From cf8cb47d090d31afcd40c35bed9dea03e1e3daa3 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 25 Sep 2020 12:55:38 +0200 Subject: [PATCH] 4.19-stable patches added patches: mm-memcg-fix-memcg-reclaim-soft-lockup.patch --- ...-memcg-fix-memcg-reclaim-soft-lockup.patch | 70 +++++++++++++++++++ queue-4.19/series | 1 + 2 files changed, 71 insertions(+) create mode 100644 queue-4.19/mm-memcg-fix-memcg-reclaim-soft-lockup.patch diff --git a/queue-4.19/mm-memcg-fix-memcg-reclaim-soft-lockup.patch b/queue-4.19/mm-memcg-fix-memcg-reclaim-soft-lockup.patch new file mode 100644 index 00000000000..e509af4400a --- /dev/null +++ b/queue-4.19/mm-memcg-fix-memcg-reclaim-soft-lockup.patch @@ -0,0 +1,70 @@ +From e3336cab2579012b1e72b5265adf98e2d6e244ad Mon Sep 17 00:00:00 2001 +From: Xunlei Pang +Date: Fri, 4 Sep 2020 16:35:27 -0700 +Subject: mm: memcg: fix memcg reclaim soft lockup + +From: Xunlei Pang + +commit e3336cab2579012b1e72b5265adf98e2d6e244ad upstream. + +We've met softlockup with "CONFIG_PREEMPT_NONE=y", when the target memcg +doesn't have any reclaimable memory. + +It can be easily reproduced as below: + + watchdog: BUG: soft lockup - CPU#0 stuck for 111s![memcg_test:2204] + CPU: 0 PID: 2204 Comm: memcg_test Not tainted 5.9.0-rc2+ #12 + Call Trace: + shrink_lruvec+0x49f/0x640 + shrink_node+0x2a6/0x6f0 + do_try_to_free_pages+0xe9/0x3e0 + try_to_free_mem_cgroup_pages+0xef/0x1f0 + try_charge+0x2c1/0x750 + mem_cgroup_charge+0xd7/0x240 + __add_to_page_cache_locked+0x2fd/0x370 + add_to_page_cache_lru+0x4a/0xc0 + pagecache_get_page+0x10b/0x2f0 + filemap_fault+0x661/0xad0 + ext4_filemap_fault+0x2c/0x40 + __do_fault+0x4d/0xf9 + handle_mm_fault+0x1080/0x1790 + +It only happens on our 1-vcpu instances, because there's no chance for +oom reaper to run to reclaim the to-be-killed process. + +Add a cond_resched() at the upper shrink_node_memcgs() to solve this +issue, this will mean that we will get a scheduling point for each memcg +in the reclaimed hierarchy without any dependency on the reclaimable +memory in that memcg thus making it more predictable. + +Suggested-by: Michal Hocko +Signed-off-by: Xunlei Pang +Signed-off-by: Andrew Morton +Acked-by: Chris Down +Acked-by: Michal Hocko +Acked-by: Johannes Weiner +Link: http://lkml.kernel.org/r/1598495549-67324-1-git-send-email-xlpang@linux.alibaba.com +Signed-off-by: Linus Torvalds +Signed-off-by: Julius Hemanth Pitti +Signed-off-by: Greg Kroah-Hartman +--- + mm/vmscan.c | 8 ++++++++ + 1 file changed, 8 insertions(+) + +--- a/mm/vmscan.c ++++ b/mm/vmscan.c +@@ -2708,6 +2708,14 @@ static bool shrink_node(pg_data_t *pgdat + unsigned long reclaimed; + unsigned long scanned; + ++ /* ++ * This loop can become CPU-bound when target memcgs ++ * aren't eligible for reclaim - either because they ++ * don't have any reclaimable pages, or because their ++ * memory is explicitly protected. Avoid soft lockups. ++ */ ++ cond_resched(); ++ + switch (mem_cgroup_protected(root, memcg)) { + case MEMCG_PROT_MIN: + /* diff --git a/queue-4.19/series b/queue-4.19/series index 86580339943..c8db4a844f7 100644 --- a/queue-4.19/series +++ b/queue-4.19/series @@ -31,3 +31,4 @@ x86-boot-kbuild-allow-readelf-executable-to-be-specified.patch kbuild-remove-as-variable.patch kbuild-replace-as-clang-with-llvm_ias-1.patch kbuild-support-llvm-1-to-switch-the-default-tools-to-clang-llvm.patch +mm-memcg-fix-memcg-reclaim-soft-lockup.patch -- 2.47.3