hugetlbfs: revert "use i_mmap_rwsem for more pmd sharing synchronization"

This reverts b43a9990055958e70347c56f90ea2ae32c67334c

The reverted commit caused issues with migration and poisoning of anon
huge pages.  The LTP move_pages12 test will cause an "unable to handle
kernel NULL pointer" BUG would occur with stack similar to:

  RIP: 0010:down_write+0x1b/0x40
  Call Trace:
    migrate_pages+0x81f/0xb90
    __ia32_compat_sys_migrate_pages+0x190/0x190
    do_move_pages_to_node.isra.53.part.54+0x2a/0x50
    kernel_move_pages+0x566/0x7b0
    __x64_sys_move_pages+0x24/0x30
    do_syscall_64+0x5b/0x180
    entry_SYSCALL_64_after_hwframe+0x44/0xa9

The purpose of the reverted patch was to fix some long existing races
with huge pmd sharing.  It used i_mmap_rwsem for this purpose with the
idea that this could also be used to address truncate/page fault races
with another patch.  Further analysis has determined that i_mmap_rwsem
can not be used to address all these hugetlbfs synchronization issues.
Therefore, revert this patch while working an another approach to the
underlying issues.

Link: http://lkml.kernel.org/r/20190103235452.29335-2-mike.kravetz@oracle.com
Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com>
Reported-by: Jan Stancek <jstancek@redhat.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: "Aneesh Kumar K . V" <aneesh.kumar@linux.vnet.ibm.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: "Kirill A . Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Prakash Sangappa <prakash.sangappa@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 15 insertions, 49 deletions

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index aedc1b183cf9..df2e7dd5ff17 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3238,7 +3238,6 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 	struct page *ptepage;
 	unsigned long addr;
 	int cow;
-	struct address_space *mapping = vma->vm_file->f_mapping;
 	struct hstate *h = hstate_vma(vma);
 	unsigned long sz = huge_page_size(h);
 	struct mmu_notifier_range range;
@@ -3250,23 +3249,13 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 		mmu_notifier_range_init(&range, src, vma->vm_start,
 					vma->vm_end);
 		mmu_notifier_invalidate_range_start(&range);
-	} else {
-		/*
-		 * For shared mappings i_mmap_rwsem must be held to call
-		 * huge_pte_alloc, otherwise the returned ptep could go
-		 * away if part of a shared pmd and another thread calls
-		 * huge_pmd_unshare.
-		 */
-		i_mmap_lock_read(mapping);
 	}
 
 	for (addr = vma->vm_start; addr < vma->vm_end; addr += sz) {
 		spinlock_t *src_ptl, *dst_ptl;
-
 		src_pte = huge_pte_offset(src, addr, sz);
 		if (!src_pte)
 			continue;
-
 		dst_pte = huge_pte_alloc(dst, addr, sz);
 		if (!dst_pte) {
 			ret = -ENOMEM;
@@ -3337,8 +3326,6 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 
 	if (cow)
 		mmu_notifier_invalidate_range_end(&range);
-	else
-		i_mmap_unlock_read(mapping);
 
 	return ret;
 }
@@ -3784,18 +3771,14 @@ retry:
 			};
 
 			/*
-			 * hugetlb_fault_mutex and i_mmap_rwsem must be
-			 * dropped before handling userfault.  Reacquire
-			 * after handling fault to make calling code simpler.
+			 * hugetlb_fault_mutex must be dropped before
+			 * handling userfault.  Reacquire after handling
+			 * fault to make calling code simpler.
 			 */
 			hash = hugetlb_fault_mutex_hash(h, mm, vma, mapping,
 							idx, haddr);
 			mutex_unlock(&hugetlb_fault_mutex_table[hash]);
-			i_mmap_unlock_read(mapping);
-
 			ret = handle_userfault(&vmf, VM_UFFD_MISSING);
-
-			i_mmap_lock_read(mapping);
 			mutex_lock(&hugetlb_fault_mutex_table[hash]);
 			goto out;
 		}
@@ -3943,11 +3926,6 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 
 	ptep = huge_pte_offset(mm, haddr, huge_page_size(h));
 	if (ptep) {
-		/*
-		 * Since we hold no locks, ptep could be stale.  That is
-		 * OK as we are only making decisions based on content and
-		 * not actually modifying content here.
-		 */
 		entry = huge_ptep_get(ptep);
 		if (unlikely(is_hugetlb_entry_migration(entry))) {
 			migration_entry_wait_huge(vma, mm, ptep);
@@ -3955,31 +3933,20 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 		} else if (unlikely(is_hugetlb_entry_hwpoisoned(entry)))
 			return VM_FAULT_HWPOISON_LARGE |
 				VM_FAULT_SET_HINDEX(hstate_index(h));
+	} else {
+		ptep = huge_pte_alloc(mm, haddr, huge_page_size(h));
+		if (!ptep)
+			return VM_FAULT_OOM;
 	}
 
