bpf, arm64: support exceptions

The prologue generation code has been modified to make the callback
program use the stack of the program marked as exception boundary where
callee-saved registers are already pushed.

As the bpf_throw function never returns, if it clobbers any callee-saved
registers, they would remain clobbered. So, the prologue of the
exception-boundary program is modified to push R23 and R24 as well,
which the callback will then recover in its epilogue.

The Procedure Call Standard for the Arm 64-bit Architecture[1] states
that registers r19 to r28 should be saved by the callee. BPF programs on
ARM64 already save all callee-saved registers except r23 and r24. This
patch adds an instruction in prologue of the  program to save these
two registers and another instruction in the epilogue to recover them.

These extra instructions are only added if bpf_throw() is used. Otherwise
the emitted prologue/epilogue remains unchanged.

[1] https://github.com/ARM-software/abi-aa/blob/main/aapcs64/aapcs64.rst

Signed-off-by: Puranjay Mohan <puranjay12@gmail.com>
Link: https://lore.kernel.org/r/20240201125225.72796-3-puranjay12@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

Author: puranjaymohan

arch/arm64/net/bpf_jit_comp.c

@@ -285,7 +285,8 @@ static bool is_lsi_offset(int offset, int scale)
 /* Tail call offset to jump into */
 #define PROLOGUE_OFFSET (BTI_INSNS + 2 + PAC_INSNS + 8)
 
-static int build_prologue(struct jit_ctx *ctx, bool ebpf_from_cbpf)
+static int build_prologue(struct jit_ctx *ctx, bool ebpf_from_cbpf,
+			  bool is_exception_cb)
 {
 	const struct bpf_prog *prog = ctx->prog;
 	const bool is_main_prog = !bpf_is_subprog(prog);
@@ -333,19 +334,34 @@ static int build_prologue(struct jit_ctx *ctx, bool ebpf_from_cbpf)
 	emit(A64_MOV(1, A64_R(9), A64_LR), ctx);
 	emit(A64_NOP, ctx);
 
-	/* Sign lr */
-	if (IS_ENABLED(CONFIG_ARM64_PTR_AUTH_KERNEL))
-		emit(A64_PACIASP, ctx);
-
-	/* Save FP and LR registers to stay align with ARM64 AAPCS */
-	emit(A64_PUSH(A64_FP, A64_LR, A64_SP), ctx);
-	emit(A64_MOV(1, A64_FP, A64_SP), ctx);
-
-	/* Save callee-saved registers */
-	emit(A64_PUSH(r6, r7, A64_SP), ctx);
-	emit(A64_PUSH(r8, r9, A64_SP), ctx);
-	emit(A64_PUSH(fp, tcc, A64_SP), ctx);
-	emit(A64_PUSH(fpb, A64_R(28), A64_SP), ctx);
+	if (!is_exception_cb) {
+		/* Sign lr */
+		if (IS_ENABLED(CONFIG_ARM64_PTR_AUTH_KERNEL))
+			emit(A64_PACIASP, ctx);
+		/* Save FP and LR registers to stay align with ARM64 AAPCS */
+		emit(A64_PUSH(A64_FP, A64_LR, A64_SP), ctx);
+		emit(A64_MOV(1, A64_FP, A64_SP), ctx);
+
+		/* Save callee-saved registers */
+		emit(A64_PUSH(r6, r7, A64_SP), ctx);
+		emit(A64_PUSH(r8, r9, A64_SP), ctx);
+		emit(A64_PUSH(fp, tcc, A64_SP), ctx);
+		emit(A64_PUSH(fpb, A64_R(28), A64_SP), ctx);
+	} else {
+		/*
+		 * Exception callback receives FP of Main Program as third
+		 * parameter
+		 */
+		emit(A64_MOV(1, A64_FP, A64_R(2)), ctx);
+		/*
+		 * Main Program already pushed the frame record and the
+		 * callee-saved registers. The exception callback will not push
+		 * anything and re-use the main program's stack.
+		 *
+		 * 10 registers are on the stack
+		 */
+		emit(A64_SUB_I(1, A64_SP, A64_FP, 80), ctx);
+	}
 
 	/* Set up BPF prog stack base register */
 	emit(A64_MOV(1, fp, A64_SP), ctx);
@@ -365,6 +381,20 @@ static int build_prologue(struct jit_ctx *ctx, bool ebpf_from_cbpf)
 		emit_bti(A64_BTI_J, ctx);
 	}
 
