From a254129e8686bff7a340b58f35241b04927e81c0 Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Wed, 6 Aug 2014 16:05:25 -0700 Subject: CMA: generalize CMA reserved area management functionality Currently, there are two users on CMA functionality, one is the DMA subsystem and the other is the KVM on powerpc. They have their own code to manage CMA reserved area even if they looks really similar. From my guess, it is caused by some needs on bitmap management. KVM side wants to maintain bitmap not for 1 page, but for more size. Eventually it use bitmap where one bit represents 64 pages. When I implement CMA related patches, I should change those two places to apply my change and it seem to be painful to me. I want to change this situation and reduce future code management overhead through this patch. This change could also help developer who want to use CMA in their new feature development, since they can use CMA easily without copying & pasting this reserved area management code. In previous patches, we have prepared some features to generalize CMA reserved area management and now it's time to do it. This patch moves core functions to mm/cma.c and change DMA APIs to use these functions. There is no functional change in DMA APIs. Signed-off-by: Joonsoo Kim Acked-by: Michal Nazarewicz Acked-by: Zhang Yanfei Acked-by: Minchan Kim Reviewed-by: Aneesh Kumar K.V Cc: Alexander Graf Cc: Aneesh Kumar K.V Cc: Gleb Natapov Acked-by: Marek Szyprowski Tested-by: Marek Szyprowski Cc: Paolo Bonzini Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/cma.c | 333 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 333 insertions(+) create mode 100644 mm/cma.c (limited to 'mm/cma.c') diff --git a/mm/cma.c b/mm/cma.c new file mode 100644 index 00000000000000..6560042169530c --- /dev/null +++ b/mm/cma.c @@ -0,0 +1,333 @@ +/* + * Contiguous Memory Allocator + * + * Copyright (c) 2010-2011 by Samsung Electronics. + * Copyright IBM Corporation, 2013 + * Copyright LG Electronics Inc., 2014 + * Written by: + * Marek Szyprowski + * Michal Nazarewicz + * Aneesh Kumar K.V + * Joonsoo Kim + * + * 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 +#include +#include +#include +#include +#include +#include +#include + +struct cma { + unsigned long base_pfn; + unsigned long count; + unsigned long *bitmap; + unsigned int order_per_bit; /* Order of pages represented by one bit */ + struct mutex lock; +}; + +static struct cma cma_areas[MAX_CMA_AREAS]; +static unsigned cma_area_count; +static DEFINE_MUTEX(cma_mutex); + +phys_addr_t cma_get_base(struct cma *cma) +{ + return PFN_PHYS(cma->base_pfn); +} + +unsigned long cma_get_size(struct cma *cma) +{ + return cma->count << PAGE_SHIFT; +} + +static unsigned long cma_bitmap_aligned_mask(struct cma *cma, int align_order) +{ + return (1UL << (align_order >> cma->order_per_bit)) - 1; +} + +static unsigned long cma_bitmap_maxno(struct cma *cma) +{ + return cma->count >> cma->order_per_bit; +} + +static unsigned long cma_bitmap_pages_to_bits(struct cma *cma, + unsigned long pages) +{ + return ALIGN(pages, 1UL << cma->order_per_bit) >> cma->order_per_bit; +} + +static void cma_clear_bitmap(struct cma *cma, unsigned long pfn, int count) +{ + unsigned long bitmap_no, bitmap_count; + + bitmap_no = (pfn - cma->base_pfn) >> cma->order_per_bit; + bitmap_count = cma_bitmap_pages_to_bits(cma, count); + + mutex_lock(&cma->lock); + bitmap_clear(cma->bitmap, bitmap_no, bitmap_count); + mutex_unlock(&cma->lock); +} + +static int __init cma_activate_area(struct cma *cma) +{ + int bitmap_size = BITS_TO_LONGS(cma_bitmap_maxno(cma)) * sizeof(long); + unsigned long base_pfn = cma->base_pfn, pfn = base_pfn; + unsigned i = cma->count >> pageblock_order; + struct zone *zone; + + cma->bitmap = kzalloc(bitmap_size, GFP_KERNEL); + + if (!cma->bitmap) + return -ENOMEM; + + 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)); + /* + * alloc_contig_range requires the pfn range + * specified to be in the same zone. Make this + * simple by forcing the entire CMA resv range + * to be in the same zone. + */ + if (page_zone(pfn_to_page(pfn)) != zone) + goto err; + } + init_cma_reserved_pageblock(pfn_to_page(base_pfn)); + } while (--i); + + mutex_init(&cma->lock); + return 0; + +err: + kfree(cma->bitmap); + return -EINVAL; +} + +static int __init cma_init_reserved_areas(void) +{ + int i; + + for (i = 0; i < cma_area_count; i++) { + int ret = cma_activate_area(&cma_areas[i]); + + if (ret) + return ret; + } + + return 0; +} +core_initcall(cma_init_reserved_areas); + +/** + * cma_declare_contiguous() - reserve custom contiguous area + * @size: Size of the reserved area (in bytes), + * @base: Base address of the reserved area optional, use 0 for any + * @limit: End address of the reserved memory (optional, 0 for any). + * @alignment: Alignment for the CMA area, should be power of 2 or zero + * @order_per_bit: Order of pages represented by one bit on bitmap. + * @res_cma: Pointer to store the created cma region. + * @fixed: hint about where to place the reserved area + * + * 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. This function allows to create custom reserved areas. + * + * If @fixed is true, reserve contiguous area at exactly @base. If false, + * reserve in range from @base to @limit. + */ +int __init cma_declare_contiguous(phys_addr_t size, + phys_addr_t base, phys_addr_t limit, + phys_addr_t alignment, unsigned int order_per_bit, + struct cma **res_cma, bool fixed) +{ + struct cma *cma = &cma_areas[cma_area_count]; + int ret = 0; + + pr_debug("%s(size %lx, base %08lx, limit %08lx alignment %08lx)\n", + __func__, (unsigned long)size, (unsigned long)base, + (unsigned long)limit, (unsigned long)alignment); + + if (cma_area_count == ARRAY_SIZE(cma_areas)) { + pr_err("Not enough slots for CMA reserved regions!\n"); + return -ENOSPC; + } + + if (!size) + return -EINVAL; + + if (alignment && !is_power_of_2(alignment)) + return -EINVAL; + + /* + * Sanitise input arguments. + * Pages both ends in CMA area could be merged into adjacent unmovable + * migratetype page by page allocator's buddy algorithm. In the case, + * you couldn't get a contiguous memory, which is not what we want. + */ + alignment = max(alignment, + (phys_addr_t)PAGE_SIZE << max(MAX_ORDER - 1, pageblock_order)); + base = ALIGN(base, alignment); + size = ALIGN(size, alignment); + limit &= ~(alignment - 1); + + /* size should be aligned with order_per_bit */ + if (!IS_ALIGNED(size >> PAGE_SHIFT, 1 << order_per_bit)) + return -EINVAL; + + /* Reserve memory */ + if (base && fixed) { + if (memblock_is_region_reserved(base, size) || + memblock_reserve(base, size) < 0) { + ret = -EBUSY; + goto err; + } + } else { + phys_addr_t addr = memblock_alloc_range(size, alignment, base, + limit); + if (!addr) { + ret = -ENOMEM; + goto err; + } else { + base = addr; + } + } + + /* + * Each reserved area must be initialised later, when more kernel + * subsystems (like slab allocator) are available. + */ + cma->base_pfn = PFN_DOWN(base); + cma->count = size >> PAGE_SHIFT; + cma->order_per_bit = order_per_bit; + *res_cma = cma; + cma_area_count++; + + pr_info("CMA: reserved %ld MiB at %08lx\n", (unsigned long)size / SZ_1M, + (unsigned long)base); + return 0; + +err: + pr_err("CMA: failed to reserve %ld MiB\n", (unsigned long)size / SZ_1M); + return ret; +} + +/** + * cma_alloc() - allocate pages from contiguous area + * @cma: Contiguous memory region for which the allocation is performed. + * @count: Requested number of pages. + * @align: Requested alignment of pages (in PAGE_SIZE order). + * + * This function allocates part of contiguous memory on specific + * contiguous memory area. + */ +struct page *cma_alloc(struct cma *cma, int count, unsigned int align) +{ + unsigned long mask, pfn, start = 0; + unsigned long bitmap_maxno, bitmap_no, bitmap_count; + struct page *page = NULL; + int ret; + + if (!cma || !cma->count) + return NULL; + + pr_debug("%s(cma %p, count %d, align %d)\n", __func__, (void *)cma, + count, align); + + if (!count) + return NULL; + + mask = cma_bitmap_aligned_mask(cma, align); + bitmap_maxno = cma_bitmap_maxno(cma); + bitmap_count = cma_bitmap_pages_to_bits(cma, count); + + for (;;) { + mutex_lock(&cma->lock); + bitmap_no = bitmap_find_next_zero_area(cma->bitmap, + bitmap_maxno, start, bitmap_count, mask); + if (bitmap_no >= bitmap_maxno) { + mutex_unlock(&cma->lock); + break; + } + bitmap_set(cma->bitmap, bitmap_no, bitmap_count); + /* + * It's safe to drop the lock here. We've marked this region for + * our exclusive use. If the migration fails we will take the + * lock again and unmark it. + */ + mutex_unlock(&cma->lock); + + pfn = cma->base_pfn + (bitmap_no << cma->order_per_bit); + mutex_lock(&cma_mutex); + ret = alloc_contig_range(pfn, pfn + count, MIGRATE_CMA); + mutex_unlock(&cma_mutex); + if (ret == 0) { + page = pfn_to_page(pfn); + break; + } else if (ret != -EBUSY) { + cma_clear_bitmap(cma, pfn, count); + break; + } + cma_clear_bitmap(cma, pfn, count); + 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 = bitmap_no + mask + 1; + } + + pr_debug("%s(): returned %p\n", __func__, page); + return page; +} + +/** + * cma_release() - release allocated pages + * @cma: Contiguous memory region for which the allocation is performed. + * @pages: Allocated pages. + * @count: Number of allocated pages. + * + * This function releases memory allocated by alloc_cma(). + * It returns false when provided pages do not belong to contiguous area and + * true otherwise. + */ +bool cma_release(struct cma *cma, struct page *pages, int count) +{ + 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); + + free_contig_range(pfn, count); + cma_clear_bitmap(cma, pfn, count); + + return true; +} -- cgit 1.2.3-korg From b7155e76a702d97553660828347b9f10858b4dd5 Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Wed, 6 Aug 2014 16:05:30 -0700 Subject: mm, CMA: clean-up CMA allocation error path We can remove one call sites for clear_cma_bitmap() if we first call it before checking error number. Signed-off-by: Joonsoo Kim Acked-by: Minchan Kim Reviewed-by: Michal Nazarewicz Reviewed-by: Zhang Yanfei Reviewed-by: Aneesh Kumar K.V Cc: Alexander Graf Cc: Aneesh Kumar K.V Cc: Gleb Natapov Acked-by: Marek Szyprowski Tested-by: Marek Szyprowski Cc: Paolo Bonzini Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/cma.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'mm/cma.c') diff --git a/mm/cma.c b/mm/cma.c index 6560042169530c..103a6663b7c730 100644 --- a/mm/cma.c +++ b/mm/cma.c @@ -285,11 +285,12 @@ struct page *cma_alloc(struct cma *cma, int count, unsigned int align) if (ret == 0) { page = pfn_to_page(pfn); break; - } else if (ret != -EBUSY) { - cma_clear_bitmap(cma, pfn, count); - break; } + cma_clear_bitmap(cma, pfn, count); + if (ret != -EBUSY) + 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 */ -- cgit 1.2.3-korg From c1f733aaaf30a0068a3126d5aa9d5b4c25ba4c0c Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Wed, 6 Aug 2014 16:05:32 -0700 Subject: mm, CMA: change cma_declare_contiguous() to obey coding convention Conventionally, we put output param to the end of param list and put the 'base' ahead of 'size', but cma_declare_contiguous() doesn't look like that, so change it. Additionally, move down cma_areas reference code to the position where it is really needed. Signed-off-by: Joonsoo Kim Acked-by: Michal Nazarewicz Reviewed-by: Aneesh Kumar K.V Cc: Alexander Graf Cc: Aneesh Kumar K.V Cc: Gleb Natapov Acked-by: Marek Szyprowski Tested-by: Marek Szyprowski Cc: Minchan Kim Cc: Paolo Bonzini Cc: Zhang Yanfei Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/powerpc/kvm/book3s_hv_builtin.c | 4 ++-- drivers/base/dma-contiguous.c | 2 +- include/linux/cma.h | 2 +- mm/cma.c | 13 +++++++------ 4 files changed, 11 insertions(+), 10 deletions(-) (limited to 'mm/cma.c') diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c index 3960e0bceaf259..6cf498a9bc987d 100644 --- a/arch/powerpc/kvm/book3s_hv_builtin.c +++ b/arch/powerpc/kvm/book3s_hv_builtin.c @@ -185,8 +185,8 @@ void __init kvm_cma_reserve(void) align_size = HPT_ALIGN_PAGES << PAGE_SHIFT; align_size = max(kvm_rma_pages << PAGE_SHIFT, align_size); - cma_declare_contiguous(selected_size, 0, 0, align_size, - KVM_CMA_CHUNK_ORDER - PAGE_SHIFT, &kvm_cma, false); + cma_declare_contiguous(0, selected_size, 0, align_size, + KVM_CMA_CHUNK_ORDER - PAGE_SHIFT, false, &kvm_cma); } } diff --git a/drivers/base/dma-contiguous.c b/drivers/base/dma-contiguous.c index 0411c1c57005cc..6606abdf880c81 100644 --- a/drivers/base/dma-contiguous.c +++ b/drivers/base/dma-contiguous.c @@ -165,7 +165,7 @@ int __init dma_contiguous_reserve_area(phys_addr_t size, phys_addr_t base, { int ret; - ret = cma_declare_contiguous(size, base, limit, 0, 0, res_cma, fixed); + ret = cma_declare_contiguous(base, size, limit, 0, 0, fixed, res_cma); if (ret) return ret; diff --git a/include/linux/cma.h b/include/linux/cma.h index f6f7809acb98cf..371b9304252052 100644 --- a/include/linux/cma.h +++ b/include/linux/cma.h @@ -21,7 +21,7 @@ extern unsigned long cma_get_size(struct cma *cma); extern int __init cma_declare_contiguous(phys_addr_t size, phys_addr_t base, phys_addr_t limit, phys_addr_t alignment, unsigned int order_per_bit, - struct cma **res_cma, bool fixed); + bool fixed, struct cma **res_cma); extern struct page *cma_alloc(struct cma *cma, int count, unsigned int align); extern bool cma_release(struct cma *cma, struct page *pages, int count); #endif diff --git a/mm/cma.c b/mm/cma.c index 103a6663b7c730..488e50810ed187 100644 --- a/mm/cma.c +++ b/mm/cma.c @@ -141,13 +141,13 @@ core_initcall(cma_init_reserved_areas); /** * cma_declare_contiguous() - reserve custom contiguous area - * @size: Size of the reserved area (in bytes), * @base: Base address of the reserved area optional, use 0 for any + * @size: Size of the reserved area (in bytes), * @limit: End address of the reserved memory (optional, 0 for any). * @alignment: Alignment for the CMA area, should be power of 2 or zero * @order_per_bit: Order of pages represented by one bit on bitmap. - * @res_cma: Pointer to store the created cma region. * @fixed: hint about where to place the reserved area + * @res_cma: Pointer to store the created cma region. * * This function reserves memory from early allocator. It should be * called by arch specific code once the early allocator (memblock or bootmem) @@ -157,12 +157,12 @@ core_initcall(cma_init_reserved_areas); * If @fixed is true, reserve contiguous area at exactly @base. If false, * reserve in range from @base to @limit. */ -int __init cma_declare_contiguous(phys_addr_t size, - phys_addr_t base, phys_addr_t limit, +int __init cma_declare_contiguous(phys_addr_t base, + phys_addr_t size, phys_addr_t limit, phys_addr_t alignment, unsigned int order_per_bit, - struct cma **res_cma, bool fixed) + bool fixed, struct cma **res_cma) { - struct cma *cma = &cma_areas[cma_area_count]; + struct cma *cma; int ret = 0; pr_debug("%s(size %lx, base %08lx, limit %08lx alignment %08lx)\n", @@ -218,6 +218,7 @@ int __init cma_declare_contiguous(phys_addr_t size, * Each reserved area must be initialised later, when more kernel * subsystems (like slab allocator) are available. */ + cma = &cma_areas[cma_area_count]; cma->base_pfn = PFN_DOWN(base); cma->count = size >> PAGE_SHIFT; cma->order_per_bit = order_per_bit; -- cgit 1.2.3-korg From 0de9d2ebe590f9203dac59d4b8e298c473764b92 Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Wed, 6 Aug 2014 16:05:34 -0700 Subject: mm, CMA: clean-up log message We don't need explicit 'CMA:' prefix, since we already define prefix 'cma:' in pr_fmt. So remove it. Signed-off-by: Joonsoo Kim Acked-by: Michal Nazarewicz Reviewed-by: Zhang Yanfei Cc: "Aneesh Kumar K.V" Cc: Alexander Graf Cc: Aneesh Kumar K.V Cc: Gleb Natapov Acked-by: Marek Szyprowski Tested-by: Marek Szyprowski Cc: Minchan Kim Cc: Paolo Bonzini Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/cma.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'mm/cma.c') diff --git a/mm/cma.c b/mm/cma.c index 488e50810ed187..c17751c0dcafb9 100644 --- a/mm/cma.c +++ b/mm/cma.c @@ -225,12 +225,12 @@ int __init cma_declare_contiguous(phys_addr_t base, *res_cma = cma; cma_area_count++; - pr_info("CMA: reserved %ld MiB at %08lx\n", (unsigned long)size / SZ_1M, + pr_info("Reserved %ld MiB at %08lx\n", (unsigned long)size / SZ_1M, (unsigned long)base); return 0; err: - pr_err("CMA: failed to reserve %ld MiB\n", (unsigned long)size / SZ_1M); + pr_err("Failed to reserve %ld MiB\n", (unsigned long)size / SZ_1M); return ret; } -- cgit 1.2.3-korg From f7426b983a6a353cf21e5733e84458219c4a817e Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Thu, 9 Oct 2014 15:26:47 -0700 Subject: mm: cma: adjust address limit to avoid hitting low/high memory boundary Russell King recently noticed that limiting default CMA region only to low memory on ARM architecture causes serious memory management issues with machines having a lot of memory (which is mainly available as high memory). More information can be found the following thread: http://thread.gmane.org/gmane.linux.ports.arm.kernel/348441/ Those two patches removes this limit letting kernel to put default CMA region into high memory when this is possible (there is enough high memory available and architecture specific DMA