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

Daniel Borkmann says:

====================
pull-request: bpf-next 2022-05-23

We've added 113 non-merge commits during the last 26 day(s) which contain
a total of 121 files changed, 7425 insertions(+), 1586 deletions(-).

The main changes are:

1) Speed up symbol resolution for kprobes multi-link attachments, from Jiri Olsa.

2) Add BPF dynamic pointer infrastructure e.g. to allow for dynamically sized ringbuf
   reservations without extra memory copies, from Joanne Koong.

3) Big batch of libbpf improvements towards libbpf 1.0 release, from Andrii Nakryiko.

4) Add BPF link iterator to traverse links via seq_file ops, from Dmitrii Dolgov.

5) Add source IP address to BPF tunnel key infrastructure, from Kaixi Fan.

6) Refine unprivileged BPF to disable only object-creating commands, from Alan Maguire.

7) Fix JIT blinding of ld_imm64 when they point to subprogs, from Alexei Starovoitov.

8) Add BPF access to mptcp_sock structures and their meta data, from Geliang Tang.

9) Add new BPF helper for access to remote CPU's BPF map elements, from Feng Zhou.

10) Allow attaching 64-bit cookie to BPF link of fentry/fexit/fmod_ret, from Kui-Feng Lee.

11) Follow-ups to typed pointer support in BPF maps, from Kumar Kartikeya Dwivedi.

12) Add busy-poll test cases to the XSK selftest suite, from Magnus Karlsson.

13) Improvements in BPF selftest test_progs subtest output, from Mykola Lysenko.

14) Fill bpf_prog_pack allocator areas with illegal instructions, from Song Liu.

15) Add generic batch operations for BPF map-in-map cases, from Takshak Chahande.

16) Make bpf_jit_enable more user friendly when permanently on 1, from Tiezhu Yang.

17) Fix an array overflow in bpf_trampoline_get_progs(), from Yuntao Wang.

====================

Link: https://lore.kernel.org/r/20220523223805.27931-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

7 files changed, 105 insertions, 20 deletions

diff --git a/net/bpf/bpf_dummy_struct_ops.c b/net/bpf/bpf_dummy_struct_ops.c
index d0e54e30658a..e78dadfc5829 100644
--- a/net/bpf/bpf_dummy_struct_ops.c
+++ b/net/bpf/bpf_dummy_struct_ops.c
@@ -72,13 +72,16 @@ static int dummy_ops_call_op(void *image, struct bpf_dummy_ops_test_args *args)
 		    args->args[3], args->args[4]);
 }
 
+extern const struct bpf_link_ops bpf_struct_ops_link_lops;
+
 int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr,
 			    union bpf_attr __user *uattr)
 {
 	const struct bpf_struct_ops *st_ops = &bpf_bpf_dummy_ops;
 	const struct btf_type *func_proto;
 	struct bpf_dummy_ops_test_args *args;
-	struct bpf_tramp_progs *tprogs;
+	struct bpf_tramp_links *tlinks;
+	struct bpf_tramp_link *link = NULL;
 	void *image = NULL;
 	unsigned int op_idx;
 	int prog_ret;
@@ -92,8 +95,8 @@ int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr,
 	if (IS_ERR(args))
 		return PTR_ERR(args);
 
-	tprogs = kcalloc(BPF_TRAMP_MAX, sizeof(*tprogs), GFP_KERNEL);
-	if (!tprogs) {
+	tlinks = kcalloc(BPF_TRAMP_MAX, sizeof(*tlinks), GFP_KERNEL);
+	if (!tlinks) {
 		err = -ENOMEM;
 		goto out;
 	}
@@ -105,8 +108,17 @@ int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr,
 	}
 	set_vm_flush_reset_perms(image);
 
