/*
- * Basic general purpose allocator for managing special purpose memory
- * not managed by the regular kmalloc/kfree interface.
- * Uses for this includes on-device special memory, uncached memory
- * etc.
+ * Basic general purpose allocator for managing special purpose
+ * memory, for example, memory that is not managed by the regular
+ * kmalloc/kfree interface. Uses for this includes on-device special
+ * memory, uncached memory etc.
*
- * This code is based on the buddy allocator found in the sym53c8xx_2
- * driver Copyright (C) 1999-2001 Gerard Roudier <groudier@free.fr>,
- * and adapted for general purpose use.
+ * It is safe to use the allocator in NMI handlers and other special
+ * unblockable contexts that could otherwise deadlock on locks. This
+ * is implemented by using atomic operations and retries on any
+ * conflicts. The disadvantage is that there may be livelocks in
+ * extreme cases. For better scalability, one allocator can be used
+ * for each CPU.
+ *
+ * The lockless operation only works if there is enough memory
+ * available. If new memory is added to the pool a lock has to be
+ * still taken. So any user relying on locklessness has to ensure
+ * that sufficient memory is preallocated.
+ *
+ * The basic atomic operation of this allocator is cmpxchg on long.
+ * On architectures that don't have NMI-safe cmpxchg implementation,
+ * the allocator can NOT be used in NMI handler. So code uses the
+ * allocator in NMI handler should depend on
+ * CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG.
*
* Copyright 2005 (C) Jes Sorensen <jes@trained-monkey.org>
*
* Version 2. See the file COPYING for more details.
*/
-#include <linux/module.h>
-#include <linux/stddef.h>
-#include <linux/kernel.h>
-#include <linux/string.h>
#include <linux/slab.h>
-#include <linux/init.h>
-#include <linux/mm.h>
-#include <linux/spinlock.h>
+#include <linux/export.h>
+#include <linux/bitmap.h>
+#include <linux/rculist.h>
+#include <linux/interrupt.h>
#include <linux/genalloc.h>
-#include <asm/page.h>
+static int set_bits_ll(unsigned long *addr, unsigned long mask_to_set)
+{
+ unsigned long val, nval;
+
+ nval = *addr;
+ do {
+ val = nval;
+ if (val & mask_to_set)
+ return -EBUSY;
+ cpu_relax();
+ } while ((nval = cmpxchg(addr, val, val | mask_to_set)) != val);
+ return 0;
+}
-struct gen_pool *gen_pool_create(int nr_chunks, int max_chunk_shift,
- unsigned long (*fp)(struct gen_pool *),
- unsigned long data)
+static int clear_bits_ll(unsigned long *addr, unsigned long mask_to_clear)
+{
+ unsigned long val, nval;
+
+ nval = *addr;
+ do {
+ val = nval;
+ if ((val & mask_to_clear) != mask_to_clear)
+ return -EBUSY;
+ cpu_relax();
+ } while ((nval = cmpxchg(addr, val, val & ~mask_to_clear)) != val);
+
+ return 0;
+}
+
+/*
+ * bitmap_set_ll - set the specified number of bits at the specified position
+ * @map: pointer to a bitmap
+ * @start: a bit position in @map
+ * @nr: number of bits to set
+ *
+ * Set @nr bits start from @start in @map lock-lessly. Several users
+ * can set/clear the same bitmap simultaneously without lock. If two
+ * users set the same bit, one user will return remain bits, otherwise
+ * return 0.
+ */
+static int bitmap_set_ll(unsigned long *map, int start, int nr)
{
- struct gen_pool *poolp;
- unsigned long tmp;
- int i;
-
- /*
- * This is really an arbitrary limit, +10 is enough for
- * IA64_GRANULE_SHIFT, aka 16MB. If anyone needs a large limit
- * this can be increased without problems.
