mm: account pud page tables

On a machine with 5-level paging support a process can allocate
significant amount of memory and stay unnoticed by oom-killer and memory
cgroup.  The trick is to allocate a lot of PUD page tables.  We don't
account PUD page tables, only PMD and PTE.

We already addressed the same issue for PMD page tables, see commit
dc6c9a35b66b ("mm: account pmd page tables to the process").
Introduction of 5-level paging brings the same issue for PUD page
tables.

The patch expands accounting to PUD level.

[kirill.shutemov@linux.intel.com: s/pmd_t/pud_t/]
  Link: http://lkml.kernel.org/r/20171004074305.x35eh5u7ybbt5kar@black.fi.intel.com
[heiko.carstens@de.ibm.com: s390/mm: fix pud table accounting]
  Link: http://lkml.kernel.org/r/20171103090551.18231-1-heiko.carstens@de.ibm.com
Link: http://lkml.kernel.org/r/20171002080427.3320-1-kirill.shutemov@linux.intel.com
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Acked-by: Rik van Riel <riel@redhat.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 18 insertions, 11 deletions

diff --git a/mm/debug.c b/mm/debug.c
index 6726bec731c9..a12d826bb774 100644
--- a/mm/debug.c
+++ b/mm/debug.c
@@ -105,7 +105,8 @@ void dump_mm(const struct mm_struct *mm)
 		"get_unmapped_area %p\n"
 #endif
 		"mmap_base %lu mmap_legacy_base %lu highest_vm_end %lu\n"
-		"pgd %p mm_users %d mm_count %d nr_ptes %lu nr_pmds %lu map_count %d\n"
+		"pgd %p mm_users %d mm_count %d\n"
+		"nr_ptes %lu nr_pmds %lu nr_puds %lu map_count %d\n"
 		"hiwater_rss %lx hiwater_vm %lx total_vm %lx locked_vm %lx\n"
 		"pinned_vm %lx data_vm %lx exec_vm %lx stack_vm %lx\n"
 		"start_code %lx end_code %lx start_data %lx end_data %lx\n"
@@ -136,7 +137,8 @@ void dump_mm(const struct mm_struct *mm)
 		mm->pgd, atomic_read(&mm->mm_users),
 		atomic_read(&mm->mm_count),
 		atomic_long_read((atomic_long_t *)&mm->nr_ptes),
-		mm_nr_pmds((struct mm_struct *)mm),
+		mm_nr_pmds(mm),
+		mm_nr_puds(mm),
 		mm->map_count,
 		mm->hiwater_rss, mm->hiwater_vm, mm->total_vm, mm->locked_vm,
 		mm->pinned_vm, mm->data_vm, mm->exec_vm, mm->stack_vm,
diff --git a/mm/memory.c b/mm/memory.c
index 42fb30300bb5..6bbd4078ec98 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -506,6 +506,7 @@ static inline void free_pud_range(struct mmu_gather *tlb, p4d_t *p4d,
 	pud = pud_offset(p4d, start);
 	p4d_clear(p4d);
 	pud_free_tlb(tlb, pud, start);
+	mm_dec_nr_puds(tlb->mm);
 }
 
 static inline void free_p4d_range(struct mmu_gather *tlb, pgd_t *pgd,
@@ -4149,15 +4150,17 @@ int __pud_alloc(struct mm_struct *mm, p4d_t *p4d, unsigned long address)
 
 	spin_lock(&mm->page_table_lock);
 #ifndef __ARCH_HAS_5LEVEL_HACK
-	if (p4d_present(*p4d))		/* Another has populated it */
-		pud_free(mm, new);
-	else
+	if (!p4d_present(*p4d)) {
+		mm_inc_nr_puds(mm);
 		p4d_populate(mm, p4d, new);
-#else
-	if (pgd_present(*p4d))		/* Another has populated it */
+	} else	/* Another has populated it */
 		pud_free(mm, new);
-	else
+#else
+	if (!pgd_present(*p4d)) {
+		mm_inc_nr_puds(mm);
 		pgd_populate(mm, p4d, new);
+	} else	/* Another has populated it */
+		pud_free(mm, new);
 #endif /* __ARCH_HAS_5LEVEL_HACK */
 	spin_unlock(&mm->page_table_lock);
 	return 0;
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 3023919970f7..f642a45b7f14 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -221,7 +221,8 @@ unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg,
 	 * task's rss, pagetable and swap space use.
 	 */
 	points = get_mm_rss(p->mm) + get_mm_counter(p->mm, MM_SWAPENTS) +
-		atomic_long_read(&p->mm->nr_ptes) + mm_nr_pmds(p->mm);
+		atomic_long_read(&p->mm->nr_ptes) + mm_nr_pmds(p->mm) +
+		mm_nr_puds(p->mm);
 	task_unlock(p);
 
 	/*
@@ -397,7 +398,7 @@ static void dump_tasks(struct mem_cgroup *memcg, const nodemask_t *nodemask)
 	struct task_struct *p;
 	struct task_struct *task;
 
-	pr_info("[ pid ]   uid  tgid total_vm      rss nr_ptes nr_pmds swapents oom_score_adj name\n");
+	pr_info("[ pid ]   uid  tgid total_vm      rss nr_ptes nr_pmds nr_puds swapents oom_score_adj name\n");
 	rcu_read_lock();
 	for_each_process(p) {
 		if (oom_unkillable_task(p, memcg, nodemask))
@@ -413,11 +414,12 @@ static void dump_tasks(struct mem_cgroup *memcg, const nodemask_t *nodemask)
 			continue;
 		}
 
-		pr_info("[%5d] %5d %5d %8lu %8lu %7ld %7ld %8lu         %5hd %s\n",
+		pr_info("[%5d] %5d %5d %8lu %8lu %7ld %7ld %7ld %8lu         %5hd %s\n",
 			task->pid, from_kuid(&init_user_ns, task_uid(task)),
 			task->tgid, task->mm->total_vm, get_mm_rss(task->mm),
 			atomic_long_read(&task->mm->nr_ptes),
 			mm_nr_pmds(task->mm),
+			mm_nr_puds(task->mm),
 			get_mm_counter(task->mm, MM_SWAPENTS),
 			task->signal->oom_score_adj, task->comm);
 		task_unlock(task);