diff options
Diffstat (limited to 'arch/arm/mm')
34 files changed, 607 insertions, 618 deletions
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig index 3fd629d..35955b5 100644 --- a/arch/arm/mm/Kconfig +++ b/arch/arm/mm/Kconfig @@ -43,7 +43,7 @@ config CPU_ARM740T depends on !MMU select CPU_32v4T select CPU_ABRT_LV4T - select CPU_CACHE_V3 # although the core is v4t + select CPU_CACHE_V4 select CPU_CP15_MPU select CPU_PABRT_LEGACY help @@ -397,6 +397,13 @@ config CPU_V7 select CPU_PABRT_V7 select CPU_TLB_V7 if MMU +config CPU_THUMBONLY + bool + # There are no CPUs available with MMU that don't implement an ARM ISA: + depends on !MMU + help + Select this if your CPU doesn't support the 32 bit ARM instructions. + # Figure out what processor architecture version we should be using. # This defines the compiler instruction set which depends on the machine type. config CPU_32v3 @@ -469,9 +476,6 @@ config CPU_PABRT_V7 bool # The cache model -config CPU_CACHE_V3 - bool - config CPU_CACHE_V4 bool @@ -608,7 +612,7 @@ config ARCH_DMA_ADDR_T_64BIT bool config ARM_THUMB - bool "Support Thumb user binaries" + bool "Support Thumb user binaries" if !CPU_THUMBONLY depends on CPU_ARM720T || CPU_ARM740T || CPU_ARM920T || CPU_ARM922T || CPU_ARM925T || CPU_ARM926T || CPU_ARM940T || CPU_ARM946E || CPU_ARM1020 || CPU_ARM1020E || CPU_ARM1022 || CPU_ARM1026 || CPU_XSCALE || CPU_XSC3 || CPU_MOHAWK || CPU_V6 || CPU_V6K || CPU_V7 || CPU_FEROCEON default y help @@ -629,8 +633,9 @@ config ARM_THUMBEE make use of it. Say N for code that can run on CPUs without ThumbEE. config ARM_VIRT_EXT - bool "Native support for the ARM Virtualization Extensions" - depends on MMU && CPU_V7 + bool + depends on MMU + default y if CPU_V7 help Enable the kernel to make use of the ARM Virtualization Extensions to install hypervisors without run-time firmware @@ -640,11 +645,6 @@ config ARM_VIRT_EXT use of this feature. Refer to Documentation/arm/Booting for details. - It is safe to enable this option even if the kernel may not be - booted in HYP mode, may not have support for the - virtualization extensions, or may be booted with a - non-compliant bootloader. - config SWP_EMULATE bool "Emulate SWP/SWPB instructions" depends on !CPU_USE_DOMAINS && CPU_V7 diff --git a/arch/arm/mm/Makefile b/arch/arm/mm/Makefile index 8a9c4cb..9e51be9 100644 --- a/arch/arm/mm/Makefile +++ b/arch/arm/mm/Makefile @@ -6,7 +6,7 @@ obj-y := dma-mapping.o extable.o fault.o init.o \ iomap.o obj-$(CONFIG_MMU) += fault-armv.o flush.o idmap.o ioremap.o \ - mmap.o pgd.o mmu.o vmregion.o + mmap.o pgd.o mmu.o ifneq ($(CONFIG_MMU),y) obj-y += nommu.o @@ -33,7 +33,6 @@ obj-$(CONFIG_CPU_PABRT_LEGACY) += pabort-legacy.o obj-$(CONFIG_CPU_PABRT_V6) += pabort-v6.o obj-$(CONFIG_CPU_PABRT_V7) += pabort-v7.o -obj-$(CONFIG_CPU_CACHE_V3) += cache-v3.o obj-$(CONFIG_CPU_CACHE_V4) += cache-v4.o obj-$(CONFIG_CPU_CACHE_V4WT) += cache-v4wt.o obj-$(CONFIG_CPU_CACHE_V4WB) += cache-v4wb.o diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c index b820eda..6f4585b 100644 --- a/arch/arm/mm/alignment.c +++ b/arch/arm/mm/alignment.c @@ -749,7 +749,6 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs) unsigned long instr = 0, instrptr; int (*handler)(unsigned long addr, unsigned long instr, struct pt_regs *regs); unsigned int type; - mm_segment_t fs; unsigned int fault; u16 tinstr = 0; int isize = 4; @@ -760,16 +759,15 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs) instrptr = instruction_pointer(regs); - fs = get_fs(); - set_fs(KERNEL_DS); if (thumb_mode(regs)) { - fault = __get_user(tinstr, (u16 *)(instrptr & ~1)); + u16 *ptr = (u16 *)(instrptr & ~1); + fault = probe_kernel_address(ptr, tinstr); if (!fault) { if (cpu_architecture() >= CPU_ARCH_ARMv7 && IS_T32(tinstr)) { /* Thumb-2 32-bit */ u16 tinst2 = 0; - fault = __get_user(tinst2, (u16 *)(instrptr+2)); + fault = probe_kernel_address(ptr + 1, tinst2); instr = (tinstr << 16) | tinst2; thumb2_32b = 1; } else { @@ -778,8 +776,7 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs) } } } else - fault = __get_user(instr, (u32 *)instrptr); - set_fs(fs); + fault = probe_kernel_address(instrptr, instr); if (fault) { type = TYPE_FAULT; @@ -964,12 +961,14 @@ static int __init alignment_init(void) return -ENOMEM; #endif +#ifdef CONFIG_CPU_CP15 if (cpu_is_v6_unaligned()) { cr_alignment &= ~CR_A; cr_no_alignment &= ~CR_A; set_cr(cr_alignment); ai_usermode = safe_usermode(ai_usermode, false); } +#endif hook_fault_code(FAULT_CODE_ALIGNMENT, do_alignment, SIGBUS, BUS_ADRALN, "alignment exception"); diff --git a/arch/arm/mm/cache-feroceon-l2.c b/arch/arm/mm/cache-feroceon-l2.c index dd3d591..48bc3c0 100644 --- a/arch/arm/mm/cache-feroceon-l2.c +++ b/arch/arm/mm/cache-feroceon-l2.c @@ -343,6 +343,7 @@ void __init feroceon_l2_init(int __l2_wt_override) outer_cache.inv_range = feroceon_l2_inv_range; outer_cache.clean_range = feroceon_l2_clean_range; outer_cache.flush_range = feroceon_l2_flush_range; + outer_cache.inv_all = l2_inv_all; enable_l2(); diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c index c2f3739..c465fac 100644 --- a/arch/arm/mm/cache-l2x0.c +++ b/arch/arm/mm/cache-l2x0.c @@ -299,7 +299,7 @@ static void l2x0_unlock(u32 cache_id) int lockregs; int i; - switch (cache_id) { + switch (cache_id & L2X0_CACHE_ID_PART_MASK) { case L2X0_CACHE_ID_PART_L310: lockregs = 8; break; @@ -333,15 +333,14 @@ void __init l2x0_init(void __iomem *base, u32 aux_val, u32 aux_mask) if (cache_id_part_number_from_dt) cache_id = cache_id_part_number_from_dt; else - cache_id = readl_relaxed(l2x0_base + L2X0_CACHE_ID) - & L2X0_CACHE_ID_PART_MASK; + cache_id = readl_relaxed(l2x0_base + L2X0_CACHE_ID); aux = readl_relaxed(l2x0_base + L2X0_AUX_CTRL); aux &= aux_mask; aux |= aux_val; /* Determine the number of ways */ - switch (cache_id) { + switch (cache_id & L2X0_CACHE_ID_PART_MASK) { case L2X0_CACHE_ID_PART_L310: if (aux & (1 << 16)) ways = 16; @@ -725,7 +724,6 @@ static const struct l2x0_of_data pl310_data = { .flush_all = l2x0_flush_all, .inv_all = l2x0_inv_all, .disable = l2x0_disable, - .set_debug = pl310_set_debug, }, }; @@ -814,9 +812,8 @@ int __init l2x0_of_init(u32 aux_val, u32 aux_mask) data->save(); of_init = true; - l2x0_init(l2x0_base, aux_val, aux_mask); - memcpy(&outer_cache, &data->outer_cache, sizeof(outer_cache)); + l2x0_init(l2x0_base, aux_val, aux_mask); return 0; } diff --git a/arch/arm/mm/cache-v3.S b/arch/arm/mm/cache-v3.S deleted file mode 100644 index 8a3fade..0000000 --- a/arch/arm/mm/cache-v3.S +++ /dev/null @@ -1,137 +0,0 @@ -/* - * linux/arch/arm/mm/cache-v3.S - * - * Copyright (C) 1997-2002 Russell king - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ -#include <linux/linkage.h> -#include <linux/init.h> -#include <asm/page.h> -#include "proc-macros.S" - -/* - * flush_icache_all() - * - * Unconditionally clean and invalidate the entire icache. - */ -ENTRY(v3_flush_icache_all) - mov pc, lr -ENDPROC(v3_flush_icache_all) - -/* - * flush_user_cache_all() - * - * Invalidate all cache entries in a particular address - * space. - * - * - mm - mm_struct describing address space - */ -ENTRY(v3_flush_user_cache_all) - /* FALLTHROUGH */ -/* - * flush_kern_cache_all() - * - * Clean and invalidate the entire cache. - */ -ENTRY(v3_flush_kern_cache_all) - /* FALLTHROUGH */ - -/* - * flush_user_cache_range(start, end, flags) - * - * Invalidate a range of cache entries in the specified - * address space. - * - * - start - start address (may not be aligned) - * - end - end address (exclusive, may not be aligned) - * - flags - vma_area_struct flags describing address space - */ -ENTRY(v3_flush_user_cache_range) - mov ip, #0 - mcreq p15, 0, ip, c7, c0, 0 @ flush ID cache - mov pc, lr - -/* - * coherent_kern_range(start, end) - * - * Ensure coherency between the Icache and the Dcache in the - * region described by start. If you have non-snooping - * Harvard caches, you need to implement this function. - * - * - start - virtual start address - * - end - virtual end address - */ -ENTRY(v3_coherent_kern_range) - /* FALLTHROUGH */ - -/* - * coherent_user_range(start, end) - * - * Ensure coherency between the Icache and the Dcache in the - * region described