[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20250602141610.173698-4-osalvador@suse.de>
Date: Mon, 2 Jun 2025 16:16:10 +0200
From: Oscar Salvador <osalvador@...e.de>
To: Andrew Morton <akpm@...ux-foundation.org>
Cc: Muchun Song <muchun.song@...ux.dev>,
David Hildenbrand <david@...hat.com>,
James Houghton <jthoughton@...gle.com>,
Peter Xu <peterx@...hat.com>,
Gavin Guo <gavinguo@...lia.com>,
linux-mm@...ck.org,
linux-kernel@...r.kernel.org,
Oscar Salvador <osalvador@...e.de>
Subject: [RFC PATCH 3/3] mm, hugetlb: Drop unlikelys from hugetlb_fault
The unlikely predates an era where we were checking for
hwpoisoned/migration entries without knowing whether the pte was
present.
The code-flow has changed, and we do not do that anymore, plus
they do not bring any advantatge at all.
Signed-off-by: Oscar Salvador <osalvador@...e.de>
---
mm/hugetlb.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 6ef90958839f..02ede63e7e5e 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -6768,7 +6768,7 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
* or hwpoisoned entry.
*/
if (!pte_present(vmf.orig_pte)) {
- if (unlikely(is_hugetlb_entry_migration(vmf.orig_pte))) {
+ if (is_hugetlb_entry_migration(vmf.orig_pte)) {
/*
* Release the hugetlb fault lock now, but retain
* the vma lock, because it is needed to guard the
@@ -6779,7 +6779,7 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
mutex_unlock(&hugetlb_fault_mutex_table[hash]);
migration_entry_wait_huge(vma, vmf.address, vmf.pte);
return 0;
- } else if (unlikely(is_hugetlb_entry_hwpoisoned(vmf.orig_pte)))
+ } else if (is_hugetlb_entry_hwpoisoned(vmf.orig_pte))
ret = VM_FAULT_HWPOISON_LARGE |
VM_FAULT_SET_HINDEX(hstate_index(h));
goto out_mutex;
--
2.49.0
Powered by blists - more mailing lists