Merge tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Daniel Borkmann says:

====================
pull-request: bpf-next 2023-06-23

We've added 49 non-merge commits during the last 24 day(s) which contain
a total of 70 files changed, 1935 insertions(+), 442 deletions(-).

The main changes are:

1) Extend bpf_fib_lookup helper to allow passing the route table ID,
   from Louis DeLosSantos.

2) Fix regsafe() in verifier to call check_ids() for scalar registers,
   from Eduard Zingerman.

3) Extend the set of cpumask kfuncs with bpf_cpumask_first_and()
   and a rework of bpf_cpumask_any*() kfuncs. Additionally,
   add selftests, from David Vernet.

4) Fix socket lookup BPF helpers for tc/XDP to respect VRF bindings,
   from Gilad Sever.

5) Change bpf_link_put() to use workqueue unconditionally to fix it
   under PREEMPT_RT, from Sebastian Andrzej Siewior.

6) Follow-ups to address issues in the bpf_refcount shared ownership
   implementation, from Dave Marchevsky.

7) A few general refactorings to BPF map and program creation permissions
   checks which were part of the BPF token series, from Andrii Nakryiko.

8) Various fixes for benchmark framework and add a new benchmark
   for BPF memory allocator to BPF selftests, from Hou Tao.

9) Documentation improvements around iterators and trusted pointers,
   from Anton Protopopov.

10) Small cleanup in verifier to improve allocated object check,
    from Daniel T. Lee.

11) Improve performance of bpf_xdp_pointer() by avoiding access
    to shared_info when XDP packet does not have frags,
    from Jesper Dangaard Brouer.

12) Silence a harmless syzbot-reported warning in btf_type_id_size(),
    from Yonghong Song.

13) Remove duplicate bpfilter_umh_cleanup in favor of umd_cleanup_helper,
    from Jarkko Sakkinen.

14) Fix BPF selftests build for resolve_btfids under custom HOSTCFLAGS,
    from Viktor Malik.

* tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (49 commits)
  bpf, docs: Document existing macros instead of deprecated
  bpf, docs: BPF Iterator Document
  selftests/bpf: Fix compilation failure for prog vrf_socket_lookup
  selftests/bpf: Add vrf_socket_lookup tests
  bpf: Fix bpf socket lookup from tc/xdp to respect socket VRF bindings
  bpf: Call __bpf_sk_lookup()/__bpf_skc_lookup() directly via TC hookpoint
  bpf: Factor out socket lookup functions for the TC hookpoint.
  selftests/bpf: Set the default value of consumer_cnt as 0
  selftests/bpf: Ensure that next_cpu() returns a valid CPU number
  selftests/bpf: Output the correct error code for pthread APIs
  selftests/bpf: Use producer_cnt to allocate local counter array
  xsk: Remove unused inline function xsk_buff_discard()
  bpf: Keep BPF_PROG_LOAD permission checks clear of validations
  bpf: Centralize permissions checks for all BPF map types
  bpf: Inline map creation logic in map_create() function
  bpf: Move unprivileged checks into map_create() and bpf_prog_load()
  bpf: Remove in_atomic() from bpf_link_put().
  selftests/bpf: Verify that check_ids() is used for scalars in regsafe()
  bpf: Verify scalar ids mapping in regsafe() using check_ids()
  selftests/bpf: Check if mark_chain_precision() follows scalar ids
  ...
====================

Link: https://lore.kernel.org/r/20230623211256.8409-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

2 files changed, 119 insertions, 32 deletions

diff --git a/net/core/filter.c b/net/core/filter.c
index 968139f4a1ac..06ba0e56e369 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3948,20 +3948,21 @@ void bpf_xdp_copy_buf(struct xdp_buff *xdp, unsigned long off,
 
 void *bpf_xdp_pointer(struct xdp_buff *xdp, u32 offset, u32 len)
 {
-	struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp);
 	u32 size = xdp->data_end - xdp->data;
+	struct skb_shared_info *sinfo;
 	void *addr = xdp->data;
 	int i;
 
 	if (unlikely(offset > 0xffff || len > 0xffff))
 		return ERR_PTR(-EFAULT);
 
-	if (offset + len > xdp_get_buff_len(xdp))
+	if (unlikely(offset + len > xdp_get_buff_len(xdp)))
 		return ERR_PTR(-EINVAL);
 
-	if (offset < size) /* linear area */
+	if (likely(offset < size)) /* linear area */
 		goto out;
 
