The buffer pool is a quantity of memory available for buffering a group
of flows (e.g. frames having the same priority, frames received from the
same port), while waiting to be transmitted on a port. The buffer pool
tracks internal memory consumption with upper bound limits and optionally
a non-shared portion when associated with a shared buffer pool. Currently
the shared buffer pool is not supported, it will be added in the future.

For i.MX94, the switch has 4 ports and 8 buffer pools, so each port is
allocated two buffer pools. For frames with priorities of 0 to 3, they
will be mapped to the first buffer pool; For frames with priorities of
4 to 7, they will be mapped to the second buffer pool. Each buffer pool
has a flow control on threshold and a flow control off threshold. By
setting these threshold, add the flow control support to each port.

Signed-off-by: Wei Fang <wei.fang@nxp.com>
---
 drivers/net/dsa/netc/netc_main.c      | 133 ++++++++++++++++++++++++++
 drivers/net/dsa/netc/netc_switch.h    |   9 ++
 drivers/net/dsa/netc/netc_switch_hw.h |  12 +++
 3 files changed, 154 insertions(+)

diff --git a/drivers/net/dsa/netc/netc_main.c b/drivers/net/dsa/netc/netc_main.c
index 4b331971dd8c..2a7ad39f8bed 100644
--- a/drivers/net/dsa/netc/netc_main.c
+++ b/drivers/net/dsa/netc/netc_main.c
@@ -379,6 +379,8 @@ static void netc_port_set_mlo(struct netc_port *np, enum netc_mlo mlo)
 
 static void netc_port_fixed_config(struct netc_port *np)
 {
+	u32 pqnt = 0xffff, qth = 0xff00;
+
 	/* Default IPV and DR setting */
 	netc_port_rmw(np, NETC_PQOSMR, PQOSMR_VS | PQOSMR_VE,
 		      PQOSMR_VS | PQOSMR_VE);
@@ -386,6 +388,15 @@ static void netc_port_fixed_config(struct netc_port *np)
 	/* Enable L2 and L3 DOS */
 	netc_port_rmw(np, NETC_PCR, PCR_L2DOSE | PCR_L3DOSE,
 		      PCR_L2DOSE | PCR_L3DOSE);
+
+	/* Set the quanta value of TX PAUSE frame */
+	netc_mac_port_wr(np, NETC_PM_PAUSE_QUANTA(0), pqnt);
+
+	/* When a quanta timer counts down and reaches this value,
+	 * the MAC sends a refresh PAUSE frame with the programmed
+	 * full quanta value if a pause condition still exists.
+	 */
+	netc_mac_port_wr(np, NETC_PM_PAUSE_TRHESH(0), qth);
 }
 
 static void netc_port_default_config(struct netc_port *np)
@@ -617,6 +628,80 @@ static int netc_add_standalone_fdb_bcast_entry(struct netc_switch *priv)
 				       bcast, NETC_STANDALONE_PVID);
 }
 
