From 6c1b748ebf27befffec83b77ca1960bf70ed6ac9 Mon Sep 17 00:00:00 2001
From: John Hubbard <jhubbard@nvidia.com>
Date: Tue, 27 Feb 2024 19:41:51 -0800
Subject: [PATCH] mm/memory.c: do_numa_page(): remove a redundant page table
read
do_numa_page() is reading from the same page table entry, twice, while
holding the page table lock: once while checking that the pte hasn't
changed, and again in order to modify the pte.
Instead, just read the pte once, and save it in the same old_pte variable
that already exists. This has no effect on behavior, other than to
provide a tiny potential improvement to performance, by avoiding the
redundant memory read (which the compiler cannot elide, due to
READ_ONCE()).
Also improve the associated comments nearby.
Link: https://lkml.kernel.org/r/20240228034151.459370-1-jhubbard@nvidia.com
Signed-off-by: John Hubbard <jhubbard@nvidia.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Ryan Roberts <ryan.roberts@arm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/memory.c | 12 ++++++------
1 file changed, 6 insertions(+), 6 deletions(-)
diff --git a/mm/memory.c b/mm/memory.c
index 75e0abda86427..230bcd12a3362 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -5127,18 +5127,18 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf)
int flags = 0;
/*
- * The "pte" at this point cannot be used safely without
- * validation through pte_unmap_same(). It's of NUMA type but
- * the pfn may be screwed if the read is non atomic.
+ * The pte cannot be used safely until we verify, while holding the page
+ * table lock, that its contents have not changed during fault handling.
*/
spin_lock(vmf->ptl);
- if (unlikely(!pte_same(ptep_get(vmf->pte), vmf->orig_pte))) {
+ /* Read the live PTE from the page tables: */
+ old_pte = ptep_get(vmf->pte);
+
+ if (unlikely(!pte_same(old_pte, vmf->orig_pte))) {
pte_unmap_unlock(vmf->pte, vmf->ptl);
goto out;
}
- /* Get the normal PTE */
- old_pte = ptep_get(vmf->pte);
pte = pte_modify(old_pte, vma->vm_page_prot);
/*
--
GitLab