RE: [PATCH net-next v11 3/7] r8169: add support for new interrupt mapping

On 8/13/26 6:51 PM, javen wrote:

quoted

From: Javen Xu <redacted>

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_VEC_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 <redacted>
---
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()

Changes in v7:
  - remove recheck_desc_ownbit
  - change return value of rtl_tx
  - remove message_id which only used once

Changes in v8:
  - fix rtl8169_netpoll()
  - remove tx_done

Changes in v9:
  - change the way of getting message_id of napi

Changes in v10:
  - no changes

Changes in v11:
  - add comment on rtl8169_poll_msix_tx, only use 1 tx
  - remove napi for other. Separate napi only for datapath, control path
    like linkchg is handled in interrupt function, which will not call
    napi any more.
---
  drivers/net/ethernet/realtek/r8169_main.c | 213 +++++++++++++++++++---
  1 file changed, 187 insertions(+), 26 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169_main.c

b/drivers/net/ethernet/realtek/r8169_main.c
index 9311a0cab4eb..b30f0a31d7c7 100644

--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c

@@ -84,6 +84,7 @@
  #define R8169_RX_RING_BYTES ((NUM_RX_DESC + 1) * sizeof(struct

RxDesc))

quoted

  #define R8169_TX_STOP_THRS  (MAX_SKB_FRAGS + 1)
  #define R8169_TX_START_THRS (2 * R8169_TX_STOP_THRS)
+#define R8169_MAX_QUEUES     16
  #define R8169_MAX_RX_QUEUES 8
  #define R8169_DEFAULT_RX_QUEUES     1
  #define R8169_MAX_TX_QUEUES 1

@@ -455,8 +456,12 @@ 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)

@@ -587,6 +592,9 @@ enum rtl_register_content {

      /* magic enable v2 */
      MagicPacket_v2  = (1 << 16),    /* Wake up when receives a Magic Packet

*/

quoted

+#define      ISRIMR_LINKCHG  BIT(29)
+#define      ISRIMR_TOK_Q0   BIT(8)
+#define      ISRIMR_ROK_Q0   BIT(0)
  };

  enum rtl_desc_bit {

@@ -1663,26 +1671,38 @@ 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) @@
-4382,13 +4402,17 @@ static void rtl8169_tx_clear(struct
rtl8169_private *tp)

  static void rtl8169_napi_disable(struct rtl8169_private *tp)
  {
-     for (int i = 0; i < tp->irq_nvecs; i++)
+     int napi_num = min(tp->irq_nvecs, R8169_MAX_QUEUES);
+
+     for (int i = 0; i < napi_num; i++)
              napi_disable(&tp->rtl8169_napi[i]);
  }

  static void rtl8169_napi_enable(struct rtl8169_private *tp)
  {
-     for (int i = 0; i < tp->irq_nvecs; i++)
+     int napi_num = min(tp->irq_nvecs, R8169_MAX_QUEUES);
+
+     for (int i = 0; i < napi_num; i++)
              napi_enable(&tp->rtl8169_napi[i]);
  }

@@ -5030,13 +5054,66 @@ static irqreturn_t rtl8169_interrupt(int irq, void

*dev_instance)

quoted

      return IRQ_HANDLED;
  }

+static void rtl8169_free_one_irq(struct rtl8169_private *tp, int i) {
+     if (tp->irq_nvecs > 1) {
+             if (i < R8169_MAX_QUEUES)
+                     pci_free_irq(tp->pci_dev, i, &tp->rtl8169_napi[i]);
+             else if (i == MSIX_ID_VEC_MAP_LINKCHG)
+                     pci_free_irq(tp->pci_dev, i, tp);
+     } else {
+             pci_free_irq(tp->pci_dev, i, &tp->rtl8169_napi[i]);
+     }
+}
+
  static void rtl8169_free_irq(struct rtl8169_private *tp)
  {
-     for (int i = 0; i < tp->irq_nvecs; i++) {
-             struct napi_struct *napi = &tp->rtl8169_napi[i];
+     for (int i = 0; i < tp->irq_nvecs; i++)
+             rtl8169_free_one_irq(tp, i); }

-             pci_free_irq(tp->pci_dev, i, napi);
-     }
+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;
+     struct rtl8169_private *tp;
+     int message_id;
+
+     tp = netdev_priv(dev);
+     message_id = napi - tp->rtl8169_napi;
+
+     rtl8169_disable_hw_interrupt_msix(tp, message_id);
+     rtl8169_clear_hw_isr(tp, message_id);
+
+     napi_schedule(napi);
+
+     return IRQ_HANDLED;
+}
+
+static irqreturn_t rtl8169_interrupt_other(int irq, void
+*dev_instance) {
+     struct rtl8169_private *tp = dev_instance;
+
+     rtl8169_clear_hw_isr(tp, MSIX_ID_VEC_MAP_LINKCHG);
+     phy_mac_interrupt(tp->phydev);
+     return IRQ_HANDLED;
  }

  static int rtl8169_request_irq(struct rtl8169_private *tp) @@
-5047,8 +5124,26 @@ 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) {
+                     if (i < R8169_MAX_QUEUES)
+                             rc = pci_request_irq(tp->pci_dev, i,
+                                                  rtl8169_interrupt_msix,
+                                                  NULL, napi, "%s-%d",
+                                                  dev->name, i);
+                     else if (i == MSIX_ID_VEC_MAP_LINKCHG)
+                             rc = pci_request_irq(tp->pci_dev, i,
+                                                  rtl8169_interrupt_other,
+                                                  NULL, tp, "%s-%d",
+                                                  dev->name, i);
+                     else
+                             continue;
+             } else {
+                     rc = pci_request_irq(tp->pci_dev, i,
+                                          rtl8169_interrupt,
+                                          NULL, napi, "%s-%d",
+                                          dev->name, i);
+             }
+
              if (rc)
                      goto free_irq;
      }

@@ -5056,7 +5151,7 @@ static int rtl8169_request_irq(struct

rtl8169_private *tp)

  free_irq:
      while (--i >= 0)
-             pci_free_irq(tp->pci_dev, i, &tp->rtl8169_napi[i]);
+             rtl8169_free_one_irq(tp, i);
      return rc;
  }

@@ -5255,8 +5350,12 @@ static void rtl8169_netpoll(struct net_device

*dev)

quoted

      struct rtl8169_private *tp = netdev_priv(dev);

      for (int i = 0; i < tp->irq_nvecs; i++) {

Looking at r8169_init_napi(), later down the patch, it only calls
netif_napi_add() for min(tp->irq_nvecs, R8169_MAX_QUEUES) vectors, but this
loop iterates all tp->irq_nvecs. Can this be an issue? Looks like it will be
because entries entries >= R8169_MAX_QUEUES are zeroed but
rtl8169_interrupt_msix() would set dev to NULL.

Thanks for pointing out this. I have forgotten to modify this.

Thanks,
Javen