diff options
Diffstat (limited to 'arch/arm/mm')
-rw-r--r-- | arch/arm/mm/Kconfig | 46 | ||||
-rw-r--r-- | arch/arm/mm/abort-ev6.S | 5 | ||||
-rw-r--r-- | arch/arm/mm/alignment.c | 9 | ||||
-rw-r--r-- | arch/arm/mm/cache-v7.S | 14 | ||||
-rw-r--r-- | arch/arm/mm/context.c | 55 | ||||
-rw-r--r-- | arch/arm/mm/dma-mapping.c | 2 | ||||
-rw-r--r-- | arch/arm/mm/extable.c | 7 | ||||
-rw-r--r-- | arch/arm/mm/fault.c | 13 | ||||
-rw-r--r-- | arch/arm/mm/init.c | 2 | ||||
-rw-r--r-- | arch/arm/mm/ioremap.c | 10 | ||||
-rw-r--r-- | arch/arm/mm/mmap.c | 8 | ||||
-rw-r--r-- | arch/arm/mm/mmu.c | 24 | ||||
-rw-r--r-- | arch/arm/mm/nommu.c | 6 | ||||
-rw-r--r-- | arch/arm/mm/pgd.c | 3 | ||||
-rw-r--r-- | arch/arm/mm/proc-macros.S | 19 | ||||
-rw-r--r-- | arch/arm/mm/proc-v6.S | 7 | ||||
-rw-r--r-- | arch/arm/mm/proc-v7-2level.S | 9 | ||||
-rw-r--r-- | arch/arm/mm/proc-v7-3level.S | 20 | ||||
-rw-r--r-- | arch/arm/mm/proc-v7.S | 17 |
19 files changed, 192 insertions, 84 deletions
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig index 35955b54944c..36e9f24e03b0 100644 --- a/arch/arm/mm/Kconfig +++ b/arch/arm/mm/Kconfig @@ -411,28 +411,31 @@ config CPU_32v3 select CPU_USE_DOMAINS if MMU select NEEDS_SYSCALL_FOR_CMPXCHG if SMP select TLS_REG_EMUL if SMP || !MMU + select NEED_KUSER_HELPERS config CPU_32v4 bool select CPU_USE_DOMAINS if MMU select NEEDS_SYSCALL_FOR_CMPXCHG if SMP select TLS_REG_EMUL if SMP || !MMU + select NEED_KUSER_HELPERS config CPU_32v4T bool select CPU_USE_DOMAINS if MMU select NEEDS_SYSCALL_FOR_CMPXCHG if SMP select TLS_REG_EMUL if SMP || !MMU + select NEED_KUSER_HELPERS config CPU_32v5 bool select CPU_USE_DOMAINS if MMU select NEEDS_SYSCALL_FOR_CMPXCHG if SMP select TLS_REG_EMUL if SMP || !MMU + select NEED_KUSER_HELPERS config CPU_32v6 bool - select CPU_USE_DOMAINS if CPU_V6 && MMU select TLS_REG_EMUL if !CPU_32v6K && !MMU config CPU_32v6K @@ -647,7 +650,7 @@ config ARM_VIRT_EXT config SWP_EMULATE bool "Emulate SWP/SWPB instructions" - depends on !CPU_USE_DOMAINS && CPU_V7 + depends on CPU_V7 default y if SMP select HAVE_PROC_CPU if PROC_FS help @@ -756,6 +759,7 @@ config CPU_BPREDICT_DISABLE config TLS_REG_EMUL bool + select NEED_KUSER_HELPERS help An SMP system using a pre-ARMv6 processor (there are apparently a few prototypes like that in existence) and therefore access to @@ -763,11 +767,43 @@ config TLS_REG_EMUL config NEEDS_SYSCALL_FOR_CMPXCHG bool + select NEED_KUSER_HELPERS help SMP on a pre-ARMv6 processor? Well OK then. Forget about fast user space cmpxchg support. It is just not possible. +config NEED_KUSER_HELPERS + bool + +config KUSER_HELPERS + bool "Enable kuser helpers in vector page" if !NEED_KUSER_HELPERS + default y + help + Warning: disabling this option may break user programs. + + Provide kuser helpers in the vector page. The kernel provides + helper code to userspace in read only