From 72a20e22f49e2dad3180c23980a9df1c63faab0a Mon Sep 17 00:00:00 2001 From: Russell King Date: Tue, 4 Jan 2011 19:04:00 +0000 Subject: ARM: P2V: eliminate head.S use of PHYS_OFFSET for !XIP_KERNEL head.S makes use of PHYS_OFFSET. When it becomes a variable, the assembler won't understand this. Compute PHYS_OFFSET by the following method. This code is linked at its virtual address, but run at before the MMU is enabled, so at his physical address. 1: .long . .long PAGE_OFFSET adr r0, 1b @ r0 = physical ',' ldmia r0, {r1, r2} @ r1 = virtual '.', r2 = PAGE_OFFSET sub r1, r0, r1 @ r1 = physical-virtual add r2, r2, r1 @ r2 = PAGE_OFFSET + physical-virtual @ := PHYS_OFFSET. Switch XIP users of PHYS_OFFSET to use PLAT_PHYS_OFFSET - we can't use this method for XIP kernels as the code doesn't execute in RAM. Tested-by: Tony Lindgren Reviewed-by: Nicolas Pitre Signed-off-by: Russell King --- arch/arm/kernel/head.S | 44 ++++++++++++++++++++++---------------------- 1 file changed, 22 insertions(+), 22 deletions(-) (limited to 'arch/arm/kernel/head.S') diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S index 8a154b940fe..03a588b6e15 100644 --- a/arch/arm/kernel/head.S +++ b/arch/arm/kernel/head.S @@ -26,14 +26,6 @@ #include #endif -#if (PHYS_OFFSET & 0x001fffff) -#error "PHYS_OFFSET must be at an even 2MiB boundary!" -#endif - -#define KERNEL_RAM_VADDR (PAGE_OFFSET + TEXT_OFFSET) -#define KERNEL_RAM_PADDR (PHYS_OFFSET + TEXT_OFFSET) - - /* * swapper_pg_dir is the virtual address of the initial page table. * We place the page tables 16K below KERNEL_RAM_VADDR. Therefore, we must @@ -41,6 +33,7 @@ * the least significant 16 bits to be 0x8000, but we could probably * relax this restriction to KERNEL_RAM_VADDR >= PAGE_OFFSET + 0x4000. */ +#define KERNEL_RAM_VADDR (PAGE_OFFSET + TEXT_OFFSET) #if (KERNEL_RAM_VADDR & 0xffff) != 0x8000 #error KERNEL_RAM_VADDR must start at 0xXXXX8000 #endif @@ -48,8 +41,8 @@ .globl swapper_pg_dir .equ swapper_pg_dir, KERNEL_RAM_VADDR - 0x4000 - .macro pgtbl, rd - ldr \rd, =(KERNEL_RAM_PADDR - 0x4000) + .macro pgtbl, rd, phys + add \rd, \phys, #TEXT_OFFSET - 0x4000 .endm #ifdef CONFIG_XIP_KERNEL @@ -88,9 +81,18 @@ ENTRY(stext) THUMB( it eq ) @ force fixup-able long branch encoding beq __error_p @ yes, error 'p' +#ifndef CONFIG_XIP_KERNEL + adr r3, 2f + ldmia r3, {r4, r8} + sub r4, r3, r4 @ (PHYS_OFFSET - PAGE_OFFSET) + add r8, r8, r4 @ PHYS_OFFSET +#else + ldr r8, =PLAT_PHYS_OFFSET +#endif + /* * r1 = machine no, r2 = atags, - * r9 = cpuid, r10 = procinfo + * r8 = phys_offset, r9 = cpuid, r10 = procinfo */ bl __vet_atags #ifdef CONFIG_SMP_ON_UP @@ -114,21 +116,24 @@ ENTRY(stext) 1: b __enable_mmu ENDPROC(stext) .ltorg +#ifndef CONFIG_XIP_KERNEL +2: .long . + .long PAGE_OFFSET +#endif /* * Setup the initial page tables. We only setup the barest * amount which are required to get the kernel running, which * generally means mapping in the kernel code. * - * r9 = cpuid - * r10 = procinfo + * r8 = phys_offset, r9 = cpuid, r10 = procinfo * * Returns: * r0, r3, r5-r7 corrupted * r4 = physical page table address */ __create_page_tables: - pgtbl r4 @ page table address + pgtbl r4, r8 @ page table address /* * Clear the 16K level 1 swapper page table @@ -184,10 +189,8 @@ __create_page_tables: /* * Map some ram to cover our .data and .bss