[PATCH v3] mm/hugetlb: fix copy_hugetlb_page_range() to use ->pt_share_count

[Jane Chu <jane.chu@oracle.com>]

commit 59d9094df3d79 ("mm: hugetlb: independent PMD page table shared count")
introduced ->pt_share_count dedicated to hugetlb PMD share count tracking,
but omitted fixing copy_hugetlb_page_range(), leaving the function relying on
page_count() for tracking that no longer works.

When lazy page table copy for hugetlb is disabled, that is, revert
commit bcd51a3c679d ("hugetlb: lazy page table copies in fork()")
fork()'ing with hugetlb PMD sharing quickly lockup -

[  239.446559] watchdog: BUG: soft lockup - CPU#75 stuck for 27s!
[  239.446611] RIP: 0010:native_queued_spin_lock_slowpath+0x7e/0x2e0
[  239.446631] Call Trace:
[  239.446633]  <TASK>
[  239.446636]  _raw_spin_lock+0x3f/0x60
[  239.446639]  copy_hugetlb_page_range+0x258/0xb50
[  239.446645]  copy_page_range+0x22b/0x2c0
[  239.446651]  dup_mmap+0x3e2/0x770
[  239.446654]  dup_mm.constprop.0+0x5e/0x230
[  239.446657]  copy_process+0xd17/0x1760
[  239.446660]  kernel_clone+0xc0/0x3e0
[  239.446661]  __do_sys_clone+0x65/0xa0
[  239.446664]  do_syscall_64+0x82/0x930
[  239.446668]  ? count_memcg_events+0xd2/0x190
[  239.446671]  ? syscall_trace_enter+0x14e/0x1f0
[  239.446676]  ? syscall_exit_work+0x118/0x150
[  239.446677]  ? arch_exit_to_user_mode_prepare.constprop.0+0x9/0xb0
[  239.446681]  ? clear_bhb_loop+0x30/0x80
[  239.446684]  ? clear_bhb_loop+0x30/0x80
[  239.446686]  entry_SYSCALL_64_after_hwframe+0x76/0x7e

There are two options to resolve the potential latent issue:
  1. warn against PMD sharing in copy_hugetlb_page_range(),
  2. fix it.
This patch opts for the second option.
While at it, simplify the comment, the details are not actually relevant
anymore.

Fixes: 59d9094df3d79 ("mm: hugetlb: independent PMD page table shared count")
Signed-off-by: Jane Chu <jane.chu@oracle.com>
Reviewed-by: Harry Yoo <harry.yoo@oracle.com>
---
 include/linux/mm_types.h |  5 +++++
 mm/hugetlb.c             | 15 +++++----------
 2 files changed, 10 insertions(+), 10 deletions(-)

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 08bc2442db93..a643fae8a349 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -631,6 +631,11 @@ static inline int ptdesc_pmd_pts_count(struct ptdesc *ptdesc)
 {
 	return atomic_read(&ptdesc->pt_share_count);
 }
+
+static inline bool ptdesc_pmd_is_shared(struct ptdesc *ptdesc)
+{
+	return !!ptdesc_pmd_pts_count(ptdesc);
+}
 #else
 static inline void ptdesc_pmd_pts_init(struct ptdesc *ptdesc)
 {
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index eed59cfb5d21..6cfe0b43ab8f 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -5594,18 +5594,13 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 			break;
 		}
 
-		/*
-		 * If the pagetables are shared don't copy or take references.
-		 *
-		 * dst_pte == src_pte is the common case of src/dest sharing.
-		 * However, src could have 'unshared' and dst shares with
-		 * another vma. So page_count of ptep page is checked instead
-		 * to reliably determine whether pte is shared.
-		 */
-		if (page_count(virt_to_page(dst_pte)) > 1) {
+#ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING
+		/* If the pagetables are shared, there is nothing to do */
+		if (ptdesc_pmd_is_shared(virt_to_ptdesc(dst_pte))) {
 			addr |= last_addr_mask;
 			continue;
 		}
+#endif
 
 		dst_ptl = huge_pte_lock(h, dst, dst_pte);
 		src_ptl = huge_pte_lockptr(h, src, src_pte);
@@ -7602,7 +7597,7 @@ int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma,
 	hugetlb_vma_assert_locked(vma);
 	if (sz != PMD_SIZE)
 		return 0;
-	if (!ptdesc_pmd_pts_count(virt_to_ptdesc(ptep)))
+	if (!ptdesc_pmd_is_shared(virt_to_ptdesc(ptep)))
 		return 0;
 
 	pud_clear(pud);
-- 
2.43.5