Skip to contentSkip to conversation

hugetlbfs: close race between MADV_DONTNEED and page fault

PATCH Superseded [email protected] 3 participants 8 messages Sep 26, 2023 – Sep 30, 2023

Subsystems (4)

v4 of 7 Superseded Latest is v7 →

lore
Share & tools
lore
#0 lore raw

v4 cover hugetlbfs: close race between MADV_DONTNEED and page fault

v4: fix unmap_vmas locking issue pointed out by Mike Kravetz, and resulting lockdep fallout
v3: fix compile error w/ lockdep and test case errors with patch 3
v2: fix the locking bug found with the libhugetlbfs tests.

Malloc libraries, like jemalloc and tcalloc, take decisions on when to call madvise independently from the code in the main application.

This sometimes results in the application page faulting on an address, right after the malloc library has shot down the backing memory with MADV_DONTNEED.

Usually this is harmless, because we always have some 4kB pages sitting around to satisfy a page fault. However, with hugetlbfs systems often allocate only the exact number of huge pages that the application wants.

Due to TLB batching, hugetlbfs MADV_DONTNEED will free pages outside of any lock taken on the page fault path, which can open up the following race condition:

CPU 1 CPU 2

MADV_DONTNEED
unmap page
shoot down TLB entry
page fault
fail to allocate a huge page killed with SIGBUS
free page

Fix that race by extending the hugetlb_vma_lock locking scheme to also cover private hugetlb mappings (with resv_map), and pulling the locking from __unmap_hugepage_final_range into helper functions called from zap_page_range_single. This ensures page faults stay locked out of the MADV_DONTNEED VMA until the huge pages have actually been freed.

The third patch in the series is more of an RFC. Using the invalidate_lock instead of the hugetlb_vma_lock greatly simplifies the code, but at the cost of turning a per-VMA lock into a lock per backing hugetlbfs file, which could slow things down when multiple processes are mapping the same hugetlbfs file.

#1 lore raw

PATCH v4 1/3 hugetlbfs: extend hugetlb_vma_lock to private VMAs

From: Rik van Riel <[email protected]>

Extend the locking scheme used to protect shared hugetlb mappings from truncate vs page fault races, in order to protect private hugetlb mappings (with resv_map) against MADV_DONTNEED.

Add a read-write semaphore to the resv_map data structure, and use that from the hugetlb_vma_(un)lock_* functions, in preparation for closing the race between MADV_DONTNEED and page faults.

---
 include/linux/hugetlb.h |  6 ++++++
 mm/hugetlb.c            | 41 +++++++++++++++++++++++++++++++++++++----
 2 files changed, 43 insertions(+), 4 deletions(-)
include/linux/hugetlb.h +6 -0
index 5b2626063f4f..694928fa06a3 100644
@@ -60,6 +60,7 @@ struct resv_map {
 	long adds_in_progress;
 	struct list_head region_cache;
 	long region_cache_count;
+	struct rw_semaphore rw_sema;
 #ifdef CONFIG_CGROUP_HUGETLB
 	/*
 	 * On private mappings, the counter to uncharge reservations is stored
@@ -1231,6 +1232,11 @@ static inline bool __vma_shareable_lock(struct vm_area_struct *vma)
 	return (vma->vm_flags & VM_MAYSHARE) && vma->vm_private_data;
 }
 
+static inline bool __vma_private_lock(struct vm_area_struct *vma)
+{
+	return (!(vma->vm_flags & VM_MAYSHARE)) && vma->vm_private_data;
+}
+
 /*
  * Safe version of huge_pte_offset() to check the locks.  See comments
  * above huge_pte_offset().
mm/hugetlb.c +37 -4

96 lines not on this page · raw message

Signature · 1 line
2.41.0
#2 lore raw

Re: [PATCH 1/3] hugetlbfs: extend hugetlb_vma_lock to private VMAs

Quoted 10 lines · On 09/25/23 23:10, [email protected] wrote:

From: Rik van Riel <[email protected]>

Extend the locking scheme used to protect shared hugetlb mappings from truncate vs page fault races, in order to protect private hugetlb mappings (with resv_map) against MADV_DONTNEED.

Add a read-write semaphore to the resv_map data structure, and use that from the hugetlb_vma_(un)lock_* functions, in preparation for closing the race between MADV_DONTNEED and page faults.

