[PATCH net-next 5/7] page_pool: don't use driver-set flags field directly

[Alexander Lobakin <aleksander.lobakin@intel.com>]

page_pool::p is driver-defined params, copied directly from the
structure passed to page_pool_create(). The structure isn't meant
to be modified by the Page Pool core code and this even might look
confusing[0][1].
In order to be able to alter some flags, let's define our own, internal
fields the same way as the already existing one (::has_init_callback).
They are defined as bits in the driver-set params, leave them so here
as well, to not waste byte-per-bit or so. Almost 30 bits are still free
for future extensions.
We could've defined only new flags here or only the ones we may need
to alter, but checking some flags in one place while others in another
doesn't sound convenient or intuitive. ::flags passed by the driver can
now go to the "slow" PP params.

Suggested-by: Jakub Kicinski <kuba@kernel.org>
Link[0]: https://lore.kernel.org/netdev/20230703133207.4f0c54ce@kernel.org
Suggested-by: Alexander Duyck <alexanderduyck@fb.com>
Link[1]: https://lore.kernel.org/netdev/CAKgT0UfZCGnWgOH96E4GV3ZP6LLbROHM7SHE8NKwq+exX+Gk_Q@mail.gmail.com
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
---
 include/net/page_pool/types.h |  9 ++++++---
 net/core/page_pool.c          | 34 ++++++++++++++++++----------------
 2 files changed, 24 insertions(+), 19 deletions(-)

diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h
index 217e73b7e4fc..6a767ad1c572 100644
--- a/include/net/page_pool/types.h
+++ b/include/net/page_pool/types.h
@@ -44,7 +44,6 @@ struct pp_alloc_cache {
 
 /**
  * struct page_pool_params - page pool parameters
- * @flags:	PP_FLAG_DMA_MAP, PP_FLAG_DMA_SYNC_DEV
  * @order:	2^order pages on allocation
  * @pool_size:	size of the ptr_ring
  * @nid:	NUMA node id to allocate from pages from
@@ -54,10 +53,10 @@ struct pp_alloc_cache {
  * @dma_dir:	DMA mapping direction
  * @max_len:	max DMA sync memory size for PP_FLAG_DMA_SYNC_DEV
  * @offset:	DMA sync address offset for PP_FLAG_DMA_SYNC_DEV
+ * @flags:	PP_FLAG_DMA_MAP, PP_FLAG_DMA_SYNC_DEV
  */
 struct page_pool_params {
 	struct_group_tagged(page_pool_params_fast, fast,
-		unsigned int	flags;
 		unsigned int	order;
 		unsigned int	pool_size;
 		int		nid;
@@ -68,6 +67,7 @@ struct page_pool_params {
 		unsigned int	offset;
 	);
 	struct_group_tagged(page_pool_params_slow, slow,
+		unsigned int	flags;
 		struct net_device *netdev;
 /* private: used by test code only */
 		void (*init_callback)(struct page *page, void *arg);
@@ -129,7 +129,10 @@ struct page_pool {
 	struct page_pool_params_fast p;
 
 	u32 pages_state_hold_cnt;
-	bool has_init_callback;
+
+	bool dma_map:1;			/* Perform DMA mapping */
+	bool dma_sync:1;		/* Perform DMA sync */
+	bool has_init_callback:1;	/* slow.init_callback is set */
 
 	/* The following block must stay within one cacheline. On 32-bit
 	 * systems, sizeof(long) == sizeof(int), so that the block size is
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index be1219816990..2c353906407c 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -188,7 +188,7 @@ static int page_pool_init(struct page_pool *pool,
 	memcpy(&pool->slow, &params->slow, sizeof(pool->slow));
 
 	/* Validate only known flags were used */
-	if (pool->p.flags & ~(PP_FLAG_ALL))
+	if (pool->slow.flags & ~(PP_FLAG_ALL))
 		return -EINVAL;
 
 	if (pool->p.pool_size)
@@ -202,22 +202,26 @@ static int page_pool_init(struct page_pool *pool,
 	 * DMA_BIDIRECTIONAL is for allowing page used for DMA sending,
 	 * which is the XDP_TX use-case.
 	 */
-	if (pool->p.flags & PP_FLAG_DMA_MAP) {
+	if (pool->slow.flags & PP_FLAG_DMA_MAP) {
 		if ((pool->p.dma_dir != DMA_FROM_DEVICE) &&
 		    (pool->p.dma_dir != DMA_BIDIRECTIONAL))
 			return -EINVAL;
+
+		pool->dma_map = true;
 	}
 
