[PATCH net-next 00/10] Add support for DCB feature in hns3 driver

[PATCH net-next 00/10] Add support for DCB feature in hns3 driver

[Yunsheng Lin]

The patchset contains some enhancement related to DCB before
adding support for DCB feature.

This patchset depends on the following patchset:
https://patchwork.ozlabs.org/cover/815646/
https://patchwork.ozlabs.org/cover/816145/

High Level Architecture:

       [ tc qdisc ]	       [ lldpad ]
             |                     |
             |                     |
             |                     |
       [ hns3_enet ]        [ hns3_dcbnl ]
             \                    /
                \              /
                   \        /
                 [ hclge_dcb ]
                   /      \
                /            \
             /                  \
     [ hclgc_main ]        [ hclge_tm ]

Current patch-set support following functionality:
1. Use of tc qdisc to configure the tc num and prio_tc_map.
2. Use of lldptool to configure the tc schedule mode, tc
   bandwidth(if schedule mode is ETS), prio_tc_map and
   PFC parameter.

Yunsheng Lin (10):
  net: hns3: Support for dynamically assigning tx buffer to TC
  net: hns3: Add support for dynamically buffer reallocation
  net: hns3: Add support for PFC setting in TM module
  net: hns3: Add support for port shaper setting in TM module
  net: hns3: Add tc-based TM support for sriov enabled port
  net: hns3: Add some interface for the support of DCB feature
  net: hns3: Add hclge_dcb module for the support of DCB feature
  net: hns3: Add dcb netlink interface for the support of DCB feature
  net: hns3: Setting for fc_mode and dcb enable flag in TM module
  net: hns3: Add mqprio support when interacting with network stack

 drivers/net/ethernet/hisilicon/Kconfig             |   9 +
 drivers/net/ethernet/hisilicon/hns3/hnae3.h        |  20 ++
 .../net/ethernet/hisilicon/hns3/hns3pf/Makefile    |   4 +
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h |   6 +
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c | 327 +++++++++++++++++++++
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.h |  21 ++
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.c    | 219 +++++++++-----
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.h    |   8 +-
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c  | 232 +++++++++++++--
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h  |  15 +
 .../ethernet/hisilicon/hns3/hns3pf/hns3_dcbnl.c    | 106 +++++++
 .../net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c | 137 +++++++--
 .../net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.h |   7 +
 13 files changed, 983 insertions(+), 128 deletions(-)
 create mode 100644 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c
 create mode 100644 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.h
 create mode 100644 drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_dcbnl.c

-- 
1.9.1

[PATCH net-next 01/10] net: hns3: Support for dynamically assigning tx buffer to TC

[Yunsheng Lin]

This patch add support of dynamically assigning tx buffer to
TC when the TC is enabled.
It will save buffer for rx direction to avoid packet loss.

Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
---
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h |  1 +
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.c    | 69 ++++++++++++++++++----
 2 files changed, 60 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
index 758cf39..a81c6cb 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
@@ -311,6 +311,7 @@ struct hclge_tc_thrd {
 struct hclge_priv_buf {
 	struct hclge_waterline wl;	/* Waterline for low and high*/
 	u32 buf_size;	/* TC private buffer size */
+	u32 tx_buf_size;
 	u32 enable;	/* Enable TC private buffer or not */
 };
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index d27618b..dfe0fd2 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -1324,23 +1324,28 @@ static int hclge_alloc_vport(struct hclge_dev *hdev)
 	return 0;
 }
 
-static int  hclge_cmd_alloc_tx_buff(struct hclge_dev *hdev, u16 buf_size)
+static int  hclge_cmd_alloc_tx_buff(struct hclge_dev *hdev)
 {
 /* TX buffer size is unit by 128 byte */
 #define HCLGE_BUF_SIZE_UNIT_SHIFT	7
 #define HCLGE_BUF_SIZE_UPDATE_EN_MSK	BIT(15)
 	struct hclge_tx_buff_alloc *req;
+	struct hclge_priv_buf *priv;
 	struct hclge_desc desc;
+	u32 buf_size;
 	int ret;
 	u8 i;
 
 	req = (struct hclge_tx_buff_alloc *)desc.data;
 
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_TX_BUFF_ALLOC, 0);
-	for (i = 0; i < HCLGE_TC_NUM; i++)
+	for (i = 0; i < HCLGE_TC_NUM; i++) {
+		priv = &hdev->priv_buf[i];
+		buf_size = priv->tx_buf_size;
 		req->tx_pkt_buff[i] =
 			cpu_to_le16((buf_size >> HCLGE_BUF_SIZE_UNIT_SHIFT) |
 				     HCLGE_BUF_SIZE_UPDATE_EN_MSK);
+	}
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
 	if (ret) {
@@ -1352,9 +1357,9 @@ static int  hclge_cmd_alloc_tx_buff(struct hclge_dev *hdev, u16 buf_size)
 	return 0;
 }
 
-static int hclge_tx_buffer_alloc(struct hclge_dev *hdev, u32 buf_size)
+static int hclge_tx_buffer_alloc(struct hclge_dev *hdev)
 {
-	int ret = hclge_cmd_alloc_tx_buff(hdev, buf_size);
+	int ret = hclge_cmd_alloc_tx_buff(hdev);
 
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
@@ -1433,6 +1438,18 @@ static u32 hclge_get_rx_priv_buff_alloced(struct hclge_dev *hdev)
 	return rx_priv;
 }
 
+static u32 hclge_get_tx_buff_alloced(struct hclge_dev *hdev)
+{
+	struct hclge_priv_buf *priv;
+	u32 tx_buf = 0, i;
+
+	for (i = 0; i < HCLGE_MAX_TC_NUM; i++) {
+		priv = &hdev->priv_buf[i];
+		tx_buf += priv->tx_buf_size;
+	}
+	return tx_buf;
+}
+
 static bool  hclge_is_rx_buf_ok(struct hclge_dev *hdev, u32 rx_all)
 {
 	u32 shared_buf_min, shared_buf_tc, shared_std;
@@ -1477,18 +1494,44 @@ static bool  hclge_is_rx_buf_ok(struct hclge_dev *hdev, u32 rx_all)
 	return true;
 }
 
+static int hclge_tx_buffer_calc(struct hclge_dev *hdev)
+{
+	struct hclge_priv_buf *priv;
+	u32 i, total_size;
+
+	total_size = hdev->pkt_buf_size;
+
+	/* alloc tx buffer for all enabled tc */
+	for (i = 0; i < HCLGE_MAX_TC_NUM; i++) {
+		priv = &hdev->priv_buf[i];
+
+		if (total_size < HCLGE_DEFAULT_TX_BUF)
+			return -ENOMEM;
+
+		if (hdev->hw_tc_map & BIT(i))
+			priv->tx_buf_size = HCLGE_DEFAULT_TX_BUF;
+		else
+			priv->tx_buf_size = 0;
+
+		total_size -= priv->tx_buf_size;
+	}
+
+	return 0;
+}
+
 /* hclge_rx_buffer_calc: calculate the rx private buffer size for all TCs
  * @hdev: pointer to struct hclge_dev
- * @tx_size: the allocated tx buffer for all TCs
  * @return: 0: calculate sucessful, negative: fail
  */
-int hclge_rx_buffer_calc(struct hclge_dev *hdev, u32 tx_size)
+int hclge_rx_buffer_calc(struct hclge_dev *hdev)
 {
-	u32 rx_all = hdev->pkt_buf_size - tx_size;
+	u32 rx_all = hdev->pkt_buf_size;
 	int no_pfc_priv_num, pfc_priv_num;
 	struct hclge_priv_buf *priv;
 	int i;
 
+	rx_all -= hclge_get_tx_buff_alloced(hdev);
+
 	/* When DCB is not supported, rx private
 	 * buffer is not allocated.
 	 */
@@ -1771,7 +1814,6 @@ static int hclge_common_wl_config(struct hclge_dev *hdev)
 
 int hclge_buffer_alloc(struct hclge_dev *hdev)
 {
-	u32 tx_buf_size = HCLGE_DEFAULT_TX_BUF;
 	int ret;
 
 	hdev->priv_buf = devm_kmalloc_array(&hdev->pdev->dev, HCLGE_MAX_TC_NUM,
@@ -1780,14 +1822,21 @@ int hclge_buffer_alloc(struct hclge_dev *hdev)
 	if (!hdev->priv_buf)
 		return -ENOMEM;
 
-	ret = hclge_tx_buffer_alloc(hdev, tx_buf_size);
+	ret = hclge_tx_buffer_calc(hdev);
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"could not calc tx buffer size for all TCs %d\n", ret);
+		return ret;
+	}
+
+	ret = hclge_tx_buffer_alloc(hdev);
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
 			"could not alloc tx buffers %d\n", ret);
 		return ret;
 	}
 
-	ret = hclge_rx_buffer_calc(hdev, tx_buf_size);
+	ret = hclge_rx_buffer_calc(hdev);
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
 			"could not calc rx priv buffer size for all TCs %d\n",
-- 
1.9.1

Re: [PATCH net-next 01/10] net: hns3: Support for dynamically assigning tx buffer to TC

[David Miller]

From: Yunsheng Lin <linyunsheng@huawei.com>
Date: Thu, 21 Sep 2017 19:21:44 +0800

> @@ -1324,23 +1324,28 @@ static int hclge_alloc_vport(struct hclge_dev *hdev)
>  	return 0;
>  }
>  
> -static int  hclge_cmd_alloc_tx_buff(struct hclge_dev *hdev, u16 buf_size)
> +static int  hclge_cmd_alloc_tx_buff(struct hclge_dev *hdev)
>  {
>  /* TX buffer size is unit by 128 byte */
>  #define HCLGE_BUF_SIZE_UNIT_SHIFT	7
>  #define HCLGE_BUF_SIZE_UPDATE_EN_MSK	BIT(15)
>  	struct hclge_tx_buff_alloc *req;
> +	struct hclge_priv_buf *priv;
>  	struct hclge_desc desc;
> +	u32 buf_size;
>  	int ret;
>  	u8 i;
>  
>  	req = (struct hclge_tx_buff_alloc *)desc.data;
>  
>  	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_TX_BUFF_ALLOC, 0);
> -	for (i = 0; i < HCLGE_TC_NUM; i++)
> +	for (i = 0; i < HCLGE_TC_NUM; i++) {
> +		priv = &hdev->priv_buf[i];
> +		buf_size = priv->tx_buf_size;
>  		req->tx_pkt_buff[i] =
>  			cpu_to_le16((buf_size >> HCLGE_BUF_SIZE_UNIT_SHIFT) |
>  				     HCLGE_BUF_SIZE_UPDATE_EN_MSK);
> +	}
>  
>  	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
>  	if (ret) {

Local variable 'buf_size' is assigned but never used in this function.
And with 'buf_size' removed, 'priv' also becomes unused.

If it gets used in a later patch, add it in that later patch.

You can also declare the variables locally in the basic block of
the for() loop.

Re: [PATCH net-next 01/10] net: hns3: Support for dynamically assigning tx buffer to TC

[Yunsheng Lin]

Hi, David

On 2017/9/22 9:41, David Miller wrote:
> From: Yunsheng Lin <linyunsheng@huawei.com>
> Date: Thu, 21 Sep 2017 19:21:44 +0800
> 
>> @@ -1324,23 +1324,28 @@ static int hclge_alloc_vport(struct hclge_dev *hdev)
>>  	return 0;
>>  }
>>  
>> -static int  hclge_cmd_alloc_tx_buff(struct hclge_dev *hdev, u16 buf_size)
>> +static int  hclge_cmd_alloc_tx_buff(struct hclge_dev *hdev)
>>  {
>>  /* TX buffer size is unit by 128 byte */
>>  #define HCLGE_BUF_SIZE_UNIT_SHIFT	7
>>  #define HCLGE_BUF_SIZE_UPDATE_EN_MSK	BIT(15)
>>  	struct hclge_tx_buff_alloc *req;
>> +	struct hclge_priv_buf *priv;
>>  	struct hclge_desc desc;
>> +	u32 buf_size;
>>  	int ret;
>>  	u8 i;
>>  
>>  	req = (struct hclge_tx_buff_alloc *)desc.data;
>>  
>>  	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_TX_BUFF_ALLOC, 0);
>> -	for (i = 0; i < HCLGE_TC_NUM; i++)
>> +	for (i = 0; i < HCLGE_TC_NUM; i++) {
>> +		priv = &hdev->priv_buf[i];
>> +		buf_size = priv->tx_buf_size;
>>  		req->tx_pkt_buff[i] =
>>  			cpu_to_le16((buf_size >> HCLGE_BUF_SIZE_UNIT_SHIFT) |

buf_size is used here

>>  				     HCLGE_BUF_SIZE_UPDATE_EN_MSK);
>> +	}
>>  
>>  	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
>>  	if (ret) {
> 
> Local variable 'buf_size' is assigned but never used in this function.
> And with 'buf_size' removed, 'priv' also becomes unused.

> 
> If it gets used in a later patch, add it in that later patch.
> 
> You can also declare the variables locally in the basic block of
> the for() loop.

You are right. Will do it if there is more comment coming, thanks for
reviewing .

> 
> .
> 

Re: [PATCH net-next 01/10] net: hns3: Support for dynamically assigning tx buffer to TC

[David Miller]

From: Yunsheng Lin <linyunsheng@huawei.com>
Date: Fri, 22 Sep 2017 09:57:31 +0800

> Hi, David
> 
> On 2017/9/22 9:41, David Miller wrote:
>> From: Yunsheng Lin <linyunsheng@huawei.com>
>> Date: Thu, 21 Sep 2017 19:21:44 +0800
>> 
>>> @@ -1324,23 +1324,28 @@ static int hclge_alloc_vport(struct hclge_dev *hdev)
>>>  	return 0;
>>>  }
>>>  
>>> -static int  hclge_cmd_alloc_tx_buff(struct hclge_dev *hdev, u16 buf_size)
>>> +static int  hclge_cmd_alloc_tx_buff(struct hclge_dev *hdev)
>>>  {
>>>  /* TX buffer size is unit by 128 byte */
>>>  #define HCLGE_BUF_SIZE_UNIT_SHIFT	7
>>>  #define HCLGE_BUF_SIZE_UPDATE_EN_MSK	BIT(15)
>>>  	struct hclge_tx_buff_alloc *req;
>>> +	struct hclge_priv_buf *priv;
>>>  	struct hclge_desc desc;
>>> +	u32 buf_size;
>>>  	int ret;
>>>  	u8 i;
>>>  
>>>  	req = (struct hclge_tx_buff_alloc *)desc.data;
>>>  
>>>  	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_TX_BUFF_ALLOC, 0);
>>> -	for (i = 0; i < HCLGE_TC_NUM; i++)
>>> +	for (i = 0; i < HCLGE_TC_NUM; i++) {
>>> +		priv = &hdev->priv_buf[i];
>>> +		buf_size = priv->tx_buf_size;
>>>  		req->tx_pkt_buff[i] =
>>>  			cpu_to_le16((buf_size >> HCLGE_BUF_SIZE_UNIT_SHIFT) |
> 
> buf_size is used here

My bad, I misread the code.

