Merge branch 'bpf: Implement two type cast kfuncs'

Yonghong Song says:

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

Currenty, a non-tracing bpf program typically has a single 'context' argument
with predefined uapi struct type. Following these uapi struct, user is able
to access other fields defined in uapi header. Inside the kernel, the
user-seen 'context' argument is replaced with 'kernel context' (or 'kctx'
in short) which can access more information than what uapi header provides.
To access other info not in uapi header, people typically do two things:
  (1). extend uapi to access more fields rooted from 'context'.
  (2). use bpf_probe_read_kernl() helper to read particular field based on
    kctx.
Using (1) needs uapi change and using (2) makes code more complex since
direct memory access is not allowed.

There are already a few instances trying to access more information from
kctx:
  . trying to access some fields from perf_event kctx ([1]).
  . trying to access some fields from xdp kctx ([2]).

This patch set tried to allow direct memory access for kctx fields
by introducing bpf_cast_to_kern_ctx() kfunc.

Martin mentioned a use case like type casting below:
  #define skb_shinfo(SKB) ((struct skb_shared_info *)(skb_end_pointer(SKB)))
basically a 'unsigned char *" casted to 'struct skb_shared_info *'. This patch
set tries to support such a use case as well with bpf_rdonly_cast().

For the patch series, Patch 1 added support for a kfunc available to all
prog types. Patch 2 added bpf_cast_to_kern_ctx() kfunc. Patch 3 added
bpf_rdonly_cast() kfunc. Patch 4 added a few positive and negative tests.

  [1] https://lore.kernel.org/bpf/ad15b398-9069-4a0e-48cb-4bb651ec3088@meta.com/
  [2] https://lore.kernel.org/bpf/20221109215242.1279993-1-john.fastabend@gmail.com/

Changelog:
  v3 -> v4:
    - remove unnecessary bpf_ctx_convert.t error checking
    - add and use meta.ret_btf_id instead of meta.arg_constant.value for
      bpf_cast_to_kern_ctx().
    - add PTR_TRUSTED to the return PTR_TO_BTF_ID type for bpf_cast_to_kern_ctx().
  v2 -> v3:
    - rebase on top of bpf-next (for merging conflicts)
    - add the selftest to s390x deny list
  rfcv1 -> v2:
    - break original one kfunc into two.
    - add missing error checks and error logs.
    - adapt to the new conventions in
      https://lore.kernel.org/all/20221118015614.2013203-1-memxor@gmail.com/
      for example, with __ign and __k suffix.
    - added support in fixup_kfunc_call() to replace kfunc calls with a single mov.
====================