by start. If you have non-snooping - * Harvard caches, you need to implement this function. - * - * - start - virtual start address - * - end - virtual end address - */ -ENTRY(v3_coherent_user_range) - mov r0, #0 - mov pc, lr - -/* - * flush_kern_dcache_area(void *page, size_t size) - * - * Ensure no D cache aliasing occurs, either with itself or - * the I cache - * - * - addr - kernel address - * - size - region size - */ -ENTRY(v3_flush_kern_dcache_area) - /* FALLTHROUGH */ - -/* - * dma_flush_range(start, end) - * - * Clean and invalidate the specified virtual address range. - * - * - start - virtual start address - * - end - virtual end address - */ -ENTRY(v3_dma_flush_range) - mov r0, #0 - mcr p15, 0, r0, c7, c0, 0 @ flush ID cache - mov pc, lr - -/* - * dma_unmap_area(start, size, dir) - * - start - kernel virtual start address - * - size - size of region - * - dir - DMA direction - */ -ENTRY(v3_dma_unmap_area) - teq r2, #DMA_TO_DEVICE - bne v3_dma_flush_range - /* FALLTHROUGH */ - -/* - * dma_map_area(start, size, dir) - * - start - kernel virtual start address - * - size - size of region - * - dir - DMA direction - */ -ENTRY(v3_dma_map_area) - mov pc, lr -ENDPROC(v3_dma_unmap_area) -ENDPROC(v3_dma_map_area) - - .globl v3_flush_kern_cache_louis - .equ v3_flush_kern_cache_louis, v3_flush_kern_cache_all - - __INITDATA - - @ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S) - define_cache_functions v3 diff --git a/arch/arm/mm/cache-v4.S b/arch/arm/mm/cache-v4.S index 43e5d77..a7ba68f 100644 --- a/arch/arm/mm/cache-v4.S +++ b/arch/arm/mm/cache-v4.S @@ -58,7 +58,7 @@ ENTRY(v4_flush_kern_cache_all) ENTRY(v4_flush_user_cache_range) #ifdef CONFIG_CPU_CP15 mov ip, #0 - mcreq p15, 0, ip, c7, c7, 0 @ flush ID cache + mcr p15, 0, ip, c7, c7, 0 @ flush ID cache mov pc, lr #else /* FALLTHROUGH */ diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S index 7539ec2..515b000 100644 --- a/arch/arm/mm/cache-v7.S +++ b/arch/arm/mm/cache-v7.S @@ -19,6 +19,52 @@ #include "proc-macros.S" /* + * The secondary kernel init calls v7_flush_dcache_all before it enables + * the L1; however, the L1 comes out of reset in an undefined state, so + * the clean + invalidate performed by v7_flush_dcache_all causes a bunch + * of cache lines with uninitialized data and uninitialized tags to get + * written out to memory, which does really unpleasant things to the main + * processor. We fix this by performing an invalidate, rather than a + * clean + invalidate, before jumping into the kernel. + * + * This function is cloned from arch/arm/mach-tegra/headsmp.S, and needs + * to be called for both secondary cores startup and primary core resume + * procedures. + */ +ENTRY(v7_invalidate_l1) + mov r0, #0 + mcr p15, 2, r0, c0, c0, 0 + mrc p15, 1, r0, c0, c0, 0 + + ldr r1, =0x7fff + and r2, r1, r0, lsr #13 + + ldr r1, =0x3ff + + and r3, r1, r0, lsr #3 @ NumWays - 1 + add r2, r2, #1 @ NumSets + + and r0, r0, #0x7 + add r0, r0, #4 @ SetShift + + clz r1, r3 @ WayShift + add r4, r3, #1 @ NumWays +1: sub r2, r2, #1 @ NumSets-- + mov r3, r4 @ Temp = NumWays +2: subs r3, r3, #1 @ Temp-- + mov r5, r3, lsl r1 + mov r6, r2, lsl r0 + orr r5, r5, r6 @ Reg = (Temp<<WayShift)|(NumSets<<SetShift) + mcr p15, 0, r5, c7, c6, 2 + bgt 2b + cmp r2, #0 + bgt 1b + dsb + isb + mov pc, lr +ENDPROC(v7_invalidate_l1) + +/* * v7_flush_icache_all() * * Flush the whole I-cache. @@ -46,6 +92,14 @@ ENTRY(v7_flush_dcache_louis) mrc p15, 1, r0, c0, c0, 1 @ read clidr, r0 = clidr ALT_SMP(ands r3, r0, #(7 << 21)) @ extract LoUIS from clidr ALT_UP(ands r3, r0, #(7 << 27)) @ extract LoUU from clidr +#ifdef CONFIG_ARM_ERRATA_643719 + ALT_SMP(mrceq p15, 0, r2, c0, c0, 0) @ read main ID register + ALT_UP(moveq pc, lr) @ LoUU is zero, so nothing to do + ldreq r1, =0x410fc090 @ ID of ARM Cortex A9 r0p? + biceq r2, r2, #0x0000000f @ clear minor revision number + teqeq r2, r1 @ test for errata affected core and if so... + orreqs r3, #(1 << 21) @ fix LoUIS value (and set flags state to 'ne') +#endif ALT_SMP(mov r3, r3, lsr #20) @ r3 = LoUIS * 2 ALT_UP(mov r3, r3, lsr #26) @ r3 = LoUU * 2 moveq pc, lr @ return if level == 0 diff --git a/arch/arm/mm/context.c b/arch/arm/mm/context.c index bc4a5e9..2ac3737 100644 --- a/arch/arm/mm/context.c +++ b/arch/arm/mm/context.c @@ -34,6 +34,9 @@ * The ASID is used to tag entries in the CPU caches and TLBs. * The context ID is used by debuggers and trace logic, and * should be unique within all running processes. + * + * In big endian operation, the two 32 bit words are swapped if accesed by + * non 64-bit operations. */ #define ASID_FIRST_VERSION (1ULL << ASID_BITS) #define NUM_USER_ASIDS (ASID_FIRST_VERSION - 1) @@ -45,7 +48,7 @@ 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); -static DEFINE_PER_CPU(atomic64_t, active_asids); +DEFINE_PER_CPU(atomic64_t, active_asids); static DEFINE_PER_CPU(u64, reserved_asids); static cpumask_t tlb_flush_pending; @@ -149,9 +152,9 @@ static int is_reserved_asid(u64 asid) return 0; } -static void new_context(struct mm_struct *mm, unsigned int cpu) +static u64 new_context(struct mm_struct *mm, unsigned int cpu) { - u64 asid = mm->context.id; + u64 asid = atomic64_read(&mm->context.id); u64 generation = atomic64_read(&asid_generation); if (asid != 0 && is_reserved_asid(asid)) { @@ -178,13 +181,14 @@ static void new_context(struct mm_struct *mm, unsigned int cpu) cpumask_clear(mm_cpumask(mm)); } - mm->context.id = asid; + return asid; } void check_and_switch_context(struct mm_struct *mm, struct task_struct *tsk) { unsigned long flags; unsigned int cpu = smp_processor_id(); + u64 asid; if (unlikely(mm->context.vmalloc_seq != init_mm.context.vmalloc_seq)) __check_vmalloc_seq(mm); @@ -195,20 +199,27 @@ void check_and_switch_context(struct mm_struct *mm, struct task_struct *tsk) */ cpu_set_reserved_ttbr0(); - if (!((mm->context.id ^ atomic64_read(&asid_generation)) >> ASID_BITS) - && atomic64_xchg(&per_cpu(active_asids, cpu), mm->context.id)) + asid = atomic64_read(&mm->context.id); + if (!((asid ^ atomic64_read(&asid_generation)) >> ASID_BITS) + && atomic64_xchg(&per_cpu(active_asids, cpu), asid)) goto switch_mm_fastpath; raw_spin_lock_irqsave(&cpu_asid_lock, flags); /* Check that our ASID belongs to the current generation. */ - if ((mm->context.id ^ atomic64_read(&asid_generation)) >> ASID_BITS) - new_context(mm, cpu); - - atomic64_set(&per_cpu(active_asids, cpu), mm->context.id); - cpumask_set_cpu(cpu, mm_cpumask(mm)); + asid = atomic64_read(&mm->context.id); + if ((asid ^ atomic64_read(&asid_generation)) >> ASID_BITS) { + asid = new_context(mm, cpu); + atomic64_set(&mm->context.id, asid); + } - if (cpumask_test_and_clear_cpu(cpu, &tlb_flush_pending)) + if (cpumask_test_and_clear_cpu(cpu, &tlb_flush_pending)) { + local_flush_bp_all(); local_flush_tlb_all(); + dummy_flush_tlb_a15_erratum(); + } + + atomic64_set(&per_cpu(active_asids, cpu), asid); + cpumask_set_cpu(cpu, mm_cpumask(mm)); raw_spin_unlock_irqrestore(&cpu_asid_lock, flags); switch_mm_fastpath: diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index dda3904..ef3e0f3 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -186,13 +186,24 @@ static u64 get_coherent_dma_mask(struct device *dev) static void __dma_clear_buffer(struct page *page, size_t size) { - void *ptr; /* * Ensure that the allocated pages are zeroed, and that any data * lurking in the kernel direct-mapped region is invalidated. */ - ptr = page_address(page); - if (ptr) { + if (PageHighMem(page)) { + phys_addr_t base = __pfn_to_phys(page_to_pfn(page)); + phys_addr_t end = base + size; + while (size > 0) { + void *ptr = kmap_atomic(page); + memset(ptr, 0, PAGE_SIZE); + dmac_flush_range(ptr, ptr + PAGE_SIZE); + kunmap_atomic(ptr); + page++; + size -= PAGE_SIZE; + } + outer_flush_range(base, end); + } else { + void *ptr = page_address(page); memset(ptr, 0, size); dmac_flush_range(ptr, ptr + size); outer_flush_range(__pa(ptr), __pa(ptr) + size); @@ -243,7 +254,8 @@ static void __dma_free_buffer(struct page *page, size_t size) #endif static void *__alloc_from_contiguous(struct device *dev, size_t size, - pgprot_t prot, struct page **ret_page); + pgprot_t prot, struct page **ret_page, + const