form at a fixed location + in the high vector page to allow userspace to be independent of + the CPU type fitted to the system. This permits binaries to be + run on ARMv4 through to ARMv7 without modification. + + See Documentation/arm/kernel_user_helpers.txt for details. + + However, the fixed address nature of these helpers can be used + by ROP (return orientated programming) authors when creating + exploits. + + If all of the binaries and libraries which run on your platform + are built specifically for your platform, and make no use of + these helpers, then you can turn this option off to hinder + such exploits. However, in that case, if a binary or library + relying on those helpers is run, it will receive a SIGILL signal, + which will terminate the program. + + Say N here only if you are absolutely certain that you do not + need these helpers; otherwise, the safe option is to say Y. + config DMA_CACHE_RWFO bool "Enable read/write for ownership DMA cache maintenance" depends on CPU_V6K && SMP @@ -895,3 +931,9 @@ config ARCH_HAS_BARRIERS help This option allows the use of custom mandatory barriers included via the mach/barriers.h file. + +config ARCH_SUPPORTS_BIG_ENDIAN + bool + help + This option specifies the architecture can support big endian + operation. diff --git a/arch/arm/mm/abort-ev6.S b/arch/arm/mm/abort-ev6.S index 80741992a9fc..3815a8262af0 100644 --- a/arch/arm/mm/abort-ev6.S +++ b/arch/arm/mm/abort-ev6.S @@ -38,9 +38,8 @@ ENTRY(v6_early_abort) bne do_DataAbort bic r1, r1, #1 << 11 @ clear bit 11 of FSR ldr r3, [r4] @ read aborted ARM instruction -#ifdef CONFIG_CPU_ENDIAN_BE8 - rev r3, r3 -#endif + ARM_BE8(rev r3, r3) + do_ldrd_abort tmp=ip, insn=r3 tst r3, #1 << 20 @ L = 0 -> write orreq r1, r1, #1 << 11 @ yes. diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c index 6f4585b89078..924036473b16 100644 --- a/arch/arm/mm/alignment.c +++ b/arch/arm/mm/alignment.c @@ -25,6 +25,7 @@ #include <asm/cp15.h> #include <asm/system_info.h> #include <asm/unaligned.h> +#include <asm/opcodes.h> #include "fault.h" @@ -762,21 +763,25 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs) if (thumb_mode(regs)) { u16 *ptr = (u16 *)(instrptr & ~1); fault = probe_kernel_address(ptr, tinstr); + tinstr = __mem_to_opcode_thumb16(tinstr); if (!fault) { if (cpu_architecture() >= CPU_ARCH_ARMv7 && IS_T32(tinstr)) { /* Thumb-2 32-bit */ u16 tinst2 = 0; fault = probe_kernel_address(ptr + 1, tinst2); - instr = (tinstr << 16) | tinst2; + tinst2 = __mem_to_opcode_thumb16(tinst2); + instr = __opcode_thumb32_compose(tinstr, tinst2); thumb2_32b = 1; } else { isize = 2; instr = thumb2arm(tinstr); } } - } else + } else { fault = probe_kernel_address(instrptr, instr); + instr = __mem_to_opcode_arm(instr); + } if (fault) { type = TYPE_FAULT; diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S index 515b00064da8..a84e0536ce74 