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

Daniel Borkmann says:

====================
pull-request: bpf-next 2022-09-05

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

We've added 106 non-merge commits during the last 18 day(s) which contain
a total of 159 files changed, 5225 insertions(+), 1358 deletions(-).

There are two small merge conflicts, resolve them as follows:

1) tools/testing/selftests/bpf/DENYLIST.s390x

  Commit 27e23836ce22 ("selftests/bpf: Add lru_bug to s390x deny list") in
  bpf tree was needed to get BPF CI green on s390x, but it conflicted with
  newly added tests on bpf-next. Resolve by adding both hunks, result:

  [...]
  lru_bug                                  # prog 'printk': failed to auto-attach: -524
  setget_sockopt                           # attach unexpected error: -524                                               (trampoline)
  cb_refs                                  # expected error message unexpected error: -524                               (trampoline)
  cgroup_hierarchical_stats                # JIT does not support calling kernel function                                (kfunc)
  htab_update                              # failed to attach: ERROR: strerror_r(-524)=22                                (trampoline)
  [...]

2) net/core/filter.c

  Commit 1227c1771dd2 ("net: Fix data-races around sysctl_[rw]mem_(max|default).")
  from net tree conflicts with commit 29003875bd5b ("bpf: Change bpf_setsockopt(SOL_SOCKET)
  to reuse sk_setsockopt()") from bpf-next tree. Take the code as it is from
  bpf-next tree, result:

  [...]
	if (getopt) {
		if (optname == SO_BINDTODEVICE)
			return -EINVAL;
		return sk_getsockopt(sk, SOL_SOCKET, optname,
				     KERNEL_SOCKPTR(optval),
				     KERNEL_SOCKPTR(optlen));
	}

	return sk_setsockopt(sk, SOL_SOCKET, optname,
			     KERNEL_SOCKPTR(optval), *optlen);
  [...]

The main changes are:

1) Add any-context BPF specific memory allocator which is useful in particular for BPF
   tracing with bonus of performance equal to full prealloc, from Alexei Starovoitov.

2) Big batch to remove duplicated code from bpf_{get,set}sockopt() helpers as an effort
   to reuse the existing core socket code as much as possible, from Martin KaFai Lau.

3) Extend BPF flow dissector for BPF programs to just augment the in-kernel dissector
   with custom logic. In other words, allow for partial replacement, from Shmulik Ladkani.

4) Add a new cgroup iterator to BPF with different traversal options, from Hao Luo.

5) Support for BPF to collect hierarchical cgroup statistics efficiently through BPF
   integration with the rstat framework, from Yosry Ahmed.

6) Support bpf_{g,s}et_retval() under more BPF cgroup hooks, from Stanislav Fomichev.

7) BPF hash table and local storages fixes under fully preemptible kernel, from Hou Tao.

8) Add various improvements to BPF selftests and libbpf for compilation with gcc BPF
   backend, from James Hilliard.

9) Fix verifier helper permissions and reference state management for synchronous
   callbacks, from Kumar Kartikeya Dwivedi.

10) Add support for BPF selftest's xskxceiver to also be used against real devices that
    support MAC loopback, from Maciej Fijalkowski.

11) Various fixes to the bpf-helpers(7) man page generation script, from Quentin Monnet.

12) Document BPF verifier's tnum_in(tnum_range(), ...) gotchas, from Shung-Hsi Yu.

13) Various minor misc improvements all over the place.

