tmp_suning_uos_patched/mm/mempool.c
Qian Cai abe1de4209 mm/mempool: fix a data race in mempool_free()
mempool_t pool.curr_nr could be accessed concurrently as noticed by
KCSAN,

 BUG: KCSAN: data-race in mempool_free / remove_element

 write to 0xffffffffa937638c of 4 bytes by task 6359 on cpu 113:
  remove_element+0x4a/0x1c0
  remove_element at mm/mempool.c:132
  mempool_alloc+0x102/0x210
  (inlined by) mempool_alloc at mm/mempool.c:399
  bio_alloc_bioset+0x106/0x2c0
  get_swap_bio+0x49/0x230
  __swap_writepage+0x680/0xc30
  swap_writepage+0x9c/0xf0
  pageout+0x33e/0xae0
  shrink_page_list+0x1f57/0x2870
  shrink_inactive_list+0x316/0x880
  shrink_lruvec+0x8dc/0x1380
  shrink_node+0x317/0xd80
  do_try_to_free_pages+0x1f7/0xa10
  try_to_free_pages+0x26c/0x5e0
  __alloc_pages_slowpath+0x458/0x1290
  <snip>

 read to 0xffffffffa937638c of 4 bytes by interrupt on cpu 64:
  mempool_free+0x3e/0x150
  mempool_free at mm/mempool.c:492
  bio_free+0x192/0x280
  bio_put+0x91/0xd0
  end_swap_bio_write+0x1d8/0x280
  bio_endio+0x2c2/0x5b0
  dec_pending+0x22b/0x440 [dm_mod]
  clone_endio+0xe4/0x2c0 [dm_mod]
  bio_endio+0x2c2/0x5b0
  blk_update_request+0x217/0x940
  scsi_end_request+0x6b/0x4d0
  scsi_io_completion+0xb7/0x7e0
  scsi_finish_command+0x223/0x310
  scsi_softirq_done+0x1d5/0x210
  blk_mq_complete_request+0x224/0x250
  scsi_mq_done+0xc2/0x250
  pqi_raid_io_complete+0x5a/0x70 [smartpqi]
  pqi_irq_handler+0x150/0x1410 [smartpqi]
  __handle_irq_event_percpu+0x90/0x540
  handle_irq_event_percpu+0x49/0xd0
  handle_irq_event+0x85/0xca
  handle_edge_irq+0x13f/0x3e0
  do_IRQ+0x86/0x190
  <snip>

Since the write is under pool->lock but the read is done as lockless.
Even though the commit 5b990546e3 ("mempool: fix and document
synchronization and memory barrier usage") introduced the smp_wmb() and
smp_rmb() pair to improve the situation, it is adequate to protect it
from data races which could lead to a logic bug, so fix it by adding
READ_ONCE() for the read.

Signed-off-by: Qian Cai <cai@lca.pw>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Marco Elver <elver@google.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Link: http://lkml.kernel.org/r/1581446384-2131-1-git-send-email-cai@lca.pw
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-08-14 19:56:57 -07:00

558 lines
16 KiB
C

// SPDX-License-Identifier: GPL-2.0
/*
* 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 __always_inline void kasan_poison_element(mempool_t *pool, void *element)
{
if (pool->alloc == mempool_alloc_slab || pool->alloc == mempool_kmalloc)
kasan_poison_kfree(element, _RET_IP_);
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)
{
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 __always_inline 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)
{
void *element = pool->elements[--pool->curr_nr];
BUG_ON(pool->curr_nr < 0);
kasan_unpoison_element(pool, element);
check_element(pool, element);
return element;
}
/**
* mempool_exit - exit a mempool initialized with mempool_init()
* @pool: pointer to the memory pool which was initialized with
* mempool_init().
*
* Free all reserved elements in @pool and @pool itself. This function
* only sleeps if the free_fn() function sleeps.
*
* May be called on a zeroed but uninitialized mempool (i.e. allocated with
* kzalloc()).
*/
void mempool_exit(mempool_t *pool)
{
while (pool->curr_nr) {
void *element = remove_element(pool);
pool->free(element, pool->pool_data);
}
kfree(pool->elements);
pool->elements = NULL;
}
EXPORT_SYMBOL(mempool_exit);
/**
* 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;
mempool_exit(pool);
kfree(pool);
}
EXPORT_SYMBOL(mempool_destroy);
int mempool_init_node(mempool_t *pool, int min_nr, mempool_alloc_t *alloc_fn,
mempool_free_t *free_fn, void *pool_data,
gfp_t gfp_mask, int node_id)
{
spin_lock_init(&pool->lock);
pool->min_nr = min_nr;
pool->pool_data = pool_data;
pool->alloc = alloc_fn;
pool->free = free_fn;
init_waitqueue_head(&pool->wait);
pool->elements = kmalloc_array_node(min_nr, sizeof(void *),
gfp_mask, node_id);
if (!pool->elements)
return -ENOMEM;
/*
* 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_exit(pool);
return -ENOMEM;
}
add_element(pool, element);
}
return 0;
}
EXPORT_SYMBOL(mempool_init_node);
/**
* mempool_init - initialize a memory pool
* @pool: pointer to the memory pool that should be initialized
* @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.
*
* Like mempool_create(), but initializes the pool in (i.e. embedded in another
* structure).
*
* Return: %0 on success, negative error code otherwise.
*/
int mempool_init(mempool_t *pool, int min_nr, mempool_alloc_t *alloc_fn,
mempool_free_t *free_fn, void *pool_data)
{
return mempool_init_node(pool, min_nr, alloc_fn, free_fn,
pool_data, GFP_KERNEL, NUMA_NO_NODE);
}
EXPORT_SYMBOL(mempool_init);
/**
* 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.
*
* Return: pointer to the created memory pool object or %NULL on error.
*/
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;
if (mempool_init_node(pool, min_nr, alloc_fn, free_fn, pool_data,
gfp_mask, node_id)) {
kfree(pool);
return NULL;
}
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.
*
* Return: %0 on success, negative error code otherwise.
*/
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);
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.
*
* Return: pointer to the allocated element or %NULL on error.
*/
void *mempool_alloc(mempool_t *pool, gfp_t gfp_mask)
{
void *element;
unsigned long flags;
wait_queue_entry_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);
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(READ_ONCE(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);