arch/x86: Implement arch_bpf_stack_walk

The plumbing for offline unwinding when we throw an exception in
programs would require walking the stack, hence introduce a new
arch_bpf_stack_walk function. This is provided when the JIT supports
exceptions, i.e. bpf_jit_supports_exceptions is true. The arch-specific
code is really minimal, hence it should be straightforward to extend
this support to other architectures as well, as it reuses the logic of
arch_stack_walk, but allowing access to unwind_state data.

Once the stack pointer and frame pointer are known for the main subprog
during the unwinding, we know the stack layout and location of any
callee-saved registers which must be restored before we return back to
the kernel. This handling will be added in the subsequent patches.

Note that while we primarily unwind through BPF frames, which are
effectively CONFIG_UNWINDER_FRAME_POINTER, we still need one of this or
CONFIG_UNWINDER_ORC to be able to unwind through the bpf_throw frame
from which we begin walking the stack. We also require both sp and bp
(stack and frame pointers) from the unwind_state structure, which are
only available when one of these two options are enabled.
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Link: https://lore.kernel.org/r/20230912233214.1518551-3-memxor@gmail.comSigned-off-by: Alexei Starovoitov <ast@kernel.org>

arch/x86/net/bpf_jit_comp.c

@@ -16,6 +16,7 @@
 #include <asm/set_memory.h>
 #include <asm/nospec-branch.h>
 #include <asm/text-patching.h>
+#include <asm/unwind.h>
 
 static u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len)
 {
@@ -2933,3 +2934,30 @@ void bpf_jit_free(struct bpf_prog *prog)
 
 	bpf_prog_unlock_free(prog);
 }
+
+bool bpf_jit_supports_exceptions(void)
+{
+	/* We unwind through both kernel frames (starting from within bpf_throw
+	 * call) and BPF frames. Therefore we require one of ORC or FP unwinder
+	 * to be enabled to walk kernel frames and reach BPF frames in the stack
+	 * trace.
+	 */
+	return IS_ENABLED(CONFIG_UNWINDER_ORC) || IS_ENABLED(CONFIG_UNWINDER_FRAME_POINTER);
+}
+
+void arch_bpf_stack_walk(bool (*consume_fn)(void *cookie, u64 ip, u64 sp, u64 bp), void *cookie)
+{
+#if defined(CONFIG_UNWINDER_ORC) || defined(CONFIG_UNWINDER_FRAME_POINTER)
+	struct unwind_state state;
+	unsigned long addr;
+
+	for (unwind_start(&state, current, NULL, NULL); !unwind_done(&state);
+	     unwind_next_frame(&state)) {
+		addr = unwind_get_return_address(&state);
+		if (!addr || !consume_fn(cookie, (u64)addr, (u64)state.sp, (u64)state.bp))
+			break;
+	}
+	return;
+#endif
+	WARN(1, "verification of programs using bpf_throw should have failed\n");
+}

include/linux/filter.h

@@ -954,6 +954,8 @@ bool bpf_jit_needs_zext(void);
 bool bpf_jit_supports_subprog_tailcalls(void);
 bool bpf_jit_supports_kfunc_call(void);
 bool bpf_jit_supports_far_kfunc_call(void);
+bool bpf_jit_supports_exceptions(void);
+void arch_bpf_stack_walk(bool (*consume_fn)(void *cookie, u64 ip, u64 sp, u64 bp), void *cookie);
 bool bpf_helper_changes_pkt_data(void *func);
 
 static inline bool bpf_dump_raw_ok(const struct cred *cred)

kernel/bpf/core.c

@@ -2914,6 +2914,15 @@ int __weak bpf_arch_text_invalidate(void *dst, size_t len)
 	return -ENOTSUPP;
 }
 
+bool __weak bpf_jit_supports_exceptions(void)
+{
+	return false;
+}
+
+void __weak arch_bpf_stack_walk(bool (*consume_fn)(void *cookie, u64 ip, u64 sp, u64 bp), void *cookie)
+{
+}
+
 #ifdef CONFIG_BPF_SYSCALL
 static int __init bpf_global_ma_init(void)
 {