#include <linux/vmalloc.h>
#include <linux/workqueue.h>
#include <linux/kmemleak.h>
+#include <linux/sched.h>
#include <asm/cacheflush.h>
#include <asm/sections.h>
/**
* pcpu_mem_zalloc - allocate memory
* @size: bytes to allocate
+ * @gfp: allocation flags
*
* Allocate @size bytes. If @size is smaller than PAGE_SIZE,
- * kzalloc() is used; otherwise, vzalloc() is used. The returned
- * memory is always zeroed.
+ * kzalloc() is used; otherwise, the equivalent of vzalloc() is used.
+ * This is to facilitate passing through whitelisted flags. The
+ * returned memory is always zeroed.
*
* CONTEXT:
* Does GFP_KERNEL allocation.
* RETURNS:
* Pointer to the allocated area on success, NULL on failure.
*/
-static void *pcpu_mem_zalloc(size_t size)
+static void *pcpu_mem_zalloc(size_t size, gfp_t gfp)
{
if (WARN_ON_ONCE(!slab_is_available()))
return NULL;
if (size <= PAGE_SIZE)
- return kzalloc(size, GFP_KERNEL);
+ return kzalloc(size, gfp | GFP_KERNEL);
else
- return vzalloc(size);
+ return __vmalloc(size, gfp | GFP_KERNEL | __GFP_ZERO,
+ PAGE_KERNEL);
}
/**
return chunk;
}
-static struct pcpu_chunk *pcpu_alloc_chunk(void)
+static struct pcpu_chunk *pcpu_alloc_chunk(gfp_t gfp)
{
struct pcpu_chunk *chunk;
int region_bits;
- chunk = pcpu_mem_zalloc(pcpu_chunk_struct_size);
+ chunk = pcpu_mem_zalloc(pcpu_chunk_struct_size, gfp);
if (!chunk)
return NULL;
region_bits = pcpu_chunk_map_bits(chunk);
chunk->alloc_map = pcpu_mem_zalloc(BITS_TO_LONGS(region_bits) *
- sizeof(chunk->alloc_map[0]));
+ sizeof(chunk->alloc_map[0]), gfp);
if (!chunk->alloc_map)
goto alloc_map_fail;
chunk->bound_map = pcpu_mem_zalloc(BITS_TO_LONGS(region_bits + 1) *
- sizeof(chunk->bound_map[0]));
+ sizeof(chunk->bound_map[0]), gfp);
if (!chunk->bound_map)
goto bound_map_fail;
chunk->md_blocks = pcpu_mem_zalloc(pcpu_chunk_nr_blocks(chunk) *
- sizeof(chunk->md_blocks[0]));
+ sizeof(chunk->md_blocks[0]), gfp);
if (!chunk->md_blocks)
goto md_blocks_fail;
{
if (!chunk)
return;
+ pcpu_mem_free(chunk->md_blocks);
pcpu_mem_free(chunk->bound_map);
pcpu_mem_free(chunk->alloc_map);
pcpu_mem_free(chunk);
* pcpu_addr_to_page - translate address to physical address
* pcpu_verify_alloc_info - check alloc_info is acceptable during init
*/
-static int pcpu_populate_chunk(struct pcpu_chunk *chunk, int off, int size);
+static int pcpu_populate_chunk(struct pcpu_chunk *chunk, int off, int size,
+ gfp_t gfp);
static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk, int off, int size);
-static struct pcpu_chunk *pcpu_create_chunk(void);
+static struct pcpu_chunk *pcpu_create_chunk(gfp_t gfp);
static void pcpu_destroy_chunk(struct pcpu_chunk *chunk);
static struct page *pcpu_addr_to_page(void *addr);
static int __init pcpu_verify_alloc_info(const struct pcpu_alloc_info *ai);
* @gfp: allocation flags
*
* Allocate percpu area of @size bytes aligned at @align. If @gfp doesn't
- * contain %GFP_KERNEL, the allocation is atomic.