Thanks.

[PATCH net-next 02/10] net: hns3: Add support for dynamically buffer reallocation

[Yunsheng Lin]

Current buffer allocation can only happen at init, when
doing buffer reallocation after init, care must be taken
care of memory which priv_buf points to.
This patch fixes it by using a dynamic allocated temporary
memory. Because we only do buffer reallocation at init or
when setting up the DCB parameter, and priv_buf is only
used at buffer allocation process, so it is ok to use a
dynamic allocated temporary memory.

Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
---
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h |   5 +
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.c    | 150 +++++++++++----------
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.h    |   2 -
 3 files changed, 87 insertions(+), 70 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
index a81c6cb..6b6d28e 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
@@ -322,6 +322,11 @@ struct hclge_shared_buf {
 	u32 buf_size;
 };
 
+struct hclge_pkt_buf_alloc {
+	struct hclge_priv_buf priv_buf[HCLGE_MAX_TC_NUM];
+	struct hclge_shared_buf s_buf;
+};
+
 #define HCLGE_RX_COM_WL_EN_B	15
 struct hclge_rx_com_wl_buf {
 	__le16 high_wl;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index dfe0fd2..c27b460 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -1324,7 +1324,8 @@ static int hclge_alloc_vport(struct hclge_dev *hdev)
 	return 0;
 }
 
-static int  hclge_cmd_alloc_tx_buff(struct hclge_dev *hdev)
+static int  hclge_cmd_alloc_tx_buff(struct hclge_dev *hdev,
+				    struct hclge_pkt_buf_alloc *buf_alloc)
 {
 /* TX buffer size is unit by 128 byte */
 #define HCLGE_BUF_SIZE_UNIT_SHIFT	7
@@ -1340,7 +1341,7 @@ static int  hclge_cmd_alloc_tx_buff(struct hclge_dev *hdev)
 
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_TX_BUFF_ALLOC, 0);
 	for (i = 0; i < HCLGE_TC_NUM; i++) {
-		priv = &hdev->priv_buf[i];
+		priv = &buf_alloc->priv_buf[i];
 		buf_size = priv->tx_buf_size;
 		req->tx_pkt_buff[i] =
 			cpu_to_le16((buf_size >> HCLGE_BUF_SIZE_UNIT_SHIFT) |
@@ -1357,9 +1358,10 @@ static int  hclge_cmd_alloc_tx_buff(struct hclge_dev *hdev)
 	return 0;
 }
 
-static int hclge_tx_buffer_alloc(struct hclge_dev *hdev)
+static int hclge_tx_buffer_alloc(struct hclge_dev *hdev,
+				 struct hclge_pkt_buf_alloc *buf_alloc)
 {
-	int ret = hclge_cmd_alloc_tx_buff(hdev);
+	int ret = hclge_cmd_alloc_tx_buff(hdev, buf_alloc);
 
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
@@ -1392,13 +1394,14 @@ static int hclge_get_pfc_enalbe_num(struct hclge_dev *hdev)
 }
 
 /* Get the number of pfc enabled TCs, which have private buffer */
-static int hclge_get_pfc_priv_num(struct hclge_dev *hdev)
+static int hclge_get_pfc_priv_num(struct hclge_dev *hdev,
+				  struct hclge_pkt_buf_alloc *buf_alloc)
 {
 	struct hclge_priv_buf *priv;
 	int i, cnt = 0;
 
 	for (i = 0; i < HCLGE_MAX_TC_NUM; i++) {
-		priv = &hdev->priv_buf[i];
+		priv = &buf_alloc->priv_buf[i];
 		if ((hdev->tm_info.hw_pfc_map & BIT(i)) &&
 		    priv->enable)
 			cnt++;
@@ -1408,13 +1411,14 @@ static int hclge_get_pfc_priv_num(struct hclge_dev *hdev)
 }
 
 /* Get the number of pfc disabled TCs, which have private buffer */
-static int hclge_get_no_pfc_priv_num(struct hclge_dev *hdev)
+static int hclge_get_no_pfc_priv_num(struct hclge_dev *hdev,
+				     struct hclge_pkt_buf_alloc *buf_alloc)
 {
 	struct hclge_priv_buf *priv;
 	int i, cnt = 0;
 
 	for (i = 0; i < HCLGE_MAX_TC_NUM; i++) {
-		priv = &hdev->priv_buf[i];
+		priv = &buf_alloc->priv_buf[i];
 		if (hdev->hw_tc_map & BIT(i) &&
 		    !(hdev->tm_info.hw_pfc_map & BIT(i)) &&
 		    priv->enable)
@@ -1424,33 +1428,35 @@ static int hclge_get_no_pfc_priv_num(struct hclge_dev *hdev)
 	return cnt;
 }
 
-static u32 hclge_get_rx_priv_buff_alloced(struct hclge_dev *hdev)
+static u32 hclge_get_rx_priv_buff_alloced(struct hclge_pkt_buf_alloc *buf_alloc)
 {
 	struct hclge_priv_buf *priv;
 	u32 rx_priv = 0;
 	int i;
 
 	for (i = 0; i < HCLGE_MAX_TC_NUM; i++) {
-		priv = &hdev->priv_buf[i];
+		priv = &buf_alloc->priv_buf[i];
 		if (priv->enable)
 			rx_priv += priv->buf_size;
 	}
 	return rx_priv;
 }
 
-static u32 hclge_get_tx_buff_alloced(struct hclge_dev *hdev)
+static u32 hclge_get_tx_buff_alloced(struct hclge_pkt_buf_alloc *buf_alloc)
 {
 	struct hclge_priv_buf *priv;
 	u32 tx_buf = 0, i;
 
 	for (i = 0; i < HCLGE_MAX_TC_NUM; i++) {
-		priv = &hdev->priv_buf[i];
+		priv = &buf_alloc->priv_buf[i];
 		tx_buf += priv->tx_buf_size;
 	}
 	return tx_buf;
 }
 
-static bool  hclge_is_rx_buf_ok(struct hclge_dev *hdev, u32 rx_all)
+static bool  hclge_is_rx_buf_ok(struct hclge_dev *hdev,
+				struct hclge_pkt_buf_alloc *buf_alloc,
+				u32 rx_all)
 {
 	u32 shared_buf_min, shared_buf_tc, shared_std;
 	int tc_num, pfc_enable_num;
@@ -1471,30 +1477,31 @@ static bool  hclge_is_rx_buf_ok(struct hclge_dev *hdev, u32 rx_all)
 			hdev->mps;
 	shared_std = max_t(u32, shared_buf_min, shared_buf_tc);
 
-	rx_priv = hclge_get_rx_priv_buff_alloced(hdev);
+	rx_priv = hclge_get_rx_priv_buff_alloced(buf_alloc);
 	if (rx_all <= rx_priv + shared_std)
 		return false;
 
 	shared_buf = rx_all - rx_priv;
-	hdev->s_buf.buf_size = shared_buf;
-	hdev->s_buf.self.high = shared_buf;
-	hdev->s_buf.self.low =  2 * hdev->mps;
+	buf_alloc->s_buf.buf_size = shared_buf;
+	buf_alloc->s_buf.self.high = shared_buf;
+	buf_alloc->s_buf.self.low =  2 * hdev->mps;
 
 	for (i = 0; i < HCLGE_MAX_TC_NUM; i++) {
 		if ((hdev->hw_tc_map & BIT(i)) &&
 		    (hdev->tm_info.hw_pfc_map & BIT(i))) {
-			hdev->s_buf.tc_thrd[i].low = hdev->mps;
-			hdev->s_buf.tc_thrd[i].high = 2 * hdev->mps;
+			buf_alloc->s_buf.tc_thrd[i].low = hdev->mps;
+			buf_alloc->s_buf.tc_thrd[i].high = 2 * hdev->mps;
 		} else {
-			hdev->s_buf.tc_thrd[i].low = 0;
-			hdev->s_buf.tc_thrd[i].high = hdev->mps;
+			buf_alloc->s_buf.tc_thrd[i].low = 0;
+			buf_alloc->s_buf.tc_thrd[i].high = hdev->mps;
 		}
 	}
 
 	return true;
 }
 
-static int hclge_tx_buffer_calc(struct hclge_dev *hdev)
+static int hclge_tx_buffer_calc(struct hclge_dev *hdev,
+				struct hclge_pkt_buf_alloc *buf_alloc)
 {
 	struct hclge_priv_buf *priv;
 	u32 i, total_size;
@@ -1503,7 +1510,7 @@ static int hclge_tx_buffer_calc(struct hclge_dev *hdev)
 
 	/* alloc tx buffer for all enabled tc */
 	for (i = 0; i < HCLGE_MAX_TC_NUM; i++) {
-		priv = &hdev->priv_buf[i];
+		priv = &buf_alloc->priv_buf[i];
 
 		if (total_size < HCLGE_DEFAULT_TX_BUF)
 			return -ENOMEM;
@@ -1521,22 +1528,24 @@ static int hclge_tx_buffer_calc(struct hclge_dev *hdev)
 
 /* hclge_rx_buffer_calc: calculate the rx private buffer size for all TCs
  * @hdev: pointer to struct hclge_dev
+ * @buf_alloc: pointer to buffer calculation data
  * @return: 0: calculate sucessful, negative: fail
  */
-int hclge_rx_buffer_calc(struct hclge_dev *hdev)
+int hclge_rx_buffer_calc(struct hclge_dev *hdev,
+			 struct hclge_pkt_buf_alloc *buf_alloc)
 {
 	u32 rx_all = hdev->pkt_buf_size;
 	int no_pfc_priv_num, pfc_priv_num;
 	struct hclge_priv_buf *priv;
 	int i;
 
-	rx_all -= hclge_get_tx_buff_alloced(hdev);
+	rx_all -= hclge_get_tx_buff_alloced(buf_alloc);
 
 	/* When DCB is not supported, rx private
 	 * buffer is not allocated.
 	 */
 	if (!hnae3_dev_dcb_supported(hdev)) {
-		if (!hclge_is_rx_buf_ok(hdev, rx_all))
+		if (!hclge_is_rx_buf_ok(hdev, buf_alloc, rx_all))
 			return -ENOMEM;
 
 		return 0;
@@ -1544,7 +1553,7 @@ int hclge_rx_buffer_calc(struct hclge_dev *hdev)
 
 	/* step 1, try to alloc private buffer for all enabled tc */
 	for (i = 0; i < HCLGE_MAX_TC_NUM; i++) {
-		priv = &hdev->priv_buf[i];
+		priv = &buf_alloc->priv_buf[i];
 		if (hdev->hw_tc_map & BIT(i)) {
 			priv->enable = 1;
 			if (hdev->tm_info.hw_pfc_map & BIT(i)) {
@@ -1565,14 +1574,14 @@ int hclge_rx_buffer_calc(struct hclge_dev *hdev)
 		}
 	}
 
-	if (hclge_is_rx_buf_ok(hdev, rx_all))
+	if (hclge_is_rx_buf_ok(hdev, buf_alloc, rx_all))
 		return 0;
 
 	/* step 2, try to decrease the buffer size of
 	 * no pfc TC's private buffer
 	 */
 	for (i = 0; i < HCLGE_MAX_TC_NUM; i++) {
-		priv = &hdev->priv_buf[i];
+		priv = &buf_alloc->priv_buf[i];
 
 		priv->enable = 0;
 		priv->wl.low = 0;
@@ -1595,18 +1604,18 @@ int hclge_rx_buffer_calc(struct hclge_dev *hdev)
 		}
 	}
 
-	if (hclge_is_rx_buf_ok(hdev, rx_all))
+	if (hclge_is_rx_buf_ok(hdev, buf_alloc, rx_all))
 		return 0;
 
 	/* step 3, try to reduce the number of pfc disabled TCs,
 	 * which have private buffer
 	 */
 	/* get the total no pfc enable TC number, which have private buffer */
-	no_pfc_priv_num = hclge_get_no_pfc_priv_num(hdev);
+	no_pfc_priv_num = hclge_get_no_pfc_priv_num(hdev, buf_alloc);
 
 	/* let the last to be cleared first */
 	for (i = HCLGE_MAX_TC_NUM - 1; i >= 0; i--) {
-		priv = &hdev->priv_buf[i];
+		priv = &buf_alloc->priv_buf[i];
 
 		if (hdev->hw_tc_map & BIT(i) &&
 		    !(hdev->tm_info.hw_pfc_map & BIT(i))) {
@@ -1618,22 +1627,22 @@ int hclge_rx_buffer_calc(struct hclge_dev *hdev)
 			no_pfc_priv_num--;
 		}
 
-		if (hclge_is_rx_buf_ok(hdev, rx_all) ||
+		if (hclge_is_rx_buf_ok(hdev, buf_alloc, rx_all) ||
 		    no_pfc_priv_num == 0)
 			break;
 	}
 
-	if (hclge_is_rx_buf_ok(hdev, rx_all))
+	if (hclge_is_rx_buf_ok(hdev, buf_alloc, rx_all))
 		return 0;
 
 	/* step 4, try to reduce the number of pfc enabled TCs
 	 * which have private buffer.
 	 */
-	pfc_priv_num = hclge_get_pfc_priv_num(hdev);
+	pfc_priv_num = hclge_get_pfc_priv_num(hdev, buf_alloc);
 
 	/* let the last to be cleared first */
 	for (i = HCLGE_MAX_TC_NUM - 1; i >= 0; i--) {
-		priv = &hdev->priv_buf[i];
+		priv = &buf_alloc->priv_buf[i];
 
 		if (hdev->hw_tc_map & BIT(i) &&
 		    hdev->tm_info.hw_pfc_map & BIT(i)) {
@@ -1645,17 +1654,18 @@ int hclge_rx_buffer_calc(struct hclge_dev *hdev)
 			pfc_priv_num--;
 		}
 