100644 --- a/arch/arm/mm/cache-v7.S +++ b/arch/arm/mm/cache-v7.S @@ -146,18 +146,18 @@ flush_levels: ldr r7, =0x7fff ands r7, r7, r1, lsr #13 @ extract max number of the index size loop1: - mov r9, r4 @ create working copy of max way size + mov r9, r7 @ create working copy of max index loop2: - ARM( orr r11, r10, r9, lsl r5 ) @ factor way and cache number into r11 - THUMB( lsl r6, r9, r5 ) + ARM( orr r11, r10, r4, lsl r5 ) @ factor way and cache number into r11 + THUMB( lsl r6, r4, r5 ) THUMB( orr r11, r10, r6 ) @ factor way and cache number into r11 - ARM( orr r11, r11, r7, lsl r2 ) @ factor index number into r11 - THUMB( lsl r6, r7, r2 ) + ARM( orr r11, r11, r9, lsl r2 ) @ factor index number into r11 + THUMB( lsl r6, r9, 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 + subs r9, r9, #1 @ decrement the index bge loop2 - subs r7, r7, #1 @ decrement the index + subs r4, r4, #1 @ decrement the way bge loop1 skip: add r10, r10, #2 @ increment cache number diff --git a/arch/arm/mm/context.c b/arch/arm/mm/context.c index 2ac37372ef52..eeab06ebd06e 100644 --- a/arch/arm/mm/context.c +++ b/arch/arm/mm/context.c @@ -39,19 +39,43 @@ * non 64-bit operations. */ #define ASID_FIRST_VERSION (1ULL << ASID_BITS) -#define NUM_USER_ASIDS (ASID_FIRST_VERSION - 1) - -#define ASID_TO_IDX(asid) ((asid & ~ASID_MASK) - 1) -#define IDX_TO_ASID(idx) ((idx + 1) & ~ASID_MASK) +#define NUM_USER_ASIDS ASID_FIRST_VERSION static DEFINE_RAW_SPINLOCK(cpu_asid_lock); static atomic64_t asid_generation = ATOMIC64_INIT(ASID_FIRST_VERSION); static DECLARE_BITMAP(asid_map, NUM_USER_ASIDS); -DEFINE_PER_CPU(atomic64_t, active_asids); +static DEFINE_PER_CPU(atomic64_t, active_asids); static DEFINE_PER_CPU(u64, reserved_asids); static cpumask_t tlb_flush_pending; +#ifdef CONFIG_ARM_ERRATA_798181 +void a15_erratum_get_cpumask(int this_cpu, struct mm_struct *mm, + cpumask_t *mask) +{ + int cpu; + unsigned long flags; + u64 context_id, asid; + + raw_spin_lock_irqsave(&cpu_asid_lock, flags); + context_id = mm->context.id.counter; + for_each_online_cpu(cpu) { + if (cpu == this_cpu) + continue; + /* + * We only need to send an IPI if the other CPUs are + * running the same ASID as the one being invalidated. + */ + asid = per_cpu(active_asids, cpu).counter; + if (asid == 0) + asid = per_cpu(reserved_asids, cpu); + if (context_id == asid) + cpumask_set_cpu(cpu, mask); + } + raw_spin_unlock_irqrestore(&cpu_asid_lock, flags); +} +#endif + #ifdef CONFIG_ARM_LPAE static void cpu_set_reserved_ttbr0(void) { @@ -128,7 +152,16 @@ static void flush_context(unsigned int cpu) asid = 0; } else { asid = atomic64_xchg(&per_cpu(active_asids, i), 0); - __set_bit(ASID_TO_IDX(asid), asid_map); + /* + * If this CPU has already been through a + * rollover, but hasn't run another task in + * the meantime, we must preserve its reserved + * ASID, as this is the only trace we