[PATCH bpf-next v10 14/24] bpf, x86: Dispatch exception cleanup pads at run time

[Yonghong Song <yonghong.song@linux.dev>]

Add what bpf_unwind() relies on to send each frame of a program to its
landing pad or its epilogue on x86-64:

 - arch_bpf_stack_walk_ra(): the ORC walk, handing out each frame's
   return address, state.ip, and the slot it was read from,
   unwind_get_return_address_ptr(). A BPF frame is unwound through its
   frame pointer, which the JIT always sets up.
 - aux->epilogue_ip: the address of the one epilogue the JIT emits per
   function, at the offset it keeps as ctx->cleanup_addr.
 - Once the image is final, the JIT fills in the native cleanup table.
 - bpf_jit_supports_cleanup_pads() says yes with CONFIG_UNWINDER_ORC, as
   bpf_jit_supports_exceptions() does.

A pad needs no ENDBR: it is only reached as a return address.

Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
---
 arch/x86/net/bpf_jit_comp.c | 36 ++++++++++++++++++++++++++++++++++++
 1 file changed, 36 insertions(+)

diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 083fcd6cf15b..d434871b5a11 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -15,6 +15,7 @@
 #include <linux/memory.h>
 #include <linux/sort.h>
 #include <linux/execmem.h>
+#include <linux/kprobes.h>
 #include <asm/extable.h>
 #include <asm/ftrace.h>
 #include <asm/set_memory.h>
@@ -3279,6 +3280,8 @@ static int do_jit(struct bpf_verifier_env *env, struct bpf_prog *bpf_prog, int *
 			seen_exit = true;
 			/* Update cleanup_addr */
 			ctx->cleanup_addr = proglen;
+			/* Where an unwind sends a frame with no pad. */
+			bpf_prog->aux->epilogue_ip = (u64)image + proglen;
 			if (bpf_prog_was_classic(bpf_prog) &&
 			    !ns_capable_noaudit(&init_user_ns, CAP_SYS_ADMIN)) {
 				if (emit_spectre_bhb_barrier(&prog, ip, bpf_prog))
@@ -4462,6 +4465,13 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_verifier_env *env, struct bpf_pr
 		 */
 		bpf_prog_update_insn_ptrs(prog, addrs, image);
 
+		/*
+		 * Same mapping, consumed by the bpf_unwind() walk:
+		 * turn the cleanup records into native address ranges now
+		 * that the image is final.
+		 */
+		bpf_exc_fill_native_ranges(prog, addrs, image);
+
 		/*
 		 * ctx.prog_offset is used when CFI preambles put code *before*
 		 * the function. See emit_cfi(). For FineIBT specifically this code
@@ -4600,6 +4610,11 @@ bool bpf_jit_supports_exceptions(void)
 	return IS_ENABLED(CONFIG_UNWINDER_ORC);
 }
 
+bool bpf_jit_supports_cleanup_pads(void)
+{
+	return IS_ENABLED(CONFIG_UNWINDER_ORC);
+}
+
 bool bpf_jit_supports_private_stack(void)
 {
 	return true;
@@ -4621,6 +4636,27 @@ void arch_bpf_stack_walk(bool (*consume_fn)(void *cookie, u64 ip, u64 sp, u64 bp
 #endif
 }
 
+notrace void arch_bpf_stack_walk_ra(bool (*consume_fn)(void *cookie, u64 ip, u64 sp, u64 bp,
+							u64 *ra),
+				    void *cookie)
+{
+#if defined(CONFIG_UNWINDER_ORC)
+	struct unwind_state state;
+	unsigned long addr, *ra;
+
+	for (unwind_start(&state, current, NULL, NULL); !unwind_done(&state);
+	     unwind_next_frame(&state)) {
+		addr = state.ip;
+		ra = unwind_get_return_address_ptr(&state);
+		if (!ra)
+			break;
+		if (!consume_fn(cookie, (u64)addr, (u64)state.sp, (u64)state.bp, (u64 *)ra))
+			break;
+	}
+#endif
+}
+NOKPROBE_SYMBOL(arch_bpf_stack_walk_ra);
+
 void bpf_arch_poke_desc_update(struct bpf_jit_poke_descriptor *poke,
 			       struct bpf_prog *new, struct bpf_prog *old)
 {
-- 
2.53.0-Meta