-		if (hclge_is_rx_buf_ok(hdev, rx_all) ||
+		if (hclge_is_rx_buf_ok(hdev, buf_alloc, rx_all) ||
 		    pfc_priv_num == 0)
 			break;
 	}
-	if (hclge_is_rx_buf_ok(hdev, rx_all))
+	if (hclge_is_rx_buf_ok(hdev, buf_alloc, rx_all))
 		return 0;
 
 	return -ENOMEM;
 }
 
-static int hclge_rx_priv_buf_alloc(struct hclge_dev *hdev)
+static int hclge_rx_priv_buf_alloc(struct hclge_dev *hdev,
+				   struct hclge_pkt_buf_alloc *buf_alloc)
 {
 	struct hclge_rx_priv_buff *req;
 	struct hclge_desc desc;
@@ -1667,7 +1677,7 @@ static int hclge_rx_priv_buf_alloc(struct hclge_dev *hdev)
 
 	/* Alloc private buffer TCs */
 	for (i = 0; i < HCLGE_MAX_TC_NUM; i++) {
-		struct hclge_priv_buf *priv = &hdev->priv_buf[i];
+		struct hclge_priv_buf *priv = &buf_alloc->priv_buf[i];
 
 		req->buf_num[i] =
 			cpu_to_le16(priv->buf_size >> HCLGE_BUF_UNIT_S);
@@ -1676,7 +1686,7 @@ static int hclge_rx_priv_buf_alloc(struct hclge_dev *hdev)
 	}
 
 	req->shared_buf =
-		cpu_to_le16((hdev->s_buf.buf_size >> HCLGE_BUF_UNIT_S) |
+		cpu_to_le16((buf_alloc->s_buf.buf_size >> HCLGE_BUF_UNIT_S) |
 			    (1 << HCLGE_TC0_PRI_BUF_EN_B));
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
@@ -1691,7 +1701,8 @@ static int hclge_rx_priv_buf_alloc(struct hclge_dev *hdev)
 
 #define HCLGE_PRIV_ENABLE(a) ((a) > 0 ? 1 : 0)
 
-static int hclge_rx_priv_wl_config(struct hclge_dev *hdev)
+static int hclge_rx_priv_wl_config(struct hclge_dev *hdev,
+				   struct hclge_pkt_buf_alloc *buf_alloc)
 {
 	struct hclge_rx_priv_wl_buf *req;
 	struct hclge_priv_buf *priv;
@@ -1711,7 +1722,9 @@ static int hclge_rx_priv_wl_config(struct hclge_dev *hdev)
 			desc[i].flag &= ~cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
 
 		for (j = 0; j < HCLGE_TC_NUM_ONE_DESC; j++) {
-			priv = &hdev->priv_buf[i * HCLGE_TC_NUM_ONE_DESC + j];
+			u32 idx = i * HCLGE_TC_NUM_ONE_DESC + j;
+
+			priv = &buf_alloc->priv_buf[idx];
 			req->tc_wl[j].high =
 				cpu_to_le16(priv->wl.high >> HCLGE_BUF_UNIT_S);
 			req->tc_wl[j].high |=
@@ -1736,9 +1749,10 @@ static int hclge_rx_priv_wl_config(struct hclge_dev *hdev)
 	return 0;
 }
 
-static int hclge_common_thrd_config(struct hclge_dev *hdev)
+static int hclge_common_thrd_config(struct hclge_dev *hdev,
+				    struct hclge_pkt_buf_alloc *buf_alloc)
 {
-	struct hclge_shared_buf *s_buf = &hdev->s_buf;
+	struct hclge_shared_buf *s_buf = &buf_alloc->s_buf;
 	struct hclge_rx_com_thrd *req;
 	struct hclge_desc desc[2];
 	struct hclge_tc_thrd *tc;
@@ -1782,9 +1796,10 @@ static int hclge_common_thrd_config(struct hclge_dev *hdev)
 	return 0;
 }
 
-static int hclge_common_wl_config(struct hclge_dev *hdev)
+static int hclge_common_wl_config(struct hclge_dev *hdev,
+				  struct hclge_pkt_buf_alloc *buf_alloc)
 {
-	struct hclge_shared_buf *buf = &hdev->s_buf;
+	struct hclge_shared_buf *buf = &buf_alloc->s_buf;
 	struct hclge_rx_com_wl *req;
 	struct hclge_desc desc;
 	int ret;
@@ -1814,69 +1829,68 @@ static int hclge_common_wl_config(struct hclge_dev *hdev)
 
 int hclge_buffer_alloc(struct hclge_dev *hdev)
 {
+	struct hclge_pkt_buf_alloc *pkt_buf;
 	int ret;
 
-	hdev->priv_buf = devm_kmalloc_array(&hdev->pdev->dev, HCLGE_MAX_TC_NUM,
-					    sizeof(struct hclge_priv_buf),
-					    GFP_KERNEL | __GFP_ZERO);
-	if (!hdev->priv_buf)
+	pkt_buf = kzalloc(sizeof(*pkt_buf), GFP_KERNEL);
+	if (!pkt_buf)
 		return -ENOMEM;
 
-	ret = hclge_tx_buffer_calc(hdev);
+	ret = hclge_tx_buffer_calc(hdev, pkt_buf);
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
 			"could not calc tx buffer size for all TCs %d\n", ret);
-		return ret;
+		goto out;
 	}
 
-	ret = hclge_tx_buffer_alloc(hdev);
+	ret = hclge_tx_buffer_alloc(hdev, pkt_buf);
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
 			"could not alloc tx buffers %d\n", ret);
-		return ret;
+		goto out;
 	}
 
-	ret = hclge_rx_buffer_calc(hdev);
+	ret = hclge_rx_buffer_calc(hdev, pkt_buf);
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
 			"could not calc rx priv buffer size for all TCs %d\n",
 			ret);
-		return ret;
+		goto out;
 	}
 
-	ret = hclge_rx_priv_buf_alloc(hdev);
+	ret = hclge_rx_priv_buf_alloc(hdev, pkt_buf);
 	if (ret) {
 		dev_err(&hdev->pdev->dev, "could not alloc rx priv buffer %d\n",
 			ret);
-		return ret;
+		goto out;
 	}
 
 	if (hnae3_dev_dcb_supported(hdev)) {
-		ret = hclge_rx_priv_wl_config(hdev);
+		ret = hclge_rx_priv_wl_config(hdev, pkt_buf);
 		if (ret) {
 			dev_err(&hdev->pdev->dev,
 				"could not configure rx private waterline %d\n",
 				ret);
-			return ret;
+			goto out;
 		}
 
-		ret = hclge_common_thrd_config(hdev);
+		ret = hclge_common_thrd_config(hdev, pkt_buf);
 		if (ret) {
 			dev_err(&hdev->pdev->dev,
 				"could not configure common threshold %d\n",
 				ret);
-			return ret;
+			goto out;
 		}
 	}
 
-	ret = hclge_common_wl_config(hdev);
-	if (ret) {
+	ret = hclge_common_wl_config(hdev, pkt_buf);
+	if (ret)
 		dev_err(&hdev->pdev->dev,
 			"could not configure common waterline %d\n", ret);
-		return ret;
-	}
 
-	return 0;
+out:
+	kfree(pkt_buf);
+	return ret;
 }
 
 static int hclge_init_roce_base_info(struct hclge_vport *vport)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index 9fcfd93..4fc36f0 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -463,8 +463,6 @@ struct hclge_dev {
 
 	u32 pkt_buf_size; /* Total pf buf size for tx/rx */
 	u32 mps; /* Max packet size */
-	struct hclge_priv_buf *priv_buf;
-	struct hclge_shared_buf s_buf;
 
 	enum hclge_mta_dmac_sel_type mta_mac_sel_type;
 	bool enable_mta; /* Mutilcast filter enable */
-- 
1.9.1

[PATCH net-next 03/10] net: hns3: Add support for PFC setting in TM module

[Yunsheng Lin]

This patch add a pfc_pause_en cmd, and use it to configure
PFC option according to fc_mode in hdev->tm_info.

Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
---
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c  | 68 ++++++++++++++++++++--
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h  |  5 ++
 2 files changed, 68 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
index 73a75d7..0b4b5d9 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
@@ -124,6 +124,20 @@ static int hclge_mac_pause_en_cfg(struct hclge_dev *hdev, bool tx, bool rx)
 	return hclge_cmd_send(&hdev->hw, &desc, 1);
 }
 
+static int hclge_pfc_pause_en_cfg(struct hclge_dev *hdev, u8 tx_rx_bitmap,
+				  u8 pfc_bitmap)
+{
+	struct hclge_desc desc;
+	struct hclge_pfc_en_cmd *pfc = (struct hclge_pfc_en_cmd *)&desc.data;
+
+	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CFG_PFC_PAUSE_EN, false);
+
+	pfc->tx_rx_en_bitmap = tx_rx_bitmap;
+	pfc->pri_en_bitmap = pfc_bitmap;
+
+	return hclge_cmd_send(&hdev->hw, &desc, 1);
+}
+
 static int hclge_fill_pri_array(struct hclge_dev *hdev, u8 *pri, u8 pri_id)
 {
 	u8 tc;
@@ -969,20 +983,64 @@ static int hclge_tm_schd_setup_hw(struct hclge_dev *hdev)
 	return hclge_tm_schd_mode_hw(hdev);
 }
 
+static int hclge_pfc_setup_hw(struct hclge_dev *hdev)
+{
+	u8 enable_bitmap = 0;
+
+	if (hdev->tm_info.fc_mode == HCLGE_FC_PFC)
+		enable_bitmap = HCLGE_TX_MAC_PAUSE_EN_MSK |
+				HCLGE_RX_MAC_PAUSE_EN_MSK;
+
+	return hclge_pfc_pause_en_cfg(hdev, enable_bitmap,
+				      hdev->tm_info.hw_pfc_map);
+}
+
+static int hclge_mac_pause_setup_hw(struct hclge_dev *hdev)
+{
+	bool tx_en, rx_en;
+
+	switch (hdev->tm_info.fc_mode) {
+	case HCLGE_FC_NONE:
+		tx_en = false;
+		rx_en = false;
+		break;
+	case HCLGE_FC_RX_PAUSE:
+		tx_en = false;
+		rx_en = true;
+		break;
+	case HCLGE_FC_TX_PAUSE:
+		tx_en = true;
+		rx_en = false;
+		break;
+	case HCLGE_FC_FULL:
+		tx_en = true;
+		rx_en = true;
+		break;
+	default:
+		tx_en = true;
+		rx_en = true;
+	}
+
+	return hclge_mac_pause_en_cfg(hdev, tx_en, rx_en);
+}
+
 int hclge_pause_setup_hw(struct hclge_dev *hdev)
 {
-	bool en = hdev->tm_info.fc_mode != HCLGE_FC_PFC;
 	int ret;
 	u8 i;
 
-	ret = hclge_mac_pause_en_cfg(hdev, en, en);
-	if (ret)
-		return ret;
+	if (hdev->tm_info.fc_mode != HCLGE_FC_PFC)
+		return hclge_mac_pause_setup_hw(hdev);
 
-	/* Only DCB-supported dev supports qset back pressure setting */
+	/* Only DCB-supported dev supports qset back pressure and pfc cmd */
 	if (!hnae3_dev_dcb_supported(hdev))
 		return 0;
 
+	/* When MAC is GE Mode, hdev does not support pfc setting */
+	ret = hclge_pfc_setup_hw(hdev);
+	if (ret)
+		dev_warn(&hdev->pdev->dev, "set pfc pause failed:%d\n", ret);
+
 	for (i = 0; i < hdev->tm_info.num_tc; i++) {
 		ret = hclge_tm_qs_bp_cfg(hdev, i);
 		if (ret)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h
index 85158b0..8ecd83c 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h
@@ -94,6 +94,11 @@ struct hclge_bp_to_qs_map_cmd {
 	u32 rsvd1;
 };
 
+struct hclge_pfc_en_cmd {
+	u8 tx_rx_en_bitmap;
+	u8 pri_en_bitmap;
+};
+
 #define hclge_tm_set_field(dest, string, val) \
 			hnae_set_field((dest), (HCLGE_TM_SHAP_##string##_MSK), \
 				       (HCLGE_TM_SHAP_##string##_LSH), val)
-- 
1.9.1

[PATCH net-next 04/10] net: hns3: Add support for port shaper setting in TM module

[Yunsheng Lin]

This patch add a tm_port_shaper cmd and set port shaper
to HCLGE_ETHER_MAX_RATE on TM initialization process.

Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
---
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c  | 33 ++++++++++++++++++++++
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h  |  4 +++
 2 files changed, 37 insertions(+)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
index 0b4b5d9..33090d0 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
@@ -301,6 +301,35 @@ static int hclge_tm_pg_shapping_cfg(struct hclge_dev *hdev,
 	return hclge_cmd_send(&hdev->hw, &desc, 1);
 }
 
+static int hclge_tm_port_shaper_cfg(struct hclge_dev *hdev)
+{
+	struct hclge_port_shapping_cmd *shap_cfg_cmd;
+	struct hclge_desc desc;
+	u8 ir_u, ir_b, ir_s;
+	int ret;
+
+	ret = hclge_shaper_para_calc(HCLGE_ETHER_MAX_RATE,
+				     HCLGE_SHAPER_LVL_PORT,
+				     &ir_b, &ir_u, &ir_s);
+	if (ret)
+		return ret;
+
+	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_TM_PORT_SHAPPING, false);
+	shap_cfg_cmd = (struct hclge_port_shapping_cmd *)desc.data;
+
+	hclge_tm_set_field(shap_cfg_cmd->port_shapping_para, IR_B, ir_b);
+	hclge_tm_set_field(shap_cfg_cmd->port_shapping_para, IR_U, ir_u);
+	hclge_tm_set_field(shap_cfg_cmd->port_shapping_para, IR_S, ir_s);
+	hclge_tm_set_field(shap_cfg_cmd->port_shapping_para,
+			   BS_B, HCLGE_SHAPER_BS_U_DEF);
+	hclge_tm_set_field(shap_cfg_cmd->port_shapping_para,
+			   BS_S, HCLGE_SHAPER_BS_S_DEF);
+	shap_cfg_cmd->port_shapping_para =
+				cpu_to_le32(shap_cfg_cmd->port_shapping_para);
+
+	return hclge_cmd_send(&hdev->hw, &desc, 1);
+}
+
 static int hclge_tm_pri_shapping_cfg(struct hclge_dev *hdev,
 				     enum hclge_shap_bucket bucket, u8 pri_id,
 				     u8 ir_b, u8 ir_u, u8 ir_s,
@@ -864,6 +893,10 @@ static int hclge_tm_shaper_cfg(struct hclge_dev *hdev)
 {
 	int ret;
 
+	ret = hclge_tm_port_shaper_cfg(hdev);
+	if (ret)
+		return ret;
+
 	ret = hclge_tm_pg_shaper_cfg(hdev);
 	if (ret)
 		return ret;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h
index 8ecd83c..19a01e4 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h
@@ -99,6 +99,10 @@ struct hclge_pfc_en_cmd {
 	u8 pri_en_bitmap;
 };
 
+struct hclge_port_shapping_cmd {
+	__le32 port_shapping_para;
+};
+
 #define hclge_tm_set_field(dest, string, val) \
 			hnae_set_field((dest), (HCLGE_TM_SHAP_##string##_MSK), \
 				       (HCLGE_TM_SHAP_##string##_LSH), val)
-- 
1.9.1

[PATCH net-next 05/10] net: hns3: Add tc-based TM support for sriov enabled port

[Yunsheng Lin]

When sriov is enabled and TM is in tc-based mode, vf's TM
parameters is not set in TM initialization process.
This patch add the tc_based TM support for sriov enabled
using the information in vport struct.

Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
---
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c  | 49 ++++++++++++++--------
 1 file changed, 31 insertions(+), 18 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
index 33090d0..2bc7d63c 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
@@ -389,13 +389,13 @@ static int hclge_tm_pri_schd_mode_cfg(struct hclge_dev *hdev, u8 pri_id)
 	return hclge_cmd_send(&hdev->hw, &desc, 1);
 }
 
-static int hclge_tm_qs_schd_mode_cfg(struct hclge_dev *hdev, u16 qs_id)
+static int hclge_tm_qs_schd_mode_cfg(struct hclge_dev *hdev, u16 qs_id, u8 mode)
 {
 	struct hclge_desc desc;
 
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_TM_QS_SCH_MODE_CFG, false);
 
-	if (hdev->tm_info.tc_info[qs_id].tc_sch_mode == HCLGE_SCH_MODE_DWRR)
+	if (mode == HCLGE_SCH_MODE_DWRR)
 		desc.data[1] = cpu_to_le32(HCLGE_TM_TX_SCHD_DWRR_MSK);
 	else
 		desc.data[1] = 0;
@@ -639,17 +639,18 @@ static int hclge_tm_pri_q_qs_cfg(struct hclge_dev *hdev)
 {
 	struct hclge_vport *vport = hdev->vport;
 	int ret;
-	u32 i;
+	u32 i, k;
 
 	if (hdev->tx_sch_mode == HCLGE_FLAG_TC_BASE_SCH_MODE) {
 		/* Cfg qs -> pri mapping, one by one mapping */
-		for (i = 0; i < hdev->tm_info.num_tc; i++) {
-			ret = hclge_tm_qs_to_pri_map_cfg(hdev, i, i);
-			if (ret)
-				return ret;
-		}
+		for (k = 0; k < hdev->num_alloc_vport; k++)
+			for (i = 0; i < hdev->tm_info.num_tc; i++) {
+				ret = hclge_tm_qs_to_pri_map_cfg(
+					hdev, vport[k].qs_offset + i, i);
+				if (ret)
+					return ret;
+			}
 	} else if (hdev->tx_sch_mode == HCLGE_FLAG_VNET_BASE_SCH_MODE) {
-		int k;
 		/* Cfg qs -> pri mapping,  qs = tc, pri = vf, 8 qs -> 1 pri */
 		for (k = 0; k < hdev->num_alloc_vport; k++)
 			for (i = 0; i < HNAE3_MAX_TC; i++) {
@@ -798,10 +799,11 @@ static int hclge_tm_pri_shaper_cfg(struct hclge_dev *hdev)
 
 static int hclge_tm_pri_tc_base_dwrr_cfg(struct hclge_dev *hdev)
 {
+	struct hclge_vport *vport = hdev->vport;
 	struct hclge_pg_info *pg_info;
 	u8 dwrr;
 	int ret;
-	u32 i;
+	u32 i, k;
 
 	for (i = 0; i < hdev->tm_info.num_tc; i++) {
 		pg_info =
@@ -812,9 +814,13 @@ static int hclge_tm_pri_tc_base_dwrr_cfg(struct hclge_dev *hdev)
 		if (ret)
 			return ret;
 
-		ret = hclge_tm_qs_weight_cfg(hdev, i, dwrr);
-		if (ret)
-			return ret;
+		for (k = 0; k < hdev->num_alloc_vport; k++) {
+			ret = hclge_tm_qs_weight_cfg(
+				hdev, vport[k].qs_offset + i,
+				vport[k].dwrr);
+			if (ret)
+				return ret;
+		}
 	}
 
 	return 0;
@@ -945,7 +951,10 @@ static int hclge_tm_schd_mode_vnet_base_cfg(struct hclge_vport *vport)
 		return ret;
 
 	for (i = 0; i < kinfo->num_tc; i++) {
-		ret = hclge_tm_qs_schd_mode_cfg(hdev, vport->qs_offset + i);
+		u8 sch_mode = hdev->tm_info.tc_info[i].tc_sch_mode;
+
+		ret = hclge_tm_qs_schd_mode_cfg(hdev, vport->qs_offset + i,
+						sch_mode);
 		if (ret)
 			return ret;
 	}
@@ -957,7 +966,7 @@ static int hclge_tm_lvl34_schd_mode_cfg(struct hclge_dev *hdev)
 {
 	struct hclge_vport *vport = hdev->vport;
 	int ret;
-	u8 i;
+	u8 i, k;
 
 	if (hdev->tx_sch_mode == HCLGE_FLAG_TC_BASE_SCH_MODE) {
 		for (i = 0; i < hdev->tm_info.num_tc; i++) {
@@ -965,9 +974,13 @@ static int hclge_tm_lvl34_schd_mode_cfg(struct hclge_dev *hdev)
 			if (ret)
 				return ret;
 
-			ret = hclge_tm_qs_schd_mode_cfg(hdev, i);
-			if (ret)
-				return ret;
+			for (k = 0; k < hdev->num_alloc_vport; k++) {
+				ret = hclge_tm_qs_schd_mode_cfg(
+					hdev, vport[k].qs_offset + i,
+					HCLGE_SCH_MODE_DWRR);
+				if (ret)
+					return ret;
+			}
 		}
 	} else {
 		for (i = 0; i < hdev->num_alloc_vport; i++) {
-- 
1.9.1

[PATCH net-next 06/10] net: hns3: Add some interface for the support of DCB feature

[Yunsheng Lin]

This patch add some interface and export some interface from
hclge_tm and hclgc_main to support the upcoming DCB feature.

Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
---
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.c    |  3 +-
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.h    |  3 ++
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c  | 48 ++++++++++++++++++++--
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h  |  6 +++
 4 files changed, 55 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index c27b460..49a11d5 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -30,7 +30,6 @@
 #define HCLGE_64BIT_STATS_FIELD_OFF(f) (offsetof(struct hclge_64_bit_stats, f))
 #define HCLGE_32BIT_STATS_FIELD_OFF(f) (offsetof(struct hclge_32_bit_stats, f))
 
-static int hclge_rss_init_hw(struct hclge_dev *hdev);
 static int hclge_set_mta_filter_mode(struct hclge_dev *hdev,
 				     enum hclge_mta_dmac_sel_type mta_mac_sel,
 				     bool enable);
@@ -2660,7 +2659,7 @@ static int hclge_get_tc_size(struct hnae3_handle *handle)
 	return hdev->rss_size_max;
 }
 
-static int hclge_rss_init_hw(struct hclge_dev *hdev)
+int hclge_rss_init_hw(struct hclge_dev *hdev)
 {
 	const  u8 hfunc = HCLGE_RSS_HASH_ALGO_TOEPLITZ;
 	struct hclge_vport *vport = hdev->vport;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index 4fc36f0..394b587 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -515,4 +515,7 @@ static inline int hclge_get_queue_id(struct hnae3_queue *queue)
 int hclge_cfg_mac_speed_dup(struct hclge_dev *hdev, int speed, u8 duplex);
 int hclge_set_vf_vlan_common(struct hclge_dev *vport, int vfid,
 			     bool is_kill, u16 vlan, u8 qos, __be16 proto);
+
+int hclge_buffer_alloc(struct hclge_dev *hdev);
+int hclge_rss_init_hw(struct hclge_dev *hdev);
 #endif
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
index 2bc7d63c..e158e66 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
@@ -884,10 +884,14 @@ static int hclge_tm_pri_dwrr_cfg(struct hclge_dev *hdev)
 	return 0;
 }
 
-static int hclge_tm_map_cfg(struct hclge_dev *hdev)
+int hclge_tm_map_cfg(struct hclge_dev *hdev)
 {
 	int ret;
 
+	ret = hclge_up_to_tc_map(hdev);
+	if (ret)
+		return ret;
+
 	ret = hclge_tm_pg_to_pri_map(hdev);
 	if (ret)
 		return ret;
@@ -995,7 +999,7 @@ static int hclge_tm_lvl34_schd_mode_cfg(struct hclge_dev *hdev)
 	return 0;
 }
 
-static int hclge_tm_schd_mode_hw(struct hclge_dev *hdev)
+int hclge_tm_schd_mode_hw(struct hclge_dev *hdev)
 {
 	int ret;
 
@@ -1093,7 +1097,45 @@ int hclge_pause_setup_hw(struct hclge_dev *hdev)
 			return ret;
 	}
 
-	return hclge_up_to_tc_map(hdev);
+	return 0;
+}
+
+int hclge_tm_prio_tc_info_update(struct hclge_dev *hdev, u8 *prio_tc)
+{
+	struct hclge_vport *vport = hdev->vport;
+	struct hnae3_knic_private_info *kinfo;
+	u32 i, k;
+
+	for (i = 0; i < HNAE3_MAX_USER_PRIO; i++) {
+		if (prio_tc[i] >= hdev->tm_info.num_tc)
+			return -EINVAL;
+		hdev->tm_info.prio_tc[i] = prio_tc[i];
+
+		for (k = 0;  k < hdev->num_alloc_vport; k++) {
+			kinfo = &vport[k].nic.kinfo;
+			kinfo->prio_tc[i] = prio_tc[i];
+		}
+	}
+	return 0;
+}
+
+void hclge_tm_schd_info_update(struct hclge_dev *hdev, u8 num_tc)
+{
+	u8 i, bit_map = 0;
+
+	hdev->tm_info.num_tc = num_tc;
+
+	for (i = 0; i < hdev->tm_info.num_tc; i++)
+		bit_map |= BIT(i);
+
+	if (!bit_map) {
+		bit_map = 1;
+		hdev->tm_info.num_tc = 1;
+	}
+
+	hdev->hw_tc_map = bit_map;
+
+	hclge_tm_schd_info_init(hdev);
 }
 
 int hclge_tm_init_hw(struct hclge_dev *hdev)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h
index 19a01e4..bf59961 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h
@@ -112,4 +112,10 @@ struct hclge_port_shapping_cmd {
 
 int hclge_tm_schd_init(struct hclge_dev *hdev);
 int hclge_pause_setup_hw(struct hclge_dev *hdev);
+int hclge_tm_schd_mode_hw(struct hclge_dev *hdev);
+int hclge_tm_prio_tc_info_update(struct hclge_dev *hdev, u8 *prio_tc);
+void hclge_tm_schd_info_update(struct hclge_dev *hdev, u8 num_tc);
+int hclge_tm_dwrr_cfg(struct hclge_dev *hdev);
+int hclge_tm_map_cfg(struct hclge_dev *hdev);
+int hclge_tm_init_hw(struct hclge_dev *hdev);
 #endif
-- 
1.9.1

[PATCH net-next 07/10] net: hns3: Add hclge_dcb module for the support of DCB feature

[Yunsheng Lin]

The hclge_dcb module calls the interface from hclge_main/tm
and provide interface for the dcb netlink interface.

This patch also update Makefiles required to build the DCB
supported code in HNS3 Ethernet driver and update the existing
Kconfig file in the hisilicon folder.

Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
---
 drivers/net/ethernet/hisilicon/Kconfig             |   9 +
 drivers/net/ethernet/hisilicon/hns3/hnae3.h        |  20 ++
 .../net/ethernet/hisilicon/hns3/hns3pf/Makefile    |   2 +
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c | 327 +++++++++++++++++++++
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.h |  21 ++
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.c    |  25 +-
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.h    |   3 +
 7 files changed, 401 insertions(+), 6 deletions(-)
 create mode 100644 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c
 create mode 100644 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.h

diff --git a/drivers/net/ethernet/hisilicon/Kconfig b/drivers/net/ethernet/hisilicon/Kconfig
index 91c7bdb..9d7cb03 100644
--- a/drivers/net/ethernet/hisilicon/Kconfig
+++ b/drivers/net/ethernet/hisilicon/Kconfig
@@ -103,4 +103,13 @@ config HNS3_ENET
 	  family of SoCs. This module depends upon HNAE3 driver to access the HNAE3
 	  devices and their associated operations.
 