+static u32 netc_get_buffer_pool_num(struct netc_switch *priv)
+{
+	return netc_base_rd(&priv->regs, NETC_BPCAPR) & BPCAPR_NUM_BP;
+}
+
+static void netc_port_set_pbpmcr(struct netc_port *np, u64 mapping)
+{
+	u32 pbpmcr0 = lower_32_bits(mapping);
+	u32 pbpmcr1 = upper_32_bits(mapping);
+
+	netc_port_wr(np, NETC_PBPMCR0, pbpmcr0);
+	netc_port_wr(np, NETC_PBPMCR1, pbpmcr1);
+}
+
+static void netc_ipv_to_buffer_pool_mapping(struct netc_switch *priv)
+{
+	int num_port_bp = priv->num_bp / priv->info->num_ports;
+	int q = NETC_IPV_NUM / num_port_bp;
+	int r = NETC_IPV_NUM % num_port_bp;
+	int num = q + r;
+
+	/* IPV-to–buffer-pool mapping per port:
+	 * Each port is allocated 'num_port_bp' buffer pools and supports 8
+	 * IPVs, where a higher IPV indicates a higher frame priority. Each
+	 * IPV can be mapped to only one buffer pool.
+	 *
+	 * The mapping rule is as follows:
+	 * - The first 'num' IPVs share the port's first buffer pool (index
+	 * 'base_id').
+	 * - After that, every 'q' IPVs share one buffer pool, with pool
+	 * indices increasing sequentially.
+	 */
+	for (int i = 0; i < priv->info->num_ports; i++) {
+		u32 base_id = i * num_port_bp;
+		u32 bp_id = base_id;
+		u64 mapping = 0;
+
+		for (int ipv = 0; ipv < NETC_IPV_NUM; ipv++) {
+			/* Update the buffer pool index */
+			if (ipv >= num)
+				bp_id = base_id + ((ipv - num) / q) + 1;
+
+			mapping |= (u64)bp_id << (ipv * 8);
+		}
+
+		netc_port_set_pbpmcr(priv->ports[i], mapping);
+	}
+}
+
+static int netc_switch_bpt_default_config(struct netc_switch *priv)
+{
+	priv->num_bp = netc_get_buffer_pool_num(priv);
+	priv->bpt_list = devm_kcalloc(priv->dev, priv->num_bp,
+				      sizeof(struct bpt_cfge_data),
+				      GFP_KERNEL);
+	if (!priv->bpt_list)
+		return -ENOMEM;
+
+	/* Initialize the maximum threshold of each buffer pool entry */
+	for (int i = 0; i < priv->num_bp; i++) {
+		struct bpt_cfge_data *cfge = &priv->bpt_list[i];
+		int err;
+
+		cfge->max_thresh = cpu_to_le16(NETC_BP_THRESH);
+		err = ntmp_bpt_update_entry(&priv->ntmp, i, cfge);
+		if (err)
+			return err;
+	}
+
+	netc_ipv_to_buffer_pool_mapping(priv);
+
+	return 0;
+}
+
 static int netc_setup(struct dsa_switch *ds)
 {
 	struct netc_switch *priv = ds->priv;
@@ -644,6 +729,10 @@ static int netc_setup(struct dsa_switch *ds)
 	dsa_switch_for_each_available_port(dp, ds)
 		netc_port_default_config(priv->ports[dp->index]);
 
+	err = netc_switch_bpt_default_config(priv);
+	if (err)
+		goto free_lock_and_ntmp_user;
+
 	err = netc_add_standalone_vlan_entry(priv);
 	if (err)
 		goto free_lock_and_ntmp_user;
@@ -1224,6 +1313,40 @@ static void netc_port_set_hd_flow_control(struct netc_port *np, bool en)
 			  en ? PM_CMD_CFG_HD_FCEN : 0);
 }
 
+static void netc_port_set_tx_pause(struct netc_port *np, bool tx_pause)
+{
+	struct netc_switch *priv = np->switch_priv;
+	int port = np->dp->index;
+	int i, j, num_bp;
+
+	num_bp = priv->num_bp / priv->info->num_ports;
+	for (i = 0, j = port * num_bp; i < num_bp; i++, j++) {
+		struct bpt_cfge_data *cfge;
+
+		cfge = &priv->bpt_list[j];
+		if (tx_pause) {
+			cfge->fc_on_thresh = cpu_to_le16(NETC_FC_THRESH_ON);
+			cfge->fc_off_thresh = cpu_to_le16(NETC_FC_THRESH_OFF);
+			cfge->fccfg_sbpen = FIELD_PREP(BPT_FC_CFG,
+						       BPT_FC_CFG_EN_BPFC);
+			cfge->fc_ports = cpu_to_le32(BIT(port));
+		} else {
+			cfge->fc_on_thresh = cpu_to_le16(0);
+			cfge->fc_off_thresh = cpu_to_le16(0);
+			cfge->fccfg_sbpen = 0;
+			cfge->fc_ports = cpu_to_le32(0);
+		}
+
+		ntmp_bpt_update_entry(&priv->ntmp, j, cfge);
+	}
+}
+
+static void netc_port_set_rx_pause(struct netc_port *np, bool rx_pause)
+{
+	netc_mac_port_rmw(np, NETC_PM_CMD_CFG(0), PM_CMD_CFG_PAUSE_IGN,
+			  rx_pause ? 0 : PM_CMD_CFG_PAUSE_IGN);
+}
+
 static void netc_port_mac_rx_enable(struct netc_port *np)
 {
 	netc_port_rmw(np, NETC_POR, PCR_RXDIS, 0);
@@ -1288,7 +1411,17 @@ static void netc_mac_link_up(struct phylink_config *config,
 		netc_port_set_rmii_mii_mac(np, speed, duplex);
 	}
 
