On 2024/6/12 20:28, Kefeng Wang wrote:
The large folio is mapped with folio size(not greater PMD_SIZE) aligned
virtual address during the pagefault, ie, 'addr = ALIGN_DOWN(vmf->address,
nr_pages * PAGE_SIZE)' in do_anonymous_page(). But after the mremap(),
the virtual address only requires PAGE_SIZE alignment. Also pte is moved
to new in move_page_tables(), then traversal of the new pte in the
numa_rebuild_large_mapping() could hit the following issue,
Unable to handle kernel paging request at virtual address 00000a80c021a788
Mem abort info:
ESR = 0x0000000096000004
EC = 0x25: DABT (current EL), IL = 32 bits
SET = 0, FnV = 0
EA = 0, S1PTW = 0
FSC = 0x04: level 0 translation fault
Data abort info:
ISV = 0, ISS = 0x00000004, ISS2 = 0x00000000
CM = 0, WnR = 0, TnD = 0, TagAccess = 0
GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0
user pgtable: 4k pages, 48-bit VAs, pgdp=00002040341a6000
[00000a80c021a788] pgd=0000000000000000, p4d=0000000000000000
Internal error: Oops: 0000000096000004 [#1] SMP
...
CPU: 76 PID: 15187 Comm: git Kdump: loaded Tainted: G W 6.10.0-rc2+ #209
Hardware name: Huawei TaiShan 2280 V2/BC82AMDD, BIOS 1.79 08/21/2021
pstate: 60400009 (nZCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
pc : numa_rebuild_large_mapping+0x338/0x638
lr : numa_rebuild_large_mapping+0x320/0x638
sp : ffff8000b41c3b00
x29: ffff8000b41c3b30 x28: ffff8000812a0000 x27: 00000000000a8000
x26: 00000000000000a8 x25: 0010000000000001 x24: ffff20401c7170f0
x23: 0000ffff33a1e000 x22: 0000ffff33a76000 x21: ffff20400869eca0
x20: 0000ffff33976000 x19: 00000000000000a8 x18: ffffffffffffffff
x17: 0000000000000000 x16: 0000000000000020 x15: ffff8000b41c36a8
x14: 0000000000000000 x13: 205d373831353154 x12: 5b5d333331363732
x11: 000000000011ff78 x10: 000000000011ff10 x9 : ffff800080273f30
x8 : 000000320400869e x7 : c0000000ffffd87f x6 : 00000000001e6ba8
x5 : ffff206f3fb5af88 x4 : 0000000000000000 x3 : 0000000000000000
x2 : 0000000000000000 x1 : fffffdffc0000000 x0 : 00000a80c021a780
Call trace:
numa_rebuild_large_mapping+0x338/0x638
do_numa_page+0x3e4/0x4e0
handle_pte_fault+0x1bc/0x238
__handle_mm_fault+0x20c/0x400
handle_mm_fault+0xa8/0x288
do_page_fault+0x124/0x498
do_translation_fault+0x54/0x80
do_mem_abort+0x4c/0xa8
el0_da+0x40/0x110
el0t_64_sync_handler+0xe4/0x158
el0t_64_sync+0x188/0x190
Fix it by making the start and end not only within the vma range, but
also within the page table range.
Fixes: d2136d749d76 ("mm: support multi-size THP numa balancing")
Signed-off-by: Kefeng Wang <wangkefeng.wang@xxxxxxxxxx>
LGTM. Thanks.
Reviewed-by: Baolin Wang <baolin.wang@xxxxxxxxxxxxxxxxx>
---
v2:
- don't pass nr_pages into numa_rebuild_large_mapping()
- address comment and suggestion from David
mm/memory.c | 14 ++++++++++----
1 file changed, 10 insertions(+), 4 deletions(-)
diff --git a/mm/memory.c b/mm/memory.c
index 0d309cfb703c..60f7a05ad0cd 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -5228,10 +5228,16 @@ static void numa_rebuild_large_mapping(struct vm_fault *vmf, struct vm_area_stru
bool ignore_writable, bool pte_write_upgrade)
{
int nr = pte_pfn(fault_pte) - folio_pfn(folio);
- unsigned long start = max(vmf->address - nr * PAGE_SIZE, vma->vm_start);
- unsigned long end = min(vmf->address + (folio_nr_pages(folio) - nr) * PAGE_SIZE, vma->vm_end);
- pte_t *start_ptep = vmf->pte - (vmf->address - start) / PAGE_SIZE;
- unsigned long addr;
+ unsigned long start, end, addr = vmf->address;
+ unsigned long addr_start = addr - (nr << PAGE_SHIFT);
+ unsigned long pt_start = ALIGN_DOWN(addr, PMD_SIZE);
+ pte_t *start_ptep;
+
+ /* Stay within the VMA and within the page table. */
+ start = max3(addr_start, pt_start, vma->vm_start);
+ end = min3(addr_start + folio_size(folio), pt_start + PMD_SIZE,
+ vma->vm_end);
+ start_ptep = vmf->pte - ((addr - start) >> PAGE_SHIFT);
/* Restore all PTEs' mapping of the large folio */
for (addr = start; addr != end; start_ptep++, addr += PAGE_SIZE) {