+config HNS3_DCB
+	bool "Hisilicon HNS3 Data Center Bridge Support"
+	default n
+	depends on HNS3 && HNS3_HCLGE && DCB
+	---help---
+	  Say Y here if you want to use Data Center Bridging (DCB) in the HNS3 driver.
+
+	  If unsure, say N.
+
 endif # NET_VENDOR_HISILICON
diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
index 1a01cad..5a6fa53 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
@@ -28,6 +28,7 @@
  */
 
 #include <linux/acpi.h>
+#include <linux/dcbnl.h>
 #include <linux/delay.h>
 #include <linux/device.h>
 #include <linux/module.h>
@@ -131,6 +132,7 @@ struct hnae3_client_ops {
 	int (*init_instance)(struct hnae3_handle *handle);
 	void (*uninit_instance)(struct hnae3_handle *handle, bool reset);
 	void (*link_status_change)(struct hnae3_handle *handle, bool state);
+	int (*setup_tc)(struct hnae3_handle *handle, u8 tc);
 };
 
 #define HNAE3_CLIENT_NAME_LENGTH 16
@@ -363,6 +365,23 @@ struct hnae3_ae_ops {
 				  u16 vlan, u8 qos, __be16 proto);
 };
 
+struct hnae3_dcb_ops {
+	/* IEEE 802.1Qaz std */
+	int (*ieee_getets)(struct hnae3_handle *, struct ieee_ets *);
+	int (*ieee_setets)(struct hnae3_handle *, struct ieee_ets *);
+	int (*ieee_getpfc)(struct hnae3_handle *, struct ieee_pfc *);
+	int (*ieee_setpfc)(struct hnae3_handle *, struct ieee_pfc *);
+
+	/* DCBX configuration */
+	u8   (*getdcbx)(struct hnae3_handle *);
+	u8   (*setdcbx)(struct hnae3_handle *, u8);
+
+	/* TC setup */
+	int (*setup_tc)(struct hnae3_handle *, u8, u8 *);
+
+	int (*map_update)(struct hnae3_handle *);
+};
+
 struct hnae3_ae_algo {
 	const struct hnae3_ae_ops *ops;
 	struct list_head node;
@@ -394,6 +413,7 @@ struct hnae3_knic_private_info {
 
 	u16 num_tqps;		  /* total number of TQPs in this handle */
 	struct hnae3_queue **tqp;  /* array base of all TQPs in this instance */
+	const struct hnae3_dcb_ops *dcb_ops;
 };
 
 struct hnae3_roce_private_info {
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile b/drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile
index 162e8a42..7023dc87 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile
@@ -7,5 +7,7 @@ ccflags-y := -Idrivers/net/ethernet/hisilicon/hns3
 obj-$(CONFIG_HNS3_HCLGE) += hclge.o
 hclge-objs = hclge_main.o hclge_cmd.o hclge_mdio.o hclge_tm.o
 
+hclge-$(CONFIG_HNS3_DCB) += hclge_dcb.o
+
 obj-$(CONFIG_HNS3_ENET) += hns3.o
 hns3-objs = hns3_enet.o hns3_ethtool.o
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c
new file mode 100644
index 0000000..178333b
--- /dev/null
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c
@@ -0,0 +1,327 @@
+/*
+ * Copyright (c) 2016-2017 Hisilicon Limited.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include "hclge_main.h"
+#include "hclge_tm.h"
+#include "hnae3.h"
+
+#define BW_PERCENT	100
+
+static int hclge_ieee_ets_to_tm_info(struct hclge_dev *hdev,
+				     struct ieee_ets *ets)
+{
+	u8 i;
+
+	for (i = 0; i < HNAE3_MAX_TC; i++) {
+		switch (ets->tc_tsa[i]) {
+		case IEEE_8021QAZ_TSA_STRICT:
+			hdev->tm_info.tc_info[i].tc_sch_mode =
+				HCLGE_SCH_MODE_SP;
+			hdev->tm_info.pg_info[0].tc_dwrr[i] = 0;
+			break;
+		case IEEE_8021QAZ_TSA_ETS:
+			hdev->tm_info.tc_info[i].tc_sch_mode =
+				HCLGE_SCH_MODE_DWRR;
+			hdev->tm_info.pg_info[0].tc_dwrr[i] =
+				ets->tc_tx_bw[i];
+			break;
+		default:
+			/* Hardware only supports SP (strict priority)
+			 * or ETS (enhanced transmission selection)
+			 * algorithms, if we receive some other value
+			 * from dcbnl, then throw an error.
+			 */
+			return -EINVAL;
+		}
+	}
+
+	return hclge_tm_prio_tc_info_update(hdev, ets->prio_tc);
+}
+
+static void hclge_tm_info_to_ieee_ets(struct hclge_dev *hdev,
+				      struct ieee_ets *ets)
+{
+	u32 i;
+
+	memset(ets, 0, sizeof(*ets));
+	ets->willing = 1;
+	ets->ets_cap = hdev->tc_max;
+
+	for (i = 0; i < HNAE3_MAX_TC; i++) {
+		ets->prio_tc[i] = hdev->tm_info.prio_tc[i];
+		ets->tc_tx_bw[i] = hdev->tm_info.pg_info[0].tc_dwrr[i];
+
+		if (hdev->tm_info.tc_info[i].tc_sch_mode ==
+		    HCLGE_SCH_MODE_SP)
+			ets->tc_tsa[i] = IEEE_8021QAZ_TSA_STRICT;
+		else
+			ets->tc_tsa[i] = IEEE_8021QAZ_TSA_ETS;
+	}
+}
+
+/* IEEE std */
+static int hclge_ieee_getets(struct hnae3_handle *h, struct ieee_ets *ets)
+{
+	struct hclge_vport *vport = hclge_get_vport(h);
+	struct hclge_dev *hdev = vport->back;
+
+	hclge_tm_info_to_ieee_ets(hdev, ets);
+
+	return 0;
+}
+
+static int hclge_ets_validate(struct hclge_dev *hdev, struct ieee_ets *ets,
+			      u8 *tc, bool *changed)
+{
+	u32 total_ets_bw = 0;
+	u8 max_tc = 0;
+	u8 i;
+
+	for (i = 0; i < HNAE3_MAX_TC; i++) {
+		if (ets->prio_tc[i] >= hdev->tc_max ||
+		    i >= hdev->tc_max)
+			return -EINVAL;
+
+		if (ets->prio_tc[i] != hdev->tm_info.prio_tc[i])
+			*changed = true;
+
+		if (ets->prio_tc[i] > max_tc)
+			max_tc = ets->prio_tc[i];
+
+		switch (ets->tc_tsa[i]) {
+		case IEEE_8021QAZ_TSA_STRICT:
+			if (hdev->tm_info.tc_info[i].tc_sch_mode !=
+				HCLGE_SCH_MODE_SP)
+				*changed = true;
+			break;
+		case IEEE_8021QAZ_TSA_ETS:
+			if (hdev->tm_info.tc_info[i].tc_sch_mode !=
+				HCLGE_SCH_MODE_DWRR)
+				*changed = true;
+
+			total_ets_bw += ets->tc_tx_bw[i];
+		break;
+		default:
+			return -EINVAL;
+		}
+	}
+
+	if (total_ets_bw != BW_PERCENT)
+		return -EINVAL;
+
+	*tc = max_tc + 1;
+	if (*tc != hdev->tm_info.num_tc)
+		*changed = true;
+
+	return 0;
+}
+
+static int hclge_map_update(struct hnae3_handle *h)
+{
+	struct hclge_vport *vport = hclge_get_vport(h);
+	struct hclge_dev *hdev = vport->back;
+	int ret;
+
+	ret = hclge_tm_map_cfg(hdev);
+	if (ret)
+		return ret;
+
+	ret = hclge_tm_schd_mode_hw(hdev);
+	if (ret)
+		return ret;
+
+	ret = hclge_pause_setup_hw(hdev);
+	if (ret)
+		return ret;
+
+	ret = hclge_buffer_alloc(hdev);
+	if (ret)
+		return ret;
+
+	return hclge_rss_init_hw(hdev);
+}
+
+static int hclge_client_setup_tc(struct hclge_dev *hdev)
+{
+	struct hclge_vport *vport = hdev->vport;
+	struct hnae3_client *client;
+	struct hnae3_handle *handle;
+	int ret;
+	u32 i;
+
+	for (i = 0; i < hdev->num_vmdq_vport + 1; i++) {
+		handle = &vport[i].nic;
+		client = handle->client;
+
+		if (!client || !client->ops || !client->ops->setup_tc)
+			continue;
+
+		ret = client->ops->setup_tc(handle, hdev->tm_info.num_tc);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int hclge_ieee_setets(struct hnae3_handle *h, struct ieee_ets *ets)
+{
+	struct hclge_vport *vport = hclge_get_vport(h);
+	struct hclge_dev *hdev = vport->back;
+	bool map_changed = false;
+	u8 num_tc = 0;
+	int ret;
+
+	if (!(hdev->dcbx_cap & DCB_CAP_DCBX_VER_IEEE))
+		return -EINVAL;
+
+	ret = hclge_ets_validate(hdev, ets, &num_tc, &map_changed);
+	if (ret)
+		return ret;
+
+	hclge_tm_schd_info_update(hdev, num_tc);
+
+	ret = hclge_ieee_ets_to_tm_info(hdev, ets);
+	if (ret)
+		return ret;
+
+	if (map_changed) {
+		ret = hclge_client_setup_tc(hdev);
+		if (ret)
+			return ret;
+	}
+
+	return hclge_tm_dwrr_cfg(hdev);
+}
+
+static int hclge_ieee_getpfc(struct hnae3_handle *h, struct ieee_pfc *pfc)
+{
+	struct hclge_vport *vport = hclge_get_vport(h);
+	struct hclge_dev *hdev = vport->back;
+	u8 i, j, pfc_map, *prio_tc;
+
+	memset(pfc, 0, sizeof(*pfc));
+	pfc->pfc_cap = hdev->pfc_max;
+	prio_tc = hdev->tm_info.prio_tc;
+	pfc_map = hdev->tm_info.hw_pfc_map;
+
+	/* Pfc setting is based on TC */
+	for (i = 0; i < hdev->tm_info.num_tc; i++) {
+		for (j = 0; j < HNAE3_MAX_USER_PRIO; j++) {
+			if ((prio_tc[j] == i) && (pfc_map & BIT(i)))
+				pfc->pfc_en |= BIT(j);
+		}
+	}
+
+	return 0;
+}
+
+static int hclge_ieee_setpfc(struct hnae3_handle *h, struct ieee_pfc *pfc)
+{
+	struct hclge_vport *vport = hclge_get_vport(h);
+	struct hclge_dev *hdev = vport->back;
+	u8 i, j, pfc_map, *prio_tc;
+
+	if (!(hdev->dcbx_cap & DCB_CAP_DCBX_VER_IEEE))
+		return -EINVAL;
+
+	prio_tc = hdev->tm_info.prio_tc;
+	pfc_map = 0;
+
+	for (i = 0; i < hdev->tm_info.num_tc; i++) {
+		for (j = 0; j < HNAE3_MAX_USER_PRIO; j++) {
+			if ((prio_tc[j] == i) && (pfc->pfc_en & BIT(j))) {
+				pfc_map |= BIT(i);
+				break;
+			}
+		}
+	}
+
+	if (pfc_map == hdev->tm_info.hw_pfc_map)
+		return 0;
+
+	hdev->tm_info.hw_pfc_map = pfc_map;
+
+	return hclge_pause_setup_hw(hdev);
+}
+
+/* DCBX configuration */
+static u8 hclge_getdcbx(struct hnae3_handle *h)
+{
+	struct hclge_vport *vport = hclge_get_vport(h);
+	struct hclge_dev *hdev = vport->back;
+
+	return hdev->dcbx_cap;
+}
+
+static u8 hclge_setdcbx(struct hnae3_handle *h, u8 mode)
+{
+	struct hclge_vport *vport = hclge_get_vport(h);
+	struct hclge_dev *hdev = vport->back;
+
+	/* No support for LLD_MANAGED modes or CEE */
+	if ((mode & DCB_CAP_DCBX_LLD_MANAGED) ||
+	    (mode & DCB_CAP_DCBX_VER_CEE) ||
+	    !(mode & DCB_CAP_DCBX_HOST))
+		return 1;
+
+	hdev->dcbx_cap = mode;
+
+	return 0;
+}
+
+static int hclge_setup_tc(struct hnae3_handle *h, u8 tc, u8 *prio_tc)
+{
+	struct hclge_vport *vport = hclge_get_vport(h);
+	struct hclge_dev *hdev = vport->back;
+	int ret;
+
+	if (tc > hdev->tc_max) {
+		dev_err(&hdev->pdev->dev,
+			"setup tc failed, tc(%u) > tc_max(%u)\n",
+			tc, hdev->tc_max);
+		return -EINVAL;
+	}
+
+	hclge_tm_schd_info_update(hdev, tc);
+
+	ret = hclge_tm_prio_tc_info_update(hdev, prio_tc);
+	if (ret)
+		return ret;
+
+	return hclge_tm_init_hw(hdev);
+}
+
+static const struct hnae3_dcb_ops hns3_dcb_ops = {
+	.ieee_getets	= hclge_ieee_getets,
+	.ieee_setets	= hclge_ieee_setets,
+	.ieee_getpfc	= hclge_ieee_getpfc,
+	.ieee_setpfc	= hclge_ieee_setpfc,
+	.getdcbx	= hclge_getdcbx,
+	.setdcbx	= hclge_setdcbx,
+	.setup_tc	= hclge_setup_tc,
+	.map_update	= hclge_map_update,
+};
+
+void hclge_dcb_ops_set(struct hclge_dev *hdev)
+{
+	struct hclge_vport *vport = hdev->vport;
+	struct hnae3_knic_private_info *kinfo;
+
+	/* Hdev does not support DCB or vport is
+	 * not a pf, then dcb_ops is not set.
+	 */
+	if (!hnae3_dev_dcb_supported(hdev) ||
+	    vport->vport_id != 0)
+		return;
+
+	kinfo = &vport->nic.kinfo;
+	kinfo->dcb_ops = &hns3_dcb_ops;
+	hdev->dcbx_cap = DCB_CAP_DCBX_VER_IEEE | DCB_CAP_DCBX_HOST;
+}
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.h
new file mode 100644
index 0000000..7d808ee
--- /dev/null
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.h
@@ -0,0 +1,21 @@
+/*
+ * Copyright (c) 2016~2017 Hisilicon Limited.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef __HCLGE_DCB_H__
+#define __HCLGE_DCB_H__
+
+#include "hclge_main.h"
+
+#ifdef CONFIG_HNS3_DCB
+void hclge_dcb_ops_set(struct hclge_dev *hdev);
+#else
+static inline void hclge_dcb_ops_set(struct hclge_dev *hdev) {}
+#endif
+
+#endif /* __HCLGE_DCB_H__ */
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 49a11d5..28bd118 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -19,6 +19,7 @@
 #include <linux/platform_device.h>
 
 #include "hclge_cmd.h"
+#include "hclge_dcb.h"
 #include "hclge_main.h"
 #include "hclge_mdio.h"
 #include "hclge_tm.h"
@@ -1057,7 +1058,7 @@ static int hclge_configure(struct hclge_dev *hdev)
 	hdev->hw.mac.phy_addr = cfg.phy_addr;
 	hdev->num_desc = cfg.tqp_desc_num;
 	hdev->tm_info.num_pg = 1;
-	hdev->tm_info.num_tc = cfg.tc_num;
+	hdev->tc_max = cfg.tc_num;
 	hdev->tm_info.hw_pfc_map = 0;
 
 	ret = hclge_parse_speed(cfg.default_speed, &hdev->hw.mac.speed);
@@ -1066,15 +1067,25 @@ static int hclge_configure(struct hclge_dev *hdev)
 		return ret;
 	}
 
-	if ((hdev->tm_info.num_tc > HNAE3_MAX_TC) ||
-	    (hdev->tm_info.num_tc < 1)) {
+	if ((hdev->tc_max > HNAE3_MAX_TC) ||
+	    (hdev->tc_max < 1)) {
 		dev_warn(&hdev->pdev->dev, "TC num = %d.\n",
-			 hdev->tm_info.num_tc);
-		hdev->tm_info.num_tc = 1;
+			 hdev->tc_max);
+		hdev->tc_max = 1;
 	}
 
+	/* Dev does not support DCB */
+	if (!hnae3_dev_dcb_supported(hdev)) {
+		hdev->tc_max = 1;
+		hdev->pfc_max = 0;
+	} else {
+		hdev->pfc_max = hdev->tc_max;
+	}
+
+	hdev->tm_info.num_tc = hdev->tc_max;
+
 	/* Currently not support uncontiuous tc */
-	for (i = 0; i < cfg.tc_num; i++)
+	for (i = 0; i < hdev->tm_info.num_tc; i++)
 		hnae_set_bit(hdev->hw_tc_map, i, 1);
 
 	if (!hdev->num_vmdq_vport && !hdev->num_req_vfs)
@@ -4242,6 +4253,8 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
 		return ret;
 	}
 
+	hclge_dcb_ops_set(hdev);
+
 	setup_timer(&hdev->service_timer, hclge_service_timer,
 		    (unsigned long)hdev);
 	INIT_WORK(&hdev->service_task, hclge_service_task);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index 394b587..7c66c00 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -421,8 +421,11 @@ struct hclge_dev {
 #define HCLGE_FLAG_TC_BASE_SCH_MODE		1
 #define HCLGE_FLAG_VNET_BASE_SCH_MODE		2
 	u8 tx_sch_mode;
+	u8 tc_max;
+	u8 pfc_max;
 
 	u8 default_up;
+	u8 dcbx_cap;
 	struct hclge_tm_info tm_info;
 
 	u16 num_msi;
-- 
1.9.1

[PATCH net-next 08/10] net: hns3: Add dcb netlink interface for the support of DCB feature

[Yunsheng Lin]

This patch add dcb netlink interface by calling the interface from
hclge_dcb module.

