page_pool: transition to reference count management after page draining

To support multiple users referencing the same fragment,
'pp_frag_count' is renamed to 'pp_ref_count', transitioning pp pages
from fragment management to reference count management after draining
based on the suggestion from [1].

The idea is that the concept of fragmenting exists before the page is
drained, and all related functions retain their current names.
However, once the page is drained, its management shifts to being
governed by 'pp_ref_count'. Therefore, all functions associated with
that lifecycle stage of a pp page are renamed.

[1]
http://lore.kernel.org/netdev/f71d9448-70c8-8793-dc9a-0eb48a570300@huawei.com

Signed-off-by: Liang Chen <liangchen.linux@gmail.com>
Reviewed-by: Yunsheng Lin <linyunsheng@huawei.com>
Reviewed-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Reviewed-by: Mina Almasry <almasrymina@google.com>
Link: https://lore.kernel.org/r/20231212044614.42733-2-liangchen.linux@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

2 files changed, 37 insertions, 29 deletions

diff --git a/include/net/page_pool/helpers.h b/include/net/page_pool/helpers.h
index 7dc65774cde5..841e0a930bd7 100644
--- a/include/net/page_pool/helpers.h
+++ b/include/net/page_pool/helpers.h
@@ -29,7 +29,7 @@
  * page allocated from page pool. Page splitting enables memory saving and thus
  * avoids TLB/cache miss for data access, but there also is some cost to
  * implement page splitting, mainly some cache line dirtying/bouncing for
- * 'struct page' and atomic operation for page->pp_frag_count.
+ * 'struct page' and atomic operation for page->pp_ref_count.
  *
  * The API keeps track of in-flight pages, in order to let API users know when
  * it is safe to free a page_pool object, the API users must call
@@ -210,69 +210,77 @@ inline enum dma_data_direction page_pool_get_dma_dir(struct page_pool *pool)
 	return pool->p.dma_dir;
 }
 
-/* pp_frag_count represents the number of writers who can update the page
- * either by updating skb->data or via DMA mappings for the device.
- * We can't rely on the page refcnt for that as we don't know who might be
- * holding page references and we can't reliably destroy or sync DMA mappings
- * of the fragments.
+/**
+ * page_pool_fragment_page() - split a fresh page into fragments
+ * @page:	page to split
+ * @nr:		references to set
+ *
+ * pp_ref_count represents the number of outstanding references to the page,
+ * which will be freed using page_pool APIs (rather than page allocator APIs
+ * like put_page()). Such references are usually held by page_pool-aware
+ * objects like skbs marked for page pool recycling.
  *
- * When pp_frag_count reaches 0 we can either recycle the page if the page
- * refcnt is 1 or return it back to the memory allocator and destroy any
- * mappings we have.
+ * This helper allows the caller to take (set) multiple references to a
+ * freshly allocated page. The page must be freshly allocated (have a
+ * pp_ref_count of 1). This is commonly done by drivers and
+ * "fragment allocators" to save atomic operations - either when they know
+ * upfront how many references they will need; or to take MAX references and
+ * return the unused ones with a single atomic dec(), instead of performing
+ * multiple atomic inc() operations.
  */
 static inline void page_pool_fragment_page(struct page *page, long nr)
 {
-	atomic_long_set(&page->pp_frag_count, nr);
+	atomic_long_set(&page->pp_ref_count, nr);
 }
 
-static inline long page_pool_defrag_page(struct page *page, long nr)
+static inline long page_pool_unref_page(struct page *page, long nr)
 {
 	long ret;
 
-	/* If nr == pp_frag_count then we have cleared all remaining
+	/* If nr == pp_ref_count then we have cleared all remaining
 	 * references to the page:
 	 * 1. 'n == 1': no need to actually overwrite it.
 	 * 2. 'n != 1': overwrite it with one, which is the rare case
-	 *              for pp_frag_count draining.
+	 *              for pp_ref_count draining.
 	 *
 	 * The main advantage to doing this is that not only we avoid a atomic
 	 * update, as an atomic_read is generally a much cheaper operation than
 	 * an atomic update, especially when dealing with a page that may be
-	 * partitioned into only 2 or 3 pieces; but also unify the pp_frag_count
+	 * referenced by only 2 or 3 users; but also unify the pp_ref_count
 	 * handling by ensuring all pages have partitioned into only 1 piece
 	 * initially, and only overwrite it when the page is partitioned into
 	 * more than one piece.
 	 */
-	if (atomic_long_read(&page->pp_frag_count) == nr) {
+	if (atomic_long_read(&page->pp_ref_count) == nr) {
 		/* As we have ensured nr is always one for constant case using
 		 * the BUILD_BUG_ON(), only need to handle the non-constant case
-		 * here for pp_frag_count draining, which is a rare case.
+		 * here for pp_ref_count draining, which is a rare case.
 		 */
 		BUILD_BUG_ON(__builtin_constant_p(nr) && nr != 1);
 		if (!__builtin_constant_p(nr))
-			atomic_long_set(&page->pp_frag_count, 1);
+			atomic_long_set(&page->pp_ref_count, 1);
 
 		return 0;
 	}
 
-	ret = atomic_long_sub_return(nr, &page->pp_frag_count);
+	ret = atomic_long_sub_return(nr, &page->pp_ref_count);
 	WARN_ON(ret < 0);
 
-	/* We are the last user here too, reset pp_frag_count back to 1 to
+	/* We are the last user here too, reset pp_ref_count back to 1 to
 	 * ensure all pages have been partitioned into 1 piece initially,
 	 * this should be the rare case when the last two fragment users call
-	 * page_pool_defrag_page() currently.
+	 * page_pool_unref_page() currently.
 	 */
 	if (unlikely(!ret))
-		atomic_long_set(&page->pp_frag_count, 1);
+		atomic_long_set(&page->pp_ref_count, 1);
 
 	return ret;
 }
 
-static inline bool page_pool_is_last_frag(struct page *page)
+static inline bool page_pool_is_last_ref(struct page *page)
 {
-	/* If page_pool_defrag_page() returns 0, we were the last user */
-	return page_pool_defrag_page(page, 1) == 0;
+	/* If page_pool_unref_page() returns 0, we were the last user */
+	return page_pool_unref_page(page, 1) == 0;
 }
 
 /**
@@ -297,10 +305,10 @@ static inline void page_pool_put_page(struct page_pool *pool,
 	 * allow registering MEM_TYPE_PAGE_POOL, but shield linker.
 	 */
 #ifdef CONFIG_PAGE_POOL
-	if (!page_pool_is_last_frag(page))
+	if (!page_pool_is_last_ref(page))
 		return;
 
-	page_pool_put_defragged_page(pool, page, dma_sync_size, allow_direct);
+	page_pool_put_unrefed_page(pool, page, dma_sync_size, allow_direct);
 #endif
 }
 
diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h
index ac286ea8ce2d..76481c465375 100644
--- a/include/net/page_pool/types.h
+++ b/include/net/page_pool/types.h
@@ -234,9 +234,9 @@ static inline void page_pool_put_page_bulk(struct page_pool *pool, void **data,
 }
 #endif
 
-void page_pool_put_defragged_page(struct page_pool *pool, struct page *page,
-				  unsigned int dma_sync_size,
-				  bool allow_direct);
+void page_pool_put_unrefed_page(struct page_pool *pool, struct page *page,
+				unsigned int dma_sync_size,
+				bool allow_direct);
 
 static inline bool is_page_pool_compiled_in(void)
 {