mm: handle shared faults under the VMA lock

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 a flag to
indicate that it's safe to call ->fault while only holding the vma lock.

Link: https://lkml.kernel.org/r/20231006195318.4087158-4-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Suren Baghdasaryan <surenb@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/mm/memory.c b/mm/memory.c
index c437d3562d18913e9bd874218d1a06f865a30a4b..7b240a67f207a814230f43a1ad5bf76b87182665 100644 (file)
--- 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_can_call_fault(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_can_call_fault(vmf);
+       if (ret)
+               return ret;
 
        ret = __do_fault(vmf);
        if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY)))