diff options
Diffstat (limited to 'arch/arm64/mm')
| -rw-r--r-- | arch/arm64/mm/Makefile | 2 | ||||
| -rw-r--r-- | arch/arm64/mm/dma-mapping.c | 195 | ||||
| -rw-r--r-- | arch/arm64/mm/flush.c | 16 | ||||
| -rw-r--r-- | arch/arm64/mm/init.c | 13 | ||||
| -rw-r--r-- | arch/arm64/mm/ioremap.c | 4 | ||||
| -rw-r--r-- | arch/arm64/mm/mmap.c | 2 | ||||
| -rw-r--r-- | arch/arm64/mm/mmu.c | 14 | ||||
| -rw-r--r-- | arch/arm64/mm/pageattr.c | 97 | ||||
| -rw-r--r-- | arch/arm64/mm/pgd.c | 18 | ||||
| -rw-r--r-- | arch/arm64/mm/proc.S | 15 |
10 files changed, 311 insertions, 65 deletions
diff --git a/arch/arm64/mm/Makefile b/arch/arm64/mm/Makefile index 3ecb56c624d3..c56179ed2c09 100644 --- a/arch/arm64/mm/Makefile +++ b/arch/arm64/mm/Makefile @@ -1,5 +1,5 @@ obj-y := dma-mapping.o extable.o fault.o init.o \ cache.o copypage.o flush.o \ ioremap.o mmap.o pgd.o mmu.o \ - context.o proc.o + context.o proc.o pageattr.o obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index 4164c5ace9f8..d92094203913 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -20,13 +20,11 @@ #include <linux/gfp.h> #include <linux/export.h> #include <linux/slab.h> +#include <linux/genalloc.h> #include <linux/dma-mapping.h> #include <linux/dma-contiguous.h> -#include <linux/of.h> -#include <linux/platform_device.h> #include <linux/vmalloc.h> #include <linux/swiotlb.h> -#include <linux/amba/bus.h> #include <asm/cacheflush.h> @@ -41,6 +39,54 @@ static pgprot_t __get_dma_pgprot(struct dma_attrs *attrs, pgprot_t prot, return prot; } +static struct gen_pool *atomic_pool; + +#define DEFAULT_DMA_COHERENT_POOL_SIZE SZ_256K +static size_t atomic_pool_size = DEFAULT_DMA_COHERENT_POOL_SIZE; + +static int __init early_coherent_pool(char *p) +{ + atomic_pool_size = memparse(p, &p); + return 0; +} +early_param("coherent_pool", early_coherent_pool); + +static void *__alloc_from_pool(size_t size, struct page **ret_page) +{ + unsigned long val; + void *ptr = NULL; + + if (!atomic_pool) { + WARN(1, "coherent pool not initialised!\n"); + return NULL; + } + + val = gen_pool_alloc(atomic_pool, size); + if (val) { + phys_addr_t phys = gen_pool_virt_to_phys(atomic_pool, val); + + *ret_page = phys_to_page(phys); + ptr = (void *)val; + } + + return ptr; +} + +static bool __in_atomic_pool(void *start, size_t size) +{ + return addr_in_gen_pool(atomic_pool, (unsigned long)start, size); +} + +static int __free_from_pool(void *start, size_t size) +{ + if (!__in_atomic_pool(start, size)) + return 0; + + gen_pool_free(atomic_pool, (unsigned long)start, size); + + return 1; +} + static void *__dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t flags, struct dma_attrs *attrs) @@ -53,7 +99,7 @@ static void *__dma_alloc_coherent(struct device *dev, size_t size, if (IS_ENABLED(CONFIG_ZONE_DMA) && dev->coherent_dma_mask <= DMA_BIT_MASK(32)) flags |= GFP_DMA; - if (IS_ENABLED(CONFIG_DMA_CMA)) { + if (IS_ENABLED(CONFIG_DMA_CMA) && (flags & __GFP_WAIT)) { struct page *page; size = PAGE_ALIGN(size); @@ -73,50 +119,54 @@ static void __dma_free_coherent(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_handle, struct dma_attrs *attrs) { + bool freed; + phys_addr_t paddr = dma_to_phys(dev, dma_handle); + if (dev == NULL) { WARN_ONCE(1, "Use an actual device structure for DMA allocation\n"); return; } - if (IS_ENABLED(CONFIG_DMA_CMA)) { - phys_addr_t paddr = dma_to_phys(dev, dma_handle); - - dma_release_from_contiguous(dev, + freed = dma_release_from_contiguous(dev, phys_to_page(paddr), size >> PAGE_SHIFT); - } else { + if (!freed) swiotlb_free_coherent(dev, size, vaddr, dma_handle); - } } static void *__dma_alloc_noncoherent(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t flags, struct dma_attrs *attrs) { - struct page *page, **map; + struct page *page; void *ptr, *coherent_ptr; - int order, i; size = PAGE_ALIGN(size); - order = get_order(size); + + if (!(flags & __GFP_WAIT)) { + struct page *page = NULL; + void *addr = __alloc_from_pool(size, &page); + + if (addr) + *dma_handle = phys_to_dma(dev, page_to_phys(page)); + + return addr; + + } ptr = __dma_alloc_coherent(dev, size, dma_handle, flags, attrs); if (!ptr) goto no_mem; - map = kmalloc(sizeof(struct page *) << order, flags & ~GFP_DMA); - if (!map) - goto no_map; /* remove any dirty cache lines on the kernel alias */ __dma_flush_range(ptr, ptr + size); /* create a coherent mapping */ page = virt_to_page(ptr); - for (i = 0; i < (size >> PAGE_SHIFT); i++) - map[i] = page + i; - coherent_ptr = vmap(map, size >> PAGE_SHIFT, VM_MAP, - __get_dma_pgprot(attrs, __pgprot(PROT_NORMAL_NC), false)); - kfree(map); + coherent_ptr = dma_common_contiguous_remap(page, size, VM_USERMAP, + __get_dma_pgprot(attrs, + __pgprot(PROT_NORMAL_NC), false), + NULL); if (!coherent_ptr) goto no_map; @@ -125,7 +175,7 @@ static void *__dma_alloc_noncoherent(struct device *dev, size_t size, no_map: __dma_free_coherent(dev, size, ptr, *dma_handle, attrs); no_mem: - *dma_handle = ~0; + *dma_handle = DMA_ERROR_CODE; return NULL; } @@ -135,6 +185,8 @@ static void __dma_free_noncoherent(struct device *dev, size_t size, { void *swiotlb_addr = phys_to_virt(dma_to_phys(dev, dma_handle)); + if (__free_from_pool(vaddr, size)) + return; vunmap(vaddr); __dma_free_coherent(dev, size, swiotlb_addr, dma_handle, attrs); } @@ -308,45 +360,88 @@ struct dma_map_ops coherent_swiotlb_dma_ops = { }; EXPORT_SYMBOL(coherent_swiotlb_dma_ops); -static int dma_bus_notifier(struct notifier_block *nb, - unsigned long event, void *_dev) -{ - struct device *dev = _dev; - - if (event != BUS_NOTIFY_ADD_DEVICE) - return NOTIFY_DONE; - - if (of_property_read_bool(dev->of_node, "dma-coherent")) - set_dma_ops(dev, &coherent_swiotlb_dma_ops); +extern int swiotlb_late_init_with_default_size(size_t default_size); - return NOTIFY_OK; +static int __init atomic_pool_init(void) +{ + pgprot_t prot = __pgprot(PROT_NORMAL_NC); + unsigned long nr_pages = atomic_pool_size >> PAGE_SHIFT; + struct page *page; + void *addr; + unsigned int pool_size_order = get_order(atomic_pool_size); + + if (dev_get_cma_area(NULL)) + page = dma_alloc_from_contiguous(NULL, nr_pages, + pool_size_order); + else + page = alloc_pages(GFP_DMA, pool_size_order); + + if (page) { + int ret; + void *page_addr = page_address(page); + + memset(page_addr, 0, atomic_pool_size); + __dma_flush_range(page_addr, page_addr + atomic_pool_size); + + atomic_pool = gen_pool_create(PAGE_SHIFT, -1); + if (!atomic_pool) + goto free_page; + + addr = dma_common_contiguous_remap(page, atomic_pool_size, + VM_USERMAP, prot, atomic_pool_init); + + if (!addr) + goto destroy_genpool; + + ret = gen_pool_add_virt(atomic_pool, (unsigned long)addr, + page_to_phys(page), + atomic_pool_size, -1); + if (ret) + goto remove_mapping; + + gen_pool_set_algo(atomic_pool, + gen_pool_first_fit_order_align, + (void *)PAGE_SHIFT); + + pr_info("DMA: preallocated %zu KiB pool for atomic allocations\n", + atomic_pool_size / 1024); + return 0; + } + goto out; + +remove_mapping: + dma_common_free_remap(addr, atomic_pool_size, VM_USERMAP); +destroy_genpool: + gen_pool_destroy(atomic_pool); + atomic_pool = NULL; +free_page: + if (!dma_release_from_contiguous(NULL, page, nr_pages)) + __free_pages(page, pool_size_order); +out: + pr_err("DMA: failed to allocate %zu KiB pool for atomic coherent allocation\n", + atomic_pool_size / 1024); + return -ENOMEM; } -static struct notifier_block platform_bus_nb = { - .notifier_call = dma_bus_notifier, -}; - -static struct notifier_block amba_bus_nb = { - .notifier_call = dma_bus_notifier, -}; - -extern int swiotlb_late_init_with_default_size(size_t default_size); - static int __init swiotlb_late_init(void) { size_t swiotlb_size = min(SZ_64M, MAX_ORDER_NR_PAGES << PAGE_SHIFT); - /* - * These must be registered before of_platform_populate(). - */ - bus_register_notifier(&platform_bus_type, &platform_bus_nb); - bus_register_notifier(&amba_bustype, &amba_bus_nb); - dma_ops = &noncoherent_swiotlb_dma_ops; return swiotlb_late_init_with_default_size(swiotlb_size); } -arch_initcall(swiotlb_late_init); + +static int __init arm64_dma_init(void) +{ + int ret = 0; + + ret |= swiotlb_late_init(); + ret |= atomic_pool_init(); + + return ret; +} +arch_initcall(arm64_dma_init); #define PREALLOC_DMA_DEBUG_ENTRIES 4096 diff --git a/arch/arm64/mm/flush.c b/arch/arm64/mm/flush.c index 0d64089d28b5..b6f14e8d2121 100644 --- a/arch/arm64/mm/flush.c +++ b/arch/arm64/mm/flush.c @@ -104,3 +104,19 @@ EXPORT_SYMBOL(flush_dcache_page); */ EXPORT_SYMBOL(flush_cache_all); EXPORT_SYMBOL(flush_icache_range); + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +#ifdef CONFIG_HAVE_RCU_TABLE_FREE +void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address, + pmd_t *pmdp) +{ + pmd_t pmd = pmd_mksplitting(*pmdp); + + VM_BUG_ON(address & ~PMD_MASK); + set_pmd_at(vma->vm_mm, address, pmdp, pmd); + + /* dummy IPI to serialise against fast_gup */ + kick_all_cpus_sync(); +} +#endif /* CONFIG_HAVE_RCU_TABLE_FREE */ +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 5472c2401876..494297c698ca 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -149,8 +149,7 @@ void __init arm64_memblock_init(void) memblock_reserve(__virt_to_phys(initrd_start), initrd_end - initrd_start); #endif - if (!efi_enabled(EFI_MEMMAP)) - early_init_fdt_scan_reserved_mem(); + early_init_fdt_scan_reserved_mem(); /* 4GB maximum for 32-bit only capable devices */ if (IS_ENABLED(CONFIG_ZONE_DMA)) @@ -256,7 +255,7 @@ static void __init free_unused_memmap(void) */ void __init mem_init(void) { - max_mapnr = pfn_to_page(max_pfn + PHYS_PFN_OFFSET) - mem_map; + set_max_mapnr(pfn_to_page(max_pfn) - mem_map); #ifndef