| /* |
| * Contiguous Memory Allocator for DMA mapping framework |
| * Copyright (c) 2010-2011 by Samsung Electronics. |
| * Written by: |
| * Marek Szyprowski <m.szyprowski@samsung.com> |
| * Michal Nazarewicz <mina86@mina86.com> |
| * |
| * This program is free software; you can redistribute it and/or |
| * modify it under the terms of the GNU General Public License as |
| * published by the Free Software Foundation; either version 2 of the |
| * License or (at your optional) any later version of the license. |
| */ |
| |
| #define pr_fmt(fmt) "cma: " fmt |
| |
| #ifdef CONFIG_CMA_DEBUG |
| #ifndef DEBUG |
| # define DEBUG |
| #endif |
| #endif |
| |
| #include <asm/page.h> |
| #include <asm/dma-contiguous.h> |
| |
| #include <linux/buffer_head.h> |
| #include <linux/memblock.h> |
| #include <linux/err.h> |
| #include <linux/mm.h> |
| #include <linux/mutex.h> |
| #include <linux/page-isolation.h> |
| #include <linux/sizes.h> |
| #include <linux/slab.h> |
| #include <linux/swap.h> |
| #include <linux/mm_types.h> |
| #include <linux/dma-contiguous.h> |
| #include <linux/dma-mapping.h> |
| |
| #include <asm/tlbflush.h> |
| #include <asm/cacheflush.h> |
| #include <asm/outercache.h> |
| |
| struct cma { |
| unsigned long base_pfn; |
| unsigned long count; |
| unsigned long *bitmap; |
| }; |
| |
| struct cma *dma_contiguous_default_area; |
| |
| #ifdef CONFIG_CMA_SIZE_MBYTES |
| #define CMA_SIZE_MBYTES CONFIG_CMA_SIZE_MBYTES |
| #else |
| #define CMA_SIZE_MBYTES 0 |
| #endif |
| |
| /* |
| * Default global CMA area size can be defined in kernel's .config. |
| * This is usefull mainly for distro maintainers to create a kernel |
| * that works correctly for most supported systems. |
| * The size can be set in bytes or as a percentage of the total memory |
| * in the system. |
| * |
| * Users, who want to set the size of global CMA area for their system |
| * should use cma= kernel parameter. |
| */ |
| static const phys_addr_t size_bytes = CMA_SIZE_MBYTES * SZ_1M; |
| static phys_addr_t size_cmdline = -1; |
| |
| static int __init early_cma(char *p) |
| { |
| pr_debug("%s(%s)\n", __func__, p); |
| size_cmdline = memparse(p, &p); |
| return 0; |
| } |
| early_param("cma", early_cma); |
| |
| #ifdef CONFIG_CMA_SIZE_PERCENTAGE |
| |
| static phys_addr_t __init __maybe_unused cma_early_percent_memory(void) |
| { |
| struct memblock_region *reg; |
| unsigned long total_pages = 0; |
| |
| /* |
| * We cannot use memblock_phys_mem_size() here, because |
| * memblock_analyze() has not been called yet. |
| */ |
| for_each_memblock(memory, reg) |
| total_pages += memblock_region_memory_end_pfn(reg) - |
| memblock_region_memory_base_pfn(reg); |
| |
| return (total_pages * CONFIG_CMA_SIZE_PERCENTAGE / 100) << PAGE_SHIFT; |
| } |
| |
| #else |
| |
| static inline __maybe_unused phys_addr_t cma_early_percent_memory(void) |
| { |
| return 0; |
| } |
| |
| #endif |
| |
| /** |
| * dma_contiguous_reserve() - reserve area for contiguous memory handling |
| * @limit: End address of the reserved memory (optional, 0 for any). |
| * |
| * This function reserves memory from early allocator. It should be |
| * called by arch specific code once the early allocator (memblock or bootmem) |
| * has been activated and all other subsystems have already allocated/reserved |
| * memory. |
| */ |
| void __init dma_contiguous_reserve(phys_addr_t limit) |
| { |
| phys_addr_t selected_size = 0; |
| |
| pr_debug("%s(limit %08lx)\n", __func__, (unsigned long)limit); |
| |
| if (size_cmdline != -1) { |
| selected_size = size_cmdline; |
| } else { |
| #ifdef CONFIG_CMA_SIZE_SEL_MBYTES |
| selected_size = size_bytes; |
| #elif defined(CONFIG_CMA_SIZE_SEL_PERCENTAGE) |
| selected_size = cma_early_percent_memory(); |
| #elif defined(CONFIG_CMA_SIZE_SEL_MIN) |
