Merge branch 'hns3-next'

Guangbin Huang says:

====================
net: hns3: updates for -next

This series includes some optimization in IO path for the HNS3 ethernet
driver.
====================

Cc: Loic Poulain <loic.poulain@linaro.org>
Cc: Bjorn Andersson <bjorn.andersson@linaro.org>
Signed-off-by: Stephan Gerhold <stephan@gerhold.net>
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/hisilicon/hns3/hnae3.h

@@ -159,13 +159,6 @@ enum HNAE3_PF_CAP_BITS {
 #define ring_ptr_move_bw(ring, p) \
 	((ring)->p = ((ring)->p - 1 + (ring)->desc_num) % (ring)->desc_num)
 
-enum hns_desc_type {
-	DESC_TYPE_UNKNOWN,
-	DESC_TYPE_SKB,
-	DESC_TYPE_FRAGLIST_SKB,
-	DESC_TYPE_PAGE,
-};
-
 struct hnae3_handle;
 
 struct hnae3_queue {
@@ -767,6 +760,7 @@ struct hnae3_knic_private_info {
 	u16 rx_buf_len;
 	u16 num_tx_desc;
 	u16 num_rx_desc;
+	u32 tx_spare_buf_size;
 
 	struct hnae3_tc_info tc_info;
 

drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c

@@ -392,6 +392,56 @@ static void hns3_dbg_fill_content(char *content, u16 len,
 	*pos++ = '\0';
 }
 
+static const struct hns3_dbg_item tx_spare_info_items[] = {
+	{ "QUEUE_ID", 2 },
+	{ "COPYBREAK", 2 },
+	{ "LEN", 7 },
+	{ "NTU", 4 },
+	{ "NTC", 4 },
+	{ "LTC", 4 },
+	{ "DMA", 17 },
+};
+
+static void hns3_dbg_tx_spare_info(struct hns3_enet_ring *ring, char *buf,
+				   int len, u32 ring_num, int *pos)
+{
+	char data_str[ARRAY_SIZE(tx_spare_info_items)][HNS3_DBG_DATA_STR_LEN];
+	struct hns3_tx_spare *tx_spare = ring->tx_spare;
+	char *result[ARRAY_SIZE(tx_spare_info_items)];
+	char content[HNS3_DBG_INFO_LEN];
+	u32 i, j;
+
+	if (!tx_spare) {
+		*pos += scnprintf(buf + *pos, len - *pos,
+				  "tx spare buffer is not enabled\n");
+		return;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(tx_spare_info_items); i++)
+		result[i] = &data_str[i][0];
+
+	*pos += scnprintf(buf + *pos, len - *pos, "tx spare buffer info\n");
+	hns3_dbg_fill_content(content, sizeof(content), tx_spare_info_items,
+			      NULL, ARRAY_SIZE(tx_spare_info_items));
+	*pos += scnprintf(buf + *pos, len - *pos, "%s", content);
+
+	for (i = 0; i < ring_num; i++) {
+		j = 0;
+		sprintf(result[j++], "%8u", i);
+		sprintf(result[j++], "%9u", ring->tx_copybreak);
+		sprintf(result[j++], "%3u", tx_spare->len);
+		sprintf(result[j++], "%3u", tx_spare->next_to_use);
+		sprintf(result[j++], "%3u", tx_spare->next_to_clean);
+		sprintf(result[j++], "%3u", tx_spare->last_to_clean);
+		sprintf(result[j++], "%pad", &tx_spare->dma);
+		hns3_dbg_fill_content(content, sizeof(content),
+				      tx_spare_info_items,
+				      (const char **)result,
+				      ARRAY_SIZE(tx_spare_info_items));
+		*pos += scnprintf(buf + *pos, len - *pos, "%s", content);
+	}
+}
+
 static const struct hns3_dbg_item rx_queue_info_items[] = {
 	{ "QUEUE_ID", 2 },
 	{ "BD_NUM", 2 },
@@ -400,6 +450,7 @@ static const struct hns3_dbg_item rx_queue_info_items[] = {
 	{ "HEAD", 2 },
 	{ "FBDNUM", 2 },
 	{ "PKTNUM", 2 },
+	{ "COPYBREAK", 2 },
 	{ "RING_EN", 2 },
 	{ "RX_RING_EN", 2 },
 	{ "BASE_ADDR", 10 },
@@ -431,6 +482,7 @@ static void hns3_dump_rx_queue_info(struct hns3_enet_ring *ring,
 
 	sprintf(result[j++], "%6u", readl_relaxed(ring->tqp->io_base +
 		HNS3_RING_RX_RING_PKTNUM_RECORD_REG));
+	sprintf(result[j++], "%9u", ring->rx_copybreak);
 
 	sprintf(result[j++], "%7s", readl_relaxed(ring->tqp->io_base +
 		HNS3_RING_EN_REG) ? "on" : "off");
@@ -593,6 +645,8 @@ static int hns3_dbg_tx_queue_info(struct hnae3_handle *h,
 		pos += scnprintf(buf + pos, len - pos, "%s", content);
 	}
 
