Merge branch 'add-frag-page-support-in-page-pool'

Yunsheng Lin says:

====================
add frag page support in page pool

This patchset adds frag page support in page pool and
enable skb's page frag recycling based on page pool in
hns3 drvier.
====================

Link: https://lore.kernel.org/r/[e-mail]
Signed-off-by: Jakub Kicinski <[e-mail]>

drivers/net/ethernet/hisilicon/Kconfig

···
 	tristate "Hisilicon Network Subsystem Support HNS3 (Framework)"
 	depends on PCI
 	select NET_DEVLINK
+	select PAGE_POOL
 	help
 	  This selects the framework support for Hisilicon Network Subsystem 3.
 	  This layer facilitates clients like ENET, RoCE and user-space ethernet

drivers/net/ethernet/hisilicon/hns3/hns3_enet.c

···
 	unsigned int order = hns3_page_order(ring);
 	struct page *p;
 
+	if (ring->page_pool) {
+		p = page_pool_dev_alloc_frag(ring->page_pool,
+					     &cb->page_offset,
+					     hns3_buf_size(ring));
+		if (unlikely(!p))
+			return -ENOMEM;
+
+		cb->priv = p;
+		cb->buf = page_address(p);
+		cb->dma = page_pool_get_dma_addr(p);
+		cb->type = DESC_TYPE_PP_FRAG;
+		cb->reuse_flag = 0;
+		return 0;
+	}
+
 	p = dev_alloc_pages(order);
 	if (!p)
 		return -ENOMEM;
···
 	if (cb->type & (DESC_TYPE_SKB | DESC_TYPE_BOUNCE_HEAD |
 			DESC_TYPE_BOUNCE_ALL | DESC_TYPE_SGL_SKB))
 		napi_consume_skb(cb->priv, budget);
-	else if (!HNAE3_IS_TX_RING(ring) && cb->pagecnt_bias)
-		__page_frag_cache_drain(cb->priv, cb->pagecnt_bias);
+	else if (!HNAE3_IS_TX_RING(ring)) {
+		if (cb->type & DESC_TYPE_PAGE && cb->pagecnt_bias)
+			__page_frag_cache_drain(cb->priv, cb->pagecnt_bias);
+		else if (cb->type & DESC_TYPE_PP_FRAG)
+			page_pool_put_full_page(ring->page_pool, cb->priv,
+						false);
+	}
 	memset(cb, 0, sizeof(*cb));
 }
 
···
 	int ret;
 
 	ret = hns3_alloc_buffer(ring, cb);
-	if (ret)
+	if (ret || ring->page_pool)
 		goto out;
 
 	ret = hns3_map_buffer(ring, cb);
···
 	if (ret)
 		return ret;
 
-	ring->desc[i].addr = cpu_to_le64(ring->desc_cb[i].dma);
+	ring->desc[i].addr = cpu_to_le64(ring->desc_cb[i].dma +
+					 ring->desc_cb[i].page_offset);
 
 	return 0;
 }
···
 {
 	hns3_unmap_buffer(ring, &ring->desc_cb[i]);
 	ring->desc_cb[i] = *res_cb;
-	ring->desc[i].addr = cpu_to_le64(ring->desc_cb[i].dma);
+	ring->desc[i].addr = cpu_to_le64(ring->desc_cb[i].dma +
+					 ring->desc_cb[i].page_offset);
 	ring->desc[i].rx.bd_base_info = 0;
 }
 
···
 	u32 truesize = hns3_buf_size(ring);
 	u32 frag_size = size - pull_len;
 	bool reused;
+
+	if (ring->page_pool) {
+		skb_add_rx_frag(skb, i, desc_cb->priv, frag_offset,
+				frag_size, truesize);
+		return;
+	}
 
