A lockless page table walk should be safe against parallel THP collapse, THP
split and madvise(MADV_DONTNEED)/parallel fault. This patch makes sure kernel
won't reload the pteval when checking for different conditions. The patch also added
a check for pte_present to make sure the kernel is indeed operating
on a PTE and not a pointer to level 0 table page.
The pfn value we find here can be different from the actual pfn on which
machine check happened. This can happen if we raced with a parallel update
of the page table. In such a scenario we end up isolating a wrong pfn. But that
doesn't have any other side effect.
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200505071729.54912-7-aneesh.kumar@linux.ibm.com
*/
unsigned long addr_to_pfn(struct pt_regs *regs, unsigned long addr)
{
- pte_t *ptep;
+ pte_t *ptep, pte;
unsigned int shift;
unsigned long pfn, flags;
struct mm_struct *mm;
local_irq_save(flags);
ptep = __find_linux_pte(mm->pgd, addr, NULL, &shift);
+ if (!ptep) {
+ pfn = ULONG_MAX;
+ goto out;
+ }
+ pte = READ_ONCE(*ptep);
- if (!ptep || pte_special(*ptep)) {
+ if (!pte_present(pte) || pte_special(pte)) {
pfn = ULONG_MAX;
goto out;
}
if (shift <= PAGE_SHIFT)
- pfn = pte_pfn(*ptep);
+ pfn = pte_pfn(pte);
else {
unsigned long rpnmask = (1ul << shift) - PAGE_SIZE;
- pfn = pte_pfn(__pte(pte_val(*ptep) | (addr & rpnmask)));
+ pfn = pte_pfn(__pte(pte_val(pte) | (addr & rpnmask)));
}
-
out:
local_irq_restore(flags);
return pfn;