- */
- if ((max_chunk_shift > (PAGE_SHIFT + 10)) ||
- ((max_chunk_shift < ALLOC_MIN_SHIFT) && max_chunk_shift))
- return NULL;
-
- if (!max_chunk_shift)
- max_chunk_shift = PAGE_SHIFT;
-
- poolp = kmalloc(sizeof(struct gen_pool), GFP_KERNEL);
- if (!poolp)
- return NULL;
- memset(poolp, 0, sizeof(struct gen_pool));
- poolp->h = kmalloc(sizeof(struct gen_pool_link) *
- (max_chunk_shift - ALLOC_MIN_SHIFT + 1),
- GFP_KERNEL);
- if (!poolp->h) {
- printk(KERN_WARNING "gen_pool_alloc() failed to allocate\n");
- kfree(poolp);
- return NULL;
+ unsigned long *p = map + BIT_WORD(start);
+ const int size = start + nr;
+ int bits_to_set = BITS_PER_LONG - (start % BITS_PER_LONG);
+ unsigned long mask_to_set = BITMAP_FIRST_WORD_MASK(start);
+
+ while (nr - bits_to_set >= 0) {
+ if (set_bits_ll(p, mask_to_set))
+ return nr;
+ nr -= bits_to_set;
+ bits_to_set = BITS_PER_LONG;
+ mask_to_set = ~0UL;
+ p++;
}
- memset(poolp->h, 0, sizeof(struct gen_pool_link) *
- (max_chunk_shift - ALLOC_MIN_SHIFT + 1));
-
- spin_lock_init(&poolp->lock);
- poolp->get_new_chunk = fp;
- poolp->max_chunk_shift = max_chunk_shift;
- poolp->private = data;
-
- for (i = 0; i < nr_chunks; i++) {
- tmp = poolp->get_new_chunk(poolp);
- printk(KERN_INFO "allocated %lx\n", tmp);
- if (!tmp)
- break;
- gen_pool_free(poolp, tmp, (1 << poolp->max_chunk_shift));
+ if (nr) {
+ mask_to_set &= BITMAP_LAST_WORD_MASK(size);
+ if (set_bits_ll(p, mask_to_set))
+ return nr;
}
- return poolp;
+ return 0;
}
-EXPORT_SYMBOL(gen_pool_create);
-
/*
- * Simple power of two buddy-like generic allocator.
- * Provides naturally aligned memory chunks.
+ * bitmap_clear_ll - clear the specified number of bits at the specified position
+ * @map: pointer to a bitmap
+ * @start: a bit position in @map
+ * @nr: number of bits to set
+ *
+ * Clear @nr bits start from @start in @map lock-lessly. Several users
+ * can set/clear the same bitmap simultaneously without lock. If two
+ * users clear the same bit, one user will return remain bits,
+ * otherwise return 0.
*/
-unsigned long gen_pool_alloc(struct gen_pool *poolp, int size)
+static int bitmap_clear_ll(unsigned long *map, int start, int nr)
{
- int j, i, s, max_chunk_size;
- unsigned long a, flags;
- struct gen_pool_link *h = poolp->h;
+ unsigned long *p = map + BIT_WORD(start);
+ const int size = start + nr;
+ int bits_to_clear = BITS_PER_LONG - (start % BITS_PER_LONG);
+ unsigned long mask_to_clear = BITMAP_FIRST_WORD_MASK(start);
- max_chunk_size = 1 << poolp->max_chunk_shift;
+ while (nr - bits_to_clear >= 0) {
+ if (clear_bits_ll(p, mask_to_clear))
+ return nr;
+ nr -= bits_to_clear;
+ bits_to_clear = BITS_PER_LONG;
+ mask_to_clear = ~0UL;
+ p++;
+ }
+ if (nr) {
+ mask_to_clear &= BITMAP_LAST_WORD_MASK(size);
+ if (clear_bits_ll(p, mask_to_clear))
+ return nr;
+ }
- if (size > max_chunk_size)
- return 0;
+ return 0;
+}
- size = max(size, 1 << ALLOC_MIN_SHIFT);
- i = fls(size - 1);
- s = 1 << i;
- j = i -= ALLOC_MIN_SHIFT;
-
- spin_lock_irqsave(&poolp->lock, flags);
- while (!h[j].next) {
- if (s == max_chunk_size) {
- struct gen_pool_link *ptr;
- spin_unlock_irqrestore(&poolp->lock, flags);
- ptr = (struct gen_pool_link *)poolp->get_new_chunk(poolp);
- spin_lock_irqsave(&poolp->lock, flags);
- if (ptr != NULL) {
- ptr->next = h[j].next;
- h[j].next = ptr;
- }
- break;
- }
- j++;
- s <<= 1;
+/**
+ * gen_pool_create - create a new special memory pool
+ * @min_alloc_order: log base 2 of number of bytes each bitmap bit represents
+ * @nid: node id of the node the pool structure should be allocated on, or -1
+ *
+ * Create a new special memory pool that can be used to manage special purpose
+ * memory not managed by the regular kmalloc/kfree interface.
