page_pool: split types and declarations from page_pool.h

Split types and pure function declarations from page_pool.h
and add them in page_page/types.h, so that C sources can
include page_pool.h and headers should generally only include
page_pool/types.h as suggested by jakub.
Rename page_pool.h to page_pool/helpers.h to have both in
one place.

Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Suggested-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Reviewed-by: Alexander Duyck <alexanderduyck@fb.com>
Link: https://lore.kernel.org/r/20230804180529.2483231-2-aleksander.lobakin@intel.com
[Jakub: change microsoft/mana, fix kdoc paths in Documentation]
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

4 files changed, 245 insertions, 239 deletions

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 16a49ba534e4..888e3d7e74c1 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -32,7 +32,7 @@
 #include <linux/if_packet.h>
 #include <linux/llist.h>
 #include <net/flow.h>
-#include <net/page_pool.h>
+#include <net/page_pool/types.h>
 #if IS_ENABLED(CONFIG_NF_CONNTRACK)
 #include <linux/netfilter/nf_conntrack_common.h>
 #endif
diff --git a/include/net/page_pool.h b/include/net/page_pool/helpers.h
index 73d4f786418d..78df91804c87 100644
--- a/include/net/page_pool.h
+++ b/include/net/page_pool/helpers.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0
  *
- * page_pool.h
+ * page_pool/helpers.h
  *	Author:	Jesper Dangaard Brouer <netoptimizer@brouer.com>
  *	Copyright (C) 2016 Red Hat, Inc.
  */
@@ -26,126 +26,12 @@
  * will release the DMA mapping and in-flight state accounting.  We
  * hope to lift this requirement in the future.
  */
-#ifndef _NET_PAGE_POOL_H
-#define _NET_PAGE_POOL_H
+#ifndef _NET_PAGE_POOL_HELPERS_H
+#define _NET_PAGE_POOL_HELPERS_H
 
-#include <linux/mm.h> /* Needed by ptr_ring */
-#include <linux/ptr_ring.h>
-#include <linux/dma-direction.h>
-
-#define PP_FLAG_DMA_MAP		BIT(0) /* Should page_pool do the DMA
-					* map/unmap
-					*/
-#define PP_FLAG_DMA_SYNC_DEV	BIT(1) /* If set all pages that the driver gets
-					* from page_pool will be
-					* DMA-synced-for-device according to
-					* the length provided by the device
-					* driver.
-					* Please note DMA-sync-for-CPU is still
-					* device driver responsibility
-					*/
-#define PP_FLAG_PAGE_FRAG	BIT(2) /* for page frag feature */
-#define PP_FLAG_ALL		(PP_FLAG_DMA_MAP |\
-				 PP_FLAG_DMA_SYNC_DEV |\
-				 PP_FLAG_PAGE_FRAG)
-
-/*
- * Fast allocation side cache array/stack
- *
- * The cache size and refill watermark is related to the network
- * use-case.  The NAPI budget is 64 packets.  After a NAPI poll the RX
- * ring is usually refilled and the max consumed elements will be 64,
- * thus a natural max size of objects needed in the cache.
- *
- * Keeping room for more objects, is due to XDP_DROP use-case.  As
- * XDP_DROP allows the opportunity to recycle objects directly into
- * this array, as it shares the same softirq/NAPI protection.  If
- * cache is already full (or partly full) then the XDP_DROP recycles
- * would have to take a slower code path.
- */
-#define PP_ALLOC_CACHE_SIZE	128
-#define PP_ALLOC_CACHE_REFILL	64
-struct pp_alloc_cache {
-	u32 count;
-	struct page *cache[PP_ALLOC_CACHE_SIZE];
-};
-
-/**
- * struct page_pool_params - page pool parameters
- * @flags:	PP_FLAG_DMA_MAP, PP_FLAG_DMA_SYNC_DEV, PP_FLAG_PAGE_FRAG
- * @order:	2^order pages on allocation
- * @pool_size:	size of the ptr_ring
- * @nid:	NUMA node id to allocate from pages from
- * @dev:	device, for DMA pre-mapping purposes
- * @napi:	NAPI which is the sole consumer of pages, otherwise NULL
- * @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
- */
-struct page_pool_params {
-	unsigned int	flags;
-	unsigned int	order;
-	unsigned int	pool_size;
-	int		nid;
-	struct device	*dev;
-	struct napi_struct *napi;
-	enum dma_data_direction dma_dir;
-	unsigned int	max_len;
-	unsigned int	offset;
-/* private: used by test code only */
-	void (*init_callback)(struct page *page, void *arg);
-	void *init_arg;
-};
+#include <net/page_pool/types.h>
 