Signed-off-by: Alexei Starovoitov <ast@kernel.org>

3 files changed, 198 insertions, 0 deletions

diff --git a/tools/testing/selftests/bpf/DENYLIST.s390x b/tools/testing/selftests/bpf/DENYLIST.s390x
index f70a677b38e5..12cf2159975e 100644
--- a/tools/testing/selftests/bpf/DENYLIST.s390x
+++ b/tools/testing/selftests/bpf/DENYLIST.s390x
@@ -71,6 +71,7 @@ trace_printk                             # trace_printk__load unexpected error:
 trace_vprintk                            # trace_vprintk__open_and_load unexpected error: -9                           (?)
 tracing_struct                           # failed to auto-attach: -524                                                 (trampoline)
 trampoline_count                         # prog 'prog1': failed to attach: ERROR: strerror_r(-524)=22                  (trampoline)
+type_cast                                # JIT does not support calling kernel function
 unpriv_bpf_disabled                      # fentry
 user_ringbuf                             # failed to find kernel BTF type ID of '__s390x_sys_prctl': -3                (?)
 verif_stats                              # trace_vprintk__open_and_load unexpected error: -9                           (?)
diff --git a/tools/testing/selftests/bpf/prog_tests/type_cast.c b/tools/testing/selftests/bpf/prog_tests/type_cast.c
new file mode 100644
index 000000000000..9317d5fa2635
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/type_cast.c
@@ -0,0 +1,114 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */
+#include <test_progs.h>
+#include <network_helpers.h>
+#include "type_cast.skel.h"
+
+static void test_xdp(void)
+{
+	struct type_cast *skel;
+	int err, prog_fd;
+	char buf[128];
+
+	LIBBPF_OPTS(bpf_test_run_opts, topts,
+		.data_in = &pkt_v4,
+		.data_size_in = sizeof(pkt_v4),
+		.data_out = buf,
+		.data_size_out = sizeof(buf),
+		.repeat = 1,
+	);
+
+	skel = type_cast__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		return;
+
+	bpf_program__set_autoload(skel->progs.md_xdp, true);
+	err = type_cast__load(skel);
+	if (!ASSERT_OK(err, "skel_load"))
+		goto out;
+
+	prog_fd = bpf_program__fd(skel->progs.md_xdp);
+	err = bpf_prog_test_run_opts(prog_fd, &topts);
+	ASSERT_OK(err, "test_run");
+	ASSERT_EQ(topts.retval, XDP_PASS, "xdp test_run retval");
+
+	ASSERT_EQ(skel->bss->ifindex, 1, "xdp_md ifindex");
+	ASSERT_EQ(skel->bss->ifindex, skel->bss->ingress_ifindex, "xdp_md ingress_ifindex");
+	ASSERT_STREQ(skel->bss->name, "lo", "xdp_md name");
+	ASSERT_NEQ(skel->bss->inum, 0, "xdp_md inum");
+
+out:
+	type_cast__destroy(skel);
+}
+
+static void test_tc(void)
+{
+	struct type_cast *skel;
+	int err, prog_fd;
+
+	LIBBPF_OPTS(bpf_test_run_opts, topts,
+		.data_in = &pkt_v4,
+		.data_size_in = sizeof(pkt_v4),
+		.repeat = 1,
+	);
+
+	skel = type_cast__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		return;
+
+	bpf_program__set_autoload(skel->progs.md_skb, true);
+	err = type_cast__load(skel);
+	if (!ASSERT_OK(err, "skel_load"))
+		goto out;
+
+	prog_fd = bpf_program__fd(skel->progs.md_skb);
+	err = bpf_prog_test_run_opts(prog_fd, &topts);
+	ASSERT_OK(err, "test_run");
+	ASSERT_EQ(topts.retval, 0, "tc test_run retval");
+
+	ASSERT_EQ(skel->bss->meta_len, 0, "skb meta_len");
+	ASSERT_EQ(skel->bss->frag0_len, 0, "skb frag0_len");
+	ASSERT_NEQ(skel->bss->kskb_len, 0, "skb len");
+	ASSERT_NEQ(skel->bss->kskb2_len, 0, "skb2 len");
+	ASSERT_EQ(skel->bss->kskb_len, skel->bss->kskb2_len, "skb len compare");
+
+out:
+	type_cast__destroy(skel);
+}
+
+static const char * const negative_tests[] = {
+	"untrusted_ptr",
+	"kctx_u64",
+};
+
+static void test_negative(void)
+{
+	struct bpf_program *prog;
+	struct type_cast *skel;
+	int i, err;
+
+	for (i = 0; i < ARRAY_SIZE(negative_tests); i++) {
+		skel = type_cast__open();
+		if (!ASSERT_OK_PTR(skel, "skel_open"))
+			return;
+
+		prog = bpf_object__find_program_by_name(skel->obj, negative_tests[i]);
+		if (!ASSERT_OK_PTR(prog, "bpf_object__find_program_by_name"))
+			goto out;
+		bpf_program__set_autoload(prog, true);
+		err = type_cast__load(skel);
+		ASSERT_ERR(err, "skel_load");
+out:
+		type_cast__destroy(skel);
+	}
+}
+
+void test_type_cast(void)
+{
+	if (test__start_subtest("xdp"))
+		test_xdp();
+	if (test__start_subtest("tc"))
+		test_tc();
+	if (test__start_subtest("negative"))
+		test_negative();
+}
diff --git a/tools/testing/selftests/bpf/progs/type_cast.c b/tools/testing/selftests/bpf/progs/type_cast.c
new file mode 100644
index 000000000000..eb78e6f03129
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/type_cast.c
@@ -0,0 +1,83 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_core_read.h>
+
+struct {
+	__uint(type, BPF_MAP_TYPE_TASK_STORAGE);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, int);
+	__type(value, long);
+} enter_id SEC(".maps");
+
+#define	IFNAMSIZ 16
+
+int ifindex, ingress_ifindex;
+char name[IFNAMSIZ];
+unsigned int inum;
+unsigned int meta_len, frag0_len, kskb_len, kskb2_len;
+
+void *bpf_cast_to_kern_ctx(void *) __ksym;
+void *bpf_rdonly_cast(void *, __u32) __ksym;
+
+SEC("?xdp")
+int md_xdp(struct xdp_md *ctx)
+{
+	struct xdp_buff *kctx = bpf_cast_to_kern_ctx(ctx);
+	struct net_device *dev;
+
+	dev = kctx->rxq->dev;
+	ifindex = dev->ifindex;
+	inum = dev->nd_net.net->ns.inum;
+	__builtin_memcpy(name, dev->name, IFNAMSIZ);
+	ingress_ifindex = ctx->ingress_ifindex;
+	return XDP_PASS;
+}
+
+SEC("?tc")
+int md_skb(struct __sk_buff *skb)
+{
+	struct sk_buff *kskb = bpf_cast_to_kern_ctx(skb);
+	struct skb_shared_info *shared_info;
+	struct sk_buff *kskb2;
+
+	kskb_len = kskb->len;
+
+	/* Simulate the following kernel macro:
+	 *   #define skb_shinfo(SKB) ((struct skb_shared_info *)(skb_end_pointer(SKB)))
+	 */
+	shared_info = bpf_rdonly_cast(kskb->head + kskb->end,
+		bpf_core_type_id_kernel(struct skb_shared_info));
+	meta_len = shared_info->meta_len;
+	frag0_len = shared_info->frag_list->len;
+
+	/* kskb2 should be equal to kskb */
+	kskb2 = bpf_rdonly_cast(kskb, bpf_core_type_id_kernel(struct sk_buff));
+	kskb2_len = kskb2->len;
+	return 0;
+}
+
+SEC("?tp_btf/sys_enter")
+int BPF_PROG(untrusted_ptr, struct pt_regs *regs, long id)
+{
+	struct task_struct *task, *task_dup;
+	long *ptr;
+
+	task = bpf_get_current_task_btf();
+	task_dup = bpf_rdonly_cast(task, bpf_core_type_id_kernel(struct task_struct));
+	(void)bpf_task_storage_get(&enter_id, task_dup, 0, 0);
+	return 0;
+}
+
+SEC("?tracepoint/syscalls/sys_enter_nanosleep")
+int kctx_u64(void *ctx)
+{
+	u64 *kctx = bpf_rdonly_cast(ctx, bpf_core_type_id_kernel(u64));
+
+	(void)kctx;
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";