kernel-ark/mm/mempool.c
Michal Hocko 4e390b2b2f Revert "mm, mempool: only set __GFP_NOMEMALLOC if there are free elements"
This reverts commit f9054c70d2 ("mm, mempool: only set __GFP_NOMEMALLOC
if there are free elements").

There has been a report about OOM killer invoked when swapping out to a
dm-crypt device.  The primary reason seems to be that the swapout out IO
managed to completely deplete memory reserves.  Ondrej was able to
bisect and explained the issue by pointing to f9054c70d2 ("mm,
mempool: only set __GFP_NOMEMALLOC if there are free elements").

The reason is that the swapout path is not throttled properly because
the md-raid layer needs to allocate from the generic_make_request path
which means it allocates from the PF_MEMALLOC context.  dm layer uses
mempool_alloc in order to guarantee a forward progress which used to
inhibit access to memory reserves when using page allocator.  This has
changed by f9054c70d2 ("mm, mempool: only set __GFP_NOMEMALLOC if
there are free elements") which has dropped the __GFP_NOMEMALLOC
protection when the memory pool is depleted.

If we are running out of memory and the only way forward to free memory
is to perform swapout we just keep consuming memory reserves rather than
throttling the mempool allocations and allowing the pending IO to
complete up to a moment when the memory is depleted completely and there
is no way forward but invoking the OOM killer.  This is less than
optimal.

The original intention of f9054c70d2 was to help with the OOM
situations where the oom victim depends on mempool allocation to make a
forward progress.  David has mentioned the following backtrace:

  schedule
  schedule_timeout
  io_schedule_timeout
  mempool_alloc
  __split_and_process_bio
  dm_request
  generic_make_request
  submit_bio
  mpage_readpages
  ext4_readpages
  __do_page_cache_readahead
  ra_submit
  filemap_fault
  handle_mm_fault
  __do_page_fault
  do_page_fault
  page_fault

We do not know more about why the mempool is depleted without being
replenished in time, though.  In any case the dm layer shouldn't depend
on any allocations outside of the dedicated pools so a forward progress
should be guaranteed.  If this is not the case then the dm should be
fixed rather than papering over the problem and postponing it to later
by accessing more memory reserves.

mempools are a mechanism to maintain dedicated memory reserves to
guaratee forward progress.  Allowing them an unbounded access to the
page allocator memory reserves is going against the whole purpose of
this mechanism.

Bisected by Ondrej Kozina.

[akpm@linux-foundation.org: coding-style fixes]
Link: http://lkml.kernel.org/r/20160721145309.GR26379@dhcp22.suse.cz
Signed-off-by: Michal Hocko <mhocko@suse.com>
Reported-by: Ondrej Kozina <okozina@redhat.com>
Reviewed-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: NeilBrown <neilb@suse.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mikulas Patocka <mpatocka@redhat.com>
Cc: Ondrej Kozina <okozina@redhat.com>
Cc: Tetsuo Handa <penguin-kernel@i-love.sakura.ne.jp>
Cc: Mel Gorman <mgorman@suse.de>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-07-28 16:07:41 -07:00