+	if (duplex == DUPLEX_HALF) {
+		/* As per 802.3 annex 31B, PAUSE frames are only supported
+		 * when the link is configured for full duplex operation.
+		 */
+		tx_pause = false;
+		rx_pause = false;
+	}
+
 	netc_port_set_hd_flow_control(np, duplex == DUPLEX_HALF);
+	netc_port_set_tx_pause(np, tx_pause);
+	netc_port_set_rx_pause(np, rx_pause);
 	netc_port_mac_rx_enable(np);
 }
 
diff --git a/drivers/net/dsa/netc/netc_switch.h b/drivers/net/dsa/netc/netc_switch.h
index 4b229a71578e..7ebffb136b2f 100644
--- a/drivers/net/dsa/netc/netc_switch.h
+++ b/drivers/net/dsa/netc/netc_switch.h
@@ -32,6 +32,12 @@
 
 #define NETC_STANDALONE_PVID		0
 
+#define NETC_IPV_NUM			8
+/* MANT = bits 11:4, EXP = bits 3:0, threshold = MANT * 2 ^ EXP */
+#define NETC_BP_THRESH			0x334
+#define NETC_FC_THRESH_ON		0x533
+#define NETC_FC_THRESH_OFF		0x3c3
+
 struct netc_switch;
 
 struct netc_switch_info {
@@ -90,6 +96,9 @@ struct netc_switch {
 	struct ntmp_user ntmp;
 	struct hlist_head fdb_list;
 	struct mutex fdbt_lock; /* FDB table lock */
+
+	u32 num_bp;
+	struct bpt_cfge_data *bpt_list;
 };
 
 #define NETC_PRIV(ds)			((struct netc_switch *)((ds)->priv))
diff --git a/drivers/net/dsa/netc/netc_switch_hw.h b/drivers/net/dsa/netc/netc_switch_hw.h
index a2b0c1a712f8..7ef870fbba4d 100644
--- a/drivers/net/dsa/netc/netc_switch_hw.h
+++ b/drivers/net/dsa/netc/netc_switch_hw.h
@@ -12,6 +12,12 @@
 #define NETC_SWITCH_DEVICE_ID		0xeef2
 
 /* Definition of Switch base registers */
+#define NETC_BPCAPR			0x0008
+#define  BPCAPR_NUM_BP			GENMASK(7, 0)
+
+#define NETC_PBPMCR0			0x0400
+#define NETC_PBPMCR1			0x0404
+
 #define NETC_CBDRMR(a)			(0x0800 + (a) * 0x30)
 #define NETC_CBDRBAR0(a)		(0x0810 + (a) * 0x30)
 #define NETC_CBDRBAR1(a)		(0x0814 + (a) * 0x30)
@@ -163,6 +169,12 @@ enum netc_stg_stage {
 #define NETC_PM_IEVENT(a)		(0x1040 + (a) * 0x400)
 #define  PM_IEVENT_RX_EMPTY		BIT(6)
 
