mm/gup: move gup_must_unshare() to mm/internal.h

This function is only used in gup.c and closely related.  It touches
FOLL_PIN so it must be moved before the next patch.

Link: https://lkml.kernel.org/r/12-v2-987e91b59705+36b-gup_tidy_jgg@nvidia.com
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: John Hubbard <jhubbard@nvidia.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Claudio Imbrenda <imbrenda@linux.ibm.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Mike Rapoport (IBM) <rppt@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 65 insertions, 0 deletions

diff --git a/mm/internal.h b/mm/internal.h
index 3f75763b0fc2..4f5ca3401b05 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -858,6 +858,71 @@ int migrate_device_coherent_page(struct page *page);
 struct folio *try_grab_folio(struct page *page, int refs, unsigned int flags);
 int __must_check try_grab_page(struct page *page, unsigned int flags);
 
+/*
+ * Indicates for which pages that are write-protected in the page table,
+ * whether GUP has to trigger unsharing via FAULT_FLAG_UNSHARE such that the
+ * GUP pin will remain consistent with the pages mapped into the page tables
+ * of the MM.
+ *
+ * Temporary unmapping of PageAnonExclusive() pages or clearing of
+ * PageAnonExclusive() has to protect against concurrent GUP:
+ * * Ordinary GUP: Using the PT lock
+ * * GUP-fast and fork(): mm->write_protect_seq
+ * * GUP-fast and KSM or temporary unmapping (swap, migration): see
+ *    page_try_share_anon_rmap()
+ *
+ * Must be called with the (sub)page that's actually referenced via the
+ * page table entry, which might not necessarily be the head page for a
+ * PTE-mapped THP.
+ *
+ * If the vma is NULL, we're coming from the GUP-fast path and might have
+ * to fallback to the slow path just to lookup the vma.
+ */
+static inline bool gup_must_unshare(struct vm_area_struct *vma,
+				    unsigned int flags, struct page *page)
+{
+	/*
+	 * FOLL_WRITE is implicitly handled correctly as the page table entry
+	 * has to be writable -- and if it references (part of) an anonymous
+	 * folio, that part is required to be marked exclusive.
+	 */
+	if ((flags & (FOLL_WRITE | FOLL_PIN)) != FOLL_PIN)
+		return false;
+	/*
+	 * Note: PageAnon(page) is stable until the page is actually getting
+	 * freed.
+	 */
+	if (!PageAnon(page)) {
+		/*
+		 * We only care about R/O long-term pining: R/O short-term
+		 * pinning does not have the semantics to observe successive
+		 * changes through the process page tables.
+		 */
+		if (!(flags & FOLL_LONGTERM))
+			return false;
+
+		/* We really need the vma ... */
+		if (!vma)
+			return true;
+
+		/*
+		 * ... because we only care about writable private ("COW")
+		 * mappings where we have to break COW early.
+		 */
+		return is_cow_mapping(vma->vm_flags);
+	}
+
+	/* Paired with a memory barrier in page_try_share_anon_rmap(). */
+	if (IS_ENABLED(CONFIG_HAVE_FAST_GUP))
+		smp_rmb();
+
+	/*
+	 * Note that PageKsm() pages cannot be exclusive, and consequently,
+	 * cannot get pinned.
+	 */
+	return !PageAnonExclusive(page);
+}
+
 extern bool mirrored_kernelcore;
 
 static inline bool vma_soft_dirty_enabled(struct vm_area_struct *vma)