[v2,06/10] mm/mmu_gather: define ENCODED_PAGE_FLAG_DELAY_RMAP

Message ID 20240209221509.585251-7-david@redhat.com
State New
Headers
Series mm/memory: optimize unmap/zap with PTE-mapped THP |

Commit Message

David Hildenbrand Feb. 9, 2024, 10:15 p.m. UTC
  Nowadays, encoded pages are only used in mmu_gather handling. Let's
update the documentation, and define ENCODED_PAGE_BIT_DELAY_RMAP. While at
it, rename ENCODE_PAGE_BITS to ENCODED_PAGE_BITS.

If encoded page pointers would ever be used in other context again, we'd
likely want to change the defines to reflect their context (e.g.,
ENCODED_PAGE_FLAG_MMU_GATHER_DELAY_RMAP). For now, let's keep it simple.

This is a preparation for using the remaining spare bit to indicate that
the next item in an array of encoded pages is a "nr_pages" argument and
not an encoded page.

Reviewed-by: Ryan Roberts <ryan.roberts@arm.com>
Signed-off-by: David Hildenbrand <david@redhat.com>
---
 include/linux/mm_types.h | 17 +++++++++++------
 mm/mmu_gather.c          |  5 +++--
 2 files changed, 14 insertions(+), 8 deletions(-)
  

Patch

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 8b611e13153e..1b89eec0d6df 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -210,8 +210,8 @@  struct page {
  *
  * An 'encoded_page' pointer is a pointer to a regular 'struct page', but
  * with the low bits of the pointer indicating extra context-dependent
- * information. Not super-common, but happens in mmu_gather and mlock
- * handling, and this acts as a type system check on that use.
+ * information. Only used in mmu_gather handling, and this acts as a type
+ * system check on that use.
  *
  * We only really have two guaranteed bits in general, although you could
  * play with 'struct page' alignment (see CONFIG_HAVE_ALIGNED_STRUCT_PAGE)
@@ -220,21 +220,26 @@  struct page {
  * Use the supplied helper functions to endcode/decode the pointer and bits.
  */
 struct encoded_page;
-#define ENCODE_PAGE_BITS 3ul
+
+#define ENCODED_PAGE_BITS			3ul
+
+/* Perform rmap removal after we have flushed the TLB. */
+#define ENCODED_PAGE_BIT_DELAY_RMAP		1ul
+
 static __always_inline struct encoded_page *encode_page(struct page *page, unsigned long flags)
 {
-	BUILD_BUG_ON(flags > ENCODE_PAGE_BITS);
+	BUILD_BUG_ON(flags > ENCODED_PAGE_BITS);
 	return (struct encoded_page *)(flags | (unsigned long)page);
 }
 
 static inline unsigned long encoded_page_flags(struct encoded_page *page)
 {
-	return ENCODE_PAGE_BITS & (unsigned long)page;
+	return ENCODED_PAGE_BITS & (unsigned long)page;
 }
 
 static inline struct page *encoded_page_ptr(struct encoded_page *page)
 {
-	return (struct page *)(~ENCODE_PAGE_BITS & (unsigned long)page);
+	return (struct page *)(~ENCODED_PAGE_BITS & (unsigned long)page);
 }
 
 /*
diff --git a/mm/mmu_gather.c b/mm/mmu_gather.c
index ac733d81b112..6540c99c6758 100644
--- a/mm/mmu_gather.c
+++ b/mm/mmu_gather.c
@@ -53,7 +53,7 @@  static void tlb_flush_rmap_batch(struct mmu_gather_batch *batch, struct vm_area_
 	for (int i = 0; i < batch->nr; i++) {
 		struct encoded_page *enc = batch->encoded_pages[i];
 
-		if (encoded_page_flags(enc)) {
+		if (encoded_page_flags(enc) & ENCODED_PAGE_BIT_DELAY_RMAP) {
 			struct page *page = encoded_page_ptr(enc);
 			folio_remove_rmap_pte(page_folio(page), page, vma);
 		}
@@ -119,6 +119,7 @@  static void tlb_batch_list_free(struct mmu_gather *tlb)
 bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page,
 		bool delay_rmap, int page_size)
 {
+	int flags = delay_rmap ? ENCODED_PAGE_BIT_DELAY_RMAP : 0;
 	struct mmu_gather_batch *batch;
 
 	VM_BUG_ON(!tlb->end);
@@ -132,7 +133,7 @@  bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page,
 	 * Add the page and check if we are full. If so
 	 * force a flush.
 	 */
-	batch->encoded_pages[batch->nr++] = encode_page(page, delay_rmap);
+	batch->encoded_pages[batch->nr++] = encode_page(page, flags);
 	if (batch->nr == batch->max) {
 		if (!tlb_next_batch(tlb))
 			return true;