| selected_size = min(size_bytes, cma_early_percent_memory()); |
| #elif defined(CONFIG_CMA_SIZE_SEL_MAX) |
| selected_size = max(size_bytes, cma_early_percent_memory()); |
| #endif |
| } |
| |
| if (selected_size) { |
| pr_debug("%s: reserving %ld MiB for global area\n", __func__, |
| (unsigned long)selected_size / SZ_1M); |
| |
| dma_declare_contiguous(NULL, selected_size, 0, limit); |
| } |
| }; |
| |
| static DEFINE_MUTEX(cma_mutex); |
| |
| static __init int cma_activate_area(unsigned long base_pfn, unsigned long count) |
| { |
| unsigned long pfn = base_pfn; |
| unsigned i = count >> pageblock_order; |
| struct zone *zone; |
| |
| WARN_ON_ONCE(!pfn_valid(pfn)); |
| zone = page_zone(pfn_to_page(pfn)); |
| |
| do { |
| unsigned j; |
| base_pfn = pfn; |
| for (j = pageblock_nr_pages; j; --j, pfn++) { |
| WARN_ON_ONCE(!pfn_valid(pfn)); |
| if (page_zone(pfn_to_page(pfn)) != zone) |
| return -EINVAL; |
| } |
| init_cma_reserved_pageblock(pfn_to_page(base_pfn)); |
| } while (--i); |
| return 0; |
| } |
| |
| static __init struct cma *cma_create_area(unsigned long base_pfn, |
| unsigned long count) |
| { |
| int bitmap_size = BITS_TO_LONGS(count) * sizeof(long); |
| struct cma *cma; |
| int ret = -ENOMEM; |
| |
| pr_debug("%s(base %08lx, count %lx)\n", __func__, base_pfn, count); |
| |
| cma = kmalloc(sizeof *cma, GFP_KERNEL); |
| if (!cma) |
| return ERR_PTR(-ENOMEM); |
| |
| cma->base_pfn = base_pfn; |
| cma->count = count; |
| cma->bitmap = kzalloc(bitmap_size, GFP_KERNEL); |
| |
| if (!cma->bitmap) |
| goto no_mem; |
| |
| ret = cma_activate_area(base_pfn, count); |
| if (ret) |
| goto error; |
| |
| pr_debug("%s: returned %p\n", __func__, (void *)cma); |
| return cma; |
| |
| error: |
| kfree(cma->bitmap); |
| no_mem: |
| kfree(cma); |
| return ERR_PTR(ret); |
| } |
| |
| static struct cma_reserved { |
| phys_addr_t start; |
| unsigned long size; |
| struct device *dev; |
| } cma_reserved[MAX_CMA_AREAS] __initdata; |
| static unsigned cma_reserved_count __initdata; |
| static unsigned long cma_total_pages; |
| |
| static int __init cma_init_reserved_areas(void) |
| { |
| struct cma_reserved *r = cma_reserved; |
| unsigned i = cma_reserved_count; |
| |
| pr_debug("%s()\n", __func__); |
| |
| for (; i; --i, ++r) { |
| struct cma *cma; |
| cma = cma_create_area(PFN_DOWN(r->start), |
| r->size >> PAGE_SHIFT); |
| if (!IS_ERR(cma)) |
| dev_set_cma_area(r->dev, cma); |
| } |
| return 0; |
| } |
| core_initcall(cma_init_reserved_areas); |
| |
| /** |
| * dma_declare_contiguous() - reserve area for contiguous memory handling |
| * for particular device |
| * @dev: Pointer to device structure. |
| * @size: Size of the reserved memory. |
| * @base: Start address of the reserved memory (optional, 0 for any). |
| * @limit: End address of the reserved memory (optional, 0 for any). |
| * |
| * This function reserves memory for specified device. It should be |
| * called by board specific code when early allocator (memblock or bootmem) |
| * is still activate. |
| */ |
| int __init dma_declare_contiguous(struct device *dev, phys_addr_t size, |
| phys_addr_t base, phys_addr_t limit) |
| { |
| struct cma_reserved *r = &cma_reserved[cma_reserved_count]; |
| phys_addr_t alignment; |
| |
| pr_debug("%s(size %lx, base %08lx, limit %08lx)\n", __func__, |
| (unsigned long)size, (unsigned long)base, |
| (unsigned long)limit); |
| |
| /* Sanity checks */ |
| if (cma_reserved_count == ARRAY_SIZE(cma_reserved)) { |
| pr_err("Not enough slots for CMA reserved regions!\n"); |
| return -ENOSPC; |
| } |
| |
| if (!size) |
| return -EINVAL; |
| |
| /* Sanitise input arguments */ |
| alignment = PAGE_SIZE << max(MAX_ORDER - 1, pageblock_order); |
| base = ALIGN(base, alignment); |
| size = ALIGN(size, alignment); |