This patch also update Makefile in order to build hns3_dcbnl module.

Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
---
 .../net/ethernet/hisilicon/hns3/hns3pf/Makefile    |   2 +
 .../ethernet/hisilicon/hns3/hns3pf/hns3_dcbnl.c    | 106 +++++++++++++++++++++
 .../net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c |   2 +
 .../net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.h |   7 ++
 4 files changed, 117 insertions(+)
 create mode 100644 drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_dcbnl.c

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile b/drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile
index 7023dc87..d2b20d0 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile
@@ -11,3 +11,5 @@ hclge-$(CONFIG_HNS3_DCB) += hclge_dcb.o
 
 obj-$(CONFIG_HNS3_ENET) += hns3.o
 hns3-objs = hns3_enet.o hns3_ethtool.o
+
+hns3-$(CONFIG_HNS3_DCB) += hns3_dcbnl.o
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_dcbnl.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_dcbnl.c
new file mode 100644
index 0000000..9832172
--- /dev/null
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_dcbnl.c
@@ -0,0 +1,106 @@
+/*
+ * Copyright (c) 2016-2017 Hisilicon Limited.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include "hnae3.h"
+#include "hns3_enet.h"
+
+static
+int hns3_dcbnl_ieee_getets(struct net_device *ndev, struct ieee_ets *ets)
+{
+	struct hns3_nic_priv *priv = netdev_priv(ndev);
+	struct hnae3_handle *h = priv->ae_handle;
+
+	if (h->kinfo.dcb_ops->ieee_getets)
+		return h->kinfo.dcb_ops->ieee_getets(h, ets);
+
+	return -EOPNOTSUPP;
+}
+
+static
+int hns3_dcbnl_ieee_setets(struct net_device *ndev, struct ieee_ets *ets)
+{
+	struct hns3_nic_priv *priv = netdev_priv(ndev);
+	struct hnae3_handle *h = priv->ae_handle;
+
+	if (h->kinfo.dcb_ops->ieee_setets)
+		return h->kinfo.dcb_ops->ieee_setets(h, ets);
+
+	return -EOPNOTSUPP;
+}
+
+static
+int hns3_dcbnl_ieee_getpfc(struct net_device *ndev, struct ieee_pfc *pfc)
+{
+	struct hns3_nic_priv *priv = netdev_priv(ndev);
+	struct hnae3_handle *h = priv->ae_handle;
+
+	if (h->kinfo.dcb_ops->ieee_getpfc)
+		return h->kinfo.dcb_ops->ieee_getpfc(h, pfc);
+
+	return -EOPNOTSUPP;
+}
+
+static
+int hns3_dcbnl_ieee_setpfc(struct net_device *ndev, struct ieee_pfc *pfc)
+{
+	struct hns3_nic_priv *priv = netdev_priv(ndev);
+	struct hnae3_handle *h = priv->ae_handle;
+
+	if (h->kinfo.dcb_ops->ieee_setpfc)
+		return h->kinfo.dcb_ops->ieee_setpfc(h, pfc);
+
+	return -EOPNOTSUPP;
+}
+
+/* DCBX configuration */
+static u8 hns3_dcbnl_getdcbx(struct net_device *ndev)
+{
+	struct hns3_nic_priv *priv = netdev_priv(ndev);
+	struct hnae3_handle *h = priv->ae_handle;
+
+	if (h->kinfo.dcb_ops->getdcbx)
+		return h->kinfo.dcb_ops->getdcbx(h);
+
+	return 0;
+}
+
+/* return 0 if successful, otherwise fail */
+static u8 hns3_dcbnl_setdcbx(struct net_device *ndev, u8 mode)
+{
+	struct hns3_nic_priv *priv = netdev_priv(ndev);
+	struct hnae3_handle *h = priv->ae_handle;
+
+	if (h->kinfo.dcb_ops->setdcbx)
+		return h->kinfo.dcb_ops->setdcbx(h, mode);
+
+	return 1;
+}
+
+static const struct dcbnl_rtnl_ops hns3_dcbnl_ops = {
+	.ieee_getets	= hns3_dcbnl_ieee_getets,
+	.ieee_setets	= hns3_dcbnl_ieee_setets,
+	.ieee_getpfc	= hns3_dcbnl_ieee_getpfc,
+	.ieee_setpfc	= hns3_dcbnl_ieee_setpfc,
+	.getdcbx	= hns3_dcbnl_getdcbx,
+	.setdcbx	= hns3_dcbnl_setdcbx,
+};
+
+/* hclge_dcbnl_setup - DCBNL setup
+ * @handle: the corresponding vport handle
+ * Set up DCBNL
+ */
+void hns3_dcbnl_setup(struct hnae3_handle *handle)
+{
+	struct net_device *dev = handle->kinfo.netdev;
+
+	if (!handle->kinfo.dcb_ops)
+		return;
+
+	dev->dcbnl_ops = &hns3_dcbnl_ops;
+}
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c
index 35369e1..11dab26 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c
@@ -2790,6 +2790,8 @@ static int hns3_client_init(struct hnae3_handle *handle)
 		goto out_reg_netdev_fail;
 	}
 
+	hns3_dcbnl_setup(handle);
+
 	/* MTU range: (ETH_MIN_MTU(kernel default) - 9706) */
 	netdev->max_mtu = HNS3_MAX_MTU - (ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN);
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.h
index 7e87461..481eada 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.h
@@ -590,4 +590,11 @@ static inline void hns3_write_reg(void __iomem *base, u32 reg, u32 value)
 void hns3_ethtool_set_ops(struct net_device *netdev);
 
 int hns3_clean_tx_ring(struct hns3_enet_ring *ring, int budget);
+
+#ifdef CONFIG_HNS3_DCB
+void hns3_dcbnl_setup(struct hnae3_handle *handle);
+#else
+static inline void hns3_dcbnl_setup(struct hnae3_handle *handle) {}
+#endif
+
 #endif
-- 
1.9.1

[PATCH net-next 09/10] net: hns3: Setting for fc_mode and dcb enable flag in TM module

[Yunsheng Lin]

After the DCB feature is supported, fc_mode and dcb enable flag
must be set according to the DCB parameter.

Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
---
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c  | 34 +++++++++++++++++++---
 1 file changed, 30 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
index e158e66..cc5efda 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
@@ -487,7 +487,11 @@ static void hclge_tm_tc_info_init(struct hclge_dev *hdev)
 		hdev->tm_info.prio_tc[i] =
 			(i >= hdev->tm_info.num_tc) ? 0 : i;
 
-	hdev->flag &= ~HCLGE_FLAG_DCB_ENABLE;
+	/* DCB is enabled if we have more than 1 TC */
+	if (hdev->tm_info.num_tc > 1)
+		hdev->flag |= HCLGE_FLAG_DCB_ENABLE;
+	else
+		hdev->flag &= ~HCLGE_FLAG_DCB_ENABLE;
 }
 
 static void hclge_tm_pg_info_init(struct hclge_dev *hdev)
@@ -513,6 +517,24 @@ static void hclge_tm_pg_info_init(struct hclge_dev *hdev)
 	}
 }
 
+static void hclge_pfc_info_init(struct hclge_dev *hdev)
+{
+	if (!(hdev->flag & HCLGE_FLAG_DCB_ENABLE)) {
+		if (hdev->fc_mode_last_time == HCLGE_FC_PFC)
+			dev_warn(&hdev->pdev->dev,
+				 "DCB is disable, but last mode is FC_PFC\n");
+
+		hdev->tm_info.fc_mode = hdev->fc_mode_last_time;
+	} else if (hdev->tm_info.fc_mode != HCLGE_FC_PFC) {
+		/* fc_mode_last_time record the last fc_mode when
+		 * DCB is enabled, so that fc_mode can be set to
+		 * the correct value when DCB is disabled.
+		 */
+		hdev->fc_mode_last_time = hdev->tm_info.fc_mode;
+		hdev->tm_info.fc_mode = HCLGE_FC_PFC;
+	}
+}
+
 static int hclge_tm_schd_info_init(struct hclge_dev *hdev)
 {
 	if ((hdev->tx_sch_mode != HCLGE_FLAG_TC_BASE_SCH_MODE) &&
@@ -525,8 +547,7 @@ static int hclge_tm_schd_info_init(struct hclge_dev *hdev)
 
 	hclge_tm_vport_info_update(hdev);
 
-	hdev->tm_info.fc_mode = HCLGE_FC_NONE;
-	hdev->fc_mode_last_time = hdev->tm_info.fc_mode;
+	hclge_pfc_info_init(hdev);
 
 	return 0;
 }
@@ -1159,8 +1180,13 @@ int hclge_tm_init_hw(struct hclge_dev *hdev)
 
 int hclge_tm_schd_init(struct hclge_dev *hdev)
 {
-	int ret = hclge_tm_schd_info_init(hdev);
+	int ret;
+
+	/* fc_mode is HCLGE_FC_FULL on reset */
+	hdev->tm_info.fc_mode = HCLGE_FC_FULL;
+	hdev->fc_mode_last_time = hdev->tm_info.fc_mode;
 
+	ret = hclge_tm_schd_info_init(hdev);
 	if (ret)
 		return ret;
 
-- 
1.9.1

[PATCH net-next 10/10] net: hns3: Add mqprio support when interacting with network stack

[Yunsheng Lin]

When using tc qdisc to configure DCB parameter, dcb_ops->setup_tc
is used to tell hclge_dcb module to do the setup.
When using lldptool to configure DCB parameter, hclge_dcb module
call the client_ops->setup_tc to tell network stack which queue
and priority is using for specific tc.

Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
---
 .../net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c | 135 +++++++++++++++++----
 1 file changed, 111 insertions(+), 24 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c
index 11dab26..31fcda4 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c
@@ -196,6 +196,32 @@ static void hns3_vector_gl_rl_init(struct hns3_enet_tqp_vector *tqp_vector)
 	tqp_vector->tx_group.flow_level = HNS3_FLOW_LOW;
 }
 
+static int hns3_nic_set_real_num_queue(struct net_device *netdev)
+{
+	struct hns3_nic_priv *priv = netdev_priv(netdev);
+	struct hnae3_handle *h = priv->ae_handle;
+	struct hnae3_knic_private_info *kinfo = &h->kinfo;
+	unsigned int queue_size = kinfo->rss_size * kinfo->num_tc;
+	int ret;
+
+	ret = netif_set_real_num_tx_queues(netdev, queue_size);
+	if (ret) {
+		netdev_err(netdev,
+			   "netif_set_real_num_tx_queues fail, ret=%d!\n",
+			   ret);
+		return ret;
+	}
+
+	ret = netif_set_real_num_rx_queues(netdev, queue_size);
+	if (ret) {
+		netdev_err(netdev,
+			   "netif_set_real_num_rx_queues fail, ret=%d!\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
 static int hns3_nic_net_up(struct net_device *netdev)
 {
 	struct hns3_nic_priv *priv = netdev_priv(netdev);
@@ -232,26 +258,13 @@ static int hns3_nic_net_up(struct net_device *netdev)
 
 static int hns3_nic_net_open(struct net_device *netdev)
 {
-	struct hns3_nic_priv *priv = netdev_priv(netdev);
-	struct hnae3_handle *h = priv->ae_handle;
 	int ret;
 
 	netif_carrier_off(netdev);
 
-	ret = netif_set_real_num_tx_queues(netdev, h->kinfo.num_tqps);
-	if (ret) {
-		netdev_err(netdev,
-			   "netif_set_real_num_tx_queues fail, ret=%d!\n",
-			   ret);
-		return ret;
-	}
-
-	ret = netif_set_real_num_rx_queues(netdev, h->kinfo.num_tqps);
-	if (ret) {
-		netdev_err(netdev,
-			   "netif_set_real_num_rx_queues fail, ret=%d!\n", ret);
+	ret = hns3_nic_set_real_num_queue(netdev);
+	if (ret)
 		return ret;
-	}
 
 	ret = hns3_nic_net_up(netdev);
 	if (ret) {
@@ -1193,32 +1206,40 @@ static void hns3_nic_udp_tunnel_del(struct net_device *netdev,
 	}
 }
 
-static int hns3_setup_tc(struct net_device *netdev, u8 tc)
+static int hns3_setup_tc(struct net_device *netdev, u8 tc, u8 *prio_tc)
 {
 	struct hns3_nic_priv *priv = netdev_priv(netdev);
 	struct hnae3_handle *h = priv->ae_handle;
 	struct hnae3_knic_private_info *kinfo = &h->kinfo;
+	bool if_running = netif_running(netdev);
 	unsigned int i;
 	int ret;
 
 	if (tc > HNAE3_MAX_TC)
 		return -EINVAL;
 
-	if (kinfo->num_tc == tc)
-		return 0;
-
 	if (!netdev)
 		return -EINVAL;
 
-	if (!tc) {
+	if (if_running) {
+		(void)hns3_nic_net_stop(netdev);
+		msleep(100);
+	}
+
+	ret = (kinfo->dcb_ops && kinfo->dcb_ops->setup_tc) ?
+		kinfo->dcb_ops->setup_tc(h, tc, prio_tc) : -EOPNOTSUPP;
+	if (ret)
+		goto err_out;
+
+	if (tc <= 1) {
 		netdev_reset_tc(netdev);
-		return 0;
+		goto out;
 	}
 
