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>

1 files changed, 94 insertions, 40 deletions

diff --git a/net/core/sock.c b/net/core/sock.c
index 788c1372663c..eeb6cbac6f49 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -703,15 +703,17 @@ static int sock_setbindtodevice(struct sock *sk, sockptr_t optval, int optlen)
 			goto out;
 	}
 
-	return sock_bindtoindex(sk, index, true);
+	sockopt_lock_sock(sk);
+	ret = sock_bindtoindex_locked(sk, index);
+	sockopt_release_sock(sk);
 out:
 #endif
 
 	return ret;
 }
 
-static int sock_getbindtodevice(struct sock *sk, char __user *optval,
-				int __user *optlen, int len)
+static int sock_getbindtodevice(struct sock *sk, sockptr_t optval,
+				sockptr_t optlen, int len)
 {
 	int ret = -ENOPROTOOPT;
 #ifdef CONFIG_NETDEVICES
@@ -735,12 +737,12 @@ static int sock_getbindtodevice(struct sock *sk, char __user *optval,
 	len = strlen(devname) + 1;
 
 	ret = -EFAULT;
-	if (copy_to_user(optval, devname, len))
+	if (copy_to_sockptr(optval, devname, len))
 		goto out;
 
 zero:
 	ret = -EFAULT;
-	if (put_user(len, optlen))
+	if (copy_to_sockptr(optlen, &len, sizeof(int)))
 		goto out;
 
 	ret = 0;
@@ -1036,17 +1038,51 @@ static int sock_reserve_memory(struct sock *sk, int bytes)
 	return 0;
 }
 
+void sockopt_lock_sock(struct sock *sk)
+{
+	/* When current->bpf_ctx is set, the setsockopt is called from
+	 * a bpf prog.  bpf has ensured the sk lock has been
+	 * acquired before calling setsockopt().
+	 */
+	if (has_current_bpf_ctx())
+		return;
+
+	lock_sock(sk);
+}
+EXPORT_SYMBOL(sockopt_lock_sock);
+
+void sockopt_release_sock(struct sock *sk)
+{
+	if (has_current_bpf_ctx())
+		return;
+
+	release_sock(sk);
+}
+EXPORT_SYMBOL(sockopt_release_sock);
+
+bool sockopt_ns_capable(struct user_namespace *ns, int cap)
+{
+	return has_current_bpf_ctx() || ns_capable(ns, cap);
+}
+EXPORT_SYMBOL(sockopt_ns_capable);
+
+bool sockopt_capable(int cap)
+{
+	return has_current_bpf_ctx() || capable(cap);
+}
+EXPORT_SYMBOL(sockopt_capable);
+
 /*
  *	This is meant for all protocols to use and covers goings on
  *	at the socket level. Everything here is generic.
  */
 
-int sock_setsockopt(struct socket *sock, int level, int optname,
-		    sockptr_t optval, unsigned int optlen)
+int sk_setsockopt(struct sock *sk, int level, int optname,
+		  sockptr_t optval, unsigned int optlen)
 {
 	struct so_timestamping timestamping;
+	struct socket *sock = sk->sk_socket;
 	struct sock_txtime sk_txtime;
-	struct sock *sk = sock->sk;
 	int val;
 	int valbool;
 	struct linger ling;
@@ -1067,11 +1103,11 @@ int sock_setsockopt(struct socket *sock, int level, int optname,
 
 	valbool = val ? 1 : 0;
 
-	lock_sock(sk);
+	sockopt_lock_sock(sk);
 
 	switch (optname) {
 	case SO_DEBUG:
-		if (val && !capable(CAP_NET_ADMIN))
+		if (val && !sockopt_capable(CAP_NET_ADMIN))
 			ret = -EACCES;
 		else
 			sock_valbool_flag(sk, SOCK_DBG, valbool);
@@ -1115,7 +1151,7 @@ set_sndbuf:
 		break;
 
 	case SO_SNDBUFFORCE:
-		if (!capable(CAP_NET_ADMIN)) {
+		if (!sockopt_capable(CAP_NET_ADMIN)) {
 			ret = -EPERM;
 			break;
 		}
@@ -1137,7 +1173,7 @@ set_sndbuf:
 		break;
 
