From 9e6717af61dfe6de304562602364a19d70c886d4 Mon Sep 17 00:00:00 2001
From: Zhongzhu Liu <liuzhongzhu@huawei.com>
Date: Fri, 9 Aug 2019 10:31:07 +0800
Subject: [PATCH 01/12] net: hns3: fix GFP flag error in
 hclge_mac_update_stats()

When CONFIG_DEBUG_ATOMIC_SLEEP on, calling kzalloc with
GFP_KERNEL in hclge_mac_update_stats() will get below warning:

[   52.514677] BUG: sleeping function called from invalid context at mm/slab.h:501
[   52.522051] in_atomic(): 0, irqs_disabled(): 0, pid: 1015, name: ifconfig
[   52.528827] 2 locks held by ifconfig/1015:
[   52.532921]  #0: (____ptrval____) (&p->lock){....}, at: seq_read+0x54/0x748
[   52.539878]  #1: (____ptrval____) (rcu_read_lock){....}, at: dev_seq_start+0x0/0x140
[   52.547610] CPU: 16 PID: 1015 Comm: ifconfig Not tainted 5.3.0-rc3-00697-g20b80be #98
[   52.555408] Hardware name: Huawei TaiShan 2280 V2/BC82AMDC, BIOS 2280-V2 CS V3.B050.01 08/08/2019
[   52.564242] Call trace:
[   52.566687]  dump_backtrace+0x0/0x1f8
[   52.570338]  show_stack+0x14/0x20
[   52.573646]  dump_stack+0xb4/0xec
[   52.576950]  ___might_sleep+0x178/0x198
[   52.580773]  __might_sleep+0x74/0xe0
[   52.584338]  __kmalloc+0x244/0x2d8
[   52.587744]  hclge_mac_update_stats+0xc8/0x1f8 [hclge]
[   52.592870]  hclge_update_stats+0xe0/0x170 [hclge]
[   52.597651]  hns3_nic_get_stats64+0xa0/0x458 [hns3]
[   52.602514]  dev_get_stats+0x58/0x138
[   52.606165]  dev_seq_printf_stats+0x8c/0x280
[   52.610420]  dev_seq_show+0x14/0x40
[   52.613898]  seq_read+0x574/0x748
[   52.617205]  proc_reg_read+0xb4/0x108
[   52.620857]  __vfs_read+0x54/0xa8
[   52.624162]  vfs_read+0xa0/0x190
[   52.627380]  ksys_read+0xc8/0x178
[   52.630685]  __arm64_sys_read+0x40/0x50
[   52.634509]  el0_svc_common.constprop.0+0x120/0x1e0
[   52.639369]  el0_svc_handler+0x50/0x90
[   52.643106]  el0_svc+0x8/0xc

So this patch uses GFP_ATOMIC instead of GFP_KERNEL to fix it.

Fixes: d174ea75c96a ("net: hns3: add statistics for PFC frames and MAC control frames")
Signed-off-by: Zhongzhu Liu <liuzhongzhu@huawei.com>
Reviewed-by: Yunsheng Lin <linyunsheng@huawei.com>
Reviewed-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index b7399f5ba2c3..c0feae3a9f86 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -364,9 +364,13 @@ static int hclge_mac_update_stats_complete(struct hclge_dev *hdev, u32 desc_num)
 	u16 i, k, n;
 	int ret;
 
-	desc = kcalloc(desc_num, sizeof(struct hclge_desc), GFP_KERNEL);
+	/* This may be called inside atomic sections,
+	 * so GFP_ATOMIC is more suitalbe here
+	 */
+	desc = kcalloc(desc_num, sizeof(struct hclge_desc), GFP_ATOMIC);
 	if (!desc)
 		return -ENOMEM;
+
 	hclge_cmd_setup_basic_desc(&desc[0], HCLGE_OPC_STATS_MAC_ALL, true);
 	ret = hclge_cmd_send(&hdev->hw, desc, desc_num);
 	if (ret) {

From 130509213baeb3cada40c19dd87341a6787f8b23 Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Fri, 9 Aug 2019 10:31:08 +0800
Subject: [PATCH 02/12] net: hns3: fix interrupt clearing error for VF

Currently, VF driver has two kinds of interrupts, reset & CMDQ RX.
For revision 0x21, according to the UM, each interrupt should be
cleared by write 0 to the corresponding bit, but the implementation
writes 0 to the whole register in fact, it will clear other
interrupt at the same time, then the VF will loss the interrupt.
But for revision 0x20, this interrupt clear register is a read &
write register, for compatible, we just keep the old implementation
for 0x20.

This patch fixes it, also, adds a new register for reading the interrupt
status according to hardware user manual.

Fixes: e2cb1dec9779 ("net: hns3: Add HNS3 VF HCL(Hardware Compatibility Layer) Support")
Fixes: b90fcc5bd904 ("net: hns3: add reset handling for VF when doing Core/Global/IMP reset")

Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Reviewed-by: Yunsheng Lin <linyunsheng@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../hisilicon/hns3/hns3vf/hclgevf_main.c      | 28 +++++++++++++------
 .../hisilicon/hns3/hns3vf/hclgevf_main.h      |  2 ++
 2 files changed, 21 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index ce82b2b0f8f5..d8b828180aa8 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -1889,21 +1889,20 @@ static void hclgevf_clear_event_cause(struct hclgevf_dev *hdev, u32 regclr)
 static enum hclgevf_evt_cause hclgevf_check_evt_cause(struct hclgevf_dev *hdev,
 						      u32 *clearval)
 {
-	u32 val, cmdq_src_reg, rst_ing_reg;
+	u32 val, cmdq_stat_reg, rst_ing_reg;
 
 	/* fetch the events from their corresponding regs */
-	cmdq_src_reg = hclgevf_read_dev(&hdev->hw,
-					HCLGEVF_VECTOR0_CMDQ_SRC_REG);
+	cmdq_stat_reg = hclgevf_read_dev(&hdev->hw,
+					 HCLGEVF_VECTOR0_CMDQ_STAT_REG);
 
-	if (BIT(HCLGEVF_VECTOR0_RST_INT_B) & cmdq_src_reg) {
+	if (BIT(HCLGEVF_VECTOR0_RST_INT_B) & cmdq_stat_reg) {
 		rst_ing_reg = hclgevf_read_dev(&hdev->hw, HCLGEVF_RST_ING);
 		dev_info(&hdev->pdev->dev,
 			 "receive reset interrupt 0x%x!\n", rst_ing_reg);
 		set_bit(HNAE3_VF_RESET, &hdev->reset_pending);
 		set_bit(HCLGEVF_RESET_PENDING, &hdev->reset_state);
 		set_bit(HCLGEVF_STATE_CMD_DISABLE, &hdev->state);
-		cmdq_src_reg &= ~BIT(HCLGEVF_VECTOR0_RST_INT_B);
-		*clearval = cmdq_src_reg;
+		*clearval = ~(1U << HCLGEVF_VECTOR0_RST_INT_B);
 		hdev->rst_stats.vf_rst_cnt++;
 		/* set up VF hardware reset status, its PF will clear
 		 * this status when PF has initialized done.
@@ -1915,9 +1914,20 @@ static enum hclgevf_evt_cause hclgevf_check_evt_cause(struct hclgevf_dev *hdev,
 	}
 
 	/* check for vector0 mailbox(=CMDQ RX) event source */
-	if (BIT(HCLGEVF_VECTOR0_RX_CMDQ_INT_B) & cmdq_src_reg) {
-		cmdq_src_reg &= ~BIT(HCLGEVF_VECTOR0_RX_CMDQ_INT_B);
-		*clearval = cmdq_src_reg;
+	if (BIT(HCLGEVF_VECTOR0_RX_CMDQ_INT_B) & cmdq_stat_reg) {
+		/* for revision 0x21, clearing interrupt is writing bit 0
+		 * to the clear register, writing bit 1 means to keep the
+		 * old value.
+		 * for revision 0x20, the clear register is a read & write
+		 * register, so we should just write 0 to the bit we are
+		 * handling, and keep other bits as cmdq_stat_reg.
+		 */
+		if (hdev->pdev->revision >= 0x21)
+			*clearval = ~(1U << HCLGEVF_VECTOR0_RX_CMDQ_INT_B);
+		else
+			*clearval = cmdq_stat_reg &
+				    ~BIT(HCLGEVF_VECTOR0_RX_CMDQ_INT_B);
+
 		return HCLGEVF_VECTOR0_EVENT_MBX;
 	}
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
index f0736b060884..4ccf107079eb 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
@@ -87,6 +87,8 @@
 
 /* Vector0 interrupt CMDQ event source register(RW) */
 #define HCLGEVF_VECTOR0_CMDQ_SRC_REG	0x27100
+/* Vector0 interrupt CMDQ event status register(RO) */
+#define HCLGEVF_VECTOR0_CMDQ_STAT_REG	0x27104
 /* CMDQ register bits for RX event(=MBX event) */
 #define HCLGEVF_VECTOR0_RX_CMDQ_INT_B	1
 /* RST register bits for RESET event */

From eb977d996e9316c66e4d9908fd12d682e4db14e9 Mon Sep 17 00:00:00 2001
From: Yunsheng Lin <linyunsheng@huawei.com>
Date: Fri, 9 Aug 2019 10:31:09 +0800
Subject: [PATCH 03/12] net: hns3: clean up for vlan handling in
 hns3_fill_desc_vtags

This patch refactors the hns3_fill_desc_vtags function
by avoiding passing too many parameters, reducing indent
level and some other clean up.

This patch also adds the hns3_fill_skb_desc function to
fill the first desc of a skb.

Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Reviewed-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/hisilicon/hns3/hns3_enet.c   | 167 ++++++++++--------
 1 file changed, 89 insertions(+), 78 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index ed05fb9f04ed..fd6a3d589f40 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -45,6 +45,9 @@ MODULE_PARM_DESC(debug, " Network interface message level setting");
 #define DEFAULT_MSG_LEVEL (NETIF_MSG_PROBE | NETIF_MSG_LINK | \
 			   NETIF_MSG_IFDOWN | NETIF_MSG_IFUP)
 
+#define HNS3_INNER_VLAN_TAG	1
+#define HNS3_OUTER_VLAN_TAG	2
+
 /* hns3_pci_tbl - PCI Device ID Table
  *
  * Last entry must be all 0s
@@ -961,16 +964,16 @@ static void hns3_set_txbd_baseinfo(u16 *bdtp_fe_sc_vld_ra_ri, int frag_end)
 	hns3_set_field(*bdtp_fe_sc_vld_ra_ri, HNS3_TXD_VLD_B, 1U);
 }
 
-static int hns3_fill_desc_vtags(struct sk_buff *skb,
-				struct hns3_enet_ring *tx_ring,
-				u32 *inner_vlan_flag,
-				u32 *out_vlan_flag,
-				u16 *inner_vtag,
-				u16 *out_vtag)
+static int hns3_handle_vtags(struct hns3_enet_ring *tx_ring,
+			     struct sk_buff *skb)
 {
-#define HNS3_TX_VLAN_PRIO_SHIFT 13
-
 	struct hnae3_handle *handle = tx_ring->tqp->handle;
+	struct vlan_ethhdr *vhdr;
+	int rc;
+
+	if (!(skb->protocol == htons(ETH_P_8021Q) ||
+	      skb_vlan_tag_present(skb)))
+		return 0;
 
 	/* Since HW limitation, if port based insert VLAN enabled, only one VLAN
 	 * header is allowed in skb, otherwise it will cause RAS error.
@@ -981,8 +984,7 @@ static int hns3_fill_desc_vtags(struct sk_buff *skb,
 		return -EINVAL;
 
 	if (skb->protocol == htons(ETH_P_8021Q) &&
-	    !(tx_ring->tqp->handle->kinfo.netdev->features &
-	    NETIF_F_HW_VLAN_CTAG_TX)) {
+	    !(handle->kinfo.netdev->features & NETIF_F_HW_VLAN_CTAG_TX)) {
 		/* When HW VLAN acceleration is turned off, and the stack
 		 * sets the protocol to 802.1q, the driver just need to
 		 * set the protocol to the encapsulated ethertype.
@@ -992,45 +994,92 @@ static int hns3_fill_desc_vtags(struct sk_buff *skb,
 	}
 
 	if (skb_vlan_tag_present(skb)) {
-		u16 vlan_tag;
-
-		vlan_tag = skb_vlan_tag_get(skb);
-		vlan_tag |= (skb->priority & 0x7) << HNS3_TX_VLAN_PRIO_SHIFT;
-
 		/* Based on hw strategy, use out_vtag in two layer tag case,
 		 * and use inner_vtag in one tag case.
 		 */
-		if (skb->protocol == htons(ETH_P_8021Q)) {
-			if (handle->port_base_vlan_state ==
-			    HNAE3_PORT_BASE_VLAN_DISABLE){
-				hns3_set_field(*out_vlan_flag,
-					       HNS3_TXD_OVLAN_B, 1);
-				*out_vtag = vlan_tag;
-			} else {
-				hns3_set_field(*inner_vlan_flag,
-					       HNS3_TXD_VLAN_B, 1);
-				*inner_vtag = vlan_tag;
-			}
-		} else {
-			hns3_set_field(*inner_vlan_flag, HNS3_TXD_VLAN_B, 1);
-			*inner_vtag = vlan_tag;
-		}
-	} else if (skb->protocol == htons(ETH_P_8021Q)) {
-		struct vlan_ethhdr *vhdr;
-		int rc;
+		if (skb->protocol == htons(ETH_P_8021Q) &&
+		    handle->port_base_vlan_state ==
+		    HNAE3_PORT_BASE_VLAN_DISABLE)
+			rc = HNS3_OUTER_VLAN_TAG;
+		else
+			rc = HNS3_INNER_VLAN_TAG;
 
-		rc = skb_cow_head(skb, 0);
-		if (unlikely(rc < 0))
-			return rc;
-		vhdr = (struct vlan_ethhdr *)skb->data;
-		vhdr->h_vlan_TCI |= cpu_to_be16((skb->priority & 0x7)
-					<< HNS3_TX_VLAN_PRIO_SHIFT);
+		skb->protocol = vlan_get_protocol(skb);
+		return rc;
 	}
 
+	rc = skb_cow_head(skb, 0);
+	if (unlikely(rc < 0))
+		return rc;
+
+	vhdr = (struct vlan_ethhdr *)skb->data;
+	vhdr->h_vlan_TCI |= cpu_to_be16((skb->priority << VLAN_PRIO_SHIFT)
+					 & VLAN_PRIO_MASK);
+
 	skb->protocol = vlan_get_protocol(skb);
 	return 0;
 }
 
+static int hns3_fill_skb_desc(struct hns3_enet_ring *ring,
+			      struct sk_buff *skb, struct hns3_desc *desc)
+{
+	u32 ol_type_vlan_len_msec = 0;
+	u32 type_cs_vlan_tso = 0;
+	u32 paylen = skb->len;
+	u16 inner_vtag = 0;
+	u16 out_vtag = 0;
+	u16 mss = 0;
+	int ret;
+
+	ret = hns3_handle_vtags(ring, skb);
+	if (unlikely(ret < 0)) {
+		return ret;
+	} else if (ret == HNS3_INNER_VLAN_TAG) {
+		inner_vtag = skb_vlan_tag_get(skb);
+		inner_vtag |= (skb->priority << VLAN_PRIO_SHIFT) &
+				VLAN_PRIO_MASK;
+		hns3_set_field(type_cs_vlan_tso, HNS3_TXD_VLAN_B, 1);
+	} else if (ret == HNS3_OUTER_VLAN_TAG) {
+		out_vtag = skb_vlan_tag_get(skb);
+		out_vtag |= (skb->priority << VLAN_PRIO_SHIFT) &
+				VLAN_PRIO_MASK;
+		hns3_set_field(ol_type_vlan_len_msec, HNS3_TXD_OVLAN_B,
+			       1);
+	}
+
+	if (skb->ip_summed == CHECKSUM_PARTIAL) {
+		u8 ol4_proto, il4_proto;
+
+		skb_reset_mac_len(skb);
+
+		ret = hns3_get_l4_protocol(skb, &ol4_proto, &il4_proto);
+		if (unlikely(ret))
+			return ret;
+
+		ret = hns3_set_l2l3l4(skb, ol4_proto, il4_proto,
+				      &type_cs_vlan_tso,
+				      &ol_type_vlan_len_msec);
+		if (unlikely(ret))
+			return ret;
+
+		ret = hns3_set_tso(skb, &paylen, &mss,
+				   &type_cs_vlan_tso);
+		if (unlikely(ret))
+			return ret;
+	}
+
+	/* Set txbd */
+	desc->tx.ol_type_vlan_len_msec =
+		cpu_to_le32(ol_type_vlan_len_msec);
+	desc->tx.type_cs_vlan_tso_len = cpu_to_le32(type_cs_vlan_tso);
+	desc->tx.paylen = cpu_to_le32(paylen);
+	desc->tx.mss = cpu_to_le16(mss);
+	desc->tx.vlan_tag = cpu_to_le16(inner_vtag);
+	desc->tx.outer_vlan_tag = cpu_to_le16(out_vtag);
+
+	return 0;
+}
+
 static int hns3_fill_desc(struct hns3_enet_ring *ring, void *priv,
 			  unsigned int size, int frag_end,
 			  enum hns_desc_type type)
@@ -1045,50 +1094,12 @@ static int hns3_fill_desc(struct hns3_enet_ring *ring, void *priv,
 
 	if (type == DESC_TYPE_SKB) {
 		struct sk_buff *skb = (struct sk_buff *)priv;
-		u32 ol_type_vlan_len_msec = 0;
-		u32 type_cs_vlan_tso = 0;
-		u32 paylen = skb->len;
-		u16 inner_vtag = 0;
-		u16 out_vtag = 0;
-		u16 mss = 0;
 		int ret;
 
-		ret = hns3_fill_desc_vtags(skb, ring, &type_cs_vlan_tso,
-					   &ol_type_vlan_len_msec,
-					   &inner_vtag, &out_vtag);
+		ret = hns3_fill_skb_desc(ring, skb, desc);
 		if (unlikely(ret))
 			return ret;
 
-		if (skb->ip_summed == CHECKSUM_PARTIAL) {
-			u8 ol4_proto, il4_proto;
-
-			skb_reset_mac_len(skb);
-
-			ret = hns3_get_l4_protocol(skb, &ol4_proto, &il4_proto);
-			if (unlikely(ret))
-				return ret;
-
-			ret = hns3_set_l2l3l4(skb, ol4_proto, il4_proto,
-					      &type_cs_vlan_tso,
-					      &ol_type_vlan_len_msec);
-			if (unlikely(ret))
-				return ret;
-
-			ret = hns3_set_tso(skb, &paylen, &mss,
-					   &type_cs_vlan_tso);
-			if (unlikely(ret))
-				return ret;
-		}
-
-		/* Set txbd */
-		desc->tx.ol_type_vlan_len_msec =
-			cpu_to_le32(ol_type_vlan_len_msec);
-		desc->tx.type_cs_vlan_tso_len =	cpu_to_le32(type_cs_vlan_tso);
-		desc->tx.paylen = cpu_to_le32(paylen);
-		desc->tx.mss = cpu_to_le16(mss);
-		desc->tx.vlan_tag = cpu_to_le16(inner_vtag);
-		desc->tx.outer_vlan_tag = cpu_to_le16(out_vtag);
-
 		dma = dma_map_single(dev, skb->data, size, DMA_TO_DEVICE);
 	} else {
 		frag = (skb_frag_t *)priv;

From 7ac243f99d61f4580a72f62e638ed4e04aa52aa1 Mon Sep 17 00:00:00 2001
From: Yufeng Mo <moyufeng@huawei.com>
Date: Fri, 9 Aug 2019 10:31:10 +0800
Subject: [PATCH 04/12] net: hns3: add input length check for debugfs write
 function

If the input length reaches the maximum value of size_t, the reverse is
triggered when 1 is added. In addition, there is no need to have such a
large length. Therefore, the input length should be checked and the value
should be less than or equal to 1024.