have of + * the process it is still running. + */ + if (asid == 0) + asid = per_cpu(reserved_asids, i); + __set_bit(asid & ~ASID_MASK, asid_map); } per_cpu(reserved_asids, i) = asid; } @@ -167,17 +200,19 @@ static u64 new_context(struct mm_struct *mm, unsigned int cpu) /* * Allocate a free ASID. If we can't find one, take a * note of the currently active ASIDs and mark the TLBs - * as requiring flushes. + * as requiring flushes. We always count from ASID #1, + * as we reserve ASID #0 to switch via TTBR0 and indicate + * rollover events. */ - asid = find_first_zero_bit(asid_map, NUM_USER_ASIDS); + asid = find_next_zero_bit(asid_map, NUM_USER_ASIDS, 1); if (asid == NUM_USER_ASIDS) { generation = atomic64_add_return(ASID_FIRST_VERSION, &asid_generation); flush_context(cpu); - asid = find_first_zero_bit(asid_map, NUM_USER_ASIDS); + asid = find_next_zero_bit(asid_map, NUM_USER_ASIDS, 1); } __set_bit(asid, asid_map); - asid = generation | IDX_TO_ASID(asid); + asid |= generation; cpumask_clear(mm_cpumask(mm)); } diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index 1fb40dc37ec2..051e904a5379 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -1311,7 +1311,7 @@ static void *arm_iommu_alloc_attrs(struct device *dev, size_t size, *handle = DMA_ERROR_CODE; size = PAGE_ALIGN(size); - if (gfp & GFP_ATOMIC) + if (!(gfp & __GFP_WAIT)) return __iommu_alloc_atomic(dev, size, handle); pages = __iommu_alloc_buffer(dev, size, gfp, attrs); diff --git a/arch/arm/mm/extable.c b/arch/arm/mm/extable.c index 9d285626bc7d..312e15e6d00b 100644 --- a/arch/arm/mm/extable.c +++ b/arch/arm/mm/extable.c @@ -9,8 +9,13 @@ int fixup_exception(struct pt_regs *regs) const struct exception_table_entry *fixup; fixup = search_exception_tables(instruction_pointer(regs)); - if (fixup) + if (fixup) { regs->ARM_pc = fixup->fixup; +#ifdef CONFIG_THUMB2_KERNEL + /* Clear the IT state to avoid nasty surprises in the fixup */ + regs->ARM_cpsr &= ~PSR_IT_MASK; +#endif + } return fixup != NULL; } diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c index 5dbf13f954f6..e207aa5f846f 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -446,8 +446,16 @@ do_translation_fault(unsigned long addr, unsigned int fsr, if (pud_none(*pud_k)) goto bad_area; - if (!pud_present(*pud)) + if (!pud_present(*pud)) { set_pud(pud, *pud_k); + /* + * There is a small window during free_pgtables() where the + * user *pud entry is 0 but the TLB has not been invalidated + * and we get a level 2 (pmd) translation fault caused by the + * intermediate TLB caching of the old level 1 (pud) entry. + */ + flush_tlb_kernel_page(addr); + } pmd = pmd_offset(pud, addr); pmd_k = pmd_offset(pud_k, addr); @@ -470,8 +478,9 @@ do_translation_fault(unsigned long addr, unsigned int fsr, #endif if (pmd_none(pmd_k[index])) goto bad_area; + if (!pmd_present(pmd[index])) + copy_pmd(pmd, pmd_k); - copy_pmd(pmd, pmd_k); return 