Re: [Patch net-next v6 3/7] r8169: add support for new interrupt mapping

[Heiner Kallweit]

On 26.05.2026 10:11, javen wrote:
> From: Javen Xu <javen_xu@xxxxxxxxxxxxxx>
> 
> To support RSS, the number of hardware interrupt bits should match the
> interrupt of software. So we add support for new interrupt mapping here.
> ISR_VER_MAP_REG is the hardware register to indicate interrupt status.
> IMR_SET_VEC_MAP_REG is interrupt mask which is set to enable irq.
> 
> Signed-off-by: Javen Xu <javen_xu@xxxxxxxxxxxxxx>
> ---
> Changes in v2:
>  - no changes
> 
> Changes in v3:
>  - init index in napi_struct and get message_id from index
>  - move rtl8169_disable_hw_interrupt_msix directly before the call to
>    napi_schedule()
>  - change the condition in rtl8169_request_irq when RTL_VEC_MAP_ENABLE
>    enabled, use rtl8169_interrupt_msix
> 
> Changes in v4:
>  - remove flag tp->feature, replace tp->features & RTL_VEC_MAP_ENABLE
>    with tp->irq_nvecs > 1, they are equivalent.
>  - follow reverse xmas tree, in rtl8169_interrupt_msix(),
>    rtl8169_poll_msix_rx(), rtl8169_poll_msix_tx(),
>    rtl8169_poll_msix_other()
>  - use napi->index in rtl8169_poll_msix_other()
>  - add a comment to describe RTL8127 MSI-X vector layout
>  - simplify r8169_init_napi()
> 
> Changes in v5:
>  - replace magic number in rtl8169_poll_msix_tx()
> 
> Changes in v6:
>  - when irq_nvecs <= 1, use register IntrMask_8125, else using vec map
>  - fix irq sequence in rtl8169_interrupt_msix(), disable interrupts
>    before clean it
>  - remove dead code in rtl8169_poll_msix_tx()
> ---
>  drivers/net/ethernet/realtek/r8169_main.c | 166 +++++++++++++++++++---
>  1 file changed, 150 insertions(+), 16 deletions(-)
> 
> diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
> index 62bf77aa1ec8..951d2046a81b 100644
> --- a/drivers/net/ethernet/realtek/r8169_main.c
> +++ b/drivers/net/ethernet/realtek/r8169_main.c
> @@ -79,6 +79,7 @@
>  #define R8169_TX_START_THRS	(2 * R8169_TX_STOP_THRS)
>  #define R8169_MAX_RX_QUEUES	8
>  #define R8127_MAX_RX_QUEUES	8
> +#define R8127_MAX_TX_QUEUES	8
>  #define R8169_DEFAULT_RX_QUEUES	1
>  #define R8169_MAX_TX_QUEUES	1
>  
> @@ -449,8 +450,12 @@ enum rtl8125_registers {
>  	RSS_CTRL_8125		= 0x4500,
>  	Q_NUM_CTRL_8125		= 0x4800,
>  	EEE_TXIDLE_TIMER_8125	= 0x6048,
> +	IMR_CLEAR_VEC_MAP_REG	= 0x0d00,
> +	ISR_VEC_MAP_REG		= 0x0d04,
> +	IMR_SET_VEC_MAP_REG	= 0x0d0c,
>  };
>  
> +#define MSIX_ID_VEC_MAP_LINKCHG	29
>  #define LEDSEL_MASK_8125	0x23f
>  
>  #define RX_VLAN_INNER_8125	BIT(22)
> @@ -581,6 +586,9 @@ enum rtl_register_content {
>  
>  	/* magic enable v2 */
>  	MagicPacket_v2	= (1 << 16),	/* Wake up when receives a Magic Packet */
> +#define	ISRIMR_LINKCHG	BIT(29)
> +#define	ISRIMR_TOK_Q0	BIT(8)
> +#define	ISRIMR_ROK_Q0	BIT(0)
>  };
>  
>  enum rtl_desc_bit {
> @@ -1664,26 +1672,38 @@ static u32 rtl_get_events(struct rtl8169_private *tp)
>  
>  static void rtl_ack_events(struct rtl8169_private *tp, u32 bits)
>  {
> -	if (rtl_is_8125(tp))