CONFIG_SPARSEMEM_VMEMMAP free_unused_memmap(); @@ -334,8 +333,14 @@ static int keep_initrd; void free_initrd_mem(unsigned long start, unsigned long end) { - if (!keep_initrd) + if (!keep_initrd) { + if (start == initrd_start) + start = round_down(start, PAGE_SIZE); + if (end == initrd_end) + end = round_up(end, PAGE_SIZE); + free_reserved_area((void *)start, (void *)end, 0, "initrd"); + } } static int __init keepinitrd_setup(char *__unused) diff --git a/arch/arm64/mm/ioremap.c b/arch/arm64/mm/ioremap.c index fa324bd5a5c4..4a07630a6616 100644 --- a/arch/arm64/mm/ioremap.c +++ b/arch/arm64/mm/ioremap.c @@ -105,10 +105,10 @@ EXPORT_SYMBOL(ioremap_cache); static pte_t bm_pte[PTRS_PER_PTE] __page_aligned_bss; #if CONFIG_ARM64_PGTABLE_LEVELS > 2 -static pte_t bm_pmd[PTRS_PER_PMD] __page_aligned_bss; +static pmd_t bm_pmd[PTRS_PER_PMD] __page_aligned_bss; #endif #if CONFIG_ARM64_PGTABLE_LEVELS > 3 -static pte_t bm_pud[PTRS_PER_PUD] __page_aligned_bss; +static pud_t bm_pud[PTRS_PER_PUD] __page_aligned_bss; #endif static inline pud_t * __init early_ioremap_pud(unsigned long addr) diff --git a/arch/arm64/mm/mmap.c b/arch/arm64/mm/mmap.c index 8ed6cb1a900f..1d73662f00ff 100644 --- a/arch/arm64/mm/mmap.c +++ b/arch/arm64/mm/mmap.c @@ -102,7 +102,7 @@ EXPORT_SYMBOL_GPL(arch_pick_mmap_layout); * You really shouldn't be using read() or write() on /dev/mem. This might go * away in the future. */ -int valid_phys_addr_range(unsigned long addr, size_t size) +int valid_phys_addr_range(phys_addr_t addr, size_t size) { if (addr < PHYS_OFFSET) return 0; diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index c55567283cde..0bf90d26e745 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -94,7 +94,7 @@ static int __init early_cachepolicy(char *p) */ asm volatile( " mrs %0, mair_el1\n" - " bfi %0, %1, #%2, #8\n" + " bfi %0, %1, %2, #8\n" " msr mair_el1, %0\n" " isb\n" : "=&r" (tmp) @@ -297,11 +297,15 @@ static void __init map_mem(void) * create_mapping requires puds, pmds and ptes to be allocated from * memory addressable from the initial direct kernel mapping. * - * The initial direct kernel mapping, located at swapper_pg_dir, - * gives us PUD_SIZE memory starting from PHYS_OFFSET (which must be - * aligned to 2MB as per Documentation/arm64/booting.txt). + * The initial direct kernel mapping, located at swapper_pg_dir, gives + * us PUD_SIZE (4K pages) or PMD_SIZE (64K pages) memory starting from + * PHYS_OFFSET (which must be aligned to 2MB as per + * Documentation/arm64/booting.txt). */ - limit = PHYS_OFFSET + PUD_SIZE; + if (IS_ENABLED(CONFIG_ARM64_64K_PAGES)) + limit = PHYS_OFFSET + PMD_SIZE; + else + limit = PHYS_OFFSET + PUD_SIZE; memblock_set_current_limit(limit); /* map all the memory banks */ diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c new file mode 100644 index 000000000000..bb0ea94c4ba1 --- /dev/null +++ b/arch/arm64/mm/pageattr.c @@ -0,0 +1,97 @@ +/* + * Copyright (c) 2014, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ +#include <linux/kernel.h> +#include <linux/mm.h> +#include <linux/module.h> +#include <linux/sched.h> + +#include <asm/pgtable.h> +#include <asm/tlbflush.h> + +struct page_change_data { + pgprot_t