bpf, arm64: Add JIT support for timed may_goto

When verifier sees a timed may_goto instruction, it emits a call to
arch_bpf_timed_may_goto() with a stack offset in BPF_REG_AX (arm64 r9)
and expects a count value to be returned in the same register. The
verifier doesn't save or restore any registers before emitting this
call.

arch_bpf_timed_may_goto() should act as a trampoline to call
bpf_check_timed_may_goto() with AAPCS64 calling convention.

To support this custom calling convention, implement
arch_bpf_timed_may_goto() in assembly and make sure BPF caller saved
registers are saved and restored, call bpf_check_timed_may_goto with
arm64 calling convention where first argument and return value both are
in x0, then put the result back into BPF_REG_AX before returning.

Signed-off-by: Puranjay Mohan <puranjay@kernel.org>
Acked-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Acked-by: Xu Kuohai <xukuohai@huawei.com>
Link: https://lore.kernel.org/r/20250827113245.52629-2-puranjay@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

arch/arm64/net/Makefile

@@ -2,4 +2,4 @@
 #
 # ARM64 networking code
 #
-obj-$(CONFIG_BPF_JIT) += bpf_jit_comp.o
+obj-$(CONFIG_BPF_JIT) += bpf_jit_comp.o bpf_timed_may_goto.o

arch/arm64/net/bpf_jit_comp.c

@@ -1558,7 +1558,13 @@ emit_cond_jmp:
 		if (ret < 0)
 			return ret;
 		emit_call(func_addr, ctx);
-		emit(A64_MOV(1, r0, A64_R(0)), ctx);
+		/*
+		 * Call to arch_bpf_timed_may_goto() is emitted by the
+		 * verifier and called with custom calling convention with
+		 * first argument and return value in BPF_REG_AX (x9).
+		 */
+		if (func_addr != (u64)arch_bpf_timed_may_goto)
+			emit(A64_MOV(1, r0, A64_R(0)), ctx);
 		break;
 	}
 	/* tail call */
@@ -3038,6 +3044,11 @@ bool bpf_jit_bypass_spec_v4(void)
 	return true;
 }
 
+bool bpf_jit_supports_timed_may_goto(void)
+{
+	return true;
+}
+
 bool bpf_jit_inlines_helper_call(s32 imm)
 {
 	switch (imm) {

arch/arm64/net/bpf_timed_may_goto.S

@@ -0,0 +1,40 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2025 Puranjay Mohan <puranjay@kernel.org> */
+
+#include <linux/linkage.h>
+
+SYM_FUNC_START(arch_bpf_timed_may_goto)
+	/* Allocate stack space and emit frame record */
+	stp     x29, x30, [sp, #-64]!
+	mov     x29, sp
+
+	/* Save BPF registers R0 - R5 (x7, x0-x4)*/
+	stp	x7, x0, [sp, #16]
+	stp	x1, x2, [sp, #32]
+	stp	x3, x4, [sp, #48]
+
+	/*
+	 * Stack depth was passed in BPF_REG_AX (x9), add it to the BPF_FP
+	 * (x25) to get the pointer to count and timestamp and pass it as the
+	 * first argument in x0.
+	 *
+	 * Before generating the call to arch_bpf_timed_may_goto, the verifier
+	 * generates a load instruction using FP, i.e. REG_AX = *(u64 *)(FP -
+	 * stack_off_cnt), so BPF_REG_FP (x25) is always set up by the arm64
+	 * jit in this case.
+	 */
+	add	x0, x9, x25
+	bl	bpf_check_timed_may_goto
+	/* BPF_REG_AX(x9) will be stored into count, so move return value to it. */
+	mov	x9, x0
+
+	/* Restore BPF registers R0 - R5 (x7, x0-x4) */
+	ldp	x7, x0, [sp, #16]
+	ldp	x1, x2, [sp, #32]
+	ldp	x3, x4, [sp, #48]
+
+	/* Restore FP and LR */
+	ldp     x29, x30, [sp], #64
+
+	ret
+SYM_FUNC_END(arch_bpf_timed_may_goto)