arm64: avoid dynamic relocations in early boot code

Before implementing KASLR for arm64 by building a self-relocating PIE
executable, we have to ensure that values we use before the relocation
routine is executed are not subject to dynamic relocation themselves.
This applies not only to virtual addresses, but also to values that are
supplied by the linker at build time and relocated using R_AARCH64_ABS64
relocations.

So instead, use assemble time constants, or force the use of static
relocations by folding the constants into the instructions.

Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>

arch/arm64/kernel/efi-entry.S

@@ -61,7 +61,7 @@ ENTRY(entry)
 	 */
 	mov	x20, x0		// DTB address
 	ldr	x0, [sp, #16]	// relocated _text address
-	ldr	x21, =stext_offset
+	movz	x21, #:abs_g0:stext_offset
 	add	x21, x0, x21
 
 	/*

arch/arm64/kernel/head.S

@@ -67,12 +67,11 @@
  * in the entry routines.
  */
 	__HEAD
-
+_head:
 	/*
 	 * DO NOT MODIFY. Image header expected by Linux boot-loaders.
 	 */
 #ifdef CONFIG_EFI
-efi_head:
 	/*
 	 * This add instruction has no meaningful effect except that
 	 * its opcode forms the magic "MZ" signature required by UEFI.
@@ -94,14 +93,14 @@ efi_head:
 	.byte	0x4d
 	.byte	0x64
 #ifdef CONFIG_EFI
-	.long	pe_header - efi_head		// Offset to the PE header.
+	.long	pe_header - _head		// Offset to the PE header.
 #else
 	.word	0				// reserved
 #endif
 
 #ifdef CONFIG_EFI
 	.globl	__efistub_stext_offset
-	.set	__efistub_stext_offset, stext - efi_head
+	.set	__efistub_stext_offset, stext - _head
 	.align 3
 pe_header:
 	.ascii	"PE"
@@ -124,7 +123,7 @@ optional_header:
 	.long	_end - stext			// SizeOfCode
 	.long	0				// SizeOfInitializedData
 	.long	0				// SizeOfUninitializedData
-	.long	__efistub_entry - efi_head	// AddressOfEntryPoint
+	.long	__efistub_entry - _head		// AddressOfEntryPoint
 	.long	__efistub_stext_offset		// BaseOfCode
 
 extra_header_fields:
@@ -139,7 +138,7 @@ extra_header_fields:
 	.short	0				// MinorSubsystemVersion
 	.long	0				// Win32VersionValue
 
-	.long	_end - efi_head			// SizeOfImage
+	.long	_end - _head			// SizeOfImage
 
 	// Everything before the kernel image is considered part of the header
 	.long	__efistub_stext_offset		// SizeOfHeaders
@@ -219,11 +218,13 @@ ENTRY(stext)
 	 * On return, the CPU will be ready for the MMU to be turned on and
 	 * the TCR will have been set.
 	 */
-	ldr	x27, =__mmap_switched		// address to jump to after
+	ldr	x27, 0f				// address to jump to after
 						// MMU has been enabled
 	adr_l	lr, __enable_mmu		// return (PIC) address
 	b	__cpu_setup			// initialise processor
 ENDPROC(stext)
+	.align	3
+0:	.quad	__mmap_switched - (_head - TEXT_OFFSET) + KIMAGE_VADDR
 
 /*
  * Preserve the arguments passed by the bootloader in x0 .. x3
@@ -391,7 +392,8 @@ __create_page_tables:
 	mov	x0, x26				// swapper_pg_dir
 	ldr	x5, =KIMAGE_VADDR
 	create_pgd_entry x0, x5, x3, x6
-	ldr	x6, =KERNEL_END			// __va(KERNEL_END)
+	ldr	w6, kernel_img_size
+	add	x6, x6, x5
 	mov	x3, x24				// phys offset
 	create_block_map x0, x7, x3, x5, x6
 
@@ -408,6 +410,9 @@ __create_page_tables:
 	mov	lr, x27
 	ret
 ENDPROC(__create_page_tables)
+
+kernel_img_size:
+	.long	_end - (_head - TEXT_OFFSET)
 	.ltorg
 
 /*
@@ -415,6 +420,10 @@ ENDPROC(__create_page_tables)
  */
 	.set	initial_sp, init_thread_union + THREAD_START_SP
 __mmap_switched:
+	adr_l	x8, vectors			// load VBAR_EL1 with virtual
+	msr	vbar_el1, x8			// vector table address
+	isb
+
 	// Clear BSS
 	adr_l	x0, __bss_start
 	mov	x1, xzr
@@ -610,13 +619,19 @@ ENTRY(secondary_startup)
 	adrp	x26, swapper_pg_dir
 	bl	__cpu_setup			// initialise processor
 
-	ldr	x21, =secondary_data
-	ldr	x27, =__secondary_switched	// address to jump to after enabling the MMU
+	ldr	x8, =KIMAGE_VADDR
+	ldr	w9, 0f
+	sub	x27, x8, w9, sxtw		// address to jump to after enabling the MMU
 	b	__enable_mmu
 ENDPROC(secondary_startup)
+0:	.long	(_text - TEXT_OFFSET) - __secondary_switched
 
 ENTRY(__secondary_switched)
-	ldr	x0, [x21]			// get secondary_data.stack
+	adr_l	x5, vectors
+	msr	vbar_el1, x5
+	isb
+
+	ldr_l	x0, secondary_data		// get secondary_data.stack
 	mov	sp, x0
 	and	x0, x0, #~(THREAD_SIZE - 1)
 	msr	sp_el0, x0			// save thread_info
@@ -641,8 +656,6 @@ __enable_mmu:
 	ubfx	x2, x1, #ID_AA64MMFR0_TGRAN_SHIFT, 4
 	cmp	x2, #ID_AA64MMFR0_TGRAN_SUPPORTED
 	b.ne	__no_granule_support
-	ldr	x5, =vectors
-	msr	vbar_el1, x5
 	msr	ttbr0_el1, x25			// load TTBR0
 	msr	ttbr1_el1, x26			// load TTBR1
 	isb