[PATCH] hugetlb: supports unmapping private mappings

[PATCH] hugetlb: supports unmapping private mappings

[Edward Adam Davis]

If a file has a private mapping, then truncating the file's original logic
will only unmap it according to the shared mapping method, potentially
hitting:

refcount_t: addition on 0; use-after-free.
kernel BUG at lib/refcount.c:34!
RIP: 0010:refcount_warn_saturate+0xf0/0x110 lib/refcount.c:34
Call Trace:
 kref_get include/linux/kref.h:45 [inline]
 hugetlb_unmap_file_folio fs/hugetlbfs/inode.c:413 [inline]
 remove_inode_single_folio fs/hugetlbfs/inode.c:512 [inline]
 remove_inode_hugepages+0xbdb/0x10f0 fs/hugetlbfs/inode.c:577
 hugetlb_vmtruncate fs/hugetlbfs/inode.c:621 [inline]
 hugetlbfs_setattr+0x4f0/0x6d0 fs/hugetlbfs/inode.c:856
 notify_change+0xbb8/0xec0 fs/attr.c:556
 do_truncate+0x1c2/0x250 fs/open.c:68

Add logic to handle the unmapping of private mappings.

Fixes: 40549ba8f8e0 ("hugetlb: use new vma_lock for pmd sharing synchronization")
Reported-by: syzbot+2fcec0eca7f4cade53b2@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=2fcec0eca7f4cade53b2
Signed-off-by: Edward Adam Davis <eadavis@sina.com>
---
 fs/hugetlbfs/inode.c    | 58 +++++++++++++++++++++++++----------------
 include/linux/hugetlb.h |  6 +++++
 mm/hugetlb.c            |  3 +--
 3 files changed, 43 insertions(+), 24 deletions(-)

diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 6656807ce437..166183b7ee36 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -382,6 +382,7 @@ static void hugetlb_unmap_file_folio(struct hstate *h,
 					struct folio *folio, pgoff_t index)
 {
 	struct hugetlb_vma_lock *vma_lock;
+	struct resv_map *resv_map;
 	unsigned long pfn = folio_pfn(folio);
 	struct vm_area_struct *vma;
 	unsigned long v_start;
@@ -394,6 +395,7 @@ static void hugetlb_unmap_file_folio(struct hstate *h,
 	i_mmap_lock_write(mapping);
 retry:
 	vma_lock = NULL;
+	resv_map = NULL;
 	mapping_rmap_tree_foreach(vma, mapping, start, end - 1) {
 		v_start = vma_offset_start(vma, start);
 		v_end = vma_offset_end(vma, end);
@@ -402,15 +404,21 @@ static void hugetlb_unmap_file_folio(struct hstate *h,
 			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);
+			if (vma->vm_flags & VM_MAYSHARE) {
+				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);
+			} else {
+				resv_map = vma_resv_map(vma);
+				kref_get(&resv_map->refs);
+			}
+
 			break;
 		}
 
@@ -421,25 +429,28 @@ static void hugetlb_unmap_file_folio(struct hstate *h,
 
 	i_mmap_unlock_write(mapping);
 
-	if (vma_lock) {
+	if (vma_lock || resv_map) {
 		/*
 		 * 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);
+		hugetlb_vma_lock_write(vma);
 		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;
+		if (vma_lock) {
+			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;
+			}
 		}
 
 		/*
@@ -452,7 +463,10 @@ static void hugetlb_unmap_file_folio(struct hstate *h,
 			unmap_hugepage_range(vma, v_start, v_end, NULL,
 					     ZAP_FLAG_DROP_MARKER);
 
-		kref_put(&vma_lock->refs, hugetlb_vma_lock_release);
+		if (vma_lock)
+			kref_put(&vma_lock->refs, hugetlb_vma_lock_release);
+		else
+			kref_put(&resv_map->refs, resv_map_release);
 		hugetlb_vma_unlock_write(vma);
 
 		goto retry;
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 80a5a03e9cee..f980191c651b 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -268,6 +268,7 @@ 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);
+struct resv_map *vma_resv_map(struct vm_area_struct *vma);
 void hugetlb_vma_assert_locked(struct vm_area_struct *vma);
 void hugetlb_vma_lock_release(struct kref *kref);
 long hugetlb_change_protection(struct vm_area_struct *vma,
@@ -392,6 +393,11 @@ static inline int is_hugepage_only_range(struct mm_struct *mm,
 	return 0;
 }
 
