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>
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 6fb6927..7b22ada 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -190,7 +190,7 @@
 
 #endif	/* CONFIG_X86_PAE */
 
-static void free_pmds(pmd_t *pmds[])
+static void free_pmds(struct mm_struct *mm, pmd_t *pmds[])
 {
 	int i;
 
@@ -198,10 +198,11 @@
 		if (pmds[i]) {
 			pgtable_pmd_page_dtor(virt_to_page(pmds[i]));
 			free_page((unsigned long)pmds[i]);
+			mm_dec_nr_pmds(mm);
 		}
 }
 
-static int preallocate_pmds(pmd_t *pmds[])
+static int preallocate_pmds(struct mm_struct *mm, pmd_t *pmds[])
 {
 	int i;
 	bool failed = false;
@@ -215,11 +216,13 @@
 			pmd = NULL;
 			failed = true;
 		}
+		if (pmd)
+			mm_inc_nr_pmds(mm);
 		pmds[i] = pmd;
 	}
 
 	if (failed) {
-		free_pmds(pmds);
+		free_pmds(mm, pmds);
 		return -ENOMEM;
 	}
 
@@ -246,6 +249,7 @@
 
 			paravirt_release_pmd(pgd_val(pgd) >> PAGE_SHIFT);
 			pmd_free(mm, pmd);
+			mm_dec_nr_pmds(mm);
 		}
 	}
 }
@@ -283,7 +287,7 @@
 
 	mm->pgd = pgd;
 
-	if (preallocate_pmds(pmds) != 0)
+	if (preallocate_pmds(mm, pmds) != 0)
 		goto out_free_pgd;
 
 	if (paravirt_pgd_alloc(mm) != 0)
@@ -304,7 +308,7 @@
 	return pgd;
 
 out_free_pmds:
-	free_pmds(pmds);
+	free_pmds(mm, pmds);
 out_free_pgd:
 	free_page((unsigned long)pgd);
 out: