--- /dev/null
+From ed5fc1705afc6874cdcbda6a19101d88730e513c Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Fri, 25 Oct 2019 09:58:36 -0700
+Subject: memfd: Fix locking when tagging pins
+
+From: Matthew Wilcox (Oracle) <willy@infradead.org>
+
+The RCU lock is insufficient to protect the radix tree iteration as
+a deletion from the tree can occur before we take the spinlock to
+tag the entry. In 4.19, this has manifested as a bug with the following
+trace:
+
+kernel BUG at lib/radix-tree.c:1429!
+invalid opcode: 0000 [#1] SMP KASAN PTI
+CPU: 7 PID: 6935 Comm: syz-executor.2 Not tainted 4.19.36 #25
+Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1ubuntu1 04/01/2014
+RIP: 0010:radix_tree_tag_set+0x200/0x2f0 lib/radix-tree.c:1429
+Code: 00 00 5b 5d 41 5c 41 5d 41 5e 41 5f c3 48 89 44 24 10 e8 a3 29 7e fe 48 8b 44 24 10 48 0f ab 03 e9 d2 fe ff ff e8 90 29 7e fe <0f> 0b 48 c7 c7 e0 5a 87 84 e8 f0 e7 08 ff 4c 89 ef e8 4a ff ac fe
+RSP: 0018:ffff88837b13fb60 EFLAGS: 00010016
+RAX: 0000000000040000 RBX: ffff8883c5515d58 RCX: ffffffff82cb2ef0
+RDX: 0000000000000b72 RSI: ffffc90004cf2000 RDI: ffff8883c5515d98
+RBP: ffff88837b13fb98 R08: ffffed106f627f7e R09: ffffed106f627f7e
+R10: 0000000000000001 R11: ffffed106f627f7d R12: 0000000000000004
+R13: ffffea000d7fea80 R14: 1ffff1106f627f6f R15: 0000000000000002
+FS: 00007fa1b8df2700(0000) GS:ffff8883e2fc0000(0000) knlGS:0000000000000000
+CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
+CR2: 00007fa1b8df1db8 CR3: 000000037d4d2001 CR4: 0000000000160ee0
+Call Trace:
+ memfd_tag_pins mm/memfd.c:51 [inline]
+ memfd_wait_for_pins+0x2c5/0x12d0 mm/memfd.c:81
+ memfd_add_seals mm/memfd.c:215 [inline]
+ memfd_fcntl+0x33d/0x4a0 mm/memfd.c:247
+ do_fcntl+0x589/0xeb0 fs/fcntl.c:421
+ __do_sys_fcntl fs/fcntl.c:463 [inline]
+ __se_sys_fcntl fs/fcntl.c:448 [inline]
+ __x64_sys_fcntl+0x12d/0x180 fs/fcntl.c:448
+ do_syscall_64+0xc8/0x580 arch/x86/entry/common.c:293
+
+The problem does not occur in mainline due to the XArray rewrite which
+changed the locking to exclude modification of the tree during iteration.
+At the time, nobody realised this was a bugfix. Backport the locking
+changes to stable.
+
+Cc: stable@vger.kernel.org
+Reported-by: zhong jiang <zhongjiang@huawei.com>
+Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ mm/shmem.c | 18 ++++++++++--------
+ 1 file changed, 10 insertions(+), 8 deletions(-)
+
+diff --git a/mm/shmem.c b/mm/shmem.c
+index 944242491059d..ac8a5fedc2454 100644
+--- a/mm/shmem.c
++++ b/mm/shmem.c
+@@ -2457,11 +2457,12 @@ static void shmem_tag_pins(struct address_space *mapping)
+ void **slot;
+ pgoff_t start;
+ struct page *page;
++ unsigned int tagged = 0;
+
+ lru_add_drain();
+ start = 0;
+- rcu_read_lock();
+
++ spin_lock_irq(&mapping->tree_lock);
+ radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, start) {
+ page = radix_tree_deref_slot(slot);
+ if (!page || radix_tree_exception(page)) {
+@@ -2470,18 +2471,19 @@ static void shmem_tag_pins(struct address_space *mapping)
+ continue;
+ }
+ } else if (page_count(page) - page_mapcount(page) > 1) {
+- spin_lock_irq(&mapping->tree_lock);
+ radix_tree_tag_set(&mapping->page_tree, iter.index,
+ SHMEM_TAG_PINNED);
+- spin_unlock_irq(&mapping->tree_lock);
+ }
+
+- if (need_resched()) {
+- cond_resched_rcu();
+- slot = radix_tree_iter_next(&iter);
+- }
++ if (++tagged % 1024)
++ continue;
++
++ slot = radix_tree_iter_next(&iter);
++ spin_unlock_irq(&mapping->tree_lock);
++ cond_resched();
++ spin_lock_irq(&mapping->tree_lock);
+ }
+- rcu_read_unlock();
++ spin_unlock_irq(&mapping->tree_lock);
+ }
+
+ /*
+--
+2.20.1
+