 	/* Set num_tc for netdev */
 	ret = netdev_set_num_tc(netdev, tc);
 	if (ret)
-		return ret;
+		goto err_out;
 
 	/* Set per TC queues for the VSI */
 	for (i = 0; i < HNAE3_MAX_TC; i++) {
@@ -1229,7 +1250,14 @@ static int hns3_setup_tc(struct net_device *netdev, u8 tc)
 					    kinfo->tc_info[i].tqp_offset);
 	}
 
-	return 0;
+out:
+	ret = hns3_nic_set_real_num_queue(netdev);
+
+err_out:
+	if (if_running)
+		(void)hns3_nic_net_open(netdev);
+
+	return ret;
 }
 
 static int hns3_nic_setup_tc(struct net_device *dev, enum tc_setup_type type,
@@ -1240,7 +1268,7 @@ static int hns3_nic_setup_tc(struct net_device *dev, enum tc_setup_type type,
 	if (type != TC_SETUP_MQPRIO)
 		return -EOPNOTSUPP;
 
-	return hns3_setup_tc(dev, mqprio->num_tc);
+	return hns3_setup_tc(dev, mqprio->num_tc, mqprio->prio_tc_map);
 }
 
 static int hns3_vlan_rx_add_vid(struct net_device *netdev,
@@ -2848,10 +2876,69 @@ static void hns3_link_status_change(struct hnae3_handle *handle, bool linkup)
 	}
 }
 
+static int hns3_client_setup_tc(struct hnae3_handle *handle, u8 tc)
+{
+	struct hnae3_knic_private_info *kinfo = &handle->kinfo;
+	struct net_device *ndev = kinfo->netdev;
+	bool if_running = netif_running(ndev);
+	int ret;
+	u8 i;
+
+	if (tc > HNAE3_MAX_TC)
+		return -EINVAL;
+
+	if (!ndev)
+		return -ENODEV;
+
+	ret = netdev_set_num_tc(ndev, tc);
+	if (ret)
+		return ret;
+
+	if (if_running) {
+		(void)hns3_nic_net_stop(ndev);
+		msleep(100);
+	}
+
+	ret = (kinfo->dcb_ops && kinfo->dcb_ops->map_update) ?
+		kinfo->dcb_ops->map_update(handle) : -EOPNOTSUPP;
+	if (ret)
+		goto err_out;
+
+	if (tc <= 1) {
+		netdev_reset_tc(ndev);
+		goto out;
+	}
+
+	for (i = 0; i < HNAE3_MAX_TC; i++) {
+		struct hnae3_tc_info *tc_info = &kinfo->tc_info[i];
+
+		if (tc_info->enable)
+			netdev_set_tc_queue(ndev,
+					    tc_info->tc,
+					    tc_info->tqp_count,
+					    tc_info->tqp_offset);
+	}
+
+	for (i = 0; i < HNAE3_MAX_USER_PRIO; i++) {
+		netdev_set_prio_tc_map(ndev, i,
+				       kinfo->prio_tc[i]);
+	}
+
+out:
+	ret = hns3_nic_set_real_num_queue(ndev);
+
+err_out:
+	if (if_running)
+		(void)hns3_nic_net_open(ndev);
+
+	return ret;
+}
+
 const struct hnae3_client_ops client_ops = {
 	.init_instance = hns3_client_init,
 	.uninit_instance = hns3_client_uninit,
 	.link_status_change = hns3_link_status_change,
+	.setup_tc = hns3_client_setup_tc,
 };
 
 /* hns3_init_module - Driver registration routine
-- 
1.9.1

Re: [PATCH net-next 10/10] net: hns3: Add mqprio support when interacting with network stack

[Jiri Pirko]

Thu, Sep 21, 2017 at 01:21:53PM CEST, linyunsheng@huawei.com wrote:
>When using tc qdisc to configure DCB parameter, dcb_ops->setup_tc
>is used to tell hclge_dcb module to do the setup.
>When using lldptool to configure DCB parameter, hclge_dcb module
>call the client_ops->setup_tc to tell network stack which queue
>and priority is using for specific tc.
>
>Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>

[...]
	
	
	
>-static int hns3_setup_tc(struct net_device *netdev, u8 tc)
>+static int hns3_setup_tc(struct net_device *netdev, u8 tc, u8 *prio_tc)
> {
> 	struct hns3_nic_priv *priv = netdev_priv(netdev);
> 	struct hnae3_handle *h = priv->ae_handle;
> 	struct hnae3_knic_private_info *kinfo = &h->kinfo;
>+	bool if_running = netif_running(netdev);
> 	unsigned int i;
> 	int ret;
> 
> 	if (tc > HNAE3_MAX_TC)
> 		return -EINVAL;
> 
>-	if (kinfo->num_tc == tc)
>-		return 0;
>-
> 	if (!netdev)
> 		return -EINVAL;
> 
>-	if (!tc) {
>+	if (if_running) {
>+		(void)hns3_nic_net_stop(netdev);
>+		msleep(100);
>+	}
>+
>+	ret = (kinfo->dcb_ops && kinfo->dcb_ops->setup_tc) ?
>+		kinfo->dcb_ops->setup_tc(h, tc, prio_tc) : -EOPNOTSUPP;

This is most odd. Why do you call dcb_ops from ndo_setup_tc callback?
Why are you mixing this together? prio->tc mapping can be done
directly in dcbnl

Re: [PATCH net-next 10/10] net: hns3: Add mqprio support when interacting with network stack

[Jiri Pirko]

Fri, Sep 22, 2017 at 04:11:51PM CEST, linyunsheng@huawei.com wrote:
>Hi, Jiri
>
>>>- if (!tc) {
>>>+ if (if_running) {
>>>+ (void)hns3_nic_net_stop(netdev);
>>>+ msleep(100);
>>>+ }
>>>+
>>>+ ret = (kinfo->dcb_ops && kinfo->dcb_ops->>setup_tc) ?
>>>+ kinfo->dcb_ops->setup_tc(h, tc, prio_tc) : ->EOPNOTSUPP;
>
>>This is most odd. Why do you call dcb_ops from >ndo_setup_tc callback?
>>Why are you mixing this together? prio->tc mapping >can be done
>>directly in dcbnl
>
>Here is what we do in dcb_ops->setup_tc:
>Firstly, if current tc num is different from the tc num
>that user provide, then we setup the queues for each
>tc.
>
>Secondly, we tell hardware the pri to tc mapping that
>the stack is using. In rx direction, our hardware need
>that mapping to put different packet into different tc'
>queues according to the priority of the packet, then
>rss decides which specific queue in the tc should the
>packet goto.
>
>By mixing, I suppose you meant why we need the
>pri to tc infomation?

by mixing, I mean what I wrote. You are calling dcb_ops callback from
ndo_setup_tc callback. So you are mixing DCBNL subsystem and TC
subsystem. Why? Why do you need sch_mqprio? Why DCBNL is not enough for
all?



>I hope I did not misunderstand your question, thanks
>for your time reviewing.

Re: [PATCH net-next 10/10] net: hns3: Add mqprio support when interacting with network stack

[Yunsheng Lin]

Hi, Jiri

On 2017/9/23 0:03, Jiri Pirko wrote:
> Fri, Sep 22, 2017 at 04:11:51PM CEST, linyunsheng@huawei.com wrote:
>> Hi, Jiri
>>
>>>> - if (!tc) {
>>>> + if (if_running) {
>>>> + (void)hns3_nic_net_stop(netdev);
>>>> + msleep(100);
>>>> + }
>>>> +
>>>> + ret = (kinfo->dcb_ops && kinfo->dcb_ops->>setup_tc) ?
>>>> + kinfo->dcb_ops->setup_tc(h, tc, prio_tc) : ->EOPNOTSUPP;
>>
>>> This is most odd. Why do you call dcb_ops from >ndo_setup_tc callback?
>>> Why are you mixing this together? prio->tc mapping >can be done
>>> directly in dcbnl
>>
>> Here is what we do in dcb_ops->setup_tc:
>> Firstly, if current tc num is different from the tc num
>> that user provide, then we setup the queues for each
>> tc.
>>
>> Secondly, we tell hardware the pri to tc mapping that
>> the stack is using. In rx direction, our hardware need
>> that mapping to put different packet into different tc'
>> queues according to the priority of the packet, then
>> rss decides which specific queue in the tc should the
>> packet goto.
>>
>> By mixing, I suppose you meant why we need the
>> pri to tc infomation?
> 
> by mixing, I mean what I wrote. You are calling dcb_ops callback from
> ndo_setup_tc callback. So you are mixing DCBNL subsystem and TC
> subsystem. Why? Why do you need sch_mqprio? Why DCBNL is not enough for
> all?

When using lldptool, dcbnl is involved.

But when using tc qdisc, dcbbl is not involved, below is the a few key
call graph in the kernel when tc qdisc cmd is executed.

cmd:
tc qdisc add dev eth0 root handle 1:0 mqprio num_tc 4 map 1 2 3 3 1 3 1 1 hw 1

call graph:
rtnetlink_rcv_msg -> tc_modify_qdisc -> qdisc_create -> mqprio_init ->
hns3_nic_setup_tc

When hns3_nic_setup_tc is called, we need to know how many tc num and
prio_tc mapping from the tc_mqprio_qopt which is provided in the paramter
in the ndo_setup_tc function, and dcb_ops is the our hardware specific
method to setup the tc related parameter to the hardware, so this is why
we call dcb_ops callback in ndo_setup_tc callback.

I hope this will answer your question, thanks for your time.

> 
> 
> 
>> I hope I did not misunderstand your question, thanks
>> for your time reviewing.
> 
> .
> 

Re: [PATCH net-next 10/10] net: hns3: Add mqprio support when interacting with network stack

[Jiri Pirko]

Sat, Sep 23, 2017 at 02:47:20AM CEST, linyunsheng@huawei.com wrote:
>Hi, Jiri
>
>On 2017/9/23 0:03, Jiri Pirko wrote:
>> Fri, Sep 22, 2017 at 04:11:51PM CEST, linyunsheng@huawei.com wrote:
>>> Hi, Jiri
>>>
>>>>> - if (!tc) {
>>>>> + if (if_running) {
>>>>> + (void)hns3_nic_net_stop(netdev);
>>>>> + msleep(100);
>>>>> + }
>>>>> +
>>>>> + ret = (kinfo->dcb_ops && kinfo->dcb_ops->>setup_tc) ?
>>>>> + kinfo->dcb_ops->setup_tc(h, tc, prio_tc) : ->EOPNOTSUPP;
>>>
>>>> This is most odd. Why do you call dcb_ops from >ndo_setup_tc callback?
>>>> Why are you mixing this together? prio->tc mapping >can be done
>>>> directly in dcbnl
>>>
>>> Here is what we do in dcb_ops->setup_tc:
>>> Firstly, if current tc num is different from the tc num
>>> that user provide, then we setup the queues for each
>>> tc.
>>>
>>> Secondly, we tell hardware the pri to tc mapping that
>>> the stack is using. In rx direction, our hardware need
>>> that mapping to put different packet into different tc'
>>> queues according to the priority of the packet, then
>>> rss decides which specific queue in the tc should the
>>> packet goto.
>>>
>>> By mixing, I suppose you meant why we need the
>>> pri to tc infomation?
>> 
>> by mixing, I mean what I wrote. You are calling dcb_ops callback from
>> ndo_setup_tc callback. So you are mixing DCBNL subsystem and TC
>> subsystem. Why? Why do you need sch_mqprio? Why DCBNL is not enough for
>> all?
>
>When using lldptool, dcbnl is involved.
>
>But when using tc qdisc, dcbbl is not involved, below is the a few key
>call graph in the kernel when tc qdisc cmd is executed.
>
>cmd:
>tc qdisc add dev eth0 root handle 1:0 mqprio num_tc 4 map 1 2 3 3 1 3 1 1 hw 1
>
>call graph:
>rtnetlink_rcv_msg -> tc_modify_qdisc -> qdisc_create -> mqprio_init ->
>hns3_nic_setup_tc
>
>When hns3_nic_setup_tc is called, we need to know how many tc num and
>prio_tc mapping from the tc_mqprio_qopt which is provided in the paramter
>in the ndo_setup_tc function, and dcb_ops is the our hardware specific
>method to setup the tc related parameter to the hardware, so this is why
>we call dcb_ops callback in ndo_setup_tc callback.
>
>I hope this will answer your question, thanks for your time.

Okay. I understand that you have a usecase for mqprio mapping offload
without lldptool being involved. Ok. I believe it is wrong to call dcb_ops
from tc callback. You should have a generic layer inside the driver and
call it from both dcb_ops and tc callbacks.

Also, what happens If I run lldptool concurrently with mqprio? Who wins
and is going to configure the mapping?


>
>> 
>> 
>> 
>>> I hope I did not misunderstand your question, thanks
>>> for your time reviewing.
>> 
>> .
>> 
>

Re: [PATCH net-next 10/10] net: hns3: Add mqprio support when interacting with network stack

[Yunsheng Lin]

Hi, Jiri

On 2017/9/24 19:37, Jiri Pirko wrote:
> Sat, Sep 23, 2017 at 02:47:20AM CEST, linyunsheng@huawei.com wrote:
>> Hi, Jiri
>>
>> On 2017/9/23 0:03, Jiri Pirko wrote:
>>> Fri, Sep 22, 2017 at 04:11:51PM CEST, linyunsheng@huawei.com wrote:
>>>> Hi, Jiri
>>>>
>>>>>> - if (!tc) {
>>>>>> + if (if_running) {
>>>>>> + (void)hns3_nic_net_stop(netdev);
>>>>>> + msleep(100);
>>>>>> + }
>>>>>> +
>>>>>> + ret = (kinfo->dcb_ops && kinfo->dcb_ops->>setup_tc) ?
>>>>>> + kinfo->dcb_ops->setup_tc(h, tc, prio_tc) : ->EOPNOTSUPP;
>>>>
>>>>> This is most odd. Why do you call dcb_ops from >ndo_setup_tc callback?
>>>>> Why are you mixing this together? prio->tc mapping >can be done
>>>>> directly in dcbnl
>>>>
>>>> Here is what we do in dcb_ops->setup_tc:
>>>> Firstly, if current tc num is different from the tc num
>>>> that user provide, then we setup the queues for each
>>>> tc.
>>>>
>>>> Secondly, we tell hardware the pri to tc mapping that
>>>> the stack is using. In rx direction, our hardware need
>>>> that mapping to put different packet into different tc'
>>>> queues according to the priority of the packet, then
>>>> rss decides which specific queue in the tc should the
>>>> packet goto.
>>>>
>>>> By mixing, I suppose you meant why we need the
>>>> pri to tc infomation?
>>>
>>> by mixing, I mean what I wrote. You are calling dcb_ops callback from
>>> ndo_setup_tc callback. So you are mixing DCBNL subsystem and TC
>>> subsystem. Why? Why do you need sch_mqprio? Why DCBNL is not enough for
>>> all?
>>
>> When using lldptool, dcbnl is involved.
>>
>> But when using tc qdisc, dcbbl is not involved, below is the a few key
>> call graph in the kernel when tc qdisc cmd is executed.
>>
>> cmd:
>> tc qdisc add dev eth0 root handle 1:0 mqprio num_tc 4 map 1 2 3 3 1 3 1 1 hw 1
>>
>> call graph:
>> rtnetlink_rcv_msg -> tc_modify_qdisc -> qdisc_create -> mqprio_init ->
>> hns3_nic_setup_tc
>>
>> When hns3_nic_setup_tc is called, we need to know how many tc num and
>> prio_tc mapping from the tc_mqprio_qopt which is provided in the paramter
>> in the ndo_setup_tc function, and dcb_ops is the our hardware specific
>> method to setup the tc related parameter to the hardware, so this is why
>> we call dcb_ops callback in ndo_setup_tc callback.
>>
>> I hope this will answer your question, thanks for your time.
> 
> Okay. I understand that you have a usecase for mqprio mapping offload
> without lldptool being involved. Ok. I believe it is wrong to call dcb_ops
> from tc callback. You should have a generic layer inside the driver and
> call it from both dcb_ops and tc callbacks.

