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

…/git/bpf/bpf

Daniel Borkmann says:

====================
pull-request: bpf 2024-07-25

We've added 14 non-merge commits during the last 8 day(s) which contain
a total of 19 files changed, 177 insertions(+), 70 deletions(-).

The main changes are:

1) Fix af_unix to disable MSG_OOB handling for sockets in BPF sockmap and
   BPF sockhash. Also add test coverage for this case, from Michal Luczaj.

2) Fix a segmentation issue when downgrading gso_size in the BPF helper
   bpf_skb_adjust_room(), from Fred Li.

3) Fix a compiler warning in resolve_btfids due to a missing type cast,
   from Liwei Song.

4) Fix stack allocation for arm64 to align the stack pointer at a 16 byte
   boundary in the fexit_sleep BPF selftest, from Puranjay Mohan.

5) Fix a xsk regression to require a flag when actuating tx_metadata_len,
   from Stanislav Fomichev.

6) Fix function prototype BTF dumping in libbpf for prototypes that have
   no input arguments, from Andrii Nakryiko.

7) Fix stacktrace symbol resolution in perf script for BPF programs
   containing subprograms, from Hou Tao.

* tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf:
  selftests/bpf: Add XDP_UMEM_TX_METADATA_LEN to XSK TX metadata test
  xsk: Require XDP_UMEM_TX_METADATA_LEN to actuate tx_metadata_len
  bpf: Fix a segment issue when downgrading gso_size
  tools/resolve_btfids: Fix comparison of distinct pointer types warning in resolve_btfids
  bpf, events: Use prog to emit ksymbol event for main program
  selftests/bpf: Test sockmap redirect for AF_UNIX MSG_OOB
  selftests/bpf: Parametrize AF_UNIX redir functions to accept send() flags
  selftests/bpf: Support SOCK_STREAM in unix_inet_redir_to_connected()
  af_unix: Disable MSG_OOB handling for sockets in sockmap/sockhash
  bpftool: Fix typo in usage help
  libbpf: Fix no-args func prototype BTF dumping syntax
  MAINTAINERS: Update powerpc BPF JIT maintainers
  MAINTAINERS: Update email address of Naveen
  selftests/bpf: fexit_sleep: Fix stack allocation for arm64
====================

Link: https://patch.msgid.link/20240725114312.32197-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

.mailmap

@@ -474,6 +474,8 @@ Nadia Yvette Chambers <nyc@holomorphy.com> William Lee Irwin III <wli@holomorphy
 Naoya Horiguchi <nao.horiguchi@gmail.com> <n-horiguchi@ah.jp.nec.com>
 Naoya Horiguchi <nao.horiguchi@gmail.com> <naoya.horiguchi@nec.com>
 Nathan Chancellor <nathan@kernel.org> <natechancellor@gmail.com>
+Naveen N Rao <naveen@kernel.org> <naveen.n.rao@linux.ibm.com>
+Naveen N Rao <naveen@kernel.org> <naveen.n.rao@linux.vnet.ibm.com>
 Neeraj Upadhyay <neeraj.upadhyay@kernel.org> <quic_neeraju@quicinc.com>
 Neeraj Upadhyay <neeraj.upadhyay@kernel.org> <neeraju@codeaurora.org>
 Neil Armstrong <neil.armstrong@linaro.org> <narmstrong@baylibre.com>

Documentation/networking/xsk-tx-metadata.rst

@@ -11,12 +11,16 @@ metadata on the receive side.
 General Design
 ==============
 
-The headroom for the metadata is reserved via ``tx_metadata_len`` in
-``struct xdp_umem_reg``. The metadata length is therefore the same for
-every socket that shares the same umem. The metadata layout is a fixed UAPI,
-refer to ``union xsk_tx_metadata`` in ``include/uapi/linux/if_xdp.h``.
-Thus, generally, the ``tx_metadata_len`` field above should contain
-``sizeof(union xsk_tx_metadata)``.
+The headroom for the metadata is reserved via ``tx_metadata_len`` and
+``XDP_UMEM_TX_METADATA_LEN`` flag in ``struct xdp_umem_reg``. The metadata
+length is therefore the same for every socket that shares the same umem.
+The metadata layout is a fixed UAPI, refer to ``union xsk_tx_metadata`` in
+``include/uapi/linux/if_xdp.h``. Thus, generally, the ``tx_metadata_len``
+field above should contain ``sizeof(union xsk_tx_metadata)``.
+
+Note that in the original implementation the ``XDP_UMEM_TX_METADATA_LEN``
+flag was not required. Applications might attempt to create a umem
+with a flag first and if it fails, do another attempt without a flag.
 