+ */
+struct gen_pool *gen_pool_create(int min_alloc_order, int nid)
+{
+ struct gen_pool *pool;
+
+ pool = kmalloc_node(sizeof(struct gen_pool), GFP_KERNEL, nid);
+ if (pool != NULL) {
+ spin_lock_init(&pool->lock);
+ INIT_LIST_HEAD(&pool->chunks);
+ pool->min_alloc_order = min_alloc_order;
}
- a = (unsigned long) h[j].next;
- if (a) {
- h[j].next = h[j].next->next;
- /*
- * This should be split into a seperate function doing
- * the chunk split in order to support custom
- * handling memory not physically accessible by host
- */
- while (j > i) {
- j -= 1;
- s >>= 1;
- h[j].next = (struct gen_pool_link *) (a + s);
- h[j].next->next = NULL;
+ return pool;
+}
+EXPORT_SYMBOL(gen_pool_create);
+
+/**
+ * gen_pool_add_virt - add a new chunk of special memory to the pool
+ * @pool: pool to add new memory chunk to
+ * @virt: virtual starting address of memory chunk to add to pool
+ * @phys: physical starting address of memory chunk to add to pool
+ * @size: size in bytes of the memory chunk to add to pool
+ * @nid: node id of the node the chunk structure and bitmap should be
+ * allocated on, or -1
+ *
+ * Add a new chunk of special memory to the specified pool.
+ *
+ * Returns 0 on success or a -ve errno on failure.
+ */
+int gen_pool_add_virt(struct gen_pool *pool, unsigned long virt, phys_addr_t phys,
+ size_t size, int nid)
+{
+ struct gen_pool_chunk *chunk;
+ int nbits = size >> pool->min_alloc_order;
+ int nbytes = sizeof(struct gen_pool_chunk) +
+ (nbits + BITS_PER_BYTE - 1) / BITS_PER_BYTE;
+
+ chunk = kmalloc_node(nbytes, GFP_KERNEL | __GFP_ZERO, nid);
+ if (unlikely(chunk == NULL))
+ return -ENOMEM;
+
+ chunk->phys_addr = phys;
+ chunk->start_addr = virt;
+ chunk->end_addr = virt + size;
+ atomic_set(&chunk->avail, size);
+
+ spin_lock(&pool->lock);
+ list_add_rcu(&chunk->next_chunk, &pool->chunks);
+ spin_unlock(&pool->lock);
+
+ return 0;
+}
+EXPORT_SYMBOL(gen_pool_add_virt);
+
+/**
+ * gen_pool_virt_to_phys - return the physical address of memory
+ * @pool: pool to allocate from
+ * @addr: starting address of memory
+ *
+ * Returns the physical address on success, or -1 on error.
