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

Daniel Borkmann says:

====================
pull-request: bpf-next 2023-10-16

We've added 90 non-merge commits during the last 25 day(s) which contain
a total of 120 files changed, 3519 insertions(+), 895 deletions(-).

The main changes are:

1) Add missed stats for kprobes to retrieve the number of missed kprobe
   executions and subsequent executions of BPF programs, from Jiri Olsa.

2) Add cgroup BPF sockaddr hooks for unix sockets. The use case is
   for systemd to reimplement the LogNamespace feature which allows
   running multiple instances of systemd-journald to process the logs
   of different services, from Daan De Meyer.

3) Implement BPF CPUv4 support for s390x BPF JIT, from Ilya Leoshkevich.

4) Improve BPF verifier log output for scalar registers to better
   disambiguate their internal state wrt defaults vs min/max values
   matching, from Andrii Nakryiko.

5) Extend the BPF fib lookup helpers for IPv4/IPv6 to support retrieving
   the source IP address with a new BPF_FIB_LOOKUP_SRC flag,
   from Martynas Pumputis.

6) Add support for open-coded task_vma iterator to help with symbolization
   for BPF-collected user stacks, from Dave Marchevsky.

7) Add libbpf getters for accessing individual BPF ring buffers which
   is useful for polling them individually, for example, from Martin Kelly.

8) Extend AF_XDP selftests to validate the SHARED_UMEM feature,
   from Tushar Vyavahare.

9) Improve BPF selftests cross-building support for riscv arch,
   from Björn Töpel.

10) Add the ability to pin a BPF timer to the same calling CPU,
   from David Vernet.

11) Fix libbpf's bpf_tracing.h macros for riscv to use the generic
   implementation of PT_REGS_SYSCALL_REGS() to access syscall arguments,
   from Alexandre Ghiti.

12) Extend libbpf to support symbol versioning for uprobes, from Hengqi Chen.

13) Fix bpftool's skeleton code generation to guarantee that ELF data
    is 8 byte aligned, from Ian Rogers.

14) Inherit system-wide cpu_mitigations_off() setting for Spectre v1/v4
    security mitigations in BPF verifier, from Yafang Shao.

15) Annotate struct bpf_stack_map with __counted_by attribute to prepare
    BPF side for upcoming __counted_by compiler support, from Kees Cook.

* tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (90 commits)
  bpf: Ensure proper register state printing for cond jumps
  bpf: Disambiguate SCALAR register state output in verifier logs
  selftests/bpf: Make align selftests more robust
  selftests/bpf: Improve missed_kprobe_recursion test robustness
  selftests/bpf: Improve percpu_alloc test robustness
  selftests/bpf: Add tests for open-coded task_vma iter
  bpf: Introduce task_vma open-coded iterator kfuncs
  selftests/bpf: Rename bpf_iter_task_vma.c to bpf_iter_task_vmas.c
  bpf: Don't explicitly emit BTF for struct btf_iter_num
  bpf: Change syscall_nr type to int in struct syscall_tp_t
  net/bpf: Avoid unused "sin_addr_len" warning when CONFIG_CGROUP_BPF is not set
  bpf: Avoid unnecessary audit log for CPU security mitigations
  selftests/bpf: Add tests for cgroup unix socket address hooks
  selftests/bpf: Make sure mount directory exists
  documentation/bpf: Document cgroup unix socket address hooks
  bpftool: Add support for cgroup unix socket address hooks
  libbpf: Add support for cgroup unix socket address hooks
  bpf: Implement cgroup sockaddr hooks for unix sockets
  bpf: Add bpf_sock_addr_set_sun_path() to allow writing unix sockaddr from bpf
  bpf: Propagate modified uaddrlen from cgroup sockaddr programs
  ...
====================