0; bad_area: diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c index afeaef7a8ffc..c12ae661d4ab 100644 --- a/arch/arm/mm/init.c +++ b/arch/arm/mm/init.c @@ -600,7 +600,7 @@ void __init mem_init(void) #ifdef CONFIG_SA1111 /* now that our DMA memory is actually so designated, we can free it */ - free_reserved_area(__va(PHYS_PFN_OFFSET), swapper_pg_dir, 0, NULL); + free_reserved_area(__va(PHYS_OFFSET), swapper_pg_dir, 0, NULL); #endif free_highpages(); diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c index 04d9006eab1f..f123d6eb074b 100644 --- a/arch/arm/mm/ioremap.c +++ b/arch/arm/mm/ioremap.c @@ -331,10 +331,10 @@ void __iomem * __arm_ioremap_pfn_caller(unsigned long pfn, return (void __iomem *) (offset + addr); } -void __iomem *__arm_ioremap_caller(unsigned long phys_addr, size_t size, +void __iomem *__arm_ioremap_caller(phys_addr_t phys_addr, size_t size, unsigned int mtype, void *caller) { - unsigned long last_addr; + phys_addr_t last_addr; unsigned long offset = phys_addr & ~PAGE_MASK; unsigned long pfn = __phys_to_pfn(phys_addr); @@ -367,12 +367,12 @@ __arm_ioremap_pfn(unsigned long pfn, unsigned long offset, size_t size, } EXPORT_SYMBOL(__arm_ioremap_pfn); -void __iomem * (*arch_ioremap_caller)(unsigned long, size_t, +void __iomem * (*arch_ioremap_caller)(phys_addr_t, size_t, unsigned int, void *) = __arm_ioremap_caller; void __iomem * -__arm_ioremap(unsigned long phys_addr, size_t size, unsigned int mtype) +__arm_ioremap(phys_addr_t phys_addr, size_t size, unsigned int mtype) { return arch_ioremap_caller(phys_addr, size, mtype, __builtin_return_address(0)); @@ -387,7 +387,7 @@ EXPORT_SYMBOL(__arm_ioremap); * CONFIG_GENERIC_ALLOCATOR for allocating external memory. */ void __iomem * -__arm_ioremap_exec(unsigned long phys_addr, size_t size, bool cached) +__arm_ioremap_exec(phys_addr_t phys_addr, size_t size, bool cached) { unsigned int mtype; diff --git a/arch/arm/mm/mmap.c b/arch/arm/mm/mmap.c index 10062ceadd1c..5ef506c6f492 100644 --- a/arch/arm/mm/mmap.c +++ b/arch/arm/mm/mmap.c @@ -146,7 +146,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, info.flags = VM_UNMAPPED_AREA_TOPDOWN; info.length = len; - info.low_limit = PAGE_SIZE; + info.low_limit = FIRST_USER_ADDRESS; info.high_limit = mm->mmap_base; info.align_mask = do_align ? (PAGE_MASK & (SHMLBA - 1)) : 0; info.align_offset = pgoff << PAGE_SHIFT; @@ -204,13 +204,11 @@ int valid_phys_addr_range(phys_addr_t addr, size_t size) } /* - * We don't use supersection mappings for mmap() on /dev/mem, which - * means that we can't map the memory area above the 4G barrier into - * userspace. + * Do not allow /dev/mem mappings beyond the supported physical range. */ int valid_mmap_phys_addr_range(unsigned long pfn, size_t size) { - return !