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

Alexei Starovoitov says:

====================
pull-request: bpf-next 2021-11-01

We've added 181 non-merge commits during the last 28 day(s) which contain
a total of 280 files changed, 11791 insertions(+), 5879 deletions(-).

The main changes are:

1) Fix bpf verifier propagation of 64-bit bounds, from Alexei.

2) Parallelize bpf test_progs, from Yucong and Andrii.

3) Deprecate various libbpf apis including af_xdp, from Andrii, Hengqi, Magnus.

4) Improve bpf selftests on s390, from Ilya.

5) bloomfilter bpf map type, from Joanne.

6) Big improvements to JIT tests especially on Mips, from Johan.

7) Support kernel module function calls from bpf, from Kumar.

8) Support typeless and weak ksym in light skeleton, from Kumar.

9) Disallow unprivileged bpf by default, from Pawan.

10) BTF_KIND_DECL_TAG support, from Yonghong.

11) Various bpftool cleanups, from Quentin.

* https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (181 commits)
  libbpf: Deprecate AF_XDP support
  kbuild: Unify options for BTF generation for vmlinux and modules
  selftests/bpf: Add a testcase for 64-bit bounds propagation issue.
  bpf: Fix propagation of signed bounds from 64-bit min/max into 32-bit.
  bpf: Fix propagation of bounds from 64-bit min/max into 32-bit and var_off.
  selftests/bpf: Fix also no-alu32 strobemeta selftest
  bpf: Add missing map_delete_elem method to bloom filter map
  selftests/bpf: Add bloom map success test for userspace calls
  bpf: Add alignment padding for "map_extra" + consolidate holes
  bpf: Bloom filter map naming fixups
  selftests/bpf: Add test cases for struct_ops prog
  bpf: Add dummy BPF STRUCT_OPS for test purpose
  bpf: Factor out helpers for ctx access checking
  bpf: Factor out a helper to prepare trampoline for struct_ops prog
  selftests, bpf: Fix broken riscv build
  riscv, libbpf: Add RISC-V (RV64) support to bpf_tracing.h
  tools, build: Add RISC-V to HOSTARCH parsing
  riscv, bpf: Increase the maximum number of iterations
  selftests, bpf: Add one test for sockmap with strparser
  selftests, bpf: Fix test_txmsg_ingress_parser error
  ...
====================

Link: https://lore.kernel.org/r/20211102013123.9005-1-alexei.starovoitov@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

2 files changed, 56 insertions, 10 deletions

diff --git a/net/core/filter.c b/net/core/filter.c
index 4bace37a6a44..8e8d3b49c297 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -10723,6 +10723,26 @@ const struct bpf_func_proto bpf_skc_to_udp6_sock_proto = {
 	.ret_btf_id		= &btf_sock_ids[BTF_SOCK_TYPE_UDP6],
 };
 
+BPF_CALL_1(bpf_skc_to_unix_sock, struct sock *, sk)
+{
+	/* unix_sock type is not generated in dwarf and hence btf,
+	 * trigger an explicit type generation here.
+	 */
+	BTF_TYPE_EMIT(struct unix_sock);
+	if (sk && sk_fullsock(sk) && sk->sk_family == AF_UNIX)
+		return (unsigned long)sk;
+
+	return (unsigned long)NULL;
+}
+
+const struct bpf_func_proto bpf_skc_to_unix_sock_proto = {
+	.func			= bpf_skc_to_unix_sock,
+	.gpl_only		= false,
+	.ret_type		= RET_PTR_TO_BTF_ID_OR_NULL,
+	.arg1_type		= ARG_PTR_TO_BTF_ID_SOCK_COMMON,
+	.ret_btf_id		= &btf_sock_ids[BTF_SOCK_TYPE_UNIX],
+};
+
 BPF_CALL_1(bpf_sock_from_file, struct file *, file)
 {
 	return (unsigned long)sock_from_file(file);
@@ -10762,6 +10782,9 @@ bpf_sk_base_func_proto(enum bpf_func_id func_id)
 	case BPF_FUNC_skc_to_udp6_sock:
 		func = &bpf_skc_to_udp6_sock_proto;
 		break;
+	case BPF_FUNC_skc_to_unix_sock:
+		func = &bpf_skc_to_unix_sock_proto;
+		break;
 	default:
 		return bpf_base_func_proto(func_id);
 	}
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index a86ef7e844f8..1ae52ac943f6 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -508,6 +508,7 @@ static struct sk_msg *sk_psock_create_ingress_msg(struct sock *sk,
 }
 
 static int sk_psock_skb_ingress_enqueue(struct sk_buff *skb,
+					u32 off, u32 len,
 					struct sk_psock *psock,
 					struct sock *sk,
 					struct sk_msg *msg)
@@ -521,11 +522,11 @@ static int sk_psock_skb_ingress_enqueue(struct sk_buff *skb,
 	 */
 	if (skb_linearize(skb))
 		return -EAGAIN;
-	num_sge = skb_to_sgvec(skb, msg->sg.data, 0, skb->len);
+	num_sge = skb_to_sgvec(skb, msg->sg.data, off, len);
 	if (unlikely(num_sge < 0))
 		return num_sge;
 
