alistair23-linux/mm/mempool.c
Tejun Heo 5b990546e3 mempool: fix and document synchronization and memory barrier usage
mempool_alloc/free() use undocumented smp_mb()'s.  The code is slightly
broken and misleading.

The lockless part is in mempool_free().  It wants to determine whether the
item being freed needs to be returned to the pool or backing allocator
without grabbing pool->lock.  Two things need to be guaranteed for correct
operation.

1. pool->curr_nr + #allocated should never dip below pool->min_nr.
2. Waiters shouldn't be left dangling.

For #1, The only necessary condition is that curr_nr visible at free is
from after the allocation of the element being freed (details in the
comment).  For most cases, this is true without any barrier but there can
be fringe cases where the allocated pointer is passed to the freeing task
without going through memory barriers.  To cover this case, wmb is
necessary before returning from allocation and rmb is necessary before
reading curr_nr.  IOW,

	ALLOCATING TASK			FREEING TASK

	update pool state after alloc;
	wmb();
	pass pointer to freeing task;
					read pointer;
					rmb();
					read pool state to free;

The current code doesn't have wmb after pool update during allocation and
may theoretically, on machines where unlock doesn't behave as full wmb,
lead to pool depletion and deadlock.  smp_wmb() needs to be added after
successful allocation from reserved elements and smp_mb() in
mempool_free() can be replaced with smp_rmb().

For #2, the waiter needs to add itself to waitqueue and then check the
wait condition and the waker needs to update the wait condition and then
wake up.  Because waitqueue operations always go through full spinlock
synchronization, there is no need for extra memory barriers.

Furthermore, mempool_alloc() is already holding pool->lock when it decides
that it needs to wait.  There is no reason to do unlock - add waitqueue -
test condition again.  It can simply add itself to waitqueue while holding
pool->lock and then unlock and sleep.

This patch adds smp_wmb() after successful allocation from reserved pool,
replaces smp_mb() in mempool_free() with smp_rmb() and extend pool->lock
over waitqueue addition.  More importantly, it explains what memory
barriers do and how the lockless testing is correct.

-v2: Oleg pointed out that unlock doesn't imply wmb.  Added explicit
     smp_wmb() after successful allocation from reserved pool and
     updated comments accordingly.

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: David Howells <dhowells@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-01-10 16:30:45 -08:00

