mirrors
/
linux-stable
mirror of https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
1
0
Fork 0
Code Issues Releases Wiki Activity

mm/huge_memory: prevent THP_ZERO_PAGE_ALLOC increased twice 

A user who reads THP_ZERO_PAGE_ALLOC may be more concerned about the huge
zero pages that are really allocated for thp.  It is misleading to
increase THP_ZERO_PAGE_ALLOC twice if two threads call get_huge_zero_page
concurrently.  Don't increase the value if the huge page is not really
used.

Update Documentation/admin-guide/mm/transhuge.rst to suit.

Link: https://lkml.kernel.org/r/20220909021653.3371879-1-liushixin2@huawei.com
Signed-off-by: Liu Shixin <liushixin2@huawei.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
This commit is contained in:
Liu Shixin 2022-09-09 10:16:53 +08:00 committed by Andrew Morton
parent 13cc378403
commit f498150208
2 changed files with 4 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
Documentation/admin-guide/mm/transhuge.rst
View File

@ -366,10 +366,9 @@ thp_split_pmd
page table entry.
thp_zero_page_alloc
is incremented every time a huge zero page is
successfully allocated. It includes allocations which where
dropped due race with other allocation. Note, it doesn't count
every map of the huge zero page, only its allocation.
is incremented every time a huge zero page used for thp is
successfully allocated. Note, it doesn't count every map of
the huge zero page, only its allocation.
thp_zero_page_alloc_failed
is incremented if kernel fails to allocate

2
mm/huge_memory.c
View File

@ -163,7 +163,6 @@ retry:
count_vm_event(THP_ZERO_PAGE_ALLOC_FAILED);
return false;
}
count_vm_event(THP_ZERO_PAGE_ALLOC);
preempt_disable();
if (cmpxchg(&huge_zero_page, NULL, zero_page)) {
preempt_enable();
@ -175,6 +174,7 @@ retry:
/* We take additional reference here. It will be put back by shrinker */
atomic_set(&huge_zero_refcount, 2);
preempt_enable();
count_vm_event(THP_ZERO_PAGE_ALLOC);
return true;
}