hugetlb: use new vma_lock for pmd sharing synchronization

The new hugetlb vma lock is used to address this race:

Faulting thread                                 Unsharing thread
...                                                  ...
ptep = huge_pte_offset()
      or
ptep = huge_pte_alloc()
...
                                                i_mmap_lock_write
                                                lock page table
ptep invalid   <------------------------        huge_pmd_unshare()
Could be in a previously                        unlock_page_table
sharing process or worse                        i_mmap_unlock_write
...

The vma_lock is used as follows:
- During fault processing. The lock is acquired in read mode before
  doing a page table lock and allocation (huge_pte_alloc).  The lock is
  held until code is finished with the page table entry (ptep).
- The lock must be held in write mode whenever huge_pmd_unshare is
  called.

Lock ordering issues come into play when unmapping a page from all
vmas mapping the page.  The i_mmap_rwsem must be held to search for the
vmas, and the vma lock must be held before calling unmap which will
call huge_pmd_unshare.  This is done today in:
- try_to_migrate_one and try_to_unmap_ for page migration and memory
  error handling.  In these routines we 'try' to obtain the vma lock and
  fail to unmap if unsuccessful.  Calling routines already deal with the
  failure of unmapping.
- hugetlb_vmdelete_list for truncation and hole punch.  This routine
  also tries to acquire the vma lock.  If it fails, it skips the
  unmapping.  However, we can not have file truncation or hole punch
  fail because of contention.  After hugetlb_vmdelete_list, truncation
  and hole punch call remove_inode_hugepages.  remove_inode_hugepages
  checks for mapped pages and call hugetlb_unmap_file_page to unmap them.
  hugetlb_unmap_file_page is designed to drop locks and reacquire in the
  correct order to guarantee unmap success.

Link: https://lkml.kernel.org/r/20220914221810.95771-9-mike.kravetz@oracle.com
Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: James Houghton <jthoughton@google.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mina Almasry <almasrymina@google.com>
Cc: Muchun Song <songmuchun@bytedance.com>
Cc: Naoya Horiguchi <naoya.horiguchi@linux.dev>
Cc: Pasha Tatashin <pasha.tatashin@soleen.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Prakash Sangappa <prakash.sangappa@oracle.com>
Cc: Sven Schnelle <svens@linux.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 93 insertions, 9 deletions

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index f44b79998ac2..d78504959df7 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -4796,6 +4796,14 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 		mmu_notifier_invalidate_range_start(&range);
 		mmap_assert_write_locked(src);
 		raw_write_seqcount_begin(&src->write_protect_seq);
+	} else {
+		/*
+		 * For shared mappings the vma lock must be held before
+		 * calling huge_pte_offset in the src vma. Otherwise, the
+		 * returned ptep could go away if part of a shared pmd and
+		 * another thread calls huge_pmd_unshare.
+		 */
+		hugetlb_vma_lock_read(src_vma);
 	}
 
 	last_addr_mask = hugetlb_mask_last_page(h);
@@ -4942,6 +4950,8 @@ again:
 	if (cow) {
 		raw_write_seqcount_end(&src->write_protect_seq);
 		mmu_notifier_invalidate_range_end(&range);
+	} else {
+		hugetlb_vma_unlock_read(src_vma);
 	}
 
 	return ret;
@@ -5000,6 +5010,7 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma,
 	mmu_notifier_invalidate_range_start(&range);
 	last_addr_mask = hugetlb_mask_last_page(h);
 	/* Prevent race with file truncation */
+	hugetlb_vma_lock_write(vma);
 	i_mmap_lock_write(mapping);
 	for (; old_addr < old_end; old_addr += sz, new_addr += sz) {
 		src_pte = huge_pte_offset(mm, old_addr, sz);
@@ -5031,6 +5042,7 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma,
 		flush_tlb_range(vma, old_end - len, old_end);
 	mmu_notifier_invalidate_range_end(&range);
 	i_mmap_unlock_write(mapping);
+	hugetlb_vma_unlock_write(vma);
 
 	return len + old_addr - old_end;
 }
@@ -5350,8 +5362,29 @@ retry_avoidcopy:
 		 * may get SIGKILLed if it later faults.
 		 */
 		if (outside_reserve) {
+			struct address_space *mapping = vma->vm_file->f_mapping;
+			pgoff_t idx;
+			u32 hash;
+
 			put_page(old_page);
+			/*
+			 * Drop hugetlb_fault_mutex and vma_lock before
+			 * unmapping.  unmapping needs to hold vma_lock
+			 * in write mode.  Dropping vma_lock in read mode
+			 * here is OK as COW mappings do not interact with
+			 * PMD sharing.
+			 *
+			 * Reacquire both after unmap operation.
+			 */
+			idx = vma_hugecache_offset(h, vma, haddr);
+			hash = hugetlb_fault_mutex_hash(mapping, idx);
+			hugetlb_vma_unlock_read(vma);
+			mutex_unlock(&hugetlb_fault_mutex_table[hash]);
+
 			unmap_ref_private(mm, vma, old_page, haddr);
+
+			mutex_lock(&hugetlb_fault_mutex_table[hash]);
+			hugetlb_vma_lock_read(vma);
 			spin_lock(ptl);
 			ptep = huge_pte_offset(mm, haddr, huge_page_size(h));
 			if (likely(ptep &&
@@ -5500,14 +5533,16 @@ static inline vm_fault_t hugetlb_handle_userfault(struct vm_area_struct *vma,
 	};
 
