bpf-for-netdev

-----BEGIN PGP SIGNATURE-----
 
 iHUEABYIAB0WIQTFp0I1jqZrAX+hPRXbK58LschIgwUCY6YkXgAKCRDbK58LschI
 g25kAP4jYi+YomSlmGUzN/fUbEIHkXXyh85Yh2/yHGYdVuIuvwEA0uXeC7JHQTca
 dkcyYvgY6zJwFBV0lAVnhTRzFirFkQk=
 =THs1
 -----END PGP SIGNATURE-----

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

Daniel Borkmann says:

====================
The following pull-request contains BPF updates for your *net* tree.

We've added 7 non-merge commits during the last 5 day(s) which contain
a total of 11 files changed, 231 insertions(+), 3 deletions(-).

The main changes are:

1) Fix a splat in bpf_skb_generic_pop() under CHECKSUM_PARTIAL due to
   misuse of skb_postpull_rcsum(), from Jakub Kicinski with test case
   from Martin Lau.

2) Fix BPF verifier's nullness propagation when registers are of
   type PTR_TO_BTF_ID, from Hao Sun.

3) Fix bpftool build for JIT disassembler under statically built
   libllvm, from Anton Protopopov.

4) Fix warnings reported by resolve_btfids when building vmlinux
   with CONFIG_SECURITY_NETWORK disabled, from Hou Tao.

5) Minor fix up for BPF selftest gitignore, from Stanislav Fomichev.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

kernel/bpf/bpf_lsm.c

@@ -351,8 +351,10 @@ BTF_ID(func, bpf_lsm_bpf_prog_alloc_security)
 BTF_ID(func, bpf_lsm_bpf_prog_free_security)
 BTF_ID(func, bpf_lsm_file_alloc_security)
 BTF_ID(func, bpf_lsm_file_free_security)
+#ifdef CONFIG_SECURITY_NETWORK
 BTF_ID(func, bpf_lsm_sk_alloc_security)
 BTF_ID(func, bpf_lsm_sk_free_security)
+#endif /* CONFIG_SECURITY_NETWORK */
 BTF_ID(func, bpf_lsm_task_free)
 BTF_SET_END(untrusted_lsm_hooks)
 

kernel/bpf/verifier.c

@@ -11822,10 +11822,17 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
 	 *      register B - not null
 	 * for JNE A, B, ... - A is not null in the false branch;
 	 * for JEQ A, B, ... - A is not null in the true branch.
+	 *
+	 * Since PTR_TO_BTF_ID points to a kernel struct that does
+	 * not need to be null checked by the BPF program, i.e.,
+	 * could be null even without PTR_MAYBE_NULL marking, so
+	 * only propagate nullness when neither reg is that type.
 	 */
 	if (!is_jmp32 && BPF_SRC(insn->code) == BPF_X &&
 	    __is_pointer_value(false, src_reg) && __is_pointer_value(false, dst_reg) &&
-	    type_may_be_null(src_reg->type) != type_may_be_null(dst_reg->type)) {
+	    type_may_be_null(src_reg->type) != type_may_be_null(dst_reg->type) &&
+	    base_type(src_reg->type) != PTR_TO_BTF_ID &&
+	    base_type(dst_reg->type) != PTR_TO_BTF_ID) {
 		eq_branch_regs = NULL;
 		switch (opcode) {
 		case BPF_JEQ:

net/core/filter.c

@@ -3180,15 +3180,18 @@ static int bpf_skb_generic_push(struct sk_buff *skb, u32 off, u32 len)
 
 static int bpf_skb_generic_pop(struct sk_buff *skb, u32 off, u32 len)
 {
+	void *old_data;
+
 	/* skb_ensure_writable() is not needed here, as we're
 	 * already working on an uncloned skb.
 	 */
 	if (unlikely(!pskb_may_pull(skb, off + len)))
 		return -ENOMEM;
 
-	skb_postpull_rcsum(skb, skb->data + off, len);
-	memmove(skb->data + len, skb->data, off);
+	old_data = skb->data;
 	__skb_pull(skb, len);
+	skb_postpull_rcsum(skb, old_data + off, len);
+	memmove(skb->data, old_data, off);
 
 	return 0;
 }

tools/bpf/bpftool/Makefile

@@ -145,6 +145,10 @@ ifeq ($(feature-llvm),1)
   LLVM_CONFIG_LIB_COMPONENTS := mcdisassembler all-targets
   CFLAGS  += $(shell $(LLVM_CONFIG) --cflags --libs $(LLVM_CONFIG_LIB_COMPONENTS))
   LIBS    += $(shell $(LLVM_CONFIG) --libs $(LLVM_CONFIG_LIB_COMPONENTS))
+  ifeq ($(shell $(LLVM_CONFIG) --shared-mode),static)
+    LIBS += $(shell $(LLVM_CONFIG) --system-libs $(LLVM_CONFIG_LIB_COMPONENTS))
+    LIBS += -lstdc++
+  endif
   LDFLAGS += $(shell $(LLVM_CONFIG) --ldflags)
 else
   # Fall back on libbfd

