mm/hugetlb: take page table lock in follow_huge_pmd()

We have a race condition between move_pages() and freeing hugepages, where
move_pages() calls follow_page(FOLL_GET) for hugepages internally and
tries to get its refcount without preventing concurrent freeing.  This
race crashes the kernel, so this patch fixes it by moving FOLL_GET code
for hugepages into follow_huge_pmd() with taking the page table lock.

This patch intentionally removes page==NULL check after pte_page.
This is justified because pte_page() never returns NULL for any
architectures or configurations.

This patch changes the behavior of follow_huge_pmd() for tail pages and
then tail pages can be pinned/returned.  So the caller must be changed to
properly handle the returned tail pages.

We could have a choice to add the similar locking to
follow_huge_(addr|pud) for consistency, but it's not necessary because
currently these functions don't support FOLL_GET flag, so let's leave it
for future development.

Here is the reproducer:

  $ cat movepages.c
  #include <stdio.h>
  #include <stdlib.h>
  #include <numaif.h>

  #define ADDR_INPUT      0x700000000000UL
  #define HPS             0x200000
  #define PS              0x1000

  int main(int argc, char *argv[]) {
          int i;
          int nr_hp = strtol(argv[1], NULL, 0);
          int nr_p  = nr_hp * HPS / PS;
          int ret;
          void **addrs;
          int *status;
          int *nodes;
          pid_t pid;

          pid = strtol(argv[2], NULL, 0);
          addrs  = malloc(sizeof(char *) * nr_p + 1);
          status = malloc(sizeof(char *) * nr_p + 1);
          nodes  = malloc(sizeof(char *) * nr_p + 1);

          while (1) {
                  for (i = 0; i < nr_p; i++) {
                          addrs[i] = (void *)ADDR_INPUT + i * PS;
                          nodes[i] = 1;
                          status[i] = 0;
                  }
                  ret = numa_move_pages(pid, nr_p, addrs, nodes, status,
                                        MPOL_MF_MOVE_ALL);
                  if (ret == -1)
                          err("move_pages");

                  for (i = 0; i < nr_p; i++) {
                          addrs[i] = (void *)ADDR_INPUT + i * PS;
                          nodes[i] = 0;
                          status[i] = 0;
                  }
                  ret = numa_move_pages(pid, nr_p, addrs, nodes, status,
                                        MPOL_MF_MOVE_ALL);
                  if (ret == -1)
                          err("move_pages");
          }
          return 0;
  }

  $ cat hugepage.c
  #include <stdio.h>
  #include <sys/mman.h>
  #include <string.h>

  #define ADDR_INPUT      0x700000000000UL
  #define HPS             0x200000

  int main(int argc, char *argv[]) {
          int nr_hp = strtol(argv[1], NULL, 0);
          char *p;

          while (1) {
                  p = mmap((void *)ADDR_INPUT, nr_hp * HPS, PROT_READ | PROT_WRITE,
                           MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB, -1, 0);
                  if (p != (void *)ADDR_INPUT) {
                          perror("mmap");
                          break;
                  }
                  memset(p, 0, nr_hp * HPS);
                  munmap(p, nr_hp * HPS);
          }
  }

  $ sysctl vm.nr_hugepages=40
  $ ./hugepage 10 &
  $ ./movepages 10 $(pgrep -f hugepage)

Fixes: e632a938d914 ("mm: migrate: add hugepage migration code to move_pages()")
Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Reported-by: Hugh Dickins <hughd@google.com>
Cc: James Hogan <james.hogan@imgtec.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Rik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Luiz Capitulino <lcapitulino@redhat.com>
Cc: Nishanth Aravamudan <nacc@linux.vnet.ibm.com>
Cc: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Steve Capper <steve.capper@linaro.org>
Cc: <stable@vger.kernel.org>	[3.12+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 45 insertions, 33 deletions

