mirror of
https://github.com/torvalds/linux.git
synced 2026-05-23 14:42:08 +02:00
mm/mempolicy: fix a race between offset_il_node and mpol_rebind_task
Servers happened below panic:
Kernel version:5.4.56
BUG: unable to handle page fault for address: 0000000000002c48
RIP: 0010:__next_zones_zonelist+0x1d/0x40
Call Trace:
__alloc_pages_nodemask+0x277/0x310
alloc_page_interleave+0x13/0x70
handle_mm_fault+0xf99/0x1390
__do_page_fault+0x288/0x500
do_page_fault+0x30/0x110
page_fault+0x3e/0x50
The reason for the panic is that MAX_NUMNODES is passed in the third
parameter in __alloc_pages_nodemask(preferred_nid). So access to
zonelist->zoneref->zone_idx in __next_zones_zonelist will cause a panic.
In offset_il_node(), first_node() returns nid from pol->v.nodes, after
this other threads may chang pol->v.nodes before next_node(). This race
condition will let next_node return MAX_NUMNODES. So put pol->nodes in
a local variable.
The race condition is between offset_il_node and cpuset_change_task_nodemask:
CPU0: CPU1:
alloc_pages_vma()
interleave_nid(pol,)
offset_il_node(pol,)
first_node(pol->v.nodes) cpuset_change_task_nodemask
//nodes==0xc mpol_rebind_task
mpol_rebind_policy
mpol_rebind_nodemask(pol,nodes)
//nodes==0x3
next_node(nid, pol->v.nodes)//return MAX_NUMNODES
Link: https://lkml.kernel.org/r/20210906034658.48721-1-yanghui.def@bytedance.com
Signed-off-by: yanghui <yanghui.def@bytedance.com>
Reviewed-by: Muchun Song <songmuchun@bytedance.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This commit is contained in:
parent
79d3705040
commit
276aeee1c5
|
|
@ -1979,17 +1979,26 @@ unsigned int mempolicy_slab_node(void)
|
|||
*/
|
||||
static unsigned offset_il_node(struct mempolicy *pol, unsigned long n)
|
||||
{
|
||||
unsigned nnodes = nodes_weight(pol->nodes);
|
||||
unsigned target;
|
||||
nodemask_t nodemask = pol->nodes;
|
||||
unsigned int target, nnodes;
|
||||
int i;
|
||||
int nid;
|
||||
/*
|
||||
* The barrier will stabilize the nodemask in a register or on
|
||||
* the stack so that it will stop changing under the code.
|
||||
*
|
||||
* Between first_node() and next_node(), pol->nodes could be changed
|
||||
* by other threads. So we put pol->nodes in a local stack.
|
||||
*/
|
||||
barrier();
|
||||
|
||||
nnodes = nodes_weight(nodemask);
|
||||
if (!nnodes)
|
||||
return numa_node_id();
|
||||
target = (unsigned int)n % nnodes;
|
||||
nid = first_node(pol->nodes);
|
||||
nid = first_node(nodemask);
|
||||
for (i = 0; i < target; i++)
|
||||
nid = next_node(nid, pol->nodes);
|
||||
nid = next_node(nid, nodemask);
|
||||
return nid;
|
||||
}
|
||||
|
||||
|
|
|
|||
Loading…
Reference in New Issue
Block a user