+	/*
+	 * Program acting as exception boundary should save all ARM64
+	 * Callee-saved registers as the exception callback needs to recover
+	 * all ARM64 Callee-saved registers in its epilogue.
+	 */
+	if (prog->aux->exception_boundary) {
+		/*
+		 * As we are pushing two more registers, BPF_FP should be moved
+		 * 16 bytes
+		 */
+		emit(A64_SUB_I(1, fp, fp, 16), ctx);
+		emit(A64_PUSH(A64_R(23), A64_R(24), A64_SP), ctx);
+	}
+
 	emit(A64_SUB_I(1, fpb, fp, ctx->fpb_offset), ctx);
 
 	/* Stack must be multiples of 16B */
@@ -653,7 +683,7 @@ static void build_plt(struct jit_ctx *ctx)
 		plt->target = (u64)&dummy_tramp;
 }
 
-static void build_epilogue(struct jit_ctx *ctx)
+static void build_epilogue(struct jit_ctx *ctx, bool is_exception_cb)
 {
 	const u8 r0 = bpf2a64[BPF_REG_0];
 	const u8 r6 = bpf2a64[BPF_REG_6];
@@ -666,6 +696,15 @@ static void build_epilogue(struct jit_ctx *ctx)
 	/* We're done with BPF stack */
 	emit(A64_ADD_I(1, A64_SP, A64_SP, ctx->stack_size), ctx);
 
+	/*
+	 * Program acting as exception boundary pushes R23 and R24 in addition
+	 * to BPF callee-saved registers. Exception callback uses the boundary
+	 * program's stack frame, so recover these extra registers in the above
+	 * two cases.
+	 */
+	if (ctx->prog->aux->exception_boundary || is_exception_cb)
+		emit(A64_POP(A64_R(23), A64_R(24), A64_SP), ctx);
+
 	/* Restore x27 and x28 */
 	emit(A64_POP(fpb, A64_R(28), A64_SP), ctx);
 	/* Restore fs (x25) and x26 */
@@ -1575,7 +1614,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	 * BPF line info needs ctx->offset[i] to be the offset of
 	 * instruction[i] in jited image, so build prologue first.
 	 */
-	if (build_prologue(&ctx, was_classic)) {
+	if (build_prologue(&ctx, was_classic, prog->aux->exception_cb)) {
 		prog = orig_prog;
 		goto out_off;
 	}
@@ -1586,7 +1625,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	}
 
 	ctx.epilogue_offset = ctx.idx;
-	build_epilogue(&ctx);
+	build_epilogue(&ctx, prog->aux->exception_cb);
 	build_plt(&ctx);
 
 	extable_align = __alignof__(struct exception_table_entry);
@@ -1614,15 +1653,15 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	ctx.idx = 0;
 	ctx.exentry_idx = 0;
 
-	build_prologue(&ctx, was_classic);
+	build_prologue(&ctx, was_classic, prog->aux->exception_cb);
 
 	if (build_body(&ctx, extra_pass)) {
 		bpf_jit_binary_free(header);
 		prog = orig_prog;
 		goto out_off;
 	}
 
-	build_epilogue(&ctx);
+	build_epilogue(&ctx, prog->aux->exception_cb);
 	build_plt(&ctx);
 
 	/* 3. Extra pass to validate JITed code. */
@@ -2310,3 +2349,13 @@ bool bpf_jit_supports_ptr_xchg(void)
 {
 	return true;
 }
+
+bool bpf_jit_supports_exceptions(void)
+{
+	/* We unwind through both kernel frames starting from within bpf_throw
+	 * call and BPF frames. Therefore we require FP unwinder to be enabled
+	 * to walk kernel frames and reach BPF frames in the stack trace.
+	 * ARM64 kernel is aways compiled with CONFIG_FRAME_POINTER=y
+	 */
+	return true;
+}

tools/testing/selftests/bpf/DENYLIST.aarch64

@@ -1,6 +1,5 @@
 bpf_cookie/multi_kprobe_attach_api               # kprobe_multi_link_api_subtest:FAIL:fentry_raw_skel_load unexpected error: -3
 bpf_cookie/multi_kprobe_link_api                 # kprobe_multi_link_api_subtest:FAIL:fentry_raw_skel_load unexpected error: -3
-exceptions					 # JIT does not support calling kfunc bpf_throw: -524
 fexit_sleep                                      # The test never returns. The remaining tests cannot start.
 kprobe_multi_bench_attach                        # needs CONFIG_FPROBE
 kprobe_multi_test                                # needs CONFIG_FPROBE