tools/testing/selftests/bpf/.gitignore

@@ -36,6 +36,7 @@ test_cpp
 *.lskel.h
 /no_alu32
 /bpf_gcc
+/host-tools
 /tools
 /runqslower
 /bench

tools/testing/selftests/bpf/DENYLIST.s390x

@@ -14,6 +14,7 @@ cgrp_kfunc                               # JIT does not support calling kernel f
 cgrp_local_storage                       # prog_attach unexpected error: -524                                          (trampoline)
 core_read_macros                         # unknown func bpf_probe_read#4                                               (overlapping)
 d_path                                   # failed to auto-attach program 'prog_stat': -524                             (trampoline)
+decap_sanity                             # JIT does not support calling kernel function                                (kfunc)
 deny_namespace                           # failed to attach: ERROR: strerror_r(-524)=22                                (trampoline)
 dummy_st_ops                             # test_run unexpected error: -524 (errno 524)                                 (trampoline)
 fentry_fexit                             # fentry attach failed: -524                                                  (trampoline)

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

@@ -0,0 +1,85 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */
+
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <net/if.h>
+#include <linux/in6.h>
+
+#include "test_progs.h"
+#include "network_helpers.h"
+#include "decap_sanity.skel.h"
+
+#define SYS(fmt, ...)						\
+	({							\
+		char cmd[1024];					\
+		snprintf(cmd, sizeof(cmd), fmt, ##__VA_ARGS__);	\
+		if (!ASSERT_OK(system(cmd), cmd))		\
+			goto fail;				\
+	})
+
+#define NS_TEST "decap_sanity_ns"
+#define IPV6_IFACE_ADDR "face::1"
+#define UDP_TEST_PORT 7777
+
+void test_decap_sanity(void)
+{
+	LIBBPF_OPTS(bpf_tc_hook, qdisc_hook, .attach_point = BPF_TC_EGRESS);
+	LIBBPF_OPTS(bpf_tc_opts, tc_attach);
+	struct nstoken *nstoken = NULL;
+	struct decap_sanity *skel;
+	struct sockaddr_in6 addr;
+	socklen_t addrlen;
+	char buf[128] = {};
+	int sockfd, err;
+
+	skel = decap_sanity__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel open_and_load"))
+		return;
+
+	SYS("ip netns add %s", NS_TEST);
+	SYS("ip -net %s -6 addr add %s/128 dev lo nodad", NS_TEST, IPV6_IFACE_ADDR);
+	SYS("ip -net %s link set dev lo up", NS_TEST);
+
+	nstoken = open_netns(NS_TEST);
+	if (!ASSERT_OK_PTR(nstoken, "open_netns"))
+		goto fail;
+
+	qdisc_hook.ifindex = if_nametoindex("lo");
+	if (!ASSERT_GT(qdisc_hook.ifindex, 0, "if_nametoindex lo"))
+		goto fail;
+
+	err = bpf_tc_hook_create(&qdisc_hook);
+	if (!ASSERT_OK(err, "create qdisc hook"))
+		goto fail;
+
+	tc_attach.prog_fd = bpf_program__fd(skel->progs.decap_sanity);
+	err = bpf_tc_attach(&qdisc_hook, &tc_attach);
+	if (!ASSERT_OK(err, "attach filter"))
+		goto fail;
+
+	addrlen = sizeof(addr);
+	err = make_sockaddr(AF_INET6, IPV6_IFACE_ADDR, UDP_TEST_PORT,
+			    (void *)&addr, &addrlen);
+	if (!ASSERT_OK(err, "make_sockaddr"))
+		goto fail;
+	sockfd = socket(AF_INET6, SOCK_DGRAM, 0);
+	if (!ASSERT_NEQ(sockfd, -1, "socket"))
+		goto fail;
+	err = sendto(sockfd, buf, sizeof(buf), 0, (void *)&addr, addrlen);
+	close(sockfd);
+	if (!ASSERT_EQ(err, sizeof(buf), "send"))
+		goto fail;
+
+	ASSERT_TRUE(skel->bss->init_csum_partial, "init_csum_partial");
+	ASSERT_TRUE(skel->bss->final_csum_none, "final_csum_none");
+	ASSERT_FALSE(skel->bss->broken_csum_start, "broken_csum_start");
+
+fail:
+	if (nstoken) {
+		bpf_tc_hook_destroy(&qdisc_hook);
+		close_netns(nstoken);
+	}
+	system("ip netns del " NS_TEST " >& /dev/null");
+	decap_sanity__destroy(skel);
+}

