On 7/19/19 6:01 AM, Vlastimil Babka wrote:
On 7/18/19 7:17 PM, Yang Shi wrote:
When running syzkaller internally, we ran into the below bug on 4.9.x
kernel:
kernel BUG at mm/huge_memory.c:2124!
invalid opcode: 0000 [#1] SMP KASAN
Dumping ftrace buffer:
(ftrace buffer empty)
Modules linked in:
CPU: 0 PID: 1518 Comm: syz-executor107 Not tainted 4.9.168+ #2
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 0.5.1 01/01/2011
task: ffff880067b34900 task.stack: ffff880068998000
RIP: 0010:[<ffffffff81895d6b>] [<ffffffff81895d6b>] split_huge_page_to_list+0x8fb/0x1030 mm/huge_memory.c:2124
RSP: 0018:ffff88006899f980 EFLAGS: 00010286
RAX: 0000000000000000 RBX: ffffea00018f1700 RCX: 0000000000000000
RDX: 1ffffd400031e2e7 RSI: 0000000000000001 RDI: ffffea00018f1738
RBP: ffff88006899f9e8 R08: 0000000000000001 R09: 0000000000000000
R10: 0000000000000000 R11: fffffbfff0d8b13e R12: ffffea00018f1400
R13: ffffea00018f1400 R14: ffffea00018f1720 R15: ffffea00018f1401
FS: 00007fa333996740(0000) GS:ffff88006c600000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000020000040 CR3: 0000000066b9c000 CR4: 00000000000606f0
Stack:
0000000000000246 ffff880067b34900 0000000000000000 ffff88007ffdc000
0000000000000000 ffff88006899f9e8 ffffffff812b4015 ffff880064c64e18
ffffea00018f1401 dffffc0000000000 ffffea00018f1700 0000000020ffd000
Call Trace:
[<ffffffff818490f1>] split_huge_page include/linux/huge_mm.h:100 [inline]
[<ffffffff818490f1>] queue_pages_pte_range+0x7e1/0x1480 mm/mempolicy.c:538
[<ffffffff817ed0da>] walk_pmd_range mm/pagewalk.c:50 [inline]
[<ffffffff817ed0da>] walk_pud_range mm/pagewalk.c:90 [inline]
[<ffffffff817ed0da>] walk_pgd_range mm/pagewalk.c:116 [inline]
[<ffffffff817ed0da>] __walk_page_range+0x44a/0xdb0 mm/pagewalk.c:208
[<ffffffff817edb94>] walk_page_range+0x154/0x370 mm/pagewalk.c:285
[<ffffffff81844515>] queue_pages_range+0x115/0x150 mm/mempolicy.c:694
[<ffffffff8184f493>] do_mbind mm/mempolicy.c:1241 [inline]
[<ffffffff8184f493>] SYSC_mbind+0x3c3/0x1030 mm/mempolicy.c:1370
[<ffffffff81850146>] SyS_mbind+0x46/0x60 mm/mempolicy.c:1352
[<ffffffff810097e2>] do_syscall_64+0x1d2/0x600 arch/x86/entry/common.c:282
[<ffffffff82ff6f93>] entry_SYSCALL_64_after_swapgs+0x5d/0xdb
Code: c7 80 1c 02 00 e8 26 0a 76 01 <0f> 0b 48 c7 c7 40 46 45 84 e8 4c
RIP [<ffffffff81895d6b>] split_huge_page_to_list+0x8fb/0x1030 mm/huge_memory.c:2124
RSP <ffff88006899f980>
...
@@ -532,7 +531,14 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr,
has_unmovable |= true;
break;
}
- migrate_page_add(page, qp->pagelist, flags);
+
+ /*
+ * Do not abort immediately since there may be
+ * temporary off LRU pages in the range. Still
+ * need migrate other LRU pages.
+ */
+ if (migrate_page_add(page, qp->pagelist, flags))
+ has_unmovable |= true;
Also = instead of |=
OK
} else
break;
}
@@ -961,10 +967,21 @@ static long do_get_mempolicy(int *policy, nodemask_t *nmask,
/*
* page migration, thp tail pages can be passed.
*/
-static void migrate_page_add(struct page *page, struct list_head *pagelist,
+static int migrate_page_add(struct page *page, struct list_head *pagelist,
unsigned long flags)
{
struct page *head = compound_head(page);
+
+ /*
+ * Non-movable page may reach here. And, there may be
+ * temporary off LRU pages or non-LRU movable pages.
+ * Treat them as unmovable pages since they can't be
+ * isolated, so they can't be moved at the moment. It
+ * should return -EIO for this case too.
+ */
+ if (!PageLRU(head) && (flags & MPOL_MF_STRICT))
+ return -EIO;
As this test is racy, why not just use the result of isolate_lru_page().
Sounds good to me. Will fix in v4.
Thanks,
Yang
+
/*
* Avoid migrating a page that is shared with others.
*/
@@ -976,6 +993,8 @@ static void migrate_page_add(struct page *page, struct list_head *pagelist,
hpage_nr_pages(head));
}
}
+
+ return 0;
}
/* page allocation callback for NUMA node migration */
@@ -1178,9 +1197,10 @@ static struct page *new_page(struct page *page, unsigned long start)
}
#else
-static void migrate_page_add(struct page *page, struct list_head *pagelist,
+static int migrate_page_add(struct page *page, struct list_head *pagelist,
unsigned long flags)
{
+ return -EIO;
}
int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from,