Link: https://lore.kernel.org/r/20231016204803.30153-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 63 insertions, 4 deletions

diff --git a/net/core/filter.c b/net/core/filter.c
index a094694899c9..cc2e4babc85f 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -81,6 +81,7 @@
 #include <net/xdp.h>
 #include <net/mptcp.h>
 #include <net/netfilter/nf_conntrack_bpf.h>
+#include <linux/un.h>
 
 static const struct bpf_func_proto *
 bpf_sk_base_func_proto(enum bpf_func_id func_id);
@@ -5850,6 +5851,9 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 	params->rt_metric = res.fi->fib_priority;
 	params->ifindex = dev->ifindex;
 
+	if (flags & BPF_FIB_LOOKUP_SRC)
+		params->ipv4_src = fib_result_prefsrc(net, &res);
+
 	/* xdp and cls_bpf programs are run in RCU-bh so
 	 * rcu_read_lock_bh is not needed here
 	 */
@@ -5992,6 +5996,18 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 	params->rt_metric = res.f6i->fib6_metric;
 	params->ifindex = dev->ifindex;
 
+	if (flags & BPF_FIB_LOOKUP_SRC) {
+		if (res.f6i->fib6_prefsrc.plen) {
+			*src = res.f6i->fib6_prefsrc.addr;
+		} else {
+			err = ipv6_bpf_stub->ipv6_dev_get_saddr(net, dev,
+								&fl6.daddr, 0,
+								src);
+			if (err)
+				return BPF_FIB_LKUP_RET_NO_SRC_ADDR;
+		}
+	}
+
 	if (flags & BPF_FIB_LOOKUP_SKIP_NEIGH)
 		goto set_fwd_params;
 
@@ -6010,7 +6026,8 @@ 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_TBID)
+			     BPF_FIB_LOOKUP_SKIP_NEIGH | BPF_FIB_LOOKUP_TBID | \
+			     BPF_FIB_LOOKUP_SRC)
 
 BPF_CALL_4(bpf_xdp_fib_lookup, struct xdp_buff *, ctx,
 	   struct bpf_fib_lookup *, params, int, plen, u32, flags)
@@ -7858,14 +7875,19 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		case BPF_CGROUP_INET6_BIND:
 		case BPF_CGROUP_INET4_CONNECT:
 		case BPF_CGROUP_INET6_CONNECT:
+		case BPF_CGROUP_UNIX_CONNECT:
 		case BPF_CGROUP_UDP4_RECVMSG:
 		case BPF_CGROUP_UDP6_RECVMSG:
+		case BPF_CGROUP_UNIX_RECVMSG:
 		case BPF_CGROUP_UDP4_SENDMSG:
 		case BPF_CGROUP_UDP6_SENDMSG:
+		case BPF_CGROUP_UNIX_SENDMSG:
 		case BPF_CGROUP_INET4_GETPEERNAME:
 		case BPF_CGROUP_INET6_GETPEERNAME:
+		case BPF_CGROUP_UNIX_GETPEERNAME:
 		case BPF_CGROUP_INET4_GETSOCKNAME:
 		case BPF_CGROUP_INET6_GETSOCKNAME:
+		case BPF_CGROUP_UNIX_GETSOCKNAME:
 			return &bpf_sock_addr_setsockopt_proto;
 		default:
 			return NULL;
@@ -7876,14 +7898,19 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		case BPF_CGROUP_INET6_BIND:
 		case BPF_CGROUP_INET4_CONNECT:
 		case BPF_CGROUP_INET6_CONNECT:
+		case BPF_CGROUP_UNIX_CONNECT:
 		case BPF_CGROUP_UDP4_RECVMSG:
 		case BPF_CGROUP_UDP6_RECVMSG:
+		case BPF_CGROUP_UNIX_RECVMSG:
 		case BPF_CGROUP_UDP4_SENDMSG:
 		case BPF_CGROUP_UDP6_SENDMSG:
+		case BPF_CGROUP_UNIX_SENDMSG:
 		case BPF_CGROUP_INET4_GETPEERNAME:
 		case BPF_CGROUP_INET6_GETPEERNAME:
+		case BPF_CGROUP_UNIX_GETPEERNAME:
 		case BPF_CGROUP_INET4_GETSOCKNAME:
 		case BPF_CGROUP_INET6_GETSOCKNAME:
+		case BPF_CGROUP_UNIX_GETSOCKNAME:
 			return &bpf_sock_addr_getsockopt_proto;
 		default:
 			return NULL;
@@ -8931,8 +8958,8 @@ static bool sock_addr_is_valid_access(int off, int size,
 	if (off % size != 0)
 		return false;
 