Quoted 6 lines
---
 include/linux/hugetlb.h |  6 ++++++
 mm/hugetlb.c            | 41 +++++++++++++++++++++++++++++++++++++----
 2 files changed, 43 insertions(+), 4 deletions(-)

My bad during the review of patch 2!

In reply to patch 1, I suggested the changes:

Quoted 5 lines
mm/hugetlb.c +0 -0
index f906c5fa4d09..8f3d5895fffc 100644

mm/hugetlb.c static void __hugetlb_vma_unlock_write_free(struct vm_area_struct *vma) · line 381

Quoted 10 lines
mm/hugetlb.c +5 -0
@@ -372,6 +372,11 @@ static void __hugetlb_vma_unlock_write_free(struct vm_area_struct *vma)
 		struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
 
 		__hugetlb_vma_unlock_write_put(vma_lock);
+	} else if (__vma_private_lock(vma)) {
+		struct resv_map *resv_map = vma_resv_map(vma);
+
+		/* no free for anon vmas, but still need to unlock */
+		up_write(&resv_map->rw_sema);
 	}
 }

However, the check for 'if (__vma_private_lock(vma))' was dropped.

mm/hugetlb.c static void __hugetlb_vma_unlock_write_free(struct vm_area_struct *vma) · line 381

Quoted 11 lines
mm/hugetlb.c +5 -0
@@ -345,6 +372,11 @@ static void __hugetlb_vma_unlock_write_free(struct vm_area_struct *vma)
 		struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
 
 		__hugetlb_vma_unlock_write_put(vma_lock);
+	} else {
+		struct resv_map *resv_map = vma_resv_map(vma);
+
+		/* no free for anon vmas, but still need to unlock */
+		up_write(&resv_map->rw_sema);
 	}
 }

So, the map_high_truncate_2 (2M: 32) libhugetlbfs test still BUGs with:

BUG: kernel NULL pointer dereference
Signature · 1 line
Mike Kravetz
#3 lore raw

Re: [PATCH 1/3] hugetlbfs: extend hugetlb_vma_lock to private VMAs

Quoted 24 lines · Mike Kravetz

On 09/25/23 23:10, [email protected] wrote:

In reply to patch 1, I suggested the changes:

Quoted 8 lines
mm/hugetlb.c +0 -0
index f906c5fa4d09..8f3d5895fffc 100644
@@ -372,6 +372,11 @@ static void
 __hugetlb_vma_unlock_write_free(struct vm_area_struct *vma)

                struct hugetlb_vma_lock *vma_lock = vma-

Quoted 1 line

vm_private_data;

Quoted 10 lines


                __hugetlb_vma_unlock_write_put(vma_lock); +       } else if (__vma_private_lock(vma)) {
+               struct resv_map *resv_map = vma_resv_map(vma); +
+               /* no free for anon vmas, but still need to unlock */
+               up_write(&resv_map->rw_sema);
        }
 }

Quoted 1 line

However, the check for 'if (__vma_private_lock(vma))' was dropped.

Oh ugh. I definitely added that in somewhere, but must have committed that to the wrong git branch :(

Let me send out a new version with that change.

Sorry about that.

Signature · 1 line
All Rights Reversed.
#4 lore raw

PATCH v4 2/3 hugetlbfs: close race between MADV_DONTNEED and page fault

In reply to [email protected]

From: Rik van Riel <[email protected]>

Malloc libraries, like jemalloc and tcalloc, take decisions on when to call madvise independently from the code in the main application.

This sometimes results in the application page faulting on an address, right after the malloc library has shot down the backing memory with MADV_DONTNEED.

Usually this is harmless, because we always have some 4kB pages sitting around to satisfy a page fault. However, with hugetlbfs systems often allocate only the exact number of huge pages that the application wants.

Due to TLB batching, hugetlbfs MADV_DONTNEED will free pages outside of any lock taken on the page fault path, which can open up the following race condition:

CPU 1 CPU 2

MADV_DONTNEED
unmap page
shoot down TLB entry
page fault
fail to allocate a huge page killed with SIGBUS
free page

Fix that race by pulling the locking from __unmap_hugepage_final_range into helper functions called from zap_page_range_single. This ensures page faults stay locked out of the MADV_DONTNEED VMA until the huge pages have actually been freed.

