diff options
Diffstat (limited to 'mm/dmapool.c')
| -rw-r--r-- | mm/dmapool.c | 533 |
1 files changed, 273 insertions, 260 deletions
diff --git a/mm/dmapool.c b/mm/dmapool.c index c69781e97cf9..5d8af6e29127 100644 --- a/mm/dmapool.c +++ b/mm/dmapool.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * DMA Pool allocator * @@ -5,10 +6,6 @@ * Copyright 2007 Intel Corporation * Author: Matthew Wilcox <willy@linux.intel.com> * - * This software may be redistributed and/or modified under the terms of - * the GNU General Public License ("GPL") version 2 as published by the - * Free Software Foundation. - * * This allocator returns small blocks of a given size which are DMA-able by * the given device. It uses the dma_alloc_coherent page allocator to get * new pages, then splits them up into blocks of the required size. @@ -18,7 +15,7 @@ * represented by the 'struct dma_pool' which keeps a doubly-linked list of * allocated pages. Each page in the page_list is split into blocks of at * least 'size' bytes. Free blocks are tracked in an unsorted singly-linked - * list of free blocks within the page. Used blocks aren't tracked, but we + * list of free blocks across all pages. Used blocks aren't tracked, but we * keep a count of how many are currently allocated from each page. */ @@ -31,6 +28,7 @@ #include <linux/mutex.h> #include <linux/poison.h> #include <linux/sched.h> +#include <linux/sched/mm.h> #include <linux/slab.h> #include <linux/stat.h> #include <linux/spinlock.h> @@ -38,17 +36,27 @@ #include <linux/types.h> #include <linux/wait.h> -#if defined(CONFIG_DEBUG_SLAB) || defined(CONFIG_SLUB_DEBUG_ON) +#ifdef CONFIG_SLUB_DEBUG_ON #define DMAPOOL_DEBUG 1 #endif +struct dma_block { + struct dma_block *next_block; + dma_addr_t dma; +}; + struct dma_pool { /* the pool */ struct list_head page_list; spinlock_t lock; - size_t size; + struct dma_block *next_block; + size_t nr_blocks; + size_t nr_active; + size_t nr_pages; struct device *dev; - size_t allocation; - size_t boundary; + unsigned int size; + unsigned int allocation; + unsigned int boundary; + int node; char name[32]; struct list_head pools; }; @@ -57,67 +65,152 @@ struct dma_page { /* cacheable header for 'allocation' bytes */ struct list_head page_list; void *vaddr; dma_addr_t dma; - unsigned int in_use; - unsigned int offset; }; static DEFINE_MUTEX(pools_lock); +static DEFINE_MUTEX(pools_reg_lock); -static ssize_t -show_pools(struct device *dev, struct device_attribute *attr, char *buf) +static ssize_t pools_show(struct device *dev, struct device_attribute *attr, char *buf) { - unsigned temp; - unsigned size; - char *next; - struct dma_page *page; struct dma_pool *pool; + unsigned size; - next = buf; - size = PAGE_SIZE; - - temp = scnprintf(next, size, "poolinfo - 0.1\n"); - size -= temp; - next += temp; + size = sysfs_emit(buf, "poolinfo - 0.1\n"); mutex_lock(&pools_lock); list_for_each_entry(pool, &dev->dma_pools, pools) { - unsigned pages = 0; - unsigned blocks = 0; + /* per-pool info, no real statistics yet */ + size += sysfs_emit_at(buf, size, "%-16s %4zu %4zu %4u %2zu\n", + pool->name, pool->nr_active, + pool->nr_blocks, pool->size, + pool->nr_pages); + } + mutex_unlock(&pools_lock); + + return size; +} + +static DEVICE_ATTR_RO(pools); + +#ifdef DMAPOOL_DEBUG +static void pool_check_block(struct dma_pool *pool, struct dma_block *block, + gfp_t mem_flags) +{ + u8 *data = (void *)block; + int i; + + for (i = sizeof(struct dma_block); i < pool->size; i++) { + if (data[i] == POOL_POISON_FREED) + continue; + dev_err(pool->dev, "%s %s, %p (corrupted)\n", __func__, + pool->name, block); + + /* + * Dump the first 4 bytes even if they are not + * POOL_POISON_FREED + */ + print_hex_dump(KERN_ERR, "", DUMP_PREFIX_OFFSET, 16, 1, + data, pool->size, 1); + break; + } + + if (!want_init_on_alloc(mem_flags)) + memset(block, POOL_POISON_ALLOCATED, pool->size); +} + +static struct dma_page *pool_find_page(struct dma_pool *pool, dma_addr_t