* https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (106 commits)
  bpf: Optimize rcu_barrier usage between hash map and bpf_mem_alloc.
  bpf: Remove usage of kmem_cache from bpf_mem_cache.
  bpf: Remove prealloc-only restriction for sleepable bpf programs.
  bpf: Prepare bpf_mem_alloc to be used by sleepable bpf programs.
  bpf: Remove tracing program restriction on map types
  bpf: Convert percpu hash map to per-cpu bpf_mem_alloc.
  bpf: Add percpu allocation support to bpf_mem_alloc.
  bpf: Batch call_rcu callbacks instead of SLAB_TYPESAFE_BY_RCU.
  bpf: Adjust low/high watermarks in bpf_mem_cache
  bpf: Optimize call_rcu in non-preallocated hash map.
  bpf: Optimize element count in non-preallocated hash map.
  bpf: Relax the requirement to use preallocated hash maps in tracing progs.
  samples/bpf: Reduce syscall overhead in map_perf_test.
  selftests/bpf: Improve test coverage of test_maps
  bpf: Convert hash map to bpf_mem_alloc.
  bpf: Introduce any context BPF specific memory allocator.
  selftest/bpf: Add test for bpf_getsockopt()
  bpf: Change bpf_getsockopt(SOL_IPV6) to reuse do_ipv6_getsockopt()
  bpf: Change bpf_getsockopt(SOL_IP) to reuse do_ip_getsockopt()
  bpf: Change bpf_getsockopt(SOL_TCP) to reuse do_tcp_getsockopt()
  ...
====================

Link: https://lore.kernel.org/r/20220905161136.9150-1-daniel@iogearbox.net
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

4 files changed, 70 insertions, 63 deletions

diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 2ce0c44d0081..19732b5dce23 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -1057,6 +1057,8 @@ static const struct ipv6_stub ipv6_stub_impl = {
 static const struct ipv6_bpf_stub ipv6_bpf_stub_impl = {
 	.inet6_bind = __inet6_bind,
 	.udp6_lib_lookup = __udp6_lib_lookup,
+	.ipv6_setsockopt = do_ipv6_setsockopt,
+	.ipv6_getsockopt = do_ipv6_getsockopt,
 };
 
 static int __init inet6_init(void)
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index a9ba41648e36..516e83b52f26 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -1827,8 +1827,8 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, sockptr_t optval,
  *	Getsock opt support for the multicast routing system.
  */
 
-int ip6_mroute_getsockopt(struct sock *sk, int optname, char __user *optval,
-			  int __user *optlen)
+int ip6_mroute_getsockopt(struct sock *sk, int optname, sockptr_t optval,
+			  sockptr_t optlen)
 {
 	int olr;
 	int val;
@@ -1859,16 +1859,16 @@ int ip6_mroute_getsockopt(struct sock *sk, int optname, char __user *optval,
 		return -ENOPROTOOPT;
 	}
 
-	if (get_user(olr, optlen))
+	if (copy_from_sockptr(&olr, optlen, sizeof(int)))
 		return -EFAULT;
 
 	olr = min_t(int, olr, sizeof(int));
 	if (olr < 0)
 		return -EINVAL;
 
-	if (put_user(olr, optlen))
+	if (copy_to_sockptr(optlen, &olr, sizeof(int)))
 		return -EFAULT;
-	if (copy_to_user(optval, &val, olr))
+	if (copy_to_sockptr(optval, &val, olr))
 		return -EFAULT;
 	return 0;
 }
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index e0dcc7a193df..2d2f4dd9e5df 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -327,7 +327,7 @@ static int ipv6_set_opt_hdr(struct sock *sk, int optname, sockptr_t optval,
 	int err;
 
 	/* hop-by-hop / destination options are privileged option */
-	if (optname != IPV6_RTHDR && !ns_capable(net->user_ns, CAP_NET_RAW))
+	if (optname != IPV6_RTHDR && !sockopt_ns_capable(net->user_ns, CAP_NET_RAW))
 		return -EPERM;
 
 	/* remove any sticky options header with a zero option
@@ -391,8 +391,8 @@ sticky_done:
 	return err;
 }
 
-static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
-		   sockptr_t optval, unsigned int optlen)
+int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
+		       sockptr_t optval, unsigned int optlen)
 {
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct net *net = sock_net(sk);
@@ -417,7 +417,7 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 
 	if (needs_rtnl)
 		rtnl_lock();
-	lock_sock(sk);
+	sockopt_lock_sock(sk);
 
 	switch (optname) {
 
@@ -634,8 +634,8 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 		break;
 