 #ifdef CONFIG_PAGE_POOL_STATS
-/**
- * struct page_pool_alloc_stats - allocation statistics
- * @fast:	successful fast path allocations
- * @slow:	slow path order-0 allocations
- * @slow_high_order: slow path high order allocations
- * @empty:	ptr ring is empty, so a slow path allocation was forced
- * @refill:	an allocation which triggered a refill of the cache
- * @waive:	pages obtained from the ptr ring that cannot be added to
- *		the cache due to a NUMA mismatch
- */
-struct page_pool_alloc_stats {
-	u64 fast;
-	u64 slow;
-	u64 slow_high_order;
-	u64 empty;
-	u64 refill;
-	u64 waive;
-};
-
-/**
- * struct page_pool_recycle_stats - recycling (freeing) statistics
- * @cached:	recycling placed page in the page pool cache
- * @cache_full:	page pool cache was full
- * @ring:	page placed into the ptr ring
- * @ring_full:	page released from page pool because the ptr ring was full
- * @released_refcnt:	page released (and not recycled) because refcnt > 1
- */
-struct page_pool_recycle_stats {
-	u64 cached;
-	u64 cache_full;
-	u64 ring;
-	u64 ring_full;
-	u64 released_refcnt;
-};
-
-/**
- * struct page_pool_stats - combined page pool use statistics
- * @alloc_stats:	see struct page_pool_alloc_stats
- * @recycle_stats:	see struct page_pool_recycle_stats
- *
- * Wrapper struct for combining page pool stats with different storage
- * requirements.
- */
-struct page_pool_stats {
-	struct page_pool_alloc_stats alloc_stats;
-	struct page_pool_recycle_stats recycle_stats;
-};
-
 int page_pool_ethtool_stats_get_count(void);
 u8 *page_pool_ethtool_stats_get_strings(u8 *data);
 u64 *page_pool_ethtool_stats_get(u64 *data, void *stats);
@@ -158,7 +44,6 @@ u64 *page_pool_ethtool_stats_get(u64 *data, void *stats);
 bool page_pool_get_stats(struct page_pool *pool,
 			 struct page_pool_stats *stats);
 #else
-
 static inline int page_pool_ethtool_stats_get_count(void)
 {
 	return 0;
@@ -173,72 +58,7 @@ static inline u64 *page_pool_ethtool_stats_get(u64 *data, void *stats)
 {
 	return data;
 }
-
-#endif
-
-struct page_pool {
-	struct page_pool_params p;
-
-	struct delayed_work release_dw;
-	void (*disconnect)(void *);
-	unsigned long defer_start;
-	unsigned long defer_warn;
-
-	u32 pages_state_hold_cnt;
-	unsigned int frag_offset;
-	struct page *frag_page;
-	long frag_users;
-
-#ifdef CONFIG_PAGE_POOL_STATS
-	/* these stats are incremented while in softirq context */
-	struct page_pool_alloc_stats alloc_stats;
 #endif
-	u32 xdp_mem_id;
-
-	/*
-	 * Data structure for allocation side
-	 *
-	 * Drivers allocation side usually already perform some kind
-	 * of resource protection.  Piggyback on this protection, and
-	 * require driver to protect allocation side.
-	 *
-	 * For NIC drivers this means, allocate a page_pool per
-	 * RX-queue. As the RX-queue is already protected by
-	 * Softirq/BH scheduling and napi_schedule. NAPI schedule
-	 * guarantee that a single napi_struct will only be scheduled
-	 * on a single CPU (see napi_schedule).
-	 */
-	struct pp_alloc_cache alloc ____cacheline_aligned_in_smp;
-
-	/* Data structure for storing recycled pages.
-	 *
-	 * Returning/freeing pages is more complicated synchronization
-	 * wise, because free's can happen on remote CPUs, with no
-	 * association with allocation resource.
-	 *
-	 * Use ptr_ring, as it separates consumer and producer
-	 * effeciently, it a way that doesn't bounce cache-lines.
-	 *
-	 * TODO: Implement bulk return pages into this structure.
-	 */
-	struct ptr_ring ring;
-
-#ifdef CONFIG_PAGE_POOL_STATS
-	/* recycle stats are per-cpu to avoid locking */
-	struct page_pool_recycle_stats __percpu *recycle_stats;
-#endif
-	atomic_t pages_state_release_cnt;
-
-	/* A page_pool is strictly tied to a single RX-queue being
-	 * protected by NAPI, due to above pp_alloc_cache. This
-	 * refcnt serves purpose is to simplify drivers error handling.
-	 */
-	refcount_t user_cnt;
-
-	u64 destroy_cnt;
-};
-
-struct page *page_pool_alloc_pages(struct page_pool *pool, gfp_t gfp);
 
