The large folio is mapped with folio size aligned virtual address during
the pagefault, eg, 'addr = ALIGN_DOWN(vmf->address, nr_pages * PAGE_SIZE)'
in do_anonymous_page(), but after the mremap(), the virtual address only
require PAGE_SIZE aligned, also pte is moved to new in move_page_tables(),
then traverse the new pte in numa_rebuild_large_mapping() will hint 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 correct the start and end, which may lead to only rebuild part
of large mapping in one numa page fault, there is no issue since other part
could rebuild by another pagefault.
Fixes: d2136d749d76 ("mm: support multi-size THP numa balancing")
Signed-off-by: Kefeng Wang <wangkefeng.wang@xxxxxxxxxx>
---
mm/memory.c | 24 +++++++++++++++---------
1 file changed, 15 insertions(+), 9 deletions(-)
diff --git a/mm/memory.c b/mm/memory.c
index db9130488231..0ad57b6485ca 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -5223,15 +5223,21 @@ static void numa_rebuild_single_mapping(struct vm_fault *vmf, struct vm_area_str
update_mmu_cache_range(vmf, vma, fault_addr, fault_pte, 1);
}
-static void numa_rebuild_large_mapping(struct vm_fault *vmf, struct vm_area_struct *vma,
- struct folio *folio, pte_t fault_pte,
- bool ignore_writable, bool pte_write_upgrade)
+static void numa_rebuild_large_mapping(struct vm_fault *vmf,
+ struct vm_area_struct *vma, struct folio *folio, int nr_pages,
+ pte_t fault_pte, 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 folio_size = nr_pages * PAGE_SIZE;
+ unsigned long addr = vmf->address;
+ unsigned long start, end, align_addr;
+ pte_t *start_ptep;
+
+ align_addr = ALIGN_DOWN(addr, folio_size);
+ start = max3(addr - nr * PAGE_SIZE, align_addr, vma->vm_start);
+ end = min3(addr + (nr_pages - nr) * PAGE_SIZE, align_addr + folio_size,
+ vma->vm_end);
+ start_ptep = vmf->pte - (addr - start) / PAGE_SIZE;
/* Restore all PTEs' mapping of the large folio */
for (addr = start; addr != end; start_ptep++, addr += PAGE_SIZE) {
@@ -5361,8 +5367,8 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf)
* non-accessible ptes, some can allow access by kernel mode.
*/
if (folio && folio_test_large(folio))
- numa_rebuild_large_mapping(vmf, vma, folio, pte, ignore_writable,
- pte_write_upgrade);
+ numa_rebuild_large_mapping(vmf, vma, folio, nr_pages, pte,
+ ignore_writable, pte_write_upgrade);
else
numa_rebuild_single_mapping(vmf, vma, vmf->address, vmf->pte,
writable);
--
2.27.0
