diff options
Diffstat (limited to 'arch/arm/boot/compressed/head.S')
| -rw-r--r-- | arch/arm/boot/compressed/head.S | 151 |
1 files changed, 119 insertions, 32 deletions
diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S index b8c64b80baf..3a8b32df6b3 100644 --- a/arch/arm/boot/compressed/head.S +++ b/arch/arm/boot/compressed/head.S @@ -9,7 +9,9 @@ * published by the Free Software Foundation. */ #include <linux/linkage.h> +#include <asm/assembler.h> + .arch armv7-a /* * Debugging stuff * @@ -43,7 +45,7 @@ #else -#include <mach/debug-macro.S> +#include CONFIG_DEBUG_LL_INCLUDE .macro writeb, ch, rb senduart \ch, \rb @@ -58,11 +60,6 @@ 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 @@ -132,10 +129,15 @@ start: .word start @ absolute load/run zImage address .word _edata @ zImage end address THUMB( .thumb ) -1: mov r7, r1 @ save architecture ID +1: + ARM_BE8( setend be ) @ go BE8 if compiled for BE8 + 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 __ARM_ARCH_2__ /* * Booting from Angel - need to enter SVC mode and disable * FIQs/IRQs (numeric definitions from angel arm.h source). @@ -148,13 +150,9 @@ start: ARM( swi 0x123456 ) @ angel_SWI_ARM THUMB( svc 0xab ) @ angel_SWI_THUMB not_angel: - mrs r2, cpsr @ turn off interrupts to - orr r2, r2, #0xc0 @ prevent angel from running - msr cpsr_c, r2 -#else - teqp pc, #0x0c000003 @ turn off interrupts -#endif - + safe_svcmode_maskall r0 + msr spsr_cxsf, r9 @ Save the CPU boot mode in + @ SPSR /* * Note that some cache flushing and other stuff may * be needed here - is there an Angel SWI call for this? @@ -176,7 +174,19 @@ not_angel: ldr r4, =zreladdr #endif - bl cache_on + /* + * Set up a page table only if it won't overwrite ourself. + * 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 + 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} @@ -222,7 +232,7 @@ restart: adr r0, LC0 * r0 = delta * r2 = BSS start * r3 = BSS end - * r4 = final kernel address + * r4 = final kernel address (possibly with LSB set) * r5 = appended dtb size (still unknown) * r6 = _edata * r7 = architecture ID @@ -270,6 +280,7 @@ restart: adr r0, LC0 */ cmp r0, #1 sub r0, r4, #TEXT_OFFSET + bic r0, r0, #1 add r0, r0, #0x100 mov r1, r6 sub r2, sp, r6 @@ -316,12 +327,13 @@ dtb_check_done: /* * Check to see if we will overwrite ourselves. - * r4 = final kernel address + * r4 = final kernel address (possibly with LSB set) * r9 = size of decompressed image * r10 = end of this image, including bss/stack/malloc space if non XIP * We basically want: * r4 - 16k page directory >= r10 -> OK * r4 + image length <= address of wont_overwrite -> OK + * Note: the possible LSB in r4 is harmless here. */ add r10, r10, #16384 cmp r4, r10 @@ -350,6 +362,20 @@ dtb_check_done: adr r5, restart bic r5, r5, #31 +/* Relocate the hyp vector base if necessary */ +#ifdef CONFIG_ARM_VIRT_EXT + mrs r0, spsr + and r0, r0, #MODE_MASK + cmp r0, #HYP_MODE + bne 1f + + bl __hyp_get_vectors + sub r0, r0, r5 + add r0, r0, r10 + bl __hyp_set_vectors +1: +#endif + sub r9, r6, r5 @ size to copy add r9, r9, #31 @ rounded up to a multiple bic r9, r9, #31 @ ... of 32 bytes @@ -369,7 +395,8 @@ dtb_check_done: add sp, sp, r6 #endif - bl cache_clean_flush + tst r4, #1 + bleq cache_clean_flush adr r0, BSYM(restart) add r0, r0, r6 @@ -381,7 +408,7 @@ wont_overwrite: * r0 = delta * r2 = BSS start * r3 = BSS end - * r4 = kernel execution address + * r4 = kernel execution address (possibly with LSB set) * r5 = appended dtb size (0 if not present) * r7 = architecture ID * r8 = atags pointer @@ -444,6 +471,15 @@ not_relocated: mov r0, #0 cmp r2, r3 blo 1b + /* + * Did we skip the cache setup earlier? + * That is indicated by the LSB in r4. + * Do it now if so. + */ + tst r4, #1 + bic r4, r4, #1 + blne cache_on + /* * The C runtime environment should now be setup sufficiently. * Set up some pointers, and start decompressing. @@ -458,11 +494,29 @@ not_relocated: mov r0, #0 bl decompress_kernel bl cache_clean_flush bl cache_off - mov r0, #0 @ must be zero mov r1, r7 @ restore architecture number mov r2, r8 @ restore atags pointer - ARM( mov pc, r4 ) @ call kernel - THUMB( bx r4 ) @ entry point is always ARM + +#ifdef CONFIG_ARM_VIRT_EXT + mrs r0, spsr @ Get saved CPU boot mode + and r0, r0, #MODE_MASK + 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 + + 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 .align 2 .type LC0, #object @@ -474,6 +528,7 @@ LC0: .word LC0 @ r1 .word _got_start @ r11 .word _got_end @ ip .word .L_user_stack_end @ sp + .word _end - restart + 16384 + 1024*1024 .size LC0, . - LC0 #ifdef CONFIG_ARCH_RPC @@ -614,6 +669,15 @@ __setup_mmu: sub r3, r4, #16384 @ Page directory size mov pc, lr ENDPROC(__setup_mmu) +@ Enable unaligned access on v6, to allow better code generation +@ for the decompressor C code: +__armv6_mmu_cache_on: + mrc p15, 0, r0, c1, c0, 0 @ read SCTLR + bic r0, r0, #2 @ A (no unaligned access fault) + orr r0, r0, #1 << 22 @ U (v6 unaligned access model) + mcr p15, 0, r0, c1, c0, 0 @ write SCTLR + b __armv4_mmu_cache_on + __arm926ejs_mmu_cache_on: #ifdef CONFIG_CPU_DCACHE_WRITETHROUGH mov r0, #4 @ put dcache in WT mode @@ -631,9 +695,7 @@ __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 @@ -653,16 +715,22 @@ __armv7_mmu_cache_on: mcrne p15, 0, r0, c8, c7, 0 @ flush I,D TLBs #endif mrc p15, 0, r0, c1, c0, 0 @ read control reg + bic r0, r0, #1 << 28 @ clear SCTLR.TRE orr r0, r0, #0x5000 @ I-cache enable, RR cache replacement orr r0, r0, #0x003c @ write buffer + bic r0, r0, #2 @ A (no unaligned access fault) + 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 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 #endif mcr p15, 0, r0, c7, c5, 4 @ ISB mcr p15, 0, r0, c1, c0, 0 @ load control register @@ -750,8 +818,8 @@ call_cache_fn: adr r12, proc_types .align 2 .type proc_types,#object proc_types: - .word 0x00000000 @ old ARM ID - .word 0x0000f000 + .word 0x41000000 @ old ARM ID + .word 0xff00f000 mov pc, lr THUMB( nop ) mov pc, lr @@ -871,7 +939,7 @@ proc_types: .word 0x0007b000 @ ARMv6 .word 0x000ff000 - W(b) __armv4_mmu_cache_on + W(b) __armv6_mmu_cache_on W(b) __armv4_mmu_cache_off W(b) __armv6_mmu_cache_flush @@ -1191,6 +1259,25 @@ memdump: mov r12, r0 #endif .ltorg + +#ifdef CONFIG_ARM_VIRT_EXT +.align 5 +__hyp_reentry_vectors: + W(b) . @ reset + W(b) . @ undef + W(b) . @ svc + W(b) . @ pabort + W(b) . @ dabort + W(b) __enter_kernel @ hyp + W(b) . @ irq + W(b) . @ fiq +#endif /* CONFIG_ARM_VIRT_EXT */ + +__enter_kernel: + mov r0, #0 @ must be 0 + ARM( mov pc, r4 ) @ call kernel + THUMB( bx r4 ) @ entry point is always ARM + reloc_code_end: .align |