x86/fgraph,bpf: Fix ORC stack unwind from return probe

arch/x86/events/core.c

@@ -2789,13 +2789,13 @@ perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *re
 		return;
 	}
 
-	if (perf_callchain_store(entry, regs->ip))
-		return;
-
-	if (perf_hw_regs(regs))
+	if (perf_hw_regs(regs)) {
+		if (perf_callchain_store(entry, regs->ip))
+			return;
 		unwind_start(&state, current, regs, NULL);
-	else
+	} else {
 		unwind_start(&state, current, NULL, (void *)regs->sp);
+	}
 
 	for (; !unwind_done(&state); unwind_next_frame(&state)) {
 		addr = unwind_get_return_address(&state);

arch/x86/include/asm/ftrace.h

@@ -56,6 +56,11 @@ arch_ftrace_get_regs(struct ftrace_regs *fregs)
 	return &arch_ftrace_regs(fregs)->regs;
 }
 
+#define arch_ftrace_partial_regs(regs) do {	\
+	regs->flags &= ~X86_EFLAGS_FIXED;	\
+	regs->cs = __KERNEL_CS;			\
+} while (0)
+
 #define arch_ftrace_fill_perf_regs(fregs, _regs) do {	\
 		(_regs)->ip = arch_ftrace_regs(fregs)->regs.ip;		\
 		(_regs)->sp = arch_ftrace_regs(fregs)->regs.sp;		\

arch/x86/kernel/ftrace_64.S

@@ -354,12 +354,17 @@ SYM_CODE_START(return_to_handler)
 	UNWIND_HINT_UNDEFINED
 	ANNOTATE_NOENDBR
 
+	/* Restore return_to_handler value that got eaten by previous ret instruction. */
+	subq $8, %rsp
+	UNWIND_HINT_FUNC
+
 	/* Save ftrace_regs for function exit context  */
 	subq $(FRAME_SIZE), %rsp
 
 	movq %rax, RAX(%rsp)
 	movq %rdx, RDX(%rsp)
 	movq %rbp, RBP(%rsp)
+	movq %rsp, RSP(%rsp)
 	movq %rsp, %rdi
 
 	call ftrace_return_to_handler
@@ -368,7 +373,8 @@ SYM_CODE_START(return_to_handler)
 	movq RDX(%rsp), %rdx
 	movq RAX(%rsp), %rax
 
-	addq $(FRAME_SIZE), %rsp
+	addq $(FRAME_SIZE) + 8, %rsp
+
 	/*
 	 * Jump back to the old return address. This cannot be JMP_NOSPEC rdi
 	 * since IBT would demand that contain ENDBR, which simply isn't so for

include/linux/ftrace.h

@@ -193,6 +193,10 @@ static __always_inline struct pt_regs *ftrace_get_regs(struct ftrace_regs *fregs
 #if !defined(CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS) || \
 	defined(CONFIG_HAVE_FTRACE_REGS_HAVING_PT_REGS)
 
+#ifndef arch_ftrace_partial_regs
+#define arch_ftrace_partial_regs(regs) do {} while (0)
+#endif
+
 static __always_inline struct pt_regs *
 ftrace_partial_regs(struct ftrace_regs *fregs, struct pt_regs *regs)
 {
@@ -202,7 +206,11 @@ ftrace_partial_regs(struct ftrace_regs *fregs, struct pt_regs *regs)
 	 * Since arch_ftrace_get_regs() will check some members and may return
 	 * NULL, we can not use it.
 	 */
-	return &arch_ftrace_regs(fregs)->regs;
+	regs = &arch_ftrace_regs(fregs)->regs;
+
+	/* Allow arch specific updates to regs. */
+	arch_ftrace_partial_regs(regs);
+	return regs;
 }
 
 #endif /* !CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS || CONFIG_HAVE_FTRACE_REGS_HAVING_PT_REGS */