> -		RTL_W32(tp, IntrStatus_8125, bits);
> -	else
> +	if (rtl_is_8125(tp)) {
> +		if (tp->irq_nvecs > 1)
> +			RTL_W32(tp, ISR_VEC_MAP_REG, bits);
> +		else
> +			RTL_W32(tp, IntrStatus_8125, bits);
> +	} else {
>  		RTL_W16(tp, IntrStatus, bits);
> +	}
>  }
>  
>  static void rtl_irq_disable(struct rtl8169_private *tp)
>  {
> -	if (rtl_is_8125(tp))
> -		RTL_W32(tp, IntrMask_8125, 0);
> -	else
> +	if (rtl_is_8125(tp)) {
> +		if (tp->irq_nvecs > 1)
> +			RTL_W32(tp, IMR_CLEAR_VEC_MAP_REG, 0xffffffff);
> +		else
> +			RTL_W32(tp, IntrMask_8125, 0);
> +	} else {
>  		RTL_W16(tp, IntrMask, 0);
> +	}
>  }
>  
>  static void rtl_irq_enable(struct rtl8169_private *tp)
>  {
> -	if (rtl_is_8125(tp))
> -		RTL_W32(tp, IntrMask_8125, tp->irq_mask);
> -	else
> +	if (rtl_is_8125(tp)) {
> +		if (tp->irq_nvecs > 1)
> +			RTL_W32(tp, IMR_SET_VEC_MAP_REG, tp->irq_mask);
> +		else
> +			RTL_W32(tp, IntrMask_8125, tp->irq_mask);
> +	} else {
>  		RTL_W16(tp, IntrMask, tp->irq_mask);
> +	}
>  }
>  
>  static void rtl8169_irq_mask_and_ack(struct rtl8169_private *tp)
> @@ -5062,6 +5082,45 @@ static void rtl8169_free_irq(struct rtl8169_private *tp)
>  	}
>  }
>  
> +static void rtl8169_disable_hw_interrupt_msix(struct rtl8169_private *tp, int message_id)
> +{
> +	RTL_W32(tp, IMR_CLEAR_VEC_MAP_REG, BIT(message_id));
> +}
> +
> +static void rtl8169_clear_hw_isr(struct rtl8169_private *tp, int message_id)
> +{
> +	RTL_W32(tp, ISR_VEC_MAP_REG, BIT(message_id));
> +}
> +
> +static void rtl8169_enable_hw_interrupt_msix(struct rtl8169_private *tp, int message_id)
> +{
> +	RTL_W32(tp, IMR_SET_VEC_MAP_REG, BIT(message_id));
> +}
> +
> +static irqreturn_t rtl8169_interrupt_msix(int irq, void *dev_instance)
> +{
> +	struct napi_struct *napi = dev_instance;
> +	struct net_device *dev = napi->dev;
> +	int message_id = napi->index;
> +	struct rtl8169_private *tp;
> +
> +	tp = netdev_priv(dev);
> +
> +	if (message_id == MSIX_ID_VEC_MAP_LINKCHG) {
> +		rtl8169_clear_hw_isr(tp, message_id);
> +		phy_mac_interrupt(tp->phydev);
> +		return IRQ_HANDLED;
> +	}
> +
> +	rtl8169_disable_hw_interrupt_msix(tp, message_id);
> +	rtl8169_clear_hw_isr(tp, message_id);
> +
> +	tp->recheck_desc_ownbit = true;
> +	napi_schedule(napi);
> +
> +	return IRQ_HANDLED;
> +}
> +
>  static int rtl8169_request_irq(struct rtl8169_private *tp)
>  {
>  	struct net_device *dev = tp->dev;
> @@ -5070,8 +5129,12 @@ static int rtl8169_request_irq(struct rtl8169_private *tp)
>  
>  	for (i = 0; i < tp->irq_nvecs; i++) {
>  		napi = &tp->rtl8169_napi[i];
> -		rc = pci_request_irq(tp->pci_dev, i, rtl8169_interrupt,
> -				     NULL, napi, "%s-%d", dev->name, i);
> +		if (tp->irq_nvecs > 1)
> +			rc = pci_request_irq(tp->pci_dev, i, rtl8169_interrupt_msix,
> +					     NULL, napi, "%s-%d", dev->name, i);
> +		else
> +			rc = pci_request_irq(tp->pci_dev, i, rtl8169_interrupt,
> +					     NULL, napi, "%s-%d", dev->name, i);
>  		if (rc)
>  			goto free_irq;
>  	}
> @@ -5517,10 +5580,16 @@ static const struct net_device_ops rtl_netdev_ops = {
