libvmbase: Separate aarch64 asm files

Separate aarch64 assembly files to architecture specific directory.
This commit add new directory `asm` that should contain only entry assembly code separate per CPU architecture.


Bug: 362733888
Test: m {libvmbase,pvmfw}

Change-Id: Ie7f9d29c2c718eab0040e2ed7b5520c3d6b8cc09
diff --git a/libs/libvmbase/asm/aarch64/entry.S b/libs/libvmbase/asm/aarch64/entry.S
new file mode 100644
index 0000000..6dffbab
--- /dev/null
+++ b/libs/libvmbase/asm/aarch64/entry.S
@@ -0,0 +1,176 @@
+/*
+ * Copyright 2022 The Android Open Source Project
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *     https://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+#include "common.h"
+
+.set .L_MAIR_DEV_nGnRE,	0x04
+.set .L_MAIR_MEM_WBWA,	0xff
+.set .Lmairval, .L_MAIR_DEV_nGnRE | (.L_MAIR_MEM_WBWA << 8)
+
+/* 4 KiB granule size for TTBR0_EL1. */
+.set .L_TCR_TG0_4KB, 0x0 << 14
+/* 4 KiB granule size for TTBR1_EL1. */
+.set .L_TCR_TG1_4KB, 0x2 << 30
+/* Disable translation table walk for TTBR1_EL1, generating a translation fault instead. */
+.set .L_TCR_EPD1, 0x1 << 23
+/* Translation table walks for TTBR0_EL1 are inner sharable. */
+.set .L_TCR_SH_INNER, 0x3 << 12
+/*
+ * Translation table walks for TTBR0_EL1 are outer write-back read-allocate write-allocate
+ * cacheable.
+ */
+.set .L_TCR_RGN_OWB, 0x1 << 10
+/*
+ * Translation table walks for TTBR0_EL1 are inner write-back read-allocate write-allocate
+ * cacheable.
+ */
+.set .L_TCR_RGN_IWB, 0x1 << 8
+/* Size offset for TTBR0_EL1 is 2**39 bytes (512 GiB). */
+.set .L_TCR_T0SZ_512, 64 - 39
+.set .Ltcrval, .L_TCR_TG0_4KB | .L_TCR_TG1_4KB | .L_TCR_EPD1 | .L_TCR_RGN_OWB
+.set .Ltcrval, .Ltcrval | .L_TCR_RGN_IWB | .L_TCR_SH_INNER | .L_TCR_T0SZ_512
+
+/* Stage 1 instruction access cacheability is unaffected. */
+.set .L_SCTLR_ELx_I, 0x1 << 12
+/* SP alignment fault if SP is not aligned to a 16 byte boundary. */
+.set .L_SCTLR_ELx_SA, 0x1 << 3
+/* Stage 1 data access cacheability is unaffected. */
+.set .L_SCTLR_ELx_C, 0x1 << 2
+/* EL0 and EL1 stage 1 MMU enabled. */
+.set .L_SCTLR_ELx_M, 0x1 << 0
+/* Privileged Access Never is unchanged on taking an exception to EL1. */
+.set .L_SCTLR_EL1_SPAN, 0x1 << 23
+/* All writable memory regions are treated as XN. */
+.set .L_SCTLR_EL1_WXN, 0x1 << 19
+/* SETEND instruction disabled at EL0 in aarch32 mode. */
+.set .L_SCTLR_EL1_SED, 0x1 << 8
+/* Various IT instructions are disabled at EL0 in aarch32 mode. */
+.set .L_SCTLR_EL1_ITD, 0x1 << 7
+.set .L_SCTLR_EL1_RES1, (0x1 << 11) | (0x1 << 20) | (0x1 << 22) | (0x1 << 28) | (0x1 << 29)
+.set .Lsctlrval, .L_SCTLR_ELx_M | .L_SCTLR_ELx_C | .L_SCTLR_ELx_SA | .L_SCTLR_EL1_ITD | .L_SCTLR_EL1_SED
+.set .Lsctlrval, .Lsctlrval | .L_SCTLR_ELx_I | .L_SCTLR_EL1_SPAN | .L_SCTLR_EL1_RES1 | .L_SCTLR_EL1_WXN
+
+/**
+ * This is a generic entry point for an image. It carries out the operations required to prepare the
+ * loaded image to be run. Specifically, it zeroes the bss section using registers x25 and above,
+ * prepares the stack, enables floating point, and sets up the exception vector. It preserves x0-x3
+ * for the Rust entry point, as these may contain boot parameters.
+ */
+.section .init.entry, "ax"
+.global entry
+entry:
+	/* Load and apply the memory management configuration, ready to enable MMU and caches. */
+
+	adr x30, vector_table_panic
+	msr vbar_el1, x30
+
+	/*
+	 * Our load address is set by the host so validate it before proceeding.
+	 */
+	adr x30, entry
+	mov_i x29, entry
+	cmp x29, x30
+	b.eq 1f
+	reset_or_hang
+1:
+
+	adrp x30, idmap
+	msr ttbr0_el1, x30
+
+	mov_i x30, .Lmairval
+	msr mair_el1, x30
+
+	mov_i x30, .Ltcrval
+	/* Copy the supported PA range into TCR_EL1.IPS. */
+	mrs x29, id_aa64mmfr0_el1
+	bfi x30, x29, #32, #4
+
+	msr tcr_el1, x30
+
+	mov_i x30, .Lsctlrval
+
+	/*
+	 * Ensure everything before this point has completed, then invalidate any potentially stale
+	 * local TLB entries before they start being used.
+	 */
+	isb
+	tlbi vmalle1
+	ic iallu
+	dsb nsh
+	isb
+
+	/*
+	 * Configure sctlr_el1 to enable MMU and cache and don't proceed until this has completed.
+	 */
+	msr sctlr_el1, x30
+	isb
+
+	/* Disable trapping floating point access in EL1. */
+	mrs x30, cpacr_el1
+	orr x30, x30, #(0x3 << 20)
+	msr cpacr_el1, x30
+	isb
+
+	/* Zero out the bss section. */
+	adr_l x29, bss_begin
+	adr_l x30, bss_end
+0:	cmp x29, x30
+	b.hs 1f
+	stp xzr, xzr, [x29], #16
+	b 0b
+
+1:	/* Copy the data section. */
+	adr_l x28, data_begin
+	adr_l x29, data_end
+	adr_l x30, data_lma
+2:	cmp x28, x29
+	b.ge 3f
+	ldp q0, q1, [x30], #32
+	stp q0, q1, [x28], #32
+	b 2b
+
+3:	/* Prepare the exception handler stack (SP_EL1). */
+	adr_l x30, init_eh_stack_pointer
+	msr spsel, #1
+	mov sp, x30
+
+	/* Prepare the main thread stack (SP_EL0). */
+	adr_l x30, init_stack_pointer
+	msr spsel, #0
+	mov sp, x30
+
+	/* Set up exception vector. */
+	adr x30, vector_table_el1
+	msr vbar_el1, x30
+
+	/*
+	 * Set up Bionic-compatible thread-local storage.
+	 *
+	 * Note that TPIDR_EL0 can't be configured from rust_entry because the
+	 * compiler will dereference it during function entry to access
+	 * __stack_chk_guard and Rust doesn't support LLVM's
+	 * __attribute__((no_stack_protector)).
+	 */
+	adr_l x30, __bionic_tls
+	msr tpidr_el0, x30
+
+	/* Call into Rust code. */
+	bl rust_entry
+
+	/* Loop forever waiting for interrupts. */
+4:	wfi
+	b 4b
+