areas. */ - orr r3, r7, #(KERNEL_RAM_PADDR & 0xff000000) - .if (KERNEL_RAM_PADDR & 0x00f00000) - orr r3, r3, #(KERNEL_RAM_PADDR & 0x00f00000) - .endif + add r3, r8, #TEXT_OFFSET + orr r3, r3, r7 add r0, r4, #(KERNEL_RAM_VADDR & 0xff000000) >> 18 str r3, [r0, #(KERNEL_RAM_VADDR & 0x00f00000) >> 18]! ldr r6, =(_end - 1) @@ -203,10 +206,7 @@ __create_page_tables: * Then map first 1MB of ram in case it contains our boot params. */ add r0, r4, #PAGE_OFFSET >> 18 - orr r6, r7, #(PHYS_OFFSET & 0xff000000) - .if (PHYS_OFFSET & 0x00f00000) - orr r6, r6, #(PHYS_OFFSET & 0x00f00000) - .endif + orr r6, r7, r8 str r6, [r0] #ifdef CONFIG_DEBUG_LL -- cgit v1.2.3-70-g09d2 From dc21af99fadcfa0ae65b52fd0895f85824f0c288 Mon Sep 17 00:00:00 2001 From: Russell King Date: Tue, 4 Jan 2011 19:09:43 +0000 Subject: ARM: P2V: introduce phys_to_virt/virt_to_phys runtime patching This idea came from Nicolas, Eric Miao produced an initial version, which was then rewritten into this. Patch the physical to virtual translations at runtime. As we modify the code, this makes it incompatible with XIP kernels, but allows us to achieve this with minimal loss of performance. As many translations are of the form: physical = virtual + (PHYS_OFFSET - PAGE_OFFSET) virtual = physical - (PHYS_OFFSET - PAGE_OFFSET) we generate an 'add' instruction for __virt_to_phys(), and a 'sub' instruction for __phys_to_virt(). We calculate at run time (PHYS_OFFSET - PAGE_OFFSET) by comparing the address prior to MMU initialization with where it should be once the MMU has been initialized, and place this constant into the above add/sub instructions. Once we have (PHYS_OFFSET - PAGE_OFFSET), we can calculate the real PHYS_OFFSET as PAGE_OFFSET is a build-time constant, and save this for the C-mode PHYS_OFFSET variable definition to use. At present, we are unable to support Realview with Sparsemem enabled as this uses a complex mapping function, and MSM as this requires a constant which will not fit in our math instruction. Add a module version magic string for this feature to prevent incompatible modules being loaded. Tested-by: Tony Lindgren Reviewed-by: Nicolas Pitre Tested-by: Nicolas Pitre Signed-off-by: Russell King --- arch/arm/Kconfig | 13 +++++++++ arch/arm/include/asm/memory.h | 55 ++++++++++++++++++++++++++-------- arch/arm/include/asm/module.h | 15 ++++++++-- arch/arm/kernel/armksyms.c | 4 +++ arch/arm/kernel/head.S | 68 +++++++++++++++++++++++++++++++++++++++++++ arch/arm/kernel/module.c | 23 ++++++++++++++- arch/arm/kernel/vmlinux.lds.S | 4 +++ 7 files changed, 167 insertions(+), 15 deletions(-) (limited to 'arch/arm/kernel/head.S') diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 5cff165b7eb..4147f76e798 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -191,6 +191,19 @@ config VECTORS_BASE help The base address of exception vectors. +config ARM_PATCH_PHYS_VIRT + bool "Patch physical to virtual translations at runtime (EXPERIMENTAL)" + depends on EXPERIMENTAL + depends on !XIP_KERNEL && !THUMB2_KERNEL && MMU + depends on !ARCH_MSM + depends on !ARCH_REALVIEW || !SPARSEMEM + help + Patch phys-to-virt translation functions at runtime according to + the position of the kernel in system memory. + + This can only be used with non-XIP, non-Thumb2, MMU kernels where + the base of physical memory