 /**
  * page_pool_dev_alloc_pages() - allocate a page.
@@ -253,9 +73,6 @@ static inline struct page *page_pool_dev_alloc_pages(struct page_pool *pool)
 	return page_pool_alloc_pages(pool, gfp);
 }
 
-struct page *page_pool_alloc_frag(struct page_pool *pool, unsigned int *offset,
-				  unsigned int size, gfp_t gfp);
-
 static inline struct page *page_pool_dev_alloc_frag(struct page_pool *pool,
 						    unsigned int *offset,
 						    unsigned int size)
@@ -278,44 +95,6 @@ inline enum dma_data_direction page_pool_get_dma_dir(struct page_pool *pool)
 	return pool->p.dma_dir;
 }
 
-bool page_pool_return_skb_page(struct page *page, bool napi_safe);
-
-struct page_pool *page_pool_create(const struct page_pool_params *params);
-
-struct xdp_mem_info;
-
-#ifdef CONFIG_PAGE_POOL
-void page_pool_unlink_napi(struct page_pool *pool);
-void page_pool_destroy(struct page_pool *pool);
-void page_pool_use_xdp_mem(struct page_pool *pool, void (*disconnect)(void *),
-			   struct xdp_mem_info *mem);
-void page_pool_put_page_bulk(struct page_pool *pool, void **data,
-			     int count);
-#else
-static inline void page_pool_unlink_napi(struct page_pool *pool)
-{
-}
-
-static inline void page_pool_destroy(struct page_pool *pool)
-{
-}
-
-static inline void page_pool_use_xdp_mem(struct page_pool *pool,
-					 void (*disconnect)(void *),
-					 struct xdp_mem_info *mem)
-{
-}
-
-static inline void page_pool_put_page_bulk(struct page_pool *pool, void **data,
-					   int count)
-{
-}
-#endif
-
-void page_pool_put_defragged_page(struct page_pool *pool, struct page *page,
-				  unsigned int dma_sync_size,
-				  bool allow_direct);
-
 /* 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
@@ -445,26 +224,15 @@ static inline void page_pool_set_dma_addr(struct page *page, dma_addr_t addr)
 		page->dma_addr_upper = upper_32_bits(addr);
 }
 
-static inline bool is_page_pool_compiled_in(void)
-{
-#ifdef CONFIG_PAGE_POOL
-	return true;
-#else
-	return false;
-#endif
-}
-
 static inline bool page_pool_put(struct page_pool *pool)
 {
 	return refcount_dec_and_test(&pool->user_cnt);
 }
 
-/* Caller must provide appropriate safe context, e.g. NAPI. */
-void page_pool_update_nid(struct page_pool *pool, int new_nid);
 static inline void page_pool_nid_changed(struct page_pool *pool, int new_nid)
 {
 	if (unlikely(pool->p.nid != new_nid))
 		page_pool_update_nid(pool, new_nid);
 }
 