Signed-off-by: Yufeng Mo <moyufeng@huawei.com>
Reviewed-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
index a4b937286f55..7996dcc21cf6 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
@@ -8,6 +8,7 @@
 #include "hns3_enet.h"
 
 #define HNS3_DBG_READ_LEN 256
+#define HNS3_DBG_WRITE_LEN 1024
 
 static struct dentry *hns3_dbgfs_root;
 
@@ -322,6 +323,9 @@ static ssize_t hns3_dbg_cmd_write(struct file *filp, const char __user *buffer,
 	    test_bit(HNS3_NIC_STATE_RESETTING, &priv->state))
 		return 0;
 
+	if (count > HNS3_DBG_WRITE_LEN)
+		return -ENOSPC;
+
 	cmd_buf = kzalloc(count + 1, GFP_KERNEL);
 	if (!cmd_buf)
 		return count;

From aacbe27e82f01f6e0e3c2ab859d51d0823604ec8 Mon Sep 17 00:00:00 2001
From: Yonglong Liu <liuyonglong@huawei.com>
Date: Fri, 9 Aug 2019 10:31:11 +0800
Subject: [PATCH 05/12] net: hns3: modify how pause options is displayed

Currently, the pause options of HNS3 shown like this:
"RX/TX" is always the same with "RX negotiated/TX negotiated".
Because of the driver covered the value of "RX/TX" with the value
of "RX negotiated/TX negotiated" after adjust link.

This patch records the pause configurations of the user, and never
covered them in adjust link.

Signed-off-by: Yonglong Liu <liuyonglong@huawei.com>
Reviewed-by: Yunsheng Lin <linyunsheng@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../hisilicon/hns3/hns3pf/hclge_main.c        | 38 ++++++++++---------
 1 file changed, 21 insertions(+), 17 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index c0feae3a9f86..381f19527d9d 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -8207,28 +8207,15 @@ static int hclge_cfg_pauseparam(struct hclge_dev *hdev, u32 rx_en, u32 tx_en)
 {
 	int ret;
 
-	if (rx_en && tx_en)
-		hdev->fc_mode_last_time = HCLGE_FC_FULL;
-	else if (rx_en && !tx_en)
-		hdev->fc_mode_last_time = HCLGE_FC_RX_PAUSE;
-	else if (!rx_en && tx_en)
-		hdev->fc_mode_last_time = HCLGE_FC_TX_PAUSE;
-	else
-		hdev->fc_mode_last_time = HCLGE_FC_NONE;
-
 	if (hdev->tm_info.fc_mode == HCLGE_FC_PFC)
 		return 0;
 
 	ret = hclge_mac_pause_en_cfg(hdev, tx_en, rx_en);
-	if (ret) {
-		dev_err(&hdev->pdev->dev, "configure pauseparam error, ret = %d.\n",
-			ret);
-		return ret;
-	}
+	if (ret)
+		dev_err(&hdev->pdev->dev,
+			"configure pauseparam error, ret = %d.\n", ret);
 
-	hdev->tm_info.fc_mode = hdev->fc_mode_last_time;
-
-	return 0;
+	return ret;
 }
 
 int hclge_cfg_flowctrl(struct hclge_dev *hdev)
@@ -8293,6 +8280,21 @@ static void hclge_get_pauseparam(struct hnae3_handle *handle, u32 *auto_neg,
 	}
 }
 
+static void hclge_record_user_pauseparam(struct hclge_dev *hdev,
+					 u32 rx_en, u32 tx_en)
+{
+	if (rx_en && tx_en)
+		hdev->fc_mode_last_time = HCLGE_FC_FULL;
+	else if (rx_en && !tx_en)
+		hdev->fc_mode_last_time = HCLGE_FC_RX_PAUSE;
+	else if (!rx_en && tx_en)
+		hdev->fc_mode_last_time = HCLGE_FC_TX_PAUSE;
+	else
+		hdev->fc_mode_last_time = HCLGE_FC_NONE;
+
+	hdev->tm_info.fc_mode = hdev->fc_mode_last_time;
+}
+
 static int hclge_set_pauseparam(struct hnae3_handle *handle, u32 auto_neg,
 				u32 rx_en, u32 tx_en)
 {
@@ -8318,6 +8320,8 @@ static int hclge_set_pauseparam(struct hnae3_handle *handle, u32 auto_neg,
 
 	hclge_set_flowctrl_adv(hdev, rx_en, tx_en);
 
+	hclge_record_user_pauseparam(hdev, rx_en, tx_en);
+
 	if (!auto_neg)
 		return hclge_cfg_pauseparam(hdev, rx_en, tx_en);
 

From ddb54554fa517be1639f10c6f2828429a871368b Mon Sep 17 00:00:00 2001
From: Guangbin Huang <huangguangbin2@huawei.com>
Date: Fri, 9 Aug 2019 10:31:12 +0800
Subject: [PATCH 06/12] net: hns3: add DFX registers information for ethtool -d

Now we can use ethtool -d command to dump some registers. However,
these registers information is not enough to find out where the problem is.

This patch adds DFX registers information after original registers
when use ethtool -d commmand to dump registers. Also, using macro
replaces some related magic number.

Signed-off-by: Guangbin Huang <huangguangbin2@huawei.com>
Reviewed-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../hisilicon/hns3/hns3pf/hclge_debugfs.c     |  12 +-
 .../hisilicon/hns3/hns3pf/hclge_main.c        | 352 +++++++++++++++---
 .../hisilicon/hns3/hns3pf/hclge_main.h        |   2 +
 3 files changed, 306 insertions(+), 60 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
index f16bfc67412a..933dec53ed8e 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
@@ -14,16 +14,8 @@ static int hclge_dbg_get_dfx_bd_num(struct hclge_dev *hdev, int offset)
 	struct hclge_desc desc[4];
 	int ret;
 
-	hclge_cmd_setup_basic_desc(&desc[0], HCLGE_OPC_DFX_BD_NUM, true);
-	desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
-	hclge_cmd_setup_basic_desc(&desc[1], HCLGE_OPC_DFX_BD_NUM, true);
-	desc[1].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
-	hclge_cmd_setup_basic_desc(&desc[2], HCLGE_OPC_DFX_BD_NUM, true);
-	desc[2].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
-	hclge_cmd_setup_basic_desc(&desc[3], HCLGE_OPC_DFX_BD_NUM, true);
-
-	ret = hclge_cmd_send(&hdev->hw, desc, 4);
-	if (ret != HCLGE_CMD_EXEC_SUCCESS) {
+	ret = hclge_query_bd_num_cmd_send(hdev, desc);
+	if (ret) {
 		dev_err(&hdev->pdev->dev,
 			"get dfx bdnum fail, status is %d.\n", ret);
 		return ret;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 381f19527d9d..7d7ab9e66383 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -36,6 +36,20 @@
 
 #define HCLGE_RESET_MAX_FAIL_CNT	5
 
+/* Get DFX BD number offset */
+#define HCLGE_DFX_BIOS_BD_OFFSET        1
+#define HCLGE_DFX_SSU_0_BD_OFFSET       2
+#define HCLGE_DFX_SSU_1_BD_OFFSET       3
+#define HCLGE_DFX_IGU_BD_OFFSET         4
+#define HCLGE_DFX_RPU_0_BD_OFFSET       5
+#define HCLGE_DFX_RPU_1_BD_OFFSET       6
+#define HCLGE_DFX_NCSI_BD_OFFSET        7
+#define HCLGE_DFX_RTC_BD_OFFSET         8
+#define HCLGE_DFX_PPP_BD_OFFSET         9
+#define HCLGE_DFX_RCB_BD_OFFSET         10
+#define HCLGE_DFX_TQP_BD_OFFSET         11
+#define HCLGE_DFX_SSU_2_BD_OFFSET       12
+
 static int hclge_set_mac_mtu(struct hclge_dev *hdev, int new_mps);
 static int hclge_init_vlan_config(struct hclge_dev *hdev);
 static void hclge_sync_vlan_filter(struct hclge_dev *hdev);
@@ -317,6 +331,36 @@ static const u8 hclge_hash_key[] = {
 	0x6A, 0x42, 0xB7, 0x3B, 0xBE, 0xAC, 0x01, 0xFA
 };
 
+static const u32 hclge_dfx_bd_offset_list[] = {
+	HCLGE_DFX_BIOS_BD_OFFSET,
+	HCLGE_DFX_SSU_0_BD_OFFSET,
+	HCLGE_DFX_SSU_1_BD_OFFSET,
+	HCLGE_DFX_IGU_BD_OFFSET,
+	HCLGE_DFX_RPU_0_BD_OFFSET,
+	HCLGE_DFX_RPU_1_BD_OFFSET,
+	HCLGE_DFX_NCSI_BD_OFFSET,
+	HCLGE_DFX_RTC_BD_OFFSET,
+	HCLGE_DFX_PPP_BD_OFFSET,
+	HCLGE_DFX_RCB_BD_OFFSET,
+	HCLGE_DFX_TQP_BD_OFFSET,
+	HCLGE_DFX_SSU_2_BD_OFFSET
+};
+
+static const enum hclge_opcode_type hclge_dfx_reg_opcode_list[] = {
+	HCLGE_OPC_DFX_BIOS_COMMON_REG,
+	HCLGE_OPC_DFX_SSU_REG_0,
+	HCLGE_OPC_DFX_SSU_REG_1,
+	HCLGE_OPC_DFX_IGU_EGU_REG,
+	HCLGE_OPC_DFX_RPU_REG_0,
+	HCLGE_OPC_DFX_RPU_REG_1,
+	HCLGE_OPC_DFX_NCSI_REG,
+	HCLGE_OPC_DFX_RTC_REG,
+	HCLGE_OPC_DFX_PPP_REG,
+	HCLGE_OPC_DFX_RCB_REG,
+	HCLGE_OPC_DFX_TQP_REG,
+	HCLGE_OPC_DFX_SSU_REG_2
+};
+
 static int hclge_mac_update_stats_defective(struct hclge_dev *hdev)
 {
 #define HCLGE_MAC_CMD_NUM 21
@@ -9332,9 +9376,222 @@ static int hclge_get_64_bit_regs(struct hclge_dev *hdev, u32 regs_num,
 }
 