is at a 16MB boundary. + source "init/Kconfig" source "kernel/Kconfig.freezer" diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h index 2efec578a62..7197879e1cb 100644 --- a/arch/arm/include/asm/memory.h +++ b/arch/arm/include/asm/memory.h @@ -24,8 +24,6 @@ */ #define UL(x) _AC(x, UL) -#define PHYS_OFFSET PLAT_PHYS_OFFSET - #ifdef CONFIG_MMU /* @@ -134,16 +132,6 @@ #define DTCM_OFFSET UL(0xfffe8000) #endif -/* - * Physical vs virtual RAM address space conversion. These are - * private definitions which should NOT be used outside memory.h - * files. Use virt_to_phys/phys_to_virt/__pa/__va instead. - */ -#ifndef __virt_to_phys -#define __virt_to_phys(x) ((x) - PAGE_OFFSET + PHYS_OFFSET) -#define __phys_to_virt(x) ((x) - PHYS_OFFSET + PAGE_OFFSET) -#endif - /* * Convert a physical address to a Page Frame Number and back */ @@ -158,6 +146,49 @@ #ifndef __ASSEMBLY__ +/* + * Physical vs virtual RAM address space conversion. These are + * private definitions which should NOT be used outside memory.h + * files. Use virt_to_phys/phys_to_virt/__pa/__va instead. + */ +#ifndef __virt_to_phys +#ifdef CONFIG_ARM_PATCH_PHYS_VIRT + +extern unsigned long __pv_phys_offset; +#define PHYS_OFFSET __pv_phys_offset + +#define __pv_stub(from,to,instr) \ + __asm__("@ __pv_stub\n" \ + "1: " instr " %0, %1, %2\n" \ + " .pushsection .pv_table,\"a\"\n" \ + " .long 1b\n" \ + " .popsection\n" \ + : "=r" (to) \ + : "r" (from), "I" (0x81000000)) + +static inline unsigned long __virt_to_phys(unsigned long x) +{ + unsigned long t; + __pv_stub(x, t, "add"); + return t; +} + +static inline unsigned long __phys_to_virt(unsigned long x) +{ + unsigned long t; + __pv_stub(x, t, "sub"); + return t; +} +#else +#define __virt_to_phys(x) ((x) - PAGE_OFFSET + PHYS_OFFSET) +#define __phys_to_virt(x) ((x) - PHYS_OFFSET + PAGE_OFFSET) +#endif +#endif + +#ifndef PHYS_OFFSET +#define PHYS_OFFSET PLAT_PHYS_OFFSET +#endif + /* * The DMA mask corresponding to the maximum bus address allocatable * using GFP_DMA. The default here places no restriction on DMA diff --git a/arch/arm/include/asm/module.h b/arch/arm/include/asm/module.h index 12c8e680cbf..d072c21332e 100644 --- a/arch/arm/include/asm/module.h +++ b/arch/arm/include/asm/module.h @@ -25,8 +25,19 @@ struct mod_arch_specific { }; /* - * Include the ARM architecture version. + * Add the ARM architecture version to the version magic string */ -#define MODULE_ARCH_VERMAGIC "ARMv" __stringify(__LINUX_ARM_ARCH__) " " +#define MODULE_ARCH_VERMAGIC_ARMVSN "ARMv" __stringify(__LINUX_ARM_ARCH__) " " + +/* Add __virt_to_phys patching state as well */ +#ifdef CONFIG_ARM_PATCH_PHYS_VIRT +#define MODULE_ARCH_VERMAGIC_P2V "p2v8 " +#else +#define MODULE_ARCH_VERMAGIC_P2V "" +#endif + +#define MODULE_ARCH_VERMAGIC \ + MODULE_ARCH_VERMAGIC_ARMVSN \ + MODULE_ARCH_VERMAGIC_P2V #endif /* _ASM_ARM_MODULE_H */ diff --git a/arch/arm/kernel/armksyms.c b/arch/arm/kernel/armksyms.c index e5e1e538767..9615423c37d 100644 --- a/arch/arm/kernel/armksyms.c +++ b/arch/arm/kernel/armksyms.c @@ -170,3 +170,7 @@ EXPORT_SYMBOL(mcount); #endif EXPORT_SYMBOL(__gnu_mcount_nc); #endif + +#ifdef CONFIG_ARM_PATCH_PHYS_VIRT +EXPORT_SYMBOL(__pv_phys_offset); +#endif diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S index 03a588b6e15..1db8ead2e33 100644 --- a/arch/arm/kernel/head.S +++ b/arch/arm/kernel/head.S @@ -97,6 +97,9 @@ ENTRY(stext) bl __vet_atags #ifdef CONFIG_SMP_ON_UP bl __fixup_smp +#endif +#ifdef CONFIG_ARM_PATCH_PHYS_VIRT + bl __fixup_pv_table #endif bl __create_page_tables @@ -438,4 +441,69 @@ smp_on_up: #endif +#ifdef CONFIG_ARM_PATCH_PHYS_VIRT + +/* __fixup_pv_table - patch the stub instructions with the delta between + * PHYS_OFFSET and PAGE_OFFSET, which is assumed to be 16MiB aligned and + * can be expressed by an immediate shifter operand. The stub instruction + * has a form of '(add|sub) rd, rn, #imm'. + */ + __HEAD +__fixup_pv_table: + adr r0, 1f + ldmia r0, {r3-r5, r7} + sub r3, r0, r3 @ PHYS_OFFSET - PAGE_OFFSET + add r4, r4, r3 @ adjust table start address + add r5, r5, r3 @ adjust table end address + str r8, [r7, r3]! @ save computed PHYS_OFFSET to __pv_phys_offset + mov r6, r3, lsr #24 @ constant for add/sub instructions + teq r3, r6, lsl #24 @ must be 16MiB aligned + bne __error + str r6, [r7, #4] @ save to __pv_offset + b __fixup_a_pv_table +ENDPROC(__fixup_pv_table) + + .align +1: .long . + .long __pv_table_begin + .long __pv_table_end +2: .long __pv_phys_offset + + .text +__fixup_a_pv_table: + b 3f +2: ldr ip, [r7, r3] + bic ip, ip, #0x000000ff + orr ip, ip, r6 + str ip, [r7, r3] +3: cmp r4, r5 + ldrcc r7, [r4], #4 @ use branch for delay slot + bcc 2b + mov pc, lr +ENDPROC(__fixup_a_pv_table) + +ENTRY(fixup_pv_table) + stmfd sp!, {r4 - r7, lr} + ldr r2, 2f @ get address of __pv_phys_offset + mov r3, #0 @ no offset + mov r4, r0 @ r0 = table start + add r5, r0, r1 @ r1 = table size + ldr r6, [r2, #4] @ get __pv_offset + bl __fixup_a_pv_table + ldmfd sp!, {r4 - r7, pc} +ENDPROC(fixup_pv_table) + + .align +2: .long __pv_phys_offset + + .data + .globl __pv_phys_offset + .type __pv_phys_offset, %object +__pv_phys_offset: + .long 0 + .size __pv_phys_offset, . - __pv_phys_offset +__pv_offset: + .long 0 +#endif + #include "head-common.S" diff --git a/arch/arm/kernel/module.c b/arch/arm/kernel/module.c index 2cfe8161b47..c5679f6d9f6 100644 --- a/arch/arm/kernel/module.c +++ b/arch/arm/kernel/module.c @@ -268,12 +268,28 @@ struct mod_unwind_map { const Elf_Shdr *txt_sec; }; +static const Elf_Shdr *find_mod_section(const Elf32_Ehdr *hdr, + const Elf_Shdr *sechdrs, const char *name) +{ + const Elf_Shdr *s, *se; + const char *secstrs = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset; + + for (s = sechdrs, se = sechdrs + hdr->e_shnum; s < se; s++) + if (strcmp(name, secstrs + s->sh_name) == 0) + return s; + + return NULL; +} + +extern void fixup_pv_table(const void *, unsigned long); + int module_finalize(const Elf32_Ehdr *hdr, const Elf_Shdr *sechdrs, struct module *mod) { + const Elf_Shdr *s = NULL; #ifdef CONFIG_ARM_UNWIND const char *secstrs = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset; - const Elf_Shdr *s, *sechdrs_end = sechdrs + hdr->e_shnum; + const Elf_Shdr *sechdrs_end = sechdrs + hdr->e_shnum; struct mod_unwind_map maps[ARM_SEC_MAX]; int i; @@ -314,6 +330,11 @@ int module_finalize(const Elf32_Ehdr *hdr, const Elf_Shdr *sechdrs, maps[i].unw_sec->sh_size, maps[i].txt_sec->sh_addr, maps[i].txt_sec->sh_size); +#endif +#ifdef CONFIG_ARM_PATCH_PHYS_VIRT + s = find_mod_section(hdr, sechdrs, ".pv_table"); + if (s) + fixup_pv_table((void *)s->sh_addr, s->sh_size); #endif return 0; } diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S index 86b66f3f203..45b5651777e 100644 --- a/arch/arm/kernel/vmlinux.lds.S +++ b/arch/arm/kernel/vmlinux.lds.S @@ -57,6 +57,10 @@ SECTIONS __smpalt_end = .; #endif + __pv_table_begin = .; + *(.pv_table) + __pv_table_end = .; + INIT_SETUP(16) INIT_CALLS -- cgit v1.2.3-70-g09d2 From cada3c0841e1deaec4c0f92654610b028dc683ff Mon Sep 17 00:00:00 2001 From: Russell King Date: Tue, 4 Jan 2011 19:39:29 +0000 Subject: ARM: P2V: extend to 16-bit translation offsets MSM's memory is aligned to 2MB, which is more than we can do with our existing method as we're limited to the upper 8 bits. Extend this by using two instructions to 16 bits, automatically selected when MSM is enabled. Acked-by: Tony Lindgren Reviewed-by: Nicolas Pitre Tested-by: Nicolas Pitre Signed-off-by: Russell King --- arch/arm/Kconfig | 5 ++++- arch/arm/include/asm/memory.h | 21 +++++++++++++++++---- arch/arm/include/asm/module.h | 4 ++++ arch/arm/kernel/head.S | 15 ++++++++++++++- 4 files changed, 39 insertions(+), 6 deletions(-) (limited to 'arch/arm/kernel/head.S') diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 4147f76e798..b357c29e7df 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -195,7 +195,6 @@ config ARM_PATCH_PHYS_VIRT bool "Patch physical to virtual translations at runtime (EXPERIMENTAL)" depends on EXPERIMENTAL depends on !XIP_KERNEL && !THUMB2_KERNEL && MMU - depends on !ARCH_MSM depends on !ARCH_REALVIEW || !SPARSEMEM help Patch phys-to-virt translation functions at runtime according to @@ -204,6 +203,10 @@ config ARM_PATCH_PHYS_VIRT This can only be used with non-XIP, non-Thumb2, MMU kernels where the base of physical memory is at a 16MB boundary. +config ARM_PATCH_PHYS_VIRT_16BIT + def_bool y + depends on ARM_PATCH_PHYS_VIRT && ARCH_MSM + source "init/Kconfig" source "kernel/Kconfig.freezer" diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h index 7197879e1cb..2398b3fc026 100644 --- a/arch/arm/include/asm/memory.h +++ b/arch/arm/include/asm/memory.h @@ -154,29 +154,42 @@ #ifndef __virt_to_phys #ifdef CONFIG_ARM_PATCH_PHYS_VIRT +/* + * Constants used to force the right instruction encodings and shifts + * so that all we need to do is modify the 8-bit constant field. + */ +#define __PV_BITS_31_24 0x81000000 +#define __PV_BITS_23_16 0x00810000 + extern unsigned long __pv_phys_offset; #define PHYS_OFFSET __pv_phys_offset -#define __pv_stub(from,to,instr) \ +#define __pv_stub(from,to,instr,type) \ __asm__("@ __pv_stub\n" \ "1: " instr " %0, %1, %2\n" \ " .pushsection .pv_table,\"a\"\n" \ " .long 1b\n" \ " .popsection\n" \ : "=r" (to) \ - : "r" (from), "I" (0x81000000)) + : "r" (from), "I" (type)) static inline unsigned long __virt_to_phys(unsigned long x) { unsigned long t; - __pv_stub(x, t, "add"); + __pv_stub(x, t, "add", __PV_BITS_31_24); +#ifdef CONFIG_ARM_PATCH_PHYS_VIRT_16BIT + __pv_stub(t, t, "add", __PV_BITS_23_16); +#endif return t; } static inline unsigned long __phys_to_virt(unsigned long x) { unsigned long t; - __pv_stub(x, t, "sub"); + __pv_stub(x, t, "sub", __PV_BITS_31_24); +#ifdef CONFIG_ARM_PATCH_PHYS_VIRT_16BIT + __pv_stub(t, t, "sub", __PV_BITS_23_16); +#endif return t; } #else diff --git a/arch/arm/include/asm/module.h b/arch/arm/include/asm/module.h index d072c21332e..a2b775b81cf 