return inet_lhash2_lookup(net, ilb2, skb, doff,
-				  saddr, sport, daddr, hnum,
-				  dif, sdif);
+	result = inet_lhash2_lookup(net, ilb2, skb, doff,
+				    saddr, sport, daddr, hnum,
+				    dif, sdif);
+	goto done;
 
 port_lookup:
 	sk_for_each_rcu(sk, &ilb->head) {
@@ -352,12 +353,15 @@ port_lookup:
 				result = reuseport_select_sock(sk, phash,
 							       skb, doff);
 				if (result)
-					return result;
+					goto done;
 			}
 			result = sk;
 			hiscore = score;
 		}
 	}
+done:
+	if (unlikely(IS_ERR(result)))
+		return NULL;
 	return result;
 }
 EXPORT_SYMBOL_GPL(__inet_lookup_listener);
@@ -567,10 +571,11 @@ static int inet_reuseport_add_sock(struct sock *sk,
 		    inet_csk(sk2)->icsk_bind_hash == tb &&
 		    sk2->sk_reuseport && uid_eq(uid, sock_i_uid(sk2)) &&
 		    inet_rcv_saddr_equal(sk, sk2, false))
-			return reuseport_add_sock(sk, sk2);
+			return reuseport_add_sock(sk, sk2,
+						  inet_rcv_saddr_any(sk));
 	}
 
-	return reuseport_alloc(sk);
+	return reuseport_alloc(sk, inet_rcv_saddr_any(sk));
 }
 
 int __inet_hash(struct sock *sk, struct sock *osk)
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 060e841dde40..f4e35b2ff8b8 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -221,11 +221,12 @@ static int udp_reuseport_add_sock(struct sock *sk, struct udp_hslot *hslot)
 		    (sk2->sk_bound_dev_if == sk->sk_bound_dev_if) &&
 		    sk2->sk_reuseport && uid_eq(uid, sock_i_uid(sk2)) &&
 		    inet_rcv_saddr_equal(sk, sk2, false)) {
-			return reuseport_add_sock(sk, sk2);
+			return reuseport_add_sock(sk, sk2,
+						  inet_rcv_saddr_any(sk));
 		}
 	}
 
-	return reuseport_alloc(sk);
+	return reuseport_alloc(sk, inet_rcv_saddr_any(sk));
 }
 
 /**
@@ -498,6 +499,8 @@ struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr,
 						  daddr, hnum, dif, sdif,
 						  exact_dif, hslot2, skb);
 		}
+		if (unlikely(IS_ERR(result)))
+			return NULL;
 		return result;
 	}
 begin:
@@ -512,6 +515,8 @@ begin:
 						   saddr, sport);
 				result = reuseport_select_sock(sk, hash, skb,
 							sizeof(struct udphdr));
+				if (unlikely(IS_ERR(result)))
+					return NULL;
 				if (result)
 					return result;
 			}
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index 595ad408dba0..3d7c7460a0c5 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -191,7 +191,7 @@ struct sock *inet6_lookup_listener(struct net *net,
 				     saddr, sport, daddr, hnum,
 				     dif, sdif);
 	if (result)
-		return result;
+		goto done;
 
 	/* Lookup lhash2 with in6addr_any */
 
@@ -200,9 +200,10 @@ struct sock *inet6_lookup_listener(struct net *net,
 	if (ilb2->count > ilb->count)
 		goto port_lookup;
 
-	return inet6_lhash2_lookup(net, ilb2, skb, doff,
-				   saddr, sport, daddr, hnum,
-				   dif, sdif);
+	result = inet6_lhash2_lookup(net, ilb2, skb, doff,
+				     saddr, sport, daddr, hnum,
+				     dif, sdif);
+	goto done;
 
 port_lookup:
 	sk_for_each(sk, &ilb->head) {
@@ -214,12 +215,15 @@ port_lookup:
 				result = reuseport_select_sock(sk, phash,
 							       skb, doff);
 				if (result)
-					return result;
+					goto done;
 			}
 			result = sk;
 			hiscore = score;
 		}
 	}
+done:
+	if (unlikely(IS_ERR(result)))
+		return NULL;
 	return result;
 }
 EXPORT_SYMBOL_GPL(inet6_lookup_listener);
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index f6b96956a8ed..83f4c77c79d8 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -235,6 +235,8 @@ struct sock *__udp6_lib_lookup(struct net *net,
 						  exact_dif, hslot2,
 						  skb);
 		}
+		if (unlikely(IS_ERR(result)))
+			return NULL;
 		return result;
 	}
 begin:
@@ -249,6 +251,8 @@ begin:
 						    saddr, sport);
 				result = reuseport_select_sock(sk, hash, skb,
 							sizeof(struct udphdr));
+				if (unlikely(IS_ERR(result)))
+					return NULL;
 				if (result)
 					return result;
 			}