 	case IPV6_TRANSPARENT:
-		if (valbool && !ns_capable(net->user_ns, CAP_NET_RAW) &&
-		    !ns_capable(net->user_ns, CAP_NET_ADMIN)) {
+		if (valbool && !sockopt_ns_capable(net->user_ns, CAP_NET_RAW) &&
+		    !sockopt_ns_capable(net->user_ns, CAP_NET_ADMIN)) {
 			retv = -EPERM;
 			break;
 		}
@@ -946,7 +946,7 @@ done:
 	case IPV6_IPSEC_POLICY:
 	case IPV6_XFRM_POLICY:
 		retv = -EPERM;
-		if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
+		if (!sockopt_ns_capable(net->user_ns, CAP_NET_ADMIN))
 			break;
 		retv = xfrm_user_policy(sk, optname, optval, optlen);
 		break;
@@ -994,14 +994,14 @@ done:
 		break;
 	}
 
-	release_sock(sk);
+	sockopt_release_sock(sk);
 	if (needs_rtnl)
 		rtnl_unlock();
 
 	return retv;
 
 e_inval:
-	release_sock(sk);
+	sockopt_release_sock(sk);
 	if (needs_rtnl)
 		rtnl_unlock();
 	return -EINVAL;
@@ -1030,7 +1030,7 @@ int ipv6_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval,
 EXPORT_SYMBOL(ipv6_setsockopt);
 
 static int ipv6_getsockopt_sticky(struct sock *sk, struct ipv6_txoptions *opt,
-				  int optname, char __user *optval, int len)
+				  int optname, sockptr_t optval, int len)
 {
 	struct ipv6_opt_hdr *hdr;
 
@@ -1058,56 +1058,53 @@ static int ipv6_getsockopt_sticky(struct sock *sk, struct ipv6_txoptions *opt,
 		return 0;
 
 	len = min_t(unsigned int, len, ipv6_optlen(hdr));
-	if (copy_to_user(optval, hdr, len))
+	if (copy_to_sockptr(optval, hdr, len))
 		return -EFAULT;
 	return len;
 }
 
-static int ipv6_get_msfilter(struct sock *sk, void __user *optval,
-		int __user *optlen, int len)
+static int ipv6_get_msfilter(struct sock *sk, sockptr_t optval,
+			     sockptr_t optlen, int len)
 {
 	const int size0 = offsetof(struct group_filter, gf_slist_flex);
-	struct group_filter __user *p = optval;
 	struct group_filter gsf;
 	int num;
 	int err;
 
 	if (len < size0)
 		return -EINVAL;
-	if (copy_from_user(&gsf, p, size0))
+	if (copy_from_sockptr(&gsf, optval, size0))
 		return -EFAULT;
 	if (gsf.gf_group.ss_family != AF_INET6)
 		return -EADDRNOTAVAIL;
 	num = gsf.gf_numsrc;
-	lock_sock(sk);
-	err = ip6_mc_msfget(sk, &gsf, p->gf_slist_flex);
+	sockopt_lock_sock(sk);
+	err = ip6_mc_msfget(sk, &gsf, optval, size0);
 	if (!err) {
 		if (num > gsf.gf_numsrc)
 			num = gsf.gf_numsrc;
-		if (put_user(GROUP_FILTER_SIZE(num), optlen) ||
-		    copy_to_user(p, &gsf, size0))
+		len = GROUP_FILTER_SIZE(num);
+		if (copy_to_sockptr(optlen, &len, sizeof(int)) ||
+		    copy_to_sockptr(optval, &gsf, size0))
 			err = -EFAULT;
 	}
-	release_sock(sk);
+	sockopt_release_sock(sk);
 	return err;
 }
 
-static int compat_ipv6_get_msfilter(struct sock *sk, void __user *optval,
-		int __user *optlen)
+static int compat_ipv6_get_msfilter(struct sock *sk, sockptr_t optval,
+				    sockptr_t optlen, int len)
 {
 	const int size0 = offsetof(struct compat_group_filter, gf_slist_flex);
-	struct compat_group_filter __user *p = optval;
 	struct compat_group_filter gf32;
 	struct group_filter gf;
-	int len, err;
+	int err;
 	int num;
 
-	if (get_user(len, optlen))
-		return -EFAULT;
 	if (len < size0)
 		return -EINVAL;
 