369 lines
10 KiB
C

/*
* linux/mm/mempool.c
*
* memory buffer pool support. Such pools are mostly used
* for guaranteed, deadlock-free memory allocations during
* extreme VM load.
*
* started by Ingo Molnar, Copyright (C) 2001
*/
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/export.h>
#include <linux/mempool.h>
#include <linux/blkdev.h>
#include <linux/writeback.h>
static void add_element(mempool_t *pool, void *element)
{
BUG_ON(pool->curr_nr >= pool->min_nr);
pool->elements[pool->curr_nr++] = element;
}
static void *remove_element(mempool_t *pool)
{
BUG_ON(pool->curr_nr <= 0);
return pool->elements[--pool->curr_nr];
}
static void free_pool(mempool_t *pool)
{
while (pool->curr_nr) {
void *element = remove_element(pool);
pool->free(element, pool->pool_data);
}
kfree(pool->elements);
kfree(pool);
}
/**
* mempool_create - create a memory pool
* @min_nr: the minimum number of elements guaranteed to be
* allocated for this pool.
* @alloc_fn: user-defined element-allocation function.
* @free_fn: user-defined element-freeing function.
* @pool_data: optional private data available to the user-defined functions.
*
* this function creates and allocates a guaranteed size, preallocated
* memory pool. The pool can be used from the mempool_alloc() and mempool_free()
* functions. This function might sleep. Both the alloc_fn() and the free_fn()
* functions might sleep - as long as the mempool_alloc() function is not called
* from IRQ contexts.
*/
mempool_t *mempool_create(int min_nr, mempool_alloc_t *alloc_fn,
mempool_free_t *free_fn, void *pool_data)
{
return mempool_create_node(min_nr,alloc_fn,free_fn, pool_data,-1);
}
EXPORT_SYMBOL(mempool_create);
mempool_t *mempool_create_node(int min_nr, mempool_alloc_t *alloc_fn,
mempool_free_t *free_fn, void *pool_data, int node_id)
{
mempool_t *pool;
pool = kmalloc_node(sizeof(*pool), GFP_KERNEL | __GFP_ZERO, node_id);
if (!pool)
return NULL;
pool->elements = kmalloc_node(min_nr * sizeof(void *),
GFP_KERNEL, node_id);
if (!pool->elements) {
kfree(pool);
return NULL;
}
spin_lock_init(&pool->lock);
pool->min_nr = min_nr;
pool->pool_data = pool_data;
init_waitqueue_head(&pool->wait);
pool->alloc = alloc_fn;
pool->free = free_fn;
/*
* First pre-allocate the guaranteed number of buffers.
*/
while (pool->curr_nr < pool->min_nr) {
void *element;
element = pool->alloc(GFP_KERNEL, pool->pool_data);
if (unlikely(!element)) {
free_pool(pool);
return NULL;
}
add_element(pool, element);
}
return pool;
}
EXPORT_SYMBOL(mempool_create_node);
/**
* mempool_resize - resize an existing memory pool
* @pool: pointer to the memory pool which was allocated via
* mempool_create().
* @new_min_nr: the new minimum number of elements guaranteed to be
* allocated for this pool.
* @gfp_mask: the usual allocation bitmask.
*
* This function shrinks/grows the pool. In the case of growing,
* it cannot be guaranteed that the pool will be grown to the new
* size immediately, but new mempool_free() calls will refill it.
*
* Note, the caller must guarantee that no mempool_destroy is called
* while this function is running. mempool_alloc() & mempool_free()
* might be called (eg. from IRQ contexts) while this function executes.
*/
int mempool_resize(mempool_t *pool, int new_min_nr, gfp_t gfp_mask)
{
void *element;
void **new_elements;
unsigned long flags;
BUG_ON(new_min_nr <= 0);
spin_lock_irqsave(&pool->lock, flags);
if (new_min_nr <= pool->min_nr) {
while (new_min_nr < pool->curr_nr) {
element = remove_element(pool);
spin_unlock_irqrestore(&pool->lock, flags);
pool->free(element, pool->pool_data);
spin_lock_irqsave(&pool->lock, flags);
}
pool->min_nr = new_min_nr;
goto out_unlock;
}
spin_unlock_irqrestore(&pool->lock, flags);
/* Grow the pool */
new_elements = kmalloc(new_min_nr * sizeof(*new_elements), gfp_mask);
if (!new_elements)
return -ENOMEM;
spin_lock_irqsave(&pool->lock, flags);
if (unlikely(new_min_nr <= pool->min_nr)) {
/* Raced, other resize will do our work */
spin_unlock_irqrestore(&pool->lock, flags);
kfree(new_elements);
goto out;
}
memcpy(new_elements, pool->elements,
pool->curr_nr * sizeof(*new_elements));
kfree(pool->elements);
pool->elements = new_elements;
pool->min_nr = new_min_nr;
while (pool->curr_nr < pool->min_nr) {
spin_unlock_irqrestore(&pool->lock, flags);
element = pool->alloc(gfp_mask, pool->pool_data);
if (!element)
goto out;
spin_lock_irqsave(&pool->lock, flags);
if (pool->curr_nr < pool->min_nr) {
add_element(pool, element);
} else {
spin_unlock_irqrestore(&pool->lock, flags);
pool->free(element, pool->pool_data); /* Raced */
goto out;
}
}
out_unlock:
spin_unlock_irqrestore(&pool->lock, flags);
out:
return 0;
}
EXPORT_SYMBOL(mempool_resize);
/**
* mempool_destroy - deallocate a memory pool
* @pool: pointer to the memory pool which was allocated via
* mempool_create().
*
* this function only sleeps if the free_fn() function sleeps. The caller
* has to guarantee that all elements have been returned to the pool (ie:
* freed) prior to calling mempool_destroy().
*/
void mempool_destroy(mempool_t *pool)
{
/* Check for outstanding elements */