set_mask; + pgprot_t clear_mask; +}; + +static int change_page_range(pte_t *ptep, pgtable_t token, unsigned long addr, + void *data) +{ + struct page_change_data *cdata = data; + pte_t pte = *ptep; + + pte = clear_pte_bit(pte, cdata->clear_mask); + pte = set_pte_bit(pte, cdata->set_mask); + + set_pte(ptep, pte); + return 0; +} + +static int change_memory_common(unsigned long addr, int numpages, + pgprot_t set_mask, pgprot_t clear_mask) +{ + unsigned long start = addr; + unsigned long size = PAGE_SIZE*numpages; + unsigned long end = start + size; + int ret; + struct page_change_data data; + + if (!IS_ALIGNED(addr, PAGE_SIZE)) { + start &= PAGE_MASK; + end = start + size; + WARN_ON_ONCE(1); + } + + if (!is_module_address(start) || !is_module_address(end - 1)) + return -EINVAL; + + data.set_mask = set_mask; + data.clear_mask = clear_mask; + + ret = apply_to_page_range(&init_mm, start, size, change_page_range, + &data); + + flush_tlb_kernel_range(start, end); + return ret; +} + +int set_memory_ro(unsigned long addr, int numpages) +{ + return change_memory_common(addr, numpages, + __pgprot(PTE_RDONLY), + __pgprot(PTE_WRITE)); +} +EXPORT_SYMBOL_GPL(set_memory_ro); + +int set_memory_rw(unsigned long addr, int numpages) +{ + return change_memory_common(addr, numpages, + __pgprot(PTE_WRITE), + __pgprot(PTE_RDONLY)); +} +EXPORT_SYMBOL_GPL(set_memory_rw); + +int set_memory_nx(unsigned long addr, int numpages) +{ + return change_memory_common(addr, numpages, + __pgprot(PTE_PXN), + __pgprot(0)); +} +EXPORT_SYMBOL_GPL(set_memory_nx); + +int set_memory_x(unsigned long addr, int numpages) +{ + return change_memory_common(addr, numpages, + __pgprot(0), + __pgprot(PTE_PXN)); +} +EXPORT_SYMBOL_GPL(set_memory_x); diff --git a/arch/arm64/mm/pgd.c b/arch/arm64/mm/pgd.c index 62c6101df260..6682b361d3ac 100644 --- a/arch/arm64/mm/pgd.c +++ b/arch/arm64/mm/pgd.c @@ -30,12 +30,14 @@ #define PGD_SIZE (PTRS_PER_PGD * sizeof(pgd_t)) +static struct kmem_cache *pgd_cache; + pgd_t *pgd_alloc(struct mm_struct *mm) { if (PGD_SIZE == PAGE_SIZE) return (pgd_t *)get_zeroed_page(GFP_KERNEL); else - return kzalloc(PGD_SIZE, GFP_KERNEL); + return kmem_cache_zalloc(pgd_cache, GFP_KERNEL); } void pgd_free(struct mm_struct *mm, pgd_t *pgd) @@ -43,5 +45,17 @@ void pgd_free(struct mm_struct *mm, pgd_t *pgd) if (PGD_SIZE == PAGE_SIZE) free_page((unsigned long)pgd); else - kfree(pgd); + kmem_cache_free(pgd_cache, pgd); +} + +static int __init pgd_cache_init(void) +{ + /* + * Naturally aligned pgds required by the architecture. + */ + if (PGD_SIZE != PAGE_SIZE) + pgd_cache = kmem_cache_create("pgd_cache", PGD_SIZE, PGD_SIZE, + SLAB_PANIC, NULL); + return 0; } +core_initcall(pgd_cache_init); diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index 7736779c9809..4e778b13291b 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -76,6 +76,21 @@ ENTRY(cpu_reset) ret x0 ENDPROC(cpu_reset) +ENTRY(cpu_soft_restart) + /* Save address of cpu_reset() and reset address */ + mov x19, x0 + mov x20, x1 + + /* Turn D-cache off */ + bl cpu_cache_off + + /* Push out all dirty data, and ensure cache is empty */ + bl flush_cache_all + + mov x0, x20 + ret x19 +ENDPROC(cpu_soft_restart) + /* * cpu_do_idle() * |