-	if (copy_from_user(&gf32, p, size0))
+	if (copy_from_sockptr(&gf32, optval, size0))
 		return -EFAULT;
 	gf.gf_interface = gf32.gf_interface;
 	gf.gf_fmode = gf32.gf_fmode;
@@ -1117,23 +1114,25 @@ static int compat_ipv6_get_msfilter(struct sock *sk, void __user *optval,
 	if (gf.gf_group.ss_family != AF_INET6)
 		return -EADDRNOTAVAIL;
 
-	lock_sock(sk);
-	err = ip6_mc_msfget(sk, &gf, p->gf_slist_flex);
-	release_sock(sk);
+	sockopt_lock_sock(sk);
+	err = ip6_mc_msfget(sk, &gf, optval, size0);
+	sockopt_release_sock(sk);
 	if (err)
 		return err;
 	if (num > gf.gf_numsrc)
 		num = gf.gf_numsrc;
 	len = GROUP_FILTER_SIZE(num) - (sizeof(gf)-sizeof(gf32));
-	if (put_user(len, optlen) ||
-	    put_user(gf.gf_fmode, &p->gf_fmode) ||
-	    put_user(gf.gf_numsrc, &p->gf_numsrc))
+	if (copy_to_sockptr(optlen, &len, sizeof(int)) ||
+	    copy_to_sockptr_offset(optval, offsetof(struct compat_group_filter, gf_fmode),
+				   &gf.gf_fmode, sizeof(gf32.gf_fmode)) ||
+	    copy_to_sockptr_offset(optval, offsetof(struct compat_group_filter, gf_numsrc),
+				   &gf.gf_numsrc, sizeof(gf32.gf_numsrc)))
 		return -EFAULT;
 	return 0;
 }
 
-static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
-		    char __user *optval, int __user *optlen, unsigned int flags)
+int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
+		       sockptr_t optval, sockptr_t optlen)
 {
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	int len;
@@ -1142,7 +1141,7 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 	if (ip6_mroute_opt(optname))
 		return ip6_mroute_getsockopt(sk, optname, optval, optlen);
 
-	if (get_user(len, optlen))
+	if (copy_from_sockptr(&len, optlen, sizeof(int)))
 		return -EFAULT;
 	switch (optname) {
 	case IPV6_ADDRFORM:
@@ -1156,7 +1155,7 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 		break;
 	case MCAST_MSFILTER:
 		if (in_compat_syscall())
-			return compat_ipv6_get_msfilter(sk, optval, optlen);
+			return compat_ipv6_get_msfilter(sk, optval, optlen, len);
 		return ipv6_get_msfilter(sk, optval, optlen, len);
 	case IPV6_2292PKTOPTIONS:
 	{
@@ -1166,16 +1165,21 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 		if (sk->sk_type != SOCK_STREAM)
 			return -ENOPROTOOPT;
 
-		msg.msg_control_user = optval;
+		if (optval.is_kernel) {
+			msg.msg_control_is_user = false;
+			msg.msg_control = optval.kernel;
+		} else {
+			msg.msg_control_is_user = true;
+			msg.msg_control_user = optval.user;
+		}
 		msg.msg_controllen = len;
-		msg.msg_flags = flags;
-		msg.msg_control_is_user = true;
+		msg.msg_flags = 0;
 
-		lock_sock(sk);
+		sockopt_lock_sock(sk);
 		skb = np->pktoptions;
 		if (skb)
 			ip6_datagram_recv_ctl(sk, &msg, skb);
-		release_sock(sk);
+		sockopt_release_sock(sk);
 		if (!skb) {
 			if (np->rxopt.bits.rxinfo) {
 				struct in6_pktinfo src_info;
@@ -1212,7 +1216,7 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 			}
 		}
 		len -= msg.msg_controllen;
-		return put_user(len, optlen);
+		return copy_to_sockptr(optlen, &len, sizeof(int));
 	}
 	case IPV6_MTU:
 	{
@@ -1264,15 +1268,15 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 	{
 		struct ipv6_txoptions *opt;
 
