From 45b9101695331d32f946c9651c08179a46a30f68 Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Wed, 28 Jun 2023 17:53:04 -0400
Subject: [PATCH] mm/hugetlb: prepare hugetlb_follow_page_mask() for FOLL_PIN
[ Upstream commit 458568c92953dee3716234711f1a2830a35261f3 ]
follow_page() doesn't use FOLL_PIN, meanwhile hugetlb seems to not be the
target of FOLL_WRITE either. However add the checks.
Namely, either the need to CoW due to missing write bit, or proper
unsharing on !AnonExclusive pages over R/O pins to reject the follow page.
That brings this function closer to follow_hugetlb_page().
So we don't care before, and also for now. But we'll care if we switch
over slow-gup to use hugetlb_follow_page_mask(). We'll also care when to
return -EMLINK properly, as that's the gup internal api to mean "we should
unshare". Not really needed for follow page path, though.
When at it, switching the try_grab_page() to use WARN_ON_ONCE(), to be
clear that it just should never fail. When error happens, instead of
setting page==NULL, capture the errno instead.
Link: https://lkml.kernel.org/r/20230628215310.73782-3-peterx@redhat.com
Signed-off-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: James Houghton <jthoughton@google.com>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Kirill A . Shutemov <kirill@shutemov.name>
Cc: Lorenzo Stoakes <lstoakes@gmail.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Mike Rapoport (IBM) <rppt@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Yang Shi <shy828301@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Stable-dep-of: 426056efe835 ("mm/hugetlb: use nth_page() in place of direct struct page manipulation")
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
mm/hugetlb.c | 33 ++++++++++++++++++++++-----------
1 file changed, 22 insertions(+), 11 deletions(-)
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 097b81c37597..d231f23088a7 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -6521,13 +6521,7 @@ struct page *hugetlb_follow_page_mask(struct vm_area_struct *vma,
struct page *page = NULL;
spinlock_t *ptl;
pte_t *pte, entry;
-
- /*
- * FOLL_PIN is not supported for follow_page(). Ordinary GUP goes via
- * follow_hugetlb_page().
- */
- if (WARN_ON_ONCE(flags & FOLL_PIN))
- return NULL;
+ int ret;
hugetlb_vma_lock_read(vma);
pte = hugetlb_walk(vma, haddr, huge_page_size(h));
@@ -6537,8 +6531,23 @@ struct page *hugetlb_follow_page_mask(struct vm_area_struct *vma,
ptl = huge_pte_lock(h, mm, pte);
entry = huge_ptep_get(pte);
if (pte_present(entry)) {
- page = pte_page(entry) +
- ((address & ~huge_page_mask(h)) >> PAGE_SHIFT);
+ page = pte_page(entry);
+
+ if (!huge_pte_write(entry)) {
+ if (flags & FOLL_WRITE) {
+ page = NULL;
+ goto out;
+ }
+
+ if (gup_must_unshare(vma, flags, page)) {
+ /* Tell the caller to do unsharing */
+ page = ERR_PTR(-EMLINK);
+ goto out;
+ }
+ }
+
+ page += ((address & ~huge_page_mask(h)) >> PAGE_SHIFT);
+
/*
* Note that page may be a sub-page, and with vmemmap
* optimizations the page struct may be read only.
@@ -6548,8 +6557,10 @@ struct page *hugetlb_follow_page_mask(struct vm_area_struct *vma,
* try_grab_page() should always be able to get the page here,
* because we hold the ptl lock and have verified pte_present().
*/
- if (try_grab_page(page, flags)) {
- page = NULL;
+ ret = try_grab_page(page, flags);
+
+ if (WARN_ON_ONCE(ret)) {
+ page = ERR_PTR(ret);
goto out;
}
}
--
GitLab