dma) +{ + struct dma_page *page; + + list_for_each_entry(page, &pool->page_list, page_list) { + if (dma < page->dma) + continue; + if ((dma - page->dma) < pool->allocation) + return page; + } + return NULL; +} + +static bool pool_block_err(struct dma_pool *pool, void *vaddr, dma_addr_t dma) +{ + struct dma_block *block = pool->next_block; + struct dma_page *page; + + page = pool_find_page(pool, dma); + if (!page) { + dev_err(pool->dev, "%s %s, %p/%pad (bad dma)\n", + __func__, pool->name, vaddr, &dma); + return true; + } - spin_lock_irq(&pool->lock); - list_for_each_entry(page, &pool->page_list, page_list) { - pages++; - blocks += page->in_use; + while (block) { + if (block != vaddr) { + block = block->next_block; + continue; } - spin_unlock_irq(&pool->lock); + dev_err(pool->dev, "%s %s, dma %pad already free\n", + __func__, pool->name, &dma); + return true; + } - /* per-pool info, no real statistics yet */ - temp = scnprintf(next, size, "%-16s %4u %4Zu %4Zu %2u\n", - pool->name, blocks, - pages * (pool->allocation / pool->size), - pool->size, pages); - size -= temp; - next += temp; + memset(vaddr, POOL_POISON_FREED, pool->size); + return false; +} + +static void pool_init_page(struct dma_pool *pool, struct dma_page *page) +{ + memset(page->vaddr, POOL_POISON_FREED, pool->allocation); +} +#else +static void pool_check_block(struct dma_pool *pool, struct dma_block *block, + gfp_t mem_flags) +{ +} + +static bool pool_block_err(struct dma_pool *pool, void *vaddr, dma_addr_t dma) +{ + if (want_init_on_free()) + memset(vaddr, 0, pool->size); + return false; +} + +static void pool_init_page(struct dma_pool *pool, struct dma_page *page) +{ +} +#endif + +static struct dma_block *pool_block_pop(struct dma_pool *pool) +{ + struct dma_block *block = pool->next_block; + + if (block) { + pool->next_block = block->next_block; + pool->nr_active++; } - mutex_unlock(&pools_lock); + return block; +} - return PAGE_SIZE - size; +static void pool_block_push(struct dma_pool *pool, struct dma_block *block, + dma_addr_t dma) +{ + block->dma = dma; + block->next_block = pool->next_block; + pool->next_block = block; } -static DEVICE_ATTR(pools, S_IRUGO, show_pools, NULL); /** - * dma_pool_create - Creates a pool of consistent memory blocks, for dma. + * dma_pool_create_node - Creates a pool of coherent DMA memory blocks. * @name: name of pool, for diagnostics * @dev: device that will be doing the DMA * @size: size of the blocks in this pool. * @align: alignment requirement for blocks; must be a power of two * @boundary: returned blocks won't cross this power of two boundary - * Context: !in_interrupt() + * @node: optional NUMA node to allocate structs 'dma_pool' and 'dma_page' on + * Context: not in_interrupt() * - * Returns a dma allocation pool with the requested characteristics, or - * null if one can't be created. Given one of these pools, dma_pool_alloc() - * may be used to allocate memory. Such memory will all have "consistent" + * Given one of these pools, dma_pool_alloc() + * may be used to allocate memory. Such memory will all have coherent * DMA mappings, accessible by the device and its driver without using * cache flushing primitives. The actual size of blocks allocated may be * larger than requested because of alignment. @@ -126,41 +219,45 @@ static DEVICE_ATTR(pools, S_IRUGO, show_pools, NULL); * cross that size boundary. This is useful for devices which have * addressing restrictions on individual DMA transfers, such as not crossing * boundaries of 4KBytes. + * + * Return: a dma allocation pool with the requested characteristics, or + * %NULL if one can't be created. */ -struct dma_pool *dma_pool_create(const char *name, struct device *dev, - size_t size, size_t align, size_t boundary) +struct dma_pool *dma_pool_create_node(const char *name, struct device *dev, + size_t size, size_t align, size_t boundary, int node) { struct dma_pool *retval; size_t allocation; + bool empty; - if (align == 0) { - align = 1; - } else if (align & (align - 1)) { + if (!dev) return NULL; - } - if (size == 0) { + if (align == 0) + align = 1; + else if (align & (align - 1)) return NULL; - } else if (size < 4) { - size = 4; - } - if ((size % align) != 0) - size = ALIGN(size, align); + if (size == 0 || size > INT_MAX) + return NULL; + if (size < sizeof(struct dma_block)) + size = sizeof(struct dma_block); + size = ALIGN(size, align); allocation = max_t(size_t, size, PAGE_SIZE); - if (!boundary) { + if (!boundary) boundary = allocation; - } else if ((boundary < size) || (boundary & (boundary - 1))) { + else if ((boundary < size) || (boundary & (boundary - 1))) return NULL; - } - retval = kmalloc_node(sizeof(*retval), GFP_KERNEL, dev_to_node(dev)); + boundary = min(boundary, allocation); + + retval = kzalloc_node(sizeof(*retval), GFP_KERNEL, node); if (!retval) return retval; - strlcpy(retval->name, name, sizeof(retval->name)); + strscpy(retval->name, name, sizeof(retval->name)); retval->dev = dev; @@ -169,84 +266,90 @@ struct dma_pool *dma_pool_create(const char *name, struct device *dev, retval->size = size; retval->boundary = boundary; retval->allocation = allocation; + retval->node = node; + INIT_LIST_HEAD(&retval->pools); - if (dev) { - int ret; - - mutex_lock(&pools_lock); - if (list_empty(&dev->dma_pools)) - ret = device_create_file(dev, &dev_attr_pools); - else - ret = 0; - /* note: not currently insisting "name" be unique */ - if (!ret) - list_add(&retval->pools, &dev->dma_pools); - else { + /* + * pools_lock ensures that the ->dma_pools list does not get corrupted. + * pools_reg_lock ensures that there is not a race between + * dma_pool_create() and dma_pool_destroy() or within dma_pool_create() + * when the first invocation of dma_pool_create() failed on + * device_create_file() and the second assumes that it has been done (I + * know it is a short window). + */ + mutex_lock(&pools_reg_lock); + mutex_lock(&pools_lock); + empty = list_empty(&dev->dma_pools); + list_add(&retval->pools, &dev->dma_pools); + mutex_unlock(&pools_lock); + if (empty) { + int err; + + err = device_create_file(dev, &dev_attr_pools); + if (err) { + mutex_lock(&pools_lock); + list_del(&retval->pools); + mutex_unlock(&pools_lock); + mutex_unlock(&pools_reg_lock); kfree(retval); - retval = NULL; + return NULL; } - mutex_unlock(&pools_lock); - } else - INIT_LIST_HEAD(&retval->pools); - + } + mutex_unlock(&pools_reg_lock); return retval; } -EXPORT_SYMBOL(dma_pool_create); +EXPORT_SYMBOL(dma_pool_create_node); static void pool_initialise_page(struct dma_pool *pool, struct dma_page *page) { - unsigned int offset = 0; - unsigned int next_boundary = pool->boundary; + unsigned int next_boundary = pool->boundary, offset = 0; + struct dma_block *block, *first = NULL, *last = NULL; - do { - unsigned int next = offset + pool->size; - if (unlikely((next + pool->size) >= next_boundary)) { - next = next_boundary; + pool_init_page(pool, page); + while (offset + pool->size <= pool->allocation) { + if (offset + pool->size > next_boundary) { + offset = next_boundary; next_boundary += pool->boundary; + continue; } - *(int *)(page->vaddr + offset) = next; - offset = next; - } while (offset < pool->allocation); + + block = page->vaddr + offset; + block->dma = page->dma + offset; + block->next_block = NULL; + + if (last) + last->next_block = block; + else + first = block; + last = block; + + offset += pool->size; + pool->nr_blocks++; + } + + last->next_block = pool->next_block; + pool->next_block = first; + + list_add(&page->page_list, &pool->page_list); + pool->nr_pages++; } static struct dma_page *pool_alloc_page(struct dma_pool *pool, gfp_t mem_flags) { struct dma_page *page; - page = kmalloc(sizeof(*page), mem_flags); + page = kmalloc_node(sizeof(*page), mem_flags, pool->node); if (!page) return NULL; + page->vaddr = dma_alloc_coherent(pool->dev, pool->allocation, &page->dma, mem_flags); - if (page->vaddr) { -#ifdef