limit fits). This should solve strange OOM issues on systems with lots of RAM (i.e. >1GiB) and large (>256M) CMA area. This patch (of 2): Automatically allocated regions should not cross low/high memory boundary, because such regions cannot be later correctly initialized due to spanning across two memory zones. This patch adds a check for this case and a simple code for moving region to low memory if automatically selected address might not fit completely into high memory. Signed-off-by: Marek Szyprowski Acked-by: Michal Nazarewicz Cc: Daniel Drake Cc: Minchan Kim Cc: Russell King Cc: Joonsoo Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/cma.c | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'mm/cma.c') diff --git a/mm/cma.c b/mm/cma.c index c17751c0dcafb9..474c644a0dc6de 100644 --- a/mm/cma.c +++ b/mm/cma.c @@ -32,6 +32,7 @@ #include #include #include +#include struct cma { unsigned long base_pfn; @@ -163,6 +164,8 @@ int __init cma_declare_contiguous(phys_addr_t base, bool fixed, struct cma **res_cma) { struct cma *cma; + phys_addr_t memblock_end = memblock_end_of_DRAM(); + phys_addr_t highmem_start = __pa(high_memory); int ret = 0; pr_debug("%s(size %lx, base %08lx, limit %08lx alignment %08lx)\n", @@ -196,6 +199,24 @@ int __init cma_declare_contiguous(phys_addr_t base, if (!IS_ALIGNED(size >> PAGE_SHIFT, 1 << order_per_bit)) return -EINVAL; + /* + * adjust limit to avoid crossing low/high memory boundary for + * automatically allocated regions + */ + if (((limit == 0 || limit > memblock_end) && + (memblock_end - size < highmem_start && + memblock_end > highmem_start)) || + (!fixed && limit > highmem_start && limit - size < highmem_start)) { + limit = highmem_start; + } + + if (fixed && base < highmem_start && base+size > highmem_start) { + ret = -EINVAL; + pr_err("Region at %08lx defined on low/high memory boundary (%08lx)\n", + (unsigned long)base, (unsigned long)highmem_start); + goto err; + } + /* Reserve memory */ if (base && fixed) { if (memblock_is_region_reserved(base, size) || -- cgit 1.2.3-korg From 68faed630fc151a7a1c4853df00fb3dcacf782b4 Mon Sep 17 00:00:00 2001 From: Weijie Yang Date: Mon, 13 Oct 2014 15:51:03 -0700 Subject: mm/cma: fix cma bitmap aligned mask computing The current cma bitmap aligned mask computation is incorrect. It could cause an unexpected alignment when using cma_alloc() if the wanted align order is larger than cma->order_per_bit. Take kvm for example (PAGE_SHIFT = 12), kvm_cma->order_per_bit is set to 6. When kvm_alloc_rma() tries to alloc kvm_rma_pages, it will use 15 as the expected align value. After using the current implementation however, we get 0 as cma bitmap aligned mask other than 511. This patch fixes the cma bitmap aligned mask calculation. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Weijie Yang Acked-by: Michal Nazarewicz Cc: Joonsoo Kim Cc: "Aneesh Kumar K.V" Cc: [3.17] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/cma.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'mm/cma.c') diff --git a/mm/cma.c b/mm/cma.c index 474c644a0dc6de..a951a3b3ed3677 100644 --- a/mm/cma.c +++ b/mm/cma.c @@ -58,7 +58,9 @@ unsigned long cma_get_size(struct cma *cma) static unsigned long cma_bitmap_aligned_mask(struct cma *cma, int align_order) { - return (1UL << (align_order >> cma->order_per_bit)) - 1; + if (align_order <= cma->order_per_bit) + return 0; + return (1UL << (align_order - cma->order_per_bit)) - 1; } static unsigned long cma_bitmap_maxno(struct cma *cma) -- cgit 1.2.3-korg From de9e14eebf33a60712a52a0bc6e08c043c0aba53 Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Mon, 13 Oct 2014 15:51:09 -0700 Subject: drivers: dma-contiguous: add initialization from device tree Add a function to create CMA region from previously reserved memory and add support for handling 'shared-dma-pool' reserved-memory device tree nodes. Based on previous code provided by Josh Cartwright Signed-off-by: Marek Szyprowski Cc: Arnd Bergmann Cc: Michal Nazarewicz Cc: Grant Likely Cc: Laura Abbott Cc: Josh Cartwright Cc: Joonsoo Kim Cc: Kyungmin Park Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/base/dma-contiguous.c | 66 +++++++++++++++++++++++++++++++++++++++++++ include/linux/cma.h | 3 ++ mm/cma.c | 62 ++++++++++++++++++++++++++++++++-------- 3 files changed, 120 insertions(+), 11 deletions(-) (limited