 	case SO_RCVBUFFORCE:
-		if (!capable(CAP_NET_ADMIN)) {
+		if (!sockopt_capable(CAP_NET_ADMIN)) {
 			ret = -EPERM;
 			break;
 		}
@@ -1164,8 +1200,8 @@ set_sndbuf:
 
 	case SO_PRIORITY:
 		if ((val >= 0 && val <= 6) ||
-		    ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) ||
-		    ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
+		    sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) ||
+		    sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
 			sk->sk_priority = val;
 		else
 			ret = -EPERM;
@@ -1228,7 +1264,7 @@ set_sndbuf:
 	case SO_RCVLOWAT:
 		if (val < 0)
 			val = INT_MAX;
-		if (sock->ops->set_rcvlowat)
+		if (sock && sock->ops->set_rcvlowat)
 			ret = sock->ops->set_rcvlowat(sk, val);
 		else
 			WRITE_ONCE(sk->sk_rcvlowat, val ? : 1);
@@ -1310,8 +1346,8 @@ set_sndbuf:
 			clear_bit(SOCK_PASSSEC, &sock->flags);
 		break;
 	case SO_MARK:
-		if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) &&
-		    !ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) {
+		if (!sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) &&
+		    !sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) {
 			ret = -EPERM;
 			break;
 		}
@@ -1319,8 +1355,8 @@ set_sndbuf:
 		__sock_set_mark(sk, val);
 		break;
 	case SO_RCVMARK:
-		if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) &&
-		    !ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) {
+		if (!sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) &&
+		    !sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) {
 			ret = -EPERM;
 			break;
 		}
@@ -1354,7 +1390,7 @@ set_sndbuf:
 #ifdef CONFIG_NET_RX_BUSY_POLL
 	case SO_BUSY_POLL:
 		/* allow unprivileged users to decrease the value */
-		if ((val > sk->sk_ll_usec) && !capable(CAP_NET_ADMIN))
+		if ((val > sk->sk_ll_usec) && !sockopt_capable(CAP_NET_ADMIN))
 			ret = -EPERM;
 		else {
 			if (val < 0)
@@ -1364,13 +1400,13 @@ set_sndbuf:
 		}
 		break;
 	case SO_PREFER_BUSY_POLL:
-		if (valbool && !capable(CAP_NET_ADMIN))
+		if (valbool && !sockopt_capable(CAP_NET_ADMIN))
 			ret = -EPERM;
 		else
 			WRITE_ONCE(sk->sk_prefer_busy_poll, valbool);
 		break;
 	case SO_BUSY_POLL_BUDGET:
-		if (val > READ_ONCE(sk->sk_busy_poll_budget) && !capable(CAP_NET_ADMIN)) {
+		if (val > READ_ONCE(sk->sk_busy_poll_budget) && !sockopt_capable(CAP_NET_ADMIN)) {
 			ret = -EPERM;
 		} else {
 			if (val < 0 || val > U16_MAX)
@@ -1441,7 +1477,7 @@ set_sndbuf:
 		 * scheduler has enough safe guards.
 		 */
 		if (sk_txtime.clockid != CLOCK_MONOTONIC &&
-		    !ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) {
+		    !sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) {
 			ret = -EPERM;
 			break;
 		}
@@ -1496,9 +1532,16 @@ set_sndbuf:
 		ret = -ENOPROTOOPT;
 		break;
 	}
-	release_sock(sk);
+	sockopt_release_sock(sk);
 	return ret;
 }
+
+int sock_setsockopt(struct socket *sock, int level, int optname,
+		    sockptr_t optval, unsigned int optlen)
+{
+	return sk_setsockopt(sock->sk, level, optname,
+			     optval, optlen);
+}
 EXPORT_SYMBOL(sock_setsockopt);
 
 static const struct cred *sk_get_peer_cred(struct sock *sk)
@@ -1525,22 +1568,25 @@ static void cred_to_ucred(struct pid *pid, const struct cred *cred,
 	}
 }
 
-static int groups_to_user(gid_t __user *dst, const struct group_info *src)
+static int groups_to_user(sockptr_t dst, const struct group_info *src)
 {
 	struct user_namespace *user_ns = current_user_ns();
 	int i;
 