+	sinfo = xdp_get_shared_info_from_buff(xdp);
 	offset -= size;
 	for (i = 0; i < sinfo->nr_frags; i++) { /* paged area */
 		u32 frag_size = skb_frag_size(&sinfo->frags[i]);
@@ -5803,6 +5804,12 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 		u32 tbid = l3mdev_fib_table_rcu(dev) ? : RT_TABLE_MAIN;
 		struct fib_table *tb;
 
+		if (flags & BPF_FIB_LOOKUP_TBID) {
+			tbid = params->tbid;
+			/* zero out for vlan output */
+			params->tbid = 0;
+		}
+
 		tb = fib_get_table(net, tbid);
 		if (unlikely(!tb))
 			return BPF_FIB_LKUP_RET_NOT_FWDED;
@@ -5936,6 +5943,12 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 		u32 tbid = l3mdev_fib_table_rcu(dev) ? : RT_TABLE_MAIN;
 		struct fib6_table *tb;
 
+		if (flags & BPF_FIB_LOOKUP_TBID) {
+			tbid = params->tbid;
+			/* zero out for vlan output */
+			params->tbid = 0;
+		}
+
 		tb = ipv6_stub->fib6_get_table(net, tbid);
 		if (unlikely(!tb))
 			return BPF_FIB_LKUP_RET_NOT_FWDED;
@@ -6008,7 +6021,7 @@ set_fwd_params:
 #endif
 
 #define BPF_FIB_LOOKUP_MASK (BPF_FIB_LOOKUP_DIRECT | BPF_FIB_LOOKUP_OUTPUT | \
-			     BPF_FIB_LOOKUP_SKIP_NEIGH)
+			     BPF_FIB_LOOKUP_SKIP_NEIGH | BPF_FIB_LOOKUP_TBID)
 
 BPF_CALL_4(bpf_xdp_fib_lookup, struct xdp_buff *, ctx,
 	   struct bpf_fib_lookup *, params, int, plen, u32, flags)
@@ -6555,12 +6568,11 @@ static struct sock *sk_lookup(struct net *net, struct bpf_sock_tuple *tuple,
 static struct sock *
 __bpf_skc_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
 		 struct net *caller_net, u32 ifindex, u8 proto, u64 netns_id,
-		 u64 flags)
+		 u64 flags, int sdif)
 {
 	struct sock *sk = NULL;
 	struct net *net;
 	u8 family;
-	int sdif;
 
 	if (len == sizeof(tuple->ipv4))
 		family = AF_INET;
@@ -6572,10 +6584,12 @@ __bpf_skc_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
 	if (unlikely(flags || !((s32)netns_id < 0 || netns_id <= S32_MAX)))
 		goto out;
 
-	if (family == AF_INET)
-		sdif = inet_sdif(skb);
-	else
-		sdif = inet6_sdif(skb);
+	if (sdif < 0) {
+		if (family == AF_INET)
+			sdif = inet_sdif(skb);
+		else
+			sdif = inet6_sdif(skb);
+	}
 
 	if ((s32)netns_id < 0) {
 		net = caller_net;
@@ -6595,10 +6609,11 @@ out:
 static struct sock *
 __bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
 		struct net *caller_net, u32 ifindex, u8 proto, u64 netns_id,
-		u64 flags)
+		u64 flags, int sdif)
 {
 	struct sock *sk = __bpf_skc_lookup(skb, tuple, len, caller_net,
-					   ifindex, proto, netns_id, flags);
+					   ifindex, proto, netns_id, flags,
+					   sdif);
 
 	if (sk) {
 		struct sock *sk2 = sk_to_full_sk(sk);
@@ -6638,7 +6653,7 @@ bpf_skc_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
 	}
 
 	return __bpf_skc_lookup(skb, tuple, len, caller_net, ifindex, proto,
-				netns_id, flags);
+				netns_id, flags, -1);
 }
 
 static struct sock *
@@ -6727,6 +6742,78 @@ static const struct bpf_func_proto bpf_sk_lookup_udp_proto = {
 	.arg5_type	= ARG_ANYTHING,
 };
 
