From dc6c9a35b66b520cf67e05d8ca60ebecad3b0479 Mon Sep 17 00:00:00 2001
From: Kirill A. Shutemov
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/memory.c | 15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)

(limited to 'mm/memory.c')

diff --git a/mm/memory.c b/mm/memory.c
index d63849b5188f..bbe6a73a899d 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -428,6 +428,7 @@ static inline void free_pmd_range(struct mmu_gather *tlb, pud_t *pud,
 	pmd = pmd_offset(pud, start);
 	pud_clear(pud);
 	pmd_free_tlb(tlb, pmd, start);
+	mm_dec_nr_pmds(tlb->mm);
 }
 
 static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd,
@@ -3322,15 +3323,17 @@ int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address)
 
 	spin_lock(&mm->page_table_lock);
 #ifndef __ARCH_HAS_4LEVEL_HACK
-	if (pud_present(*pud))		/* Another has populated it */
-		pmd_free(mm, new);
-	else
+	if (!pud_present(*pud)) {
+		mm_inc_nr_pmds(mm);
 		pud_populate(mm, pud, new);
-#else
-	if (pgd_present(*pud))		/* Another has populated it */
+	} else	/* Another has populated it */
 		pmd_free(mm, new);
-	else
+#else
+	if (!pgd_present(*pud)) {
+		mm_inc_nr_pmds(mm);
 		pgd_populate(mm, pud, new);
+	} else /* Another has populated it */
+		pmd_free(mm, new);
 #endif /* __ARCH_HAS_4LEVEL_HACK */
 	spin_unlock(&mm->page_table_lock);
 	return 0;
-- 
cgit v1.2.3-55-g7522