 	/* Avoid re-using remote or pfmem page */
 	if (unlikely(!dev_page_is_reusable(desc_cb->priv)))
···
 		/* We can reuse buffer as-is, just make sure it is reusable */
 		if (dev_page_is_reusable(desc_cb->priv))
 			desc_cb->reuse_flag = 1;
+		else if (desc_cb->type & DESC_TYPE_PP_FRAG)
+			page_pool_put_full_page(ring->page_pool, desc_cb->priv,
+						false);
 		else /* This page cannot be reused so discard it */
 			__page_frag_cache_drain(desc_cb->priv,
 						desc_cb->pagecnt_bias);
···
 		hns3_rx_ring_move_fw(ring);
 		return 0;
 	}
+
+	if (ring->page_pool)
+		skb_mark_for_recycle(skb);
+
 	u64_stats_update_begin(&ring->syncp);
 	ring->stats.seg_pkt_cnt++;
 	u64_stats_update_end(&ring->syncp);
···
 					    "alloc rx fraglist skb fail\n");
 				return -ENXIO;
 			}
+
+			if (ring->page_pool)
+				skb_mark_for_recycle(new_skb);
+
 			ring->frag_num = 0;
 
 			if (ring->tail_skb) {
···
 	priv->ring = NULL;
 }
 
+static void hns3_alloc_page_pool(struct hns3_enet_ring *ring)
+{
+	struct page_pool_params pp_params = {
+		.flags = PP_FLAG_DMA_MAP | PP_FLAG_PAGE_FRAG |
+				PP_FLAG_DMA_SYNC_DEV,
+		.order = hns3_page_order(ring),
+		.pool_size = ring->desc_num * hns3_buf_size(ring) /
+				(PAGE_SIZE << hns3_page_order(ring)),
+		.nid = dev_to_node(ring_to_dev(ring)),
+		.dev = ring_to_dev(ring),
+		.dma_dir = DMA_FROM_DEVICE,
+		.offset = 0,
+		.max_len = PAGE_SIZE << hns3_page_order(ring),
+	};
+
+	ring->page_pool = page_pool_create(&pp_params);
+	if (IS_ERR(ring->page_pool)) {
+		dev_warn(ring_to_dev(ring), "page pool creation failed: %ld\n",
+			 PTR_ERR(ring->page_pool));
+		ring->page_pool = NULL;
+	}
+}
+
 static int hns3_alloc_ring_memory(struct hns3_enet_ring *ring)
 {
 	int ret;
···
 		goto out_with_desc_cb;
 
 	if (!HNAE3_IS_TX_RING(ring)) {
+		hns3_alloc_page_pool(ring);
+
 		ret = hns3_alloc_ring_buffers(ring);
 		if (ret)
 			goto out_with_desc;
···
 			   get_order(tx_spare->len));
 		devm_kfree(ring_to_dev(ring), tx_spare);
 		ring->tx_spare = NULL;
+	}
+
+	if (!HNAE3_IS_TX_RING(ring) && ring->page_pool) {
+		page_pool_destroy(ring->page_pool);
+		ring->page_pool = NULL;
 	}
 }
 

drivers/net/ethernet/hisilicon/hns3/hns3_enet.h

···
 
 #include <linux/dim.h>
 #include <linux/if_vlan.h>
+#include <net/page_pool.h>
 
 #include "hnae3.h"
 
···
 	DESC_TYPE_BOUNCE_ALL		= 1 << 3,
 	DESC_TYPE_BOUNCE_HEAD		= 1 << 4,
 	DESC_TYPE_SGL_SKB		= 1 << 5,
+	DESC_TYPE_PP_FRAG		= 1 << 6,
 };
 
 struct hns3_desc_cb {
···
 	struct hnae3_queue *tqp;
 	int queue_index;
 	struct device *dev; /* will be used for DMA mapping of descriptors */
+	struct page_pool *page_pool;
 
 	/* statistic */
 	struct ring_stats stats;

drivers/net/ethernet/marvell/mvneta.c

···
 	if (!skb)
 		return ERR_PTR(-ENOMEM);
 