---
 include/linux/hugetlb.h | 35 +++++++++++++++++++++++++++++++++--
 mm/hugetlb.c            | 20 +++++++++++---------
 mm/memory.c             | 13 ++++++++-----
 3 files changed, 52 insertions(+), 16 deletions(-)
include/linux/hugetlb.h +33 -2
index 694928fa06a3..d9ec500cfef9 100644
@@ -139,7 +139,7 @@ struct page *hugetlb_follow_page_mask(struct vm_area_struct *vma,
 void unmap_hugepage_range(struct vm_area_struct *,
 			  unsigned long, unsigned long, struct page *,
 			  zap_flags_t);
-void __unmap_hugepage_range_final(struct mmu_gather *tlb,
+void __unmap_hugepage_range(struct mmu_gather *tlb,
 			  struct vm_area_struct *vma,
 			  unsigned long start, unsigned long end,
 			  struct page *ref_page, zap_flags_t zap_flags);
@@ -246,6 +246,25 @@ int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma,
 void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma,
 				unsigned long *start, unsigned long *end);
 
+extern void __hugetlb_zap_begin(struct vm_area_struct *vma,
+				unsigned long *begin, unsigned long *end);
+extern void __hugetlb_zap_end(struct vm_area_struct *vma,
+			      struct zap_details *details);
+
+static inline void hugetlb_zap_begin(struct vm_area_struct *vma,
+				     unsigned long *start, unsigned long *end)
+{
+	if (is_vm_hugetlb_page(vma))
+		__hugetlb_zap_begin(vma, start, end);
+}
+
+static inline void hugetlb_zap_end(struct vm_area_struct *vma,
+				   struct zap_details *details)
+{
+	if (is_vm_hugetlb_page(vma))
+		__hugetlb_zap_end(vma, details);
+}
+
 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);
@@ -297,6 +316,18 @@ static inline void adjust_range_if_pmd_sharing_possible(
 {
 }
 
+static inline void hugetlb_zap_begin(
+				struct vm_area_struct *vma,
+				unsigned long *start, unsigned long *end)
+{
+}
+
+static inline void hugetlb_zap_end(
+				struct vm_area_struct *vma,
+				struct zap_details *details)
+{
+}
+
 static inline struct page *hugetlb_follow_page_mask(
     struct vm_area_struct *vma, unsigned long address, unsigned int flags,
     unsigned int *page_mask)
@@ -442,7 +473,7 @@ static inline long hugetlb_change_protection(
 	return 0;
 }
 
-static inline void __unmap_hugepage_range_final(struct mmu_gather *tlb,
+static inline void __unmap_hugepage_range(struct mmu_gather *tlb,
 			struct vm_area_struct *vma, unsigned long start,
 			unsigned long end, struct page *ref_page,
 			zap_flags_t zap_flags)
mm/hugetlb.c +11 -9
index e859fba5bc7d..5f8b82e902a8 100644
@@ -5306,9 +5306,9 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma,
 	return len + old_addr - old_end;
 }
 
-static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
-				   unsigned long start, unsigned long end,
-				   struct page *ref_page, zap_flags_t zap_flags)
+void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
+			    unsigned long start, unsigned long end,
+			    struct page *ref_page, zap_flags_t zap_flags)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	unsigned long address;
@@ -5435,16 +5435,18 @@ static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct
 		tlb_flush_mmu_tlbonly(tlb);
 }
 
-void __unmap_hugepage_range_final(struct mmu_gather *tlb,
-			  struct vm_area_struct *vma, unsigned long start,
-			  unsigned long end, struct page *ref_page,
-			  zap_flags_t zap_flags)
+void __hugetlb_zap_begin(struct vm_area_struct *vma,
+			 unsigned long *start, unsigned long *end)
 {
+	adjust_range_if_pmd_sharing_possible(vma, start, end);
 	hugetlb_vma_lock_write(vma);
 	i_mmap_lock_write(vma->vm_file->f_mapping);
+}
 