+#define NETC_PM_PAUSE_QUANTA(a)		(0x1054 + (a) * 0x400)
+#define  PAUSE_QUANTA_PQNT		GENMASK(15, 0)
+
+#define NETC_PM_PAUSE_TRHESH(a)		(0x1064 + (a) * 0x400)
+#define  PAUSE_TRHESH_QTH		GENMASK(15, 0)
+
 #define NETC_PM_IF_MODE(a)		(0x1300 + (a) * 0x400)
 #define  PM_IF_MODE_IFMODE		GENMASK(2, 0)
 #define   IFMODE_MII			1
-- 
2.34.1

This is an AI-generated review of your patch. The human sending this
email has considered the AI review valid, or at least plausible.

For local reproduction steps see https://netdev-ai.bots.linux.dev/ai-local.html
---
net: dsa: netc: initialize buffer bool table and implement flow-control

The buffer pool is a quantity of memory available for buffering a group
of flows (e.g. frames having the same priority, frames received from the
same port), while waiting to be transmitted on a port. The buffer pool
tracks internal memory consumption with upper bound limits and optionally
a non-shared portion when associated with a shared buffer pool. Currently
the shared buffer pool is not supported, it will be added in the future.

For i.MX94, the switch has 4 ports and 8 buffer pools, so each port is
allocated two buffer pools. For frames with priorities of 0 to 3, they
will be mapped to the first buffer pool; For frames with priorities of
4 to 7, they will be mapped to the second buffer pool. Each buffer pool
has a flow control on threshold and a flow control off threshold. By
setting these threshold, add the flow control support to each port.

> diff --git a/drivers/net/dsa/netc/netc_main.c b/drivers/net/dsa/netc/netc_main.c
> index 4b331971dd8c..2a7ad39f8bed 100644
> --- a/drivers/net/dsa/netc/netc_main.c
> +++ b/drivers/net/dsa/netc/netc_main.c

[ ... ]

> @@ -617,6 +628,80 @@ static int netc_add_standalone_fdb_bcast_entry(struct netc_switch *priv)
>  				       bcast, NETC_STANDALONE_PVID);
>  }
>
> +static u32 netc_get_buffer_pool_num(struct netc_switch *priv)
> +{
> +	return netc_base_rd(&priv->regs, NETC_BPCAPR) & BPCAPR_NUM_BP;
> +}
> +
> +static void netc_port_set_pbpmcr(struct netc_port *np, u64 mapping)
> +{
> +	u32 pbpmcr0 = lower_32_bits(mapping);
> +	u32 pbpmcr1 = upper_32_bits(mapping);
> +
> +	netc_port_wr(np, NETC_PBPMCR0, pbpmcr0);
> +	netc_port_wr(np, NETC_PBPMCR1, pbpmcr1);
> +}
> +
> +static void netc_ipv_to_buffer_pool_mapping(struct netc_switch *priv)
> +{
> +	int num_port_bp = priv->num_bp / priv->info->num_ports;
> +	int q = NETC_IPV_NUM / num_port_bp;
>                ^^^^

Can this cause a division by zero?  If netc_get_buffer_pool_num() reads
the hardware register NETC_BPCAPR and returns 0, then num_port_bp would be
0 and this division would crash the kernel.

The call chain is:

netc_setup()
  netc_switch_bpt_default_config()
    priv->num_bp = netc_get_buffer_pool_num()
    netc_ipv_to_buffer_pool_mapping()
      num_port_bp = priv->num_bp / priv->info->num_ports;
      q = NETC_IPV_NUM / num_port_bp;  <- division by zero

Should netc_switch_bpt_default_config() validate that priv->num_bp is
non-zero before proceeding?