-	skb_mark_for_recycle(skb, virt_to_page(xdp->data), pool);
+	skb_mark_for_recycle(skb);
 
 	skb_reserve(skb, xdp->data - xdp->data_hard_start);
 	skb_put(skb, xdp->data_end - xdp->data);
···
 		skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
 				skb_frag_page(frag), skb_frag_off(frag),
 				skb_frag_size(frag), PAGE_SIZE);
-		/* We don't need to reset pp_recycle here. It's already set, so
-		 * just mark fragments for recycling.
-		 */
-		page_pool_store_mem_info(skb_frag_page(frag), pool);
 	}
 
 	return skb;

drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c

···
 		}
 
 		if (pp)
-			skb_mark_for_recycle(skb, page, pp);
+			skb_mark_for_recycle(skb);
 		else
 			dma_unmap_single_attrs(dev->dev.parent, dma_addr,
 					       bm_pool->buf_size, DMA_FROM_DEVICE,

drivers/net/ethernet/ti/cpsw.c

···
 	skb->protocol = eth_type_trans(skb, ndev);
 
 	/* mark skb for recycling */
-	skb_mark_for_recycle(skb, page, pool);
+	skb_mark_for_recycle(skb);
 	netif_receive_skb(skb);
 
 	ndev->stats.rx_bytes += len;

drivers/net/ethernet/ti/cpsw_new.c

···
 	skb->protocol = eth_type_trans(skb, ndev);
 
 	/* mark skb for recycling */
-	skb_mark_for_recycle(skb, page, pool);
+	skb_mark_for_recycle(skb);
 	netif_receive_skb(skb);
 
 	ndev->stats.rx_bytes += len;

include/linux/mm_types.h

···
 			unsigned long pp_magic;
 			struct page_pool *pp;
 			unsigned long _pp_mapping_pad;
-			/**
-			 * @dma_addr: might require a 64-bit value on
-			 * 32-bit architectures.
-			 */
-			unsigned long dma_addr[2];
+			unsigned long dma_addr;
+			union {
+				/**
+				 * dma_addr_upper: might require a 64-bit
+				 * value on 32-bit architectures.
+				 */
+				unsigned long dma_addr_upper;
+				/**
+				 * For frag page support, not supported in
+				 * 32-bit architectures with 64-bit DMA.
+				 */
+				atomic_long_t pp_frag_count;
+			};
 		};
 		struct {	/* slab, slob and slub */
 			union {

include/linux/skbuff.h

···
 }
 
 #ifdef CONFIG_PAGE_POOL
-static inline void skb_mark_for_recycle(struct sk_buff *skb, struct page *page,
-					struct page_pool *pp)
+static inline void skb_mark_for_recycle(struct sk_buff *skb)
 {
 	skb->pp_recycle = 1;
-	page_pool_store_mem_info(page, pp);
 }
 #endif
 

include/net/page_pool.h

···
 					* Please note DMA-sync-for-CPU is still
 					* device driver responsibility
 					*/
-#define PP_FLAG_ALL		(PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV)
+#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
···
 	unsigned long defer_warn;
 
 	u32 pages_state_hold_cnt;
+	unsigned int frag_offset;
+	struct page *frag_page;
+	long frag_users;
 
 	/*
 	 * Data structure for allocation side
···
 	gfp_t gfp = (GFP_ATOMIC | __GFP_NOWARN);
 
 	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)
+{
+	gfp_t gfp = (GFP_ATOMIC | __GFP_NOWARN);
+
+	return page_pool_alloc_frag(pool, offset, size, gfp);
 }
 
 /* get the stored dma direction. A driver might decide to treat this locally and
···
 	page_pool_put_full_page(pool, page, true);
 }
 