void *caller); static void *__alloc_remap_buffer(struct device *dev, size_t size, gfp_t gfp, pgprot_t prot, struct page **ret_page, @@ -330,6 +342,7 @@ static int __init atomic_pool_init(void) { struct dma_pool *pool = &atomic_pool; pgprot_t prot = pgprot_dmacoherent(pgprot_kernel); + gfp_t gfp = GFP_KERNEL | GFP_DMA; unsigned long nr_pages = pool->size >> PAGE_SHIFT; unsigned long *bitmap; struct page *page; @@ -346,10 +359,11 @@ static int __init atomic_pool_init(void) goto no_pages; if (IS_ENABLED(CONFIG_CMA)) - ptr = __alloc_from_contiguous(NULL, pool->size, prot, &page); + ptr = __alloc_from_contiguous(NULL, pool->size, prot, &page, + atomic_pool_init); else - ptr = __alloc_remap_buffer(NULL, pool->size, GFP_KERNEL, prot, - &page, NULL); + ptr = __alloc_remap_buffer(NULL, pool->size, gfp, prot, &page, + atomic_pool_init); if (ptr) { int i; @@ -542,27 +556,41 @@ static int __free_from_pool(void *start, size_t size) } static void *__alloc_from_contiguous(struct device *dev, size_t size, - pgprot_t prot, struct page **ret_page) + pgprot_t prot, struct page **ret_page, + const void *caller) { unsigned long order = get_order(size); size_t count = size >> PAGE_SHIFT; struct page *page; + void *ptr; page = dma_alloc_from_contiguous(dev, count, order); if (!page) return NULL; __dma_clear_buffer(page, size); - __dma_remap(page, size, prot); + if (PageHighMem(page)) { + ptr = __dma_alloc_remap(page, size, GFP_KERNEL, prot, caller); + if (!ptr) { + dma_release_from_contiguous(dev, page, count); + return NULL; + } + } else { + __dma_remap(page, size, prot); + ptr = page_address(page); + } *ret_page = page; - return page_address(page); + return ptr; } static void __free_from_contiguous(struct device *dev, struct page *page, - size_t size) + void *cpu_addr, size_t size) { - __dma_remap(page, size, pgprot_kernel); + if (PageHighMem(page)) + __dma_free_remap(cpu_addr, size); + else + __dma_remap(page, size, pgprot_kernel); dma_release_from_contiguous(dev, page, size >> PAGE_SHIFT); } @@ -583,9 +611,9 @@ static inline pgprot_t __get_dma_pgprot(struct dma_attrs *attrs, pgprot_t prot) #define __get_dma_pgprot(attrs, prot) __pgprot(0) #define __alloc_remap_buffer(dev, size, gfp, prot, ret, c) NULL #define __alloc_from_pool(size, ret_page) NULL -#define __alloc_from_contiguous(dev, size, prot, ret) NULL +#define __alloc_from_contiguous(dev, size, prot, ret, c) NULL #define __free_from_pool(cpu_addr, size) 0 -#define __free_from_contiguous(dev, page, size) do { } while (0) +#define __free_from_contiguous(dev, page, cpu_addr, size) do { } while (0) #define __dma_free_remap(cpu_addr, size) do { } while (0) #endif /* CONFIG_MMU */ @@ -645,7 +673,7 @@ static void *__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, else if (!IS_ENABLED(CONFIG_CMA)) addr = __alloc_remap_buffer(dev, size, gfp, prot, &page, caller); else - addr = __alloc_from_contiguous(dev, size, prot, &page); + addr = __alloc_from_contiguous(dev, size, prot, &page, caller); if (addr) *handle = pfn_to_dma(dev, page_to_pfn(page)); @@ -739,7 +767,7 @@ static void __arm_dma_free(struct device *dev, size_t size, void *cpu_addr, * Non-atomic allocations cannot be freed with IRQs disabled */ WARN_ON(irqs_disabled()); - __free_from_contiguous(dev, page, size); + __free_from_contiguous(dev, page, cpu_addr, size); } } @@ -795,16 +823,17 @@ static void dma_cache_maint_page(struct page *page, unsigned long offset, if (PageHighMem(page)) { if (len + offset > PAGE_SIZE) len = PAGE_SIZE - offset; - vaddr = kmap_high_get(page); - if (vaddr) { - vaddr += offset; - op(vaddr, len, dir); - kunmap_high(page); - } else if (cache_is_vipt()) { - /* unmapped pages might still be cached */ + + if (cache_is_vipt_nonaliasing()) { vaddr = kmap_atomic(page); op(vaddr + offset, len, dir); kunmap_atomic(vaddr); + } else { + vaddr = kmap_high_get(page); + if (vaddr) { + op(vaddr + offset, len, dir); + kunmap_high(page); + } } } else { vaddr = page_address(page) + offset; @@ -1002,6 +1031,9 @@ static inline dma_addr_t __alloc_iova(struct dma_iommu_mapping *mapping, unsigned int count, start; unsigned long flags; + if (order > CONFIG_ARM_DMA_IOMMU_ALIGNMENT) + order = CONFIG_ARM_DMA_IOMMU_ALIGNMENT; + count = ((PAGE_ALIGN(size) >> PAGE_SHIFT) + (1 << mapping->order) - 1) >> mapping->order; @@ -1068,12 +1100,17 @@ static struct page **__iommu_alloc_buffer(struct device *dev, size_t size, return pages; } + /* + * IOMMU can map any pages, so himem can also be used here + */ + gfp |= __GFP_NOWARN | __GFP_HIGHMEM; + while (count) { int j, order = __fls(count); - pages[i] = alloc_pages(gfp | __GFP_NOWARN, order); + pages[i] = alloc_pages(gfp, order); while (!pages[i] && order) - pages[i] = alloc_pages(gfp | __GFP_NOWARN, --order); + pages[i] = alloc_pages(gfp, --order); if (!pages[i]) goto error; @@ -1257,11 +1294,11 @@ err_mapping: return NULL; } -static void __iommu_free_atomic(struct device *dev, struct page **pages, +static void __iommu_free_atomic(struct device *dev, void *cpu_addr, dma_addr_t handle, size_t size) { __iommu_remove_mapping(dev, handle, size); - __free_from_pool(page_address(pages[0]), size); + __free_from_pool(cpu_addr, size); } static void *arm_iommu_alloc_attrs(struct device *dev, size_t size, @@ -1344,7 +1381,7 @@ void arm_iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr, } if (__in_atomic_pool(cpu_addr, size)) { - __iommu_free_atomic(dev, pages, handle, size); + __iommu_free_atomic(dev, cpu_addr, handle, size); return; } @@ -1732,6 +1769,8 @@ struct dma_map_ops iommu_ops = { .unmap_sg = arm_iommu_unmap_sg, .sync_sg_for_cpu = arm_iommu_sync_sg_for_cpu, .sync_sg_for_device = arm_iommu_sync_sg_for_device, + + .set_dma_mask = arm_dma_set_mask, }; struct dma_map_ops iommu_coherent_ops = { @@ -1745,6 +1784,8 @@ struct dma_map_ops iommu_coherent_ops = { .map_sg = arm_coherent_iommu_map_sg, .unmap_sg = arm_coherent_iommu_unmap_sg, + + .set_dma_mask = arm_dma_set_mask, }; /** @@ -1799,6 +1840,7 @@ err2: err: return ERR_PTR(err); } +EXPORT_SYMBOL_GPL(arm_iommu_create_mapping); static void release_iommu_mapping(struct kref *kref) { @@ -1815,6 +1857,7 @@ void arm_iommu_release_mapping(struct dma_iommu_mapping *mapping) if (mapping) kref_put(&mapping->kref, release_iommu_mapping); } +EXPORT_SYMBOL_GPL(arm_iommu_release_mapping); /** * arm_iommu_attach_device @@ -1843,5 +1886,32 @@ int arm_iommu_attach_device(struct device *dev, pr_debug("Attached IOMMU controller to %s device.\n", dev_name(dev)); return 0; } +EXPORT_SYMBOL_GPL(arm_iommu_attach_device); + +/** + * arm_iommu_detach_device + * @dev: valid struct device pointer + * + * Detaches the provided device from a previously attached map. + * This voids the dma operations (dma_map_ops pointer) + */ +void arm_iommu_detach_device(struct device *dev) +{ + struct dma_iommu_mapping *mapping; + + mapping = to_dma_iommu_mapping(dev); + if (!mapping) { + dev_warn(dev, "Not attached\n"); + return; + } + + iommu_detach_device(mapping->domain, dev); + kref_put(&mapping->kref, release_iommu_mapping); + mapping = NULL; + set_dma_ops(dev, NULL); + + pr_debug("Detached IOMMU controller from %s device.