 #define MAX_SEPARATE_NUM	4
-#define SEPARATOR_VALUE		0xFFFFFFFF
+#define SEPARATOR_VALUE		0xFDFCFBFA
 #define REG_NUM_PER_LINE	4
 #define REG_LEN_PER_LINE	(REG_NUM_PER_LINE * sizeof(u32))
+#define REG_SEPARATOR_LINE	1
+#define REG_NUM_REMAIN_MASK	3
+#define BD_LIST_MAX_NUM		30
+
+int hclge_query_bd_num_cmd_send(struct hclge_dev *hdev, struct hclge_desc *desc)
+{
+	/*prepare 4 commands to query DFX BD number*/
+	hclge_cmd_setup_basic_desc(&desc[0], HCLGE_OPC_DFX_BD_NUM, true);
+	desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
+	hclge_cmd_setup_basic_desc(&desc[1], HCLGE_OPC_DFX_BD_NUM, true);
+	desc[1].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
+	hclge_cmd_setup_basic_desc(&desc[2], HCLGE_OPC_DFX_BD_NUM, true);
+	desc[2].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
+	hclge_cmd_setup_basic_desc(&desc[3], HCLGE_OPC_DFX_BD_NUM, true);
+
+	return hclge_cmd_send(&hdev->hw, desc, 4);
+}
+
+static int hclge_get_dfx_reg_bd_num(struct hclge_dev *hdev,
+				    int *bd_num_list,
+				    u32 type_num)
+{
+#define HCLGE_DFX_REG_BD_NUM	4
+
+	u32 entries_per_desc, desc_index, index, offset, i;
+	struct hclge_desc desc[HCLGE_DFX_REG_BD_NUM];
+	int ret;
+
+	ret = hclge_query_bd_num_cmd_send(hdev, desc);
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"Get dfx bd num fail, status is %d.\n", ret);
+		return ret;
+	}
+
+	entries_per_desc = ARRAY_SIZE(desc[0].data);
+	for (i = 0; i < type_num; i++) {
+		offset = hclge_dfx_bd_offset_list[i];
+		index = offset % entries_per_desc;
+		desc_index = offset / entries_per_desc;
+		bd_num_list[i] = le32_to_cpu(desc[desc_index].data[index]);
+	}
+
+	return ret;
+}
+
+static int hclge_dfx_reg_cmd_send(struct hclge_dev *hdev,
+				  struct hclge_desc *desc_src, int bd_num,
+				  enum hclge_opcode_type cmd)
+{
+	struct hclge_desc *desc = desc_src;
+	int i, ret;
+
+	hclge_cmd_setup_basic_desc(desc, cmd, true);
+	for (i = 0; i < bd_num - 1; i++) {
+		desc->flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
+		desc++;
+		hclge_cmd_setup_basic_desc(desc, cmd, true);
+	}
+
+	desc = desc_src;
+	ret = hclge_cmd_send(&hdev->hw, desc, bd_num);
+	if (ret)
+		dev_err(&hdev->pdev->dev,
+			"Query dfx reg cmd(0x%x) send fail, status is %d.\n",
+			cmd, ret);
+
+	return ret;
+}
+
+static int hclge_dfx_reg_fetch_data(struct hclge_desc *desc_src, int bd_num,
+				    void *data)
+{
+	int entries_per_desc, reg_num, separator_num, desc_index, index, i;
+	struct hclge_desc *desc = desc_src;
+	u32 *reg = data;
+
+	entries_per_desc = ARRAY_SIZE(desc->data);
+	reg_num = entries_per_desc * bd_num;
+	separator_num = REG_NUM_PER_LINE - (reg_num & REG_NUM_REMAIN_MASK);
+	for (i = 0; i < reg_num; i++) {
+		index = i % entries_per_desc;
+		desc_index = i / entries_per_desc;
+		*reg++ = le32_to_cpu(desc[desc_index].data[index]);
+	}
+	for (i = 0; i < separator_num; i++)
+		*reg++ = SEPARATOR_VALUE;
+
+	return reg_num + separator_num;
+}
+
+static int hclge_get_dfx_reg_len(struct hclge_dev *hdev, int *len)
+{
+	u32 dfx_reg_type_num = ARRAY_SIZE(hclge_dfx_bd_offset_list);
+	int data_len_per_desc, data_len, bd_num, i;
+	int bd_num_list[BD_LIST_MAX_NUM];
+	int ret;
+
+	ret = hclge_get_dfx_reg_bd_num(hdev, bd_num_list, dfx_reg_type_num);
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"Get dfx reg bd num fail, status is %d.\n", ret);
+		return ret;
+	}
+
+	data_len_per_desc = FIELD_SIZEOF(struct hclge_desc, data);
+	*len = 0;
+	for (i = 0; i < dfx_reg_type_num; i++) {
+		bd_num = bd_num_list[i];
+		data_len = data_len_per_desc * bd_num;
+		*len += (data_len / REG_LEN_PER_LINE + 1) * REG_LEN_PER_LINE;
+	}
+
+	return ret;
+}
+
+static int hclge_get_dfx_reg(struct hclge_dev *hdev, void *data)
+{
+	u32 dfx_reg_type_num = ARRAY_SIZE(hclge_dfx_bd_offset_list);
+	int bd_num, bd_num_max, buf_len, i;
+	int bd_num_list[BD_LIST_MAX_NUM];
+	struct hclge_desc *desc_src;
+	u32 *reg = data;
+	int ret;
+
+	ret = hclge_get_dfx_reg_bd_num(hdev, bd_num_list, dfx_reg_type_num);
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"Get dfx reg bd num fail, status is %d.\n", ret);
+		return ret;
+	}
+
+	bd_num_max = bd_num_list[0];
+	for (i = 1; i < dfx_reg_type_num; i++)
+		bd_num_max = max_t(int, bd_num_max, bd_num_list[i]);
+
+	buf_len = sizeof(*desc_src) * bd_num_max;
+	desc_src = kzalloc(buf_len, GFP_KERNEL);
+	if (!desc_src) {
+		dev_err(&hdev->pdev->dev, "%s kzalloc failed\n", __func__);
+		return -ENOMEM;
+	}
+
+	for (i = 0; i < dfx_reg_type_num; i++) {
+		bd_num = bd_num_list[i];
+		ret = hclge_dfx_reg_cmd_send(hdev, desc_src, bd_num,
+					     hclge_dfx_reg_opcode_list[i]);
+		if (ret) {
+			dev_err(&hdev->pdev->dev,
+				"Get dfx reg fail, status is %d.\n", ret);
+			break;
+		}
+
+		reg += hclge_dfx_reg_fetch_data(desc_src, bd_num, reg);
+	}
+
+	kfree(desc_src);
+	return ret;
+}
+
+static int hclge_fetch_pf_reg(struct hclge_dev *hdev, void *data,
+			      struct hnae3_knic_private_info *kinfo)
+{
+#define HCLGE_RING_REG_OFFSET		0x200
+#define HCLGE_RING_INT_REG_OFFSET	0x4
+
+	int i, j, reg_num, separator_num;
+	int data_num_sum;
+	u32 *reg = data;
+
+	/* fetching per-PF registers valus from PF PCIe register space */
+	reg_num = ARRAY_SIZE(cmdq_reg_addr_list);
+	separator_num = MAX_SEPARATE_NUM - (reg_num & REG_NUM_REMAIN_MASK);
+	for (i = 0; i < reg_num; i++)
+		*reg++ = hclge_read_dev(&hdev->hw, cmdq_reg_addr_list[i]);
+	for (i = 0; i < separator_num; i++)
+		*reg++ = SEPARATOR_VALUE;
+	data_num_sum = reg_num + separator_num;
+
+	reg_num = ARRAY_SIZE(common_reg_addr_list);
+	separator_num = MAX_SEPARATE_NUM - (reg_num & REG_NUM_REMAIN_MASK);
+	for (i = 0; i < reg_num; i++)
+		*reg++ = hclge_read_dev(&hdev->hw, common_reg_addr_list[i]);
+	for (i = 0; i < separator_num; i++)
+		*reg++ = SEPARATOR_VALUE;
+	data_num_sum += reg_num + separator_num;
+
+	reg_num = ARRAY_SIZE(ring_reg_addr_list);
+	separator_num = MAX_SEPARATE_NUM - (reg_num & REG_NUM_REMAIN_MASK);
+	for (j = 0; j < kinfo->num_tqps; j++) {
+		for (i = 0; i < reg_num; i++)
+			*reg++ = hclge_read_dev(&hdev->hw,
+						ring_reg_addr_list[i] +
+						HCLGE_RING_REG_OFFSET * j);
+		for (i = 0; i < separator_num; i++)
+			*reg++ = SEPARATOR_VALUE;
+	}
+	data_num_sum += (reg_num + separator_num) * kinfo->num_tqps;
+
+	reg_num = ARRAY_SIZE(tqp_intr_reg_addr_list);
+	separator_num = MAX_SEPARATE_NUM - (reg_num & REG_NUM_REMAIN_MASK);
+	for (j = 0; j < hdev->num_msi_used - 1; j++) {
+		for (i = 0; i < reg_num; i++)
+			*reg++ = hclge_read_dev(&hdev->hw,
+						tqp_intr_reg_addr_list[i] +
+						HCLGE_RING_INT_REG_OFFSET * j);
+		for (i = 0; i < separator_num; i++)
+			*reg++ = SEPARATOR_VALUE;
+	}
+	data_num_sum += (reg_num + separator_num) * (hdev->num_msi_used - 1);
+
+	return data_num_sum;
+}
 
