mm: memcontrol: expose THP events on a per-memcg basis

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>

diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
index 7bf3f12..53d3288 100644 (file)
--- a/Documentation/admin-guide/cgroup-v2.rst
+++ b/Documentation/admin-guide/cgroup-v2.rst
@@ -1189,6 +1189,10 @@ 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
@@ -1248,6 +1252,18 @@ 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 af07527..d484702 100644 (file)
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -617,6 +617,7 @@ 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;
@@ -1338,6 +1339,7 @@ alloc:
        }
 
        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 4f01733..4490443 100644 (file)
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -1074,6 +1074,7 @@ 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);
@@ -1502,6 +1503,7 @@ xa_unlocked:
                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 1eca627..30bda8d 100644 (file)
--- 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>
@@ -5571,6 +5572,15 @@ 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);
@@ -5602,6 +5612,12 @@ static int memory_stat_show(struct seq_file *m, void *v)
        seq_printf(m, "pglazyfree %lu\n", acc.events[PGLAZYFREE]);
        seq_printf(m, "pglazyfreed %lu\n", acc.events[PGLAZYFREED]);
 
+#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;
 }