-		lock_sock(sk);
+		sockopt_lock_sock(sk);
 		opt = rcu_dereference_protected(np->opt,
 						lockdep_sock_is_held(sk));
 		len = ipv6_getsockopt_sticky(sk, opt, optname, optval, len);
-		release_sock(sk);
+		sockopt_release_sock(sk);
 		/* check if ipv6_getsockopt_sticky() returns err code */
 		if (len < 0)
 			return len;
-		return put_user(len, optlen);
+		return copy_to_sockptr(optlen, &len, sizeof(int));
 	}
 
 	case IPV6_RECVHOPOPTS:
@@ -1326,9 +1330,9 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 		if (!mtuinfo.ip6m_mtu)
 			return -ENOTCONN;
 
-		if (put_user(len, optlen))
+		if (copy_to_sockptr(optlen, &len, sizeof(int)))
 			return -EFAULT;
-		if (copy_to_user(optval, &mtuinfo, len))
+		if (copy_to_sockptr(optval, &mtuinfo, len))
 			return -EFAULT;
 
 		return 0;
@@ -1405,7 +1409,7 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 		if (len < sizeof(freq))
 			return -EINVAL;
 
-		if (copy_from_user(&freq, optval, sizeof(freq)))
+		if (copy_from_sockptr(&freq, optval, sizeof(freq)))
 			return -EFAULT;
 
 		if (freq.flr_action != IPV6_FL_A_GET)
@@ -1420,9 +1424,9 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 		if (val < 0)
 			return val;
 
-		if (put_user(len, optlen))
+		if (copy_to_sockptr(optlen, &len, sizeof(int)))
 			return -EFAULT;
-		if (copy_to_user(optval, &freq, len))
+		if (copy_to_sockptr(optval, &freq, len))
 			return -EFAULT;
 
 		return 0;
@@ -1474,9 +1478,9 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 		return -ENOPROTOOPT;
 	}
 	len = min_t(unsigned int, sizeof(int), len);
-	if (put_user(len, optlen))
+	if (copy_to_sockptr(optlen, &len, sizeof(int)))
 		return -EFAULT;
-	if (copy_to_user(optval, &val, len))
+	if (copy_to_sockptr(optval, &val, len))
 		return -EFAULT;
 	return 0;
 }
@@ -1492,7 +1496,8 @@ int ipv6_getsockopt(struct sock *sk, int level, int optname,
 	if (level != SOL_IPV6)
 		return -ENOPROTOOPT;
 
-	err = do_ipv6_getsockopt(sk, level, optname, optval, optlen, 0);
+	err = do_ipv6_getsockopt(sk, level, optname,
+				 USER_SOCKPTR(optval), USER_SOCKPTR(optlen));
 #ifdef CONFIG_NETFILTER
 	/* we need to exclude all possible ENOPROTOOPTs except default case */
 	if (err == -ENOPROTOOPT && optname != IPV6_2292PKTOPTIONS) {
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 87c699d57b36..0566ab03ddbe 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -580,7 +580,7 @@ done:
 }
 
 int ip6_mc_msfget(struct sock *sk, struct group_filter *gsf,
-		  struct sockaddr_storage __user *p)
+		  sockptr_t optval, size_t ss_offset)
 {
 	struct ipv6_pinfo *inet6 = inet6_sk(sk);
 	const struct in6_addr *group;
@@ -612,8 +612,7 @@ int ip6_mc_msfget(struct sock *sk, struct group_filter *gsf,
 
 	copycount = count < gsf->gf_numsrc ? count : gsf->gf_numsrc;
 	gsf->gf_numsrc = count;
-
-	for (i = 0; i < copycount; i++, p++) {
+	for (i = 0; i < copycount; i++) {
 		struct sockaddr_in6 *psin6;
 		struct sockaddr_storage ss;
 
@@ -621,8 +620,9 @@ int ip6_mc_msfget(struct sock *sk, struct group_filter *gsf,
 		memset(&ss, 0, sizeof(ss));
 		psin6->sin6_family = AF_INET6;
 		psin6->sin6_addr = psl->sl_addr[i];
-		if (copy_to_user(p, &ss, sizeof(ss)))
+		if (copy_to_sockptr_offset(optval, ss_offset, &ss, sizeof(ss)))
 			return -EFAULT;
+		ss_offset += sizeof(ss);
 	}
 	return 0;
 }