 The headroom and the metadata itself should be located right before
 ``xdp_desc->addr`` in the umem frame. Within a frame, the metadata

MAINTAINERS

@@ -3946,8 +3946,10 @@ S:	Odd Fixes
 F:	drivers/net/ethernet/netronome/nfp/bpf/
 
 BPF JIT for POWERPC (32-BIT AND 64-BIT)
-M:	Naveen N. Rao <naveen.n.rao@linux.ibm.com>
 M:	Michael Ellerman <mpe@ellerman.id.au>
+M:	Hari Bathini <hbathini@linux.ibm.com>
+M:	Christophe Leroy <christophe.leroy@csgroup.eu>
+R:	Naveen N Rao <naveen@kernel.org>
 L:	bpf@vger.kernel.org
 S:	Supported
 F:	arch/powerpc/net/
@@ -12484,7 +12486,7 @@ F:	mm/kmsan/
 F:	scripts/Makefile.kmsan
 
 KPROBES
-M:	Naveen N. Rao <naveen.n.rao@linux.ibm.com>
+M:	Naveen N Rao <naveen@kernel.org>
 M:	Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>
 M:	"David S. Miller" <davem@davemloft.net>
 M:	Masami Hiramatsu <mhiramat@kernel.org>
@@ -12861,7 +12863,7 @@ LINUX FOR POWERPC (32-BIT AND 64-BIT)
 M:	Michael Ellerman <mpe@ellerman.id.au>
 R:	Nicholas Piggin <npiggin@gmail.com>
 R:	Christophe Leroy <christophe.leroy@csgroup.eu>
-R:	Naveen N. Rao <naveen.n.rao@linux.ibm.com>
+R:	Naveen N Rao <naveen@kernel.org>
 L:	linuxppc-dev@lists.ozlabs.org
 S:	Supported
 W:	https://github.com/linuxppc/wiki/wiki

include/uapi/linux/if_xdp.h

@@ -41,6 +41,10 @@
  */
 #define XDP_UMEM_TX_SW_CSUM		(1 << 1)
 
+/* Request to reserve tx_metadata_len bytes of per-chunk metadata.
+ */
+#define XDP_UMEM_TX_METADATA_LEN	(1 << 2)
+
 struct sockaddr_xdp {
 	__u16 sxdp_family;
 	__u16 sxdp_flags;

kernel/events/core.c

@@ -9327,21 +9327,19 @@ static void perf_event_bpf_emit_ksymbols(struct bpf_prog *prog,
 	bool unregister = type == PERF_BPF_EVENT_PROG_UNLOAD;
 	int i;
 
-	if (prog->aux->func_cnt == 0) {
-		perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_BPF,
-				   (u64)(unsigned long)prog->bpf_func,
-				   prog->jited_len, unregister,
-				   prog->aux->ksym.name);
-	} else {
-		for (i = 0; i < prog->aux->func_cnt; i++) {
-			struct bpf_prog *subprog = prog->aux->func[i];
-
-			perf_event_ksymbol(
-				PERF_RECORD_KSYMBOL_TYPE_BPF,
-				(u64)(unsigned long)subprog->bpf_func,
-				subprog->jited_len, unregister,
-				subprog->aux->ksym.name);
-		}
+	perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_BPF,
+			   (u64)(unsigned long)prog->bpf_func,
+			   prog->jited_len, unregister,
+			   prog->aux->ksym.name);
+
+	for (i = 1; i < prog->aux->func_cnt; i++) {
+		struct bpf_prog *subprog = prog->aux->func[i];
+
+		perf_event_ksymbol(
+			PERF_RECORD_KSYMBOL_TYPE_BPF,
+			(u64)(unsigned long)subprog->bpf_func,
+			subprog->jited_len, unregister,
+			subprog->aux->ksym.name);
 	}
 }
 

net/core/filter.c

@@ -3548,13 +3548,20 @@ static int bpf_skb_net_grow(struct sk_buff *skb, u32 off, u32 len_diff,
 	if (skb_is_gso(skb)) {
 		struct skb_shared_info *shinfo = skb_shinfo(skb);
 