-	/* mmu notification performed in caller */
-	__unmap_hugepage_range(tlb, vma, start, end, ref_page, zap_flags);
+void __hugetlb_zap_end(struct vm_area_struct *vma,
+		       struct zap_details *details)
+{
+	zap_flags_t zap_flags = details ? details->zap_flags : 0;
 
 	if (zap_flags & ZAP_FLAG_UNMAP) {	/* final unmap */
 		/*
mm/memory.c +8 -5
index 6c264d2f969c..517221f01303 100644
@@ -1683,7 +1683,7 @@ static void unmap_single_vma(struct mmu_gather *tlb,
 			if (vma->vm_file) {
 				zap_flags_t zap_flags = details ?
 				    details->zap_flags : 0;
-				__unmap_hugepage_range_final(tlb, vma, start, end,
+				__unmap_hugepage_range(tlb, vma, start, end,
 							     NULL, zap_flags);
 			}
 		} else
@@ -1728,8 +1728,12 @@ void unmap_vmas(struct mmu_gather *tlb, struct ma_state *mas,
 				start_addr, end_addr);
 	mmu_notifier_invalidate_range_start(&range);
 	do {
-		unmap_single_vma(tlb, vma, start_addr, end_addr, &details,
+		unsigned long start = start_addr;
+		unsigned long end = end_addr;
+		hugetlb_zap_begin(vma, &start, &end);
+		unmap_single_vma(tlb, vma, start, end, &details,
 				 mm_wr_locked);
+		hugetlb_zap_end(vma, &details);
 	} while ((vma = mas_find(mas, tree_end - 1)) != NULL);
 	mmu_notifier_invalidate_range_end(&range);
 }
@@ -1753,9 +1757,7 @@ void zap_page_range_single(struct vm_area_struct *vma, unsigned long address,
 	lru_add_drain();
 	mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm,
 				address, end);
-	if (is_vm_hugetlb_page(vma))
-		adjust_range_if_pmd_sharing_possible(vma, &range.start,
-						     &range.end);
+	hugetlb_zap_begin(vma, &range.start, &range.end);
 	tlb_gather_mmu(&tlb, vma->vm_mm);
 	update_hiwater_rss(vma->vm_mm);
 	mmu_notifier_invalidate_range_start(&range);
@@ -1766,6 +1768,7 @@ void zap_page_range_single(struct vm_area_struct *vma, unsigned long address,
 	unmap_single_vma(&tlb, vma, address, end, details, false);
 	mmu_notifier_invalidate_range_end(&range);
 	tlb_finish_mmu(&tlb);
+	hugetlb_zap_end(vma, details);
 }
 
 /**
Signature · 1 line
2.41.0
maintainer
#5 lore raw
Quoted 28 lines · On Mon, 25 Sep 2023 23:10:51 -0400 [email protected] wrote:

From: Rik van Riel <[email protected]>

Malloc libraries, like jemalloc and tcalloc, take decisions on when to call madvise independently from the code in the main application.

This sometimes results in the application page faulting on an address, right after the malloc library has shot down the backing memory with MADV_DONTNEED.

Usually this is harmless, because we always have some 4kB pages sitting around to satisfy a page fault. However, with hugetlbfs systems often allocate only the exact number of huge pages that the application wants.

Due to TLB batching, hugetlbfs MADV_DONTNEED will free pages outside of any lock taken on the page fault path, which can open up the following race condition:

CPU 1 CPU 2

MADV_DONTNEED
unmap page
shoot down TLB entry
page fault
fail to allocate a huge page killed with SIGBUS
free page

Quoted 5 lines

Fix that race by pulling the locking from __unmap_hugepage_final_range into helper functions called from zap_page_range_single. This ensures page faults stay locked out of the MADV_DONTNEED VMA until the huge pages have actually been freed.

Was a -stable backport considered?

#6 lore raw
Quoted 43 lines · Andrew Morton
Quoted 33 lines · On Mon, 25 Sep 2023 23:10:51 -0400 [email protected] wrote:

From: Rik van Riel <[email protected]>

Malloc libraries, like jemalloc and tcalloc, take decisions on when to call madvise independently from the code in the main application.

This sometimes results in the application page faulting on an address,
right after the malloc library has shot down the backing memory with
MADV_DONTNEED.

Usually this is harmless, because we always have some 4kB pages sitting around to satisfy a page fault. However, with hugetlbfs systems often allocate only the exact number of huge pages that the application wants.

