diff options
Diffstat (limited to 'arch/arm/boot/compressed/head.S')
| -rw-r--r-- | arch/arm/boot/compressed/head.S | 419 |
1 files changed, 318 insertions, 101 deletions
diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S index adf583cd0c3..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_S3C2410) - .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? @@ -176,19 +174,44 @@ 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, r5, r6, r9, r11, r12} - ldr sp, [r0, #32] + 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 r5, r5, r0 @ _start add r6, r6, r0 @ _edata + add r10, r10, r0 @ inflated kernel size location + + /* + * 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 #ifndef CONFIG_ZBOOT_ROM /* malloc space is above the relocated stack (64k max) */ @@ -203,34 +226,156 @@ restart: adr r0, LC0 mov r10, r6 #endif + 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 + * r7 = architecture ID + * 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 + * dtb data will get relocated along with the kernel if necessary. + */ + + ldr lr, [r6, #0] +#ifndef __ARMEB__ + ldr r1, =0xedfe0dd0 @ sig is 0xd00dfeed big endian +#else + ldr r1, =0xd00dfeed +#endif + cmp lr, r1 + bne dtb_check_done @ not found + +#ifdef CONFIG_ARM_ATAG_DTB_COMPAT + /* + * 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. + */ + add sp, sp, #0x10000 + stmfd sp!, {r0-r3, ip, lr} + mov r0, r8 + mov r1, r6 + sub r2, sp, r6 + bl atags_to_fdt + + /* + * If returned value is 1, there is no ATAG at the location + * pointed by r8. Try the typical 0x100 offset from start + * of RAM and hope for the best. + */ + cmp r0, #1 + sub r0, r4, #TEXT_OFFSET + bic r0, r0, #1 + add r0, r0, #0x100 + mov r1, r6 + sub r2, sp, r6 + bleq atags_to_fdt + + ldmfd sp!, {r0-r3, ip, lr} + sub sp, sp, #0x10000 +#endif + + mov r8, r6 @ use the appended device tree + + /* + * Make sure that the DTB doesn't end up in the final + * kernel's .bss area. To do so, we adjust the decompressed + * kernel size to compensate if that .bss size is larger + * than the relocated code. + */ + ldr r5, =_kernel_bss_size + adr r1, wont_overwrite + sub r1, r6, r1 + subs r1, r5, r1 + addhi r9, r9, r1 + + /* Get the dtb's 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 + + /* preserve 64-bit alignment */ + add r5, r5, #7 + bic r5, r5, #7 + + /* relocate some pointers past the appended dtb */ + add r6, r6, r5 + add r10, r10, r5 + add sp, sp, r5 +dtb_check_done: +#endif + /* * Check to see if we will overwrite ourselves. - * r4 = final kernel address - * r5 = start of this image + * 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 >= r10 -> OK - * r4 + image length <= r5 -> OK + * 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 bhs wont_overwrite add r10, r4, r9 - cmp r10, r5 + adr r9, wont_overwrite + cmp r10, r9 bls wont_overwrite /* * Relocate ourselves past the end of the decompressed kernel. - * r5 = start of this image * r6 = _edata * r10 = end of the decompressed kernel * Because we always copy ahead, we need to do it from the end and go * backward in case the source and destination overlap. */ - /* Round up to next 256-byte boundary. */ - add r10, r10, #256 + /* + * Bump to the next 256-byte boundary with the size of + * the relocation code added. This avoids overwriting + * ourself when the offset is small. + */ + add r10, r10, #((reloc_code_end - restart + 256) & ~255) bic r10, r10, #255 + /* Get start of code we want to copy and align it down. */ + 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 @@ -245,7 +390,13 @@ restart: adr r0, LC0 /* Preserve offset to relocated code. */ sub r6, r9, r6 - bl cache_clean_flush +#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 adr r0, BSYM(restart) add r0, r0, r6 @@ -257,15 +408,17 @@ 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 * r11 = GOT start * r12 = GOT end * sp = stack pointer */ - teq r0, #0 + orrs r1, r0, r5 beq not_relocated + add r11, r11, r0 add r12, r12, r0 @@ -280,12 +433,21 @@ wont_overwrite: /* * Relocate all entries in the GOT table. + * Bump bss entries to _edata + dtb size */ 1: ldr r1, [r11, #0] @ relocate entries in the GOT - add r1, r1, r0 @ table. This fixes up the - str r1, [r11], #4 @ C references. + add r1, r1, r0 @ This fixes up C references + cmp r1, r2 @ if entry >= bss_start && + cmphs r3, r1 @ bss_end > entry + addhi r1, r1, r5 @ entry += dtb size + str r1, [r11], #4 @ next entry cmp r11, r12 blo 1b + + /* bump our bss pointers too */ + add r2, r2, r5 + add r3, r3, r5 + #else /* @@ -309,6 +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. @@ -323,22 +494,41 @@ 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 - mov pc, r4 @ call kernel + +#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 LC0: .word LC0 @ r1 .word __bss_start @ r2 .word _end @ r3 - .word _start @ r5 .word _edata @ r6 - .word _image_size @ r9 + .word input_data_end - 4 @ r10 (inflated size location) .word _got_start @ r11 .word _got_end @ ip - .word user_stack_end @ sp + .word .L_user_stack_end @ sp + .word _end - restart + 16384 + 1024*1024 .size LC0, . - LC0 #ifdef CONFIG_ARCH_RPC @@ -432,6 +622,12 @@ __armv3_mpu_cache_on: mcr p15, 0, r0, c7, c0, 0 @ invalidate whole cache v3 mov pc, lr +#ifdef CONFIG_CPU_DCACHE_WRITETHROUGH +#define CB_BITS 0x08 +#else +#define CB_BITS 0x0c +#endif + __setup_mmu: sub r3, r4, #16384 @ Page directory size bic r3, r3, #0xff @ Align the pointer bic r3, r3, #0x3f00 @@ -443,13 +639,14 @@ __setup_mmu: sub r3, r4, #16384 @ Page directory size mov r9, r0, lsr #18 mov r9, r9, lsl #18 @ start of RAM add r10, r9, #0x10000000 @ a reasonable RAM size - mov r1, #0x12 - orr r1, r1, #3 << 10 + mov r1, #0x12 @ XN|U + section mapping + orr r1, r1, #3 << 10 @ AP=11 add r2, r3, #16384 1: cmp r1, r9 @ if virt > start of RAM - orrhs r1, r1, #0x0c @ set cacheable, bufferable - cmp r1, r10 @ if virt > end of RAM - bichs r1, r1, #0x0c @ clear cacheable, bufferable + cmphs r10, r1 @ && end of RAM > virt + bic r1, r1, #0x1c @ clear XN|U + C + B + orrlo r1, r1, #0x10 @ Set XN|U for non-RAM + orrhs r1, r1, r6 @ set RAM section settings str r1, [r0], #4 @ 1:1 mapping add r1, r1, #1048576 teq r0, r2 @@ -460,7 +657,7 @@ __setup_mmu: sub r3, r4, #16384 @ Page directory size * so there is no map overlap problem for up to 1 MB compressed kernel. * If the execution is in RAM then we would only be duplicating the above. */ - mov r1, #0x1e + orr r1, r6, #0x04 @ ensure B is set for this orr r1, r1, #3 << 10 mov r2, pc mov r2, r2, lsr #20 @@ -472,9 +669,25 @@ __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 + mcr p15, 7, r0, c15, c0, 0 +#endif + __armv4_mmu_cache_on: mov r12, lr #ifdef CONFIG_MMU + mov r6, #CB_BITS | 0x12 @ U bl __setup_mmu mov r0, #0 mcr p15, 0, r0, c7, c10, 4 @ drain write buffer @@ -482,9 +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 @@ -496,6 +707,7 @@ __armv7_mmu_cache_on: #ifdef CONFIG_MMU mrc p15, 0, r11, c0, c1, 4 @ read ID_MMFR0 tst r11, #0xf @ VMSA + movne r6, #CB_BITS | 0x02 @ !XN blne __setup_mmu mov r0, #0 mcr p15, 0, r0, c7, c10, 4 @ drain write buffer @@ -503,17 +715,24 @@ __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, #-1 + 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 mrc p15, 0, r0, c1, c0, 0 @ and read it back mov r0, #0 @@ -522,6 +741,7 @@ __armv7_mmu_cache_on: __fa526_cache_on: mov r12, lr + mov