+	link = kzalloc(sizeof(*link), GFP_USER);
+	if (!link) {
+		err = -ENOMEM;
+		goto out;
+	}
+	/* prog doesn't take the ownership of the reference from caller */
+	bpf_prog_inc(prog);
+	bpf_link_init(&link->link, BPF_LINK_TYPE_STRUCT_OPS, &bpf_struct_ops_link_lops, prog);
+
 	op_idx = prog->expected_attach_type;
-	err = bpf_struct_ops_prepare_trampoline(tprogs, prog,
+	err = bpf_struct_ops_prepare_trampoline(tlinks, link,
 						&st_ops->func_models[op_idx],
 						image, image + PAGE_SIZE);
 	if (err < 0)
@@ -124,7 +136,9 @@ int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr,
 out:
 	kfree(args);
 	bpf_jit_free_exec(image);
-	kfree(tprogs);
+	if (link)
+		bpf_link_put(&link->link);
+	kfree(tlinks);
 	return err;
 }
 
diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index 9b5a1f630bb0..56f059b3c242 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -565,31 +565,36 @@ struct prog_test_ref_kfunc {
 	int b;
 	struct prog_test_member memb;
 	struct prog_test_ref_kfunc *next;
+	refcount_t cnt;
 };
 
 static struct prog_test_ref_kfunc prog_test_struct = {
 	.a = 42,
 	.b = 108,
 	.next = &prog_test_struct,
+	.cnt = REFCOUNT_INIT(1),
 };
 
 noinline struct prog_test_ref_kfunc *
 bpf_kfunc_call_test_acquire(unsigned long *scalar_ptr)
 {
-	/* randomly return NULL */
-	if (get_jiffies_64() % 2)
-		return NULL;
+	refcount_inc(&prog_test_struct.cnt);
 	return &prog_test_struct;
 }
 
 noinline struct prog_test_member *
 bpf_kfunc_call_memb_acquire(void)
 {
-	return &prog_test_struct.memb;
+	WARN_ON_ONCE(1);
+	return NULL;
 }
 
 noinline void bpf_kfunc_call_test_release(struct prog_test_ref_kfunc *p)
 {
+	if (!p)
+		return;
+
+	refcount_dec(&p->cnt);
 }
 
 noinline void bpf_kfunc_call_memb_release(struct prog_test_member *p)
@@ -598,12 +603,18 @@ noinline void bpf_kfunc_call_memb_release(struct prog_test_member *p)
 
 noinline void bpf_kfunc_call_memb1_release(struct prog_test_member1 *p)
 {
+	WARN_ON_ONCE(1);
 }
 
 noinline struct prog_test_ref_kfunc *
-bpf_kfunc_call_test_kptr_get(struct prog_test_ref_kfunc **p, int a, int b)
+bpf_kfunc_call_test_kptr_get(struct prog_test_ref_kfunc **pp, int a, int b)
 {
-	return &prog_test_struct;
+	struct prog_test_ref_kfunc *p = READ_ONCE(*pp);
+
+	if (!p)
+		return NULL;
+	refcount_inc(&p->cnt);
+	return p;
 }
 
 struct prog_test_pass1 {
diff --git a/net/core/filter.c b/net/core/filter.c
index b741b9f7e6a9..5af58eb48587 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -78,6 +78,7 @@
 #include <linux/btf_ids.h>
 #include <net/tls.h>
 #include <net/xdp.h>
+#include <net/mptcp.h>
 