 static int hclge_get_regs_len(struct hnae3_handle *handle)
 {
@@ -9342,24 +9599,40 @@ static int hclge_get_regs_len(struct hnae3_handle *handle)
 	struct hnae3_knic_private_info *kinfo = &handle->kinfo;
 	struct hclge_vport *vport = hclge_get_vport(handle);
 	struct hclge_dev *hdev = vport->back;
-	u32 regs_num_32_bit, regs_num_64_bit;
+	int regs_num_32_bit, regs_num_64_bit, dfx_regs_len;
+	int regs_lines_32_bit, regs_lines_64_bit;
 	int ret;
 
 	ret = hclge_get_regs_num(hdev, &regs_num_32_bit, &regs_num_64_bit);
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
 			"Get register number failed, ret = %d.\n", ret);
-		return -EOPNOTSUPP;
+		return ret;
 	}
 
-	cmdq_lines = sizeof(cmdq_reg_addr_list) / REG_LEN_PER_LINE + 1;
-	common_lines = sizeof(common_reg_addr_list) / REG_LEN_PER_LINE + 1;
-	ring_lines = sizeof(ring_reg_addr_list) / REG_LEN_PER_LINE + 1;
-	tqp_intr_lines = sizeof(tqp_intr_reg_addr_list) / REG_LEN_PER_LINE + 1;
+	ret = hclge_get_dfx_reg_len(hdev, &dfx_regs_len);
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"Get dfx reg len failed, ret = %d.\n", ret);
+		return ret;
+	}
+
+	cmdq_lines = sizeof(cmdq_reg_addr_list) / REG_LEN_PER_LINE +
+		REG_SEPARATOR_LINE;
+	common_lines = sizeof(common_reg_addr_list) / REG_LEN_PER_LINE +
+		REG_SEPARATOR_LINE;
+	ring_lines = sizeof(ring_reg_addr_list) / REG_LEN_PER_LINE +
+		REG_SEPARATOR_LINE;
+	tqp_intr_lines = sizeof(tqp_intr_reg_addr_list) / REG_LEN_PER_LINE +
+		REG_SEPARATOR_LINE;
+	regs_lines_32_bit = regs_num_32_bit * sizeof(u32) / REG_LEN_PER_LINE +
+		REG_SEPARATOR_LINE;
+	regs_lines_64_bit = regs_num_64_bit * sizeof(u64) / REG_LEN_PER_LINE +
+		REG_SEPARATOR_LINE;
 
 	return (cmdq_lines + common_lines + ring_lines * kinfo->num_tqps +
-		tqp_intr_lines * (hdev->num_msi_used - 1)) * REG_LEN_PER_LINE +
-		regs_num_32_bit * sizeof(u32) + regs_num_64_bit * sizeof(u64);
+		tqp_intr_lines * (hdev->num_msi_used - 1) + regs_lines_32_bit +
+		regs_lines_64_bit) * REG_LEN_PER_LINE + dfx_regs_len;
 }
 
 static void hclge_get_regs(struct hnae3_handle *handle, u32 *version,
@@ -9369,9 +9642,8 @@ static void hclge_get_regs(struct hnae3_handle *handle, u32 *version,
 	struct hclge_vport *vport = hclge_get_vport(handle);
 	struct hclge_dev *hdev = vport->back;
 	u32 regs_num_32_bit, regs_num_64_bit;
-	int i, j, reg_um, separator_num;
+	int i, reg_num, separator_num, ret;
 	u32 *reg = data;
-	int ret;
 
 	*version = hdev->fw_version;
 
@@ -9382,56 +9654,36 @@ static void hclge_get_regs(struct hnae3_handle *handle, u32 *version,
 		return;
 	}
 
-	/* fetching per-PF registers valus from PF PCIe register space */
-	reg_um = sizeof(cmdq_reg_addr_list) / sizeof(u32);
-	separator_num = MAX_SEPARATE_NUM - reg_um % REG_NUM_PER_LINE;
-	for (i = 0; i < reg_um; i++)
-		*reg++ = hclge_read_dev(&hdev->hw, cmdq_reg_addr_list[i]);
-	for (i = 0; i < separator_num; i++)
-		*reg++ = SEPARATOR_VALUE;
+	reg += hclge_fetch_pf_reg(hdev, reg, kinfo);
 
-	reg_um = sizeof(common_reg_addr_list) / sizeof(u32);
-	separator_num = MAX_SEPARATE_NUM - reg_um % REG_NUM_PER_LINE;
-	for (i = 0; i < reg_um; i++)
-		*reg++ = hclge_read_dev(&hdev->hw, common_reg_addr_list[i]);
-	for (i = 0; i < separator_num; i++)
-		*reg++ = SEPARATOR_VALUE;
-
-	reg_um = sizeof(ring_reg_addr_list) / sizeof(u32);
-	separator_num = MAX_SEPARATE_NUM - reg_um % REG_NUM_PER_LINE;
-	for (j = 0; j < kinfo->num_tqps; j++) {
-		for (i = 0; i < reg_um; i++)
-			*reg++ = hclge_read_dev(&hdev->hw,
-						ring_reg_addr_list[i] +
-						0x200 * j);
-		for (i = 0; i < separator_num; i++)
-			*reg++ = SEPARATOR_VALUE;
-	}
-
-	reg_um = sizeof(tqp_intr_reg_addr_list) / sizeof(u32);
-	separator_num = MAX_SEPARATE_NUM - reg_um % REG_NUM_PER_LINE;
-	for (j = 0; j < hdev->num_msi_used - 1; j++) {
-		for (i = 0; i < reg_um; i++)
-			*reg++ = hclge_read_dev(&hdev->hw,
-						tqp_intr_reg_addr_list[i] +
-						4 * j);
-		for (i = 0; i < separator_num; i++)
-			*reg++ = SEPARATOR_VALUE;
-	}
-
-	/* fetching PF common registers values from firmware */
 	ret = hclge_get_32_bit_regs(hdev, regs_num_32_bit, reg);
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
 			"Get 32 bit register failed, ret = %d.\n", ret);
 		return;
 	}
+	reg_num = regs_num_32_bit;
+	reg += reg_num;
+	separator_num = MAX_SEPARATE_NUM - (reg_num & REG_NUM_REMAIN_MASK);
+	for (i = 0; i < separator_num; i++)
+		*reg++ = SEPARATOR_VALUE;
 
-	reg += regs_num_32_bit;
 	ret = hclge_get_64_bit_regs(hdev, regs_num_64_bit, reg);
-	if (ret)
+	if (ret) {
 		dev_err(&hdev->pdev->dev,
 			"Get 64 bit register failed, ret = %d.\n", ret);
+		return;
+	}
+	reg_num = regs_num_64_bit * 2;
+	reg += reg_num;
+	separator_num = MAX_SEPARATE_NUM - (reg_num & REG_NUM_REMAIN_MASK);
+	for (i = 0; i < separator_num; i++)
+		*reg++ = SEPARATOR_VALUE;
+
+	ret = hclge_get_dfx_reg(hdev, reg);
+	if (ret)
+		dev_err(&hdev->pdev->dev,
+			"Get dfx register failed, ret = %d.\n", ret);
 }
 
 static int hclge_set_led_status(struct hclge_dev *hdev, u8 locate_led_status)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index c9b9867fc226..f6d9b57830fb 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -1029,4 +1029,6 @@ int hclge_push_vf_port_base_vlan_info(struct hclge_vport *vport, u8 vfid,
 				      u16 state, u16 vlan_tag, u16 qos,
 				      u16 vlan_proto);
 void hclge_task_schedule(struct hclge_dev *hdev, unsigned long delay_time);
+int hclge_query_bd_num_cmd_send(struct hclge_dev *hdev,
+				struct hclge_desc *desc);
 #endif

From b20d7fe51e0de28982e115b8ec0647066d73d206 Mon Sep 17 00:00:00 2001
From: Yunsheng Lin <linyunsheng@huawei.com>
Date: Fri, 9 Aug 2019 10:31:13 +0800
Subject: [PATCH 07/12] net: hns3: add some statitics info to tx process

This patch adds tx_vlan_err, tx_l4_proto_err, tx_l2l3l4_err
and tx_tso_err counter to tx process, in order to better
debug the desc filling error.

This patch also adds a missing u64_stats_update_* around
ring->stats.sw_err_cnt and adds hns3_rl_err to limit the
error printing in the IO patch.

Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Reviewed-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/hisilicon/hns3/hns3_enet.c   | 58 ++++++++++++++-----
 .../net/ethernet/hisilicon/hns3/hns3_enet.h   |  4 ++
 .../ethernet/hisilicon/hns3/hns3_ethtool.c    |  4 ++
 3 files changed, 52 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index fd6a3d589f40..b2a668d6dad7 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -28,6 +28,12 @@
 #define hns3_set_field(origin, shift, val)	((origin) |= ((val) << (shift)))
 #define hns3_tx_bd_count(S)	DIV_ROUND_UP(S, HNS3_MAX_BD_SIZE)
 
+#define hns3_rl_err(fmt, ...)						\
+	do {								\
+		if (net_ratelimit())					\
+			netdev_err(fmt, ##__VA_ARGS__);			\
+	} while (0)
+
 static void hns3_clear_all_ring(struct hnae3_handle *h, bool force);
 static void hns3_remove_hw_addr(struct net_device *netdev);
 
@@ -1033,6 +1039,9 @@ static int hns3_fill_skb_desc(struct hns3_enet_ring *ring,
 
 	ret = hns3_handle_vtags(ring, skb);
 	if (unlikely(ret < 0)) {
+		u64_stats_update_begin(&ring->syncp);
+		ring->stats.tx_vlan_err++;
+		u64_stats_update_end(&ring->syncp);
 		return ret;
 	} else if (ret == HNS3_INNER_VLAN_TAG) {
 		inner_vtag = skb_vlan_tag_get(skb);
@@ -1053,19 +1062,31 @@ static int hns3_fill_skb_desc(struct hns3_enet_ring *ring,
 		skb_reset_mac_len(skb);
 
 		ret = hns3_get_l4_protocol(skb, &ol4_proto, &il4_proto);
-		if (unlikely(ret))
+		if (unlikely(ret)) {
+			u64_stats_update_begin(&ring->syncp);
+			ring->stats.tx_l4_proto_err++;
+			u64_stats_update_end(&ring->syncp);
 			return ret;
+		}
 
 		ret = hns3_set_l2l3l4(skb, ol4_proto, il4_proto,
 				      &type_cs_vlan_tso,
 				      &ol_type_vlan_len_msec);
-		if (unlikely(ret))
+		if (unlikely(ret)) {
+			u64_stats_update_begin(&ring->syncp);
+			ring->stats.tx_l2l3l4_err++;
+			u64_stats_update_end(&ring->syncp);
 			return ret;
+		}
 
 		ret = hns3_set_tso(skb, &paylen, &mss,
 				   &type_cs_vlan_tso);
-		if (unlikely(ret))
+		if (unlikely(ret)) {
+			u64_stats_update_begin(&ring->syncp);
+			ring->stats.tx_tso_err++;
+			u64_stats_update_end(&ring->syncp);
 			return ret;
+		}
 	}
 
 	/* Set txbd */
@@ -1107,7 +1128,9 @@ static int hns3_fill_desc(struct hns3_enet_ring *ring, void *priv,
 	}
 
 	if (unlikely(dma_mapping_error(dev, dma))) {
+		u64_stats_update_begin(&ring->syncp);
 		ring->stats.sw_err_cnt++;
+		u64_stats_update_end(&ring->syncp);
 		return -ENOMEM;
 	}
 
@@ -1330,9 +1353,7 @@ netdev_tx_t hns3_nic_net_xmit(struct sk_buff *skb, struct net_device *netdev)
 			u64_stats_update_end(&ring->syncp);
 		}
 
-		if (net_ratelimit())
-			netdev_err(netdev, "xmit error: %d!\n", buf_num);
-
+		hns3_rl_err(netdev, "xmit error: %d!\n", buf_num);
 		goto out_err_tx_ok;
 	}
 
@@ -1498,7 +1519,15 @@ static void hns3_nic_get_stats64(struct net_device *netdev,
 			tx_bytes += ring->stats.tx_bytes;
 			tx_pkts += ring->stats.tx_pkts;
 			tx_drop += ring->stats.sw_err_cnt;
+			tx_drop += ring->stats.tx_vlan_err;
+			tx_drop += ring->stats.tx_l4_proto_err;
+			tx_drop += ring->stats.tx_l2l3l4_err;
+			tx_drop += ring->stats.tx_tso_err;
 			tx_errors += ring->stats.sw_err_cnt;
+			tx_errors += ring->stats.tx_vlan_err;
+			tx_errors += ring->stats.tx_l4_proto_err;
+			tx_errors += ring->stats.tx_l2l3l4_err;
+			tx_errors += ring->stats.tx_tso_err;
 		} while (u64_stats_fetch_retry_irq(&ring->syncp, start));
 
 		/* fetch the rx stats */
@@ -2382,8 +2411,9 @@ static void hns3_nic_alloc_rx_buffers(struct hns3_enet_ring *ring,
 				ring->stats.sw_err_cnt++;
 				u64_stats_update_end(&ring->syncp);
 
-				netdev_err(ring->tqp->handle->kinfo.netdev,
-					   "hnae reserve buffer map failed.\n");
+				hns3_rl_err(ring->tqp_vector->napi.dev,
+					    "alloc rx buffer failed: %d\n",
+					    ret);
 				break;
 			}
 			hns3_replace_buffer(ring, ring->next_to_use, &res_cbs);
@@ -2468,9 +2498,9 @@ static int hns3_gro_complete(struct sk_buff *skb, u32 l234info)
 		th->check = ~tcp_v6_check(skb->len - depth, &iph->saddr,
 					  &iph->daddr, 0);
 	} else {
-		netdev_err(skb->dev,
-			   "Error: FW GRO supports only IPv4/IPv6, not 0x%04x, depth: %d\n",
-			   be16_to_cpu(type), depth);
+		hns3_rl_err(skb->dev,
+			    "Error: FW GRO supports only IPv4/IPv6, not 0x%04x, depth: %d\n",
+			    be16_to_cpu(type), depth);
 		return -EFAULT;
 	}
 
@@ -2612,7 +2642,7 @@ static int hns3_alloc_skb(struct hns3_enet_ring *ring, unsigned int length,
 	ring->skb = napi_alloc_skb(&ring->tqp_vector->napi, HNS3_RX_HEAD_SIZE);
 	skb = ring->skb;
 	if (unlikely(!skb)) {
-		netdev_err(netdev, "alloc rx skb fail\n");
+		hns3_rl_err(netdev, "alloc rx skb fail\n");
 
 		u64_stats_update_begin(&ring->syncp);
 		ring->stats.sw_err_cnt++;
@@ -2687,8 +2717,8 @@ static int hns3_add_frag(struct hns3_enet_ring *ring, struct hns3_desc *desc,
 			new_skb = napi_alloc_skb(&ring->tqp_vector->napi,
 						 HNS3_RX_HEAD_SIZE);
 			if (unlikely(!new_skb)) {
-				netdev_err(ring->tqp->handle->kinfo.netdev,
-					   "alloc rx skb frag fail\n");
+				hns3_rl_err(ring->tqp_vector->napi.dev,
+					    "alloc rx fraglist skb fail\n");
 				return -ENXIO;
 			}
 			ring->frag_num = 0;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
index 0a970f5fed10..a76712c3f65c 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
@@ -377,6 +377,10 @@ struct ring_stats {
 			u64 restart_queue;
 			u64 tx_busy;
 			u64 tx_copy;
+			u64 tx_vlan_err;
+			u64 tx_l4_proto_err;
+			u64 tx_l2l3l4_err;
+			u64 tx_tso_err;
 		};
 		struct {
 			u64 rx_pkts;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
index 02f46c73ac3b..185ff32262e4 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
@@ -30,6 +30,10 @@ static const struct hns3_stats hns3_txq_stats[] = {
 	HNS3_TQP_STAT("wake", restart_queue),
 	HNS3_TQP_STAT("busy", tx_busy),
 	HNS3_TQP_STAT("copy", tx_copy),
+	HNS3_TQP_STAT("vlan_err", tx_vlan_err),
+	HNS3_TQP_STAT("l4_proto_err", tx_l4_proto_err),
+	HNS3_TQP_STAT("l2l3l4_err", tx_l2l3l4_err),
+	HNS3_TQP_STAT("tso_err", tx_tso_err),
 };
 
 #define HNS3_TXQ_STATS_COUNT ARRAY_SIZE(hns3_txq_stats)

From 42611b70f8be12c46906c869f5d819ac70dfd1c7 Mon Sep 17 00:00:00 2001
From: Yunsheng Lin <linyunsheng@huawei.com>
Date: Fri, 9 Aug 2019 10:31:14 +0800
Subject: [PATCH 08/12] net: hns3: add check for max TX BD num for tso and
 non-tso case

Hardware supports up to 8 TX BD for non-TSO skb and 63 TX
BD for TSO skb. Currently hns3 driver does not check the max
BD num that required by a skb before filling desc, which may
cause the hardware to issue a RAS error throug PCIe AER.

This patch adds the max BD num check before filling desc,
if the bd num is not within the hardware limit, it will
record the error by ring->stats.sw_err_cnt counter and
free the skb.

This patch also cleans up the hns3_nic_bd_num function by
changing the return type and removing an unnecessary check.

Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Reviewed-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/hisilicon/hns3/hns3_enet.c   | 38 ++++++++-----------
 .../net/ethernet/hisilicon/hns3/hns3_enet.h   |  3 +-
 2 files changed, 17 insertions(+), 24 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index b2a668d6dad7..df08f9ec0601 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -1186,28 +1186,20 @@ static int hns3_fill_desc(struct hns3_enet_ring *ring, void *priv,
 	return 0;
 }
 
-static int hns3_nic_bd_num(struct sk_buff *skb)
+static unsigned int hns3_nic_bd_num(struct sk_buff *skb)
 {
-	int size = skb_headlen(skb);
-	int i, bd_num;
+	unsigned int bd_num;
+	int i;
 
 	/* if the total len is within the max bd limit */
 	if (likely(skb->len <= HNS3_MAX_BD_SIZE))
 		return skb_shinfo(skb)->nr_frags + 1;
 
-	bd_num = hns3_tx_bd_count(size);
+	bd_num = hns3_tx_bd_count(skb_headlen(skb));
 
 	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
 		skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
-		int frag_bd_num;
-
-		size = skb_frag_size(frag);
-		frag_bd_num = hns3_tx_bd_count(size);
-
-		if (unlikely(frag_bd_num > HNS3_MAX_BD_PER_FRAG))
-			return -ENOMEM;
-
-		bd_num += frag_bd_num;
+		bd_num += hns3_tx_bd_count(skb_frag_size(frag));
 	}
 
 	return bd_num;
@@ -1228,7 +1220,7 @@ static unsigned int hns3_gso_hdr_len(struct sk_buff *skb)
  */
 static bool hns3_skb_need_linearized(struct sk_buff *skb)
 {
-	int bd_limit = HNS3_MAX_BD_PER_FRAG - 1;
+	int bd_limit = HNS3_MAX_BD_NUM_NORMAL - 1;
 	unsigned int tot_len = 0;
 	int i;
 
@@ -1258,21 +1250,16 @@ static int hns3_nic_maybe_stop_tx(struct hns3_enet_ring *ring,
 				  struct sk_buff **out_skb)
 {
 	struct sk_buff *skb = *out_skb;
-	int bd_num;
+	unsigned int bd_num;
 
 	bd_num = hns3_nic_bd_num(skb);
-	if (bd_num < 0)
-		return bd_num;
-
-	if (unlikely(bd_num > HNS3_MAX_BD_PER_FRAG)) {
+	if (unlikely(bd_num > HNS3_MAX_BD_NUM_NORMAL)) {
 		struct sk_buff *new_skb;
 
-		if (skb_is_gso(skb) && !hns3_skb_need_linearized(skb))
+		if (skb_is_gso(skb) && bd_num <= HNS3_MAX_BD_NUM_TSO &&
+		    !hns3_skb_need_linearized(skb))
 			goto out;
 
-		bd_num = hns3_tx_bd_count(skb->len);
-		if (unlikely(ring_space(ring) < bd_num))
-			return -EBUSY;
 		/* manual split the send packet */
 		new_skb = skb_copy(skb, GFP_ATOMIC);
 		if (!new_skb)
@@ -1280,6 +1267,11 @@ static int hns3_nic_maybe_stop_tx(struct hns3_enet_ring *ring,
 		dev_kfree_skb_any(skb);
 		*out_skb = new_skb;
 
+		bd_num = hns3_nic_bd_num(new_skb);
+		if ((skb_is_gso(new_skb) && bd_num > HNS3_MAX_BD_NUM_TSO) ||
+		    (!skb_is_gso(new_skb) && bd_num > HNS3_MAX_BD_NUM_NORMAL))
+			return -ENOMEM;
+
 		u64_stats_update_begin(&ring->syncp);
 		ring->stats.tx_copy++;
 		u64_stats_update_end(&ring->syncp);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
index a76712c3f65c..5b0ee1fe40f1 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
@@ -195,7 +195,8 @@ enum hns3_nic_state {
 #define HNS3_VECTOR_INITED			1
 
 #define HNS3_MAX_BD_SIZE			65535
-#define HNS3_MAX_BD_PER_FRAG			8
+#define HNS3_MAX_BD_NUM_NORMAL			8
+#define HNS3_MAX_BD_NUM_TSO			63
 #define HNS3_MAX_BD_PER_PKT			MAX_SKB_FRAGS
 
 #define HNS3_VECTOR_GL0_OFFSET			0x100

From dec8466001f740868f01a3cb75b21174197be85e Mon Sep 17 00:00:00 2001
From: Yufeng Mo <moyufeng@huawei.com>
Date: Fri, 9 Aug 2019 10:31:15 +0800
Subject: [PATCH 09/12] net: hns3: add function display NCL_CONFIG info

This adds a new function hclge_ncl_config_data_print()
to print the data of NCL_CONFIG, to make the code more
readable. Also, using macro replaces some magic number.

Signed-off-by: Yufeng Mo <moyufeng@huawei.com>
Reviewed-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../hisilicon/hns3/hns3pf/hclge_debugfs.c     | 52 +++++++++++--------
 1 file changed, 30 insertions(+), 22 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
index 933dec53ed8e..f0295d12a1b6 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
@@ -995,6 +995,33 @@ void hclge_dbg_get_m7_stats_info(struct hclge_dev *hdev)
 	kfree(desc_src);
 }
 
+#define HCLGE_CMD_NCL_CONFIG_BD_NUM	5
+
+static void hclge_ncl_config_data_print(struct hclge_dev *hdev,
+					struct hclge_desc *desc, int *offset,
+					int *length)
+{
+#define HCLGE_CMD_DATA_NUM		6
+
+	int i;
+	int j;
+
+	for (i = 0; i < HCLGE_CMD_NCL_CONFIG_BD_NUM; i++) {
+		for (j = 0; j < HCLGE_CMD_DATA_NUM; j++) {
+			if (i == 0 && j == 0)
+				continue;
+
+			dev_info(&hdev->pdev->dev, "0x%04x | 0x%08x\n",
+				 *offset,
+				 le32_to_cpu(desc[i].data[j]));
+			*offset += sizeof(u32);
+			*length -= sizeof(u32);
+			if (*length <= 0)
+				return;
+		}
+	}
+}
+
 /* hclge_dbg_dump_ncl_config: print specified range of NCL_CONFIG file
  * @hdev: pointer to struct hclge_dev
  * @cmd_buf: string that contains offset and length
@@ -1004,17 +1031,13 @@ static void hclge_dbg_dump_ncl_config(struct hclge_dev *hdev,
 {
 #define HCLGE_MAX_NCL_CONFIG_OFFSET	4096
 #define HCLGE_MAX_NCL_CONFIG_LENGTH	(20 + 24 * 4)
-#define HCLGE_CMD_DATA_NUM		6
 
-	struct hclge_desc desc[5];
-	u32 byte_offset;
-	int bd_num = 5;
+	struct hclge_desc desc[HCLGE_CMD_NCL_CONFIG_BD_NUM];
+	int bd_num = HCLGE_CMD_NCL_CONFIG_BD_NUM;
 	int offset;
 	int length;
 	int data0;
 	int ret;
-	int i;
-	int j;
 
 	ret = sscanf(cmd_buf, "%x %x", &offset, &length);
 	if (ret != 2 || offset >= HCLGE_MAX_NCL_CONFIG_OFFSET ||
@@ -1040,22 +1063,7 @@ static void hclge_dbg_dump_ncl_config(struct hclge_dev *hdev,
 		if (ret)
 			return;
 
-		byte_offset = offset;
-		for (i = 0; i < bd_num; i++) {
-			for (j = 0; j < HCLGE_CMD_DATA_NUM; j++) {
-				if (i == 0 && j == 0)
-					continue;
-
-				dev_info(&hdev->pdev->dev, "0x%04x | 0x%08x\n",
-					 byte_offset,
-					 le32_to_cpu(desc[i].data[j]));
-				byte_offset += sizeof(u32);
-				length -= sizeof(u32);
-				if (length <= 0)
-					return;
-			}
-		}
-		offset += HCLGE_MAX_NCL_CONFIG_LENGTH;
+		hclge_ncl_config_data_print(hdev, desc, &offset, &length);
 	}
 }
 

From 615466ce415a8a94d3c2cbd5ac35aa29bd189ebe Mon Sep 17 00:00:00 2001
From: Yufeng Mo <moyufeng@huawei.com>
Date: Fri, 9 Aug 2019 10:31:16 +0800
Subject: [PATCH 10/12] net: hns3: refine MAC pause statistics querying
 function

This patch refines the interface for querying MAC pause
statistics, and adds structure hns3_mac_stats to keep the
count of TX & RX.

Signed-off-by: Yufeng Mo <moyufeng@huawei.com>
Reviewed-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hnae3.h          | 11 +++++++++--
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.c      | 11 ++++-------
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c  | 12 +++++++-----
 3 files changed, 20 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
index a4624db3b5d5..43740ee9d8d8 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
@@ -91,6 +91,11 @@ struct hnae3_queue {
 	u16 rx_desc_num;/* total number of rx desc */
 };
 
+struct hns3_mac_stats {
+	u64 tx_pause_cnt;
+	u64 rx_pause_cnt;
+};
+
 /*hnae3 loop mode*/
 enum hnae3_loop {
 	HNAE3_LOOP_APP,
@@ -298,6 +303,8 @@ struct hnae3_ae_dev {
  *   Remove multicast address from mac table
  * update_stats()
  *   Update Old network device statistics
+ * get_mac_stats()
+ *   get mac pause statistics including tx_cnt and rx_cnt
  * get_ethtool_stats()
  *   Get ethtool network device statistics
  * get_strings()
@@ -426,8 +433,8 @@ struct hnae3_ae_ops {
 	void (*update_stats)(struct hnae3_handle *handle,
 			     struct net_device_stats *net_stats);
 	void (*get_stats)(struct hnae3_handle *handle, u64 *data);
-	void (*get_mac_pause_stats)(struct hnae3_handle *handle, u64 *tx_cnt,
-				    u64 *rx_cnt);
+	void (*get_mac_stats)(struct hnae3_handle *handle,
+			      struct hns3_mac_stats *mac_stats);
 	void (*get_strings)(struct hnae3_handle *handle,
 			    u32 stringset, u8 *data);
 	int (*get_sset_count)(struct hnae3_handle *handle, int stringset);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index df08f9ec0601..1750f80341e7 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -1726,15 +1726,12 @@ static bool hns3_get_tx_timeo_queue_info(struct net_device *ndev)
 	/* When mac received many pause frames continuous, it's unable to send
 	 * packets, which may cause tx timeout
 	 */
-	if (h->ae_algo->ops->update_stats &&
-	    h->ae_algo->ops->get_mac_pause_stats) {
-		u64 tx_pause_cnt, rx_pause_cnt;
+	if (h->ae_algo->ops->get_mac_stats) {
+		struct hns3_mac_stats mac_stats;
 