+ */
+phys_addr_t gen_pool_virt_to_phys(struct gen_pool *pool, unsigned long addr)
+{
+ struct gen_pool_chunk *chunk;
+ phys_addr_t paddr = -1;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(chunk, &pool->chunks, next_chunk) {
+ if (addr >= chunk->start_addr && addr < chunk->end_addr) {
+ paddr = chunk->phys_addr + (addr - chunk->start_addr);
+ break;
}
- ((struct gen_pool_link *)a)->next = NULL;
- while (((volatile struct gen_pool_link *)a)->next != NULL)
- ; /* spin until uncached write gets to FSB */
}
- spin_unlock_irqrestore(&poolp->lock, flags);
- return a;
-}
-EXPORT_SYMBOL(gen_pool_alloc);
+ rcu_read_unlock();
+ return paddr;
+}
+EXPORT_SYMBOL(gen_pool_virt_to_phys);
-/*
- * Counter-part of the generic allocator.
+/**
+ * gen_pool_destroy - destroy a special memory pool
+ * @pool: pool to destroy
+ *
+ * Destroy the specified special memory pool. Verifies that there are no
+ * outstanding allocations.
*/
-void gen_pool_free(struct gen_pool *poolp, unsigned long ptr, int size)
+void gen_pool_destroy(struct gen_pool *pool)
{
- struct gen_pool_link *q;
- struct gen_pool_link *h = poolp->h;
- unsigned long a, b, flags;
- int i, s, max_chunk_size;
+ struct list_head *_chunk, *_next_chunk;
+ struct gen_pool_chunk *chunk;
+ int order = pool->min_alloc_order;
+ int bit, end_bit;
+
+ list_for_each_safe(_chunk, _next_chunk, &pool->chunks) {
+ chunk = list_entry(_chunk, struct gen_pool_chunk, next_chunk);
+ list_del(&chunk->next_chunk);
+
+ end_bit = (chunk->end_addr - chunk->start_addr) >> order;
+ bit = find_next_bit(chunk->bits, end_bit, 0);
+ BUG_ON(bit < end_bit);
+
+ kfree(chunk);
+ }
+ kfree(pool);
+ return;
+}
+EXPORT_SYMBOL(gen_pool_destroy);
- max_chunk_size = 1 << poolp->max_chunk_shift;
+/**
+ * gen_pool_alloc - allocate special memory from the pool
+ * @pool: pool to allocate from
+ * @size: number of bytes to allocate from the pool
+ *
+ * Allocate the requested number of bytes from the specified pool.
+ * Uses a first-fit algorithm. Can not be used in NMI handler on
+ * architectures without NMI-safe cmpxchg implementation.
+ */
+unsigned long gen_pool_alloc(struct gen_pool *pool, size_t size)
+{
+ struct gen_pool_chunk *chunk;
+ unsigned long addr = 0;
+ int order = pool->min_alloc_order;
+ int nbits, start_bit = 0, end_bit, remain;
- if (size > max_chunk_size)
- return;
+#ifndef CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG
+ BUG_ON(in_nmi());
+#endif
- size = max(size, 1 << ALLOC_MIN_SHIFT);
- i = fls(size - 1);
- s = 1 << i;
- i -= ALLOC_MIN_SHIFT;
+ if (size == 0)
+ return 0;
- a = ptr;
+ nbits = (size + (1UL << order) - 1) >> order;
+ rcu_read_lock();
+ list_for_each_entry_rcu(chunk, &pool->chunks, next_chunk) {
+ if (size > atomic_read(&chunk->avail))
+ continue;
- spin_lock_irqsave(&poolp->lock, flags);
- while (1) {
- if (s == max_chunk_size) {
- break;
+ end_bit = (chunk->end_addr - chunk->start_addr) >> order;
+retry:
+ start_bit = bitmap_find_next_zero_area(chunk->bits, end_bit,
+ start_bit, nbits, 0);
+ if (start_bit >= end_bit)
+ continue;
+ remain = bitmap_set_ll(chunk->bits, start_bit, nbits);
+ if (remain) {
+ remain = bitmap_clear_ll(chunk->bits, start_bit,
+ nbits - remain);
+ BUG_ON(remain);
+ goto retry;
}
- b = a ^ s;
- q = &h[i];
- while (q->next && q->next != (struct gen_pool_link *)b)
- q = q->next;
+ addr = chunk->start_addr + ((unsigned long)start_bit << order);
+ size = nbits << order;
+ atomic_sub(size, &chunk->avail);
+ break;
+ }
+ rcu_read_unlock();
+ return addr;
+}
+EXPORT_SYMBOL(gen_pool_alloc);
- if (!q->next) {
- break;
+/**
+ * gen_pool_free - free allocated special memory back to the pool
+ * @pool: pool to free to
+ * @addr: starting address of memory to free back to pool
+ * @size: size in bytes of memory to free
+ *
+ * Free previously allocated special memory back to the specified
+ * pool. Can not be used in NMI handler on architectures without
+ * NMI-safe cmpxchg implementation.