to 'mm/cma.c') diff --git a/drivers/base/dma-contiguous.c b/drivers/base/dma-contiguous.c index 6606abdf880c81..473ff48924015f 100644 --- a/drivers/base/dma-contiguous.c +++ b/drivers/base/dma-contiguous.c @@ -211,3 +211,69 @@ bool dma_release_from_contiguous(struct device *dev, struct page *pages, { return cma_release(dev_get_cma_area(dev), pages, count); } + +/* + * Support for reserved memory regions defined in device tree + */ +#ifdef CONFIG_OF_RESERVED_MEM +#include +#include +#include + +#undef pr_fmt +#define pr_fmt(fmt) fmt + +static void rmem_cma_device_init(struct reserved_mem *rmem, struct device *dev) +{ + dev_set_cma_area(dev, rmem->priv); +} + +static void rmem_cma_device_release(struct reserved_mem *rmem, + struct device *dev) +{ + dev_set_cma_area(dev, NULL); +} + +static const struct reserved_mem_ops rmem_cma_ops = { + .device_init = rmem_cma_device_init, + .device_release = rmem_cma_device_release, +}; + +static int __init rmem_cma_setup(struct reserved_mem *rmem) +{ + phys_addr_t align = PAGE_SIZE << max(MAX_ORDER - 1, pageblock_order); + phys_addr_t mask = align - 1; + unsigned long node = rmem->fdt_node; + struct cma *cma; + int err; + + if (!of_get_flat_dt_prop(node, "reusable", NULL) || + of_get_flat_dt_prop(node, "no-map", NULL)) + return -EINVAL; + + if ((rmem->base & mask) || (rmem->size & mask)) { + pr_err("Reserved memory: incorrect alignment of CMA region\n"); + return -EINVAL; + } + + err = cma_init_reserved_mem(rmem->base, rmem->size, 0, &cma); + if (err) { + pr_err("Reserved memory: unable to setup CMA region\n"); + return err; + } + /* Architecture specific contiguous memory fixup. */ + dma_contiguous_early_fixup(rmem->base, rmem->size); + + if (of_get_flat_dt_prop(node, "linux,cma-default", NULL)) + dma_contiguous_set_default(cma); + + rmem->ops = &rmem_cma_ops; + rmem->priv = cma; + + pr_info("Reserved memory: created CMA memory pool at %pa, size %ld MiB\n", + &rmem->base, (unsigned long)rmem->size / SZ_1M); + + return 0; +} +RESERVEDMEM_OF_DECLARE(cma, "shared-dma-pool", rmem_cma_setup); +#endif diff --git a/include/linux/cma.h b/include/linux/cma.h index 371b9304252052..0430ed05d3b9f0 100644 --- a/include/linux/cma.h +++ b/include/linux/cma.h @@ -22,6 +22,9 @@ extern int __init cma_declare_contiguous(phys_addr_t size, phys_addr_t base, phys_addr_t limit, phys_addr_t alignment, unsigned int order_per_bit, bool fixed, struct cma **res_cma); +extern int cma_init_reserved_mem(phys_addr_t size, + phys_addr_t base, int order_per_bit, + struct cma **res_cma); extern struct page *cma_alloc(struct cma *cma, int count, unsigned int align); extern bool cma_release(struct cma *cma, struct page *pages, int count); #endif diff --git a/mm/cma.c b/mm/cma.c index a951a3b3ed3677..963bc4add9af88 100644 --- a/mm/cma.c +++ b/mm/cma.c @@ -142,6 +142,54 @@ static int __init cma_init_reserved_areas(void) } core_initcall(cma_init_reserved_areas); +/** + * cma_init_reserved_mem() - create custom contiguous area from reserved memory + * @base: Base address of the reserved area + * @size: Size of the reserved area (in bytes), + * @order_per_bit: Order of pages represented by one bit on bitmap. + * @res_cma: Pointer to store the created cma region. + * + * This function creates custom contiguous area from already reserved memory. + */ +int __init cma_init_reserved_mem(phys_addr_t base, phys_addr_t size, + int order_per_bit, struct cma **res_cma) +{ + struct cma *cma; + phys_addr_t alignment; + + /* Sanity checks */ + if (cma_area_count == ARRAY_SIZE(cma_areas)) { + pr_err("Not enough slots for CMA reserved regions!\n"); + return -ENOSPC; + } + + if (!size || !memblock_is_region_reserved(base, size)) + return -EINVAL; + + /* ensure minimal alignment requied by mm core */ + alignment = PAGE_SIZE << max(MAX_ORDER - 1, pageblock_order); + + /* alignment should be aligned with order_per_bit */ + if (!IS_ALIGNED(alignment >> PAGE_SHIFT, 1 << order_per_bit)) + return -EINVAL; + + if (ALIGN(base, alignment) != base || ALIGN(size, alignment) != size) + return -EINVAL; + + /* + * Each reserved area must be initialised later, when more kernel + * subsystems (like slab allocator) are available. + */ + cma = &cma_areas[cma_area_count]; + cma->base_pfn = PFN_DOWN(base); + cma->count = size >> PAGE_SHIFT; + cma->order_per_bit = order_per_bit; + *res_cma = cma; + cma_area_count++; + + return 0; +} + /** * cma_declare_contiguous() - reserve custom contiguous area * @base: Base address of the reserved area optional, use 0 for any @@ -165,7 +213,6 @@ int __init cma_declare_contiguous(phys_addr_t base, phys_addr_t alignment, unsigned int order_per_bit, bool fixed, struct cma **res_cma) { - struct cma *cma; phys_addr_t memblock_end = memblock_end_of_DRAM(); phys_addr_t highmem_start = __pa(high_memory); int ret = 0; @@ -237,16 +284,9 @@ int __init cma_declare_contiguous(phys_addr_t base, } } - /* - * Each reserved area must be initialised later, when more kernel - * subsystems (like slab allocator) are available. - */ - cma = &cma_areas[cma_area_count]; - cma->base_pfn = PFN_DOWN(base); - cma->count = size >> PAGE_SHIFT; - cma->order_per_bit = order_per_bit; - *res_cma = cma; - cma_area_count++; + ret = cma_init_reserved_mem(base, size, order_per_bit, res_cma); + if (ret) + goto err; pr_info("Reserved %ld MiB at %08lx\n", (unsigned long)size / SZ_1M, (unsigned long)base); -- cgit 1.2.3-korg From f022d8cb7ec70fe8edd56383d876001317ee76b1 Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Fri, 24 Oct 2014 13:18:39 +0300 Subject: mm: cma: Don't crash on allocation if CMA area can't be activated If activation of the CMA area fails its mutex won't be initialized, leading to an oops at allocation time when trying to lock the mutex. Fix this by setting the cma area count field to 0 when activation fails, leading to allocation returning NULL immediately. Cc: # v3.17 Signed-off-by: Laurent Pinchart Acked-by: Michal Nazarewicz Signed-off-by: Marek Szyprowski --- mm/cma.c | 1 + 1 file changed, 1 insertion(+) (limited to 'mm/cma.c') diff --git a/mm/cma.c b/mm/cma.c index 963bc4add9af88..5aa1a6f74decad 100644 --- a/mm/cma.c +++ b/mm/cma.c @@ -124,6 +124,7 @@ static int __init cma_activate_area(struct cma *cma) err: kfree(cma->bitmap); + cma->count = 0; return -EINVAL; } -- cgit 1.2.3-korg From 800a85d3d286604b8c539ca7ee90b992316fd2a7 Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Fri, 24 Oct 2014 13:18:40 +0300 Subject: mm: cma: Always consider a 0 base address reservation as dynamic The fixed parameter to cma_declare_contiguous() tells the function whether the given base address must be honoured or should be considered as a hint only. The API considers a zero base address as meaning any base address, which must never be considered as a fixed value. Part of the implementation correctly checks both fixed and base != 0, but two locations check the fixed value only. Set fixed to false when base is 0 to fix that and simplify the code. Signed-off-by: Laurent Pinchart Acked-by: Michal Nazarewicz Signed-off-by: Marek Szyprowski --- mm/cma.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'mm/cma.c') diff --git a/mm/cma.c b/mm/cma.c index 5aa1a6f74decad..62a5dccc3fb827 100644 --- a/mm/cma.c +++ b/mm/cma.c @@ -245,6 +245,9 @@ int __init cma_declare_contiguous(phys_addr_t base, size = ALIGN(size, alignment); limit &= ~(alignment - 1); + if (!base) + fixed = false; + /* size should be aligned with order_per_bit */ if (!IS_ALIGNED(size >> PAGE_SHIFT, 1 << order_per_bit)) return -EINVAL; @@ -268,7 +271,7 @@ int __init cma_declare_contiguous(phys_addr_t base, } /* Reserve memory */ - if (base && fixed) { + if (fixed) { if (memblock_is_region_reserved(base, size) || memblock_reserve(base, size) < 0) { ret = -EBUSY; -- cgit 1.2.3-korg From 16195ddd4ebcc10c30b2f232f8e400df8d464380 Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Fri, 24 Oct 2014 13:18:41 +0300 Subject: mm: cma: Ensure that reservations never cross the low/high mem boundary Commit 95b0e655f914 ("ARM: mm: don't limit default CMA region only to low memory") extended CMA memory reservation to allow usage of high memory. It relied on commit f7426b983a6a ("mm: cma: adjust address limit to avoid hitting low/high memory boundary") to ensure that the reserved block never crossed the low/high memory boundary. While the implementation correctly lowered the limit, it failed to consider the case where the base..limit range crossed the low/high memory boundary with enough space on each side to reserve the requested size on either low or high memory. Rework the base and limit adjustment to fix the problem. The function now starts by rejecting the reservation altogether for