-		/* Due to header grow, MSS needs to be downgraded. */
-		if (!(flags & BPF_F_ADJ_ROOM_FIXED_GSO))
-			skb_decrease_gso_size(shinfo, len_diff);
-
 		/* Header must be checked, and gso_segs recomputed. */
 		shinfo->gso_type |= gso_type;
 		shinfo->gso_segs = 0;
+
+		/* Due to header growth, MSS needs to be downgraded.
+		 * There is a BUG_ON() when segmenting the frag_list with
+		 * head_frag true, so linearize the skb after downgrading
+		 * the MSS.
+		 */
+		if (!(flags & BPF_F_ADJ_ROOM_FIXED_GSO)) {
+			skb_decrease_gso_size(shinfo, len_diff);
+			if (shinfo->frag_list)
+				return skb_linearize(skb);
+		}
 	}
 
 	return 0;

net/unix/af_unix.c

@@ -2721,10 +2721,49 @@ static struct sk_buff *manage_oob(struct sk_buff *skb, struct sock *sk,
 
 static int unix_stream_read_skb(struct sock *sk, skb_read_actor_t recv_actor)
 {
+	struct unix_sock *u = unix_sk(sk);
+	struct sk_buff *skb;
+	int err;
+
 	if (unlikely(READ_ONCE(sk->sk_state) != TCP_ESTABLISHED))
 		return -ENOTCONN;
 
-	return unix_read_skb(sk, recv_actor);
+	mutex_lock(&u->iolock);
+	skb = skb_recv_datagram(sk, MSG_DONTWAIT, &err);
+	mutex_unlock(&u->iolock);
+	if (!skb)
+		return err;
+
+#if IS_ENABLED(CONFIG_AF_UNIX_OOB)
+	if (unlikely(skb == READ_ONCE(u->oob_skb))) {
+		bool drop = false;
+
+		unix_state_lock(sk);
+
+		if (sock_flag(sk, SOCK_DEAD)) {
+			unix_state_unlock(sk);
+			kfree_skb(skb);
+			return -ECONNRESET;
+		}
+
+		spin_lock(&sk->sk_receive_queue.lock);
+		if (likely(skb == u->oob_skb)) {
+			WRITE_ONCE(u->oob_skb, NULL);
+			drop = true;
+		}
+		spin_unlock(&sk->sk_receive_queue.lock);
+
+		unix_state_unlock(sk);
+
+		if (drop) {
+			WARN_ON_ONCE(skb_unref(skb));
+			kfree_skb(skb);
+			return -EAGAIN;
+		}
+	}
+#endif
+
+	return recv_actor(sk, skb);
 }
 
 static int unix_stream_read_generic(struct unix_stream_read_state *state,

net/unix/unix_bpf.c

@@ -54,6 +54,9 @@ static int unix_bpf_recvmsg(struct sock *sk, struct msghdr *msg,
 	struct sk_psock *psock;
 	int copied;
 
+	if (flags & MSG_OOB)
+		return -EOPNOTSUPP;
+
 	if (!len)
 		return 0;
 

net/xdp/xdp_umem.c

@@ -151,6 +151,7 @@ static int xdp_umem_account_pages(struct xdp_umem *umem)
 #define XDP_UMEM_FLAGS_VALID ( \
 		XDP_UMEM_UNALIGNED_CHUNK_FLAG | \
 		XDP_UMEM_TX_SW_CSUM | \
+		XDP_UMEM_TX_METADATA_LEN | \
 	0)
 
 static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
@@ -204,8 +205,11 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
 	if (headroom >= chunk_size - XDP_PACKET_HEADROOM)
 		return -EINVAL;
 
-	if (mr->tx_metadata_len >= 256 || mr->tx_metadata_len % 8)
-		return -EINVAL;
+	if (mr->flags & XDP_UMEM_TX_METADATA_LEN) {
+		if (mr->tx_metadata_len >= 256 || mr->tx_metadata_len % 8)
+			return -EINVAL;
+		umem->tx_metadata_len = mr->tx_metadata_len;
+	}
 
 	umem->size = size;
 	umem->headroom = headroom;
@@ -215,7 +219,6 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
 	umem->pgs = NULL;
 	umem->user = NULL;
 	umem->flags = mr->flags;
-	umem->tx_metadata_len = mr->tx_metadata_len;
 
 	INIT_LIST_HEAD(&umem->xsk_dma_list);
 	refcount_set(&umem->users, 1);

tools/bpf/bpftool/prog.c

@@ -2489,7 +2489,7 @@ static int do_help(int argc, char **argv)
 		"                 cgroup/connect_unix | cgroup/getpeername4 | cgroup/getpeername6 |\n"
 		"                 cgroup/getpeername_unix | cgroup/getsockname4 | cgroup/getsockname6 |\n"
 		"                 cgroup/getsockname_unix | cgroup/sendmsg4 | cgroup/sendmsg6 |\n"
-		"                 cgroup/sendmsg°unix | cgroup/recvmsg4 | cgroup/recvmsg6 | cgroup/recvmsg_unix |\n"
+		"                 cgroup/sendmsg_unix | cgroup/recvmsg4 | cgroup/recvmsg6 | cgroup/recvmsg_unix |\n"
 		"                 cgroup/getsockopt | cgroup/setsockopt | cgroup/sock_release |\n"
 		"                 struct_ops | fentry | fexit | freplace | sk_lookup }\n"
 		"       ATTACH_TYPE := { sk_msg_verdict | sk_skb_verdict | sk_skb_stream_verdict |\n"