\n", dev_name(dev)); +} +EXPORT_SYMBOL_GPL(arm_iommu_detach_device); #endif diff --git a/arch/arm/mm/flush.c b/arch/arm/mm/flush.c index 1c8f7f5..32aa586 100644 --- a/arch/arm/mm/flush.c +++ b/arch/arm/mm/flush.c @@ -170,15 +170,18 @@ void __flush_dcache_page(struct address_space *mapping, struct page *page) if (!PageHighMem(page)) { __cpuc_flush_dcache_area(page_address(page), PAGE_SIZE); } else { - void *addr = kmap_high_get(page); - if (addr) { - __cpuc_flush_dcache_area(addr, PAGE_SIZE); - kunmap_high(page); - } else if (cache_is_vipt()) { - /* unmapped pages might still be cached */ + void *addr; + + if (cache_is_vipt_nonaliasing()) { addr = kmap_atomic(page); __cpuc_flush_dcache_area(addr, PAGE_SIZE); kunmap_atomic(addr); + } else { + addr = kmap_high_get(page); + if (addr) { + __cpuc_flush_dcache_area(addr, PAGE_SIZE); + kunmap_high(page); + } } } @@ -298,6 +301,39 @@ void flush_dcache_page(struct page *page) EXPORT_SYMBOL(flush_dcache_page); /* + * Ensure cache coherency for the kernel mapping of this page. We can + * assume that the page is pinned via kmap. + * + * If the page only exists in the page cache and there are no user + * space mappings, this is a no-op since the page was already marked + * dirty at creation. Otherwise, we need to flush the dirty kernel + * cache lines directly. + */ +void flush_kernel_dcache_page(struct page *page) +{ + if (cache_is_vivt() || cache_is_vipt_aliasing()) { + struct address_space *mapping; + + mapping = page_mapping(page); + + if (!mapping || mapping_mapped(mapping)) { + void *addr; + + addr = page_address(page); + /* + * kmap_atomic() doesn't set the page virtual + * address for highmem pages, and + * kunmap_atomic() takes care of cache + * flushing already. + */ + if (!IS_ENABLED(CONFIG_HIGHMEM) || addr) + __cpuc_flush_dcache_area(addr, PAGE_SIZE); + } + } +} +EXPORT_SYMBOL(flush_kernel_dcache_page); + +/* * Flush an anonymous page so that users of get_user_pages() * can safely access the data. The expected sequence is: * diff --git a/arch/arm/mm/idmap.c b/arch/arm/mm/idmap.c index 99db769..83cb3ac 100644 --- a/arch/arm/mm/idmap.c +++ b/arch/arm/mm/idmap.c @@ -1,4 +1,6 @@ +#include <linux/module.h> #include <linux/kernel.h> +#include <linux/slab.h> #include <asm/cputype.h> #include <asm/idmap.h> @@ -59,11 +61,17 @@ static void idmap_add_pud(pgd_t *pgd, unsigned long addr, unsigned long end, } while (pud++, addr = next, addr != end); } -static void identity_mapping_add(pgd_t *pgd, unsigned long addr, unsigned long end) +static void identity_mapping_add(pgd_t *pgd, const char *text_start, + const char *text_end, unsigned long prot) { - unsigned long prot, next; + unsigned long addr, end; + unsigned long next; + + addr = virt_to_phys(text_start); + end = virt_to_phys(text_end); + + prot |= PMD_TYPE_SECT | PMD_SECT_AP_WRITE | PMD_SECT_AF; - prot = PMD_TYPE_SECT | PMD_SECT_AP_WRITE | PMD_SECT_AF; if (cpu_architecture() <= CPU_ARCH_ARMv5TEJ && !cpu_is_xscale()) prot |= PMD_BIT4; @@ -78,19 +86,14 @@ extern char __idmap_text_start[], __idmap_text_end[]; static int __init init_static_idmap(void) { - phys_addr_t idmap_start, idmap_end; - idmap_pgd = pgd_alloc(&init_mm); if (!idmap_pgd) return -ENOMEM; - /* Add an identity mapping for the physical address of the section. */ - idmap_start = virt_to_phys((void *)__idmap_text_start); - idmap_end = virt_to_phys((void *)__idmap_text_end); - - pr_info("Setting up static identity map for 0x%llx - 0x%llx\n", - (long long)idmap_start, (long long)idmap_end); - identity_mapping_add(idmap_pgd, idmap_start, idmap_end); + pr_info("Setting up static identity map for 0x%p - 0x%p\n", + __idmap_text_start, __idmap_text_end); + identity_mapping_add(idmap_pgd, __idmap_text_start, + __idmap_text_end, 0); /* Flush L1 for the hardware to see this page table content */ flush_cache_louis(); @@ -108,6 +111,7 @@ void setup_mm_for_reboot(void) { /* Switch to the identity mapping. */ cpu_switch_mm(idmap_pgd, &init_mm); + local_flush_bp_all(); #ifdef CONFIG_CPU_HAS_ASID /* diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c index ad722f1..9a5cdc0 100644 --- a/arch/arm/mm/init.c +++ b/arch/arm/mm/init.c @@ -99,6 +99,9 @@ void show_mem(unsigned int filter) printk("Mem-info:\n"); show_free_areas(filter); + if (filter & SHOW_MEM_FILTER_PAGE_COUNT) + return; + for_each_bank (i, mi) { struct membank *bank = &mi->bank[i]; unsigned int pfn1, pfn2; @@ -424,24 +427,6 @@ void __init bootmem_init(void) max_pfn = max_high - PHYS_PFN_OFFSET; } -static inline int free_area(unsigned long pfn, unsigned long end, char *s) -{ - unsigned int pages = 0, size = (end - pfn) << (PAGE_SHIFT - 10); - - for (; pfn < end; pfn++) { - struct page *page = pfn_to_page(pfn); - ClearPageReserved(page); - init_page_count(page); - __free_page(page); - pages++; - } - - if (size && s) - printk(KERN_INFO "Freeing %s memory: %dK\n", s, size); - - return pages; -} - /* * Poison init memory with an undefined instruction (ARM) or a branch to an * undefined instruction (Thumb). @@ -534,6 +519,14 @@ static void __init free_unused_memmap(struct meminfo *mi) #endif } +#ifdef CONFIG_HIGHMEM +static inline void free_area_high(unsigned long pfn, unsigned long end) +{ + for (; pfn < end; pfn++) + free_highmem_page(pfn_to_page(pfn)); +} +#endif + static void __init free_highpages(void) { #ifdef CONFIG_HIGHMEM @@ -569,8 +562,7 @@ static void __init free_highpages(void) if (res_end > end) res_end = end; if (res_start != start) - totalhigh_pages += free_area(start, res_start, - NULL); + free_area_high(start, res_start); start = res_end; if (start == end) break; @@ -578,9 +570,8 @@ static void __init free_highpages(void) /* And now free anything which remains */ if (start < end) - totalhigh_pages += free_area(start, end, NULL); + free_area_high(start, end); } - totalram_pages += totalhigh_pages; #endif } @@ -609,8 +600,7 @@ void __init mem_init(void) #ifdef CONFIG_SA1111 /* now that our DMA memory is actually so designated, we can free it */ - totalram_pages += free_area(PHYS_PFN_OFFSET, - __phys_to_pfn(__pa(swapper_pg_dir)), NULL); + free_reserved_area(__va(PHYS_PFN_OFFSET), swapper_pg_dir, 0, NULL); #endif free_highpages(); @@ -738,16 +728,12 @@ void free_initmem(void) extern char __tcm_start, __tcm_end; poison_init_mem(&__tcm_start, &__tcm_end - &__tcm_start); - totalram_pages += free_area(__phys_to_pfn(__pa(&__tcm_start)), - __phys_to_pfn(__pa(&__tcm_end)), - "TCM link"); + free_reserved_area(&__tcm_start, &__tcm_end, 0, "TCM link"); #endif poison_init_mem(__init_begin, __init_end - __init_begin); if (!machine_is_integrator() && !machine_is_cintegrator()) - totalram_pages += free_area(__phys_to_pfn(__pa(__init_begin)), - __phys_to_pfn(__pa(__init_end)), - "init"); + free_initmem_default(0); } #ifdef CONFIG_BLK_DEV_INITRD @@ -758,9 +744,7 @@ void free_initrd_mem(unsigned long start, unsigned long end) { if (!keep_initrd) { poison_init_mem((void *)start, PAGE_ALIGN(end) - start); - totalram_pages += free_area(__phys_to_pfn(__pa(start)), - __phys_to_pfn(__pa(end)), - "initrd"); + free_reserved_area(start, end, 0, "initrd"); } } diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c index 88fd86c..04d9006 100644 --- a/arch/arm/mm/ioremap.c +++ b/arch/arm/mm/ioremap.c @@ -39,6 +39,70 @@ #include <asm/mach/pci.h> #include "mm.h" + +LIST_HEAD(static_vmlist); + +static struct static_vm *find_static_vm_paddr(phys_addr_t paddr, + size_t size, unsigned int mtype) +{ + struct static_vm *svm; + struct vm_struct *vm; + + list_for_each_entry(svm, &static_vmlist, list) { + vm = &svm->vm; + if (!(vm->flags & VM_ARM_STATIC_MAPPING)) + continue; + if ((vm->flags & VM_ARM_MTYPE_MASK) != VM_ARM_MTYPE(mtype)) + continue; + + if (vm->phys_addr > paddr || + paddr + size - 1 > vm->phys_addr + vm->size - 1) + continue; + + return svm; + } + + return NULL; +} + +struct static_vm *find_static_vm_vaddr(void *vaddr) +{ + struct static_vm *svm; + struct vm_struct *vm; + + list_for_each_entry(svm, &static_vmlist, list) { + vm = &svm->vm; + + /* static_vmlist is ascending order */ + if (vm->addr > vaddr) + break; + + if (vm->addr <= vaddr && vm->addr + vm->size > vaddr) + return svm; + } + + return NULL; +} + +void __init add_static_vm_early(struct static_vm *svm) +{ + struct static_vm *curr_svm; + struct vm_struct *vm; + void *vaddr; + + vm = &svm->vm; + vm_area_add_early(vm); + vaddr = vm->addr; + + list_for_each_entry(curr_svm, &static_vmlist, list) { + vm = &curr_svm->vm; + + if (vm->addr > vaddr) + break; + } + list_add_tail(&svm->list, &curr_svm->list); +} + int ioremap_page(unsigned long virt, unsigned long phys, const struct mem_type *mtype) { @@ -197,13 +261,14 @@ void __iomem * __arm_ioremap_pfn_caller(unsigned long pfn, const struct mem_type *type; int err; unsigned long addr; - struct vm_struct * area; + struct vm_struct *area; + phys_addr_t paddr = __pfn_to_phys(pfn); #ifndef CONFIG_ARM_LPAE /* * High mappings must be supersection aligned */ - if (pfn >= 0x100000 && (__pfn_to_phys(pfn) & ~SUPERSECTION_MASK)) + if (pfn >= 0x100000 && (paddr & ~SUPERSECTION_MASK)) return NULL; #endif @@ -219,24 +284,16 @@ void __iomem * __arm_ioremap_pfn_caller(unsigned long pfn, /* * Try to reuse one of the static mapping whenever possible. */ - read_lock(&vmlist_lock); - for (area = vmlist; area; area = area->next) { - if (!size || (sizeof(phys_addr_t) == 4 && pfn >= 0x100000)) - break; - if (!