[PATCH 2/6] mm: Move FAULT_FLAG_VMA_LOCK check from handle_mm_fault()

["Matthew Wilcox (Oracle)" <willy@infradead.org>]

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.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
---
 mm/hugetlb.c |  4 ++++
 mm/memory.c  | 14 +++++++-------
 2 files changed, 11 insertions(+), 7 deletions(-)

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index efc443a906fa..39f168e3518f 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -6052,6 +6052,10 @@ 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)
+		return VM_FAULT_RETRY;
+
 	/*
 	 * Serialize hugepage allocation and instantiation, so that we don't
 	 * get spurious allocation failures if two CPUs race to instantiate
diff --git a/mm/memory.c b/mm/memory.c
index f726f85f0081..fc1f0ef9a7a5 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4992,10 +4992,10 @@ 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)
@@ -5014,6 +5014,9 @@ 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))
+		return VM_FAULT_RETRY;
+
 	pgd = pgd_offset(mm, address);
 	p4d = p4d_alloc(mm, pgd, address);
 	if (!p4d)
@@ -5223,9 +5226,6 @@ vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
 					    flags & FAULT_FLAG_REMOTE))
 		return VM_FAULT_SIGSEGV;
 
-	if ((flags & FAULT_FLAG_VMA_LOCK) && !vma_is_anonymous(vma))
-		return VM_FAULT_RETRY;
-
 	/*
 	 * Enable the memcg OOM handling for faults triggered in user
 	 * space.  Kernel faults are handled more gracefully.
-- 
2.39.2