 static const struct bpf_func_proto *
 bpf_sk_base_func_proto(enum bpf_func_id func_id);
@@ -4498,6 +4499,7 @@ BPF_CALL_4(bpf_skb_get_tunnel_key, struct sk_buff *, skb, struct bpf_tunnel_key
 	if (unlikely(size != sizeof(struct bpf_tunnel_key))) {
 		err = -EINVAL;
 		switch (size) {
+		case offsetof(struct bpf_tunnel_key, local_ipv6[0]):
 		case offsetof(struct bpf_tunnel_key, tunnel_label):
 		case offsetof(struct bpf_tunnel_key, tunnel_ext):
 			goto set_compat;
@@ -4523,10 +4525,14 @@ set_compat:
 	if (flags & BPF_F_TUNINFO_IPV6) {
 		memcpy(to->remote_ipv6, &info->key.u.ipv6.src,
 		       sizeof(to->remote_ipv6));
+		memcpy(to->local_ipv6, &info->key.u.ipv6.dst,
+		       sizeof(to->local_ipv6));
 		to->tunnel_label = be32_to_cpu(info->key.label);
 	} else {
 		to->remote_ipv4 = be32_to_cpu(info->key.u.ipv4.src);
 		memset(&to->remote_ipv6[1], 0, sizeof(__u32) * 3);
+		to->local_ipv4 = be32_to_cpu(info->key.u.ipv4.dst);
+		memset(&to->local_ipv6[1], 0, sizeof(__u32) * 3);
 		to->tunnel_label = 0;
 	}
 
@@ -4597,6 +4603,7 @@ BPF_CALL_4(bpf_skb_set_tunnel_key, struct sk_buff *, skb,
 		return -EINVAL;
 	if (unlikely(size != sizeof(struct bpf_tunnel_key))) {
 		switch (size) {
+		case offsetof(struct bpf_tunnel_key, local_ipv6[0]):
 		case offsetof(struct bpf_tunnel_key, tunnel_label):
 		case offsetof(struct bpf_tunnel_key, tunnel_ext):
 		case offsetof(struct bpf_tunnel_key, remote_ipv6[1]):
@@ -4639,10 +4646,13 @@ BPF_CALL_4(bpf_skb_set_tunnel_key, struct sk_buff *, skb,
 		info->mode |= IP_TUNNEL_INFO_IPV6;
 		memcpy(&info->key.u.ipv6.dst, from->remote_ipv6,
 		       sizeof(from->remote_ipv6));
+		memcpy(&info->key.u.ipv6.src, from->local_ipv6,
+		       sizeof(from->local_ipv6));
 		info->key.label = cpu_to_be32(from->tunnel_label) &
 				  IPV6_FLOWLABEL_MASK;
 	} else {
 		info->key.u.ipv4.dst = cpu_to_be32(from->remote_ipv4);
+		info->key.u.ipv4.src = cpu_to_be32(from->local_ipv4);
 	}
 
 	return 0;
@@ -11272,6 +11282,20 @@ const struct bpf_func_proto bpf_skc_to_unix_sock_proto = {
 	.ret_btf_id		= &btf_sock_ids[BTF_SOCK_TYPE_UNIX],
 };
 
+BPF_CALL_1(bpf_skc_to_mptcp_sock, struct sock *, sk)
+{
+	BTF_TYPE_EMIT(struct mptcp_sock);
+	return (unsigned long)bpf_mptcp_sock_from_subflow(sk);
+}
+
+const struct bpf_func_proto bpf_skc_to_mptcp_sock_proto = {
+	.func		= bpf_skc_to_mptcp_sock,
+	.gpl_only	= false,
+	.ret_type	= RET_PTR_TO_BTF_ID_OR_NULL,
+	.arg1_type	= ARG_PTR_TO_SOCK_COMMON,
+	.ret_btf_id	= &btf_sock_ids[BTF_SOCK_TYPE_MPTCP],
+};
+
 BPF_CALL_1(bpf_sock_from_file, struct file *, file)
 {
 	return (unsigned long)sock_from_file(file);
@@ -11314,6 +11338,9 @@ bpf_sk_base_func_proto(enum bpf_func_id func_id)
 	case BPF_FUNC_skc_to_unix_sock:
 		func = &bpf_skc_to_unix_sock_proto;
 		break;
+	case BPF_FUNC_skc_to_mptcp_sock:
+		func = &bpf_skc_to_mptcp_sock_proto;
+		break;
 	case BPF_FUNC_ktime_get_coarse_ns:
 		return &bpf_ktime_get_coarse_ns_proto;
 	default:
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index cc381165ea08..22b983ade0e7 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -524,16 +524,20 @@ static int sk_psock_skb_ingress_enqueue(struct sk_buff *skb,
 {
 	int num_sge, copied;
 