+BPF_CALL_5(bpf_tc_skc_lookup_tcp, struct sk_buff *, skb,
+	   struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags)
+{
+	struct net_device *dev = skb->dev;
+	int ifindex = dev->ifindex, sdif = dev_sdif(dev);
+	struct net *caller_net = dev_net(dev);
+
+	return (unsigned long)__bpf_skc_lookup(skb, tuple, len, caller_net,
+					       ifindex, IPPROTO_TCP, netns_id,
+					       flags, sdif);
+}
+
+static const struct bpf_func_proto bpf_tc_skc_lookup_tcp_proto = {
+	.func		= bpf_tc_skc_lookup_tcp,
+	.gpl_only	= false,
+	.pkt_access	= true,
+	.ret_type	= RET_PTR_TO_SOCK_COMMON_OR_NULL,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_PTR_TO_MEM | MEM_RDONLY,
+	.arg3_type	= ARG_CONST_SIZE,
+	.arg4_type	= ARG_ANYTHING,
+	.arg5_type	= ARG_ANYTHING,
+};
+
+BPF_CALL_5(bpf_tc_sk_lookup_tcp, struct sk_buff *, skb,
+	   struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags)
+{
+	struct net_device *dev = skb->dev;
+	int ifindex = dev->ifindex, sdif = dev_sdif(dev);
+	struct net *caller_net = dev_net(dev);
+
+	return (unsigned long)__bpf_sk_lookup(skb, tuple, len, caller_net,
+					      ifindex, IPPROTO_TCP, netns_id,
+					      flags, sdif);
+}
+
+static const struct bpf_func_proto bpf_tc_sk_lookup_tcp_proto = {
+	.func		= bpf_tc_sk_lookup_tcp,
+	.gpl_only	= false,
+	.pkt_access	= true,
+	.ret_type	= RET_PTR_TO_SOCKET_OR_NULL,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_PTR_TO_MEM | MEM_RDONLY,
+	.arg3_type	= ARG_CONST_SIZE,
+	.arg4_type	= ARG_ANYTHING,
+	.arg5_type	= ARG_ANYTHING,
+};
+
+BPF_CALL_5(bpf_tc_sk_lookup_udp, struct sk_buff *, skb,
+	   struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags)
+{
+	struct net_device *dev = skb->dev;
+	int ifindex = dev->ifindex, sdif = dev_sdif(dev);
+	struct net *caller_net = dev_net(dev);
+
+	return (unsigned long)__bpf_sk_lookup(skb, tuple, len, caller_net,
+					      ifindex, IPPROTO_UDP, netns_id,
+					      flags, sdif);
+}
+
+static const struct bpf_func_proto bpf_tc_sk_lookup_udp_proto = {
+	.func		= bpf_tc_sk_lookup_udp,
+	.gpl_only	= false,
+	.pkt_access	= true,
+	.ret_type	= RET_PTR_TO_SOCKET_OR_NULL,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_PTR_TO_MEM | MEM_RDONLY,
+	.arg3_type	= ARG_CONST_SIZE,
+	.arg4_type	= ARG_ANYTHING,
+	.arg5_type	= ARG_ANYTHING,
+};
+
 BPF_CALL_1(bpf_sk_release, struct sock *, sk)
 {
 	if (sk && sk_is_refcounted(sk))
@@ -6744,12 +6831,13 @@ static const struct bpf_func_proto bpf_sk_release_proto = {
 BPF_CALL_5(bpf_xdp_sk_lookup_udp, struct xdp_buff *, ctx,
 	   struct bpf_sock_tuple *, tuple, u32, len, u32, netns_id, u64, flags)
 {
-	struct net *caller_net = dev_net(ctx->rxq->dev);
-	int ifindex = ctx->rxq->dev->ifindex;
+	struct net_device *dev = ctx->rxq->dev;
+	int ifindex = dev->ifindex, sdif = dev_sdif(dev);
+	struct net *caller_net = dev_net(dev);
 
 	return (unsigned long)__bpf_sk_lookup(NULL, tuple, len, caller_net,
 					      ifindex, IPPROTO_UDP, netns_id,
-					      flags);
+					      flags, sdif);
 }
 
 static const struct bpf_func_proto bpf_xdp_sk_lookup_udp_proto = {
@@ -6767,12 +6855,13 @@ static const struct bpf_func_proto bpf_xdp_sk_lookup_udp_proto = {
 BPF_CALL_5(bpf_xdp_skc_lookup_tcp, struct xdp_buff *, ctx,
 	   struct bpf_sock_tuple *, tuple, u32, len, u32, netns_id, u64, flags)
 {
-	struct net *caller_net = dev_net(ctx->rxq->dev);
-	int ifindex = ctx->rxq->dev->ifindex;
+	struct net_device *dev = ctx->rxq->dev;
+	int ifindex = dev->ifindex, sdif = dev_sdif(dev);
+	struct net *caller_net = dev_net(dev);
 
 	return (unsigned long)__bpf_skc_lookup(NULL, tuple, len, caller_net,
 					       ifindex, IPPROTO_TCP, netns_id,
-					       flags);
+					       flags, sdif);
 }
 