-	/* Disallow access to IPv6 fields from IPv4 contex and vise
-	 * versa.
+	/* Disallow access to fields not belonging to the attach type's address
+	 * family.
 	 */
 	switch (off) {
 	case bpf_ctx_range(struct bpf_sock_addr, user_ip4):
@@ -11752,6 +11779,27 @@ __bpf_kfunc int bpf_dynptr_from_xdp(struct xdp_buff *xdp, u64 flags,
 
 	return 0;
 }
+
+__bpf_kfunc int bpf_sock_addr_set_sun_path(struct bpf_sock_addr_kern *sa_kern,
+					   const u8 *sun_path, u32 sun_path__sz)
+{
+	struct sockaddr_un *un;
+
+	if (sa_kern->sk->sk_family != AF_UNIX)
+		return -EINVAL;
+
+	/* We do not allow changing the address to unnamed or larger than the
+	 * maximum allowed address size for a unix sockaddr.
+	 */
+	if (sun_path__sz == 0 || sun_path__sz > UNIX_PATH_MAX)
+		return -EINVAL;
+
+	un = (struct sockaddr_un *)sa_kern->uaddr;
+	memcpy(un->sun_path, sun_path, sun_path__sz);
+	sa_kern->uaddrlen = offsetof(struct sockaddr_un, sun_path) + sun_path__sz;
+
+	return 0;
+}
 __diag_pop();
 
 int bpf_dynptr_from_skb_rdonly(struct sk_buff *skb, u64 flags,
@@ -11776,6 +11824,10 @@ BTF_SET8_START(bpf_kfunc_check_set_xdp)
 BTF_ID_FLAGS(func, bpf_dynptr_from_xdp)
 BTF_SET8_END(bpf_kfunc_check_set_xdp)
 
+BTF_SET8_START(bpf_kfunc_check_set_sock_addr)
+BTF_ID_FLAGS(func, bpf_sock_addr_set_sun_path)
+BTF_SET8_END(bpf_kfunc_check_set_sock_addr)
+
 static const struct btf_kfunc_id_set bpf_kfunc_set_skb = {
 	.owner = THIS_MODULE,
 	.set = &bpf_kfunc_check_set_skb,
@@ -11786,6 +11838,11 @@ static const struct btf_kfunc_id_set bpf_kfunc_set_xdp = {
 	.set = &bpf_kfunc_check_set_xdp,
 };
 
+static const struct btf_kfunc_id_set bpf_kfunc_set_sock_addr = {
+	.owner = THIS_MODULE,
+	.set = &bpf_kfunc_check_set_sock_addr,
+};
+
 static int __init bpf_kfunc_init(void)
 {
 	int ret;
@@ -11800,7 +11857,9 @@ static int __init bpf_kfunc_init(void)
 	ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_LWT_XMIT, &bpf_kfunc_set_skb);
 	ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_LWT_SEG6LOCAL, &bpf_kfunc_set_skb);
 	ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_NETFILTER, &bpf_kfunc_set_skb);
-	return ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP, &bpf_kfunc_set_xdp);
+	ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP, &bpf_kfunc_set_xdp);
+	return ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
+						&bpf_kfunc_set_sock_addr);
 }
 late_initcall(bpf_kfunc_init);