lkml.org 
[lkml]   [2019]   [Jun]   [17]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
From
Subject[PATCH] mm: mempolicy: handle vma with unmovable pages mapped correctly in mbind
Date
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>

with the below test:

---8<---

uint64_t r[1] = {0xffffffffffffffff};

int main(void)
{
syscall(__NR_mmap, 0x20000000, 0x1000000, 3, 0x32, -1, 0);
intptr_t res = 0;
res = syscall(__NR_socket, 0x11, 3, 0x300);
if (res != -1)
r[0] = res;
*(uint32_t*)0x20000040 = 0x10000;
*(uint32_t*)0x20000044 = 1;
*(uint32_t*)0x20000048 = 0xc520;
*(uint32_t*)0x2000004c = 1;
syscall(__NR_setsockopt, r[0], 0x107, 0xd, 0x20000040, 0x10);
syscall(__NR_mmap, 0x20fed000, 0x10000, 0, 0x8811, r[0], 0);
*(uint64_t*)0x20000340 = 2;
syscall(__NR_mbind, 0x20ff9000, 0x4000, 0x4002, 0x20000340,
0x45d4, 3);
return 0;
}

---8<---

Actually the test does:

mmap(0x20000000, 16777216, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED|MAP_ANONYMOUS, -1, 0) = 0x20000000
socket(AF_PACKET, SOCK_RAW, 768) = 3
setsockopt(3, SOL_PACKET, PACKET_TX_RING, {block_size=65536, block_nr=1, frame_size=50464, frame_nr=1}, 16) = 0
mmap(0x20fed000, 65536, PROT_NONE, MAP_SHARED|MAP_FIXED|MAP_POPULATE|MAP_DENYWRITE, 3, 0) = 0x20fed000
mbind(..., MPOL_MF_STRICT|MPOL_MF_MOVE) = 0

The setsockopt() would allocate compound pages (16 pages in this test)
for packet tx ring, then the mmap() would call packet_mmap() to map the
pages into the user address space specifed by the mmap() call.

When calling mbind(), it would scan the vma to queue the pages for
migration to the new node. It would split any huge page since 4.9
doesn't support THP migration, however, the packet tx ring compound
pages are not THP and even not movable. So, the above bug is triggered.

However, the later kernel is not hit by this issue due to the commit
d44d363f65780f2ac2ec672164555af54896d40d ("mm: don't assume anonymous
pages have SwapBacked flag"), which just removes the PageSwapBacked
check for a different reason.

But, there is a deeper issue. According to the semantic of mbind(), it
should return -EIO if MPOL_MF_MOVE or MPOL_MF_MOVE_ALL was specified and
the kernel was unable to move all existing pages in the range. The tx ring
of the packet socket is definitely not movable, however, mbind returns
success for this case.

Although the most socket file associates with non-movable pages, but XDP
may have movable pages from gup. So, it sounds not fine to just check
the underlying file type of vma in vma_migratable().

Change migrate_page_add() to check if the page is movable or not, if it
is unmovable, just return -EIO. We don't have to check non-LRU movable
pages since just zsmalloc and virtio-baloon support this. And, they
should be not able to reach here.

With this change the above test would return -EIO as expected.

Signed-off-by: Yang Shi <yang.shi@linux.alibaba.com>
---
include/linux/mempolicy.h | 3 ++-
mm/mempolicy.c | 22 +++++++++++++++++-----
2 files changed, 19 insertions(+), 6 deletions(-)

diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h
index 5228c62..cce7ba3 100644
--- a/include/linux/mempolicy.h
+++ b/include/linux/mempolicy.h
@@ -198,7 +198,8 @@ static inline bool vma_migratable(struct vm_area_struct *vma)
if (vma->vm_file &&
gfp_zone(mapping_gfp_mask(vma->vm_file->f_mapping))
< policy_zone)
- return false;
+ return false;
+
return true;
}

diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 2219e74..4d9e17d 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -403,7 +403,7 @@ void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new)
},
};

-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 queue_pages {
@@ -467,7 +467,9 @@ static int queue_pages_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr,
goto unlock;
}

- migrate_page_add(page, qp->pagelist, flags);
+ ret = migrate_page_add(page, qp->pagelist, flags);
+ if (ret)
+ goto unlock;
} else
ret = -EIO;
unlock:
@@ -521,7 +523,9 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr,
if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) {
if (!vma_migratable(vma))
break;
- migrate_page_add(page, qp->pagelist, flags);
+ ret = migrate_page_add(page, qp->pagelist, flags);
+ if (ret)
+ break;
} else
break;
}
@@ -940,10 +944,15 @@ 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. */
+ if (!PageLRU(head))
+ return -EIO;
+
/*
* Avoid migrating a page that is shared with others.
*/
@@ -955,6 +964,8 @@ 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 */
@@ -1157,9 +1168,10 @@ 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,
--
1.8.3.1
\
 
 \ /
  Last update: 2019-06-17 20:49    [W:0.091 / U:2.856 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site