DMAPOOL_DEBUG - memset(page->vaddr, POOL_POISON_FREED, pool->allocation); -#endif - pool_initialise_page(pool, page); - page->in_use = 0; - page->offset = 0; - } else { + if (!page->vaddr) { kfree(page); - page = NULL; + return NULL; } - return page; -} - -static inline int is_page_busy(struct dma_page *page) -{ - return page->in_use != 0; -} - -static void pool_free_page(struct dma_pool *pool, struct dma_page *page) -{ - dma_addr_t dma = page->dma; -#ifdef DMAPOOL_DEBUG - memset(page->vaddr, POOL_POISON_FREED, pool->allocation); -#endif - dma_free_coherent(pool->dev, pool->allocation, page->vaddr, dma); - list_del(&page->page_list); - kfree(page); + return page; } /** @@ -259,30 +362,32 @@ static void pool_free_page(struct dma_pool *pool, struct dma_page *page) */ void dma_pool_destroy(struct dma_pool *pool) { + struct dma_page *page, *tmp; + bool empty, busy = false; + + if (unlikely(!pool)) + return; + + mutex_lock(&pools_reg_lock); mutex_lock(&pools_lock); list_del(&pool->pools); - if (pool->dev && list_empty(&pool->dev->dma_pools)) - device_remove_file(pool->dev, &dev_attr_pools); + empty = list_empty(&pool->dev->dma_pools); mutex_unlock(&pools_lock); + if (empty) + device_remove_file(pool->dev, &dev_attr_pools); + mutex_unlock(&pools_reg_lock); + + if (pool->nr_active) { + dev_err(pool->dev, "%s %s busy\n", __func__, pool->name); + busy = true; + } - while (!list_empty(&pool->page_list)) { - struct dma_page *page; - page = list_entry(pool->page_list.next, - struct dma_page, page_list); - if (is_page_busy(page)) { - if (pool->dev) - dev_err(pool->dev, - "dma_pool_destroy %s, %p busy\n", - pool->name, page->vaddr); - else - printk(KERN_ERR - "dma_pool_destroy %s, %p busy\n", - pool->name, page->vaddr); - /* leak the still-in-use consistent memory */ - list_del(&page->page_list); - kfree(page); - } else - pool_free_page(pool, page); + list_for_each_entry_safe(page, tmp, &pool->page_list, page_list) { + if (!busy) + dma_free_coherent(pool->dev, pool->allocation, + page->vaddr, page->dma); + list_del(&page->page_list); + kfree(page); } kfree(pool); @@ -290,91 +395,51 @@ void dma_pool_destroy(struct dma_pool *pool) EXPORT_SYMBOL(dma_pool_destroy); /** - * dma_pool_alloc - get a block of consistent memory + * dma_pool_alloc - get a block of coherent memory * @pool: dma pool that will produce the block * @mem_flags: GFP_* bitmask * @handle: pointer to dma address of block * - * This returns the kernel virtual address of a currently unused block, + * Return: the kernel virtual address of a currently unused block, * and reports its dma address through the handle. * If such a memory block can't be allocated, %NULL is returned. */ void *dma_pool_alloc(struct dma_pool *pool, gfp_t mem_flags, dma_addr_t *handle) { - unsigned long flags; + struct dma_block *block; struct dma_page *page; - size_t offset; - void *retval; + unsigned long flags; - might_sleep_if(mem_flags & __GFP_WAIT); + might_alloc(mem_flags); spin_lock_irqsave(&pool->lock, flags); - list_for_each_entry(page, &pool->page_list, page_list) { - if (page->offset < pool->allocation) - goto ready; - } - - /* pool_alloc_page() might sleep, so temporarily drop &pool->lock */ - spin_unlock_irqrestore(&pool->lock, flags); - - page = pool_alloc_page(pool, mem_flags); - if (!page) - return NULL; + block = pool_block_pop(pool); + if (!block) { + /* + * pool_alloc_page() might sleep, so temporarily drop + * &pool->lock + */ + spin_unlock_irqrestore(&pool->lock, flags); - spin_lock_irqsave(&pool->lock, flags); + page = pool_alloc_page(pool, mem_flags & (~__GFP_ZERO)); + if (!page) + return NULL; - list_add(&page->page_list, &pool->page_list); - ready: - page->in_use++; - offset = page->offset; - page->offset = *(int *)(page->vaddr + offset); - retval = offset + page->vaddr; - *handle = offset + page->dma; -#ifdef DMAPOOL_DEBUG - { - int i; - u8 *data = retval; - /* page->offset is stored in first 4 bytes */ - for (i = sizeof(page->offset); i < pool->size; i++) { - if (data[i] == POOL_POISON_FREED) - continue; - if (pool->dev) - dev_err(pool->dev, - "dma_pool_alloc %s, %p (corruped)\n", - pool->name, retval); - else - pr_err("dma_pool_alloc %s, %p (corruped)\n", - pool->name, retval); - - /* - * Dump the first 4 bytes even if they are not - * POOL_POISON_FREED - */ - print_hex_dump(KERN_ERR, "", DUMP_PREFIX_OFFSET, 16, 1, - data, pool->size, 1); - break; - } + spin_lock_irqsave(&pool->lock, flags); + pool_initialise_page(pool, page); + block = pool_block_pop(pool); } - memset(retval, POOL_POISON_ALLOCATED, pool->size); -#endif spin_unlock_irqrestore(&pool->lock, flags); - return retval; -} -EXPORT_SYMBOL(dma_pool_alloc); -static struct dma_page *pool_find_page(struct dma_pool *pool, dma_addr_t dma) -{ - struct dma_page *page; + *handle = block->dma; + pool_check_block(pool, block, mem_flags); + if (want_init_on_alloc(mem_flags)) + memset(block, 0, pool->size); - list_for_each_entry(page, &pool->page_list, page_list) { - if (dma < page->dma) - continue; - if (dma < (page->dma + pool->allocation)) - return page; - } - return NULL; + return block; } +EXPORT_SYMBOL(dma_pool_alloc); /** * dma_pool_free - put block back into dma pool @@ -387,68 +452,14 @@ static struct dma_page *pool_find_page(struct dma_pool *pool, dma_addr_t dma) */ void dma_pool_free(struct dma_pool *pool, void *vaddr, dma_addr_t dma) { - struct dma_page *page; + struct dma_block *block = vaddr; unsigned long flags; - unsigned int offset; spin_lock_irqsave(&pool->lock, flags); - page = pool_find_page(pool, dma); - if (!page) { - spin_unlock_irqrestore(&pool->lock, flags); - if (pool->dev) - dev_err(pool->dev, - "dma_pool_free %s, %p/%lx (bad dma)\n", - pool->name, vaddr, (unsigned long)dma); - else - printk(KERN_ERR "dma_pool_free %s, %p/%lx (bad dma)\n", - pool->name, vaddr, (unsigned long)dma); - return; - } - - offset = vaddr - page->vaddr; -#ifdef DMAPOOL_DEBUG - if ((dma - page->dma) != offset) { - spin_unlock_irqrestore(&pool->lock, flags); - if (pool->dev) - dev_err(pool->dev, - "dma_pool_free %s, %p (bad vaddr)/%Lx\n", - pool->name, vaddr, (unsigned long long)dma); - else - printk(KERN_ERR - "dma_pool_free %s, %p (bad vaddr)/%Lx\n", - pool->name, vaddr, (unsigned long long)dma); - return; - } - { - unsigned int chain = page->offset; - while (chain < pool->allocation) { - if (chain != offset) { - chain = *(int *)(page->vaddr + chain); - continue; - } - spin_unlock_irqrestore(&pool->lock, flags); - if (pool->dev) - dev_err(pool->dev, "dma_pool_free %s, dma %Lx " - "already free\n", pool->name, - (unsigned long long)dma); - else - printk(KERN_ERR "dma_pool_free %s, dma %Lx " - "already free\n", pool->name, - (unsigned long long)dma); - return; - } + if (!pool_block_err(pool, vaddr, dma)) { + pool_block_push(pool, block, dma); + pool->nr_active--; } - memset(vaddr, POOL_POISON_FREED, pool->size); -#endif - - page->in_use--; - *(int *)vaddr = page->offset; - page->offset = offset; - /* - * Resist a temptation to do - * if (!is_page_busy(page)) pool_free_page(pool, page); - * Better have a few empty pages hang around. - */ spin_unlock_irqrestore(&pool->lock, flags); } EXPORT_SYMBOL(dma_pool_free); @@ -478,6 +489,9 @@ static int dmam_pool_match(struct device *dev, void *res, void *match_data) * * Managed dma_pool_create(). DMA pool created with this function is * automatically destroyed on driver detach. + * + * Return: a managed dma allocation pool with the requested + * characteristics, or %NULL if one can't be created. */ struct dma_pool *dmam_pool_create(const char *name, struct device *dev, size_t size, size_t align, size_t allocation) @@ -508,7 +522,6 @@ void dmam_pool_destroy(struct dma_pool *pool) { struct device *dev = pool->dev; - WARN_ON(devres_destroy(dev, dmam_pool_release, dmam_pool_match, pool)); - dma_pool_destroy(pool); + WARN_ON(devres_release(dev, dmam_pool_release, dmam_pool_match, pool)); } EXPORT_SYMBOL(dmam_pool_destroy); |
