There are many implementations of ->fault and some of them depend on
mmap_lock being held. All vm_ops that implement ->map_pages() end
up calling filemap_fault(), which I have audited to be sure it does
not rely on mmap_lock. So (for now) key off ->map_pages existing
as being a flag to indicate that it's safe to call ->fault while
only holding the vma lock.
Signed-off-by: Matthew Wilcox (Oracle) <willy@xxxxxxxxxxxxx>
---
mm/memory.c | 22 ++++++++++++++++++----
1 file changed, 18 insertions(+), 4 deletions(-)
diff --git a/mm/memory.c b/mm/memory.c
index cff78c496728..0f3da4889230 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3042,6 +3042,21 @@ static inline void wp_page_reuse(struct vm_fault *vmf)
count_vm_event(PGREUSE);
}
+/*
+ * We could add a bitflag somewhere, but for now, we know that all
+ * vm_ops that have a ->map_pages have been audited and don't need
+ * the mmap_lock to be held.
+ */
+static inline vm_fault_t vmf_maybe_unlock_vma(const struct vm_fault *vmf)
+{
+ struct vm_area_struct *vma = vmf->vma;
+
+ if (vma->vm_ops->map_pages || !(vmf->flags & FAULT_FLAG_VMA_LOCK))
+ return 0;
+ vma_end_read(vma);
+ return VM_FAULT_RETRY;
+}
+
static vm_fault_t vmf_anon_prepare(struct vm_fault *vmf)
{
struct vm_area_struct *vma = vmf->vma;
@@ -4669,10 +4684,9 @@ static vm_fault_t do_shared_fault(struct vm_fault *vmf)
vm_fault_t ret, tmp;
struct folio *folio;
- if (vmf->flags & FAULT_FLAG_VMA_LOCK) {
- vma_end_read(vma);
- return VM_FAULT_RETRY;
- }
+ ret = vmf_maybe_unlock_vma(vmf);
+ if (ret)
+ return ret;
ret = __do_fault(vmf);
if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY)))
--
2.40.1