+#define PAGE_POOL_DMA_USE_PP_FRAG_COUNT	\
+		(sizeof(dma_addr_t) > sizeof(unsigned long))
+
 static inline dma_addr_t page_pool_get_dma_addr(struct page *page)
 {
-	dma_addr_t ret = page->dma_addr[0];
-	if (sizeof(dma_addr_t) > sizeof(unsigned long))
-		ret |= (dma_addr_t)page->dma_addr[1] << 16 << 16;
+	dma_addr_t ret = page->dma_addr;
+
+	if (PAGE_POOL_DMA_USE_PP_FRAG_COUNT)
+		ret |= (dma_addr_t)page->dma_addr_upper << 16 << 16;
+
 	return ret;
 }
 
 static inline void page_pool_set_dma_addr(struct page *page, dma_addr_t addr)
 {
-	page->dma_addr[0] = addr;
-	if (sizeof(dma_addr_t) > sizeof(unsigned long))
-		page->dma_addr[1] = upper_32_bits(addr);
+	page->dma_addr = addr;
+	if (PAGE_POOL_DMA_USE_PP_FRAG_COUNT)
+		page->dma_addr_upper = upper_32_bits(addr);
+}
+
+static inline void page_pool_set_frag_count(struct page *page, long nr)
+{
+	atomic_long_set(&page->pp_frag_count, nr);
+}
+
+static inline long page_pool_atomic_sub_frag_count_return(struct page *page,
+							  long nr)
+{
+	long ret;
+
+	/* As suggested by Alexander, atomic_long_read() may cover up the
+	 * reference count errors, so avoid calling atomic_long_read() in
+	 * the cases of freeing or draining the page_frags, where we would
+	 * not expect it to match or that are slowpath anyway.
+	 */
+	if (__builtin_constant_p(nr) &&
+	    atomic_long_read(&page->pp_frag_count) == nr)
+		return 0;
+
+	ret = atomic_long_sub_return(nr, &page->pp_frag_count);
+	WARN_ON(ret < 0);
+	return ret;
 }
 
 static inline bool is_page_pool_compiled_in(void)
···
 		spin_unlock(&pool->ring.producer_lock);
 	else
 		spin_unlock_bh(&pool->ring.producer_lock);
-}
-
-/* Store mem_info on struct page and use it while recycling skb frags */
-static inline
-void page_pool_store_mem_info(struct page *page, struct page_pool *pp)
-{
-	page->pp = pp;
 }
 
 #endif /* _NET_PAGE_POOL_H */

net/core/page_pool.c

···
 #define DEFER_TIME (msecs_to_jiffies(1000))
 #define DEFER_WARN_INTERVAL (60 * HZ)
 
+#define BIAS_MAX	LONG_MAX
+
 static int page_pool_init(struct page_pool *pool,
 			  const struct page_pool_params *params)
 {
···
 		 * offset used by the DMA engine to start copying rx data
 		 */
 	}
+
+	if (PAGE_POOL_DMA_USE_PP_FRAG_COUNT &&
+	    pool->p.flags & PP_FLAG_PAGE_FRAG)
+		return -EINVAL;
 
 	if (ptr_ring_init(&pool->ring, ring_qsize, GFP_KERNEL) < 0)
 		return -ENOMEM;
···
 	return true;
 }
 
+static void page_pool_set_pp_info(struct page_pool *pool,
+				  struct page *page)
+{
+	page->pp = pool;
+	page->pp_magic |= PP_SIGNATURE;
+}
+
+static void page_pool_clear_pp_info(struct page *page)
+{
+	page->pp_magic = 0;
+	page->pp = NULL;
+}
+
 static struct page *__page_pool_alloc_page_order(struct page_pool *pool,
 						 gfp_t gfp)
 {
···
 		return NULL;
 	}
 
-	page->pp_magic |= PP_SIGNATURE;
+	page_pool_set_pp_info(pool, page);
 