100644 --- a/arch/arm/include/asm/module.h +++ b/arch/arm/include/asm/module.h @@ -31,7 +31,11 @@ struct mod_arch_specific { /* Add __virt_to_phys patching state as well */ #ifdef CONFIG_ARM_PATCH_PHYS_VIRT +#ifdef CONFIG_ARM_PATCH_PHYS_VIRT_16BIT +#define MODULE_ARCH_VERMAGIC_P2V "p2v16 " +#else #define MODULE_ARCH_VERMAGIC_P2V "p2v8 " +#endif #else #define MODULE_ARCH_VERMAGIC_P2V "" #endif diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S index 1db8ead2e33..a94dd99d54c 100644 --- a/arch/arm/kernel/head.S +++ b/arch/arm/kernel/head.S @@ -456,8 +456,13 @@ __fixup_pv_table: add r4, r4, r3 @ adjust table start address add r5, r5, r3 @ adjust table end address str r8, [r7, r3]! @ save computed PHYS_OFFSET to __pv_phys_offset +#ifndef CONFIG_ARM_PATCH_PHYS_VIRT_16BIT mov r6, r3, lsr #24 @ constant for add/sub instructions teq r3, r6, lsl #24 @ must be 16MiB aligned +#else + mov r6, r3, lsr #16 @ constant for add/sub instructions + teq r3, r6, lsl #16 @ must be 64kiB aligned +#endif bne __error str r6, [r7, #4] @ save to __pv_offset b __fixup_a_pv_table @@ -471,10 +476,18 @@ ENDPROC(__fixup_pv_table) .text __fixup_a_pv_table: +#ifdef CONFIG_ARM_PATCH_PHYS_VIRT_16BIT + and r0, r6, #255 @ offset bits 23-16 + mov r6, r6, lsr #8 @ offset bits 31-24 +#else + mov r0, #0 @ just in case... +#endif b 3f 2: ldr ip, [r7, r3] bic ip, ip, #0x000000ff - orr ip, ip, r6 + tst ip, #0x400 @ rotate shift tells us LS or MS byte + orrne ip, ip, r6 @ mask in offset bits 31-24 + orreq ip, ip, r0 @ mask in offset bits 23-16 str ip, [r7, r3] 3: cmp r4, r5 ldrcc r7, [r4], #4 @ use branch for delay slot -- cgit v1.2.3-70-g09d2 From 4d901c4271951d110afb13ee9aa73d27a6c8e53d Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Wed, 2 Feb 2011 16:33:17 +0100 Subject: ARM: 6648/1: map ATAGs when not in first 1MB of RAM If ATAGs or DTB pointer is not within first 1MB of RAM, then the boot params will not be mapped early enough, so map the 1MB region that r2 points to. Only map the first 1MB when r2 is 0. Some assembly improvements from Nicolas Pitre. Acked-by: Tony Lindgren Acked-by: Nicolas Pitre Signed-off-by: Rob Herring Signed-off-by: Russell King --- arch/arm/kernel/head.S | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) (limited to 'arch/arm/kernel/head.S') diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S index a94dd99d54c..591a2ead8ce 100644 --- a/arch/arm/kernel/head.S +++ b/arch/arm/kernel/head.S @@ -206,11 +206,17 @@ __create_page_tables: #endif /* - * Then map first 1MB of ram in case it contains our boot params. + * Then map boot params address in r2 or + * the first 1MB of ram if boot params address is not specified. */ - add r0, r4, #PAGE_OFFSET >> 18 - orr r6, r7, r8 - str r6, [r0] + mov r0, r2, lsr #20 + movs r0, r0, lsl #20 + moveq r0, r8 + sub r3, r0, r8 + add r3, r3, #PAGE_OFFSET + add r3, r4, r3, lsr #18 + orr r6, r7, r0 + str r6, [r3] #ifdef CONFIG_DEBUG_LL #ifndef CONFIG_DEBUG_ICEDCC -- cgit v1.2.3-70-g09d2 From b511d75d6150892e67c8ebfa9dc8eb37ebd02aa3 Mon Sep 17 00:00:00 2001 From: Nicolas Pitre Date: Mon, 21 Feb 2011 06:53:35 +0100 Subject: ARM: 6747/1: P2V: Thumb2 support Adding Thumb2 support to the runtime patching of the virt_to_phys and phys_to_virt opcodes. Tested both the 8-bit and the 16-bit fixups, using different placements in memory