Some architectures (e.g. arm64) can tell from looking at a pte, if some
follow-on ptes also map contiguous physical memory with the same pgprot.
(for arm64, these are contpte mappings).
Take advantage of this knowledge to optimize folio_pte_batch() so that
it can skip these ptes when scanning to create a batch. By default, if
an arch does not opt-in, folio_pte_batch() returns a compile-time 1, so
the changes are optimized out and the behaviour is as before.
arm64 will opt-in to providing this hint in the next patch, which will
greatly reduce the cost of ptep_get() when scanning a range of contptes.
Acked-by: David Hildenbrand <david@xxxxxxxxxx>
Tested-by: John Hubbard <jhubbard@xxxxxxxxxx>
Signed-off-by: Ryan Roberts <ryan.roberts@xxxxxxx>
---
include/linux/pgtable.h | 21 +++++++++++++++++++++
mm/memory.c | 19 ++++++++++++-------
2 files changed, 33 insertions(+), 7 deletions(-)
diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index bc005d84f764..a36cf4e124b0 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -212,6 +212,27 @@ static inline int pmd_dirty(pmd_t pmd)
#define arch_flush_lazy_mmu_mode() do {} while (0)
#endif
+#ifndef pte_batch_hint
+/**
+ * pte_batch_hint - Number of pages that can be added to batch without scanning.
+ * @ptep: Page table pointer for the entry.
+ * @pte: Page table entry.
+ *
+ * Some architectures know that a set of contiguous ptes all map the same
+ * contiguous memory with the same permissions. In this case, it can provide a
+ * hint to aid pte batching without the core code needing to scan every pte.
+ *
+ * An architecture implementation may ignore the PTE accessed state. Further,
+ * the dirty state must apply atomically to all the PTEs described by the hint.
+ *
+ * May be overridden by the architecture, else pte_batch_hint is always 1.
+ */
+static inline unsigned int pte_batch_hint(pte_t *ptep, pte_t pte)
+{
+ return 1;
+}
+#endif
+
#ifndef pte_advance_pfn
static inline pte_t pte_advance_pfn(pte_t pte, unsigned long nr)
{
diff --git a/mm/memory.c b/mm/memory.c
index 3b8e56eb08a3..4dd8e35b593a 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -988,16 +988,20 @@ static inline int folio_pte_batch(struct folio *folio, unsigned long addr,
{
unsigned long folio_end_pfn = folio_pfn(folio) + folio_nr_pages(folio);
const pte_t *end_ptep = start_ptep + max_nr;
- pte_t expected_pte = __pte_batch_clear_ignored(pte_next_pfn(pte), flags);
- pte_t *ptep = start_ptep + 1;
+ pte_t expected_pte, *ptep;
bool writable;
+ int nr;
if (any_writable)
*any_writable = false;
VM_WARN_ON_FOLIO(!pte_present(pte), folio);
- while (ptep != end_ptep) {
+ nr = pte_batch_hint(start_ptep, pte);
+ expected_pte = __pte_batch_clear_ignored(pte_advance_pfn(pte, nr), flags);
+ ptep = start_ptep + nr;
+
+ while (ptep < end_ptep) {
pte = ptep_get(ptep);
if (any_writable)
writable = !!pte_write(pte);
@@ -1011,17 +1015,18 @@ static inline int folio_pte_batch(struct folio *folio, unsigned long addr,
* corner cases the next PFN might fall into a different
* folio.
*/
- if (pte_pfn(pte) == folio_end_pfn)
+ if (pte_pfn(pte) >= folio_end_pfn)
break;
if (any_writable)
*any_writable |= writable;
- expected_pte = pte_next_pfn(expected_pte);
- ptep++;
+ nr = pte_batch_hint(ptep, pte);
+ expected_pte = pte_advance_pfn(expected_pte, nr);
+ ptep += nr;
}
- return ptep - start_ptep;
+ return min(ptep - start_ptep, max_nr);
}
/*
--
2.25.1