494 lines
14 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
* debugging by David Rientjes, Copyright (C) 2015
*/
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/highmem.h>
#include <linux/kasan.h>
#include <linux/kmemleak.h>
#include <linux/export.h>
#include <linux/mempool.h>
#include <linux/blkdev.h>
#include <linux/writeback.h>
#include "slab.h"
#if defined(CONFIG_DEBUG_SLAB) || defined(CONFIG_SLUB_DEBUG_ON)
static void poison_error(mempool_t *pool, void *element, size_t size,
size_t byte)
{
const int nr = pool->curr_nr;
const int start = max_t(int, byte - (BITS_PER_LONG / 8), 0);
const int end = min_t(int, byte + (BITS_PER_LONG / 8), size);
int i;
pr_err("BUG: mempool element poison mismatch\n");
pr_err("Mempool %p size %zu\n", pool, size);
pr_err(" nr=%d @ %p: %s0x", nr, element, start > 0 ? "... " : "");
for (i = start; i < end; i++)
pr_cont("%x ", *(u8 *)(element + i));
pr_cont("%s\n", end < size ? "..." : "");
dump_stack();
}
static void __check_element(mempool_t *pool, void *element, size_t size)
{
u8 *obj = element;
size_t i;
for (i = 0; i < size; i++) {
u8 exp = (i < size - 1) ? POISON_FREE : POISON_END;
if (obj[i] != exp) {
poison_error(pool, element, size, i);
return;
}
}
memset(obj, POISON_INUSE, size);
}
static void check_element(mempool_t *pool, void *element)
{
/* Mempools backed by slab allocator */
if (pool->free == mempool_free_slab || pool->free == mempool_kfree)
__check_element(pool, element, ksize(element));
/* Mempools backed by page allocator */
if (pool->free == mempool_free_pages) {
int order = (int)(long)pool->pool_data;
void *addr = kmap_atomic((struct page *)element);
__check_element(pool, addr, 1UL << (PAGE_SHIFT + order));
kunmap_atomic(addr);
}
}
static void __poison_element(void *element, size_t size)
{
u8 *obj = element;
memset(obj, POISON_FREE, size - 1);
obj[size - 1] = POISON_END;
}
static void poison_element(mempool_t *pool, void *element)
{
/* Mempools backed by slab allocator */
if (pool->alloc == mempool_alloc_slab || pool->alloc == mempool_kmalloc)
__poison_element(element, ksize(element));
/* Mempools backed by page allocator */
if (pool->alloc == mempool_alloc_pages) {
int order = (int)(long)pool->pool_data;
void *addr = kmap_atomic((struct page *)element);
__poison_element(addr, 1UL << (PAGE_SHIFT + order));
kunmap_atomic(addr);
}
}
#else /* CONFIG_DEBUG_SLAB || CONFIG_SLUB_DEBUG_ON */
static inline void check_element(mempool_t *pool, void *element)
{
}
static inline void poison_element(mempool_t *pool, void *element)
{
}
#endif /* CONFIG_DEBUG_SLAB || CONFIG_SLUB_DEBUG_ON */
static void kasan_poison_element(mempool_t *pool, void *element)
{
if (pool->alloc == mempool_alloc_slab || pool->alloc == mempool_kmalloc)
kasan_poison_kfree(element);
if (pool->alloc == mempool_alloc_pages)
kasan_free_pages(element, (unsigned long)pool->pool_data);
}
static void kasan_unpoison_element(mempool_t *pool, void *element, gfp_t flags)
{
if (pool->alloc == mempool_alloc_slab || pool->alloc == mempool_kmalloc)
kasan_unpoison_slab(element);
if (pool->alloc == mempool_alloc_pages)
kasan_alloc_pages(element, (unsigned long)pool->pool_data);
}
static void add_element(mempool_t *pool, void *element)
{
BUG_ON(pool->curr_nr >= pool->min_nr);
poison_element(pool, element);
kasan_poison_element(pool, element);
pool->elements[pool->curr_nr++] = element;
}
static void *remove_element(mempool_t *pool, gfp_t flags)
{
void *element = pool->elements[--pool->curr_nr];
BUG_ON(pool->curr_nr < 0);
kasan_unpoison_element(pool, element, flags);
check_element(pool, element);
return element;
}
/**
* mempool_destroy - deallocate a memory pool
* @pool: pointer to the memory pool which was allocated via
* mempool_create().
*
* Free all reserved elements in @pool and @pool itself. This function
* only sleeps if the free_fn() function sleeps.
*/
void mempool_destroy(mempool_t *pool)
{
if (unlikely(!pool))
return;
while (pool->curr_nr) {
void *element = remove_element(pool, GFP_KERNEL);
pool->free(element, pool->pool_data);
}
kfree(pool->elements);
kfree(pool);
}
EXPORT_SYMBOL(mempool_destroy);
/**
* 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,
GFP_KERNEL, NUMA_NO_NODE);
}
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,
gfp_t gfp_mask, int node_id)
{
mempool_t *pool;
pool = kzalloc_node(sizeof(*pool), gfp_mask, node_id);
if (!pool)
return NULL;
pool->elements = kmalloc_node(min_nr * sizeof(void *),
gfp_mask, 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_mask, pool->pool_data);
if (unlikely(!element)) {
mempool_destroy(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.
*
* 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.
* This function may sleep.
*
* 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)
{
void *element;
void **new_elements;
unsigned long flags;
BUG_ON(new_min_nr <= 0);
might_sleep();
spin_lock_irqsave(&pool->lock, flags);
if (new_min_nr <= pool->min_nr) {
while (new_min_nr < pool->curr_nr) {
element = remove_element(pool, GFP_KERNEL);
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_array(new_min_nr, sizeof(*new_elements),
GFP_KERNEL);
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_KERNEL, 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_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.)
* Note: using __GFP_ZERO is not supported.
*/
void *mempool_alloc(mempool_t *pool, gfp_t gfp_mask)
{
void *element;
unsigned long flags;
wait_queue_t wait;
gfp_t gfp_temp;
VM_WARN_ON_ONCE(gfp_mask & __GFP_ZERO);
might_sleep_if(gfp_mask & __GFP_DIRECT_RECLAIM);
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_DIRECT_RECLAIM|__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, gfp_temp);
spin_unlock_irqrestore(&pool->lock, flags);
/* paired with rmb in mempool_free(), read comment there */
smp_wmb();
/*
* Update the allocation stack trace as this is more useful
* for debugging.
*/
kmemleak_update_trace(element);
return element;
}
/*
* We use gfp mask w/o direct reclaim or IO for the first round. If
* alloc failed with that and @pool was empty, retry immediately.
*/
if (gfp_temp != gfp_mask) {
spin_unlock_irqrestore(&pool->lock, flags);
gfp_temp = gfp_mask;
goto repeat_alloc;
}
/* We must not sleep if !__GFP_DIRECT_RECLAIM */
if (!(gfp_mask & __GFP_DIRECT_RECLAIM)) {
spin_unlock_irqrestore(&pool->lock, flags);
return NULL;
}
/* Let's wait for someone else to return an element to @pool */
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 (unlikely(pool->curr_nr < pool->min_nr)) {
spin_lock_irqsave(&pool->lock, flags);
if (likely(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;
VM_BUG_ON(mem->ctor);
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);