diff options
Diffstat (limited to '')
-rw-r--r-- | arch/arm/boot/compressed/head.S | 466 |
1 files changed, 254 insertions, 212 deletions
diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S index 088b0a060876..9f406e9c0ea6 100644 --- a/arch/arm/boot/compressed/head.S +++ b/arch/arm/boot/compressed/head.S @@ -11,6 +11,12 @@ #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 ) @@ -28,19 +34,19 @@ #if defined(CONFIG_CPU_V6) || defined(CONFIG_CPU_V6K) || defined(CONFIG_CPU_V7) .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, tmp1, tmp2 .endm - .macro writeb, ch, rb + .macro writeb, ch, rb, tmp mcr p14, 0, \ch, c8, c0, 0 .endm #else .macro loadsp, rb, tmp1, tmp2 .endm - .macro writeb, ch, rb + .macro writeb, ch, rb, tmp mcr p14, 0, \ch, c1, c0, 0 .endm #endif @@ -49,18 +55,19 @@ #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, 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 #else .macro loadsp, rb, tmp1, tmp2 @@ -81,42 +88,11 @@ bl phex .endm - .macro debug_reloc_start -#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 #'-' - kphex r9, 8 /* decompressed kernel end */ - kputc #'>' - kphex r4, 8 /* kernel execution address */ - kputc #'\n' -#endif - .endm - - .macro debug_reloc_end -#ifdef DEBUG - kphex r5, 8 /* end of kernel */ - kputc #'\n' - mov r0, r4 - bl memdump /* dump 256 bytes at start of kernel */ -#endif - .endm - /* * Debug kernel copy by printing the memory addresses involved */ .macro dbgkc, begin, end, cbegin, cend #ifdef DEBUG - kputc #'\n' kputc #'C' kputc #':' kputc #'0' @@ -136,7 +112,28 @@ kputc #'x' kphex \cend, 8 /* End of kernel copy */ kputc #'\n' - kputc #'\r' +#endif + .endm + + /* + * Debug print of the final appended DTB location + */ + .macro dbgadtb, begin, size +#ifdef DEBUG + 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' #endif .endm @@ -151,6 +148,32 @@ .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 @@ -176,7 +199,8 @@ start: * were patching the initial instructions of the kernel, i.e * had started to exploit this "patch area". */ - .rept 7 + __initial_nops + .rept 5 __nop .endr #ifndef CONFIG_THUMB2_KERNEL @@ -252,10 +276,40 @@ not_angel: * are already placing their zImage in (eg) the top 64MB * of this range. */ - mov r4, pc - and r4, r4, #0xf8000000 + 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, r4, #TEXT_OFFSET + add r4, r0, #TEXT_OFFSET #else ldr r4, =zreladdr #endif @@ -268,41 +322,23 @@ not_angel: */ 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] +restart: adr r0, LC1 + ldr sp, [r0] + ldr r6, [r0, #4] + add sp, sp, r0 + add r6, r6, r0 - /* - * 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 - - /* - * 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, @@ -315,9 +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 @@ -325,8 +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 @@ -334,11 +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 @@ -354,13 +381,8 @@ restart: adr r0, LC0 /* Get the initial DTB size */ ldr r5, [r6, #4] -#ifndef __ARMEB__ - /* convert 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 + dbgadtb r6, r5 /* 50% DTB growth should be good enough */ add r5, r5, r5, lsr #1 /* preserve 64-bit alignment */ @@ -374,7 +396,6 @@ restart: adr r0, LC0 /* temporarily relocate the stack past the DTB work space */ add sp, sp, r5 - stmfd sp!, {r0-r3, ip, lr} mov r0, r8 mov r1, r6 mov r2, r5 @@ -393,7 +414,6 @@ restart: adr r0, LC0 mov r2, r5 bleq atags_to_fdt - ldmfd sp!, {r0-r3, ip, lr} sub sp, sp, r5 #endif @@ -413,13 +433,7 @@ restart: adr r0, LC0 /* 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 @@ -478,15 +492,10 @@ dtb_check_done: /* * Compute the address of the hyp vectors after relocation. - * This requires some arithmetic since we cannot directly - * reference __hyp_stub_vectors in a PC-relative way. * Call __hyp_set_vectors with the new address so that we * can HVC again after the copy. */ -0: adr r0, 0b - movw r1, #:lower16:__hyp_stub_vectors - 0b - movt r1, #:upper16:__hyp_stub_vectors - 0b - add r0, r0, r1 + adr_l r0, __hyp_stub_vectors sub r0, r0, r5 add r0, r0, r10 bl __hyp_set_vectors @@ -521,11 +530,8 @@ 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 - + mov r0, r9 @ start of relocated zImage + add r1, sp, r6 @ end of relocated zImage bl cache_clean_flush badr r0, restart @@ -533,6 +539,10 @@ dtb_check_done: 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 @@ -619,9 +629,14 @@ 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 @@ -631,17 +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 @@ -651,14 +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 @@ -668,6 +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. * @@ -1154,13 +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 @@ -1168,11 +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: @@ -1181,6 +1216,7 @@ __armv7_mmu_cache_off: .align 5 cache_clean_flush: mov r3, #16 + mov r11, r1 b call_cache_fn __armv4_mpu_cache_flush: @@ -1231,51 +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 @ switch 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 @@ -1364,7 +1365,7 @@ 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 @@ -1418,7 +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 @@ -1437,50 +1442,87 @@ __enter_kernel: reloc_code_end: #ifdef CONFIG_EFI_STUB - .align 2 -_start: .long start - . - -ENTRY(efi_stub_entry) - @ allocate space on stack for passing current zImage address - @ and for the EFI stub to return of new entry point of - @ zImage, as EFI stub may copy the kernel. Pointer address - @ is passed in r2. r0 and r1 are passed through from the - @ EFI firmware to efi_entry - adr ip, _start - ldr r3, [ip] - add r3, r3, ip - stmfd sp!, {r3, lr} - mov r2, sp @ pass zImage address in r2 - bl efi_entry - - @ Check for error return from EFI stub. r0 has FDT address - @ or error code. - cmn r0, #1 - beq efi_load_fail - - @ Preserve return value of efi_entry() in r4 - mov r4, r0 +__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 - bl cache_off - @ Set parameters for booting zImage according to boot protocol - @ put FDT address in r2, it was returned by efi_entry() - @ r1 is the machine type, and r0 needs to be 0 - mov r0, #0 - mov r1, #0xFFFFFFFF - mov r2, r4 - - @ Branch to (possibly) relocated zImage that is in [sp] - ldr lr, [sp] - ldr ip, =start_offset - add lr, lr, ip - mov pc, lr @ no mode switch - -efi_load_fail: - @ Return EFI_LOAD_ERROR to EFI firmware on error. - ldr r0, =0x80000001 - ldmfd sp!, {ip, pc} -ENDPROC(efi_stub_entry) + 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 |