From dc6c9a35b66b520cf67e05d8ca60ebecad3b0479 Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Date: Wed, 11 Feb 2015 15:26:50 -0800
Subject: mm: account pmd page tables to the process

Dave noticed that unprivileged process can allocate significant amount of
memory -- >500 MiB on x86_64 -- and stay unnoticed by oom-killer and
memory cgroup.  The trick is to allocate a lot of PMD page tables.  Linux
kernel doesn't account PMD tables to the process, only PTE.

The use-cases below use few tricks to allocate a lot of PMD page tables
while keeping VmRSS and VmPTE low.  oom_score for the process will be 0.

	#include <errno.h>
	#include <stdio.h>
	#include <stdlib.h>
	#include <unistd.h>
	#include <sys/mman.h>
	#include <sys/prctl.h>

	#define PUD_SIZE (1UL << 30)
	#define PMD_SIZE (1UL << 21)

	#define NR_PUD 130000

	int main(void)
	{
		char *addr = NULL;
		unsigned long i;

		prctl(PR_SET_THP_DISABLE);
		for (i = 0; i < NR_PUD ; i++) {
			addr = mmap(addr + PUD_SIZE, PUD_SIZE, PROT_WRITE|PROT_READ,
					MAP_ANONYMOUS|MAP_PRIVATE, -1, 0);
			if (addr == MAP_FAILED) {
				perror("mmap");
				break;
			}
			*addr = 'x';
			munmap(addr, PMD_SIZE);
			mmap(addr, PMD_SIZE, PROT_WRITE|PROT_READ,
					MAP_ANONYMOUS|MAP_PRIVATE|MAP_FIXED, -1, 0);
			if (addr == MAP_FAILED)
				perror("re-mmap"), exit(1);
		}
		printf("PID %d consumed %lu KiB in PMD page tables\n",
				getpid(), i * 4096 >> 10);
		return pause();
	}

The patch addresses the issue by account PMD tables to the process the
same way we account PTE.

The main place where PMD tables is accounted is __pmd_alloc() and
free_pmd_range(). But there're few corner cases:

 - HugeTLB can share PMD page tables. The patch handles by accounting
   the table to all processes who share it.

 - x86 PAE pre-allocates few PMD tables on fork.

 - Architectures with FIRST_USER_ADDRESS > 0. We need to adjust sanity
   check on exit(2).

Accounting only happens on configuration where PMD page table's level is
present (PMD is not folded).  As with nr_ptes we use per-mm counter.  The
counter value is used to calculate baseline for badness score by
oom-killer.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Reported-by: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Hugh Dickins <hughd@google.com>
Reviewed-by: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: Pavel Emelyanov <xemul@openvz.org>
Cc: David Rientjes <rientjes@google.com>
Tested-by: Sedat Dilek <sedat.dilek@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/debug.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'mm/debug.c')

diff --git a/mm/debug.c b/mm/debug.c
index d69cb5a7ba9a..3eb3ac2fcee7 100644
--- a/mm/debug.c
+++ b/mm/debug.c
@@ -173,7 +173,7 @@ 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 map_count %d\n"
+		"pgd %p mm_users %d mm_count %d nr_ptes %lu nr_pmds %lu map_count %d\n"
 		"hiwater_rss %lx hiwater_vm %lx total_vm %lx locked_vm %lx\n"
 		"pinned_vm %lx shared_vm %lx exec_vm %lx stack_vm %lx\n"
 		"start_code %lx end_code %lx start_data %lx end_data %lx\n"
@@ -206,6 +206,7 @@ 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->map_count,
 		mm->hiwater_rss, mm->hiwater_vm, mm->total_vm, mm->locked_vm,
 		mm->pinned_vm, mm->shared_vm, mm->exec_vm, mm->stack_vm,
-- 
cgit v1.2.3