| limit &= ~(alignment - 1); |
| |
| /* Reserve memory */ |
| if (base) { |
| if (memblock_is_region_reserved(base, size) || |
| memblock_reserve(base, size) < 0) { |
| base = -EBUSY; |
| goto err; |
| } |
| } else { |
| /* |
| * Use __memblock_alloc_base() since |
| * memblock_alloc_base() panic()s. |
| */ |
| phys_addr_t addr = __memblock_alloc_base(size, alignment, limit); |
| if (!addr) { |
| base = -ENOMEM; |
| goto err; |
| } else { |
| base = addr; |
| } |
| } |
| |
| /* |
| * Each reserved area must be initialised later, when more kernel |
| * subsystems (like slab allocator) are available. |
| */ |
| r->start = base; |
| r->size = size; |
| r->dev = dev; |
| cma_reserved_count++; |
| cma_total_pages += ((unsigned long)size / PAGE_SIZE); |
| pr_info("CMA: reserved %ld MiB at %08lx\n", (unsigned long)size / SZ_1M, |
| (unsigned long)base); |
| |
| /* Architecture specific contiguous memory fixup. */ |
| dma_contiguous_early_fixup(base, size); |
| return 0; |
| err: |
| pr_err("CMA: failed to reserve %ld MiB\n", (unsigned long)size / SZ_1M); |
| return base; |
| } |
| |
| unsigned long cma_get_total_pages(void) |
| { |
| return cma_total_pages; |
| } |
| |
| static int __dma_update_pte(pte_t *pte, pgtable_t token, unsigned long addr, |
| void *data) |
| { |
| struct page *page = virt_to_page(addr); |
| pgprot_t prot = *(pgprot_t *)data; |
| |
| set_pte(pte, mk_pte(page, prot)); |
| return 0; |
| } |
| |
| static void __dma_remap(struct page *page, size_t size, pgprot_t prot) |
| { |
| unsigned long start = (unsigned long) page_address(page); |
| unsigned end = start + size; |
| int err; |
| |
| err = apply_to_page_range(&init_mm, start, |
| size, __dma_update_pte, &prot); |
| if (err) |
| pr_err("***%s: error=%d, pfn=%lx\n", __func__, |
| err, page_to_pfn(page)); |
| dsb(); |
| flush_tlb_kernel_range(start, end); |
| } |
| |
| 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) { |
| memset(ptr, 0, size); |
| dmac_flush_range(ptr, ptr + size); |
| outer_flush_range(__pa(ptr), __pa(ptr) + size); |
| } |
| } |
| |
| struct page *dma_alloc_at_from_contiguous(struct device *dev, int count, |
| unsigned int align, phys_addr_t at_addr) |
| { |
| unsigned long mask, pfn, pageno, start = 0; |
| struct cma *cma = dev_get_cma_area(dev); |
| struct page *page = NULL; |
| int ret; |
| unsigned long start_pfn = __phys_to_pfn(at_addr); |
| |
| if (!cma || !cma->count) |
| return NULL; |
| |
| if (align > CONFIG_CMA_ALIGNMENT) |
| align = CONFIG_CMA_ALIGNMENT; |
| |
| pr_debug("%s(cma %p, count %d, align %d)\n", __func__, (void *)cma, |
| count, align); |
| |
| if (!count) |
| return NULL; |
| |
| mask = (1 << align) - 1; |
| |
| if (start_pfn && start_pfn < cma->base_pfn) |
| return NULL; |
| start = start_pfn ? start_pfn - cma->base_pfn : start; |
| |
| mutex_lock(&cma_mutex); |
| |
| for (;;) { |
| unsigned long timeout = jiffies + msecs_to_jiffies(8000); |
| |
| pageno = bitmap_find_next_zero_area(cma->bitmap, cma->count, |
| start, count, mask); |
| if (pageno >= cma->count || (start && start != pageno)) |
| break; |
| |
| pfn = cma->base_pfn + pageno; |
| retry: |
| ret = alloc_contig_range(pfn, pfn + count, MIGRATE_CMA); |
| if (ret == 0) { |
| bitmap_set(cma->bitmap, pageno, count); |
| page = pfn_to_page(pfn); |
| break; |
| } else if (start && time_before(jiffies, timeout)) { |
| cond_resched(); |
| invalidate_bh_lrus(); |
| goto retry; |
| } else if (ret != -EBUSY || start) { |
| break; |
| } |
| pr_debug("%s(): memory range at %p is busy, retrying\n", |
| __func__, pfn_to_page(pfn)); |
| /* try again with a bit different memory target */ |
| start = pageno + mask + 1; |
| } |
| |
| mutex_unlock(&cma_mutex); |
| pr_debug("%s(): returned %p\n", __func__, page); |
| if (page) { |