to exercize all code paths. Signed-off-by: Nicolas Pitre Reviewed-by: Dave Martin Signed-off-by: Russell King --- arch/arm/Kconfig | 4 ++-- arch/arm/kernel/head.S | 49 ++++++++++++++++++++++++++++++++++++++++++++++++- 2 files changed, 50 insertions(+), 3 deletions(-) (limited to 'arch/arm/kernel/head.S') diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index b357c29e7df..0233c8ff1f1 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -194,13 +194,13 @@ config VECTORS_BASE config ARM_PATCH_PHYS_VIRT bool "Patch physical to virtual translations at runtime (EXPERIMENTAL)" depends on EXPERIMENTAL - depends on !XIP_KERNEL && !THUMB2_KERNEL && MMU + depends on !XIP_KERNEL && MMU depends on !ARCH_REALVIEW || !SPARSEMEM help Patch phys-to-virt translation functions at runtime according to the position of the kernel in system memory. - This can only be used with non-XIP, non-Thumb2, MMU kernels where + This can only be used with non-XIP with MMU kernels where the base of physical memory is at a 16MB boundary. config ARM_PATCH_PHYS_VIRT_16BIT diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S index 591a2ead8ce..6a87261e1b1 100644 --- a/arch/arm/kernel/head.S +++ b/arch/arm/kernel/head.S @@ -461,7 +461,8 @@ __fixup_pv_table: sub r3, r0, r3 @ PHYS_OFFSET - PAGE_OFFSET add r4, r4, r3 @ adjust table start address add r5, r5, r3 @ adjust table end address - str r8, [r7, r3]! @ save computed PHYS_OFFSET to __pv_phys_offset + add r7, r7, r3 @ adjust __pv_phys_offset address + str r8, [r7] @ save computed PHYS_OFFSET to __pv_phys_offset #ifndef CONFIG_ARM_PATCH_PHYS_VIRT_16BIT mov r6, r3, lsr #24 @ constant for add/sub instructions teq r3, r6, lsl #24 @ must be 16MiB aligned @@ -469,6 +470,7 @@ __fixup_pv_table: mov r6, r3, lsr #16 @ constant for add/sub instructions teq r3, r6, lsl #16 @ must be 64kiB aligned #endif +THUMB( it ne @ cross section branch ) bne __error str r6, [r7, #4] @ save to __pv_offset b __fixup_a_pv_table @@ -482,6 +484,50 @@ ENDPROC(__fixup_pv_table) .text __fixup_a_pv_table: +#ifdef CONFIG_THUMB2_KERNEL +#ifdef CONFIG_ARM_PATCH_PHYS_VIRT_16BIT + lsls r0, r6, #24 + lsr r6, #8 + beq 1f + clz r7, r0 + lsr r0, #24 + lsl r0, r7 + bic r0, 0x0080 + lsrs r7, #1 + orrcs r0, #0x0080 + orr r0, r0, r7, lsl #12 +#endif +1: lsls r6, #24 + beq 4f + clz r7, r6 + lsr r6, #24 + lsl r6, r7 + bic r6, #0x0080 + lsrs r7, #1 + orrcs r6, #0x0080 + orr r6, r6, r7, lsl #12 + orr r6, #0x4000 + b 4f +2: @ at this point the C flag is always clear + add r7, r3 +#ifdef CONFIG_ARM_PATCH_PHYS_VIRT_16BIT + ldrh ip, [r7] + tst ip, 0x0400 @ the i bit tells us LS or MS byte + beq 3f + cmp r0, #0 @ set C flag, and ... + biceq ip, 0x0400 @ immediate zero value has a special encoding + streqh ip, [r7] @ that requires the i bit cleared +#endif +3: ldrh ip, [r7, #2] + and ip, 0x8f00 + orrcc ip, r6 @ mask in offset bits 31-24 + orrcs ip, r0 @ mask in offset bits 23-16 + strh ip, [r7, #2] +4: cmp r4, r5 + ldrcc r7, [r4], #4 @ use branch for delay slot + bcc 2b + bx lr +#else #ifdef CONFIG_ARM_PATCH_PHYS_VIRT_16BIT and r0, r6, #255 @ offset bits 23-16 mov r6, r6, lsr #8 @ offset bits 31-24 @@ -499,6 +545,7 @@ __fixup_a_pv_table: ldrcc r7, [r4], #4 @ use branch for delay slot bcc 2b mov pc, lr +#endif ENDPROC(__fixup_a_pv_table) ENTRY(fixup_pv_table) -- cgit v1.2.3-70-g09d2