+	hns3_dbg_tx_spare_info(ring, buf, len, h->kinfo.num_tqps, &pos);
+
 	return 0;
 }
 

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

@@ -299,6 +299,16 @@ struct __packed hns3_desc {
 	};
 };
 
+enum hns3_desc_type {
+	DESC_TYPE_UNKNOWN		= 0,
+	DESC_TYPE_SKB			= 1 << 0,
+	DESC_TYPE_FRAGLIST_SKB		= 1 << 1,
+	DESC_TYPE_PAGE			= 1 << 2,
+	DESC_TYPE_BOUNCE_ALL		= 1 << 3,
+	DESC_TYPE_BOUNCE_HEAD		= 1 << 4,
+	DESC_TYPE_SGL_SKB		= 1 << 5,
+};
+
 struct hns3_desc_cb {
 	dma_addr_t dma; /* dma address of this desc */
 	void *buf;      /* cpu addr for a desc */
@@ -398,6 +408,12 @@ struct ring_stats {
 			u64 tx_tso_err;
 			u64 over_max_recursion;
 			u64 hw_limitation;
+			u64 tx_bounce;
+			u64 tx_spare_full;
+			u64 copy_bits_err;
+			u64 tx_sgl;
+			u64 skb2sgl_err;
+			u64 map_sg_err;
 		};
 		struct {
 			u64 rx_pkts;
@@ -411,11 +427,22 @@ struct ring_stats {
 			u64 csum_complete;
 			u64 rx_multicast;
 			u64 non_reuse_pg;
+			u64 frag_alloc_err;
+			u64 frag_alloc;
 		};
 		__le16 csum;
 	};
 };
 
+struct hns3_tx_spare {
+	dma_addr_t dma;
+	void *buf;
+	u32 next_to_use;
+	u32 next_to_clean;
+	u32 last_to_clean;
+	u32 len;
+};
+
 struct hns3_enet_ring {
 	struct hns3_desc *desc; /* dma map address space */
 	struct hns3_desc_cb *desc_cb;
@@ -438,18 +465,29 @@ struct hns3_enet_ring {
 	 * next_to_use
 	 */
 	int next_to_clean;
+	u32 flag;          /* ring attribute */
+
+	int pending_buf;
 	union {
+		/* for Tx ring */
+		struct {
+			u32 fd_qb_tx_sample;
 			int last_to_use;        /* last idx used by xmit */
-		u32 pull_len;		/* memcpy len for current rx packet */
+			u32 tx_copybreak;
+			struct hns3_tx_spare *tx_spare;
 		};
-	u32 frag_num;
-	void *va; /* first buffer address for current packet */
-
-	u32 flag;          /* ring attribute */
 
-	int pending_buf;
+		/* for Rx ring */
+		struct {
+			u32 pull_len;   /* memcpy len for current rx packet */
+			u32 rx_copybreak;
+			u32 frag_num;
+			/* first buffer address for current packet */
+			unsigned char *va;
 			struct sk_buff *skb;
 			struct sk_buff *tail_skb;
+		};
+	};
 } ____cacheline_internodealigned_in_smp;
 
 enum hns3_flow_level_range {
@@ -533,6 +571,8 @@ struct hns3_nic_priv {
 
 	struct hns3_enet_coalesce tx_coal;
 	struct hns3_enet_coalesce rx_coal;
+	u32 tx_copybreak;
+	u32 rx_copybreak;
 };
 
 union l3_hdr_info {

drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c

@@ -46,6 +46,12 @@ static const struct hns3_stats hns3_txq_stats[] = {
 	HNS3_TQP_STAT("tso_err", tx_tso_err),
 	HNS3_TQP_STAT("over_max_recursion", over_max_recursion),
 	HNS3_TQP_STAT("hw_limitation", hw_limitation),
+	HNS3_TQP_STAT("bounce", tx_bounce),
+	HNS3_TQP_STAT("spare_full", tx_spare_full),
+	HNS3_TQP_STAT("copy_bits_err", copy_bits_err),
+	HNS3_TQP_STAT("sgl", tx_sgl),
+	HNS3_TQP_STAT("skb2sgl_err", skb2sgl_err),
+	HNS3_TQP_STAT("map_sg_err", map_sg_err),
 };
 
