Minki/linux
1
0
Fork 1
mirror of https://github.com/torvalds/linux.git synced 2024-11-22 12:11:40 +00:00
Code Issues Packages Projects Releases Wiki Activity

percpu: fix synchronization between synchronous map extension and chunk destruction

Browse Source 
For non-atomic allocations, pcpu_alloc() can try to extend the area
map synchronously after dropping pcpu_lock; however, the extension
wasn't synchronized against chunk destruction and the chunk might get
freed while extension is in progress.

This patch fixes the bug by putting most of non-atomic allocations
under pcpu_alloc_mutex to synchronize against pcpu_balance_work which
is responsible for async chunk management including destruction.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reported-and-tested-by: Alexei Starovoitov <alexei.starovoitov@gmail.com>
Reported-by: Vlastimil Babka <vbabka@suse.cz>
Reported-by: Sasha Levin <sasha.levin@oracle.com>
Cc: stable@vger.kernel.org # v3.18+
Fixes: 1a4d76076c ("percpu: implement asynchronous chunk population")
This commit is contained in:
Tejun Heo 2016-05-25 11:48:25 -04:00
parent 4f996e234d
commit 6710e594f7
1 changed files with 8 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
mm/percpu.c
View File

@ -162,7 +162,7 @@ static struct pcpu_chunk *pcpu_reserved_chunk;
static int pcpu_reserved_chunk_limit; static int pcpu_reserved_chunk_limit;
static DEFINE_SPINLOCK(pcpu_lock); /* all internal data structures */ static DEFINE_SPINLOCK(pcpu_lock); /* all internal data structures */
static DEFINE_MUTEX(pcpu_alloc_mutex); /* chunk create/destroy, [de]pop */ static DEFINE_MUTEX(pcpu_alloc_mutex); /* chunk create/destroy, [de]pop, map ext */
static struct list_head *pcpu_slot __read_mostly; /* chunk list slots */ static struct list_head *pcpu_slot __read_mostly; /* chunk list slots */
@ -444,6 +444,8 @@ static int pcpu_extend_area_map(struct pcpu_chunk *chunk, int new_alloc)
size_t old_size = 0, new_size = new_alloc * sizeof(new[0]); size_t old_size = 0, new_size = new_alloc * sizeof(new[0]);
unsigned long flags; unsigned long flags;
lockdep_assert_held(&pcpu_alloc_mutex);
new = pcpu_mem_zalloc(new_size); new = pcpu_mem_zalloc(new_size);
if (!new) if (!new)
return -ENOMEM; return -ENOMEM;
@ -890,6 +892,9 @@ static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved,
return NULL; return NULL;
} }
if (!is_atomic)
mutex_lock(&pcpu_alloc_mutex);
spin_lock_irqsave(&pcpu_lock, flags); spin_lock_irqsave(&pcpu_lock, flags);
/* serve reserved allocations from the reserved chunk if available */ /* serve reserved allocations from the reserved chunk if available */
@ -962,12 +967,9 @@ restart:
if (is_atomic) if (is_atomic)
goto fail; goto fail;
mutex_lock(&pcpu_alloc_mutex);
if (list_empty(&pcpu_slot[pcpu_nr_slots - 1])) { if (list_empty(&pcpu_slot[pcpu_nr_slots - 1])) {
chunk = pcpu_create_chunk(); chunk = pcpu_create_chunk();
if (!chunk) { if (!chunk) {
mutex_unlock(&pcpu_alloc_mutex);
err = "failed to allocate new chunk"; err = "failed to allocate new chunk";
goto fail; goto fail;
} }
@ -978,7 +980,6 @@ restart:
spin_lock_irqsave(&pcpu_lock, flags); spin_lock_irqsave(&pcpu_lock, flags);
} }
mutex_unlock(&pcpu_alloc_mutex);
goto restart; goto restart;
area_found: area_found:
@ -988,8 +989,6 @@ area_found:
if (!is_atomic) { if (!is_atomic) {
int page_start, page_end, rs, re; int page_start, page_end, rs, re;
mutex_lock(&pcpu_alloc_mutex);
page_start = PFN_DOWN(off); page_start = PFN_DOWN(off);
page_end = PFN_UP(off + size); page_end = PFN_UP(off + size);
@ -1000,7 +999,6 @@ area_found:
spin_lock_irqsave(&pcpu_lock, flags); spin_lock_irqsave(&pcpu_lock, flags);
if (ret) { if (ret) {
mutex_unlock(&pcpu_alloc_mutex);
pcpu_free_area(chunk, off, &occ_pages); pcpu_free_area(chunk, off, &occ_pages);
err = "failed to populate"; err = "failed to populate";
goto fail_unlock; goto fail_unlock;
@ -1040,6 +1038,8 @@ fail:
/* see the flag handling in pcpu_blance_workfn() */ /* see the flag handling in pcpu_blance_workfn() */
pcpu_atomic_alloc_failed = true; pcpu_atomic_alloc_failed = true;
pcpu_schedule_balance_work(); pcpu_schedule_balance_work();
} else {
mutex_unlock(&pcpu_alloc_mutex);
} }
return NULL; return NULL;
} }