-	for (i = 0; i < src->ngroups; i++)
-		if (put_user(from_kgid_munged(user_ns, src->gid[i]), dst + i))
+	for (i = 0; i < src->ngroups; i++) {
+		gid_t gid = from_kgid_munged(user_ns, src->gid[i]);
+
+		if (copy_to_sockptr_offset(dst, i * sizeof(gid), &gid, sizeof(gid)))
 			return -EFAULT;
+	}
 
 	return 0;
 }
 
-int sock_getsockopt(struct socket *sock, int level, int optname,
-		    char __user *optval, int __user *optlen)
+int sk_getsockopt(struct sock *sk, int level, int optname,
+		  sockptr_t optval, sockptr_t optlen)
 {
-	struct sock *sk = sock->sk;
+	struct socket *sock = sk->sk_socket;
 
 	union {
 		int val;
@@ -1557,7 +1603,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
 	int lv = sizeof(int);
 	int len;
 
-	if (get_user(len, optlen))
+	if (copy_from_sockptr(&len, optlen, sizeof(int)))
 		return -EFAULT;
 	if (len < 0)
 		return -EINVAL;
@@ -1692,7 +1738,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
 		cred_to_ucred(sk->sk_peer_pid, sk->sk_peer_cred, &peercred);
 		spin_unlock(&sk->sk_peer_lock);
 
-		if (copy_to_user(optval, &peercred, len))
+		if (copy_to_sockptr(optval, &peercred, len))
 			return -EFAULT;
 		goto lenout;
 	}
@@ -1710,11 +1756,11 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
 		if (len < n * sizeof(gid_t)) {
 			len = n * sizeof(gid_t);
 			put_cred(cred);
-			return put_user(len, optlen) ? -EFAULT : -ERANGE;
+			return copy_to_sockptr(optlen, &len, sizeof(int)) ? -EFAULT : -ERANGE;
 		}
 		len = n * sizeof(gid_t);
 
-		ret = groups_to_user((gid_t __user *)optval, cred->group_info);
+		ret = groups_to_user(optval, cred->group_info);
 		put_cred(cred);
 		if (ret)
 			return ret;
@@ -1730,7 +1776,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
 			return -ENOTCONN;
 		if (lv < len)
 			return -EINVAL;
-		if (copy_to_user(optval, address, len))
+		if (copy_to_sockptr(optval, address, len))
 			return -EFAULT;
 		goto lenout;
 	}
@@ -1747,7 +1793,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
 		break;
 
 	case SO_PEERSEC:
-		return security_socket_getpeersec_stream(sock, optval, optlen, len);
+		return security_socket_getpeersec_stream(sock, optval.user, optlen.user, len);
 
 	case SO_MARK:
 		v.val = sk->sk_mark;
@@ -1779,7 +1825,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
 		return sock_getbindtodevice(sk, optval, optlen, len);
 
 	case SO_GET_FILTER:
-		len = sk_get_filter(sk, (struct sock_filter __user *)optval, len);
+		len = sk_get_filter(sk, optval, len);
 		if (len < 0)
 			return len;
 
@@ -1827,7 +1873,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
 		sk_get_meminfo(sk, meminfo);
 
 		len = min_t(unsigned int, len, sizeof(meminfo));
-		if (copy_to_user(optval, &meminfo, len))
+		if (copy_to_sockptr(optval, &meminfo, len))
 			return -EFAULT;
 
 		goto lenout;
@@ -1896,14 +1942,22 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
 
 	if (len > lv)
 		len = lv;
-	if (copy_to_user(optval, &v, len))
+	if (copy_to_sockptr(optval, &v, len))
 		return -EFAULT;
 lenout:
-	if (put_user(len, optlen))
+	if (copy_to_sockptr(optlen, &len, sizeof(int)))
 		return -EFAULT;
 	return 0;
 }
 
+int sock_getsockopt(struct socket *sock, int level, int optname,
+		    char __user *optval, int __user *optlen)
+{
+	return sk_getsockopt(sock->sk, level, optname,
+			     USER_SOCKPTR(optval),
+			     USER_SOCKPTR(optlen));
+}
+
 /*
  * Initialize an sk_lock.
  *