-	/*
-	 * Acquire i_mmap_rwsem before calling huge_pte_alloc and hold
-	 * until finished with ptep.  This prevents huge_pmd_unshare from
-	 * being called elsewhere and making the ptep no longer valid.
-	 *
-	 * ptep could have already be assigned via huge_pte_offset.  That
-	 * is OK, as huge_pte_alloc will return the same value unless
-	 * something changed.
-	 */
 	mapping = vma->vm_file->f_mapping;
-	i_mmap_lock_read(mapping);
-	ptep = huge_pte_alloc(mm, haddr, huge_page_size(h));
-	if (!ptep) {
-		i_mmap_unlock_read(mapping);
-		return VM_FAULT_OOM;
-	}
+	idx = vma_hugecache_offset(h, vma, haddr);
 
 	/*
 	 * Serialize hugepage allocation and instantiation, so that we don't
 	 * get spurious allocation failures if two CPUs race to instantiate
 	 * the same page in the page cache.
 	 */
-	idx = vma_hugecache_offset(h, vma, haddr);
 	hash = hugetlb_fault_mutex_hash(h, mm, vma, mapping, idx, haddr);
 	mutex_lock(&hugetlb_fault_mutex_table[hash]);
 
@@ -4067,7 +4034,6 @@ out_ptl:
 	}
 out_mutex:
 	mutex_unlock(&hugetlb_fault_mutex_table[hash]);
-	i_mmap_unlock_read(mapping);
 	/*
 	 * Generally it's safe to hold refcount during waiting page lock. But
 	 * here we just wait to defer the next page fault to avoid busy loop and
@@ -4672,12 +4638,10 @@ void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma,
  * Search for a shareable pmd page for hugetlb. In any case calls pmd_alloc()
  * and returns the corresponding pte. While this is not necessary for the
  * !shared pmd case because we can allocate the pmd later as well, it makes the
- * code much cleaner.
- *
- * This routine must be called with i_mmap_rwsem held in at least read mode.
- * For hugetlbfs, this prevents removal of any page table entries associated
- * with the address space.  This is important as we are setting up sharing
- * based on existing page table entries (mappings).
+ * code much cleaner. pmd allocation is essential for the shared case because
+ * pud has to be populated inside the same i_mmap_rwsem section - otherwise
+ * racing tasks could either miss the sharing (see huge_pte_offset) or select a
+ * bad pmd for sharing.
  */
 pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
 {
@@ -4694,6 +4658,7 @@ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
 	if (!vma_shareable(vma, addr))
 		return (pte_t *)pmd_alloc(mm, pud, addr);
 
+	i_mmap_lock_write(mapping);
 	vma_interval_tree_foreach(svma, &mapping->i_mmap, idx, idx) {
 		if (svma == vma)
 			continue;
@@ -4723,6 +4688,7 @@ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
 	spin_unlock(ptl);
 out:
 	pte = (pte_t *)pmd_alloc(mm, pud, addr);
+	i_mmap_unlock_write(mapping);
 	return pte;
 }
 
@@ -4733,7 +4699,7 @@ out:
  * indicated by page_count > 1, unmap is achieved by clearing pud and
  * decrementing the ref count. If count == 1, the pte page is not shared.
  *
- * Called with page table lock held and i_mmap_rwsem held in write mode.
+ * called with page table lock held.
  *
  * returns: 1 successfully unmapped a shared pte page
  *	    0 the underlying pte page is not shared, or it is the last user