 #define HNS3_TXQ_STATS_COUNT ARRAY_SIZE(hns3_txq_stats)
@@ -65,6 +71,8 @@ static const struct hns3_stats hns3_rxq_stats[] = {
 	HNS3_TQP_STAT("csum_complete", csum_complete),
 	HNS3_TQP_STAT("multicast", rx_multicast),
 	HNS3_TQP_STAT("non_reuse_pg", non_reuse_pg),
+	HNS3_TQP_STAT("frag_alloc_err", frag_alloc_err),
+	HNS3_TQP_STAT("frag_alloc", frag_alloc),
 };
 
 #define HNS3_PRIV_FLAGS_LEN ARRAY_SIZE(hns3_priv_flags)
@@ -1592,6 +1600,60 @@ static int hns3_set_priv_flags(struct net_device *netdev, u32 pflags)
 	return 0;
 }
 
+static int hns3_get_tunable(struct net_device *netdev,
+			    const struct ethtool_tunable *tuna,
+			    void *data)
+{
+	struct hns3_nic_priv *priv = netdev_priv(netdev);
+	int ret = 0;
+
+	switch (tuna->id) {
+	case ETHTOOL_TX_COPYBREAK:
+		/* all the tx rings have the same tx_copybreak */
+		*(u32 *)data = priv->tx_copybreak;
+		break;
+	case ETHTOOL_RX_COPYBREAK:
+		*(u32 *)data = priv->rx_copybreak;
+		break;
+	default:
+		ret = -EOPNOTSUPP;
+		break;
+	}
+
+	return ret;
+}
+
+static int hns3_set_tunable(struct net_device *netdev,
+			    const struct ethtool_tunable *tuna,
+			    const void *data)
+{
+	struct hns3_nic_priv *priv = netdev_priv(netdev);
+	struct hnae3_handle *h = priv->ae_handle;
+	int i, ret = 0;
+
+	switch (tuna->id) {
+	case ETHTOOL_TX_COPYBREAK:
+		priv->tx_copybreak = *(u32 *)data;
+
+		for (i = 0; i < h->kinfo.num_tqps; i++)
+			priv->ring[i].tx_copybreak = priv->tx_copybreak;
+
+		break;
+	case ETHTOOL_RX_COPYBREAK:
+		priv->rx_copybreak = *(u32 *)data;
+
+		for (i = h->kinfo.num_tqps; i < h->kinfo.num_tqps * 2; i++)
+			priv->ring[i].rx_copybreak = priv->rx_copybreak;
+
+		break;
+	default:
+		ret = -EOPNOTSUPP;
+		break;
+	}
+
+	return ret;
+}
+
 #define HNS3_ETHTOOL_COALESCE	(ETHTOOL_COALESCE_USECS |		\
 				 ETHTOOL_COALESCE_USE_ADAPTIVE |	\
 				 ETHTOOL_COALESCE_RX_USECS_HIGH |	\
@@ -1635,6 +1697,8 @@ static const struct ethtool_ops hns3vf_ethtool_ops = {
 	.set_msglevel = hns3_set_msglevel,
 	.get_priv_flags = hns3_get_priv_flags,
 	.set_priv_flags = hns3_set_priv_flags,
+	.get_tunable = hns3_get_tunable,
+	.set_tunable = hns3_set_tunable,
 };
 
 static const struct ethtool_ops hns3_ethtool_ops = {
@@ -1674,6 +1738,8 @@ static const struct ethtool_ops hns3_ethtool_ops = {
 	.get_priv_flags = hns3_get_priv_flags,
 	.set_priv_flags = hns3_set_priv_flags,
 	.get_ts_info = hns3_get_ts_info,
+	.get_tunable = hns3_get_tunable,
+	.set_tunable = hns3_set_tunable,
 };
 
 void hns3_ethtool_set_ops(struct net_device *netdev)

drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h

@@ -542,6 +542,8 @@ struct hclge_pf_res_cmd {
 #define HCLGE_CFG_UMV_TBL_SPACE_M	GENMASK(31, 16)
 #define HCLGE_CFG_PF_RSS_SIZE_S		0
 #define HCLGE_CFG_PF_RSS_SIZE_M		GENMASK(3, 0)
+#define HCLGE_CFG_TX_SPARE_BUF_SIZE_S	4
+#define HCLGE_CFG_TX_SPARE_BUF_SIZE_M	GENMASK(15, 4)
 