diff --git a/mm/gup.c b/mm/gup.c
index 12bc2bc..1a8ab05 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -167,10 +167,10 @@ struct page *follow_page_mask(struct vm_area_struct *vma,
 	if (pud_none(*pud))
 		return no_page_table(vma, flags);
 	if (pud_huge(*pud) && vma->vm_flags & VM_HUGETLB) {
-		if (flags & FOLL_GET)
-			return NULL;
-		page = follow_huge_pud(mm, address, pud, flags & FOLL_WRITE);
-		return page;
+		page = follow_huge_pud(mm, address, pud, flags);
+		if (page)
+			return page;
+		return no_page_table(vma, flags);
 	}
 	if (unlikely(pud_bad(*pud)))
 		return no_page_table(vma, flags);
@@ -179,19 +179,10 @@ struct page *follow_page_mask(struct vm_area_struct *vma,
 	if (pmd_none(*pmd))
 		return no_page_table(vma, flags);
 	if (pmd_huge(*pmd) && vma->vm_flags & VM_HUGETLB) {
-		page = follow_huge_pmd(mm, address, pmd, flags & FOLL_WRITE);
-		if (flags & FOLL_GET) {
-			/*
-			 * Refcount on tail pages are not well-defined and
-			 * shouldn't be taken. The caller should handle a NULL
-			 * return when trying to follow tail pages.
-			 */
-			if (PageHead(page))
-				get_page(page);
-			else
-				page = NULL;
-		}
-		return page;
+		page = follow_huge_pmd(mm, address, pmd, flags);
+		if (page)
+			return page;
+		return no_page_table(vma, flags);
 	}
 	if ((flags & FOLL_NUMA) && pmd_numa(*pmd))
 		return no_page_table(vma, flags);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index d96b8bf..5aca3707 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3675,28 +3675,48 @@ follow_huge_addr(struct mm_struct *mm, unsigned long address,
 
 struct page * __weak
 follow_huge_pmd(struct mm_struct *mm, unsigned long address,
-		pmd_t *pmd, int write)
+		pmd_t *pmd, int flags)
 {
-	struct page *page;
-
-	if (!pmd_present(*pmd))
-		return NULL;
-	page = pte_page(*(pte_t *)pmd);
-	if (page)
-		page += ((address & ~PMD_MASK) >> PAGE_SHIFT);
+	struct page *page = NULL;
+	spinlock_t *ptl;
+retry:
+	ptl = pmd_lockptr(mm, pmd);
+	spin_lock(ptl);
+	/*
+	 * make sure that the address range covered by this pmd is not
+	 * unmapped from other threads.
+	 */
+	if (!pmd_huge(*pmd))
+		goto out;
+	if (pmd_present(*pmd)) {
+		page = pte_page(*(pte_t *)pmd) +
+			((address & ~PMD_MASK) >> PAGE_SHIFT);
+		if (flags & FOLL_GET)
+			get_page(page);
+	} else {
+		if (is_hugetlb_entry_migration(huge_ptep_get((pte_t *)pmd))) {
+			spin_unlock(ptl);
+			__migration_entry_wait(mm, (pte_t *)pmd, ptl);
+			goto retry;
+		}
+		/*
+		 * hwpoisoned entry is treated as no_page_table in
+		 * follow_page_mask().
+		 */
+	}
+out:
+	spin_unlock(ptl);
 	return page;
 }
 
 struct page * __weak
 follow_huge_pud(struct mm_struct *mm, unsigned long address,
-		pud_t *pud, int write)
+		pud_t *pud, int flags)
 {
-	struct page *page;
+	if (flags & FOLL_GET)
+		return NULL;
 
-	page = pte_page(*(pte_t *)pud);
-	if (page)
-		page += ((address & ~PUD_MASK) >> PAGE_SHIFT);
-	return page;
+	return pte_page(*(pte_t *)pud) + ((address & ~PUD_MASK) >> PAGE_SHIFT);
 }
 
 #ifdef CONFIG_MEMORY_FAILURE
diff --git a/mm/migrate.c b/mm/migrate.c
index 6e284bc..f98067e 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -197,7 +197,7 @@ static void remove_migration_ptes(struct page *old, struct page *new)
  * get to the page and wait until migration is finished.
  * When we return from this function the fault will be retried.
  */
-static void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep,
+void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep,
 				spinlock_t *ptl)
 {
 	pte_t pte;
@@ -1236,7 +1236,8 @@ static int do_move_page_to_node_array(struct mm_struct *mm,
 			goto put_and_set;
 
 		if (PageHuge(page)) {
-			isolate_huge_page(page, &pagelist);
+			if (PageHead(page))
+				isolate_huge_page(page, &pagelist);
 			goto put_and_set;
 		}