-#endif /* _NET_PAGE_POOL_H */
+#endif /* _NET_PAGE_POOL_HELPERS_H */
diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h
new file mode 100644
index 000000000000..9ac39191bed7
--- /dev/null
+++ b/include/net/page_pool/types.h
@@ -0,0 +1,238 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _NET_PAGE_POOL_TYPES_H
+#define _NET_PAGE_POOL_TYPES_H
+
+#include <linux/dma-direction.h>
+#include <linux/ptr_ring.h>
+
+#define PP_FLAG_DMA_MAP		BIT(0) /* Should page_pool do the DMA
+					* map/unmap
+					*/
+#define PP_FLAG_DMA_SYNC_DEV	BIT(1) /* If set all pages that the driver gets
+					* from page_pool will be
+					* DMA-synced-for-device according to
+					* the length provided by the device
+					* driver.
+					* Please note DMA-sync-for-CPU is still
+					* device driver responsibility
+					*/
+#define PP_FLAG_PAGE_FRAG	BIT(2) /* for page frag feature */
+#define PP_FLAG_ALL		(PP_FLAG_DMA_MAP |\
+				 PP_FLAG_DMA_SYNC_DEV |\
+				 PP_FLAG_PAGE_FRAG)
+
+/*
+ * Fast allocation side cache array/stack
+ *
+ * The cache size and refill watermark is related to the network
+ * use-case.  The NAPI budget is 64 packets.  After a NAPI poll the RX
+ * ring is usually refilled and the max consumed elements will be 64,
+ * thus a natural max size of objects needed in the cache.
+ *
+ * Keeping room for more objects, is due to XDP_DROP use-case.  As
+ * XDP_DROP allows the opportunity to recycle objects directly into
+ * this array, as it shares the same softirq/NAPI protection.  If
+ * cache is already full (or partly full) then the XDP_DROP recycles
+ * would have to take a slower code path.
+ */
+#define PP_ALLOC_CACHE_SIZE	128
+#define PP_ALLOC_CACHE_REFILL	64
+struct pp_alloc_cache {
+	u32 count;
+	struct page *cache[PP_ALLOC_CACHE_SIZE];
+};
+
+/**
+ * struct page_pool_params - page pool parameters
+ * @flags:	PP_FLAG_DMA_MAP, PP_FLAG_DMA_SYNC_DEV, PP_FLAG_PAGE_FRAG
+ * @order:	2^order pages on allocation
+ * @pool_size:	size of the ptr_ring
+ * @nid:	NUMA node id to allocate from pages from
+ * @dev:	device, for DMA pre-mapping purposes
+ * @napi:	NAPI which is the sole consumer of pages, otherwise NULL
+ * @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
+ */
+struct page_pool_params {
+	unsigned int	flags;
+	unsigned int	order;
+	unsigned int	pool_size;
+	int		nid;
+	struct device	*dev;
+	struct napi_struct *napi;
+	enum dma_data_direction dma_dir;
+	unsigned int	max_len;
+	unsigned int	offset;
+/* private: used by test code only */
+	void (*init_callback)(struct page *page, void *arg);
+	void *init_arg;
+};
+
+#ifdef CONFIG_PAGE_POOL_STATS
+/**
+ * struct page_pool_alloc_stats - allocation statistics
+ * @fast:	successful fast path allocations
+ * @slow:	slow path order-0 allocations
+ * @slow_high_order: slow path high order allocations
+ * @empty:	ptr ring is empty, so a slow path allocation was forced
+ * @refill:	an allocation which triggered a refill of the cache
+ * @waive:	pages obtained from the ptr ring that cannot be added to
+ *		the cache due to a NUMA mismatch
+ */
+struct page_pool_alloc_stats {
+	u64 fast;
+	u64 slow;
+	u64 slow_high_order;
+	u64 empty;
+	u64 refill;
+	u64 waive;
+};
+
+/**
+ * struct page_pool_recycle_stats - recycling (freeing) statistics
+ * @cached:	recycling placed page in the page pool cache
+ * @cache_full:	page pool cache was full
+ * @ring:	page placed into the ptr ring
+ * @ring_full:	page released from page pool because the ptr ring was full
+ * @released_refcnt:	page released (and not recycled) because refcnt > 1
+ */
+struct page_pool_recycle_stats {
+	u64 cached;
+	u64 cache_full;
+	u64 ring;
+	u64 ring_full;
+	u64 released_refcnt;
+};
+
+/**
+ * struct page_pool_stats - combined page pool use statistics
+ * @alloc_stats:	see struct page_pool_alloc_stats
+ * @recycle_stats:	see struct page_pool_recycle_stats
+ *
+ * Wrapper struct for combining page pool stats with different storage