Due to TLB batching, hugetlbfs MADV_DONTNEED will free pages outside of
any lock taken on the page fault path, which can open up the following
race condition:

       CPU 1                            CPU 2

       MADV_DONTNEED
       unmap page
       shoot down TLB entry
                                       page fault
                                       fail to allocate a huge page killed with SIGBUS free page

Quoted 7 lines

Fix that race by pulling the locking from __unmap_hugepage_final_range
into helper functions called from zap_page_range_single. This ensures
page faults stay locked out of the MADV_DONTNEED VMA until the huge pages have actually been freed.

Quoted 2 lines

Was a -stable backport considered?

That's a good idea. I'll have to see how far back
the hugetlb_vma_*_lock stuff exists.

We probably don't want to backport all the required infrastructure everywhere.

Signature · 1 line
All Rights Reversed.
#7 lore raw

PATCH v4 3/3 hugetlbfs: replace hugetlb_vma_lock with invalidate_lock

In reply to [email protected]

From: Rik van Riel <[email protected]>

Replace the custom hugetlbfs VMA locking code with the recently introduced invalidate_lock. This greatly simplifies things.

However, this is a large enough change that it should probably go in separately from the other changes.

---
 fs/hugetlbfs/inode.c    |  68 +-----------
 include/linux/fs.h      |   6 ++
 include/linux/hugetlb.h |  21 +---
 mm/hugetlb.c            | 227 ++++------------------------------------
 4 files changed, 32 insertions(+), 290 deletions(-)
fs/hugetlbfs/inode.c +5 -63
index 316c4cebd3f3..711fd3f5d86f 100644
@@ -485,7 +485,6 @@ static void hugetlb_unmap_file_folio(struct hstate *h,
 					struct folio *folio, pgoff_t index)
 {
 	struct rb_root_cached *root = &mapping->i_mmap;
-	struct hugetlb_vma_lock *vma_lock;
 	struct page *page = &folio->page;
 	struct vm_area_struct *vma;
 	unsigned long v_start;
@@ -495,9 +494,9 @@ static void hugetlb_unmap_file_folio(struct hstate *h,
 	start = index * pages_per_huge_page(h);
 	end = (index + 1) * pages_per_huge_page(h);
 
+	filemap_invalidate_lock(mapping);
 	i_mmap_lock_write(mapping);
-retry:
-	vma_lock = NULL;
+
 	vma_interval_tree_foreach(vma, root, start, end - 1) {
 		v_start = vma_offset_start(vma, start);
 		v_end = vma_offset_end(vma, end);
@@ -505,62 +504,13 @@ static void hugetlb_unmap_file_folio(struct hstate *h,
 		if (!hugetlb_vma_maps_page(vma, v_start, page))
 			continue;
 
-		if (!hugetlb_vma_trylock_write(vma)) {
-			vma_lock = vma->vm_private_data;
-			/*
-			 * If we can not get vma lock, we need to drop
-			 * immap_sema and take locks in order.  First,
-			 * take a ref on the vma_lock structure so that
-			 * we can be guaranteed it will not go away when
-			 * dropping immap_sema.
-			 */
-			kref_get(&vma_lock->refs);
-			break;
-		}
-
 		unmap_hugepage_range(vma, v_start, v_end, NULL,
 				     ZAP_FLAG_DROP_MARKER);
 		hugetlb_vma_unlock_write(vma);
 	}
 
+	filemap_invalidate_unlock(mapping);
 	i_mmap_unlock_write(mapping);
-
-	if (vma_lock) {
-		/*
-		 * Wait on vma_lock.  We know it is still valid as we have
-		 * a reference.  We must 'open code' vma locking as we do
-		 * not know if vma_lock is still attached to vma.
-		 */
-		down_write(&vma_lock->rw_sema);
-		i_mmap_lock_write(mapping);
-
-		vma = vma_lock->vma;
-		if (!vma) {
-			/*
-			 * If lock is no longer attached to vma, then just
-			 * unlock, drop our reference and retry looking for
-			 * other vmas.
-			 */
-			up_write(&vma_lock->rw_sema);
-			kref_put(&vma_lock->refs, hugetlb_vma_lock_release);
-			goto retry;
-		}
-
-		/*
-		 * vma_lock is still attached to vma.  Check to see if vma
-		 * still maps page and if so, unmap.
-		 */
-		v_start = vma_offset_start(vma, start);
-		v_end = vma_offset_end(vma, end);
-		if (hugetlb_vma_maps_page(vma, v_start, page))
-			unmap_hugepage_range(vma, v_start, v_end, NULL,
-					     ZAP_FLAG_DROP_MARKER);
-
-		kref_put(&vma_lock->refs, hugetlb_vma_lock_release);
-		hugetlb_vma_unlock_write(vma);
-
-		goto retry;
-	}
 }
 
 static void
@@ -578,20 +528,10 @@ hugetlb_vmdelete_list(struct rb_root_cached *root, pgoff_t start, pgoff_t end,
 		unsigned long v_start;
 		unsigned long v_end;
 