| __dma_remap(page, count << PAGE_SHIFT, |
| pgprot_dmacoherent(PAGE_KERNEL)); |
| __dma_clear_buffer(page, count << PAGE_SHIFT); |
| } |
| return page; |
| } |
| |
| /** |
| * dma_alloc_from_contiguous() - allocate pages from contiguous area |
| * @dev: Pointer to device for which the allocation is performed. |
| * @count: Requested number of pages. |
| * @align: Requested alignment of pages (in PAGE_SIZE order). |
| * |
| * This function allocates memory buffer for specified device. It uses |
| * device specific contiguous memory area if available or the default |
| * global one. Requires architecture specific get_dev_cma_area() helper |
| * function. |
| */ |
| struct page *dma_alloc_from_contiguous(struct device *dev, int count, |
| unsigned int align) |
| { |
| return dma_alloc_at_from_contiguous(dev, count, align, 0); |
| } |
| |
| /** |
| * dma_release_from_contiguous() - release allocated pages |
| * @dev: Pointer to device for which the pages were allocated. |
| * @pages: Allocated pages. |
| * @count: Number of allocated pages. |
| * |
| * This function releases memory allocated by dma_alloc_from_contiguous(). |
| * It returns false when provided pages do not belong to contiguous area and |
| * true otherwise. |
| */ |
| bool dma_release_from_contiguous(struct device *dev, struct page *pages, |
| int count) |
| { |
| struct cma *cma = dev_get_cma_area(dev); |
| unsigned long pfn; |
| |
| if (!cma || !pages) |
| return false; |
| |
| pr_debug("%s(page %p)\n", __func__, (void *)pages); |
| |
| pfn = page_to_pfn(pages); |
| |
| if (pfn < cma->base_pfn || pfn >= cma->base_pfn + cma->count) |
| return false; |
| |
| VM_BUG_ON(pfn + count > cma->base_pfn + cma->count); |
| |
| __dma_remap(pages, count << PAGE_SHIFT, PAGE_KERNEL_EXEC); |
| |
| mutex_lock(&cma_mutex); |
| bitmap_clear(cma->bitmap, pfn - cma->base_pfn, count); |
| free_contig_range(pfn, count); |
| mutex_unlock(&cma_mutex); |
| |
| return true; |
| } |
| |
| int dma_get_contiguous_stats(struct device *dev, |
| struct dma_contiguous_stats *stats) |
| { |
| struct cma *cma = NULL; |
| |
| if ((!dev) || !stats) |
| return -EINVAL; |
| |
| if (dev->cma_area) |
| cma = dev->cma_area; |
| |
| if (!cma) |
| return -EINVAL; |
| |
| stats->size = (cma->count) << PAGE_SHIFT; |
| stats->base = (cma->base_pfn) << PAGE_SHIFT; |
| |
| return 0; |
| } |
| |
| #define MAX_REPLACE_DEV 16 |
| static struct device *replace_dev_list[MAX_REPLACE_DEV]; |
| static atomic_t replace_dev_count; |
| |
| bool dma_contiguous_should_replace_page(struct page *page) |
| { |
| int i; |
| ulong pfn; |
| struct cma *cma; |
| struct device *dev; |
| int count = atomic_read(&replace_dev_count); |
| |
| if (!page) |
| return false; |
| pfn = page_to_pfn(page); |
| |
| for (i = 0; i < count; i++) { |
| dev = replace_dev_list[i]; |
| if (!dev) |
| continue; |
| cma = dev->cma_area; |
| if (!cma) |
| continue; |
| if (pfn >= cma->base_pfn && |
| pfn < cma->base_pfn + cma->count) |
| return true; |
| } |
| |
| return false; |
| } |
| |
| /* Enable replacing pages during get_user_pages. |
| * any ref count on CMA page from get_user_pages |
| * makes the page not migratable and can cause |
| * CMA allocation failure. Enabling replace |
| * would force replacing the CMA pages with non-CMA |
| * pages during get_user_pages |
| */ |
| int dma_contiguous_enable_replace_pages(struct device *dev) |
| { |
| int idx; |
| struct cma *cma; |
| |
| if (!dev) |
| return -EINVAL; |
| |
| idx = atomic_inc_return(&replace_dev_count); |
| if (idx > MAX_REPLACE_DEV) |
| return -EINVAL; |
| replace_dev_list[idx - 1] = dev; |
| cma = dev->cma_area; |
| if (cma) { |
| pr_info("enabled page replacement for spfn=%lx, epfn=%lx\n", |
| cma->base_pfn, cma->base_pfn + cma->count); |
| } |
| return 0; |
| } |