 	/* Track how many pages are held 'in-flight' */
 	pool->pages_state_hold_cnt++;
···
 			put_page(page);
 			continue;
 		}
-		page->pp_magic |= PP_SIGNATURE;
+
+		page_pool_set_pp_info(pool, page);
 		pool->alloc.cache[pool->alloc.count++] = page;
 		/* Track how many pages are held 'in-flight' */
 		pool->pages_state_hold_cnt++;
···
 			     DMA_ATTR_SKIP_CPU_SYNC);
 	page_pool_set_dma_addr(page, 0);
 skip_dma_unmap:
-	page->pp_magic = 0;
+	page_pool_clear_pp_info(page);
 
 	/* This may be the last page returned, releasing the pool, so
 	 * it is not safe to reference pool afterwards.
···
 __page_pool_put_page(struct page_pool *pool, struct page *page,
 		     unsigned int dma_sync_size, bool allow_direct)
 {
+	/* It is not the last user for the page frag case */
+	if (pool->p.flags & PP_FLAG_PAGE_FRAG &&
+	    page_pool_atomic_sub_frag_count_return(page, 1))
+		return NULL;
+
 	/* This allocator is optimized for the XDP mode that uses
 	 * one-frame-per-page, but have fallbacks that act like the
 	 * regular page allocator APIs.
···
 		page_pool_return_page(pool, data[i]);
 }
 EXPORT_SYMBOL(page_pool_put_page_bulk);
+
+static struct page *page_pool_drain_frag(struct page_pool *pool,
+					 struct page *page)
+{
+	long drain_count = BIAS_MAX - pool->frag_users;
+
+	/* Some user is still using the page frag */
+	if (likely(page_pool_atomic_sub_frag_count_return(page,
+							  drain_count)))
+		return NULL;
+
+	if (page_ref_count(page) == 1 && !page_is_pfmemalloc(page)) {
+		if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV)
+			page_pool_dma_sync_for_device(pool, page, -1);
+
+		return page;
+	}
+
+	page_pool_return_page(pool, page);
+	return NULL;
+}
+
+static void page_pool_free_frag(struct page_pool *pool)
+{
+	long drain_count = BIAS_MAX - pool->frag_users;
+	struct page *page = pool->frag_page;
+
+	pool->frag_page = NULL;
+
+	if (!page ||
+	    page_pool_atomic_sub_frag_count_return(page, drain_count))
+		return;
+
+	page_pool_return_page(pool, page);
+}
+
+struct page *page_pool_alloc_frag(struct page_pool *pool,
+				  unsigned int *offset,
+				  unsigned int size, gfp_t gfp)
+{
+	unsigned int max_size = PAGE_SIZE << pool->p.order;
+	struct page *page = pool->frag_page;
+
+	if (WARN_ON(!(pool->p.flags & PP_FLAG_PAGE_FRAG) ||
+		    size > max_size))
+		return NULL;
+
+	size = ALIGN(size, dma_get_cache_alignment());
+	*offset = pool->frag_offset;
+
+	if (page && *offset + size > max_size) {
+		page = page_pool_drain_frag(pool, page);
+		if (page)
+			goto frag_reset;
+	}
+
+	if (!page) {
+		page = page_pool_alloc_pages(pool, gfp);
+		if (unlikely(!page)) {
+			pool->frag_page = NULL;
+			return NULL;
+		}
+
+		pool->frag_page = page;
+
+frag_reset:
+		pool->frag_users = 1;
+		*offset = 0;
+		pool->frag_offset = size;
+		page_pool_set_frag_count(page, BIAS_MAX);
+		return page;
+	}
+
+	pool->frag_users++;
+	pool->frag_offset = *offset + size;
+	return page;
+}
+EXPORT_SYMBOL(page_pool_alloc_frag);
 
 static void page_pool_empty_ring(struct page_pool *pool)
 {
···
 	if (!page_pool_put(pool))
 		return;
 
+	page_pool_free_frag(pool);
+
 	if (!page_pool_release(pool))
 		return;
 
···
 	 * The page will be returned to the pool here regardless of the
 	 * 'flipped' fragment being in use or not.
 	 */
-	page->pp = NULL;
 	page_pool_put_full_page(pp, page, false);
 
 	return true;