From 84d60fdd3733fb86c126f2adfd0361fdc44087c3 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Thu, 24 Mar 2022 18:13:37 -0700
Subject: mm: slightly clarify KSM logic in do_swap_page()

Let's make it clearer that KSM might only have to copy a page in case we
have a page in the swapcache, not if we allocated a fresh page and
bypassed the swapcache.  While at it, add a comment why this is usually
necessary and merge the two swapcache conditions.

[akpm@linux-foundation.org: fix comment, per David]

Link: https://lkml.kernel.org/r/20220131162940.210846-4-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: David Rientjes <rientjes@google.com>
Cc: Don Dutile <ddutile@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jann Horn <jannh@google.com>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Liang Zhang <zhangliang5@huawei.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Mike Rapoport <rppt@linux.ibm.com>
Cc: Nadav Amit <nadav.amit@gmail.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Yang Shi <shy828301@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/memory.c | 38 +++++++++++++++++++++++---------------
 1 file changed, 23 insertions(+), 15 deletions(-)

(limited to 'mm')

diff --git a/mm/memory.c b/mm/memory.c
index c7723bdaf0c3..8e30675dc077 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3607,21 +3607,29 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 		goto out_release;
 	}
 
-	/*
-	 * Make sure try_to_free_swap or reuse_swap_page or swapoff did not
-	 * release the swapcache from under us.  The page pin, and pte_same
-	 * test below, are not enough to exclude that.  Even if it is still
-	 * swapcache, we need to check that the page's swap has not changed.
-	 */
-	if (unlikely((!PageSwapCache(page) ||
-			page_private(page) != entry.val)) && swapcache)
-		goto out_page;
-
-	page = ksm_might_need_to_copy(page, vma, vmf->address);
-	if (unlikely(!page)) {
-		ret = VM_FAULT_OOM;
-		page = swapcache;
-		goto out_page;
+	if (swapcache) {
+		/*
+		 * Make sure try_to_free_swap or swapoff did not release the
+		 * swapcache from under us.  The page pin, and pte_same test
+		 * below, are not enough to exclude that.  Even if it is still
+		 * swapcache, we need to check that the page's swap has not
+		 * changed.
+		 */
+		if (unlikely(!PageSwapCache(page) ||
+			     page_private(page) != entry.val))
+			goto out_page;
+
+		/*
+		 * KSM sometimes has to copy on read faults, for example, if
+		 * page->index of !PageKSM() pages would be nonlinear inside the
+		 * anon VMA -- PageKSM() is lost on actual swapout.
+		 */
+		page = ksm_might_need_to_copy(page, vma, vmf->address);
+		if (unlikely(!page)) {
+			ret = VM_FAULT_OOM;
+			page = swapcache;
+			goto out_page;
+		}
 	}
 
 	cgroup_throttle_swaprate(page, GFP_KERNEL);
-- 
cgit v1.2.3