From: Chris Down chris@chrisdown.name
mainline inclusion from mainline-5.1-rc1 commit 1ff9e6e1798c7670ea6a7680a1ad5582df2fa914 category: bugfix bugzilla: 34611 CVE: NA
-------------------------------------------------
Currently THP allocation events data is fairly opaque, since you can only get it system-wide. This patch makes it easier to reason about transparent hugepage behaviour on a per-memcg basis.
For anonymous THP-backed pages, we already have MEMCG_RSS_HUGE in v1, which is used for v1's rss_huge [sic]. This is reused here as it's fairly involved to untangle NR_ANON_THPS right now to make it per-memcg, since right now some of this is delegated to rmap before we have any memcg actually assigned to the page. It's a good idea to rework that, but let's leave untangling THP allocation for a future patch.
[akpm@linux-foundation.org: fix build] [chris@chrisdown.name: fix memcontrol build when THP is disabled] Link: http://lkml.kernel.org/r/20190131160802.GA5777@chrisdown.name Link: http://lkml.kernel.org/r/20190129205852.GA7310@chrisdown.name Signed-off-by: Chris Down chris@chrisdown.name Acked-by: Johannes Weiner hannes@cmpxchg.org Cc: Tejun Heo tj@kernel.org Cc: Roman Gushchin guro@fb.com Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org (cherry picked from commit 1ff9e6e1798c7670ea6a7680a1ad5582df2fa914) Signed-off-by: Kefeng Wang wangkefeng.wang@huawei.com
Conflicts: mm/memcontrol.c
Signed-off-by: Liu Shixin liushixin2@huawei.com Reviewed-by: Kefeng Wang wangkefeng.wang@huawei.com Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- Documentation/admin-guide/cgroup-v2.rst | 16 ++++++++++++++++ mm/huge_memory.c | 2 ++ mm/khugepaged.c | 2 ++ mm/memcontrol.c | 16 ++++++++++++++++ 4 files changed, 36 insertions(+)
diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index 4194ea1d756f..8305db50fa04 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -1183,6 +1183,10 @@ PAGE_SIZE multiple when read back. Amount of cached filesystem data that was modified and is currently being written back to disk
+ anon_thp + Amount of memory used in anonymous mappings backed by + transparent hugepages + inactive_anon, active_anon, inactive_file, active_file, unevictable Amount of memory, swap-backed and filesystem-backed, on the internal memory management lists used by the @@ -1242,6 +1246,18 @@ PAGE_SIZE multiple when read back.
Amount of reclaimed lazyfree pages
+ thp_fault_alloc + + Number of transparent hugepages which were allocated to satisfy + a page fault, including COW faults. This counter is not present + when CONFIG_TRANSPARENT_HUGEPAGE is not set. + + thp_collapse_alloc + + Number of transparent hugepages which were allocated to allow + collapsing an existing range of pages. This counter is not + present when CONFIG_TRANSPARENT_HUGEPAGE is not set. + memory.swap.current A read-only single value file which exists on non-root cgroups. diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 6aef386c1726..d6ad1132ee70 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -619,6 +619,7 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf, mm_inc_nr_ptes(vma->vm_mm); spin_unlock(vmf->ptl); count_vm_event(THP_FAULT_ALLOC); + count_memcg_events(memcg, THP_FAULT_ALLOC, 1); }
return 0; @@ -1378,6 +1379,7 @@ vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf, pmd_t orig_pmd) }
count_vm_event(THP_FAULT_ALLOC); + count_memcg_events(memcg, THP_FAULT_ALLOC, 1);
if (!page) clear_huge_page(new_page, vmf->address, HPAGE_PMD_NR); diff --git a/mm/khugepaged.c b/mm/khugepaged.c index f37be43f8cae..b75afe6f6063 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1076,6 +1076,7 @@ static void collapse_huge_page(struct mm_struct *mm, BUG_ON(!pmd_none(*pmd)); page_add_new_anon_rmap(new_page, vma, address, true); mem_cgroup_commit_charge(new_page, memcg, false, true); + count_memcg_events(memcg, THP_COLLAPSE_ALLOC, 1); lru_cache_add_active_or_unevictable(new_page, vma); pgtable_trans_huge_deposit(mm, pmd, pgtable); set_pmd_at(mm, address, pmd, _pmd); @@ -1531,6 +1532,7 @@ static void collapse_shmem(struct mm_struct *mm, page_ref_add(new_page, HPAGE_PMD_NR - 1); set_page_dirty(new_page); mem_cgroup_commit_charge(new_page, memcg, false, true); + count_memcg_events(memcg, THP_COLLAPSE_ALLOC, 1); lru_cache_add_anon(new_page);
/* diff --git a/mm/memcontrol.c b/mm/memcontrol.c index fb473b4738b1..9ad251d3f13f 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -39,6 +39,7 @@ #include <linux/shmem_fs.h> #include <linux/hugetlb.h> #include <linux/pagemap.h> +#include <linux/vm_event_item.h> #include <linux/smp.h> #include <linux/page-flags.h> #include <linux/backing-dev.h> @@ -5731,6 +5732,15 @@ static int memory_stat_show(struct seq_file *m, void *v) seq_printf(m, "file_writeback %llu\n", (u64)acc.stat[NR_WRITEBACK] * PAGE_SIZE);
+ /* + * TODO: We should eventually replace our own MEMCG_RSS_HUGE counter + * with the NR_ANON_THP vm counter, but right now it's a pain in the + * arse because it requires migrating the work out of rmap to a place + * where the page->mem_cgroup is set up and stable. + */ + seq_printf(m, "anon_thp %llu\n", + (u64)acc.stat[MEMCG_RSS_HUGE] * PAGE_SIZE); + for (i = 0; i < NR_LRU_LISTS; i++) seq_printf(m, "%s %llu\n", mem_cgroup_lru_names[i], (u64)acc.lru_pages[i] * PAGE_SIZE); @@ -5762,6 +5772,12 @@ static int memory_stat_show(struct seq_file *m, void *v) seq_printf(m, "workingset_nodereclaim %lu\n", acc.stat[WORKINGSET_NODERECLAIM]);
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE + seq_printf(m, "thp_fault_alloc %lu\n", acc.events[THP_FAULT_ALLOC]); + seq_printf(m, "thp_collapse_alloc %lu\n", + acc.events[THP_COLLAPSE_ALLOC]); +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + return 0; }