-	/* skb linearize may fail with ENOMEM, but lets simply try again
-	 * later if this happens. Under memory pressure we don't want to
-	 * drop the skb. We need to linearize the skb so that the mapping
-	 * in skb_to_sgvec can not error.
-	 */
-	if (skb_linearize(skb))
-		return -EAGAIN;
 	num_sge = skb_to_sgvec(skb, msg->sg.data, off, len);
-	if (unlikely(num_sge < 0))
-		return num_sge;
+	if (num_sge < 0) {
+		/* skb linearize may fail with ENOMEM, but lets simply try again
+		 * later if this happens. Under memory pressure we don't want to
+		 * drop the skb. We need to linearize the skb so that the mapping
+		 * in skb_to_sgvec can not error.
+		 */
+		if (skb_linearize(skb))
+			return -EAGAIN;
+
+		num_sge = skb_to_sgvec(skb, msg->sg.data, off, len);
+		if (unlikely(num_sge < 0))
+			return num_sge;
+	}
 
 	copied = len;
 	msg->sg.start = 0;
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index ca8d38325e1e..71a13596ea2b 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -264,6 +264,8 @@ static int proc_dointvec_minmax_bpf_enable(struct ctl_table *table, int write,
 					   loff_t *ppos)
 {
 	int ret, jit_enable = *(int *)table->data;
+	int min = *(int *)table->extra1;
+	int max = *(int *)table->extra2;
 	struct ctl_table tmp = *table;
 
 	if (write && !capable(CAP_SYS_ADMIN))
@@ -281,6 +283,10 @@ static int proc_dointvec_minmax_bpf_enable(struct ctl_table *table, int write,
 			ret = -EPERM;
 		}
 	}
+
+	if (write && ret && min == max)
+		pr_info_once("CONFIG_BPF_JIT_ALWAYS_ON is enabled, bpf_jit_enable is permanently set to 1.\n");
+
 	return ret;
 }
 
diff --git a/net/mptcp/Makefile b/net/mptcp/Makefile
index cb7f53f6ab22..6e7df47c9584 100644
--- a/net/mptcp/Makefile
+++ b/net/mptcp/Makefile
@@ -10,3 +10,5 @@ obj-$(CONFIG_INET_MPTCP_DIAG) += mptcp_diag.o
 mptcp_crypto_test-objs := crypto_test.o
 mptcp_token_test-objs := token_test.o
 obj-$(CONFIG_MPTCP_KUNIT_TEST) += mptcp_crypto_test.o mptcp_token_test.o
+
+obj-$(CONFIG_BPF_SYSCALL) += bpf.o
diff --git a/net/mptcp/bpf.c b/net/mptcp/bpf.c
new file mode 100644
index 000000000000..5a0a84ad94af
--- /dev/null
+++ b/net/mptcp/bpf.c
@@ -0,0 +1,21 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Multipath TCP
+ *
+ * Copyright (c) 2020, Tessares SA.
+ * Copyright (c) 2022, SUSE.
+ *
+ * Author: Nicolas Rybowski <nicolas.rybowski@tessares.net>
+ */
+
+#define pr_fmt(fmt) "MPTCP: " fmt
+
+#include <linux/bpf.h>
+#include "protocol.h"
+
+struct mptcp_sock *bpf_mptcp_sock_from_subflow(struct sock *sk)
+{
+	if (sk && sk_fullsock(sk) && sk->sk_protocol == IPPROTO_TCP && sk_is_mptcp(sk))
+		return mptcp_sk(mptcp_subflow_ctx(sk)->conn);
+
+	return NULL;
+}