diff options
Diffstat (limited to 'arch/arm/boot/compressed/head.S')
| -rw-r--r-- | arch/arm/boot/compressed/head.S | 643 |
1 files changed, 440 insertions, 203 deletions
diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S index 75189f13cf54..9f406e9c0ea6 100644 --- a/arch/arm/boot/compressed/head.S +++ b/arch/arm/boot/compressed/head.S @@ -1,17 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * linux/arch/arm/boot/compressed/head.S * * Copyright (C) 1996-2002 Russell King * Copyright (C) 2004 Hyok S. Choi (MPU support) - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/linkage.h> #include <asm/assembler.h> +#include <asm/v7m.h> + +#include "efi-header.S" + +#ifdef __ARMEB__ +#define OF_DT_MAGIC 0xd00dfeed +#else +#define OF_DT_MAGIC 0xedfe0dd0 +#endif + + AR_CLASS( .arch armv7-a ) + M_CLASS( .arch armv7-m ) - .arch armv7-a /* * Debugging stuff * @@ -24,21 +32,21 @@ #if defined(CONFIG_DEBUG_ICEDCC) #if defined(CONFIG_CPU_V6) || defined(CONFIG_CPU_V6K) || defined(CONFIG_CPU_V7) - .macro loadsp, rb, tmp + .macro loadsp, rb, tmp1, tmp2 .endm - .macro writeb, ch, rb + .macro writeb, ch, rb, tmp mcr p14, 0, \ch, c0, c5, 0 .endm #elif defined(CONFIG_CPU_XSCALE) - .macro loadsp, rb, tmp + .macro loadsp, rb, tmp1, tmp2 .endm - .macro writeb, ch, rb + .macro writeb, ch, rb, tmp mcr p14, 0, \ch, c8, c0, 0 .endm #else - .macro loadsp, rb, tmp + .macro loadsp, rb, tmp1, tmp2 .endm - .macro writeb, ch, rb + .macro writeb, ch, rb, tmp mcr p14, 0, \ch, c1, c0, 0 .endm #endif @@ -47,27 +55,23 @@ #include CONFIG_DEBUG_LL_INCLUDE - .macro writeb, ch, rb + .macro writeb, ch, rb, tmp +#ifdef CONFIG_DEBUG_UART_FLOW_CONTROL + waituartcts \tmp, \rb +#endif + waituarttxrdy \tmp, \rb senduart \ch, \rb + busyuart \tmp, \rb .endm #if defined(CONFIG_ARCH_SA1100) - .macro loadsp, rb, tmp + .macro loadsp, rb, tmp1, tmp2 mov \rb, #0x80000000 @ physical base address -#ifdef CONFIG_DEBUG_LL_SER3 - add \rb, \rb, #0x00050000 @ Ser3 -#else add \rb, \rb, #0x00010000 @ Ser1 -#endif - .endm -#elif defined(CONFIG_ARCH_S3C24XX) - .macro loadsp, rb, tmp - mov \rb, #0x50000000 - add \rb, \rb, #0x4000 * CONFIG_S3C_LOWLEVEL_UART_PORT .endm #else - .macro loadsp, rb, tmp - addruart \rb, \tmp + .macro loadsp, rb, tmp1, tmp2 + addruart \rb, \tmp1, \tmp2 .endm #endif #endif @@ -84,64 +88,148 @@ bl phex .endm - .macro debug_reloc_start + /* + * Debug kernel copy by printing the memory addresses involved + */ + .macro dbgkc, begin, end, cbegin, cend #ifdef DEBUG - kputc #'\n' - kphex r6, 8 /* processor id */ - kputc #':' - kphex r7, 8 /* architecture id */ -#ifdef CONFIG_CPU_CP15 - kputc #':' - mrc p15, 0, r0, c1, c0 - kphex r0, 8 /* control reg */ -#endif - kputc #'\n' - kphex r5, 8 /* decompressed kernel start */ + kputc #'C' + kputc #':' + kputc #'0' + kputc #'x' + kphex \begin, 8 /* Start of compressed kernel */ + kputc #'-' + kputc #'0' + kputc #'x' + kphex \end, 8 /* End of compressed kernel */ kputc #'-' - kphex r9, 8 /* decompressed kernel end */ kputc #'>' - kphex r4, 8 /* kernel execution address */ + kputc #'0' + kputc #'x' + kphex \cbegin, 8 /* Start of kernel copy */ + kputc #'-' + kputc #'0' + kputc #'x' + kphex \cend, 8 /* End of kernel copy */ kputc #'\n' #endif .endm - .macro debug_reloc_end + /* + * Debug print of the final appended DTB location + */ + .macro dbgadtb, begin, size #ifdef DEBUG - kphex r5, 8 /* end of kernel */ + kputc #'D' + kputc #'T' + kputc #'B' + kputc #':' + kputc #'0' + kputc #'x' + kphex \begin, 8 /* Start of appended DTB */ + kputc #' ' + kputc #'(' + kputc #'0' + kputc #'x' + kphex \size, 8 /* Size of appended DTB */ + kputc #')' kputc #'\n' - mov r0, r4 - bl memdump /* dump 256 bytes at start of kernel */ #endif .endm - .section ".start", #alloc, #execinstr + .macro enable_cp15_barriers, reg + mrc p15, 0, \reg, c1, c0, 0 @ read SCTLR + tst \reg, #(1 << 5) @ CP15BEN bit set? + bne .L_\@ + orr \reg, \reg, #(1 << 5) @ CP15 barrier instructions + mcr p15, 0, \reg, c1, c0, 0 @ write SCTLR + ARM( .inst 0xf57ff06f @ v7+ isb ) + THUMB( isb ) +.L_\@: + .endm + + /* + * The kernel build system appends the size of the + * decompressed kernel at the end of the compressed data + * in little-endian form. + */ + .macro get_inflated_image_size, res:req, tmp1:req, tmp2:req + adr \res, .Linflated_image_size_offset + ldr \tmp1, [\res] + add \tmp1, \tmp1, \res @ address of inflated image size + + ldrb \res, [\tmp1] @ get_unaligned_le32 + ldrb \tmp2, [\tmp1, #1] + orr \res, \res, \tmp2, lsl #8 + ldrb \tmp2, [\tmp1, #2] + ldrb \tmp1, [\tmp1, #3] + orr \res, \res, \tmp2, lsl #16 + orr \res, \res, \tmp1, lsl #24 + .endm + + .macro be32tocpu, val, tmp +#ifndef __ARMEB__ + /* convert to little endian */ + rev_l \val, \tmp +#endif + .endm + + .section ".start", "ax" /* * sort out different calling conventions */ .align - .arm @ Always enter in ARM state + /* + * Always enter in ARM state for CPUs that support the ARM ISA. + * As of today (2014) that's exactly the members of the A and R + * classes. + */ + AR_CLASS( .arm ) start: .type start,#function - .rept 7 - mov r0, r0 + /* + * These 7 nops along with the 1 nop immediately below for + * !THUMB2 form 8 nops that make the compressed kernel bootable + * on legacy ARM systems that were assuming the kernel in a.out + * binary format. The boot loaders on these systems would + * jump 32 bytes into the image to skip the a.out header. + * with these 8 nops filling exactly 32 bytes, things still + * work as expected on these legacy systems. Thumb2 mode keeps + * 7 of the nops as it turns out that some boot loaders + * were patching the initial instructions of the kernel, i.e + * had started to exploit this "patch area". + */ + __initial_nops + .rept 5 + __nop .endr - ARM( mov r0, r0 ) - ARM( b 1f ) - THUMB( adr r12, BSYM(1f) ) - THUMB( bx r12 ) - - .word 0x016f2818 @ Magic numbers to help the loader - .word start @ absolute load/run zImage address - .word _edata @ zImage end address - THUMB( .thumb ) +#ifndef CONFIG_THUMB2_KERNEL + __nop +#else + AR_CLASS( sub pc, pc, #3 ) @ A/R: switch to Thumb2 mode + M_CLASS( nop.w ) @ M: already in Thumb2 mode + .thumb +#endif + W(b) 1f + + .word _magic_sig @ Magic numbers to help the loader + .word _magic_start @ absolute load/run zImage address + .word _magic_end @ zImage end address + .word 0x04030201 @ endianness flag + .word 0x45454545 @ another magic number to indicate + .word _magic_table @ additional data table + + __EFI_HEADER 1: - mrs r9, cpsr + ARM_BE8( setend be ) @ go BE8 if compiled for BE8 + AR_CLASS( mrs r9, cpsr ) #ifdef CONFIG_ARM_VIRT_EXT bl __hyp_stub_install @ get into SVC mode, reversibly #endif mov r7, r1 @ save architecture ID mov r8, r2 @ save atags pointer +#ifndef CONFIG_CPU_V7M /* * Booting from Angel - need to enter SVC mode and disable * FIQs/IRQs (numeric definitions from angel arm.h source). @@ -157,6 +245,7 @@ not_angel: safe_svcmode_maskall r0 msr spsr_cxsf, r9 @ Save the CPU boot mode in @ SPSR +#endif /* * Note that some cache flushing and other stuff may * be needed here - is there an Angel SWI call for this? @@ -170,57 +259,86 @@ not_angel: .text #ifdef CONFIG_AUTO_ZRELADDR - @ determine final kernel image address - mov r4, pc - and r4, r4, #0xf8000000 - add r4, r4, #TEXT_OFFSET + /* + * Find the start of physical memory. As we are executing + * without the MMU on, we are in the physical address space. + * We just need to get rid of any offset by aligning the + * address. + * + * This alignment is a balance between the requirements of + * different platforms - we have chosen 128MB to allow + * platforms which align the start of their physical memory + * to 128MB to use this feature, while allowing the zImage + * to be placed within the first 128MB of memory on other + * platforms. Increasing the alignment means we place + * stricter alignment requirements on the start of physical + * memory, but relaxing it means that we break people who + * are already placing their zImage in (eg) the top 64MB + * of this range. + */ + mov r0, pc + and r0, r0, #0xf8000000 +#ifdef CONFIG_USE_OF + adr r1, LC1 +#ifdef CONFIG_ARM_APPENDED_DTB + /* + * Look for an appended DTB. If found, we cannot use it to + * validate the calculated start of physical memory, as its + * memory nodes may need to be augmented by ATAGS stored at + * an offset from the same start of physical memory. + */ + ldr r2, [r1, #4] @ get &_edata + add r2, r2, r1 @ relocate it + ldr r2, [r2] @ get DTB signature + ldr r3, =OF_DT_MAGIC + cmp r2, r3 @ do we have a DTB there? + beq 1f @ if yes, skip validation +#endif /* CONFIG_ARM_APPENDED_DTB */ + + /* + * Make sure we have some stack before calling C code. + * No GOT fixup has occurred yet, but none of the code we're + * about to call uses any global variables. + */ + ldr sp, [r1] @ get stack location + add sp, sp, r1 @ apply relocation + + /* Validate calculated start against passed DTB */ + mov r1, r8 + bl fdt_check_mem_start +1: +#endif /* CONFIG_USE_OF */ + /* Determine final kernel image address. */ + add r4, r0, #TEXT_OFFSET #else ldr r4, =zreladdr #endif /* * Set up a page table only if it won't overwrite ourself. - * That means r4 < pc && r4 - 16k page directory > &_end. + * That means r4 < pc || r4 - 16k page directory > &_end. * Given that r4 > &_end is most unfrequent, we add a rough * additional 1MB of room for a possible appended DTB. */ mov r0, pc cmp r0, r4 - ldrcc r0, LC0+32 + ldrcc r0, .Lheadroom addcc r0, r0, pc cmpcc r4, r0 orrcc r4, r4, #1 @ remember we skipped cache_on blcs cache_on -restart: adr r0, LC0 - ldmia r0, {r1, r2, r3, r6, r10, r11, r12} - ldr sp, [r0, #28] - - /* - * We might be running at a different address. We need - * to fix up various pointers. - */ - sub r0, r0, r1 @ calculate the delta offset - add r6, r6, r0 @ _edata - add r10, r10, r0 @ inflated kernel size location +restart: adr r0, LC1 + ldr sp, [r0] + ldr r6, [r0, #4] + add sp, sp, r0 + add r6, r6, r0 - /* - * The kernel build system appends the size of the - * decompressed kernel at the end of the compressed data - * in little-endian form. - */ - ldrb r9, [r10, #0] - ldrb lr, [r10, #1] - orr r9, r9, lr, lsl #8 - ldrb lr, [r10, #2] - ldrb r10, [r10, #3] - orr r9, r9, lr, lsl #16 - orr r9, r9, r10, lsl #24 + get_inflated_image_size r9, r10, lr #ifndef CONFIG_ZBOOT_ROM /* malloc space is above the relocated stack (64k max) */ - add sp, sp, r0 - add r10, sp, #0x10000 + add r10, sp, #MALLOC_SIZE #else /* * With ZBOOT_ROM the bss/stack is non relocatable, @@ -233,9 +351,6 @@ restart: adr r0, LC0 mov r5, #0 @ init dtb size to 0 #ifdef CONFIG_ARM_APPENDED_DTB /* - * r0 = delta - * r2 = BSS start - * r3 = BSS end * r4 = final kernel address (possibly with LSB set) * r5 = appended dtb size (still unknown) * r6 = _edata @@ -243,8 +358,6 @@ restart: adr r0, LC0 * r8 = atags/device tree pointer * r9 = size of decompressed image * r10 = end of this image, including bss/stack/malloc space if non XIP - * r11 = GOT start - * r12 = GOT end * sp = stack pointer * * if there are device trees (dtb) appended to zImage, advance r10 so that the @@ -252,11 +365,7 @@ restart: adr r0, LC0 */ ldr lr, [r6, #0] -#ifndef __ARMEB__ - ldr r1, =0xedfe0dd0 @ sig is 0xd00dfeed big endian -#else - ldr r1, =0xd00dfeed -#endif + ldr r1, =OF_DT_MAGIC cmp lr, r1 bne dtb_check_done @ not found @@ -265,16 +374,31 @@ restart: adr r0, LC0 * OK... Let's do some funky business here. * If we do have a DTB appended to zImage, and we do have * an ATAG list around, we want the later to be translated - * and folded into the former here. To be on the safe side, - * let's temporarily move the stack away into the malloc - * area. No GOT fixup has occurred yet, but none of the - * code we're about to call uses any global variable. + * and folded into the former here. No GOT fixup has occurred + * yet, but none of the code we're about to call uses any + * global variable. */ - add sp, sp, #0x10000 - stmfd sp!, {r0-r3, ip, lr} + + /* Get the initial DTB size */ + ldr r5, [r6, #4] + be32tocpu r5, r1 + dbgadtb r6, r5 + /* 50% DTB growth should be good enough */ + add r5, r5, r5, lsr #1 + /* preserve 64-bit alignment */ + add r5, r5, #7 + bic r5, r5, #7 + /* clamp to 32KB min and 1MB max */ + cmp r5, #(1 << 15) + movlo r5, #(1 << 15) + cmp r5, #(1 << 20) + movhi r5, #(1 << 20) + /* temporarily relocate the stack past the DTB work space */ + add sp, sp, r5 + mov r0, r8 mov r1, r6 - sub r2, sp, r6 + mov r2, r5 bl atags_to_fdt /* @@ -287,11 +411,10 @@ restart: adr r0, LC0 bic r0, r0, #1 add r0, r0, #0x100 mov r1, r6 - sub r2, sp, r6 + mov r2, r5 bleq atags_to_fdt - ldmfd sp!, {r0-r3, ip, lr} - sub sp, sp, #0x10000 + sub sp, sp, r5 #endif mov r8, r6 @ use the appended device tree @@ -308,15 +431,9 @@ restart: adr r0, LC0 subs r1, r5, r1 addhi r9, r9, r1 - /* Get the dtb's size */ + /* Get the current DTB size */ ldr r5, [r6, #4] -#ifndef __ARMEB__ - /* convert r5 (dtb size) to little endian */ - eor r1, r5, r5, ror #16 - bic r1, r1, #0x00ff0000 - mov r5, r5, ror #8 - eor r5, r5, r1, lsr #8 -#endif + be32tocpu r5, r1 /* preserve 64-bit alignment */ add r5, r5, #7 @@ -373,7 +490,12 @@ dtb_check_done: cmp r0, #HYP_MODE bne 1f - bl __hyp_get_vectors + /* + * Compute the address of the hyp vectors after relocation. + * Call __hyp_set_vectors with the new address so that we + * can HVC again after the copy. + */ + adr_l r0, __hyp_stub_vectors sub r0, r0, r5 add r0, r0, r10 bl __hyp_set_vectors @@ -386,6 +508,20 @@ dtb_check_done: add r6, r9, r5 add r9, r9, r10 +#ifdef DEBUG + sub r10, r6, r5 + sub r10, r9, r10 + /* + * We are about to copy the kernel to a new memory area. + * The boundaries of the new memory area can be found in + * r10 and r9, whilst r5 and r6 contain the boundaries + * of the memory we are going to copy. + * Calling dbgkc will help with the printing of this + * information. + */ + dbgkc r5, r6, r10, r9 +#endif + 1: ldmdb r6!, {r0 - r3, r10 - r12, lr} cmp r6, r5 stmdb r9!, {r0 - r3, r10 - r12, lr} @@ -394,19 +530,19 @@ dtb_check_done: /* Preserve offset to relocated code. */ sub r6, r9, r6 -#ifndef CONFIG_ZBOOT_ROM - /* cache_clean_flush may use the stack, so relocate it */ - add sp, sp, r6 -#endif - - tst r4, #1 - bleq cache_clean_flush + mov r0, r9 @ start of relocated zImage + add r1, sp, r6 @ end of relocated zImage + bl cache_clean_flush - adr r0, BSYM(restart) + badr r0, restart add r0, r0, r6 mov pc, r0 wont_overwrite: + adr r0, LC0 + ldmia r0, {r1, r2, r3, r11, r12} + sub r0, r0, r1 @ calculate the delta offset + /* * If delta is zero, we are running at the address we were linked at. * r0 = delta @@ -493,13 +629,16 @@ not_relocated: mov r0, #0 */ mov r0, r4 mov r1, sp @ malloc space above stack - add r2, sp, #0x10000 @ 64k max + add r2, sp, #MALLOC_SIZE @ 64k max mov r3, r7 bl decompress_kernel + + get_inflated_image_size r1, r2, r3 + + mov r0, r4 @ start of inflated image + add r1, r1, r0 @ end of inflated image bl cache_clean_flush bl cache_off - mov r1, r7 @ restore architecture number - mov r2, r8 @ restore atags pointer #ifdef CONFIG_ARM_VIRT_EXT mrs r0, spsr @ Get saved CPU boot mode @@ -507,17 +646,11 @@ not_relocated: mov r0, #0 cmp r0, #HYP_MODE @ if not booted in HYP mode... bne __enter_kernel @ boot kernel directly - adr r12, .L__hyp_reentry_vectors_offset - ldr r0, [r12] - add r0, r0, r12 - + adr_l r0, __hyp_reentry_vectors bl __hyp_set_vectors __HVC(0) @ otherwise bounce to hyp mode b . @ should never be reached - - .align 2 -.L__hyp_reentry_vectors_offset: .long __hyp_reentry_vectors - . #else b __enter_kernel #endif @@ -527,14 +660,21 @@ not_relocated: mov r0, #0 LC0: .word LC0 @ r1 .word __bss_start @ r2 .word _end @ r3 - .word _edata @ r6 - .word input_data_end - 4 @ r10 (inflated size location) .word _got_start @ r11 .word _got_end @ ip - .word .L_user_stack_end @ sp - .word _end - restart + 16384 + 1024*1024 .size LC0, . - LC0 + .type LC1, #object +LC1: .word .L_user_stack_end - LC1 @ sp + .word _edata - LC1 @ r6 + .size LC1, . - LC1 + +.Lheadroom: + .word _end - restart + 16384 + 1024*1024 + +.Linflated_image_size_offset: + .long (input_data_end - 4) - . + #ifdef CONFIG_ARCH_RPC .globl params params: ldr r0, =0x10000100 @ params_phys for RPC @@ -544,6 +684,24 @@ params: ldr r0, =0x10000100 @ params_phys for RPC #endif /* + * dcache_line_size - get the minimum D-cache line size from the CTR register + * on ARMv7. + */ + .macro dcache_line_size, reg, tmp +#ifdef CONFIG_CPU_V7M + movw \tmp, #:lower16:BASEADDR_V7M_SCB + V7M_SCB_CTR + movt \tmp, #:upper16:BASEADDR_V7M_SCB + V7M_SCB_CTR + ldr \tmp, [\tmp] +#else + mrc p15, 0, \tmp, c0, c0, 1 @ read ctr +#endif + lsr \tmp, \tmp, #16 + and \tmp, \tmp, #0xf @ cache line size encoding + mov \reg, #4 @ bytes per word + mov \reg, \reg, lsl \tmp @ actual cache line size + .endm + +/* * Turn on the cache. We need to setup some page tables so that we * can have both the I and D caches on. * @@ -699,9 +857,7 @@ __armv4_mmu_cache_on: mrc p15, 0, r0, c1, c0, 0 @ read control reg orr r0, r0, #0x5000 @ I-cache enable, RR cache replacement orr r0, r0, #0x0030 -#ifdef CONFIG_CPU_ENDIAN_BE8 - orr r0, r0, #1 << 25 @ big-endian page tables -#endif + ARM_BE8( orr