(pfn + (size >> PAGE_SHIFT) > 0x00100000); + return (pfn + (size >> PAGE_SHIFT)) <= (1 + (PHYS_MASK >> PAGE_SHIFT)); } #ifdef CONFIG_STRICT_DEVMEM diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index 4d409e6a552d..fb3c446af9e5 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -459,6 +459,16 @@ static void __init build_mem_type_table(void) hyp_device_pgprot = s2_device_pgprot = mem_types[MT_DEVICE].prot_pte; /* + * We don't use domains on ARMv6 (since this causes problems with + * v6/v7 kernels), so we must use a separate memory type for user + * r/o, kernel r/w to map the vectors page. + */ +#ifndef CONFIG_ARM_LPAE + if (cpu_arch == CPU_ARCH_ARMv6) + vecs_pgprot |= L_PTE_MT_VECTORS; +#endif + + /* * ARMv6 and above have extended page tables. */ if (cpu_arch >= CPU_ARCH_ARMv6 && (cr & CR_XP)) { @@ -1175,7 +1185,7 @@ static void __init devicemaps_init(struct machine_desc *mdesc) /* * Allocate the vector page early. */ - vectors = early_alloc(PAGE_SIZE); + vectors = early_alloc(PAGE_SIZE * 2); early_trap_init(vectors); @@ -1220,15 +1230,27 @@ static void __init devicemaps_init(struct machine_desc *mdesc) map.pfn = __phys_to_pfn(virt_to_phys(vectors)); map.virtual = 0xffff0000; map.length = PAGE_SIZE; +#ifdef CONFIG_KUSER_HELPERS map.type = MT_HIGH_VECTORS; +#else + map.type = MT_LOW_VECTORS; +#endif create_mapping(&map); if (!vectors_high()) { map.virtual = 0; + map.length = PAGE_SIZE * 2; map.type = MT_LOW_VECTORS; create_mapping(&map); } + /* Now create a kernel read-only mapping */ + map.pfn += 1; + map.virtual = 0xffff0000 + PAGE_SIZE; + map.length = PAGE_SIZE; + map.type = MT_LOW_VECTORS; + create_mapping(&map); + /* * Ask the machine support to map in the statically mapped devices. */ diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c index eb5293a69a84..7fe0524a5449 100644 --- a/arch/arm/mm/nommu.c +++ b/arch/arm/mm/nommu.c @@ -87,16 +87,16 @@ void __iomem *__arm_ioremap_pfn_caller(unsigned long pfn, unsigned long offset, return __arm_ioremap_pfn(pfn, offset, size, mtype); } -void __iomem *__arm_ioremap(unsigned long phys_addr, size_t size, +void __iomem *__arm_ioremap(phys_addr_t phys_addr, size_t size, unsigned int mtype) { return (void __iomem *)phys_addr; } EXPORT_SYMBOL(__arm_ioremap); -void __iomem * (*arch_ioremap_caller)(unsigned long, size_t, unsigned int, void *); +void __iomem * (*arch_ioremap_caller)(phys_addr_t, size_t, unsigned int, void *); -void __iomem *__arm_ioremap_caller(unsigned long phys_addr, size_t size, +void __iomem *__arm_ioremap_caller(phys_addr_t phys_addr, size_t size, unsigned int mtype, void *caller) { return __arm_ioremap(phys_addr, size, mtype); diff --git a/arch/arm/mm/pgd.c b/arch/arm/mm/pgd.c index 0acb089d0f70..1046b373d1ae 100644 --- a/arch/arm/mm/pgd.c +++ b/arch/arm/mm/pgd.c @@ -87,7 +87,8 @@ pgd_t *pgd_alloc(struct mm_struct *mm) init_pud = pud_offset(init_pgd, 0); init_pmd = pmd_offset(init_pud, 0); init_pte = pte_offset_map(init_pmd, 