 static const struct bpf_func_proto bpf_xdp_skc_lookup_tcp_proto = {
@@ -6790,12 +6879,13 @@ static const struct bpf_func_proto bpf_xdp_skc_lookup_tcp_proto = {
 BPF_CALL_5(bpf_xdp_sk_lookup_tcp, struct xdp_buff *, ctx,
 	   struct bpf_sock_tuple *, tuple, u32, len, u32, netns_id, u64, flags)
 {
-	struct net *caller_net = dev_net(ctx->rxq->dev);
-	int ifindex = ctx->rxq->dev->ifindex;
+	struct net_device *dev = ctx->rxq->dev;
+	int ifindex = dev->ifindex, sdif = dev_sdif(dev);
+	struct net *caller_net = dev_net(dev);
 
 	return (unsigned long)__bpf_sk_lookup(NULL, tuple, len, caller_net,
 					      ifindex, IPPROTO_TCP, netns_id,
-					      flags);
+					      flags, sdif);
 }
 
 static const struct bpf_func_proto bpf_xdp_sk_lookup_tcp_proto = {
@@ -6815,7 +6905,8 @@ BPF_CALL_5(bpf_sock_addr_skc_lookup_tcp, struct bpf_sock_addr_kern *, ctx,
 {
 	return (unsigned long)__bpf_skc_lookup(NULL, tuple, len,
 					       sock_net(ctx->sk), 0,
-					       IPPROTO_TCP, netns_id, flags);
+					       IPPROTO_TCP, netns_id, flags,
+					       -1);
 }
 
 static const struct bpf_func_proto bpf_sock_addr_skc_lookup_tcp_proto = {
@@ -6834,7 +6925,7 @@ BPF_CALL_5(bpf_sock_addr_sk_lookup_tcp, struct bpf_sock_addr_kern *, ctx,
 {
 	return (unsigned long)__bpf_sk_lookup(NULL, tuple, len,
 					      sock_net(ctx->sk), 0, IPPROTO_TCP,
-					      netns_id, flags);
+					      netns_id, flags, -1);
 }
 
 static const struct bpf_func_proto bpf_sock_addr_sk_lookup_tcp_proto = {
@@ -6853,7 +6944,7 @@ BPF_CALL_5(bpf_sock_addr_sk_lookup_udp, struct bpf_sock_addr_kern *, ctx,
 {
 	return (unsigned long)__bpf_sk_lookup(NULL, tuple, len,
 					      sock_net(ctx->sk), 0, IPPROTO_UDP,
-					      netns_id, flags);
+					      netns_id, flags, -1);
 }
 
 static const struct bpf_func_proto bpf_sock_addr_sk_lookup_udp_proto = {
@@ -7982,9 +8073,9 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 #endif
 #ifdef CONFIG_INET
 	case BPF_FUNC_sk_lookup_tcp:
-		return &bpf_sk_lookup_tcp_proto;
+		return &bpf_tc_sk_lookup_tcp_proto;
 	case BPF_FUNC_sk_lookup_udp:
-		return &bpf_sk_lookup_udp_proto;
+		return &bpf_tc_sk_lookup_udp_proto;
 	case BPF_FUNC_sk_release:
 		return &bpf_sk_release_proto;
 	case BPF_FUNC_tcp_sock:
@@ -7992,7 +8083,7 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_get_listener_sock:
 		return &bpf_get_listener_sock_proto;
 	case BPF_FUNC_skc_lookup_tcp:
-		return &bpf_skc_lookup_tcp_proto;
+		return &bpf_tc_skc_lookup_tcp_proto;
 	case BPF_FUNC_tcp_check_syncookie:
 		return &bpf_tcp_check_syncookie_proto;
 	case BPF_FUNC_skb_ecn_set_ce:
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index 00afb66cd095..19538d628714 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -32,8 +32,6 @@ static struct bpf_map *sock_map_alloc(union bpf_attr *attr)
 {
 	struct bpf_stab *stab;
 
-	if (!capable(CAP_NET_ADMIN))
-		return ERR_PTR(-EPERM);
 	if (attr->max_entries == 0 ||
 	    attr->key_size    != 4 ||
 	    (attr->value_size != sizeof(u32) &&
@@ -1085,8 +1083,6 @@ static struct bpf_map *sock_hash_alloc(union bpf_attr *attr)
 	struct bpf_shtab *htab;
 	int i, err;
 
-	if (!capable(CAP_NET_ADMIN))
-		return ERR_PTR(-EPERM);
 	if (attr->max_entries == 0 ||
 	    attr->key_size    == 0 ||
 	    (attr->value_size != sizeof(u32) &&