[PATCH RFC net-next v4 4/9] net: page_pool: add DMA-sync-for-CPU inline helpers

[Alexander Lobakin]

Each driver is responsible for syncing buffers written by HW for CPU
before accessing them. Almost each PP-enabled driver uses the same
pattern, which could be shorthanded into a static inline to make driver
code a little bit more compact.
Introduce a couple such functions. The first one takes the actual size
of the data written by HW and is the main one to be used on Rx. The
second does the same, but only if the PP performs DMA synchronizations
at all.
Also constify pointer arguments of page_pool_get_dma_dir() and
page_pool_get_dma_addr() to give a bit more room for optimization,
as both of them are read-only.

Signed-off-by: Alexander Lobakin <aleksander.lobakin@xxxxxxxxx>
---
 include/net/page_pool.h | 49 ++++++++++++++++++++++++++++++++++++++---
 1 file changed, 46 insertions(+), 3 deletions(-)

diff --git a/include/net/page_pool.h b/include/net/page_pool.h
index ff3772fab707..89acf9e33639 100644
--- a/include/net/page_pool.h
+++ b/include/net/page_pool.h
@@ -304,8 +304,8 @@ static inline void *page_pool_dev_cache_alloc(struct page_pool *pool,
 /* get the stored dma direction. A driver might decide to treat this locally and
  * avoid the extra cache line from page_pool to determine the direction
  */
-static
-inline enum dma_data_direction page_pool_get_dma_dir(struct page_pool *pool)
+static inline enum dma_data_direction
+page_pool_get_dma_dir(const struct page_pool *pool)
 {
 	return pool->p.dma_dir;
 }
@@ -460,7 +460,7 @@ static inline void page_pool_cache_free(struct page_pool *pool, void *data,
 	page_pool_put_page(pool, virt_to_head_page(data), -1, allow_direct);
 }
 
-static inline dma_addr_t page_pool_get_dma_addr(struct page *page)
+static inline dma_addr_t page_pool_get_dma_addr(const struct page *page)
 {
 	dma_addr_t ret = page->dma_addr;
 
@@ -477,6 +477,49 @@ static inline void page_pool_set_dma_addr(struct page *page, dma_addr_t addr)
 		page->dma_addr_upper = upper_32_bits(addr);
 }
 
+/**
+ * __page_pool_dma_sync_for_cpu - sync Rx page for CPU after it's written by HW
+ * @pool: &page_pool the page belongs to
+ * @page: page to sync
+ * @offset: offset from page start to "hard" start if using frags
+ * @dma_sync_size: size of the data written to the page
+ *
+ * Can be used as a shorthand to sync Rx pages before accessing them in the
+ * driver. Caller must ensure the pool was created with %PP_FLAG_DMA_MAP.
+ * Note that this version performs DMA sync unconditionally, even if the
+ * associated PP doesn't perform sync-for-device. Consider the non-underscored
+ * version first if unsure.
+ */
+static inline void __page_pool_dma_sync_for_cpu(const struct page_pool *pool,
+						const struct page *page,
+						u32 offset, u32 dma_sync_size)
+{
+	dma_sync_single_range_for_cpu(pool->p.dev,
+				      page_pool_get_dma_addr(page),
+				      offset + pool->p.offset, dma_sync_size,
+				      page_pool_get_dma_dir(pool));
+}
+
+/**
+ * page_pool_dma_sync_for_cpu - sync Rx page for CPU if needed
+ * @pool: &page_pool the page belongs to
+ * @page: page to sync
+ * @offset: offset from page start to "hard" start if using frags
+ * @dma_sync_size: size of the data written to the page
+ *
+ * Performs DMA sync for CPU, but *only* when:
+ * 1) page_pool was created with %PP_FLAG_DMA_SYNC_DEV to manage DMA syncs;
+ * 2) AND sync shortcut is not available (IOMMU, swiotlb, non-coherent DMA, ...)
+ */
+static inline void page_pool_dma_sync_for_cpu(const struct page_pool *pool,
+					      const struct page *page,
+					      u32 offset, u32 dma_sync_size)
+{
+	if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV)
+		__page_pool_dma_sync_for_cpu(pool, page, offset,
+					     dma_sync_size);
+}
+
 static inline bool is_page_pool_compiled_in(void)
 {
 #ifdef CONFIG_PAGE_POOL
-- 
2.41.0