mm: move FAULT_FLAG_VMA_LOCK check from handle_mm_fault()

Handle a little more of the page fault path outside the mmap sem.  The
hugetlb path doesn't need to check whether the VMA is anonymous; the
VM_HUGETLB flag is only set on hugetlbfs VMAs.  There should be no
performance change from the previous commit; this is simply a step to ease
bisection of any problems.

Link: https://lkml.kernel.org/r/20230724185410.1124082-4-willy@infradead.orgSigned-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Suren Baghdasaryan <surenb@google.com>
Cc: Arjun Roy <arjunroy@google.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Punit Agrawal <punit.agrawal@bytedance.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

mm/hugetlb.c

@@ -6062,6 +6062,12 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	int need_wait_lock = 0;
 	unsigned long haddr = address & huge_page_mask(h);
 
+	/* TODO: Handle faults under the VMA lock */
+	if (flags & FAULT_FLAG_VMA_LOCK) {
+		vma_end_read(vma);
+		return VM_FAULT_RETRY;
+	}
+
 	/*
 	 * Serialize hugepage allocation and instantiation, so that we don't
 	 * get spurious allocation failures if two CPUs race to instantiate

mm/memory.c

@@ -4984,10 +4984,10 @@ static vm_fault_t handle_pte_fault(struct vm_fault *vmf)
 }
 
 /*
- * By the time we get here, we already hold the mm semaphore
- *
- * The mmap_lock may have been released depending on flags and our
- * return value.  See filemap_fault() and __folio_lock_or_retry().
+ * On entry, we hold either the VMA lock or the mmap_lock
+ * (FAULT_FLAG_VMA_LOCK tells you which).  If VM_FAULT_RETRY is set in
+ * the result, the mmap_lock is not held on exit.  See filemap_fault()
+ * and __folio_lock_or_retry().
  */
 static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma,
 		unsigned long address, unsigned int flags)
@@ -5006,6 +5006,11 @@ static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma,
 	p4d_t *p4d;
 	vm_fault_t ret;
 
+	if ((flags & FAULT_FLAG_VMA_LOCK) && !vma_is_anonymous(vma)) {
+		vma_end_read(vma);
+		return VM_FAULT_RETRY;
+	}
+
 	pgd = pgd_offset(mm, address);
 	p4d = p4d_alloc(mm, pgd, address);
 	if (!p4d)
@@ -5222,11 +5227,6 @@ vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
 		goto out;
 	}
 
-	if ((flags & FAULT_FLAG_VMA_LOCK) && !vma_is_anonymous(vma)) {
-		vma_end_read(vma);
-		return VM_FAULT_RETRY;
-	}
-
 	/*
 	 * Enable the memcg OOM handling for faults triggered in user
 	 * space.  Kernel faults are handled more gracefully.