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

@@ -0,0 +1,150 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+#include "stacktrace_ips.skel.h"
+
+#ifdef __x86_64__
+static int check_stacktrace_ips(int fd, __u32 key, int cnt, ...)
+{
+	__u64 ips[PERF_MAX_STACK_DEPTH];
+	struct ksyms *ksyms = NULL;
+	int i, err = 0;
+	va_list args;
+
+	/* sorted by addr */
+	ksyms = load_kallsyms_local();
+	if (!ASSERT_OK_PTR(ksyms, "load_kallsyms_local"))
+		return -1;
+
+	/* unlikely, but... */
+	if (!ASSERT_LT(cnt, PERF_MAX_STACK_DEPTH, "check_max"))
+		return -1;
+
+	err = bpf_map_lookup_elem(fd, &key, ips);
+	if (err)
+		goto out;
+
+	/*
+	 * Compare all symbols provided via arguments with stacktrace ips,
+	 * and their related symbol addresses.t
+	 */
+	va_start(args, cnt);
+
+	for (i = 0; i < cnt; i++) {
+		unsigned long val;
+		struct ksym *ksym;
+
+		val = va_arg(args, unsigned long);
+		ksym = ksym_search_local(ksyms, ips[i]);
+		if (!ASSERT_OK_PTR(ksym, "ksym_search_local"))
+			break;
+		ASSERT_EQ(ksym->addr, val, "stack_cmp");
+	}
+
+	va_end(args);
+
+out:
+	free_kallsyms_local(ksyms);
+	return err;
+}
+
+static void test_stacktrace_ips_kprobe_multi(bool retprobe)
+{
+	LIBBPF_OPTS(bpf_kprobe_multi_opts, opts,
+		.retprobe = retprobe
+	);
+	LIBBPF_OPTS(bpf_test_run_opts, topts);
+	struct stacktrace_ips *skel;
+
+	skel = stacktrace_ips__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "stacktrace_ips__open_and_load"))
+		return;
+
+	if (!skel->kconfig->CONFIG_UNWINDER_ORC) {
+		test__skip();
+		goto cleanup;
+	}
+
+	skel->links.kprobe_multi_test = bpf_program__attach_kprobe_multi_opts(
+							skel->progs.kprobe_multi_test,
+							"bpf_testmod_stacktrace_test", &opts);
+	if (!ASSERT_OK_PTR(skel->links.kprobe_multi_test, "bpf_program__attach_kprobe_multi_opts"))
+		goto cleanup;
+
+	trigger_module_test_read(1);
+
+	load_kallsyms();
+
+	check_stacktrace_ips(bpf_map__fd(skel->maps.stackmap), skel->bss->stack_key, 4,
+			     ksym_get_addr("bpf_testmod_stacktrace_test_3"),
+			     ksym_get_addr("bpf_testmod_stacktrace_test_2"),
+			     ksym_get_addr("bpf_testmod_stacktrace_test_1"),
+			     ksym_get_addr("bpf_testmod_test_read"));
+
+cleanup:
+	stacktrace_ips__destroy(skel);
+}
+
+static void test_stacktrace_ips_raw_tp(void)
+{
+	__u32 info_len = sizeof(struct bpf_prog_info);
+	LIBBPF_OPTS(bpf_test_run_opts, topts);
+	struct bpf_prog_info info = {};
+	struct stacktrace_ips *skel;
+	__u64 bpf_prog_ksym = 0;
+	int err;
+
+	skel = stacktrace_ips__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "stacktrace_ips__open_and_load"))
+		return;
+
+	if (!skel->kconfig->CONFIG_UNWINDER_ORC) {
+		test__skip();
+		goto cleanup;
+	}
+
+	skel->links.rawtp_test = bpf_program__attach_raw_tracepoint(
+							skel->progs.rawtp_test,
+							"bpf_testmod_test_read");
+	if (!ASSERT_OK_PTR(skel->links.rawtp_test, "bpf_program__attach_raw_tracepoint"))
+		goto cleanup;
+
+	/* get bpf program address */
+	info.jited_ksyms = ptr_to_u64(&bpf_prog_ksym);
+	info.nr_jited_ksyms = 1;
+	err = bpf_prog_get_info_by_fd(bpf_program__fd(skel->progs.rawtp_test),
+				      &info, &info_len);
+	if (ASSERT_OK(err, "bpf_prog_get_info_by_fd"))
+		goto cleanup;
+
+	trigger_module_test_read(1);
+
+	load_kallsyms();
+
+	check_stacktrace_ips(bpf_map__fd(skel->maps.stackmap), skel->bss->stack_key, 2,
+			     bpf_prog_ksym,
+			     ksym_get_addr("bpf_trace_run2"));
+
+cleanup:
+	stacktrace_ips__destroy(skel);
+}
+
+static void __test_stacktrace_ips(void)
+{
+	if (test__start_subtest("kprobe_multi"))
+		test_stacktrace_ips_kprobe_multi(false);
+	if (test__start_subtest("kretprobe_multi"))
+		test_stacktrace_ips_kprobe_multi(true);
+	if (test__start_subtest("raw_tp"))
+		test_stacktrace_ips_raw_tp();
+}
+#else
+static void __test_stacktrace_ips(void)
+{
+	test__skip();
+}
+#endif
+
+void test_stacktrace_ips(void)
+{
+	__test_stacktrace_ips();
+}