BUG_ON(pool->curr_nr != pool->min_nr);
free_pool(pool);
}
EXPORT_SYMBOL(mempool_destroy);
/**
* mempool_alloc - allocate an element from a specific memory pool
* @pool: pointer to the memory pool which was allocated via
* mempool_create().
* @gfp_mask: the usual allocation bitmask.
*
* this function only sleeps if the alloc_fn() function sleeps or
* returns NULL. Note that due to preallocation, this function
* *never* fails when called from process contexts. (it might
* fail if called from an IRQ context.)
*/
void * mempool_alloc(mempool_t *pool, gfp_t gfp_mask)
{
void *element;
unsigned long flags;
wait_queue_t wait;
gfp_t gfp_temp;
might_sleep_if(gfp_mask & __GFP_WAIT);
gfp_mask |= __GFP_NOMEMALLOC; /* don't allocate emergency reserves */
gfp_mask |= __GFP_NORETRY; /* don't loop in __alloc_pages */
gfp_mask |= __GFP_NOWARN; /* failures are OK */
gfp_temp = gfp_mask & ~(__GFP_WAIT|__GFP_IO);
repeat_alloc:
element = pool->alloc(gfp_temp, pool->pool_data);
if (likely(element != NULL))
return element;
spin_lock_irqsave(&pool->lock, flags);
if (likely(pool->curr_nr)) {
element = remove_element(pool);
spin_unlock_irqrestore(&pool->lock, flags);
/* paired with rmb in mempool_free(), read comment there */
smp_wmb();
return element;
}
/* We must not sleep in the GFP_ATOMIC case */
if (!(gfp_mask & __GFP_WAIT)) {
spin_unlock_irqrestore(&pool->lock, flags);
return NULL;
}
/* Let's wait for someone else to return an element to @pool */
gfp_temp = gfp_mask;
init_wait(&wait);
prepare_to_wait(&pool->wait, &wait, TASK_UNINTERRUPTIBLE);
spin_unlock_irqrestore(&pool->lock, flags);
/*
* FIXME: this should be io_schedule(). The timeout is there as a
* workaround for some DM problems in 2.6.18.
*/
io_schedule_timeout(5*HZ);
finish_wait(&pool->wait, &wait);
goto repeat_alloc;
}
EXPORT_SYMBOL(mempool_alloc);
/**
* mempool_free - return an element to the pool.
* @element: pool element pointer.
* @pool: pointer to the memory pool which was allocated via
* mempool_create().
*
* this function only sleeps if the free_fn() function sleeps.
*/
void mempool_free(void *element, mempool_t *pool)
{
unsigned long flags;
if (unlikely(element == NULL))
return;
/*
* Paired with the wmb in mempool_alloc(). The preceding read is
* for @element and the following @pool->curr_nr. This ensures
* that the visible value of @pool->curr_nr is from after the
* allocation of @element. This is necessary for fringe cases
* where @element was passed to this task without going through
* barriers.
*
* For example, assume @p is %NULL at the beginning and one task
* performs "p = mempool_alloc(...);" while another task is doing
* "while (!p) cpu_relax(); mempool_free(p, ...);". This function
* may end up using curr_nr value which is from before allocation
* of @p without the following rmb.
*/
smp_rmb();
/*
* For correctness, we need a test which is guaranteed to trigger
* if curr_nr + #allocated == min_nr. Testing curr_nr < min_nr
* without locking achieves that and refilling as soon as possible
* is desirable.
*
* Because curr_nr visible here is always a value after the
* allocation of @element, any task which decremented curr_nr below
* min_nr is guaranteed to see curr_nr < min_nr unless curr_nr gets
* incremented to min_nr afterwards. If curr_nr gets incremented
* to min_nr after the allocation of @element, the elements
* allocated after that are subject to the same guarantee.
*
* Waiters happen iff curr_nr is 0 and the above guarantee also
* ensures that there will be frees which return elements to the
* pool waking up the waiters.
*/
if (pool->curr_nr < pool->min_nr) {
spin_lock_irqsave(&pool->lock, flags);
if (pool->curr_nr < pool->min_nr) {
add_element(pool, element);
spin_unlock_irqrestore(&pool->lock, flags);
wake_up(&pool->wait);
return;
}
spin_unlock_irqrestore(&pool->lock, flags);
}
pool->free(element, pool->pool_data);
}
EXPORT_SYMBOL(mempool_free);
/*
* A commonly used alloc and free fn.
*/
void *mempool_alloc_slab(gfp_t gfp_mask, void *pool_data)
{
struct kmem_cache *mem = pool_data;
return kmem_cache_alloc(mem, gfp_mask);
}
EXPORT_SYMBOL(mempool_alloc_slab);
void mempool_free_slab(void *element, void *pool_data)
{
struct kmem_cache *mem = pool_data;
kmem_cache_free(mem, element);
}
EXPORT_SYMBOL(mempool_free_slab);
/*
* A commonly used alloc and free fn that kmalloc/kfrees the amount of memory
* specified by pool_data
*/
void *mempool_kmalloc(gfp_t gfp_mask, void *pool_data)
{
size_t size = (size_t)pool_data;
return kmalloc(size, gfp_mask);
}
EXPORT_SYMBOL(mempool_kmalloc);
void mempool_kfree(void *element, void *pool_data)
{
kfree(element);
}
EXPORT_SYMBOL(mempool_kfree);
/*
* A simple mempool-backed page allocator that allocates pages
* of the order specified by pool_data.
*/
void *mempool_alloc_pages(gfp_t gfp_mask, void *pool_data)
{
int order = (int)(long)pool_data;
return alloc_pages(gfp_mask, order);
}
EXPORT_SYMBOL(mempool_alloc_pages);
void mempool_free_pages(void *element, void *pool_data)
{
int order = (int)(long)pool_data;
__free_pages(element, order);
}
EXPORT_SYMBOL(mempool_free_pages);