+ * requirements.
+ */
+struct page_pool_stats {
+	struct page_pool_alloc_stats alloc_stats;
+	struct page_pool_recycle_stats recycle_stats;
+};
+#endif
+
+struct page_pool {
+	struct page_pool_params p;
+
+	struct delayed_work release_dw;
+	void (*disconnect)(void *pool);
+	unsigned long defer_start;
+	unsigned long defer_warn;
+
+	u32 pages_state_hold_cnt;
+	unsigned int frag_offset;
+	struct page *frag_page;
+	long frag_users;
+
+#ifdef CONFIG_PAGE_POOL_STATS
+	/* these stats are incremented while in softirq context */
+	struct page_pool_alloc_stats alloc_stats;
+#endif
+	u32 xdp_mem_id;
+
+	/*
+	 * Data structure for allocation side
+	 *
+	 * Drivers allocation side usually already perform some kind
+	 * of resource protection.  Piggyback on this protection, and
+	 * require driver to protect allocation side.
+	 *
+	 * For NIC drivers this means, allocate a page_pool per
+	 * RX-queue. As the RX-queue is already protected by
+	 * Softirq/BH scheduling and napi_schedule. NAPI schedule
+	 * guarantee that a single napi_struct will only be scheduled
+	 * on a single CPU (see napi_schedule).
+	 */
+	struct pp_alloc_cache alloc ____cacheline_aligned_in_smp;
+
+	/* Data structure for storing recycled pages.
+	 *
+	 * Returning/freeing pages is more complicated synchronization
+	 * wise, because free's can happen on remote CPUs, with no
+	 * association with allocation resource.
+	 *
+	 * Use ptr_ring, as it separates consumer and producer
+	 * efficiently, it a way that doesn't bounce cache-lines.
+	 *
+	 * TODO: Implement bulk return pages into this structure.
+	 */
+	struct ptr_ring ring;
+
+#ifdef CONFIG_PAGE_POOL_STATS
+	/* recycle stats are per-cpu to avoid locking */
+	struct page_pool_recycle_stats __percpu *recycle_stats;
+#endif
+	atomic_t pages_state_release_cnt;
+
+	/* A page_pool is strictly tied to a single RX-queue being
+	 * protected by NAPI, due to above pp_alloc_cache. This
+	 * refcnt serves purpose is to simplify drivers error handling.
+	 */
+	refcount_t user_cnt;
+
+	u64 destroy_cnt;
+};
+
+struct page *page_pool_alloc_pages(struct page_pool *pool, gfp_t gfp);
+struct page *page_pool_alloc_frag(struct page_pool *pool, unsigned int *offset,
+				  unsigned int size, gfp_t gfp);
+bool page_pool_return_skb_page(struct page *page, bool napi_safe);
+
+struct page_pool *page_pool_create(const struct page_pool_params *params);
+
+struct xdp_mem_info;
+
+#ifdef CONFIG_PAGE_POOL
+void page_pool_unlink_napi(struct page_pool *pool);
+void page_pool_destroy(struct page_pool *pool);
+void page_pool_use_xdp_mem(struct page_pool *pool, void (*disconnect)(void *),
+			   struct xdp_mem_info *mem);
+void page_pool_put_page_bulk(struct page_pool *pool, void **data,
+			     int count);
+#else
+static inline void page_pool_unlink_napi(struct page_pool *pool)
+{
+}
+
+static inline void page_pool_destroy(struct page_pool *pool)
+{
+}
+
+static inline void page_pool_use_xdp_mem(struct page_pool *pool,
+					 void (*disconnect)(void *),
+					 struct xdp_mem_info *mem)
+{
+}
+
+static inline void page_pool_put_page_bulk(struct page_pool *pool, void **data,
+					   int count)
+{
+}
+#endif
+
+void page_pool_put_defragged_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)
+{
+#ifdef CONFIG_PAGE_POOL
+	return true;
+#else
+	return false;
+#endif
+}
+
+/* Caller must provide appropriate safe context, e.g. NAPI. */
+void page_pool_update_nid(struct page_pool *pool, int new_nid);
+
+#endif /* _NET_PAGE_POOL_H */
diff --git a/include/trace/events/page_pool.h b/include/trace/events/page_pool.h
index ca534501158b..6834356b2d2a 100644
--- a/include/trace/events/page_pool.h
+++ b/include/trace/events/page_pool.h
@@ -9,7 +9,7 @@
 #include <linux/tracepoint.h>
 
 #include <trace/events/mmflags.h>
-#include <net/page_pool.h>
+#include <net/page_pool/types.h>
 
 TRACE_EVENT(page_pool_release,