fixed reservations that cross the boundary, tries to reserve from high memory first and then falls back to low memory. Signed-off-by: Laurent Pinchart Signed-off-by: Marek Szyprowski --- mm/cma.c | 49 +++++++++++++++++++++++++++++++++---------------- 1 file changed, 33 insertions(+), 16 deletions(-) (limited to 'mm/cma.c') diff --git a/mm/cma.c b/mm/cma.c index 62a5dccc3fb827..c30a6edee65c30 100644 --- a/mm/cma.c +++ b/mm/cma.c @@ -253,23 +253,24 @@ int __init cma_declare_contiguous(phys_addr_t base, return -EINVAL; /* - * adjust limit to avoid crossing low/high memory boundary for - * automatically allocated regions + * If allocating at a fixed base the request region must not cross the + * low/high memory boundary. */ - if (((limit == 0 || limit > memblock_end) && - (memblock_end - size < highmem_start && - memblock_end > highmem_start)) || - (!fixed && limit > highmem_start && limit - size < highmem_start)) { - limit = highmem_start; - } - - if (fixed && base < highmem_start && base+size > highmem_start) { + if (fixed && base < highmem_start && base + size > highmem_start) { ret = -EINVAL; pr_err("Region at %08lx defined on low/high memory boundary (%08lx)\n", (unsigned long)base, (unsigned long)highmem_start); goto err; } + /* + * If the limit is unspecified or above the memblock end, its effective + * value will be the memblock end. Set it explicitly to simplify further + * checks. + */ + if (limit == 0 || limit > memblock_end) + limit = memblock_end; + /* Reserve memory */ if (fixed) { if (memblock_is_region_reserved(base, size) || @@ -278,14 +279,30 @@ int __init cma_declare_contiguous(phys_addr_t base, goto err; } } else { - phys_addr_t addr = memblock_alloc_range(size, alignment, base, - limit); + phys_addr_t addr = 0; + + /* + * All pages in the reserved area must come from the same zone. + * If the requested region crosses the low/high memory boundary, + * try allocating from high memory first and fall back to low + * memory in case of failure. + */ + if (base < highmem_start && limit > highmem_start) { + addr = memblock_alloc_range(size, alignment, + highmem_start, limit); + limit = highmem_start; + } + if (!addr) { - ret = -ENOMEM; - goto err; - } else { - base = addr; + addr = memblock_alloc_range(size, alignment, base, + limit); + if (!addr) { + ret = -ENOMEM; + goto err; + } } + + base = addr; } ret = cma_init_reserved_mem(base, size, order_per_bit, res_cma); -- cgit 1.2.3-korg From 56fa4f609badbe442093409c3d3a051811e54f72 Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Fri, 24 Oct 2014 13:18:42 +0300 Subject: mm: cma: Use %pa to print physical addresses Casting physical addresses to unsigned long and using %lu truncates the values on systems where physical addresses are larger than 32 bits. Use %pa and get rid of the cast instead. Signed-off-by: Laurent Pinchart Acked-by: Michal Nazarewicz Acked-by: Geert Uytterhoeven Signed-off-by: Marek Szyprowski --- mm/cma.c | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) (limited to 'mm/cma.c') diff --git a/mm/cma.c b/mm/cma.c index c30a6edee65c30..fde706e1284fbc 100644 --- a/mm/cma.c +++ b/mm/cma.c @@ -218,9 +218,8 @@ int __init cma_declare_contiguous(phys_addr_t base, phys_addr_t highmem_start = __pa(high_memory); int ret = 0; - pr_debug("%s(size %lx, base %08lx, limit %08lx alignment %08lx)\n", - __func__, (unsigned long)size, (unsigned long)base, - (unsigned long)limit, (unsigned long)alignment); + pr_debug("%s(size %pa, base %pa, limit %pa alignment %pa)\n", + __func__, &size, &base, &limit, &alignment); if (cma_area_count == ARRAY_SIZE(cma_areas)) { pr_err("Not enough slots for CMA reserved regions!\n"); @@ -258,8 +257,8 @@ int __init cma_declare_contiguous(phys_addr_t base, */ if (fixed && base < highmem_start && base + size > highmem_start) { ret = -EINVAL; - pr_err("Region at %08lx defined on low/high memory boundary (%08lx)\n", - (unsigned long)base, (unsigned long)highmem_start); + pr_err("Region at %pa defined on low/high memory boundary (%pa)\n", + &base, &highmem_start); goto err; } @@ -309,8 +308,8 @@ int __init cma_declare_contiguous(phys_addr_t base, if (ret) goto err; - pr_info("Reserved %ld MiB at %08lx\n", (unsigned long)size / SZ_1M, - (unsigned long)base); + pr_info("Reserved %ld MiB at %pa\n", (unsigned long)size / SZ_1M, + &base); return 0; err: -- cgit 1.2.3-korg