 #define HCLGE_CFG_CMD_CNT		4
 

drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c

@@ -1279,6 +1279,7 @@ static u32 hclge_get_max_speed(u16 speed_ability)
 
 static void hclge_parse_cfg(struct hclge_cfg *cfg, struct hclge_desc *desc)
 {
+#define HCLGE_TX_SPARE_SIZE_UNIT		4096
 #define SPEED_ABILITY_EXT_SHIFT			8
 
 	struct hclge_cfg_param_cmd *req;
@@ -1358,6 +1359,15 @@ static void hclge_parse_cfg(struct hclge_cfg *cfg, struct hclge_desc *desc)
 	cfg->pf_rss_size_max = cfg->pf_rss_size_max ?
 			       1U << cfg->pf_rss_size_max :
 			       cfg->vf_rss_size_max;
+
+	/* The unit of the tx spare buffer size queried from configuration
+	 * file is HCLGE_TX_SPARE_SIZE_UNIT(4096) bytes, so a conversion is
+	 * needed here.
+	 */
+	cfg->tx_spare_buf_size = hnae3_get_field(__le32_to_cpu(req->param[2]),
+						 HCLGE_CFG_TX_SPARE_BUF_SIZE_M,
+						 HCLGE_CFG_TX_SPARE_BUF_SIZE_S);
+	cfg->tx_spare_buf_size *= HCLGE_TX_SPARE_SIZE_UNIT;
 }
 
 /* hclge_get_cfg: query the static parameter from flash
@@ -1539,6 +1549,7 @@ static int hclge_configure(struct hclge_dev *hdev)
 	hdev->tc_max = cfg.tc_num;
 	hdev->tm_info.hw_pfc_map = 0;
 	hdev->wanted_umv_size = cfg.umv_space;
+	hdev->tx_spare_buf_size = cfg.tx_spare_buf_size;
 	if (cfg.vlan_fliter_cap == HCLGE_VLAN_FLTR_CAN_MDF)
 		set_bit(HNAE3_DEV_SUPPORT_VLAN_FLTR_MDF_B, ae_dev->caps);
 
@@ -1736,6 +1747,7 @@ static int hclge_knic_setup(struct hclge_vport *vport, u16 num_tqps,
 	kinfo->num_rx_desc = num_rx_desc;
 
 	kinfo->rx_buf_len = hdev->rx_buf_len;
+	kinfo->tx_spare_buf_size = hdev->tx_spare_buf_size;
 
 	kinfo->tqp = devm_kcalloc(&hdev->pdev->dev, num_tqps,
 				  sizeof(struct hnae3_queue *), GFP_KERNEL);
@@ -11059,6 +11071,8 @@ static void hclge_info_show(struct hclge_dev *hdev)
 		 hdev->flag & HCLGE_FLAG_DCB_ENABLE ? "enable" : "disable");
 	dev_info(dev, "MQPRIO %s\n",
 		 hdev->flag & HCLGE_FLAG_MQPRIO_ENABLE ? "enable" : "disable");
+	dev_info(dev, "Default tx spare buffer size: %u\n",
+		 hdev->tx_spare_buf_size);
 
 	dev_info(dev, "PF info end.\n");
 }

drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h

@@ -384,6 +384,7 @@ struct hclge_cfg {
 	u8 mac_addr[ETH_ALEN];
 	u8 default_speed;
 	u32 numa_node_map;
+	u32 tx_spare_buf_size;
 	u16 speed_ability;
 	u16 umv_space;
 };
@@ -848,6 +849,7 @@ struct hclge_dev {
 	u16 alloc_rss_size;		/* Allocated RSS task queue */
 	u16 vf_rss_size_max;		/* HW defined VF max RSS task queue */
 	u16 pf_rss_size_max;		/* HW defined PF max RSS task queue */
+	u32 tx_spare_buf_size;		/* HW defined TX spare buffer size */
 
 	u16 fdir_pf_filter_count; /* Num of guaranteed filters for this PF */
 	u16 num_alloc_vport;		/* Num vports this driver supports */