Skip to contentSkip to conversation

mm:fix gup_pud_range

PATCH Applied Qiujun Huang 1 participant 1 message Jan 8, 2020

Subsystems (2)
lore
Share & tools
lore
#0 lore raw

PATCH v2 1/1 mm:fix gup_pud_range

sorry for not processing for a long time. I met it again.

patch v1 https://lkml.org/lkml/2019/9/20/656

do_machine_check()
do_memory_failure()

    memory_failure()
      hw_poison_user_mappings()
        try_to_unmap()
          pteval = swp_entry_to_pte(make_hwpoison_entry(subpage));

...and now we have a swap entry that indicates that the page entry refers to a bad (and poisoned) page of memory, but gup_fast() at this level of the page table was ignoring swap entries, and incorrectly assuming that "!pxd_none() == valid and present".

And this was not just a poisoned page problem, but a generaly swap entry problem. So, any swap entry type (device memory migration, numa migration, or just regular swapping) could lead to the same problem.

Fix this by checking for pxd_present(), instead of pxd_none().

---
 mm/gup.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
mm/gup.c +1 -1
index 7646bf9..9c41670 100644
@@ -2237,7 +2237,7 @@ static int gup_pud_range(p4d_t p4d, unsigned long addr, unsigned long end,
 		pud_t pud = READ_ONCE(*pudp);
 
 		next = pud_addr_end(addr, end);
-		if (pud_none(pud))
+		if (unlikely(!pud_present(pud)))
 			return 0;
 		if (unlikely(pud_huge(pud))) {
 			if (!gup_huge_pud(pud, pudp, addr, next, flags,
Signature · 1 line
1.8.3.1