+static inline struct resv_map *vma_resv_map(struct vm_area_struct *vma)
+{
+	return NULL;
+}
+
 #ifdef CONFIG_USERFAULTFD
 static inline int hugetlb_mfill_atomic_pte(pte_t *dst_pte,
 					   struct vm_area_struct *dst_vma,
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index b017ae1dfd6f..def6aebc44fd 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -134,7 +134,6 @@ static int __huge_pmd_unshare(struct mmu_gather *tlb,
 		bool check_locks);
 static void hugetlb_unshare_pmds(struct vm_area_struct *vma,
 		unsigned long start, unsigned long end, bool take_locks);
-static struct resv_map *vma_resv_map(struct vm_area_struct *vma);
 
 static inline bool subpool_is_free(struct hugepage_subpool *spool)
 {
@@ -1145,7 +1144,7 @@ static inline struct resv_map *inode_resv_map(struct inode *inode)
 	return HUGETLBFS_I(inode)->resv_map;
 }
 
-static struct resv_map *vma_resv_map(struct vm_area_struct *vma)
+struct resv_map *vma_resv_map(struct vm_area_struct *vma)
 {
 	VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma);
 	if (vma->vm_flags & VM_MAYSHARE) {
-- 
2.43.0

[syzbot ci] Re: hugetlb: supports unmapping private mappings

[syzbot ci]

syzbot ci has tested the following series

[v1] hugetlb: supports unmapping private mappings
https://lore.kernel.org/all/20261028041528.269829-1-eadavis@sina.com
* [PATCH] hugetlb: supports unmapping private mappings

and found the following issue:
WARNING: bad unlock balance in remove_inode_hugepages

Full report is available here:
https://ci.syzbot.org/series/bf349aec-df0c-48a8-ab82-9f71361a3830

***

WARNING: bad unlock balance in remove_inode_hugepages

tree:      mm-new
URL:       https://kernel.googlesource.com/pub/scm/linux/kernel/git/akpm/mm.git
base:      7d1f84f1b94e79cb95d974ab3ec54cb3a4d64f5b
arch:      amd64
compiler:  Debian clang version 22.1.8 (1~deb13u4), Debian LLD 22.1.8
config:    https://ci.syzbot.org/builds/7d19c5c0-63db-4726-978e-d863eedfb488/config

=====================================
WARNING: bad unlock balance detected!
syzkaller #0 Not tainted
-------------------------------------
syz.4.862/12304 is trying to release lock (&vma_lock->rw_sema) at:
[<ffffffff82b5a0e7>] remove_inode_hugepages+0xc57/0x1220
but there are no more locks to release!

other info that might help us debug this:
locks held by syz.4.862/12304: 4, last CPU#1:
 #0: ffff88810729e460 (sb_writers#12){.+.+}-{0:0}, at: vfs_fallocate+0x5e0/0x7e0
 #1: ffff8881aa537b00 (&sb->s_type->i_mutex_key#24){+.+.}-{4:4}, at: hugetlbfs_fallocate+0x3f7/0x11c0
 #2: ffff8881683dc638 (&hugetlb_fault_mutex_table[i]){+.+.}-{4:4}, at: remove_inode_hugepages+0x370/0x1220
 #3: ffff8881aa537da8 (&hugetlbfs_i_mmap_rwsem_key){+.+.}-{4:4}, at: remove_inode_hugepages+0xa44/0x1220