-	copied = skb->len;
+	copied = len;
 	msg->sg.start = 0;
 	msg->sg.size = copied;
 	msg->sg.end = num_sge;
@@ -536,9 +537,11 @@ static int sk_psock_skb_ingress_enqueue(struct sk_buff *skb,
 	return copied;
 }
 
-static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb);
+static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb,
+				     u32 off, u32 len);
 
-static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb)
+static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb,
+				u32 off, u32 len)
 {
 	struct sock *sk = psock->sk;
 	struct sk_msg *msg;
@@ -549,7 +552,7 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb)
 	 * correctly.
 	 */
 	if (unlikely(skb->sk == sk))
-		return sk_psock_skb_ingress_self(psock, skb);
+		return sk_psock_skb_ingress_self(psock, skb, off, len);
 	msg = sk_psock_create_ingress_msg(sk, skb);
 	if (!msg)
 		return -EAGAIN;
@@ -561,7 +564,7 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb)
 	 * into user buffers.
 	 */
 	skb_set_owner_r(skb, sk);
-	err = sk_psock_skb_ingress_enqueue(skb, psock, sk, msg);
+	err = sk_psock_skb_ingress_enqueue(skb, off, len, psock, sk, msg);
 	if (err < 0)
 		kfree(msg);
 	return err;
@@ -571,7 +574,8 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb)
  * skb. In this case we do not need to check memory limits or skb_set_owner_r
  * because the skb is already accounted for here.
  */
-static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb)
+static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb,
+				     u32 off, u32 len)
 {
 	struct sk_msg *msg = kzalloc(sizeof(*msg), __GFP_NOWARN | GFP_ATOMIC);
 	struct sock *sk = psock->sk;
@@ -581,7 +585,7 @@ static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb
 		return -EAGAIN;
 	sk_msg_init(msg);
 	skb_set_owner_r(skb, sk);
-	err = sk_psock_skb_ingress_enqueue(skb, psock, sk, msg);
+	err = sk_psock_skb_ingress_enqueue(skb, off, len, psock, sk, msg);
 	if (err < 0)
 		kfree(msg);
 	return err;
@@ -595,7 +599,7 @@ static int sk_psock_handle_skb(struct sk_psock *psock, struct sk_buff *skb,
 			return -EAGAIN;
 		return skb_send_sock(psock->sk, skb, off, len);
 	}
-	return sk_psock_skb_ingress(psock, skb);
+	return sk_psock_skb_ingress(psock, skb, off, len);
 }
 
 static void sk_psock_skb_state(struct sk_psock *psock,
@@ -638,6 +642,12 @@ static void sk_psock_backlog(struct work_struct *work)
 	while ((skb = skb_dequeue(&psock->ingress_skb))) {
 		len = skb->len;
 		off = 0;
+		if (skb_bpf_strparser(skb)) {
+			struct strp_msg *stm = strp_msg(skb);
+
+			off = stm->offset;
+			len = stm->full_len;
+		}
 start:
 		ingress = skb_bpf_ingress(skb);
 		skb_bpf_redirect_clear(skb);
@@ -877,6 +887,7 @@ static int sk_psock_skb_redirect(struct sk_psock *from, struct sk_buff *skb)
 	 * return code, but then didn't set a redirect interface.
 	 */
 	if (unlikely(!sk_other)) {
+		skb_bpf_redirect_clear(skb);
 		sock_drop(from->sk, skb);
 		return -EIO;
 	}
@@ -944,6 +955,7 @@ static int sk_psock_verdict_apply(struct sk_psock *psock, struct sk_buff *skb,
 {
 	struct sock *sk_other;
 	int err = 0;
+	u32 len, off;
 
 	switch (verdict) {
 	case __SK_PASS:
@@ -951,6 +963,7 @@ static int sk_psock_verdict_apply(struct sk_psock *psock, struct sk_buff *skb,
 		sk_other = psock->sk;
 		if (sock_flag(sk_other, SOCK_DEAD) ||
 		    !sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) {
+			skb_bpf_redirect_clear(skb);
 			goto out_free;
 		}
 
@@ -963,7 +976,15 @@ static int sk_psock_verdict_apply(struct sk_psock *psock, struct sk_buff *skb,
 		 * retrying later from workqueue.
 		 */
 		if (skb_queue_empty(&psock->ingress_skb)) {
-			err = sk_psock_skb_ingress_self(psock, skb);
+			len = skb->len;
+			off = 0;
+			if (skb_bpf_strparser(skb)) {
+				struct strp_msg *stm = strp_msg(skb);
+
+				off = stm->offset;
+				len = stm->full_len;
+			}
+			err = sk_psock_skb_ingress_self(psock, skb, off, len);
 		}
 		if (err < 0) {
 			spin_lock_bh(&psock->ingress_lock);
@@ -1029,6 +1050,8 @@ static void sk_psock_strp_read(struct strparser *strp, struct sk_buff *skb)
 		skb_dst_drop(skb);
 		skb_bpf_redirect_clear(skb);
 		ret = bpf_prog_run_pin_on_cpu(prog, skb);
+		if (ret == SK_PASS)
+			skb_bpf_set_strparser(skb);
 		ret = sk_psock_map_verd(ret, skb_bpf_redirect_fetch(skb));
 		skb->sk = NULL;
 	}