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

@@ -0,0 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <test_progs.h>
+#include "jeq_infer_not_null_fail.skel.h"
+
+void test_jeq_infer_not_null(void)
+{
+	RUN_TESTS(jeq_infer_not_null_fail);
+}

tools/testing/selftests/bpf/progs/bpf_tracing_net.h

@@ -50,6 +50,12 @@
 #define ICSK_TIME_LOSS_PROBE	5
 #define ICSK_TIME_REO_TIMEOUT	6
 
+#define ETH_HLEN		14
+#define ETH_P_IPV6		0x86DD
+
+#define CHECKSUM_NONE		0
+#define CHECKSUM_PARTIAL	3
+
 #define IFNAMSIZ		16
 
 #define RTF_GATEWAY		0x0002

tools/testing/selftests/bpf/progs/decap_sanity.c

@@ -0,0 +1,68 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */
+
+#include "vmlinux.h"
+#include "bpf_tracing_net.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+
+#define UDP_TEST_PORT 7777
+
+void *bpf_cast_to_kern_ctx(void *) __ksym;
+bool init_csum_partial = false;
+bool final_csum_none = false;
+bool broken_csum_start = false;
+
+static unsigned int skb_headlen(const struct sk_buff *skb)
+{
+	return skb->len - skb->data_len;
+}
+
+static unsigned int skb_headroom(const struct sk_buff *skb)
+{
+	return skb->data - skb->head;
+}
+
+static int skb_checksum_start_offset(const struct sk_buff *skb)
+{
+	return skb->csum_start - skb_headroom(skb);
+}
+
+SEC("tc")
+int decap_sanity(struct __sk_buff *skb)
+{
+	struct sk_buff *kskb;
+	struct ipv6hdr ip6h;
+	struct udphdr udph;
+	int err;
+
+	if (skb->protocol != __bpf_constant_htons(ETH_P_IPV6))
+		return TC_ACT_SHOT;
+
+	if (bpf_skb_load_bytes(skb, ETH_HLEN, &ip6h, sizeof(ip6h)))
+		return TC_ACT_SHOT;
+
+	if (ip6h.nexthdr != IPPROTO_UDP)
+		return TC_ACT_SHOT;
+
+	if (bpf_skb_load_bytes(skb, ETH_HLEN + sizeof(ip6h), &udph, sizeof(udph)))
+		return TC_ACT_SHOT;
+
+	if (udph.dest != __bpf_constant_htons(UDP_TEST_PORT))
+		return TC_ACT_SHOT;
+
+	kskb = bpf_cast_to_kern_ctx(skb);
+	init_csum_partial = (kskb->ip_summed == CHECKSUM_PARTIAL);
+	err = bpf_skb_adjust_room(skb, -(s32)(ETH_HLEN + sizeof(ip6h) + sizeof(udph)),
+				  1, BPF_F_ADJ_ROOM_FIXED_GSO);
+	if (err)
+		return TC_ACT_SHOT;
+	final_csum_none = (kskb->ip_summed == CHECKSUM_NONE);
+	if (kskb->ip_summed == CHECKSUM_PARTIAL &&
+	    (unsigned int)skb_checksum_start_offset(kskb) >= skb_headlen(kskb))
+		broken_csum_start = true;
+
+	return TC_ACT_SHOT;
+}
+
+char __license[] SEC("license") = "GPL";

tools/testing/selftests/bpf/progs/jeq_infer_not_null_fail.c

@@ -0,0 +1,42 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 1);
+	__type(key, u64);
+	__type(value, u64);
+} m_hash SEC(".maps");
+
+SEC("?raw_tp")
+__failure __msg("R8 invalid mem access 'map_value_or_null")
+int jeq_infer_not_null_ptr_to_btfid(void *ctx)
+{
+	struct bpf_map *map = (struct bpf_map *)&m_hash;
+	struct bpf_map *inner_map = map->inner_map_meta;
+	u64 key = 0, ret = 0, *val;
+
+	val = bpf_map_lookup_elem(map, &key);
+	/* Do not mark ptr as non-null if one of them is
+	 * PTR_TO_BTF_ID (R9), reject because of invalid
+	 * access to map value (R8).
+	 *
+	 * Here, we need to inline those insns to access
+	 * R8 directly, since compiler may use other reg
+	 * once it figures out val==inner_map.
+	 */
+	asm volatile("r8 = %[val];\n"
+		     "r9 = %[inner_map];\n"
+		     "if r8 != r9 goto +1;\n"
+		     "%[ret] = *(u64 *)(r8 +0);\n"
+		     : [ret] "+r"(ret)
+		     : [inner_map] "r"(inner_map), [val] "r"(val)
+		     : "r8", "r9");
+
+	return ret;
+}