tools/bpf/resolve_btfids/main.c

@@ -704,7 +704,7 @@ static int sets_patch(struct object *obj)
 			 * Make sure id is at the beginning of the pairs
 			 * struct, otherwise the below qsort would not work.
 			 */
-			BUILD_BUG_ON(set8->pairs != &set8->pairs[0].id);
+			BUILD_BUG_ON((u32 *)set8->pairs != &set8->pairs[0].id);
 			qsort(set8->pairs, set8->cnt, sizeof(set8->pairs[0]), cmp_id);
 
 			/*

tools/include/uapi/linux/if_xdp.h

@@ -41,6 +41,10 @@
  */
 #define XDP_UMEM_TX_SW_CSUM		(1 << 1)
 
+/* Request to reserve tx_metadata_len bytes of per-chunk metadata.
+ */
+#define XDP_UMEM_TX_METADATA_LEN	(1 << 2)
+
 struct sockaddr_xdp {
 	__u16 sxdp_family;
 	__u16 sxdp_flags;

tools/lib/bpf/btf_dump.c

@@ -1559,10 +1559,12 @@ static void btf_dump_emit_type_chain(struct btf_dump *d,
 			 * Clang for BPF target generates func_proto with no
 			 * args as a func_proto with a single void arg (e.g.,
 			 * `int (*f)(void)` vs just `int (*f)()`). We are
-			 * going to pretend there are no args for such case.
+			 * going to emit valid empty args (void) syntax for
+			 * such case. Similarly and conveniently, valid
+			 * no args case can be special-cased here as well.
 			 */
-			if (vlen == 1 && p->type == 0) {
-				btf_dump_printf(d, ")");
+			if (vlen == 0 || (vlen == 1 && p->type == 0)) {
+				btf_dump_printf(d, "void)");
 				return;
 			}
 

tools/testing/selftests/bpf/DENYLIST.aarch64

@@ -1,6 +1,5 @@
 bpf_cookie/multi_kprobe_attach_api               # kprobe_multi_link_api_subtest:FAIL:fentry_raw_skel_load unexpected error: -3
 bpf_cookie/multi_kprobe_link_api                 # kprobe_multi_link_api_subtest:FAIL:fentry_raw_skel_load unexpected error: -3
-fexit_sleep                                      # The test never returns. The remaining tests cannot start.
 kprobe_multi_bench_attach                        # needs CONFIG_FPROBE
 kprobe_multi_test                                # needs CONFIG_FPROBE
 module_attach                                    # prog 'kprobe_multi': failed to auto-attach: -95

tools/testing/selftests/bpf/prog_tests/fexit_sleep.c

@@ -21,13 +21,13 @@ static int do_sleep(void *skel)
 }
 
 #define STACK_SIZE (1024 * 1024)
-static char child_stack[STACK_SIZE];
 
 void test_fexit_sleep(void)
 {
 	struct fexit_sleep_lskel *fexit_skel = NULL;
 	int wstatus, duration = 0;
 	pid_t cpid;
+	char *child_stack = NULL;
 	int err, fexit_cnt;
 
 	fexit_skel = fexit_sleep_lskel__open_and_load();
@@ -38,6 +38,11 @@ void test_fexit_sleep(void)
 	if (CHECK(err, "fexit_attach", "fexit attach failed: %d\n", err))
 		goto cleanup;
 
+	child_stack = mmap(NULL, STACK_SIZE, PROT_READ | PROT_WRITE, MAP_PRIVATE |
+			   MAP_ANONYMOUS | MAP_STACK, -1, 0);
+	if (!ASSERT_NEQ(child_stack, MAP_FAILED, "mmap"))
+		goto cleanup;
+
 	cpid = clone(do_sleep, child_stack + STACK_SIZE, CLONE_FILES | SIGCHLD, fexit_skel);
 	if (CHECK(cpid == -1, "clone", "%s\n", strerror(errno)))
 		goto cleanup;
@@ -78,5 +83,6 @@ void test_fexit_sleep(void)
 		goto cleanup;
 
 cleanup:
+	munmap(child_stack, STACK_SIZE);
 	fexit_sleep_lskel__destroy(fexit_skel);
 }