-	if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV) {
+	if (pool->slow.flags & PP_FLAG_DMA_SYNC_DEV) {
 		/* In order to request DMA-sync-for-device the page
 		 * needs to be mapped
 		 */
-		if (!(pool->p.flags & PP_FLAG_DMA_MAP))
+		if (!(pool->slow.flags & PP_FLAG_DMA_MAP))
 			return -EINVAL;
 
 		if (!pool->p.max_len)
 			return -EINVAL;
 
+		pool->dma_sync = true;
+
 		/* pool->p.offset has to be set according to the address
 		 * offset used by the DMA engine to start copying rx data
 		 */
@@ -243,7 +247,7 @@ static int page_pool_init(struct page_pool *pool,
 	/* Driver calling page_pool_create() also call page_pool_destroy() */
 	refcount_set(&pool->user_cnt, 1);
 
-	if (pool->p.flags & PP_FLAG_DMA_MAP)
+	if (pool->dma_map)
 		get_device(pool->p.dev);
 
 	return 0;
@@ -253,7 +257,7 @@ static void page_pool_uninit(struct page_pool *pool)
 {
 	ptr_ring_cleanup(&pool->ring, NULL);
 
-	if (pool->p.flags & PP_FLAG_DMA_MAP)
+	if (pool->dma_map)
 		put_device(pool->p.dev);
 
 #ifdef CONFIG_PAGE_POOL_STATS
@@ -396,7 +400,7 @@ static bool page_pool_dma_map(struct page_pool *pool, struct page *page)
 	if (page_pool_set_dma_addr(page, dma))
 		goto unmap_failed;
 
-	if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV)
+	if (pool->dma_sync)
 		page_pool_dma_sync_for_device(pool, page, pool->p.max_len);
 
 	return true;
@@ -442,8 +446,7 @@ static struct page *__page_pool_alloc_page_order(struct page_pool *pool,
 	if (unlikely(!page))
 		return NULL;
 
-	if ((pool->p.flags & PP_FLAG_DMA_MAP) &&
-	    unlikely(!page_pool_dma_map(pool, page))) {
+	if (pool->dma_map && unlikely(!page_pool_dma_map(pool, page))) {
 		put_page(page);
 		return NULL;
 	}
@@ -463,8 +466,8 @@ static struct page *__page_pool_alloc_pages_slow(struct page_pool *pool,
 						 gfp_t gfp)
 {
 	const int bulk = PP_ALLOC_CACHE_REFILL;
-	unsigned int pp_flags = pool->p.flags;
 	unsigned int pp_order = pool->p.order;
+	bool dma_map = pool->dma_map;
 	struct page *page;
 	int i, nr_pages;
 
@@ -489,8 +492,7 @@ static struct page *__page_pool_alloc_pages_slow(struct page_pool *pool,
 	 */
 	for (i = 0; i < nr_pages; i++) {
 		page = pool->alloc.cache[i];
-		if ((pp_flags & PP_FLAG_DMA_MAP) &&
-		    unlikely(!page_pool_dma_map(pool, page))) {
+		if (dma_map && unlikely(!page_pool_dma_map(pool, page))) {
 			put_page(page);
 			continue;
 		}
@@ -562,7 +564,7 @@ void __page_pool_release_page_dma(struct page_pool *pool, struct page *page)
 {
 	dma_addr_t dma;
 
-	if (!(pool->p.flags & PP_FLAG_DMA_MAP))
+	if (!pool->dma_map)
 		/* Always account for inflight pages, even if we didn't
 		 * map them
 		 */
@@ -640,7 +642,7 @@ static bool page_pool_recycle_in_cache(struct page *page,
 }
 
 /* If the page refcnt == 1, this will try to recycle the page.
- * if PP_FLAG_DMA_SYNC_DEV is set, we'll try to sync the DMA area for
+ * If pool->dma_sync is set, we'll try to sync the DMA area for
  * the configured size min(dma_sync_size, pool->max_len).
  * If the page refcnt != 1, then the page will be returned to memory
  * subsystem.
@@ -663,7 +665,7 @@ __page_pool_put_page(struct page_pool *pool, struct page *page,
 	if (likely(page_ref_count(page) == 1 && !page_is_pfmemalloc(page))) {
 		/* Read barrier done in page_ref_count / READ_ONCE */
 
-		if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV)
+		if (pool->dma_sync)
 			page_pool_dma_sync_for_device(pool, page,
 						      dma_sync_size);
 
@@ -776,7 +778,7 @@ static struct page *page_pool_drain_frag(struct page_pool *pool,
 		return NULL;
 
 	if (page_ref_count(page) == 1 && !page_is_pfmemalloc(page)) {
-		if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV)
+		if (pool->dma_sync)
 			page_pool_dma_sync_for_device(pool, page, -1);
 
 		return page;
-- 
2.43.0