>  
>  static void rtl_set_irq_mask(struct rtl8169_private *tp)
>  {
> -	tp->irq_mask = RxOK | RxErr | TxOK | TxErr | LinkChg;
> +	if (tp->irq_nvecs > 1) {
> +		tp->irq_mask = ISRIMR_LINKCHG | ISRIMR_TOK_Q0;
> +		for (int i = 0; i < tp->num_rx_rings; i++)
> +			tp->irq_mask |= ISRIMR_ROK_Q0 << i;
> +	} else {
> +		tp->irq_mask = RxOK | RxErr | TxOK | TxErr | LinkChg;
>  
> -	if (tp->mac_version <= RTL_GIGA_MAC_VER_06)
> -		tp->irq_mask |= SYSErr | RxFIFOOver;
> +		if (tp->mac_version <= RTL_GIGA_MAC_VER_06)
> +			tp->irq_mask |= SYSErr | RxFIFOOver;
> +	}
>  }
>  
>  static int rtl_alloc_irq(struct rtl8169_private *tp)
> @@ -5825,10 +5894,75 @@ static void r8169_del_napi_action(void *data)
>  		netif_napi_del(&tp->rtl8169_napi[i]);
>  }
>  
> +static int rtl8169_poll_msix_rx(struct napi_struct *napi, int budget)
> +{
> +	struct net_device *dev = napi->dev;
> +	const int message_id = napi->index;
> +	struct rtl8169_private *tp;
> +	int work_done = 0;
> +
> +	tp = netdev_priv(dev);
> +
> +	if (message_id < tp->num_rx_rings)
> +		work_done += rtl_rx(dev, tp, &tp->rx_ring[message_id], budget);
> +
> +	if (work_done < budget && napi_complete_done(napi, work_done))
> +		rtl8169_enable_hw_interrupt_msix(tp, message_id);
> +
> +	return work_done;
> +}
> +
> +static int rtl8169_poll_msix_tx(struct napi_struct *napi, int budget)
> +{
> +	struct net_device *dev = napi->dev;
> +	const int message_id = napi->index;
> +	struct rtl8169_private *tp;
> +
> +	tp = netdev_priv(dev);
> +
> +	rtl_tx(dev, tp, budget);
> +
> +	if (napi_complete_done(napi, 0))
> +		rtl8169_enable_hw_interrupt_msix(tp, message_id);
> +
> +	return 0;
> +}
> +
> +static int rtl8169_poll_msix_other(struct napi_struct *napi, int budget)
> +{
> +	struct net_device *dev = napi->dev;
> +	const int message_id = napi->index;

This variable is used only once, I don't really see a benefit.

> +	struct rtl8169_private *tp;
> +
> +	tp = netdev_priv(dev);
> +
> +	if (napi_complete_done(napi, 0))
> +		rtl8169_enable_hw_interrupt_msix(tp, message_id);
> +
> +	return 0;
> +}
> +
> +/* RTL8127 MSI-X vector layout:
> + * Vectors 0 .. (RxQs - 1)		: Rx Queues
> + * Vectors RxQs .. (RxQs + TxQs - 1)	: Tx Queues
> + * Vector (RxQs + TxQs) and up		: Other events (Link status(29), etc.)
> + */
>  static void r8169_init_napi(struct rtl8169_private *tp)
>  {
> -	for (int i = 0; i < tp->irq_nvecs; i++)
> -		netif_napi_add(tp->dev, &tp->rtl8169_napi[i], rtl8169_poll);
> +	for (int i = 0; i < tp->irq_nvecs; i++) {
> +		int (*poll_fn)(struct napi_struct *, int) = rtl8169_poll;
> +
> +		if (tp->irq_nvecs > 1) {
> +			if (i < R8127_MAX_RX_QUEUES)
> +				poll_fn = rtl8169_poll_msix_rx;
> +			else if (i < R8127_MAX_RX_QUEUES + R8127_MAX_TX_QUEUES)
> +				poll_fn = rtl8169_poll_msix_tx;
> +			else
> +				poll_fn = rtl8169_poll_msix_other;
> +		}
> +		netif_napi_add(tp->dev, &tp->rtl8169_napi[i], poll_fn);
> +		tp->rtl8169_napi[i].index = i;
> +	}
>  	devm_add_action_or_reset(&tp->pci_dev->dev, r8169_del_napi_action, tp);
>  }
>