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/1628217982-53533-1-git-send-email-linyunsheng@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

drivers/net/ethernet/hisilicon/Kconfig

@@ -91,6 +91,7 @@ config HNS3
 	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

@@ -3205,6 +3205,21 @@ static int hns3_alloc_buffer(struct hns3_enet_ring *ring,
 	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;
@@ -3227,8 +3242,13 @@ static void hns3_free_buffer(struct hns3_enet_ring *ring,
 	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));
 }
 
@@ -3315,7 +3335,7 @@ static int hns3_alloc_and_map_buffer(struct hns3_enet_ring *ring,
 	int ret;
 
 	ret = hns3_alloc_buffer(ring, cb);
-	if (ret)
+	if (ret || ring->page_pool)
 		goto out;
 
 	ret = hns3_map_buffer(ring, cb);
@@ -3337,7 +3357,8 @@ static int hns3_alloc_and_attach_buffer(struct hns3_enet_ring *ring, int i)
 	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;
 }
@@ -3367,7 +3388,8 @@ static void hns3_replace_buffer(struct hns3_enet_ring *ring, int i,
 {
 	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;
 }
 
@@ -3539,6 +3561,12 @@ static void hns3_nic_reuse_page(struct sk_buff *skb, int i,
 	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)))
 		goto out;
@@ -3856,13 +3884,20 @@ static int hns3_alloc_skb(struct hns3_enet_ring *ring, unsigned int length,
 		/* 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);
@@ -3901,6 +3936,10 @@ static int hns3_add_frag(struct hns3_enet_ring *ring)
 					    "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) {
@@ -4705,6 +4744,29 @@ static void hns3_put_ring_config(struct hns3_nic_priv *priv)
 	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;
@@ -4724,6 +4786,8 @@ static int hns3_alloc_ring_memory(struct hns3_enet_ring *ring)
 		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;
@@ -4764,6 +4828,11 @@ void hns3_fini_ring(struct hns3_enet_ring *ring)
 		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;
+	}
 }
 
 static int hns3_buf_size2type(u32 buf_size)

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

@@ -6,6 +6,7 @@
 
 #include <linux/dim.h>
 #include <linux/if_vlan.h>
+#include <net/page_pool.h>
 
 #include "hnae3.h"
 
@@ -307,6 +308,7 @@ enum hns3_desc_type {
 	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 {
@@ -451,6 +453,7 @@ struct hns3_enet_ring {
 	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

@@ -2327,7 +2327,7 @@ mvneta_swbm_build_skb(struct mvneta_port *pp, struct page_pool *pool,
 	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);
@@ -2339,10 +2339,6 @@ mvneta_swbm_build_skb(struct mvneta_port *pp, struct page_pool *pool,
 		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

@@ -3995,7 +3995,7 @@ static int mvpp2_rx(struct mvpp2_port *port, struct napi_struct *napi,
 		}
 
 		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

@@ -431,7 +431,7 @@ static void cpsw_rx_handler(void *token, int len, int status)
 	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

@@ -375,7 +375,7 @@ static void cpsw_rx_handler(void *token, int len, int status)
 	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

@@ -103,11 +103,19 @@ struct page {
 			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

@@ -4712,11 +4712,9 @@ static inline u64 skb_get_kcov_handle(struct sk_buff *skb)
 }
 
 #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

@@ -45,7 +45,10 @@
 					* 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
@@ -88,6 +91,9 @@ struct page_pool {
 	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
@@ -137,6 +143,18 @@ 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)
+{
+	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
  * avoid the extra cache line from page_pool to determine the direction
  */
@@ -198,19 +216,48 @@ static inline void page_pool_recycle_direct(struct page_pool *pool,
 	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)
@@ -253,11 +300,4 @@ static inline void page_pool_ring_unlock(struct page_pool *pool)
 		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 */