Actually, dcb_ops is our generic layer inside the driver.
Below is high level architecture:

       [ tc qdisc ]	       [ lldpad ]
             |                     |
             |                     |
             |                     |
       [ hns3_enet ]        [ hns3_dcbnl ]
             \                    /
                \              /
                   \        /
                 [ hclge_dcb ]
                   /      \
                /            \
             /                  \
     [ hclgc_main ]        [ hclge_tm ]

hns3_enet.c implements the ndo_setup_tc callback.
hns3_dcbnl.c implements the dcbnl_rtnl_ops for stack's DCBNL system.
hclge_dcb implements the dcb_ops.
So we already have a generic layer that tc and dcbnl all call from.

> 
> Also, what happens If I run lldptool concurrently with mqprio? Who wins
> and is going to configure the mapping?

Both lldptool and tc qdisc cmd use rtnl interface provided by stack, so
they are both protected by rtnl_lock, so we do not have to do the locking
in the driver.

The locking is in rtnetlink_rcv_msg:

	rtnl_lock();
	handlers = rtnl_dereference(rtnl_msg_handlers[family]);
	if (handlers) {
		doit = READ_ONCE(handlers[type].doit);
		if (doit)
			err = doit(skb, nlh, extack);
	}
	rtnl_unlock();

Thanks.

> 
> 
>>
>>>
>>>
>>>
>>>> I hope I did not misunderstand your question, thanks
>>>> for your time reviewing.
>>>
>>> .
>>>
>>
> 
> .
> 

Re: [PATCH net-next 10/10] net: hns3: Add mqprio support when interacting with network stack

[Jiri Pirko]

Mon, Sep 25, 2017 at 02:45:08AM CEST, linyunsheng@huawei.com wrote:
>Hi, Jiri
>
>On 2017/9/24 19:37, Jiri Pirko wrote:
>> Sat, Sep 23, 2017 at 02:47:20AM CEST, linyunsheng@huawei.com wrote:
>>> Hi, Jiri
>>>
>>> On 2017/9/23 0:03, Jiri Pirko wrote:
>>>> Fri, Sep 22, 2017 at 04:11:51PM CEST, linyunsheng@huawei.com wrote:
>>>>> Hi, Jiri
>>>>>
>>>>>>> - if (!tc) {
>>>>>>> + if (if_running) {
>>>>>>> + (void)hns3_nic_net_stop(netdev);
>>>>>>> + msleep(100);
>>>>>>> + }
>>>>>>> +
>>>>>>> + ret = (kinfo->dcb_ops && kinfo->dcb_ops->>setup_tc) ?
>>>>>>> + kinfo->dcb_ops->setup_tc(h, tc, prio_tc) : ->EOPNOTSUPP;
>>>>>
>>>>>> This is most odd. Why do you call dcb_ops from >ndo_setup_tc callback?
>>>>>> Why are you mixing this together? prio->tc mapping >can be done
>>>>>> directly in dcbnl
>>>>>
>>>>> Here is what we do in dcb_ops->setup_tc:
>>>>> Firstly, if current tc num is different from the tc num
>>>>> that user provide, then we setup the queues for each
>>>>> tc.
>>>>>
>>>>> Secondly, we tell hardware the pri to tc mapping that
>>>>> the stack is using. In rx direction, our hardware need
>>>>> that mapping to put different packet into different tc'
>>>>> queues according to the priority of the packet, then
>>>>> rss decides which specific queue in the tc should the
>>>>> packet goto.
>>>>>
>>>>> By mixing, I suppose you meant why we need the
>>>>> pri to tc infomation?
>>>>
>>>> by mixing, I mean what I wrote. You are calling dcb_ops callback from
>>>> ndo_setup_tc callback. So you are mixing DCBNL subsystem and TC
>>>> subsystem. Why? Why do you need sch_mqprio? Why DCBNL is not enough for
>>>> all?
>>>
>>> When using lldptool, dcbnl is involved.
>>>
>>> But when using tc qdisc, dcbbl is not involved, below is the a few key
>>> call graph in the kernel when tc qdisc cmd is executed.
>>>
>>> cmd:
>>> tc qdisc add dev eth0 root handle 1:0 mqprio num_tc 4 map 1 2 3 3 1 3 1 1 hw 1
>>>
>>> call graph:
>>> rtnetlink_rcv_msg -> tc_modify_qdisc -> qdisc_create -> mqprio_init ->
>>> hns3_nic_setup_tc
>>>
>>> When hns3_nic_setup_tc is called, we need to know how many tc num and
>>> prio_tc mapping from the tc_mqprio_qopt which is provided in the paramter
>>> in the ndo_setup_tc function, and dcb_ops is the our hardware specific
>>> method to setup the tc related parameter to the hardware, so this is why
>>> we call dcb_ops callback in ndo_setup_tc callback.
>>>
>>> I hope this will answer your question, thanks for your time.
>> 
>> Okay. I understand that you have a usecase for mqprio mapping offload
>> without lldptool being involved. Ok. I believe it is wrong to call dcb_ops
>> from tc callback. You should have a generic layer inside the driver and
>> call it from both dcb_ops and tc callbacks.
>
>Actually, dcb_ops is our generic layer inside the driver.
>Below is high level architecture:
>
>       [ tc qdisc ]	       [ lldpad ]
>             |                     |
>             |                     |
>             |                     |
>       [ hns3_enet ]        [ hns3_dcbnl ]
>             \                    /
>                \              /
>                   \        /
>                 [ hclge_dcb ]
>                   /      \
>                /            \
>             /                  \
>     [ hclgc_main ]        [ hclge_tm ]
>
>hns3_enet.c implements the ndo_setup_tc callback.
>hns3_dcbnl.c implements the dcbnl_rtnl_ops for stack's DCBNL system.
>hclge_dcb implements the dcb_ops.
>So we already have a generic layer that tc and dcbnl all call from.
>
>> 
>> Also, what happens If I run lldptool concurrently with mqprio? Who wins
>> and is going to configure the mapping?
>
>Both lldptool and tc qdisc cmd use rtnl interface provided by stack, so
>they are both protected by rtnl_lock, so we do not have to do the locking
>in the driver.

I was not asking about locking, which is obvious, I was asking about the
behaviour. Like for example:
If I use tc to configure some mapping, later on I run lldptool and change
the mapping. Does the tc dump show the updated values or the original
ones?

>
>The locking is in rtnetlink_rcv_msg:
>
>	rtnl_lock();
>	handlers = rtnl_dereference(rtnl_msg_handlers[family]);
>	if (handlers) {
>		doit = READ_ONCE(handlers[type].doit);
>		if (doit)
>			err = doit(skb, nlh, extack);
>	}
>	rtnl_unlock();
>
>Thanks.
>
>> 
>> 
>>>
>>>>
>>>>
>>>>
>>>>> I hope I did not misunderstand your question, thanks
>>>>> for your time reviewing.
>>>>
>>>> .
>>>>
>>>
>> 
>> .
>> 
>

Re: [PATCH net-next 10/10] net: hns3: Add mqprio support when interacting with network stack

[Yunsheng Lin]

Hi, Jiri

On 2017/9/25 14:57, Jiri Pirko wrote:
> Mon, Sep 25, 2017 at 02:45:08AM CEST, linyunsheng@huawei.com wrote:
>> Hi, Jiri
>>
>> On 2017/9/24 19:37, Jiri Pirko wrote:
>>> Sat, Sep 23, 2017 at 02:47:20AM CEST, linyunsheng@huawei.com wrote:
>>>> Hi, Jiri
>>>>
>>>> On 2017/9/23 0:03, Jiri Pirko wrote:
>>>>> Fri, Sep 22, 2017 at 04:11:51PM CEST, linyunsheng@huawei.com wrote:
>>>>>> Hi, Jiri
>>>>>>
>>>>>>>> - if (!tc) {
>>>>>>>> + if (if_running) {
>>>>>>>> + (void)hns3_nic_net_stop(netdev);
>>>>>>>> + msleep(100);
>>>>>>>> + }
>>>>>>>> +
>>>>>>>> + ret = (kinfo->dcb_ops && kinfo->dcb_ops->>setup_tc) ?
>>>>>>>> + kinfo->dcb_ops->setup_tc(h, tc, prio_tc) : ->EOPNOTSUPP;
>>>>>>
>>>>>>> This is most odd. Why do you call dcb_ops from >ndo_setup_tc callback?
>>>>>>> Why are you mixing this together? prio->tc mapping >can be done
>>>>>>> directly in dcbnl
>>>>>>
>>>>>> Here is what we do in dcb_ops->setup_tc:
>>>>>> Firstly, if current tc num is different from the tc num
>>>>>> that user provide, then we setup the queues for each
>>>>>> tc.
>>>>>>
>>>>>> Secondly, we tell hardware the pri to tc mapping that
>>>>>> the stack is using. In rx direction, our hardware need
>>>>>> that mapping to put different packet into different tc'
>>>>>> queues according to the priority of the packet, then
>>>>>> rss decides which specific queue in the tc should the
>>>>>> packet goto.
>>>>>>
>>>>>> By mixing, I suppose you meant why we need the
>>>>>> pri to tc infomation?
>>>>>
>>>>> by mixing, I mean what I wrote. You are calling dcb_ops callback from
>>>>> ndo_setup_tc callback. So you are mixing DCBNL subsystem and TC
>>>>> subsystem. Why? Why do you need sch_mqprio? Why DCBNL is not enough for
>>>>> all?
>>>>
>>>> When using lldptool, dcbnl is involved.
>>>>
>>>> But when using tc qdisc, dcbbl is not involved, below is the a few key
>>>> call graph in the kernel when tc qdisc cmd is executed.
>>>>
>>>> cmd:
>>>> tc qdisc add dev eth0 root handle 1:0 mqprio num_tc 4 map 1 2 3 3 1 3 1 1 hw 1
>>>>
>>>> call graph:
>>>> rtnetlink_rcv_msg -> tc_modify_qdisc -> qdisc_create -> mqprio_init ->
>>>> hns3_nic_setup_tc
>>>>
>>>> When hns3_nic_setup_tc is called, we need to know how many tc num and
>>>> prio_tc mapping from the tc_mqprio_qopt which is provided in the paramter
>>>> in the ndo_setup_tc function, and dcb_ops is the our hardware specific
>>>> method to setup the tc related parameter to the hardware, so this is why
>>>> we call dcb_ops callback in ndo_setup_tc callback.
>>>>
>>>> I hope this will answer your question, thanks for your time.
>>>
>>> Okay. I understand that you have a usecase for mqprio mapping offload
>>> without lldptool being involved. Ok. I believe it is wrong to call dcb_ops
>>> from tc callback. You should have a generic layer inside the driver and
>>> call it from both dcb_ops and tc callbacks.
>>
>> Actually, dcb_ops is our generic layer inside the driver.
>> Below is high level architecture:
>>
>>       [ tc qdisc ]	       [ lldpad ]
>>             |                     |
>>             |                     |
>>             |                     |
>>       [ hns3_enet ]        [ hns3_dcbnl ]
>>             \                    /
>>                \              /
>>                   \        /
>>                 [ hclge_dcb ]
>>                   /      \
>>                /            \
>>             /                  \
>>     [ hclgc_main ]        [ hclge_tm ]
>>
>> hns3_enet.c implements the ndo_setup_tc callback.
>> hns3_dcbnl.c implements the dcbnl_rtnl_ops for stack's DCBNL system.
>> hclge_dcb implements the dcb_ops.
>> So we already have a generic layer that tc and dcbnl all call from.
>>
>>>
>>> Also, what happens If I run lldptool concurrently with mqprio? Who wins
>>> and is going to configure the mapping?
>>
>> Both lldptool and tc qdisc cmd use rtnl interface provided by stack, so
>> they are both protected by rtnl_lock, so we do not have to do the locking
>> in the driver.
> 
> I was not asking about locking, which is obvious, I was asking about the
> behaviour. Like for example:
> If I use tc to configure some mapping, later on I run lldptool and change
> the mapping. Does the tc dump show the updated values or the original
> ones?

If it is that case, tc dump show the updated values.
Normally, we use tc qdisc to configure the netdev to use mqprio, and
then use the lldptool the tc_prio mapping, tc schedule mode, tc bandwidth
and pfc option.

if lldptool change the tc num and tc_prio mapping, it will tell the tc
system by the following function which is called in client_ops->setup_tc:
netdev_set_tc_queue
netdev_set_prio_tc_map

So lldptool and tc qdisc can work together.



> 
>>
>> The locking is in rtnetlink_rcv_msg:
>>
>> 	rtnl_lock();
>> 	handlers = rtnl_dereference(rtnl_msg_handlers[family]);
>> 	if (handlers) {
>> 		doit = READ_ONCE(handlers[type].doit);
>> 		if (doit)
>> 			err = doit(skb, nlh, extack);
>> 	}
>> 	rtnl_unlock();
>>
>> Thanks.
>>
>>>
>>>
>>>>
>>>>>
>>>>>
>>>>>
>>>>>> I hope I did not misunderstand your question, thanks
>>>>>> for your time reviewing.
>>>>>
>>>>> .
>>>>>
>>>>
>>>
>>> .
>>>
>>
> 
> .
>