From f25ebc70b0ed84aefd3be9ea921905cb26fc4090 Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Date: Sat, 30 Nov 2019 17:50:26 -0800
Subject: [PATCH] shmem: pin the file in shmem_fault() if mmap_sem is dropped

References: bnc#1155780 (VM/FS functional and performance backports)
Patch-mainline: v5.5-rc1
Git-commit: 8897c1b1a1795cab23d5ac13e4e23bf0b5f4e0c6

syzbot found the following crash:

  BUG: KASAN: use-after-free in perf_trace_lock_acquire+0x401/0x530 include/trace/events/lock.h:13
  Read of size 8 at addr ffff8880a5cf2c50 by task syz-executor.0/26173

  CPU: 0 PID: 26173 Comm: syz-executor.0 Not tainted 5.3.0-rc6 #146
  Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
  Call Trace:
     perf_trace_lock_acquire+0x401/0x530 include/trace/events/lock.h:13
     trace_lock_acquire include/trace/events/lock.h:13 [inline]
     lock_acquire+0x2de/0x410 kernel/locking/lockdep.c:4411
     __raw_spin_lock include/linux/spinlock_api_smp.h:142 [inline]
     _raw_spin_lock+0x2f/0x40 kernel/locking/spinlock.c:151
     spin_lock include/linux/spinlock.h:338 [inline]
     shmem_fault+0x5ec/0x7b0 mm/shmem.c:2034
     __do_fault+0x111/0x540 mm/memory.c:3083
     do_shared_fault mm/memory.c:3535 [inline]
     do_fault mm/memory.c:3613 [inline]
     handle_pte_fault mm/memory.c:3840 [inline]
     __handle_mm_fault+0x2adf/0x3f20 mm/memory.c:3964
     handle_mm_fault+0x1b5/0x6b0 mm/memory.c:4001
     do_user_addr_fault arch/x86/mm/fault.c:1441 [inline]
     __do_page_fault+0x536/0xdd0 arch/x86/mm/fault.c:1506
     do_page_fault+0x38/0x590 arch/x86/mm/fault.c:1530
     page_fault+0x39/0x40 arch/x86/entry/entry_64.S:1202

It happens if the VMA got unmapped under us while we dropped mmap_sem
and inode got freed.

Pinning the file if we drop mmap_sem fixes the issue.

Link: http://lkml.kernel.org/r/20190927083908.rhifa4mmaxefc24r@box
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Reported-by: syzbot+03ee87124ee05af991bd@syzkaller.appspotmail.com
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Hillf Danton <hdanton@sina.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 mm/shmem.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/mm/shmem.c b/mm/shmem.c
index 2bed4761f279..e70ee2546f78 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -2007,16 +2007,14 @@ static vm_fault_t shmem_fault(struct vm_fault *vmf)
 		    shmem_falloc->waitq &&
 		    vmf->pgoff >= shmem_falloc->start &&
 		    vmf->pgoff < shmem_falloc->next) {
+			struct file *fpin;
 			wait_queue_head_t *shmem_falloc_waitq;
 			DEFINE_WAIT_FUNC(shmem_fault_wait, synchronous_wake_function);
 
 			ret = VM_FAULT_NOPAGE;
-			if ((vmf->flags & FAULT_FLAG_ALLOW_RETRY) &&
-			   !(vmf->flags & FAULT_FLAG_RETRY_NOWAIT)) {
-				/* It's polite to up mmap_sem if we can */
-				up_read(&vma->vm_mm->mmap_sem);
+			fpin = maybe_unlock_mmap_for_io(vmf, NULL);
+			if (fpin)
 				ret = VM_FAULT_RETRY;
-			}
 
 			shmem_falloc_waitq = shmem_falloc->waitq;
 			prepare_to_wait(shmem_falloc_waitq, &shmem_fault_wait,
@@ -2034,6 +2032,9 @@ static vm_fault_t shmem_fault(struct vm_fault *vmf)
 			spin_lock(&inode->i_lock);
 			finish_wait(shmem_falloc_waitq, &shmem_fault_wait);
 			spin_unlock(&inode->i_lock);
+
+			if (fpin)
+				fput(fpin);
 			return ret;
 		}
 		spin_unlock(&inode->i_lock);