Ever since commit b756a3b5e7ea ("mm: device exclusive memory access")
we can return with a device-exclusive entry from page_vma_mapped_walk().
__replace_page() is not prepared for that, so teach it about these
PFN swap PTEs. Note that device-private entries are so far not
applicable on that path, because GUP would never have returned such
folios (conversion to device-private happens by page migration, not
in-place conversion of the PTE).
There is a race between GUP and us locking the folio to look it up
using page_vma_mapped_walk(), so this is likely a fix (unless something
else could prevent that race, but it doesn't look like). pte_pfn() on
something that is not a present pte could give use garbage, and we'd
wrongly mess up the mapcount because it was already adjusted by calling
folio_remove_rmap_pte() when making the entry device-exclusive.
Fixes: b756a3b5e7ea ("mm: device exclusive memory access")
Signed-off-by: David Hildenbrand <david@xxxxxxxxxx>
---
kernel/events/uprobes.c | 13 ++++++++++++-
1 file changed, 12 insertions(+), 1 deletion(-)
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 2ca797cbe465f..cd6105b100325 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -173,6 +173,7 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
DEFINE_FOLIO_VMA_WALK(pvmw, old_folio, vma, addr, 0);
int err;
struct mmu_notifier_range range;
+ pte_t pte;
mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, addr,
addr + PAGE_SIZE);
@@ -192,6 +193,16 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
if (!page_vma_mapped_walk(&pvmw))
goto unlock;
VM_BUG_ON_PAGE(addr != pvmw.address, old_page);
+ pte = ptep_get(pvmw.pte);
+
+ /*
+ * Handle PFN swap PTES, such as device-exclusive ones, that actually
+ * map pages: simply trigger GUP again to fix it up.
+ */
+ if (unlikely(!pte_present(pte))) {
+ page_vma_mapped_walk_done(&pvmw);
+ goto unlock;
+ }
if (new_page) {
folio_get(new_folio);
@@ -206,7 +217,7 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
inc_mm_counter(mm, MM_ANONPAGES);
}
- flush_cache_page(vma, addr, pte_pfn(ptep_get(pvmw.pte)));
+ flush_cache_page(vma, addr, pte_pfn(pte));
ptep_clear_flush(vma, addr, pvmw.pte);
if (new_page)
set_pte_at(mm, addr, pvmw.pte,
--
2.48.1