r6, #CB_BITS | 0x12 @ U bl __setup_mmu mov r0, #0 mcr p15, 0, r0, c7, c7, 0 @ Invalidate whole cache @@ -534,18 +754,6 @@ __fa526_cache_on: mcr p15, 0, r0, c8, c7, 0 @ flush UTLB mov pc, r12 -__arm6_mmu_cache_on: - mov r12, lr - bl __setup_mmu - mov r0, #0 - mcr p15, 0, r0, c7, c0, 0 @ invalidate whole cache v3 - mcr p15, 0, r0, c5, c0, 0 @ invalidate whole TLB v3 - mov r0, #0x30 - bl __common_mmu_cache_on - mov r0, #0 - mcr p15, 0, r0, c5, c0, 0 @ invalidate whole TLB v3 - mov pc, r12 - __common_mmu_cache_on: #ifndef CONFIG_THUMB2_KERNEL #ifndef DEBUG @@ -561,6 +769,8 @@ __common_mmu_cache_on: sub pc, lr, r0, lsr #32 @ properly flush pipeline #endif +#define PROC_ENTRY_SIZE (4*5) + /* * Here follow the relocatable cache support functions for the * various processors. This is a generic hook for locating an @@ -588,7 +798,7 @@ call_cache_fn: adr r12, proc_types ARM( addeq pc, r12, r3 ) @ call cache function THUMB( addeq r12, r3 ) THUMB( moveq pc, r12 ) @ call cache function - add r12, r12, #4*5 + add r12, r12, #PROC_ENTRY_SIZE b 1b /* @@ -608,18 +818,8 @@ call_cache_fn: adr r12, proc_types .align 2 .type proc_types,#object proc_types: - .word 0x41560600 @ ARM6/610 - .word 0xffffffe0 - W(b) __arm6_mmu_cache_off @ works, but slow - W(b) __arm6_mmu_cache_off - mov pc, lr - THUMB( nop ) -@ b __arm6_mmu_cache_on @ untested -@ b __arm6_mmu_cache_off -@ b __armv3_mmu_cache_flush - - .word 0x00000000 @ old ARM ID - .word 0x0000f000 + .word 0x41000000 @ old ARM ID + .word 0xff00f000 mov pc, lr THUMB( nop ) mov pc, lr @@ -629,8 +829,10 @@ proc_types: .word 0x41007000 @ ARM7/710 .word 0xfff8fe00 - W(b) __arm7_mmu_cache_off - W(b) __arm7_mmu_cache_off + mov pc, lr + THUMB( nop ) + mov pc, lr + THUMB( nop ) mov pc, lr THUMB( nop ) @@ -653,6 +855,12 @@ proc_types: W(b) __armv4_mpu_cache_off W(b) __armv4_mpu_cache_flush + .word 0x41069260 @ ARM926EJ-S (v5TEJ) + .word 0xff0ffff0 + W(b) __arm926ejs_mmu_cache_on + W(b) __armv4_mmu_cache_off + W(b) __armv5tej_mmu_cache_flush + .word 0x00007000 @ ARM7 IDs .word 0x0000f000 mov pc, lr @@ -731,13 +939,7 @@ proc_types: .word 0x0007b000 @ ARMv6 .word 0x000ff000 - W(b) __armv4_mmu_cache_on - W(b) __armv4_mmu_cache_off - W(b) __armv6_mmu_cache_flush - - .word 0x560f5810 @ Marvell PJ4 ARMv6 - .word 0xff0ffff0 - W(b) __armv4_mmu_cache_on + W(b) __armv6_mmu_cache_on W(b) __armv4_mmu_cache_off W(b) __armv6_mmu_cache_flush @@ -758,6 +960,16 @@ proc_types: .size proc_types, . - proc_types + /* + * If you get a "non-constant expression in ".if" statement" + * error from the assembler on this line, check that you have + * not accidentally written a "b" instruction where you should + * have written W(b). + */ + .if (. - proc_types) % PROC_ENTRY_SIZE != 0 + .error "The size of one or more proc_types entries is wrong." + .endif + /* * Turn off the Cache and MMU. ARMv3 does not support * reading the control register, but ARMv4 does. @@ -819,21 +1031,6 @@ __armv7_mmu_cache_off: mcr p15, 0, r0, c7, c5, 4 @ ISB mov pc, r12 -__arm6_mmu_cache_off: - mov r0, #0x00000030 @ ARM6 control reg. - b __armv3_mmu_cache_off - -__arm7_mmu_cache_off: - mov r0, #0x00000070 @ ARM7 control reg. - b __armv3_mmu_cache_off - -__armv3_mmu_cache_off: - mcr p15, 0, r0, c1, c0, 0 @ turn MMU and cache off - mov r0, #0 - mcr p15, 0, r0, c7, c0, 0 @ invalidate whole cache v3 - mcr p15, 0, r0, c5, c0, 0 @ invalidate whole TLB v3 - mov pc, lr - /* * Clean and flush the cache to maintain consistency. * @@ -1063,7 +1260,27 @@ memdump: mov r12, r0 .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 .section ".stack", "aw", %nobits -user_stack: .space 4096 -user_stack_end: +.L_user_stack: .space 4096 +.L_user_stack_end: |