stack backtrace:
CPU: 1 UID: 0 PID: 12304 Comm: syz.4.862 Not tainted syzkaller #0 PREEMPT(full) 
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.2-debian-1.16.2-1 04/01/2014
Call Trace:
 <TASK>
 dump_stack_lvl+0xe8/0x150
 print_unlock_imbalance_bug+0xdc/0xf0
 lock_release+0x252/0x3c0
 up_write+0x2d/0x4a0
 remove_inode_hugepages+0xc57/0x1220
 hugetlbfs_fallocate+0xc51/0x11c0
 vfs_fallocate+0x65a/0x7e0
 madvise_vma_behavior+0x2cf5/0x43b0
 madvise_walk_vmas+0x576/0xb00
 madvise_do_behavior+0x385/0x540
 do_madvise+0x327/0x3a0
 __x64_sys_madvise+0xa6/0xc0
 do_syscall_64+0x166/0x520
 entry_SYSCALL_64_after_hwframe+0x77/0x7f
RIP: 0033:0x7f0c8dd9f559
Code: ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 e8 ff ff ff f7 d8 64 89 01 48
RSP: 002b:00007f0c8bff6028 EFLAGS: 00000246 ORIG_RAX: 000000000000001c
RAX: ffffffffffffffda RBX: 00007f0c8e026450 RCX: 00007f0c8dd9f559
RDX: 0000000000000009 RSI: 0000000000c00000 RDI: 0000200000400000
RBP: 00007f0c8de36b20 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000
R13: 00007f0c8e0264e8 R14: 00007f0c8e026450 R15: 00007ffc9fc94698
 </TASK>
------------[ cut here ]------------
DEBUG_RWSEMS_WARN_ON((rwsem_owner(sem) != current) && !rwsem_test_oflags(sem, RWSEM_NONSPINNABLE)): count = 0x0, magic = 0xffff88810b4c2608, owner = 0x0, curr 0xffff88816ff4bc00, list not empty
WARNING: kernel/locking/rwsem.c:1413 at up_write+0x35c/0x4a0, CPU#1: syz.4.862/12304
Modules linked in:
CPU: 1 UID: 0 PID: 12304 Comm: syz.4.862 Not tainted syzkaller #0 PREEMPT(full) 
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.2-debian-1.16.2-1 04/01/2014
RIP: 0010:up_write+0x40f/0x4a0
Code: 0d 8c 49 c7 c2 80 33 0d 8c 4c 0f 44 d0 48 8b 7c 24 10 48 c7 c6 20 36 0d 8c 48 8b 14 24 48 8b 4c 24 08 4d 89 e0 4d 89 f9 41 52 <67> 48 0f b9 3a 48 83 c4 08 e8 f3 6f 45 03 e9 d6 fc ff ff 48 c7 c1
RSP: 0018:ffffc900040cede0 EFLAGS: 00010246
RAX: ffffffff8c0d33a0 RBX: ffff88810b4c2608 RCX: ffff88810b4c2608
RDX: 0000000000000000 RSI: ffffffff8c0d3620 RDI: ffffffff917dda70
RBP: dffffc0000000000 R08: 0000000000000000 R09: ffff88816ff4bc00
R10: ffffffff8c0d33a0 R11: ffffed10216984c3 R12: 0000000000000000
R13: ffff88810b4c2610 R14: ffff88810b4c2660 R15: ffff88816ff4bc00
FS:  00007f0c8bff66c0(0000) GS:ffff8882a7c83000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007f8981484378 CR3: 00000001ad2de000 CR4: 00000000000006f0
Call Trace:
 <TASK>
 remove_inode_hugepages+0xc57/0x1220
 hugetlbfs_fallocate+0xc51/0x11c0
 vfs_fallocate+0x65a/0x7e0
 madvise_vma_behavior+0x2cf5/0x43b0
 madvise_walk_vmas+0x576/0xb00
 madvise_do_behavior+0x385/0x540
 do_madvise+0x327/0x3a0
 __x64_sys_madvise+0xa6/0xc0
 do_syscall_64+0x166/0x520
 entry_SYSCALL_64_after_hwframe+0x77/0x7f
RIP: 0033:0x7f0c8dd9f559
Code: ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 e8 ff ff ff f7 d8 64 89 01 48
RSP: 002b:00007f0c8bff6028 EFLAGS: 00000246 ORIG_RAX: 000000000000001c
RAX: ffffffffffffffda RBX: 00007f0c8e026450 RCX: 00007f0c8dd9f559
RDX: 0000000000000009 RSI: 0000000000c00000 RDI: 0000200000400000
RBP: 00007f0c8de36b20 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000
R13: 00007f0c8e0264e8 R14: 00007f0c8e026450 R15: 00007ffc9fc94698
 </TASK>


***

If these findings have caused you to resend the series or submit a
separate fix, please add the following tag to your commit message:
  Tested-by: syzbot@syzkaller.appspotmail.com

---
This report is generated by a bot. It may contain errors.
syzbot ci engineers can be reached at syzkaller@googlegroups.com.

To test a fix for this bug, please reply with `#syz test`
(on a separate line) and attach the patch to the email.

Notes:
- The patch will be applied on top of the tested series (as an
  incremental fix).
- To test a new version of the whole series, please send it directly
  to syzbot@lists.linux.dev.
- Arguments like custom git repos and branches are not supported.