+ */
+void gen_pool_free(struct gen_pool *pool, unsigned long addr, size_t size)
+{
+ struct gen_pool_chunk *chunk;
+ int order = pool->min_alloc_order;
+ int start_bit, nbits, remain;
+
+#ifndef CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG
+ BUG_ON(in_nmi());
+#endif
+
+ nbits = (size + (1UL << order) - 1) >> order;
+ rcu_read_lock();
+ list_for_each_entry_rcu(chunk, &pool->chunks, next_chunk) {
+ if (addr >= chunk->start_addr && addr < chunk->end_addr) {
+ BUG_ON(addr + size > chunk->end_addr);
+ start_bit = (addr - chunk->start_addr) >> order;
+ remain = bitmap_clear_ll(chunk->bits, start_bit, nbits);
+ BUG_ON(remain);
+ size = nbits << order;
+ atomic_add(size, &chunk->avail);
+ rcu_read_unlock();
+ return;
}
- q->next = q->next->next;
- a = a & b;
- b = a + s;
- ((struct gen_pool_link *)b)->next = NULL;
- s <<= 1;
- i++;
}
- ((struct gen_pool_link *)a)->next = h[i].next;
- while (((volatile struct gen_pool_link *)a)->next != h[i].next)
- ; /* spin until uncached write gets to FSB */
- h[i].next = (struct gen_pool_link *)a;
- spin_unlock_irqrestore(&poolp->lock, flags);
+ rcu_read_unlock();
+ BUG();
}
EXPORT_SYMBOL(gen_pool_free);
+
+/**
+ * gen_pool_for_each_chunk - call func for every chunk of generic memory pool
+ * @pool: the generic memory pool
+ * @func: func to call
+ * @data: additional data used by @func
+ *
+ * Call @func for every chunk of generic memory pool. The @func is
+ * called with rcu_read_lock held.
+ */
+void gen_pool_for_each_chunk(struct gen_pool *pool,
+ void (*func)(struct gen_pool *pool, struct gen_pool_chunk *chunk, void *data),
+ void *data)
+{
+ struct gen_pool_chunk *chunk;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(chunk, &(pool)->chunks, next_chunk)
+ func(pool, chunk, data);
+ rcu_read_unlock();
+}
+EXPORT_SYMBOL(gen_pool_for_each_chunk);
+
+/**
+ * gen_pool_avail - get available free space of the pool
+ * @pool: pool to get available free space
+ *
+ * Return available free space of the specified pool.
+ */
+size_t gen_pool_avail(struct gen_pool *pool)
+{
+ struct gen_pool_chunk *chunk;
+ size_t avail = 0;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(chunk, &pool->chunks, next_chunk)
+ avail += atomic_read(&chunk->avail);
+ rcu_read_unlock();
+ return avail;
+}
+EXPORT_SYMBOL_GPL(gen_pool_avail);
+
+/**
+ * gen_pool_size - get size in bytes of memory managed by the pool
+ * @pool: pool to get size
+ *
+ * Return size in bytes of memory managed by the pool.
+ */
+size_t gen_pool_size(struct gen_pool *pool)
+{
+ struct gen_pool_chunk *chunk;
+ size_t size = 0;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(chunk, &pool->chunks, next_chunk)
+ size += chunk->end_addr - chunk->start_addr;
+ rcu_read_unlock();
+ return size;
+}
+EXPORT_SYMBOL_GPL(gen_pool_size);
projects / linux-flexiantxendom0-3.2.10.git / blobdiff