Re: [syzbot] upstream test error: BUG: sleeping function called from invalid context in stack_depot_save

[Hillf Danton <hdanton@sina.com>]

On Thu, 1 Jul 2021 13:10:37 +0200 Dmitry Vyukov wrote:
>On Thu, Jul 1, 2021 at 1:00 PM syzbot wrote:
>>
>> Hello,
>>
>> syzbot found the following issue on:
>>
>> HEAD commit:    dbe69e43 Merge tag 'net-next-5.14' of git://git.kernel.org..
>> git tree:       upstream
>> console output: https://syzkaller.appspot.com/x/log.txt?x=1216d478300000
>> kernel config:  https://syzkaller.appspot.com/x/.config?x=47e4697be2f5b985
>> dashboard link: https://syzkaller.appspot.com/bug?extid=e45919db2eab5e837646
>>
>> IMPORTANT: if you fix the issue, please add the following tag to the commit:
>> Reported-by: syzbot+e45919db2eab5e837646@syzkaller.appspotmail.com
>
>+kasan-dev@ for for stack_depot_save warning
>
>> BUG: sleeping function called from invalid context at mm/page_alloc.c:5179
>> in_atomic(): 0, irqs_disabled(): 1, non_block: 0, pid: 8436, name: syz-fuzzer
>> INFO: lockdep is turned off.
>> irq event stamp: 0
>> hardirqs last  enabled at (0): [<0000000000000000>] 0x0
>> hardirqs last disabled at (0): [<ffffffff814406db>] copy_process+0x1e1b/0x74c0 kernel/fork.c:2061
>> softirqs last  enabled at (0): [<ffffffff8144071c>] copy_process+0x1e5c/0x74c0 kernel/fork.c:2065
>> softirqs last disabled at (0): [<0000000000000000>] 0x0
>> CPU: 1 PID: 8436 Comm: syz-fuzzer Tainted: G        W         5.13.0-syzkaller #0
>> Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
>> Call Trace:
>>  __dump_stack lib/dump_stack.c:79 [inline]
>>  dump_stack_lvl+0xcd/0x134 lib/dump_stack.c:96
>>  ___might_sleep.cold+0x1f1/0x237 kernel/sched/core.c:9153
>>  prepare_alloc_pages+0x3da/0x580 mm/page_alloc.c:5179
>>  __alloc_pages+0x12f/0x500 mm/page_alloc.c:5375
>>  alloc_pages+0x18c/0x2a0 mm/mempolicy.c:2272
>>  stack_depot_save+0x39d/0x4e0 lib/stackdepot.c:303
>>  save_stack+0x15e/0x1e0 mm/page_owner.c:120
>>  __set_page_owner+0x50/0x290 mm/page_owner.c:181
>>  prep_new_page mm/page_alloc.c:2445 [inline]
>>  __alloc_pages_bulk+0x8b9/0x1870 mm/page_alloc.c:5313
>>  alloc_pages_bulk_array_node include/linux/gfp.h:557 [inline]
>>  vm_area_alloc_pages mm/vmalloc.c:2775 [inline]
>>  __vmalloc_area_node mm/vmalloc.c:2845 [inline]
>>  __vmalloc_node_range+0x39d/0x960 mm/vmalloc.c:2947
>>  __vmalloc_node mm/vmalloc.c:2996 [inline]
>>  vzalloc+0x67/0x80 mm/vmalloc.c:3066
>>  n_tty_open+0x16/0x170 drivers/tty/n_tty.c:1914
>>  tty_ldisc_open+0x9b/0x110 drivers/tty/tty_ldisc.c:464
>>  tty_ldisc_setup+0x43/0x100 drivers/tty/tty_ldisc.c:781
>>  tty_init_dev.part.0+0x1f4/0x610 drivers/tty/tty_io.c:1461
>>  tty_init_dev include/linux/err.h:36 [inline]
>>  tty_open_by_driver drivers/tty/tty_io.c:2102 [inline]
>>  tty_open+0xb16/0x1000 drivers/tty/tty_io.c:2150
>>  chrdev_open+0x266/0x770 fs/char_dev.c:414
>>  do_dentry_open+0x4c8/0x11c0 fs/open.c:826
>>  do_open fs/namei.c:3361 [inline]
>>  path_openat+0x1c0e/0x27e0 fs/namei.c:3494
>>  do_filp_open+0x190/0x3d0 fs/namei.c:3521
>>  do_sys_openat2+0x16d/0x420 fs/open.c:1195
>>  do_sys_open fs/open.c:1211 [inline]
>>  __do_sys_openat fs/open.c:1227 [inline]
>>  __se_sys_openat fs/open.c:1222 [inline]
>>  __x64_sys_openat+0x13f/0x1f0 fs/open.c:1222
>>  do_syscall_x64 arch/x86/entry/common.c:50 [inline]
>>  do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80
>>  entry_SYSCALL_64_after_hwframe+0x44/0xae

One of the quick fixes is move preparing new page out of the local lock (with
irq disabled) if it is difficult to add changes in saving stack.

+++ x/mm/page_alloc.c
@@ -5231,6 +5231,7 @@ unsigned long __alloc_pages_bulk(gfp_t g
 	gfp_t alloc_gfp;
 	unsigned int alloc_flags = ALLOC_WMARK_LOW;
 	int nr_populated = 0, nr_account = 0;
+	LIST_HEAD(head);
 
 	if (unlikely(nr_pages <= 0))
 		return 0;
@@ -5308,17 +5309,29 @@ unsigned long __alloc_pages_bulk(gfp_t g
 			break;
 		}
 		nr_account++;
-
-		prep_new_page(page, 0, gfp, 0);
-		if (page_list)
-			list_add(&page->lru, page_list);
-		else
-			page_array[nr_populated] = page;
+		list_add(&page->lru, &head);
 		nr_populated++;
 	}
 
 	local_unlock_irqrestore(&pagesets.lock, flags);
 
+	list_for_each_entry(page, &head, lru)
+		prep_new_page(page, 0, gfp, 0);
+
+	if (page_list)
+		list_splice(&head, page_list);
+	else {
+		int i; 
+
+		for (i = 0; i < nr_pages && !list_empty(&head); i++) {
+			/* Skip existing pages */
+			if (page_array[i])
+				continue;
+			page = list_first_entry(&head, struct page, lru);
+			list_del_init(&page->lru);
+			page_array[i] = page;
+		}
+	}
 	__count_zid_vm_events(PGALLOC, zone_idx(zone), nr_account);
 	zone_statistics(ac.preferred_zoneref->zone, zone, nr_account);