arm64: bpf: make BPF prologue and epilogue align with ARM64 AAPCS

Save and restore FP/LR in BPF prog prologue and epilogue, save SP to FP
in prologue in order to get the correct stack backtrace.

However, ARM64 JIT used FP (x29) as eBPF fp register, FP is subjected to
change during function call so it may cause the BPF prog stack base address
change too.

Use x25 to replace FP as BPF stack base register (fp). Since x25 is callee
saved register, so it will keep intact during function call.
It is initialized in BPF prog prologue when BPF prog is started to run
everytime. Save and restore x25/x26 in BPF prologue and epilogue to keep
them intact for the outside of BPF. Actually, x26 is unnecessary, but SP
requires 16 bytes alignment.

So, the BPF stack layout looks like:

                                 high
         original A64_SP =>   0:+-----+ BPF prologue
                                |FP/LR|
         current A64_FP =>  -16:+-----+
                                | ... | callee saved registers
                                +-----+
                                |     | x25/x26
         BPF fp register => -80:+-----+
                                |     |
                                | ... | BPF prog stack
                                |     |
                                |     |
         current A64_SP =>      +-----+
                                |     |
                                | ... | Function call stack
                                |     |
                                +-----+
                                  low

CC: Zi Shen Lim <zlim.lnx@gmail.com>
CC: Xi Wang <xi.wang@gmail.com>
Signed-off-by: Yang Shi <yang.shi@linaro.org>
Acked-by: Zi Shen Lim <zlim.lnx@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

arch/arm64/net/bpf_jit_comp.c

@@ -50,7 +50,7 @@ static const int bpf2a64[] = {
 	[BPF_REG_8] = A64_R(21),
 	[BPF_REG_9] = A64_R(22),
 	/* read-only frame pointer to access stack */
-	[BPF_REG_FP] = A64_FP,
+	[BPF_REG_FP] = A64_R(25),
 	/* temporary register for internal BPF JIT */
 	[TMP_REG_1] = A64_R(23),
 	[TMP_REG_2] = A64_R(24),
@@ -155,16 +155,47 @@ static void build_prologue(struct jit_ctx *ctx)
 	stack_size += 4; /* extra for skb_copy_bits buffer */
 	stack_size = STACK_ALIGN(stack_size);
 
+	/*
+	 * BPF prog stack layout
+	 *
+	 *                         high
+	 * original A64_SP =>   0:+-----+ BPF prologue
+	 *                        |FP/LR|
+	 * current A64_FP =>  -16:+-----+
+	 *                        | ... | callee saved registers
+	 *                        +-----+
+	 *                        |     | x25/x26
+	 * BPF fp register => -80:+-----+
+	 *                        |     |
+	 *                        | ... | BPF prog stack
+	 *                        |     |
+	 *                        |     |
+	 * current A64_SP =>      +-----+
+	 *                        |     |
+	 *                        | ... | Function call stack
+	 *                        |     |
+	 *                        +-----+
+	 *                          low
+	 *
+	 */
+
+	/* 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 register */
 	emit(A64_PUSH(r6, r7, A64_SP), ctx);
 	emit(A64_PUSH(r8, r9, A64_SP), ctx);
 	if (ctx->tmp_used)
 		emit(A64_PUSH(tmp1, tmp2, A64_SP), ctx);
 
-	/* Set up frame pointer */
+	/* Save fp (x25) and x26. SP requires 16 bytes alignment */
+	emit(A64_PUSH(fp, A64_R(26), A64_SP), ctx);
+
+	/* Set up BPF prog stack base register (x25) */
 	emit(A64_MOV(1, fp, A64_SP), ctx);
 
-	/* Set up BPF stack */
+	/* Set up function call stack */
 	emit(A64_SUB_I(1, A64_SP, A64_SP, stack_size), ctx);
 
 	/* Clear registers A and X */
@@ -190,14 +221,17 @@ static void build_epilogue(struct jit_ctx *ctx)
 	/* We're done with BPF stack */
 	emit(A64_ADD_I(1, A64_SP, A64_SP, stack_size), ctx);
 
+	/* Restore fs (x25) and x26 */
+	emit(A64_POP(fp, A64_R(26), A64_SP), ctx);
+
 	/* Restore callee-saved register */
 	if (ctx->tmp_used)
 		emit(A64_POP(tmp1, tmp2, A64_SP), ctx);
 	emit(A64_POP(r8, r9, A64_SP), ctx);
 	emit(A64_POP(r6, r7, A64_SP), ctx);
 
-	/* Restore frame pointer */
-	emit(A64_MOV(1, fp, A64_SP), ctx);
+	/* Restore FP/LR registers */
+	emit(A64_POP(A64_FP, A64_LR, A64_SP), ctx);
 
 	/* Set return value */
 	emit(A64_MOV(1, A64_R(0), r0), ctx);