r0, r0, #1 << 25 ) @ big-endian page tables bl __common_mmu_cache_on mov r0, #0 mcr p15, 0, r0, c8, c7, 0 @ flush I,D TLBs @@ -709,6 +865,7 @@ __armv4_mmu_cache_on: mov pc, r12 __armv7_mmu_cache_on: + enable_cp15_barriers r11 mov r12, lr #ifdef CONFIG_MMU mrc p15, 0, r11, c0, c1, 4 @ read ID_MMFR0 @@ -728,14 +885,12 @@ __armv7_mmu_cache_on: orr r0, r0, #1 << 22 @ U (v6 unaligned access model) @ (needed for ARM1176) #ifdef CONFIG_MMU -#ifdef CONFIG_CPU_ENDIAN_BE8 - orr r0, r0, #1 << 25 @ big-endian page tables -#endif + ARM_BE8( orr r0, r0, #1 << 25 ) @ big-endian page tables mrcne p15, 0, r6, c2, c0, 2 @ read ttb control reg orrne r0, r0, #1 @ MMU enabled movne r1, #0xfffffffd @ domain 0 = client bic r6, r6, #1 << 31 @ 32-bit translation system - bic r6, r6, #3 << 0 @ use only ttbr0 + bic r6, r6, #(7 << 0) | (1 << 4) @ use only ttbr0 mcrne p15, 0, r3, c2, c0, 0 @ load page table pointer mcrne p15, 0, r1, c3, c0, 0 @ load domain access control mcrne p15, 0, r6, c2, c0, 2 @ load ttb control @@ -796,6 +951,16 @@ __common_mmu_cache_on: call_cache_fn: adr r12, proc_types #ifdef CONFIG_CPU_CP15 mrc p15, 0, r9, c0, c0 @ get processor ID +#elif defined(CONFIG_CPU_V7M) + /* + * On v7-M the processor id is located in the V7M_SCB_CPUID + * register, but as cache handling is IMPLEMENTATION DEFINED on + * v7-M (if existant at all) we just return early here. + * If V7M_SCB_CPUID were used the cpu ID functions (i.e. + * __armv7_mmu_cache_{on,off,flush}) would be selected which + * use cp15 registers that are not implemented on v7-M. + */ + bx lr #else ldr r9, =CONFIG_PROCESSOR_ID #endif @@ -1023,13 +1188,11 @@ __armv4_mmu_cache_off: __armv7_mmu_cache_off: mrc p15, 0, r0, c1, c0 #ifdef CONFIG_MMU - bic r0, r0, #0x000d + bic r0, r0, #0x0005 #else - bic r0, r0, #0x000c + bic r0, r0, #0x0004 #endif mcr p15, 0, r0, c1, c0 @ turn MMU and cache off - mov r12, lr - bl __armv7_mmu_cache_flush mov r0, #0 #ifdef CONFIG_MMU mcr p15, 0, r0, c8, c7, 0 @ invalidate whole TLB @@ -1037,11 +1200,14 @@ __armv7_mmu_cache_off: mcr p15, 0, r0, c7, c5, 6 @ invalidate BTC mcr p15, 0, r0, c7, c10, 4 @ DSB mcr p15, 0, r0, c7, c5, 4 @ ISB - mov pc, r12 + mov pc, lr /* * Clean and flush the cache to maintain consistency. * + * On entry, + * r0 = start address + * r1 = end address (exclusive) * On exit, * r1, r2, r3, r9, r10, r11, r12 corrupted * This routine must preserve: @@ -1050,9 +1216,12 @@ __armv7_mmu_cache_off: .align 5 cache_clean_flush: mov r3, #16 + mov r11, r1 b call_cache_fn __armv4_mpu_cache_flush: + tst r4, #1 + movne pc, lr mov r2, #1 mov r3, #0 mcr p15, 0, ip, c7, c6, 0 @ invalidate D cache @@ -1070,6 +1239,8 @@ __armv4_mpu_cache_flush: mov pc, lr __fa526_cache_flush: + tst r4, #1 + movne pc, lr mov r1, #0 mcr p15, 0, r1, c7, c14, 0 @ clean and invalidate D cache mcr p15, 0, r1, c7, c5, 0 @ flush I cache @@ -1078,13 +1249,17 @@ __fa526_cache_flush: __armv6_mmu_cache_flush: mov r1, #0 - mcr p15, 0, r1, c7, c14, 0 @ clean+invalidate D + tst r4, #1 + mcreq p15, 0, r1, c7, c14, 0 @ clean+invalidate D mcr p15, 0, r1, c7, c5, 0 @ invalidate I+BTB - mcr p15, 0, r1, c7, c15, 0 @ clean+invalidate unified + mcreq p15, 0, r1, c7, c15, 0 @ clean+invalidate unified mcr p15, 0, r1, c7, c10, 4 @ drain WB mov pc, lr __armv7_mmu_cache_flush: + enable_cp15_barriers r10 + tst r4, #1 + bne iflush mrc p15, 0, r10, c0, c1, 5 @ read ID_MMFR1 tst r10, #0xf << 16 @ hierarchical cache (ARMv7) mov r10, #0 @@ -1092,51 +1267,16 @@ __armv7_mmu_cache_flush: mcr p15, 0, r10, c7, c14, 0 @ clean+invalidate D b iflush hierarchical: - mcr p15, 0, r10, c7, c10, 5 @ DMB - stmfd sp!, {r0-r7, r9-r11} - mrc p15, 1, r0, c0, c0, 1 @ read clidr - ands r3, r0, #0x7000000 @ extract loc from clidr - mov r3, r3, lsr #23 @ left align loc bit field - beq finished @ if loc is 0, then no need to clean - mov r10, #0 @ start clean at cache level 0 -loop1: - add r2, r10, r10, lsr #1 @ work out 3x current cache level - mov r1, r0, lsr r2 @ extract cache type bits from clidr - and r1, r1, #7 @ mask of the bits for current cache only - cmp r1, #2 @ see what cache we have at this level - blt skip @ skip if no cache, or just i-cache - mcr p15, 2, r10, c0, c0, 0 @ select current cache level in cssr - mcr p15, 0, r10, c7, c5, 4 @ isb to sych the new cssr&csidr - mrc p15, 1, r1, c0, c0, 0 @ read the new csidr - and r2, r1, #7 @ extract the length of the cache lines - add r2, r2, #4 @ add 4 (line length offset) - ldr r4, =0x3ff - ands r4, r4, r1, lsr #3 @ find maximum number on the way size - clz r5, r4 @ find bit position of way size increment - ldr r7, =0x7fff - ands r7, r7, r1, lsr #13 @ extract max number of the index size -loop2: - mov r9, r4 @ create working copy of max way size -loop3: - ARM( orr r11, r10, r9, lsl r5 ) @ factor way and cache number into r11 - ARM( orr r11, r11, r7, lsl r2 ) @ factor index number into r11 - THUMB( lsl r6, r9, r5 ) - THUMB( orr r11, r10, r6 ) @ factor way and cache number into r11 - THUMB( lsl r6, r7, r2 ) - THUMB( orr r11, r11, r6 ) @ factor index number into r11 - mcr p15, 0, r11, c7, c14, 2 @ clean & invalidate by set/way - subs r9, r9, #1 @ decrement the way - bge loop3 - subs r7, r7, #1 @ decrement the index - bge loop2 -skip: - add r10, r10, #2 @ increment cache number - cmp r3, r10 - bgt loop1 -finished: - ldmfd sp!, {r0-r7, r9-r11} - mov r10, #0 @ swith back to cache level 0 - mcr p15, 2, r10, c0, c0, 0 @ select current cache level in cssr + dcache_line_size r1, r2 @ r1 := dcache min line size + sub r2, r1, #1 @ r2 := line size mask + bic r0, r0, r2 @ round down start to line size + sub r11, r11, #1 @ end address is exclusive + bic r11, r11, r2 @ round down end to line size +0: cmp r0, r11 @ finished? + bgt iflush + mcr p15, 0, r0, c7, c14, 1 @ Dcache clean/invalidate by VA + add r0, r0, r1 + b 0b iflush: mcr p15, 0, r10, c7, c10, 4 @ DSB mcr p15, 0, r10, c7, c5, 0 @ invalidate I+BTB @@ -1145,13 +1285,17 @@ iflush: mov pc, lr __armv5tej_mmu_cache_flush: -1: mrc p15, 0, r15, c7, c14, 3 @ test,clean,invalidate D cache + tst r4, #1 + movne pc, lr +1: mrc p15, 0, APSR_nzcv, c7, c14, 3 @ test,clean,invalidate D cache bne 1b mcr p15, 0, r0, c7, c5, 0 @ flush I cache mcr p15, 0, r0, c7, c10, 4 @ drain WB mov pc, lr __armv4_mmu_cache_flush: + tst r4, #1 + movne pc, lr mov r2, #64*1024 @ default: 32K dcache size (*2) mov r11, #32 @ default: 32 byte line size mrc p15, 0, r3, c0, c0, 1 @ read cache type @@ -1185,6 +1329,8 @@ no_cache_id: __armv3_mmu_cache_flush: __armv3_mpu_cache_flush: + tst r4, #1 + movne pc, lr mov r1, #0 mcr p15, 0, r1, c7, c0, 0 @ invalidate whole cache v3 mov pc, lr @@ -1215,11 +1361,11 @@ phex: adr r3, phexbuf b 1b @ puts corrupts {r0, r1, r2, r3} -puts: loadsp r3, r1 +puts: loadsp r3, r2, r1 1: ldrb r2, [r0], #1 teq r2, #0 moveq pc, lr -2: writeb r2, r3 +2: writeb r2, r3, r1 mov r1, #0x00020000 3: subs r1, r1, #1 bne 3b @@ -1232,8 +1378,8 @@ puts: loadsp r3, r1 @ putc corrupts {r0, r1, r2, r3} putc: mov r2, r0 + loadsp r3, r1, r0 mov r0, #0 - loadsp r3, r1 b 2b @ memdump corrupts {r0, r1, r2, r3, r10, r11, r12, lr} @@ -1273,7 +1419,11 @@ memdump: mov r12, r0 __hyp_reentry_vectors: W(b) . @ reset W(b) . @ undef +#ifdef CONFIG_EFI_STUB + W(b) __enter_kernel_from_hyp @ hvc from HYP +#else W(b) . @ svc +#endif W(b) . @ pabort W(b) . @ dabort W(b) __enter_kernel @ hyp @@ -1283,11 +1433,98 @@ __hyp_reentry_vectors: __enter_kernel: mov r0, #0 @ must be 0 - ARM( mov pc, r4 ) @ call kernel - THUMB( bx r4 ) @ entry point is always ARM + mov r1, r7 @ restore architecture number + mov r2, r8 @ restore atags pointer + ARM( mov pc, r4 ) @ call kernel + M_CLASS( add r4, r4, #1 ) @ enter in Thumb mode for M class + THUMB( bx r4 ) @ entry point is always ARM for A/R classes reloc_code_end: +#ifdef CONFIG_EFI_STUB +__enter_kernel_from_hyp: + mrc p15, 4, r0, c1, c0, 0 @ read HSCTLR + bic r0, r0, #0x5 @ disable MMU and caches + mcr p15, 4, r0, c1, c0, 0 @ write HSCTLR + isb + b __enter_kernel + +ENTRY(efi_enter_kernel) + mov r4, r0 @ preserve image base + mov r8, r1 @ preserve DT pointer + + adr_l r0, call_cache_fn + adr r1, 0f @ clean the region of code we + bl cache_clean_flush @ may run with the MMU off + +#ifdef CONFIG_ARM_VIRT_EXT + @ + @ The EFI spec does not support booting on ARM in HYP mode, + @ since it mandates that the MMU and caches are on, with all + @ 32-bit addressable DRAM mapped 1:1 using short descriptors. + @ + @ While the EDK2 reference implementation adheres to this, + @ U-Boot might decide to enter the EFI stub in HYP mode + @ anyway, with the MMU and caches either on or off. + @ + mrs r0, cpsr @ get the current mode + msr spsr_cxsf, r0 @ record boot mode + and r0, r0, #MODE_MASK @ are we running in HYP mode? + cmp r0, #HYP_MODE + bne .Lefi_svc + + mrc p15, 4, r1, c1, c0, 0 @ read HSCTLR + tst r1, #0x1 @ MMU enabled at HYP? + beq 1f + + @ + @ When running in HYP mode with the caches on, we're better + @ off just carrying on using the cached 1:1 mapping that the + @ firmware provided. Set up the HYP vectors so HVC instructions + @ issued from HYP mode take us to the correct handler code. We + @ will disable the MMU before jumping to the kernel proper. + @ + ARM( bic r1, r1, #(1 << 30) ) @ clear HSCTLR.TE + THUMB( orr r1, r1, #(1 << 30) ) @ set HSCTLR.TE + mcr p15, 4, r1, c1, c0, 0 + adr r0, __hyp_reentry_vectors + mcr p15, 4, r0, c12, c0, 0 @ set HYP vector base (HVBAR) + isb + b .Lefi_hyp + + @ + @ When running in HYP mode with the caches off, we need to drop + @ into SVC mode now, and let the decompressor set up its cached + @ 1:1 mapping as usual. + @ +1: mov r9, r4 @ preserve image base + bl __hyp_stub_install @ install HYP stub vectors + safe_svcmode_maskall r1 @ drop to SVC mode + msr spsr_cxsf, r0 @ record boot mode + orr r4, r9, #1 @ restore image base and set LSB + b .Lefi_hyp +.Lefi_svc: +#endif + mrc p15, 0, r0, c1, c0, 0 @ read SCTLR + tst r0, #0x1 @ MMU enabled? + orreq r4, r4, #1 @ set LSB if not + +.Lefi_hyp: + mov r0, r8 @ DT start + add r1, r8, r2 @ DT end + bl cache_clean_flush + + adr r0, 0f @ switch to our stack + ldr sp, [r0] + add sp, sp, r0 + + mov r5, #0 @ appended DTB size + mov r7, #0xFFFFFFFF @ machine ID + b wont_overwrite +ENDPROC(efi_enter_kernel) +0: .long .L_user_stack_end - . +#endif + .align .section ".stack", "aw", %nobits .L_user_stack: .space 4096 |