From: Hugh Dickins <hu...@google.com> commit a66c0410b97c07a5708881198528ce724f7a3226 upstream.
The other pagetable walks in task_mmu.c have a cond_resched() after walking their ptes: add a cond_resched() in gather_pte_stats() too, for reading /proc/<id>/numa_maps. Only pagemap_pmd_range() has a cond_resched() in its (unusually expensive) pmd_trans_huge case: more should probably be added, but leave them unchanged for now. Link: http://lkml.kernel.org/r/alpine.LSU.2.11.1612052157400.13021@eggly.anvils Signed-off-by: Hugh Dickins <hu...@google.com> Acked-by: Michal Hocko <mho...@suse.com> Cc: David Rientjes <rient...@google.com> Cc: Gerald Schaefer <gerald.schae...@de.ibm.com> Signed-off-by: Andrew Morton <a...@linux-foundation.org> Signed-off-by: Linus Torvalds <torva...@linux-foundation.org> Reported-by: Chen si <cici...@alibaba-inc.com> Signed-off-by: Baoyou Xie <baoyou....@aliyun.com> Signed-off-by: Wen Yang <weny...@linux.alibaba.com> Signed-off-by: Zijiang Huang <zijiang....@alibaba-inc.com> Signed-off-by: Greg Kroah-Hartman <gre...@linuxfoundation.org> --- fs/proc/task_mmu.c | 1 + 1 file changed, 1 insertion(+) --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -1609,6 +1609,7 @@ static int gather_pte_stats(pmd_t *pmd, } while (pte++, addr += PAGE_SIZE, addr != end); pte_unmap_unlock(orig_pte, ptl); + cond_resched(); return 0; } #ifdef CONFIG_HUGETLB_PAGE
