Re: kernel BUG at include/linux/mm.h:699

[Hillf Danton <hdanton@sina.com>]

Sun, 19 Apr 2020 08:28:14 -0700
> syzbot found the following crash on:
> 
> HEAD commit:    8632e9b5 Merge tag 'hyperv-fixes-signed' of git://git.kern..
> git tree:       upstream
> console output: https://syzkaller.appspot.com/x/log.txt?x=11ac6be0100000
> kernel config:  https://syzkaller.appspot.com/x/.config?x=5d351a1019ed81a2
> dashboard link: https://syzkaller.appspot.com/bug?extid=a923008018a2d298247b
> compiler:       gcc (GCC) 9.0.0 20181231 (experimental)
> 
> Unfortunately, I don't have any reproducer for this crash yet.
> 
> IMPORTANT: if you fix the bug, please add the following tag to the commit:
> Reported-by: syzbot+a923008018a2d298247b@syzkaller.appspotmail.com
> 
> raw: 0000000000000000 0000000000000000 00000000ffffffff 0000000000000000
> page dumped because: VM_BUG_ON_PAGE(page_ref_count(page) == 0)
> ------------[ cut here ]------------
> kernel BUG at include/linux/mm.h:699!
> invalid opcode: 0000 [#1] PREEMPT SMP KASAN
> CPU: 0 PID: 14511 Comm: syz-executor.4 Not tainted 5.7.0-rc1-syzkaller #0
> Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
> RIP: 0010:put_page_testzero include/linux/mm.h:699 [inline]
> RIP: 0010:put_page_testzero include/linux/mm.h:697 [inline]
> RIP: 0010:release_pages+0x799/0x19b0 mm/swap.c:823
> Code: c7 f9 ff ff e8 38 9d dd ff 48 89 ef e8 20 ac ff ff e9 96 fe ff ff e8 26 9d dd ff 48 c7 c6 c0 44 33 88 48 89 ef e8 87 86 09 00 <0f> 0b e8 10 9d dd ff 49 8d 6c 24 ff e9 c5 f9 ff ff 4c 8d 6d 08 31
> RSP: 0018:ffffc90007fb7640 EFLAGS: 00010293
> RAX: ffff8880a19f4280 RBX: 0000000000000000 RCX: ffffffff819f2d28
> RDX: 0000000000000000 RSI: ffffffff819596e9 RDI: ffffea0000000038
> RBP: ffffea0000000000 R08: ffff8880a19f4280 R09: ffffed1015cc66a9
> R10: ffff8880ae633547 R11: ffffed1015cc66a8 R12: ffffea0000000034
> R13: 0000000000000000 R14: dffffc0000000000 R15: 00000000000000c6
> FS:  00007fc0946fc700(0000) GS:ffff8880ae600000(0000) knlGS:0000000000000000
> CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
> CR2: 00007f2142ba1db8 CR3: 000000008859f000 CR4: 00000000001426f0
> DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
> DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
> Call Trace:
>  tlb_batch_pages_flush mm/mmu_gather.c:49 [inline]
>  tlb_flush_mmu_free mm/mmu_gather.c:242 [inline]
>  tlb_flush_mmu+0x8d/0x610 mm/mmu_gather.c:249
>  zap_pte_range mm/memory.c:1158 [inline]
>  zap_pmd_range mm/memory.c:1196 [inline]
>  zap_pud_range mm/memory.c:1225 [inline]
>  zap_p4d_range mm/memory.c:1246 [inline]
>  unmap_page_range+0x198d/0x25d0 mm/memory.c:1267
>  unmap_single_vma+0x196/0x300 mm/memory.c:1312
>  unmap_vmas+0x16f/0x2f0 mm/memory.c:1344
>  exit_mmap+0x2aa/0x510 mm/mmap.c:3150
>  __mmput kernel/fork.c:1085 [inline]
>  mmput+0x168/0x4b0 kernel/fork.c:1106
>  exit_mm kernel/exit.c:479 [inline]
>  do_exit+0xa51/0x2dd0 kernel/exit.c:782
>  do_group_exit+0x125/0x340 kernel/exit.c:893
>  get_signal+0x47b/0x24e0 kernel/signal.c:2739
>  do_signal+0x81/0x2240 arch/x86/kernel/signal.c:784
>  exit_to_usermode_loop+0x26c/0x360 arch/x86/entry/common.c:161
>  prepare_exit_to_usermode arch/x86/entry/common.c:196 [inline]
>  syscall_return_slowpath arch/x86/entry/common.c:279 [inline]
>  do_syscall_64+0x6b1/0x7d0 arch/x86/entry/common.c:305
>  entry_SYSCALL_64_after_hwframe+0x49/0xb3

Flush TLB every chance before we get every thing done.

--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1080,8 +1080,8 @@ again:
 			page_remove_rmap(page, false);
 			if (unlikely(page_mapcount(page) < 0))
 				print_bad_pte(vma, addr, ptent, page);
+			force_flush = 1;
 			if (unlikely(__tlb_remove_page(tlb, page))) {
-				force_flush = 1;
 				addr += PAGE_SIZE;
 				break;
 			}
@@ -1146,10 +1146,9 @@ again:
 		tlb_flush_mmu(tlb);
 	}
 
-	if (addr != end) {
-		cond_resched();
+	cond_resched();
+	if (addr != end)
 		goto again;
-	}
 
 	return addr;
 }