> +	int r = NETC_IPV_NUM % num_port_bp;
> +	int num = q + r;
> +
> +	/* IPV-to–buffer-pool mapping per port:

[ ... ]

> +static int netc_switch_bpt_default_config(struct netc_switch *priv)
> +{
> +	priv->num_bp = netc_get_buffer_pool_num(priv);
> +	priv->bpt_list = devm_kcalloc(priv->dev, priv->num_bp,
> +				      sizeof(struct bpt_cfge_data),
> +				      GFP_KERNEL);
> +	if (!priv->bpt_list)
> +		return -ENOMEM;
> +
> +	/* Initialize the maximum threshold of each buffer pool entry */
> +	for (int i = 0; i < priv->num_bp; i++) {
> +		struct bpt_cfge_data *cfge = &priv->bpt_list[i];
> +		int err;
> +
> +		cfge->max_thresh = cpu_to_le16(NETC_BP_THRESH);
> +		err = ntmp_bpt_update_entry(&priv->ntmp, i, cfge);
> +		if (err)
> +			return err;
> +	}
> +
> +	netc_ipv_to_buffer_pool_mapping(priv);
> +
> +	return 0;
> +}
> +

[ ... ]

> @@ -1224,6 +1313,40 @@ static void netc_port_set_hd_flow_control(struct netc_port *np, bool en)
>  			  en ? PM_CMD_CFG_HD_FCEN : 0);
>  }
>
> +static void netc_port_set_tx_pause(struct netc_port *np, bool tx_pause)
> +{
> +	struct netc_switch *priv = np->switch_priv;
> +	int port = np->dp->index;
> +	int i, j, num_bp;
> +
> +	num_bp = priv->num_bp / priv->info->num_ports;
> +	for (i = 0, j = port * num_bp; i < num_bp; i++, j++) {
> +		struct bpt_cfge_data *cfge;
> +
> +		cfge = &priv->bpt_list[j];
> +		if (tx_pause) {
> +			cfge->fc_on_thresh = cpu_to_le16(NETC_FC_THRESH_ON);
> +			cfge->fc_off_thresh = cpu_to_le16(NETC_FC_THRESH_OFF);
> +			cfge->fccfg_sbpen = FIELD_PREP(BPT_FC_CFG,
> +						       BPT_FC_CFG_EN_BPFC);
> +			cfge->fc_ports = cpu_to_le32(BIT(port));
> +		} else {
> +			cfge->fc_on_thresh = cpu_to_le16(0);
> +			cfge->fc_off_thresh = cpu_to_le16(0);
> +			cfge->fccfg_sbpen = 0;
> +			cfge->fc_ports = cpu_to_le32(0);
> +		}
> +
> +		ntmp_bpt_update_entry(&priv->ntmp, j, cfge);
>                 ^^^^

Should the return value of ntmp_bpt_update_entry() be checked here?

Simon Horman noted in v1 review that other NTMP table operations in the
driver propagate errors from the update functions. While this was fixed
in netc_switch_bpt_default_config() in v2, the same issue remains here.

If the hardware update fails (for example, DMA allocation failure or
hardware timeout), the driver's bpt_list will have flow control values that
do not match the actual hardware state, potentially causing incorrect flow
control behavior.

https://lore.kernel.org/netdev/20260318145452.1898637-2-horms@kernel.org/

> +	}
> +}
> +

[ ... ]

On Mon, Mar 23, 2026 at 02:07:51PM +0800, Wei Fang wrote:
> @@ -1288,7 +1411,17 @@ static void netc_mac_link_up(struct phylink_config *config,
>  		netc_port_set_rmii_mii_mac(np, speed, duplex);
>  	}
>  
> +	if (duplex == DUPLEX_HALF) {
> +		/* As per 802.3 annex 31B, PAUSE frames are only supported
> +		 * when the link is configured for full duplex operation.
> +		 */
> +		tx_pause = false;
> +		rx_pause = false;
> +	}

I keep seeing this totally unnecessary code in reviews of mac_link_up()
methods. See phylink_resolve_an_pause().

-- 
RMK's Patch system: https://www.armlinux.org.uk/developer/patches/
FTTP is here! 80Mbps down 10Mbps up. Decent connectivity at last!