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

@@ -0,0 +1,49 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2018 Facebook
+
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+#ifndef PERF_MAX_STACK_DEPTH
+#define PERF_MAX_STACK_DEPTH         127
+#endif
+
+typedef __u64 stack_trace_t[PERF_MAX_STACK_DEPTH];
+
+struct {
+	__uint(type, BPF_MAP_TYPE_STACK_TRACE);
+	__uint(max_entries, 16384);
+	__type(key, __u32);
+	__type(value, stack_trace_t);
+} stackmap SEC(".maps");
+
+extern bool CONFIG_UNWINDER_ORC __kconfig __weak;
+
+/*
+ * This function is here to have CONFIG_UNWINDER_ORC
+ * used and added to object BTF.
+ */
+int unused(void)
+{
+	return CONFIG_UNWINDER_ORC ? 0 : 1;
+}
+
+__u32 stack_key;
+
+SEC("kprobe.multi")
+int kprobe_multi_test(struct pt_regs *ctx)
+{
+	stack_key = bpf_get_stackid(ctx, &stackmap, 0);
+	return 0;
+}
+
+SEC("raw_tp/bpf_testmod_test_read")
+int rawtp_test(void *ctx)
+{
+	/* Skip ebpf program entry in the stack. */
+	stack_key = bpf_get_stackid(ctx, &stackmap, 0);
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";

tools/testing/selftests/bpf/test_kmods/bpf_testmod.c

@@ -417,6 +417,30 @@ noinline int bpf_testmod_fentry_test11(u64 a, void *b, short c, int d,
 	return a + (long)b + c + d + (long)e + f + g + h + i + j + k;
 }
 
+noinline void bpf_testmod_stacktrace_test(void)
+{
+	/* used for stacktrace test as attach function */
+	asm volatile ("");
+}
+
+noinline void bpf_testmod_stacktrace_test_3(void)
+{
+	bpf_testmod_stacktrace_test();
+	asm volatile ("");
+}
+
+noinline void bpf_testmod_stacktrace_test_2(void)
+{
+	bpf_testmod_stacktrace_test_3();
+	asm volatile ("");
+}
+
+noinline void bpf_testmod_stacktrace_test_1(void)
+{
+	bpf_testmod_stacktrace_test_2();
+	asm volatile ("");
+}
+
 int bpf_testmod_fentry_ok;
 
 noinline ssize_t
@@ -497,6 +521,8 @@ bpf_testmod_test_read(struct file *file, struct kobject *kobj,
 			21, 22, 23, 24, 25, 26) != 231)
 		goto out;
 
+	bpf_testmod_stacktrace_test_1();
+
 	bpf_testmod_fentry_ok = 1;
 out:
 	return -EIO; /* always fail */