(area->flags & VM_ARM_STATIC_MAPPING)) - continue; - if ((area->flags & VM_ARM_MTYPE_MASK) != VM_ARM_MTYPE(mtype)) - continue; - if (__phys_to_pfn(area->phys_addr) > pfn || - __pfn_to_phys(pfn) + size-1 > area->phys_addr + area->size-1) - continue; - /* we can drop the lock here as we know *area is static */ - read_unlock(&vmlist_lock); - addr = (unsigned long)area->addr; - addr += __pfn_to_phys(pfn) - area->phys_addr; - return (void __iomem *) (offset + addr); + if (size && !(sizeof(phys_addr_t) == 4 && pfn >= 0x100000)) { + struct static_vm *svm; + + svm = find_static_vm_paddr(paddr, size, mtype); + if (svm) { + addr = (unsigned long)svm->vm.addr; + addr += paddr - svm->vm.phys_addr; + return (void __iomem *) (offset + addr); + } } - read_unlock(&vmlist_lock); /* * Don't allow RAM to be mapped - this causes problems with ARMv6+ @@ -248,21 +305,21 @@ void __iomem * __arm_ioremap_pfn_caller(unsigned long pfn, if (!area) return NULL; addr = (unsigned long)area->addr; - area->phys_addr = __pfn_to_phys(pfn); + area->phys_addr = paddr; #if !defined(CONFIG_SMP) && !defined(CONFIG_ARM_LPAE) if (DOMAIN_IO == 0 && (((cpu_architecture() >= CPU_ARCH_ARMv6) && (get_cr() & CR_XP)) || cpu_is_xsc3()) && pfn >= 0x100000 && - !((__pfn_to_phys(pfn) | size | addr) & ~SUPERSECTION_MASK)) { + !((paddr | size | addr) & ~SUPERSECTION_MASK)) { area->flags |= VM_ARM_SECTION_MAPPING; err = remap_area_supersections(addr, pfn, size, type); - } else if (!((__pfn_to_phys(pfn) | size | addr) & ~PMD_MASK)) { + } else if (!((paddr | size | addr) & ~PMD_MASK)) { area->flags |= VM_ARM_SECTION_MAPPING; err = remap_area_sections(addr, pfn, size, type); } else #endif - err = ioremap_page_range(addr, addr + size, __pfn_to_phys(pfn), + err = ioremap_page_range(addr, addr + size, paddr, __pgprot(type->prot_pte)); if (err) { @@ -346,34 +403,28 @@ __arm_ioremap_exec(unsigned long phys_addr, size_t size, bool cached) void __iounmap(volatile void __iomem *io_addr) { void *addr = (void *)(PAGE_MASK & (unsigned long)io_addr); - struct vm_struct *vm; + struct static_vm *svm; + + /* If this is a static mapping, we must leave it alone */ + svm = find_static_vm_vaddr(addr); + if (svm) + return; - read_lock(&vmlist_lock); - for (vm = vmlist; vm; vm = vm->next) { - if (vm->addr > addr) - break; - if (!(vm->flags & VM_IOREMAP)) - continue; - /* If this is a static mapping we must leave it alone */ - if ((vm->flags & VM_ARM_STATIC_MAPPING) && - (vm->addr <= addr) && (vm->addr + vm->size > addr)) { - read_unlock(&vmlist_lock); - return; - } #if !defined(CONFIG_SMP) && !defined(CONFIG_ARM_LPAE) + { + struct vm_struct *vm; + + vm = find_vm_area(addr); + /* * If this is a section based mapping we need to handle it * specially as the VM subsystem does not know how to handle * such a beast. */ - if ((vm->addr == addr) && - (vm->flags & VM_ARM_SECTION_MAPPING)) { + if (vm && (vm->flags & VM_ARM_SECTION_MAPPING)) unmap_area_sections((unsigned long)vm->addr, vm->size); - break; - } -#endif } - read_unlock(&vmlist_lock); +#endif vunmap(addr); } diff --git a/arch/arm/mm/mm.h b/arch/arm/mm/mm.h index a8ee92d..d5a4e9a 100644 --- a/arch/arm/mm/mm.h +++ b/arch/arm/mm/mm.h @@ -1,4 +1,6 @@ #ifdef CONFIG_MMU +#include <linux/list.h> +#include <linux/vmalloc.h> /* the upper-most page table pointer */ extern pmd_t *top_pmd; @@ -65,6 +67,16 @@ extern void __flush_dcache_page(struct address_space *mapping, struct page *page /* consistent regions used by dma_alloc_attrs() */ #define VM_ARM_DMA_CONSISTENT 0x20000000 + +struct static_vm { + struct vm_struct vm; + struct list_head list; +}; + +extern struct list_head static_vmlist; +extern struct static_vm *find_static_vm_vaddr(void *vaddr); +extern __init void add_static_vm_early(struct static_vm *svm); + #endif #ifdef CONFIG_ZONE_DMA diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index ce328c7..4d409e6 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -34,6 +34,7 @@ #include <asm/mach/pci.h> #include "mm.h" +#include "tcm.h" /* * empty_zero_page is a special page that is used for @@ -57,6 +58,9 @@ static unsigned int cachepolicy __initdata = CPOLICY_WRITEBACK; static unsigned int ecc_mask __initdata = 0; pgprot_t pgprot_user; pgprot_t pgprot_kernel; +pgprot_t pgprot_hyp_device; +pgprot_t pgprot_s2; +pgprot_t pgprot_s2_device; EXPORT_SYMBOL(pgprot_user); EXPORT_SYMBOL(pgprot_kernel); @@ -66,37 +70,50 @@ struct cachepolicy { unsigned int cr_mask; pmdval_t pmd; pteval_t pte; + pteval_t pte_s2; }; +#ifdef CONFIG_ARM_LPAE +#define s2_policy(policy) policy +#else +#define s2_policy(policy) 0 +#endif + static struct cachepolicy cache_policies[] __initdata = { { .policy = "uncached", .cr_mask = CR_W|CR_C, .pmd = PMD_SECT_UNCACHED, .pte = L_PTE_MT_UNCACHED, + .pte_s2 = s2_policy(L_PTE_S2_MT_UNCACHED), }, { .policy = "buffered", .cr_mask = CR_C, .pmd = PMD_SECT_BUFFERED, .pte = L_PTE_MT_BUFFERABLE, + .pte_s2 = s2_policy(L_PTE_S2_MT_UNCACHED), }, { .policy = "writethrough", .cr_mask = 0, .pmd = PMD_SECT_WT, .pte = L_PTE_MT_WRITETHROUGH, + .pte_s2 = s2_policy(L_PTE_S2_MT_WRITETHROUGH), }, { .policy = "writeback", .cr_mask = 0, .pmd = PMD_SECT_WB, .pte = L_PTE_MT_WRITEBACK, + .pte_s2 = s2_policy(L_PTE_S2_MT_WRITEBACK), }, { .policy = "writealloc", .cr_mask = 0, .pmd = PMD_SECT_WBWA, .pte = L_PTE_MT_WRITEALLOC, + .pte_s2 = s2_policy(L_PTE_S2_MT_WRITEBACK), } }; +#ifdef CONFIG_CPU_CP15 /* * These are useful for identifying cache coherency * problems by allowing the cache or the cache and @@ -195,6 +212,22 @@ void adjust_cr(unsigned long mask, unsigned long set) } #endif +#else /* ifdef CONFIG_CPU_CP15 */ + +static int __init early_cachepolicy(char *p) +{ + pr_warning("cachepolicy kernel parameter not supported without cp15\n"); +} +early_param("cachepolicy", early_cachepolicy); + +static int __init noalign_setup(char *__unused) +{ + pr_warning("noalign kernel parameter not supported without cp15\n"); +} +__setup("noalign", noalign_setup); + +#endif /* ifdef CONFIG_CPU_CP15 / else */ + #define PROT_PTE_DEVICE L_PTE_PRESENT|L_PTE_YOUNG|L_PTE_DIRTY|L_PTE_XN #define PROT_SECT_DEVICE PMD_TYPE_SECT|PMD_SECT_AP_WRITE @@ -310,6 +343,7 @@ static void __init build_mem_type_table(void) struct cachepolicy *cp; unsigned int cr = get_cr(); pteval_t user_pgprot, kern_pgprot, vecs_pgprot; + pteval_t hyp_device_pgprot, s2_pgprot, s2_device_pgprot; int cpu_arch = cpu_architecture(); int i; @@ -421,6 +455,8 @@ static void __init build_mem_type_table(void) */ cp = &cache_policies[cachepolicy]; vecs_pgprot = kern_pgprot = user_pgprot = cp->pte; + s2_pgprot = cp->pte_s2; + hyp_device_pgprot = s2_device_pgprot = mem_types[MT_DEVICE].prot_pte; /* * ARMv6 and above have extended page tables. @@ -444,6 +480,7 @@ static void __init build_mem_type_table(void) user_pgprot |= L_PTE_SHARED; kern_pgprot |= L_PTE_SHARED; vecs_pgprot |= L_PTE_SHARED; + s2_pgprot |= L_PTE_SHARED; mem_types[MT_DEVICE_WC].prot_sect |= PMD_SECT_S; mem_types[MT_DEVICE_WC].prot_pte |= L_PTE_SHARED; mem_types[MT_DEVICE_CACHED].prot_sect |= PMD_SECT_S; @@ -498,6 +535,9 @@ static void __init build_mem_type_table(void) pgprot_user = __pgprot(L_PTE_PRESENT | L_PTE_YOUNG | user_pgprot); pgprot_kernel = __pgprot(L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY | kern_pgprot); + pgprot_s2 = __pgprot(L_PTE_PRESENT | L_PTE_YOUNG | s2_pgprot); + pgprot_s2_device = __pgprot(s2_device_pgprot); + pgprot_hyp_device = __pgprot(hyp_device_pgprot); mem_types[MT_LOW_VECTORS].prot_l1 |= ecc_mask; mem_types[MT_HIGH_VECTORS].prot_l1 |= ecc_mask; @@ -576,39 +616,62 @@ static void __init alloc_init_pte(pmd_t *pmd, unsigned long addr, } while (pte++, addr += PAGE_SIZE, addr != end); } -static void __init alloc_init_section(pud_t *pud, unsigned long addr, - unsigned long end, phys_addr_t phys, - const struct mem_type *type) +static void __init __map_init_section(pmd_t *pmd, unsigned long addr, + unsigned long end, phys_addr_t phys, + const struct mem_type *type) { - pmd_t *pmd = pmd_offset(pud, addr); + pmd_t *p = pmd; +#ifndef CONFIG_ARM_LPAE /* - * Try a section mapping - end, addr and phys