-		if (!hugetlb_vma_trylock_write(vma))
-			continue;
-
 		v_start = vma_offset_start(vma, start);
 		v_end = vma_offset_end(vma, end);
 
 		unmap_hugepage_range(vma, v_start, v_end, NULL, zap_flags);
-
-		/*
-		 * Note that vma lock only exists for shared/non-private
-		 * vmas.  Therefore, lock is not held when calling
-		 * unmap_hugepage_range for private vmas.
-		 */
-		hugetlb_vma_unlock_write(vma);
 	}
 }
 
@@ -725,10 +665,12 @@ static void hugetlb_vmtruncate(struct inode *inode, loff_t offset)
 	pgoff = offset >> PAGE_SHIFT;
 
 	i_size_write(inode, offset);
+	filemap_invalidate_lock(mapping);
 	i_mmap_lock_write(mapping);
 	if (!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root))
 		hugetlb_vmdelete_list(&mapping->i_mmap, pgoff, 0,
 				      ZAP_FLAG_DROP_MARKER);
+	filemap_invalidate_unlock(mapping);
 	i_mmap_unlock_write(mapping);
 	remove_inode_hugepages(inode, offset, LLONG_MAX);
 }
include/linux/fs.h +6 -0
index 4aeb3fa11927..b455a8913db4 100644
@@ -847,6 +847,12 @@ static inline void filemap_invalidate_lock(struct address_space *mapping)
 	down_write(&mapping->invalidate_lock);
 }
 
+static inline int filemap_invalidate_trylock(
+					struct address_space *mapping)
+{
+	return down_write_trylock(&mapping->invalidate_lock);
+}
+
 static inline void filemap_invalidate_unlock(struct address_space *mapping)
 {
 	up_write(&mapping->invalidate_lock);
include/linux/hugetlb.h +3 -18
index d9ec500cfef9..2908c47e7bf2 100644
@@ -60,7 +60,6 @@ struct resv_map {
 	long adds_in_progress;
 	struct list_head region_cache;
 	long region_cache_count;
-	struct rw_semaphore rw_sema;
 #ifdef CONFIG_CGROUP_HUGETLB
 	/*
 	 * On private mappings, the counter to uncharge reservations is stored
@@ -107,12 +106,6 @@ struct file_region {
 #endif
 };
 
-struct hugetlb_vma_lock {
-	struct kref refs;
-	struct rw_semaphore rw_sema;
-	struct vm_area_struct *vma;
-};
-
 extern struct resv_map *resv_map_alloc(void);
 void resv_map_release(struct kref *ref);
 
@@ -1277,17 +1270,9 @@ hugetlb_walk(struct vm_area_struct *vma, unsigned long addr, unsigned long sz)
 {
 #if defined(CONFIG_HUGETLB_PAGE) && \
 	defined(CONFIG_ARCH_WANT_HUGE_PMD_SHARE) && defined(CONFIG_LOCKDEP)
-	struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
-
-	/*
-	 * If pmd sharing possible, locking needed to safely walk the
-	 * hugetlb pgtables.  More information can be found at the comment
-	 * above huge_pte_offset() in the same file.
-	 *
-	 * NOTE: lockdep_is_held() is only defined with CONFIG_LOCKDEP.
-	 */
-	if (__vma_shareable_lock(vma))
-		WARN_ON_ONCE(!lockdep_is_held(&vma_lock->rw_sema) &&
+	if (vma->vm_file)
+		WARN_ON_ONCE(!lockdep_is_held(
+				 &vma->vm_file->f_mapping->invalidate_lock) &&
 			     !lockdep_is_held(
 				 &vma->vm_file->f_mapping->i_mmap_rwsem));
 #endif
mm/hugetlb.c +18 -209

329 lines not on this page · raw message

Signature · 1 line
2.41.0