mm/pagewalk: introduce folio_walk_start() + folio_walk_end()

We want to get rid of follow_page(), and have a more reasonable way to
just lookup a folio mapped at a certain address, perform some checks while
still under PTL, and then only conditionally grab a folio reference if
really required.

Further, we might want to get rid of some walk_page_range*() users that
really only want to temporarily lookup a single folio at a single address.

So let's add a new page table walker that does exactly that, similarly to
GUP also being able to walk hugetlb VMAs.

Add folio_walk_end() as a macro for now: the compiler is not easy to
please with the pte_unmap()->kunmap_local().

Note that one difference between follow_page() and get_user_pages(1) is
that follow_page() will not trigger faults to get something mapped.  So
folio_walk is at least currently not a replacement for get_user_pages(1),
but could likely be extended/reused to achieve something similar in the
future.

Link: https://lkml.kernel.org/r/20240802155524.517137-3-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Cc: Christian Borntraeger <borntraeger@linux.ibm.com>
Cc: Claudio Imbrenda <imbrenda@linux.ibm.com>
Cc: Gerald Schaefer <gerald.schaefer@linux.ibm.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Janosch Frank <frankja@linux.ibm.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 58 insertions, 0 deletions

diff --git a/include/linux/pagewalk.h b/include/linux/pagewalk.h
index 27cd1e59ccf7..f5eb5a32aeed 100644
--- a/include/linux/pagewalk.h
+++ b/include/linux/pagewalk.h
@@ -130,4 +130,62 @@ int walk_page_mapping(struct address_space *mapping, pgoff_t first_index,
 		      pgoff_t nr, const struct mm_walk_ops *ops,
 		      void *private);
 
+typedef int __bitwise folio_walk_flags_t;
+
+/*
+ * Walk migration entries as well. Careful: a large folio might get split
+ * concurrently.
+ */
+#define FW_MIGRATION			((__force folio_walk_flags_t)BIT(0))
+
+/* Walk shared zeropages (small + huge) as well. */
+#define FW_ZEROPAGE			((__force folio_walk_flags_t)BIT(1))
+
+enum folio_walk_level {
+	FW_LEVEL_PTE,
+	FW_LEVEL_PMD,
+	FW_LEVEL_PUD,
+};
+
+/**
+ * struct folio_walk - folio_walk_start() / folio_walk_end() data
+ * @page:	exact folio page referenced (if applicable)
+ * @level:	page table level identifying the entry type
+ * @pte:	pointer to the page table entry (FW_LEVEL_PTE).
+ * @pmd:	pointer to the page table entry (FW_LEVEL_PMD).
+ * @pud:	pointer to the page table entry (FW_LEVEL_PUD).
+ * @ptl:	pointer to the page table lock.
+ *
+ * (see folio_walk_start() documentation for more details)
+ */
+struct folio_walk {
+	/* public */
+	struct page *page;
+	enum folio_walk_level level;
+	union {
+		pte_t *ptep;
+		pud_t *pudp;
+		pmd_t *pmdp;
+	};
+	union {
+		pte_t pte;
+		pud_t pud;
+		pmd_t pmd;
+	};
+	/* private */
+	struct vm_area_struct *vma;
+	spinlock_t *ptl;
+};
+
+struct folio *folio_walk_start(struct folio_walk *fw,
+		struct vm_area_struct *vma, unsigned long addr,
+		folio_walk_flags_t flags);
+
+#define folio_walk_end(__fw, __vma) do { \
+	spin_unlock((__fw)->ptl); \
+	if (likely((__fw)->level == FW_LEVEL_PTE)) \
+		pte_unmap((__fw)->ptep); \
+	vma_pgtable_walk_end(__vma); \
+} while (0)
+
 #endif /* _LINUX_PAGEWALK_H */