must all be aligned - * to a section boundary. Note that PMDs refer to the individual - * L1 entries, whereas PGDs refer to a group of L1 entries making - * up one logical pointer to an L2 table. + * In classic MMU format, puds and pmds are folded in to + * the pgds. pmd_offset gives the PGD entry. PGDs refer to a + * group of L1 entries making up one logical pointer to + * an L2 table (2MB), where as PMDs refer to the individual + * L1 entries (1MB). Hence increment to get the correct + * offset for odd 1MB sections. + * (See arch/arm/include/asm/pgtable-2level.h) */ - if (type->prot_sect && ((addr | end | phys) & ~SECTION_MASK) == 0) { - pmd_t *p = pmd; - -#ifndef CONFIG_ARM_LPAE - if (addr & SECTION_SIZE) - pmd++; + if (addr & SECTION_SIZE) + pmd++; #endif + do { + *pmd = __pmd(phys | type->prot_sect); + phys += SECTION_SIZE; + } while (pmd++, addr += SECTION_SIZE, addr != end); - do { - *pmd = __pmd(phys | type->prot_sect); - phys += SECTION_SIZE; - } while (pmd++, addr += SECTION_SIZE, addr != end); + flush_pmd_entry(p); +} - flush_pmd_entry(p); - } else { +static void __init alloc_init_pmd(pud_t *pud, unsigned long addr, + unsigned long end, phys_addr_t phys, + const struct mem_type *type) +{ + pmd_t *pmd = pmd_offset(pud, addr); + unsigned long next; + + do { /* - * No need to loop; pte's aren't interested in the - * individual L1 entries. + * With LPAE, we must loop over to map + * all the pmds for the given range. */ - alloc_init_pte(pmd, addr, end, __phys_to_pfn(phys), type); - } + next = pmd_addr_end(addr, end); + + /* + * Try a section mapping - addr, next and phys must all be + * aligned to a section boundary. + */ + if (type->prot_sect && + ((addr | next | phys) & ~SECTION_MASK) == 0) { + __map_init_section(pmd, addr, next, phys, type); + } else { + alloc_init_pte(pmd, addr, next, + __phys_to_pfn(phys), type); + } + + phys += next - addr; + + } while (pmd++, addr = next, addr != end); } static void __init alloc_init_pud(pgd_t *pgd, unsigned long addr, @@ -619,7 +682,7 @@ static void __init alloc_init_pud(pgd_t *pgd, unsigned long addr, do { next = pud_addr_end(addr, end); - alloc_init_section(pud, addr, next, phys, type); + alloc_init_pmd(pud, addr, next, phys, type); phys += next - addr; } while (pud++, addr = next, addr != end); } @@ -757,21 +820,24 @@ void __init iotable_init(struct map_desc *io_desc, int nr) { struct map_desc *md; struct vm_struct *vm; + struct static_vm *svm; if (!nr) return; - vm = early_alloc_aligned(sizeof(*vm) * nr, __alignof__(*vm)); + svm = early_alloc_aligned(sizeof(*svm) * nr, __alignof__(*svm)); for (md = io_desc; nr; md++, nr--) { create_mapping(md); + + vm = &svm->vm; vm->addr = (void *)(md->virtual & PAGE_MASK); vm->size = PAGE_ALIGN(md->length + (md->virtual & ~PAGE_MASK)); vm->phys_addr = __pfn_to_phys(md->pfn); vm->flags = VM_IOREMAP | VM_ARM_STATIC_MAPPING; vm->flags |= VM_ARM_MTYPE(md->type); vm->caller = iotable_init; - vm_area_add_early(vm++); + add_static_vm_early(svm++); } } @@ -779,13 +845,16 @@ void __init vm_reserve_area_early(unsigned long addr, unsigned long size, void *caller) { struct vm_struct *vm; + struct static_vm *svm; + + svm = early_alloc_aligned(sizeof(*svm), __alignof__(*svm)); - vm = early_alloc_aligned(sizeof(*vm), __alignof__(*vm)); + vm = &svm->vm; vm->addr = (void *)addr; vm->size = size; vm->flags = VM_IOREMAP | VM_ARM_EMPTY_MAPPING; vm->caller = caller; - vm_area_add_early(vm); + add_static_vm_early(svm); } #ifndef CONFIG_ARM_LPAE @@ -810,14 +879,13 @@ static void __init pmd_empty_section_gap(unsigned long addr) static void __init fill_pmd_gaps(void) { + struct static_vm *svm; struct vm_struct *vm; unsigned long addr, next = 0; pmd_t *pmd; - /* we're still single threaded hence no lock needed here */ - for (vm = vmlist; vm; vm = vm->next) { - if (!(vm->flags & (VM_ARM_STATIC_MAPPING | VM_ARM_EMPTY_MAPPING))) - continue; + list_for_each_entry(svm, &static_vmlist, list) { + vm = &svm->vm; addr = (unsigned long)vm->addr; if (addr < next) continue; @@ -857,19 +925,12 @@ static void __init fill_pmd_gaps(void) #if defined(CONFIG_PCI) && !defined(CONFIG_NEED_MACH_IO_H) static void __init pci_reserve_io(void) { - struct vm_struct *vm; - unsigned long addr; + struct static_vm *svm; - /* we're still single threaded hence no lock needed here */ - for (vm = vmlist; vm; vm = vm->next) { - if (!(vm->flags & VM_ARM_STATIC_MAPPING)) - continue; - addr = (unsigned long)vm->addr; - addr &= ~(SZ_2M - 1); - if (addr == PCI_IO_VIRT_BASE) - return; + svm = find_static_vm_vaddr((void *)PCI_IO_VIRT_BASE); + if (svm) + return; - } vm_reserve_area_early(PCI_IO_VIRT_BASE, SZ_2M, pci_reserve_io); } #else @@ -1236,6 +1297,7 @@ void __init paging_init(struct machine_desc *mdesc) dma_contiguous_remap(); devicemaps_init(mdesc); kmap_init(); + tcm_init(); top_pmd = pmd_off_k(0xffff0000); diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c index d51225f..eb5293a 100644 --- a/arch/arm/mm/nommu.c +++ b/arch/arm/mm/nommu.c @@ -57,6 +57,12 @@ void flush_dcache_page(struct page *page) } EXPORT_SYMBOL(flush_dcache_page); +void flush_kernel_dcache_page(struct page *page) +{ + __cpuc_flush_dcache_area(page_address(page), PAGE_SIZE); +} +EXPORT_SYMBOL(flush_kernel_dcache_page); + void copy_to_user_page(struct vm_area_struct *vma, struct page *page, unsigned long uaddr, void *dst, const void *src, unsigned long len) diff --git a/arch/arm/mm/proc-arm740.S b/arch/arm/mm/proc-arm740.S index dc5de5d..fde2d2a 100644 --- a/arch/arm/mm/proc-arm740.S +++ b/arch/arm/mm/proc-arm740.S @@ -77,24 +77,27 @@ __arm740_setup: mcr p15, 0, r0, c6, c0 @ set area 0, default ldr r0, =(CONFIG_DRAM_BASE & 0xFFFFF000) @ base[31:12] of RAM - ldr r1, =(CONFIG_DRAM_SIZE >> 12) @ size of RAM (must be >= 4KB) - mov r2, #10 @ 11 is the minimum (4KB) -1: add r2, r2, #1 @ area size *= 2 - mov r1, r1, lsr #1 + ldr r3, =(CONFIG_DRAM_SIZE >> 12) @ size of RAM (must be >= 4KB) + mov r4, #10 @ 11 is the minimum (4KB) +1: add r4, r4, #1 @ area size *= 2 + movs r3, r3, lsr #1 bne 1b @ count not zero r-shift - orr r0, r0, r2, lsl #1 @ the area register value + orr r0, r0, r4, lsl #1 @ the area register value orr r0, r0, #1 @ set enable bit mcr p15, 0, r0, c6, c1 @ set area 1, RAM ldr r0, =(CONFIG_FLASH_MEM_BASE & 0xFFFFF000) @ base[31:12] of FLASH - ldr r1, =(CONFIG_FLASH_SIZE >> 12) @ size of FLASH (must be >= 4KB) - mov r2, #10 @ 11 is the minimum (4KB) -1: add r2, r2, #1 @ area size *= 2 - mov r1, r1, lsr #1 + ldr r3, =(CONFIG_FLASH_SIZE >> 12) @ size of FLASH (must be >= 4KB) + cmp r3, #0 + moveq r0, #0 + beq 2f + mov r4, #10 @ 11 is the minimum (4KB) +1: add r4, r4, #1 @ area size *= 2 + movs r3, r3, lsr #1 bne 1b @ count not zero r-shift - orr r0, r0, r2, lsl #1 @ the area register value + orr r0, r0, r4, lsl #1 @ the area register value orr r0, r0, #1 @ set enable bit - mcr p15, 0, r0, c6, c2 @ set area 2, ROM/FLASH +2: mcr p15, 0, r0, c6, c2 @ set area 2, ROM/FLASH mov r0, #0x06 mcr p15, 0, r0, c2, c0 @ Region 1&2 cacheable @@ -137,13 +140,14 @@ __arm740_proc_info: .long 0x41807400 .long 0xfffffff0 .long 0 + .long 0 b __arm740_setup .long cpu_arch_name .long cpu_elf_name - .long HWCAP_SWP | HWCAP_HALF | HWCAP_26BIT + .long HWCAP_SWP | HWCAP_HALF | HWCAP_THUMB | HWCAP_26BIT .long cpu_arm740_name .long arm740_processor_functions .long 0 .long 0 - .long v3_cache_fns @ cache model + .long v4_cache_fns @ cache model .size __arm740_proc_info, . - __arm740_proc_info diff --git a/arch/arm/mm/proc-arm920.S b/arch/arm/mm/proc-arm920.S index 2c3b942..2556cf1 100644 --- a/arch/arm/mm/proc-arm920.S +++ b/arch/arm/mm/proc-arm920.S @@ -387,7 +387,7 @@ ENTRY(cpu_arm920_set_pte_ext) /* Suspend/resume support: taken from arch/arm/plat-s3c24xx/sleep.S */ .globl cpu_arm920_suspend_size .equ cpu_arm920_suspend_size, 4 * 3 -#ifdef CONFIG_PM_SLEEP +#ifdef CONFIG_ARM_CPU_SUSPEND ENTRY(cpu_arm920_do_suspend) stmfd sp!, {r4 - r6, lr} mrc p15, 0, r4, c13, c0, 0 @ PID diff --git a/arch/arm/mm/proc-arm926.S b/arch/arm/mm/proc-arm926.S index f1803f7..344c8a5 100644 --- a/arch/arm/mm/proc-arm926.S +++ b/arch/arm/mm/proc-arm926.S @@ -402,7 +402,7 @@ ENTRY(cpu_arm926_set_pte_ext) /* Suspend/resume support: taken from arch/arm/plat-s3c24xx/sleep.S */ .globl cpu_arm926_suspend_size .equ cpu_arm926_suspend_size, 4 * 3 -#ifdef CONFIG_PM_SLEEP +#ifdef CONFIG_ARM_CPU_SUSPEND ENTRY(cpu_arm926_do_suspend) stmfd sp!, {r4 - r6, lr} mrc p15, 0, r4, c13, c0, 0 @ PID diff --git a/arch/arm/mm/proc-fa526.S b/arch/arm/mm/proc-fa526.S index d217e97..aaeb6c1 100644 --- a/arch/arm/mm/proc-fa526.S +++ b/arch/arm/mm/proc-fa526.S @@ -81,7 +81,6 @@ ENDPROC(cpu_fa526_reset) */ .align 4 ENTRY(cpu_fa526_do_idle) - mcr p15, 0, r0, c7, c0, 4 @ Wait for interrupt mov pc, lr diff --git a/arch/arm/mm/proc-macros.S b/arch/arm/mm/proc-macros.S index eb6aa73..e3c48a3 100644 --- a/arch/arm/mm/proc-macros.S +++ b/arch/arm/mm/proc-macros.S @@ -38,9 +38,14 @@ /* * mmid - get context id from mm pointer (mm->context.id) + * note, this field is 64bit, so in big-endian the two words are swapped too. */ .macro mmid, rd, rn +#ifdef __ARMEB__ + ldr \rd, [\rn, #MM_CONTEXT_ID + 4 ] +#else ldr \rd, [\rn, #MM_CONTEXT_ID] +#endif .endm /* @@ -328,3 +333,8 @@ ENTRY(\name\()_tlb_fns) .endif .size \name\()_tlb_fns, . - \name\()_tlb_fns .endm + +.macro globl_equ x, y + .globl \x + .equ \x, \y +.endm diff --git a/arch/arm/mm/proc-mohawk.S b/arch/arm/mm/proc-mohawk.S index 82f9cdc..0b60dd3 100644 --- a/arch/arm/mm/proc-mohawk.S +++ b/arch/arm/mm/proc-mohawk.S @@ -350,7 +350,7 @@ ENTRY(cpu_mohawk_set_pte_ext) .globl cpu_mohawk_suspend_size .equ cpu_mohawk_suspend_size, 4 * 6 -#ifdef CONFIG_PM_SLEEP +#ifdef CONFIG_ARM_CPU_SUSPEND ENTRY(cpu_mohawk_do_suspend) stmfd sp!, {r4 - r9, lr} mrc p14, 0, r4, c6, c0, 0 @ clock configuration, for turbo mode diff --git a/arch/arm/mm/proc-sa1100.S b/arch/arm/mm/proc-sa1100.S index 3aa0da1..d92dfd0 100644 --- a/arch/arm/mm/proc-sa1100.S +++ b/arch/arm/mm/proc-sa1100.S @@ -172,7 +172,7 @@ ENTRY(cpu_sa1100_set_pte_ext) .globl cpu_sa1100_suspend_size .equ cpu_sa1100_suspend_size, 4 * 3 -#ifdef CONFIG_PM_SLEEP +#ifdef CONFIG_ARM_CPU_SUSPEND ENTRY(cpu_sa1100_do_suspend) stmfd sp!, {r4 - r6, lr} mrc p15, 0, r4, c3, c0, 0 @ domain ID diff --git a/arch/arm/mm/proc-syms.c b/arch/arm/mm/proc-syms.c index 3e6210b..054b491 100644 --- a/arch/arm/mm/proc-syms.c +++ b/arch/arm/mm/proc-syms.c @@ -17,7 +17,9 @@ #ifndef MULTI_CPU EXPORT_SYMBOL(cpu_dcache_clean_area); +#ifdef CONFIG_MMU EXPORT_SYMBOL(cpu_set_pte_ext); +#endif #else EXPORT_SYMBOL(processor); #endif diff --git a/arch/arm/mm/proc-v6.S b/arch/arm/mm/proc-v6.S index 09c5233..919405e 100644 --- a/arch/arm/mm/proc-v6.S +++ b/arch/arm/mm/proc-v6.S @@ -80,12 +80,10 @@ ENTRY(cpu_v6_do_idle) mov pc, lr ENTRY(cpu_v6_dcache_clean_area) -#ifndef TLB_CAN_READ_FROM_L1_CACHE 1: mcr p15, 0, r0, c7, c10, 1 @ clean D entry add r0, r0, #D_CACHE_LINE_SIZE subs r1, r1, #D_CACHE_LINE_SIZE bhi 1b -#endif mov pc, lr /* @@ -101,7 +99,7 @@ ENTRY(cpu_v6_dcache_clean_area) ENTRY(cpu_v6_switch_mm) #ifdef CONFIG_MMU mov r2, #0 - ldr r1, [r1, #MM_CONTEXT_ID] @ get mm->context.id + mmid r1, r1 @ get mm->context.id ALT_SMP(orr r0, r0, #TTB_FLAGS_SMP) ALT_UP(orr r0, r0, #TTB_FLAGS_UP) mcr p15, 0, r2, c7, c5, 6 @ flush BTAC/BTB @@ -138,7 +136,7 @@ ENTRY(cpu_v6_set_pte_ext) /* Suspend/resume support: taken from arch/arm/mach-s3c64xx/sleep.S */ .globl cpu_v6_suspend_size .equ cpu_v6_suspend_size, 4 * 6 -#ifdef CONFIG_PM_SLEEP +#ifdef CONFIG_ARM_CPU_SUSPEND ENTRY(cpu_v6_do_suspend) stmfd sp!, {r4 - r9, lr} mrc p15, 0, r4, c13, c0, 0 @ FCSE/PID diff --git a/arch/arm/mm/proc-v7-2level.S b/arch/arm/mm/proc-v7-2level.S index 6d98c13..9704097 100644 --- a/arch/arm/mm/proc-v7-2level.S +++ b/arch/arm/mm/proc-v7-2level.S @@ -40,7 +40,7 @@ ENTRY(cpu_v7_switch_mm) #ifdef CONFIG_MMU mov r2, #0 - ldr r1, [r1, #MM_CONTEXT_ID] @ get mm->context.id + mmid r1, r1 @ get mm->context.id ALT_SMP(orr r0, r0, #TTB_FLAGS_SMP) ALT_UP(orr r0, r0, #TTB_FLAGS_UP) #ifdef CONFIG_ARM_ERRATA_430973 @@ -110,7 +110,8 @@ ENTRY(cpu_v7_set_pte_ext) ARM( str r3, [r0, #2048]! ) THUMB( add r0, r0, #2048 ) THUMB( str r3, [r0] ) - mcr p15, 0, r0, c7, c10, 1 @ flush_pte + ALT_SMP(mov pc,lr) + ALT_UP (mcr p15, 0, r0, c7, c10, 1) @ flush_pte #endif mov pc, lr ENDPROC(cpu_v7_set_pte_ext) diff --git a/arch/arm/mm/proc-v7-3level.S b/arch/arm/mm/proc-v7-3level.S index 7b56386..363027e 100644 --- a/arch/arm/mm/proc-v7-3level.S +++ b/arch/arm/mm/proc-v7-3level.S @@ -47,8 +47,8 @@ */ ENTRY(cpu_v7_switch_mm) #ifdef CONFIG_MMU - ldr r1, [r1, #MM_CONTEXT_ID] @ get mm->context.id - and r3, r1, #0xff + mmid r1, r1 @ get mm->context.id + asid r3, r1 mov r3, r3, lsl #(48 - 32) @ ASID mcrr p15, 0, r0, r3, c2 @ set TTB 0 isb @@ -73,7 +73,8 @@ ENTRY(cpu_v7_set_pte_ext) tst r3, #1 << (55 - 32) @ L_PTE_DIRTY orreq r2, #L_PTE_RDONLY 1: strd r2, r3, [r0] - mcr p15, 0, r0, c7, c10, 1 @ flush_pte + ALT_SMP(mov pc, lr) + ALT_UP (mcr p15, 0, r0, c7, c10, 1) @ flush_pte #endif mov pc, lr ENDPROC(cpu_v7_set_pte_ext) diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S index 3a3c015..e35fec3 100644 --- a/arch/arm/mm/proc-v7.S +++ b/arch/arm/mm/proc-v7.S @@ -75,14 +75,14 @@ ENTRY(cpu_v7_do_idle) ENDPROC(cpu_v7_do_idle) ENTRY(cpu_v7_dcache_clean_area) -#ifndef TLB_CAN_READ_FROM_L1_CACHE + 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 add r0, r0, r2 subs r1, r1, r2 bhi 1b dsb -#endif mov pc, lr ENDPROC(cpu_v7_dcache_clean_area) @@ -140,6 +140,29 @@ ENTRY(cpu_v7_do_resume) ENDPROC(cpu_v7_do_resume) #endif +#ifdef CONFIG_CPU_PJ4B + globl_equ cpu_pj4b_switch_mm, cpu_v7_switch_mm + globl_equ cpu_pj4b_set_pte_ext, cpu_v7_set_pte_ext + globl_equ cpu_pj4b_proc_init, cpu_v7_proc_init + globl_equ cpu_pj4b_proc_fin, cpu_v7_proc_fin + globl_equ cpu_pj4b_reset, cpu_v7_reset +#ifdef CONFIG_PJ4B_ERRATA_4742 +ENTRY(cpu_pj4b_do_idle) + dsb @ WFI may enter a low-power mode + wfi + dsb @barrier + mov pc, lr +ENDPROC(cpu_pj4b_do_idle) +#else + globl_equ cpu_pj4b_do_idle, cpu_v7_do_idle +#endif + globl_equ cpu_pj4b_dcache_clean_area, cpu_v7_dcache_clean_area + globl_equ cpu_pj4b_do_suspend, cpu_v7_do_suspend + globl_equ cpu_pj4b_do_resume, cpu_v7_do_resume + globl_equ cpu_pj4b_suspend_size, cpu_v7_suspend_size + +#endif + __CPUINIT /* @@ -350,6 +373,9 @@ __v7_setup_stack: @ define struct processor (see <asm/proc-fns.h> and proc-macros.S) define_processor_functions v7, dabort=v7_early_abort, pabort=v7_pabort, suspend=1 +#ifdef CONFIG_CPU_PJ4B + define_processor_functions pj4b, dabort=v7_early_abort, pabort=v7_pabort, suspend=1 +#endif .section ".rodata" @@ -362,7 +388,7 @@ __v7_setup_stack: /* * Standard v7 proc info content */ -.macro __v7_proc initfunc, mm_mmuflags = 0, io_mmuflags = 0, hwcaps = 0 +.macro __v7_proc initfunc, mm_mmuflags = 0, io_mmuflags = 0, hwcaps = 0, proc_fns = v7_processor_functions ALT_SMP(.long PMD_TYPE_SECT | PMD_SECT_AP_WRITE | PMD_SECT_AP_READ | \ PMD_SECT_AF | PMD_FLAGS_SMP | \mm_mmuflags) ALT_UP(.long PMD_TYPE_SECT | PMD_SECT_AP_WRITE | PMD_SECT_AP_READ | \ @@ -375,7 +401,7 @@ __v7_setup_stack: .long HWCAP_SWP | HWCAP_HALF | HWCAP_THUMB | HWCAP_FAST_MULT | \ HWCAP_EDSP | HWCAP_TLS | \hwcaps .long cpu_v7_name - .long v7_processor_functions + .long \proc_fns .long v7wbi_tlb_fns .long v6_user_fns .long v7_cache_fns @@ -402,16 +428,19 @@ __v7_ca9mp_proc_info: __v7_proc __v7_ca9mp_setup .size __v7_ca9mp_proc_info, . - __v7_ca9mp_proc_info +#endif /* CONFIG_ARM_LPAE */ + /* * Marvell PJ4B processor. */ +#ifdef CONFIG_CPU_PJ4B .type __v7_pj4b_proc_info, #object __v7_pj4b_proc_info: - .long 0x562f5840 - .long 0xfffffff0 - __v7_proc __v7_pj4b_setup + .long 0x560f5800 + .long 0xff0fff00 + __v7_proc __v7_pj4b_setup, proc_fns = pj4b_processor_functions .size __v7_pj4b_proc_info, . - __v7_pj4b_proc_info -#endif /* CONFIG_ARM_LPAE */ +#endif /* * ARM Ltd. Cortex A7 processor. @@ -420,7 +449,7 @@ __v7_pj4b_proc_info: __v7_ca7mp_proc_info: .long 0x410fc070 .long 0xff0ffff0 - __v7_proc __v7_ca7mp_setup, hwcaps = HWCAP_IDIV + __v7_proc __v7_ca7mp_setup .size __v7_ca7mp_proc_info, . - __v7_ca7mp_proc_info /* @@ -430,10 +459,25 @@ __v7_ca7mp_proc_info: __v7_ca15mp_proc_info: .long 0x410fc0f0 .long 0xff0ffff0 - __v7_proc __v7_ca15mp_setup, hwcaps = HWCAP_IDIV + __v7_proc __v7_ca15mp_setup .size __v7_ca15mp_proc_info, . - __v7_ca15mp_proc_info /* + * Qualcomm Inc. Krait processors. + */ + .type __krait_proc_info, #object +__krait_proc_info: + .long 0x510f0400 @ Required ID value + .long 0xff0ffc00 @ Mask for ID + /* + * Some Krait processors don't indicate support for SDIV and UDIV + * instructions in the ARM instruction set, even though they actually + * do support them. + */ + __v7_proc __v7_setup, hwcaps = HWCAP_IDIV + .size __krait_proc_info, . - __krait_proc_info + + /* * Match any ARMv7 processor core. */ .type __v7_proc_info, #object diff --git a/arch/arm/mm/proc-xsc3.S b/arch/arm/mm/proc-xsc3.S index eb93d64..e8efd83 100644 --- a/arch/arm/mm/proc-xsc3.S +++ b/arch/arm/mm/proc-xsc3.S @@ -413,7 +413,7 @@ ENTRY(cpu_xsc3_set_pte_ext) .globl cpu_xsc3_suspend_size .equ cpu_xsc3_suspend_size, 4 * 6 -#ifdef CONFIG_PM_SLEEP +#ifdef CONFIG_ARM_CPU_SUSPEND ENTRY(cpu_xsc3_do_suspend) stmfd sp!, {r4 - r9, lr} mrc p14, 0, r4, c6, c0, 0 @ clock configuration, for turbo mode diff --git a/arch/arm/mm/proc-xscale.S b/arch/arm/mm/proc-xscale.S index 2551036..e766f88 100644 --- a/arch/arm/mm/proc-xscale.S +++ b/arch/arm/mm/proc-xscale.S @@ -528,7 +528,7 @@ ENTRY(cpu_xscale_set_pte_ext) .globl cpu_xscale_suspend_size .equ cpu_xscale_suspend_size, 4 * 6 -#ifdef CONFIG_PM_SLEEP +#ifdef CONFIG_ARM_CPU_SUSPEND ENTRY(cpu_xscale_do_suspend) stmfd sp!, {r4 - r9, lr} mrc p14, 0, r4, c6, c0, 0 @ clock configuration, for turbo mode diff --git a/arch/arm/mm/tcm.h b/arch/arm/mm/tcm.h new file mode 100644 index 0000000..8015ad4 --- /dev/null +++ b/arch/arm/mm/tcm.h @@ -0,0 +1,17 @@ +/* + * Copyright (C) 2008-2009 ST-Ericsson AB + * License terms: GNU General Public License (GPL) version 2 + * TCM memory handling for ARM systems + * + * Author: Linus Walleij <linus.walleij@stericsson.com> + * Author: Rickard Andersson <rickard.andersson@stericsson.com> + */ + +#ifdef CONFIG_HAVE_TCM +void __init tcm_init(void); +#else +/* No TCM support, just blank inlines to be optimized out */ +inline void tcm_init(void) +{ +} +#endif diff --git a/arch/arm/mm/vmregion.c b/arch/arm/mm/vmregion.c deleted file mode 100644 index a631016..0000000 --- a/arch/arm/mm/vmregion.c +++ /dev/null @@ -1,205 +0,0 @@ -#include <linux/fs.h> -#include <linux/spinlock.h> -#include <linux/list.h> -#include <linux/proc_fs.h> -#include <linux/seq_file.h> -#include <linux/slab.h> - -#include "vmregion.h" - -/* - * VM region handling support. - * - * This should become something generic, handling VM region allocations for - * vmalloc and similar (ioremap, module space, etc). - * - * I envisage vmalloc()'s supporting vm_struct becoming: - * - * struct vm_struct { - * struct vmregion region; - * unsigned long flags; - * struct page **pages; - * unsigned int nr_pages; - * unsigned long phys_addr; - * }; - * - * get_vm_area() would then call vmregion_alloc with an appropriate - * struct vmregion head (eg): - * - * struct vmregion vmalloc_head = { - * .vm_list = LIST_HEAD_INIT(vmalloc_head.vm_list), - * .vm_start = VMALLOC_START, - * .vm_end = VMALLOC_END, - * }; - * - * However, vmalloc_head.vm_start is variable (typically, it is dependent on - * the amount of RAM found at boot time.) I would imagine that get_vm_area() - * would have to initialise this each time prior to calling vmregion_alloc(). - */ - -struct arm_vmregion * -arm_vmregion_alloc(struct arm_vmregion_head *head, size_t align, - size_t size, gfp_t gfp, const void *caller) -{ - unsigned long start = head->vm_start, addr = head->vm_end; - unsigned long flags; - struct arm_vmregion *c, *new; - - if (head->vm_end - head->vm_start < size) { - printk(KERN_WARNING "%s: allocation too big (requested %#x)\n", - __func__, size); - goto out; - } - - new = kmalloc(sizeof(struct arm_vmregion), gfp); - if (!new) - goto out; - - new->caller = caller; - - spin_lock_irqsave(&head->vm_lock, flags); - - addr = rounddown(addr - size, align); - list_for_each_entry_reverse(c, &head->vm_list, vm_list) { - if (addr >= c->vm_end) - goto found; - addr = rounddown(c->vm_start - size, align); - if (addr < start) - goto nospc; - } - - found: - /* - * Insert this entry after the one we found. - */ - list_add(&new->vm_list, &c->vm_list); - new->vm_start = addr; - new->vm_end = addr + size; - new->vm_active = 1; - - spin_unlock_irqrestore(&head->vm_lock, flags); - return new; - - nospc: - spin_unlock_irqrestore(&head->vm_lock, flags); - kfree(new); - out: - return NULL; -} - -static struct arm_vmregion *__arm_vmregion_find(struct arm_vmregion_head *head, unsigned long addr) -{ - struct arm_vmregion *c; - - list_for_each_entry(c, &head->vm_list, vm_list) { - if (c->vm_active && c->vm_start == addr) - goto out; - } - c = NULL; - out: - return c; -} - -struct arm_vmregion *arm_vmregion_find(struct arm_vmregion_head *head, unsigned long addr) -{ - struct arm_vmregion *c; - unsigned long flags; - - spin_lock_irqsave(&head->vm_lock, flags); - c = __arm_vmregion_find(head, addr); - spin_unlock_irqrestore(&head->vm_lock, flags); - return c; -} - -struct arm_vmregion *arm_vmregion_find_remove(struct arm_vmregion_head *head, unsigned long addr) -{ - struct arm_vmregion *c; - unsigned long flags; - - spin_lock_irqsave(&head->vm_lock, flags); - c = __arm_vmregion_find(head, addr); - if (c) - c->vm_active = 0; - spin_unlock_irqrestore(&head->vm_lock, flags); - return c; -} - -void arm_vmregion_free(struct arm_vmregion_head *head, struct arm_vmregion *c) -{ - unsigned long flags; - - spin_lock_irqsave(&head->vm_lock, flags); - list_del(&c->vm_list); - spin_unlock_irqrestore(&head->vm_lock, flags); - - kfree(c); -} - -#ifdef CONFIG_PROC_FS -static int arm_vmregion_show(struct seq_file *m, void *p) -{ - struct arm_vmregion *c = list_entry(p, struct arm_vmregion, vm_list); - - seq_printf(m, "0x%08lx-0x%08lx %7lu", c->vm_start, c->vm_end, - c->vm_end - c->vm_start); - if (c->caller) - seq_printf(m, " %pS", (void *)c->caller); - seq_putc(m, '\n'); - return 0; -} - -static void *arm_vmregion_start(struct seq_file *m, loff_t *pos) -{ - struct arm_vmregion_head *h = m->private; - spin_lock_irq(&h->vm_lock); - return seq_list_start(&h->vm_list, *pos); -} - -static void *arm_vmregion_next(struct seq_file *m, void *p, loff_t *pos) -{ - struct arm_vmregion_head *h = m->private; - return seq_list_next(p, &h->vm_list, pos); -} - -static void arm_vmregion_stop(struct seq_file *m, void *p) -{ - struct arm_vmregion_head *h = m->private; - spin_unlock_irq(&h->vm_lock); -} - -static const struct seq_operations arm_vmregion_ops = { - .start = arm_vmregion_start, - .stop = arm_vmregion_stop, - .next = arm_vmregion_next, - .show = arm_vmregion_show, -}; - -static int arm_vmregion_open(struct inode *inode, struct file *file) -{ - struct arm_vmregion_head *h = PDE(inode)->data; - int ret = seq_open(file, &arm_vmregion_ops); - if (!ret) { - struct seq_file *m = file->private_data; - m->private = h; - } - return ret; -} - -static const struct file_operations arm_vmregion_fops = { - .open = arm_vmregion_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; - -int arm_vmregion_create_proc(const char *path, struct arm_vmregion_head *h) -{ - proc_create_data(path, S_IRUSR, NULL, &arm_vmregion_fops, h); - return 0; -} -#else -int arm_vmregion_create_proc(const char *path, struct arm_vmregion_head *h) -{ - return 0; -} -#endif diff --git a/arch/arm/mm/vmregion.h b/arch/arm/mm/vmregion.h deleted file mode 100644 index 0f5a5f2..0000000 --- a/arch/arm/mm/vmregion.h +++ /dev/null @@ -1,31 +0,0 @@ -#ifndef VMREGION_H -#define VMREGION_H - -#include <linux/spinlock.h> -#include <linux/list.h> - -struct page; - -struct arm_vmregion_head { - spinlock_t vm_lock; - struct list_head vm_list; - unsigned long vm_start; - unsigned long vm_end; -}; - -struct arm_vmregion { - struct list_head vm_list; - unsigned long vm_start; - unsigned long vm_end; - int vm_active; - const void *caller; -}; - -struct arm_vmregion *arm_vmregion_alloc(struct arm_vmregion_head *, size_t, size_t, gfp_t, const void *); -struct arm_vmregion *arm_vmregion_find(struct arm_vmregion_head *, unsigned long); -struct arm_vmregion *arm_vmregion_find_remove(struct arm_vmregion_head *, unsigned long); -void arm_vmregion_free(struct arm_vmregion_head *, struct arm_vmregion *); - -int arm_vmregion_create_proc(const char *, struct arm_vmregion_head *); - -#endif |