mm: consolidate page table accounting

Currently, we account page tables separately for each page table level,
but that's redundant -- we only make use of total memory allocated to
page tables for oom_badness calculation.  We also provide the
information to userspace, but it has dubious value there too.

This patch switches page table accounting to single counter.

mm->pgtables_bytes is now used to account all page table levels.  We use
bytes, because page table size for different levels of page table tree
may be different.

The change has user-visible effect: we don't have VmPMD and VmPUD
reported in /proc/[pid]/status.  Not sure if anybody uses them.  (As
alternative, we can always report 0 kB for them.)

OOM-killer report is also slightly changed: we now report pgtables_bytes
instead of nr_ptes, nr_pmd, nr_puds.

Apart from reducing number of counters per-mm, the benefit is that we
now calculate oom_badness() more correctly for machines which have
different size of page tables depending on level or where page tables
are less than a page in size.

The only downside can be debuggability because we do not know which page
table level could leak.  But I do not remember many bugs that would be
caught by separate counters so I wouldn't lose sleep over this.

[akpm@linux-foundation.org: fix mm/huge_memory.c]
Link: http://lkml.kernel.org/r/20171006100651.44742-2-kirill.shutemov@linux.intel.com
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Michal Hocko <mhocko@suse.com>
[kirill.shutemov@linux.intel.com: fix build]
  Link: http://lkml.kernel.org/r/20171016150113.ikfxy3e7zzfvsr4w@black.fi.intel.com
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 13 insertions, 53 deletions

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 2ca799f0d762..7c1e82a1aa77 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1605,37 +1605,20 @@ static inline int __pud_alloc(struct mm_struct *mm, p4d_t *p4d,
 {
 	return 0;
 }
-
-static inline unsigned long mm_nr_puds(const struct mm_struct *mm)
-{
-	return 0;
-}
-
-static inline void mm_nr_puds_init(struct mm_struct *mm) {}
 static inline void mm_inc_nr_puds(struct mm_struct *mm) {}
 static inline void mm_dec_nr_puds(struct mm_struct *mm) {}
 
 #else
 int __pud_alloc(struct mm_struct *mm, p4d_t *p4d, unsigned long address);
 
-static inline void mm_nr_puds_init(struct mm_struct *mm)
-{
-	atomic_long_set(&mm->nr_puds, 0);
-}
-
-static inline unsigned long mm_nr_puds(const struct mm_struct *mm)
-{
-	return atomic_long_read(&mm->nr_puds);
-}
-
 static inline void mm_inc_nr_puds(struct mm_struct *mm)
 {
-	atomic_long_inc(&mm->nr_puds);
+	atomic_long_add(PTRS_PER_PUD * sizeof(pud_t), &mm->pgtables_bytes);
 }
 
 static inline void mm_dec_nr_puds(struct mm_struct *mm)
 {
-	atomic_long_dec(&mm->nr_puds);
+	atomic_long_sub(PTRS_PER_PUD * sizeof(pud_t), &mm->pgtables_bytes);
 }
 #endif
 
@@ -1646,64 +1629,47 @@ static inline int __pmd_alloc(struct mm_struct *mm, pud_t *pud,
 	return 0;
 }
 
-static inline void mm_nr_pmds_init(struct mm_struct *mm) {}
-
-static inline unsigned long mm_nr_pmds(const struct mm_struct *mm)
-{
-	return 0;
-}
-
 static inline void mm_inc_nr_pmds(struct mm_struct *mm) {}
 static inline void mm_dec_nr_pmds(struct mm_struct *mm) {}
 
 #else
 int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address);
 
-static inline void mm_nr_pmds_init(struct mm_struct *mm)
-{
-	atomic_long_set(&mm->nr_pmds, 0);
-}
-
-static inline unsigned long mm_nr_pmds(const struct mm_struct *mm)
-{
-	return atomic_long_read(&mm->nr_pmds);
-}
-
 static inline void mm_inc_nr_pmds(struct mm_struct *mm)
 {
-	atomic_long_inc(&mm->nr_pmds);
+	atomic_long_add(PTRS_PER_PMD * sizeof(pmd_t), &mm->pgtables_bytes);
 }
 
 static inline void mm_dec_nr_pmds(struct mm_struct *mm)
 {
-	atomic_long_dec(&mm->nr_pmds);
+	atomic_long_sub(PTRS_PER_PMD * sizeof(pmd_t), &mm->pgtables_bytes);
 }
 #endif
 
 #ifdef CONFIG_MMU
-static inline void mm_nr_ptes_init(struct mm_struct *mm)
+static inline void mm_pgtables_bytes_init(struct mm_struct *mm)
 {
-	atomic_long_set(&mm->nr_ptes, 0);
+	atomic_long_set(&mm->pgtables_bytes, 0);
 }
 
-static inline unsigned long mm_nr_ptes(const struct mm_struct *mm)
+static inline unsigned long mm_pgtables_bytes(const struct mm_struct *mm)
 {
-	return atomic_long_read(&mm->nr_ptes);
+	return atomic_long_read(&mm->pgtables_bytes);
 }
 
 static inline void mm_inc_nr_ptes(struct mm_struct *mm)
 {
-	atomic_long_inc(&mm->nr_ptes);
+	atomic_long_add(PTRS_PER_PTE * sizeof(pte_t), &mm->pgtables_bytes);
 }
 
 static inline void mm_dec_nr_ptes(struct mm_struct *mm)
 {
-	atomic_long_dec(&mm->nr_ptes);
+	atomic_long_sub(PTRS_PER_PTE * sizeof(pte_t), &mm->pgtables_bytes);
 }
 #else
-static inline void mm_nr_ptes_init(struct mm_struct *mm) {}
 
-static inline unsigned long mm_nr_ptes(const struct mm_struct *mm)
+static inline void mm_pgtables_bytes_init(struct mm_struct *mm) {}
+static inline unsigned long mm_pgtables_bytes(const struct mm_struct *mm)
 {
 	return 0;
 }
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index e42048020664..09643e0472fc 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -402,13 +402,7 @@ struct mm_struct {
 	atomic_t mm_count;
 
 #ifdef CONFIG_MMU
-	atomic_long_t nr_ptes;			/* PTE page table pages */
-#endif
-#if CONFIG_PGTABLE_LEVELS > 2
-	atomic_long_t nr_pmds;			/* PMD page table pages */
-#endif
-#if CONFIG_PGTABLE_LEVELS > 3
-	atomic_long_t nr_puds;			/* PUD page table pages */
+	atomic_long_t pgtables_bytes;		/* PTE page table pages */
 #endif
 	int map_count;				/* number of VMAs */