From ece369c7e1044a333dc002d3c3c228b8853fc5f7 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Fri, 1 Apr 2022 11:28:27 -0700 Subject: mm/munlock: add lru_add_drain() to fix memcg_stat_test Mike reports that LTP memcg_stat_test usually leads to memcg_stat_test 3 TINFO: Test unevictable with MAP_LOCKED memcg_stat_test 3 TINFO: Running memcg_process --mmap-lock1 -s 135168 memcg_stat_test 3 TINFO: Warming up pid: 3460 memcg_stat_test 3 TINFO: Process is still here after warm up: 3460 memcg_stat_test 3 TFAIL: unevictable is 122880, 135168 expected but may also lead to memcg_stat_test 4 TINFO: Test unevictable with mlock memcg_stat_test 4 TINFO: Running memcg_process --mmap-lock2 -s 135168 memcg_stat_test 4 TINFO: Warming up pid: 4271 memcg_stat_test 4 TINFO: Process is still here after warm up: 4271 memcg_stat_test 4 TFAIL: unevictable is 122880, 135168 expected or both. A wee bit flaky. follow_page_pte() used to have an lru_add_drain() per each page mlocked, and the test came to rely on accurate stats. The pagevec to be drained is different now, but still covered by lru_add_drain(); and, never mind the test, I believe it's in everyone's interest that a bulk faulting interface like populate_vma_page_range() or faultin_vma_page_range() should drain its local pagevecs at the end, to save others sometimes needing the much more expensive lru_add_drain_all(). This does not absolutely guarantee exact stats - the mlocking task can be migrated between CPUs as it proceeds - but it's good enough and the tests pass. Link: https://lkml.kernel.org/r/47f6d39c-a075-50cb-1cfb-26dd957a48af@google.com Fixes: b67bf49ce7aa ("mm/munlock: delete FOLL_MLOCK and FOLL_POPULATE") Signed-off-by: Hugh Dickins Reported-by: Mike Galbraith Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/gup.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'mm') diff --git a/mm/gup.c b/mm/gup.c index 271fbe8195d7..f598a037eb04 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -1404,6 +1404,7 @@ long populate_vma_page_range(struct vm_area_struct *vma, struct mm_struct *mm = vma->vm_mm; unsigned long nr_pages = (end - start) / PAGE_SIZE; int gup_flags; + long ret; VM_BUG_ON(!PAGE_ALIGNED(start)); VM_BUG_ON(!PAGE_ALIGNED(end)); @@ -1438,8 +1439,10 @@ long populate_vma_page_range(struct vm_area_struct *vma, * We made sure addr is within a VMA, so the following will * not result in a stack expansion that recurses back here. */ - return __get_user_pages(mm, start, nr_pages, gup_flags, + ret = __get_user_pages(mm, start, nr_pages, gup_flags, NULL, NULL, locked); + lru_add_drain(); + return ret; } /* @@ -1471,6 +1474,7 @@ long faultin_vma_page_range(struct vm_area_struct *vma, unsigned long start, struct mm_struct *mm = vma->vm_mm; unsigned long nr_pages = (end - start) / PAGE_SIZE; int gup_flags; + long ret; VM_BUG_ON(!PAGE_ALIGNED(start)); VM_BUG_ON(!PAGE_ALIGNED(end)); @@ -1498,8 +1502,10 @@ long faultin_vma_page_range(struct vm_area_struct *vma, unsigned long start, if (check_vma_flags(vma, gup_flags)) return -EINVAL; - return __get_user_pages(mm, start, nr_pages, gup_flags, + ret = __get_user_pages(mm, start, nr_pages, gup_flags, NULL, NULL, locked); + lru_add_drain(); + return ret; } /* -- cgit v1.2.3-59-g8ed1b