 	/*
-	 * hugetlb_fault_mutex and i_mmap_rwsem must be
+	 * vma_lock and hugetlb_fault_mutex must be
 	 * dropped before handling userfault.  Reacquire
 	 * after handling fault to make calling code simpler.
 	 */
+	hugetlb_vma_unlock_read(vma);
 	hash = hugetlb_fault_mutex_hash(mapping, idx);
 	mutex_unlock(&hugetlb_fault_mutex_table[hash]);
 	ret = handle_userfault(&vmf, reason);
 	mutex_lock(&hugetlb_fault_mutex_table[hash]);
+	hugetlb_vma_lock_read(vma);
 
 	return ret;
 }
@@ -5741,6 +5776,11 @@ 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, ptep);
@@ -5748,23 +5788,35 @@ 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, vma, haddr, huge_page_size(h));
-		if (!ptep)
-			return VM_FAULT_OOM;
 	}
 
-	mapping = vma->vm_file->f_mapping;
-	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.
 	 */
+	mapping = vma->vm_file->f_mapping;
+	idx = vma_hugecache_offset(h, vma, haddr);
 	hash = hugetlb_fault_mutex_hash(mapping, idx);
 	mutex_lock(&hugetlb_fault_mutex_table[hash]);
 
+	/*
+	 * Acquire vma lock 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 has changed.
+	 */
+	hugetlb_vma_lock_read(vma);
+	ptep = huge_pte_alloc(mm, vma, haddr, huge_page_size(h));
+	if (!ptep) {
+		hugetlb_vma_unlock_read(vma);
+		mutex_unlock(&hugetlb_fault_mutex_table[hash]);
+		return VM_FAULT_OOM;
+	}
+
 	entry = huge_ptep_get(ptep);
 	/* PTE markers should be handled the same way as none pte */
 	if (huge_pte_none_mostly(entry)) {
@@ -5825,6 +5877,7 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 			unlock_page(pagecache_page);
 			put_page(pagecache_page);
 		}
+		hugetlb_vma_unlock_read(vma);
 		mutex_unlock(&hugetlb_fault_mutex_table[hash]);
 		return handle_userfault(&vmf, VM_UFFD_WP);
 	}
@@ -5868,6 +5921,7 @@ out_ptl:
 		put_page(pagecache_page);
 	}
 out_mutex:
+	hugetlb_vma_unlock_read(vma);
 	mutex_unlock(&hugetlb_fault_mutex_table[hash]);
 	/*
 	 * Generally it's safe to hold refcount during waiting page lock. But
@@ -6330,8 +6384,9 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 	flush_cache_range(vma, range.start, range.end);
 
 	mmu_notifier_invalidate_range_start(&range);
-	last_addr_mask = hugetlb_mask_last_page(h);
+	hugetlb_vma_lock_write(vma);
 	i_mmap_lock_write(vma->vm_file->f_mapping);
+	last_addr_mask = hugetlb_mask_last_page(h);
 	for (; address < end; address += psize) {
 		spinlock_t *ptl;
 		ptep = huge_pte_offset(mm, address, psize);
@@ -6430,6 +6485,7 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 	 * See Documentation/mm/mmu_notifier.rst
 	 */
 	i_mmap_unlock_write(vma->vm_file->f_mapping);
+	hugetlb_vma_unlock_write(vma);
 	mmu_notifier_invalidate_range_end(&range);
 
 	return pages << h->order;
@@ -6931,6 +6987,7 @@ int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma,
 	pud_t *pud = pud_offset(p4d, addr);
 
 	i_mmap_assert_write_locked(vma->vm_file->f_mapping);
+	hugetlb_vma_assert_locked(vma);
 	BUG_ON(page_count(virt_to_page(ptep)) == 0);
 	if (page_count(virt_to_page(ptep)) == 1)
 		return 0;
@@ -6943,6 +7000,31 @@ int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma,
 
 #else /* !CONFIG_ARCH_WANT_HUGE_PMD_SHARE */
 
+void hugetlb_vma_lock_read(struct vm_area_struct *vma)
+{
+}
+
+void hugetlb_vma_unlock_read(struct vm_area_struct *vma)
+{
+}
+
+void hugetlb_vma_lock_write(struct vm_area_struct *vma)
+{
+}
+
+void hugetlb_vma_unlock_write(struct vm_area_struct *vma)
+{
+}
+
+int hugetlb_vma_trylock_write(struct vm_area_struct *vma)
+{
+	return 1;
+}
+
+void hugetlb_vma_assert_locked(struct vm_area_struct *vma)
+{
+}
+
 void hugetlb_vma_lock_release(struct kref *kref)
 {
 }
@@ -7325,6 +7407,7 @@ void hugetlb_unshare_all_pmds(struct vm_area_struct *vma)
 	mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, mm,
 				start, end);
 	mmu_notifier_invalidate_range_start(&range);
+	hugetlb_vma_lock_write(vma);
 	i_mmap_lock_write(vma->vm_file->f_mapping);
 	for (address = start; address < end; address += PUD_SIZE) {
 		ptep = huge_pte_offset(mm, address, sz);
@@ -7336,6 +7419,7 @@ void hugetlb_unshare_all_pmds(struct vm_area_struct *vma)
 	}
 	flush_hugetlb_tlb_range(vma, start, end);
 	i_mmap_unlock_write(vma->vm_file->f_mapping);
+	hugetlb_vma_unlock_write(vma);
 	/*
 	 * No need to call mmu_notifier_invalidate_range(), see
 	 * Documentation/mm/mmu_notifier.rst.