+ * contain %GFP_KERNEL, the allocation is atomic. If @gfp has __GFP_NOWARN
+ * then no warning will be triggered on invalid or failed allocation
+ * requests.
*
* RETURNS:
* Percpu pointer to the allocated area on success, NULL on failure.
static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved,
gfp_t gfp)
{
+ bool is_atomic = (gfp & GFP_KERNEL) != GFP_KERNEL;
+ bool do_warn = !(gfp & __GFP_NOWARN);
static int warn_limit = 10;
struct pcpu_chunk *chunk;
const char *err;
- bool is_atomic = (gfp & GFP_KERNEL) != GFP_KERNEL;
int slot, off, cpu, ret;
unsigned long flags;
void __percpu *ptr;
if (unlikely(!size || size > PCPU_MIN_UNIT_SIZE || align > PAGE_SIZE ||
!is_power_of_2(align))) {
- WARN(true, "illegal size (%zu) or align (%zu) for percpu allocation\n",
+ WARN(do_warn, "illegal size (%zu) or align (%zu) for percpu allocation\n",
size, align);
return NULL;
}
}
if (list_empty(&pcpu_slot[pcpu_nr_slots - 1])) {
- chunk = pcpu_create_chunk();
+ chunk = pcpu_create_chunk(0);
if (!chunk) {
err = "failed to allocate new chunk";
goto fail;
page_start, page_end) {
WARN_ON(chunk->immutable);
- ret = pcpu_populate_chunk(chunk, rs, re);
+ ret = pcpu_populate_chunk(chunk, rs, re, 0);
spin_lock_irqsave(&pcpu_lock, flags);
if (ret) {
fail:
trace_percpu_alloc_percpu_fail(reserved, is_atomic, size, align);
- if (!is_atomic && warn_limit) {
+ if (!is_atomic && do_warn && warn_limit) {
pr_warn("allocation failed, size=%zu align=%zu atomic=%d, %s\n",
size, align, is_atomic, err);
dump_stack();
*
* Allocate zero-filled percpu area of @size bytes aligned at @align. If
* @gfp doesn't contain %GFP_KERNEL, the allocation doesn't block and can
- * be called from any context but is a lot more likely to fail.
+ * be called from any context but is a lot more likely to fail. If @gfp
+ * has __GFP_NOWARN then no warning will be triggered on invalid or failed
+ * allocation requests.
*
* RETURNS:
* Percpu pointer to the allocated area on success, NULL on failure.
* pcpu_balance_workfn - manage the amount of free chunks and populated pages
* @work: unused
*
- * Reclaim all fully free chunks except for the first one.
+ * Reclaim all fully free chunks except for the first one. This is also
+ * responsible for maintaining the pool of empty populated pages. However,
+ * it is possible that this is called when physical memory is scarce causing
+ * OOM killer to be triggered. We should avoid doing so until an actual
+ * allocation causes the failure as it is possible that requests can be
+ * serviced from already backed regions.
*/
static void pcpu_balance_workfn(struct work_struct *work)
{
+ /* gfp flags passed to underlying allocators */
+ const gfp_t gfp = __GFP_NORETRY | __GFP_NOWARN;
LIST_HEAD(to_free);
struct list_head *free_head = &pcpu_slot[pcpu_nr_slots - 1];
struct pcpu_chunk *chunk, *next;
chunk->nr_pages) {
int nr = min(re - rs, nr_to_pop);
- ret = pcpu_populate_chunk(chunk, rs, rs + nr);
+ ret = pcpu_populate_chunk(chunk, rs, rs + nr, gfp);
if (!ret) {
nr_to_pop -= nr;
spin_lock_irq(&pcpu_lock);
if (nr_to_pop) {
/* ran out of chunks to populate, create a new one and retry */
- chunk = pcpu_create_chunk();
+ chunk = pcpu_create_chunk(gfp);
if (chunk) {
spin_lock_irq(&pcpu_lock);
pcpu_chunk_relocate(chunk, -1);