0); - set_pte_ext(new_pte, *init_pte, 0); + set_pte_ext(new_pte + 0, init_pte[0], 0); + set_pte_ext(new_pte + 1, init_pte[1], 0); pte_unmap(init_pte); pte_unmap(new_pte); } diff --git a/arch/arm/mm/proc-macros.S b/arch/arm/mm/proc-macros.S index e3c48a3fe063..ee1d80593958 100644 --- a/arch/arm/mm/proc-macros.S +++ b/arch/arm/mm/proc-macros.S @@ -112,13 +112,9 @@ * 100x 1 0 1 r/o no acc * 10x0 1 0 1 r/o no acc * 1011 0 0 1 r/w no acc - * 110x 0 1 0 r/w r/o - * 11x0 0 1 0 r/w r/o - * 1111 0 1 1 r/w r/w - * - * If !CONFIG_CPU_USE_DOMAINS, the following permissions are changed: * 110x 1 1 1 r/o r/o * 11x0 1 1 1 r/o r/o + * 1111 0 1 1 r/w r/w */ .macro armv6_mt_table pfx \pfx\()_mt_table: @@ -137,7 +133,7 @@ .long PTE_EXT_TEX(2) @ L_PTE_MT_DEV_NONSHARED .long 0x00 @ unused .long 0x00 @ unused - .long 0x00 @ unused + .long PTE_CACHEABLE | PTE_BUFFERABLE | PTE_EXT_APX @ L_PTE_MT_VECTORS .endm .macro armv6_set_pte_ext pfx @@ -158,24 +154,21 @@ tst r1, #L_PTE_USER orrne r3, r3, #PTE_EXT_AP1 -#ifdef CONFIG_CPU_USE_DOMAINS - @ allow kernel read/write access to read-only user pages tstne r3, #PTE_EXT_APX - bicne r3, r3, #PTE_EXT_APX | PTE_EXT_AP0 -#endif + + @ user read-only -> kernel read-only + bicne r3, r3, #PTE_EXT_AP0 tst r1, #L_PTE_XN orrne r3, r3, #PTE_EXT_XN - orr r3, r3, r2 + eor r3, r3, r2 tst r1, #L_PTE_YOUNG tstne r1, #L_PTE_PRESENT moveq r3, #0 -#ifndef CONFIG_CPU_USE_DOMAINS tstne r1, #L_PTE_NONE movne r3, #0 -#endif str r3, [r0] mcr p15, 0, r0, c7, c10, 1 @ flush_pte diff --git a/arch/arm/mm/proc-v6.S b/arch/arm/mm/proc-v6.S index 919405e20b80..b96c6e64943e 100644 --- a/arch/arm/mm/proc-v6.S +++ b/arch/arm/mm/proc-v6.S @@ -206,7 +206,6 @@ __v6_setup: mcr p15, 0, r0, c7, c14, 0 @ clean+invalidate D cache mcr p15, 0, r0, c7, c5, 0 @ invalidate I cache mcr p15, 0, r0, c7, c15, 0 @ clean+invalidate cache - mcr p15, 0, r0, c7, c10, 4 @ drain write buffer #ifdef CONFIG_MMU mcr p15, 0, r0, c8, c7, 0 @ invalidate I + D TLBs mcr p15, 0, r0, c2, c0, 2 @ TTB control register @@ -216,11 +215,11 @@ __v6_setup: ALT_UP(orr r8, r8, #TTB_FLAGS_UP) mcr p15, 0, r8, c2, c0, 1 @ load TTB1 #endif /* CONFIG_MMU */ + mcr p15, 0, r0, c7, c10, 4 @ drain write buffer and + @ complete invalidations adr r5, v6_crval ldmia r5, {r5, r6} -#ifdef CONFIG_CPU_ENDIAN_BE8 - orr r6, r6, #1 << 25 @ big-endian page tables -#endif + ARM_BE8(orr r6, r6, #1 << 25) @ big-endian page tables mrc p15, 0, r0, c1, c0, 0 @ read control register bic r0, r0, r5 @ clear bits them orr r0, r0, r6 @ set them diff --git a/arch/arm/mm/proc-v7-2level.S b/arch/arm/mm/proc-v7-2level.S index 9704097c450e..bb20ba0f7bc7 100644 --- a/arch/arm/mm/proc-v7-2level.S +++ b/arch/arm/mm/proc-v7-2level.S @@ -90,27 +90,20 @@ ENTRY(cpu_v7_set_pte_ext) tst r1, #L_PTE_USER orrne r3, r3, #PTE_EXT_AP1 -#ifdef CONFIG_CPU_USE_DOMAINS - @ allow kernel read/write access to read-only user pages - tstne r3, #PTE_EXT_APX - bicne r3, r3, #PTE_EXT_APX | PTE_EXT_AP0 -#endif tst r1, #L_PTE_XN orrne r3, r3, #PTE_EXT_XN tst r1, #L_PTE_YOUNG tstne r1, #L_PTE_VALID -#ifndef CONFIG_CPU_USE_DOMAINS eorne r1, r1, #L_PTE_NONE tstne r1, #L_PTE_NONE -#endif moveq r3, #0 ARM( str r3, [r0, #2048]! ) THUMB( add r0, r0, #2048 ) THUMB( str r3, [r0] ) - ALT_SMP(mov pc,lr) + ALT_SMP(W(nop)) ALT_UP (mcr p15, 0, r0, c7, c10, 1) @ flush_pte #endif mov pc, lr diff --git a/arch/arm/mm/proc-v7-3level.S b/arch/arm/mm/proc-v7-3level.S index 363027e811d6..6f3b0476b729 100644 --- a/arch/arm/mm/proc-v7-3level.S +++ b/arch/arm/mm/proc-v7-3level.S @@ -56,6 +56,14 @@ ENTRY(cpu_v7_switch_mm) mov pc, lr ENDPROC(cpu_v7_switch_mm) +#ifdef __ARMEB__ +#define rl r3 +#define rh r2 +#else +#define rl r2 +#define rh r3 +#endif + /* * cpu_v7_set_pte_ext(ptep, pte) * @@ -65,15 +73,15 @@ ENDPROC(cpu_v7_switch_mm) */ ENTRY(cpu_v7_set_pte_ext) #ifdef CONFIG_MMU - tst r2, #L_PTE_VALID + tst rl, #L_PTE_VALID beq 1f - tst r3, #1 << (57 - 32) @ L_PTE_NONE - bicne r2, #L_PTE_VALID + tst rh, #1 << (57 - 32) @ L_PTE_NONE + bicne rl, #L_PTE_VALID bne 1f - tst r3, #1 << (55 - 32) @ L_PTE_DIRTY - orreq r2, #L_PTE_RDONLY + tst rh, #1 << (55 - 32) @ L_PTE_DIRTY + orreq rl, #L_PTE_RDONLY 1: strd r2, r3, [r0] - ALT_SMP(mov pc, lr) + ALT_SMP(W(nop)) ALT_UP (mcr p15, 0, r0, c7, c10, 1) @ flush_pte #endif mov pc, lr diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S index e35fec34453e..769496e6e8e9 100644 --- a/arch/arm/mm/proc-v7.S +++ b/arch/arm/mm/proc-v7.S @@ -75,13 +75,14 @@ ENTRY(cpu_v7_do_idle) ENDPROC(cpu_v7_do_idle) ENTRY(cpu_v7_dcache_clean_area) - ALT_SMP(mov pc, lr) @ MP extensions imply L1 PTW - ALT_UP(W(nop)) - dcache_line_size r2, r3 -1: mcr p15, 0, r0, c7, c10, 1 @ clean D entry + ALT_SMP(W(nop)) @ MP extensions imply L1 PTW + ALT_UP_B(1f) + mov pc, lr +1: dcache_line_size r2, r3 +2: mcr p15, 0, r0, c7, c10, 1 @ clean D entry add r0, r0, r2 subs r1, r1, r2 - bhi 1b + bhi 2b dsb mov pc, lr ENDPROC(cpu_v7_dcache_clean_area) @@ -328,7 +329,6 @@ __v7_setup: 3: mov r10, #0 mcr p15, 0, r10, c7, c5, 0 @ I+BTB cache invalidate - dsb #ifdef CONFIG_MMU mcr p15, 0, r10, c8, c7, 0 @ invalidate I + D TLBs v7_ttb_setup r10, r4, r8, r5 @ TTBCR, TTBRx setup @@ -337,6 +337,7 @@ __v7_setup: mcr p15, 0, r5, c10, c2, 0 @ write PRRR mcr p15, 0, r6, c10, c2, 1 @ write NMRR #endif + dsb @ Complete invalidations #ifndef CONFIG_ARM_THUMBEE mrc p15, 0, r0, c0, c1, 0 @ read ID_PFR0 for ThumbEE and r0, r0, #(0xf << 12) @ ThumbEE enabled field @@ -351,9 +352,7 @@ __v7_setup: #endif adr r5, v7_crval ldmia r5, {r5, r6} -#ifdef CONFIG_CPU_ENDIAN_BE8 - orr r6, r6, #1 << 25 @ big-endian page tables -#endif + ARM_BE8(orr r6, r6, #1 << 25) @ big-endian page tables #ifdef CONFIG_SWP_EMULATE orr r5, r5, #(1 << 10) @ set SW bit in "clear" bic r6, r6, #(1 << 10) @ clear it in "mmuset" |