-		h->ae_algo->ops->update_stats(h, &ndev->stats);
-		h->ae_algo->ops->get_mac_pause_stats(h, &tx_pause_cnt,
-						     &rx_pause_cnt);
+		h->ae_algo->ops->get_mac_stats(h, &mac_stats);
 		netdev_info(ndev, "tx_pause_cnt: %llu, rx_pause_cnt: %llu\n",
-			    tx_pause_cnt, rx_pause_cnt);
+			    mac_stats.tx_pause_cnt, mac_stats.rx_pause_cnt);
 	}
 
 	hw_head = readl_relaxed(tx_ring->tqp->io_base +
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 7d7ab9e66383..13152753c75d 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -750,14 +750,16 @@ static void hclge_get_stats(struct hnae3_handle *handle, u64 *data)
 	p = hclge_tqps_get_stats(handle, p);
 }
 
-static void hclge_get_mac_pause_stat(struct hnae3_handle *handle, u64 *tx_cnt,
-				     u64 *rx_cnt)
+static void hclge_get_mac_stat(struct hnae3_handle *handle,
+			       struct hns3_mac_stats *mac_stats)
 {
 	struct hclge_vport *vport = hclge_get_vport(handle);
 	struct hclge_dev *hdev = vport->back;
 
-	*tx_cnt = hdev->hw_stats.mac_stats.mac_tx_mac_pause_num;
-	*rx_cnt = hdev->hw_stats.mac_stats.mac_rx_mac_pause_num;
+	hclge_update_stats(handle, NULL);
+
+	mac_stats->tx_pause_cnt = hdev->hw_stats.mac_stats.mac_tx_mac_pause_num;
+	mac_stats->rx_pause_cnt = hdev->hw_stats.mac_stats.mac_rx_mac_pause_num;
 }
 
 static int hclge_parse_func_status(struct hclge_dev *hdev,
@@ -9798,7 +9800,7 @@ static const struct hnae3_ae_ops hclge_ops = {
 	.set_mtu = hclge_set_mtu,
 	.reset_queue = hclge_reset_tqp,
 	.get_stats = hclge_get_stats,
-	.get_mac_pause_stats = hclge_get_mac_pause_stat,
+	.get_mac_stats = hclge_get_mac_stat,
 	.update_stats = hclge_update_stats,
 	.get_strings = hclge_get_strings,
 	.get_sset_count = hclge_get_sset_count,

From 427a7bff66c8a9f8cf68384e24093fc4bf7763a1 Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Fri, 9 Aug 2019 10:31:17 +0800
Subject: [PATCH 11/12] net: hns3: add handshake with VF for PF reset

Before PF asserting function reset, it should make sure
that all its VFs have been ready, otherwise, it will cause
some hardware errors.

So this patch adds function hclge_func_reset_sync_vf() to
synchronize VF before asserting PF function reset. For new
firmware which supports command HCLGE_OPC_QUERY_VF_RST_RDY,
we will try to query VFs' ready status within 30 seconds.
And keep the old implementation for compatible with firmware
which does not support this command.

Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Reviewed-by: Yunsheng Lin <linyunsheng@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../hisilicon/hns3/hns3pf/hclge_cmd.h         |  7 +++
 .../hisilicon/hns3/hns3pf/hclge_main.c        | 56 ++++++++++++++++---
 2 files changed, 55 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
index dade20a37d40..29979be9e33a 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
@@ -87,6 +87,7 @@ enum hclge_opcode_type {
 	HCLGE_OPC_QUERY_VF_RSRC		= 0x0024,
 	HCLGE_OPC_GET_CFG_PARAM		= 0x0025,
 	HCLGE_OPC_PF_RST_DONE		= 0x0026,
+	HCLGE_OPC_QUERY_VF_RST_RDY	= 0x0027,
 
 	HCLGE_OPC_STATS_64_BIT		= 0x0030,
 	HCLGE_OPC_STATS_32_BIT		= 0x0031,
@@ -588,6 +589,12 @@ struct hclge_config_mac_mode_cmd {
 	u8 rsv[20];
 };
 
+struct hclge_pf_rst_sync_cmd {
+#define HCLGE_PF_RST_ALL_VF_RDY_B	0
+	u8 all_vf_ready;
+	u8 rsv[23];
+};
+
 #define HCLGE_CFG_SPEED_S		0
 #define HCLGE_CFG_SPEED_M		GENMASK(5, 0)
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 13152753c75d..d207dac1fd5e 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -35,6 +35,9 @@
 #define BUF_RESERVE_PERCENT	90
 
 #define HCLGE_RESET_MAX_FAIL_CNT	5
+#define HCLGE_RESET_SYNC_TIME		100
+#define HCLGE_PF_RESET_SYNC_TIME	20
+#define HCLGE_PF_RESET_SYNC_CNT		1500
 
 /* Get DFX BD number offset */
 #define HCLGE_DFX_BIOS_BD_OFFSET        1
@@ -3184,6 +3187,39 @@ static int hclge_set_all_vf_rst(struct hclge_dev *hdev, bool reset)
 	return 0;
 }
 
+int hclge_func_reset_sync_vf(struct hclge_dev *hdev)
+{
+	struct hclge_pf_rst_sync_cmd *req;
+	struct hclge_desc desc;
+	int cnt = 0;
+	int ret;
+
+	req = (struct hclge_pf_rst_sync_cmd *)desc.data;
+	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_QUERY_VF_RST_RDY, true);
+
+	do {
+		ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+		/* for compatible with old firmware, wait
+		 * 100 ms for VF to stop IO
+		 */
+		if (ret == -EOPNOTSUPP) {
+			msleep(HCLGE_RESET_SYNC_TIME);
+			return 0;
+		} else if (ret) {
+			dev_err(&hdev->pdev->dev, "sync with VF fail %d!\n",
+				ret);
+			return ret;
+		} else if (req->all_vf_ready) {
+			return 0;
+		}
+		msleep(HCLGE_PF_RESET_SYNC_TIME);
+		hclge_cmd_reuse_desc(&desc, true);
+	} while (cnt++ < HCLGE_PF_RESET_SYNC_CNT);
+
+	dev_err(&hdev->pdev->dev, "sync with VF timeout!\n");
+	return -ETIME;
+}
+
 int hclge_func_reset_cmd(struct hclge_dev *hdev, int func_id)
 {
 	struct hclge_desc desc;
@@ -3350,17 +3386,18 @@ static void hclge_reset_handshake(struct hclge_dev *hdev, bool enable)
 
 static int hclge_reset_prepare_wait(struct hclge_dev *hdev)
 {
-#define HCLGE_RESET_SYNC_TIME 100
-
 	u32 reg_val;
 	int ret = 0;
 
 	switch (hdev->reset_type) {
 	case HNAE3_FUNC_RESET:
-		/* There is no mechanism for PF to know if VF has stopped IO
-		 * for now, just wait 100 ms for VF to stop IO
+		/* to confirm whether all running VF is ready
+		 * before request PF reset
 		 */
-		msleep(HCLGE_RESET_SYNC_TIME);
+		ret = hclge_func_reset_sync_vf(hdev);
+		if (ret)
+			return ret;
+
 		ret = hclge_func_reset_cmd(hdev, 0);
 		if (ret) {
 			dev_err(&hdev->pdev->dev,
@@ -3377,10 +3414,13 @@ static int hclge_reset_prepare_wait(struct hclge_dev *hdev)
 		hdev->rst_stats.pf_rst_cnt++;
 		break;
 	case HNAE3_FLR_RESET:
-		/* There is no mechanism for PF to know if VF has stopped IO
-		 * for now, just wait 100 ms for VF to stop IO
+		/* to confirm whether all running VF is ready
+		 * before request PF reset
 		 */
-		msleep(HCLGE_RESET_SYNC_TIME);
+		ret = hclge_func_reset_sync_vf(hdev);
+		if (ret)
+			return ret;
+
 		set_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state);
 		set_bit(HNAE3_FLR_DOWN, &hdev->flr_state);
 		hdev->rst_stats.flr_rst_cnt++;

From eddd98600b382d80cd71e44150eec5de4a0830a4 Mon Sep 17 00:00:00 2001
From: Guojia Liao <liaoguojia@huawei.com>
Date: Fri, 9 Aug 2019 10:31:18 +0800
Subject: [PATCH 12/12] net: hns3: refine some macro definitions

Macro arguments should be enclosed in parentheses, in case of
expression argument, but parentheses of pure number in macro
definition should be removed for simplicity.

Signed-off-by: Guojia Liao <liaoguojia@huawei.com>
Signed-off-by: Guangbin Huang <huangguangbin2@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hnae3.h               | 4 ++--
 drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
index 43740ee9d8d8..6c9fd58c436f 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
@@ -58,10 +58,10 @@
 		BIT(HNAE3_DEV_SUPPORT_ROCE_B))
 
 #define hnae3_dev_roce_supported(hdev) \
-	hnae3_get_bit(hdev->ae_dev->flag, HNAE3_DEV_SUPPORT_ROCE_B)
+	hnae3_get_bit((hdev)->ae_dev->flag, HNAE3_DEV_SUPPORT_ROCE_B)
 
 #define hnae3_dev_dcb_supported(hdev) \
-	hnae3_get_bit(hdev->ae_dev->flag, HNAE3_DEV_SUPPORT_DCB_B)
+	hnae3_get_bit((hdev)->ae_dev->flag, HNAE3_DEV_SUPPORT_DCB_B)
 
 #define hnae3_dev_fd_supported(hdev) \
 	hnae3_get_bit((hdev)->ae_dev->flag, HNAE3_DEV_SUPPORT_FD_B)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
index 4ccf107079eb..bdde3afc286b 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
@@ -125,7 +125,7 @@
 #define HCLGEVF_S_IP_BIT		BIT(3)
 #define HCLGEVF_V_TAG_BIT		BIT(4)
 
-#define HCLGEVF_STATS_TIMER_INTERVAL	(36)
+#define HCLGEVF_STATS_TIMER_INTERVAL	36U
 
 enum hclgevf_evt_cause {
 	HCLGEVF_VECTOR0_EVENT_RST,