A common task for most drivers is to remember the user-set CPU affinity
to its IRQs. On each netdev reset, the driver should re-assign the
user's settings to the IRQs.

Add CPU affinity mask to napi_config. To delegate the CPU affinity
management to the core, drivers must:
 1 - set the new netdev flag "irq_affinity_auto":
                                       netif_enable_irq_affinity(netdev)
 2 - create the napi with persistent config:
                                       netif_napi_add_config()
 3 - bind an IRQ to the napi instance: netif_napi_set_irq()

the core will then make sure to use re-assign affinity to the napi's
IRQ.

The default IRQ mask is set to one cpu starting from the closest NUMA.

Signed-off-by: Ahmed Zaki <ahmed.z...@intel.com>
---
 include/linux/netdevice.h | 14 +++++++++++-
 net/core/dev.c            | 46 +++++++++++++++++++++++++++++++++------
 2 files changed, 52 insertions(+), 8 deletions(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 6f8b416aa32b..8b31fff8affa 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -351,6 +351,7 @@ struct napi_config {
        u64 gro_flush_timeout;
        u64 irq_suspend_timeout;
        u32 defer_hard_irqs;
+       cpumask_t affinity_mask;
        unsigned int napi_id;
 };
 
@@ -392,8 +393,8 @@ struct napi_struct {
        struct list_head        dev_list;
        struct hlist_node       napi_hash_node;
        int                     irq;
-#ifdef CONFIG_RFS_ACCEL
        struct irq_affinity_notify notify;
+#ifdef CONFIG_RFS_ACCEL
        int                     napi_rmap_idx;
 #endif
        int                     index;
@@ -1995,6 +1996,11 @@ enum netdev_reg_state {
  *
  *     @threaded:      napi threaded mode is enabled
  *
+ *     @irq_affinity_auto: driver wants the core to manage the IRQ affinity.
+ *                         Set by netif_napi_set_irq(), then driver must
+ *                         create persistent napi by netif_napi_add_config()
+ *                         and finally bind napi to IRQ (netif_napi_set_irq).
+ *
  *     @rx_cpu_rmap_auto: driver wants the core to manage the ARFS rmap.
  *                        Set by calling netif_enable_cpu_rmap().
  *
@@ -2405,6 +2411,7 @@ struct net_device {
        struct lock_class_key   *qdisc_tx_busylock;
        bool                    proto_down;
        bool                    threaded;
+       bool                    irq_affinity_auto;
 #ifdef CONFIG_RFS_ACCEL
        bool                    rx_cpu_rmap_auto;
 #endif
@@ -2640,6 +2647,11 @@ static inline void netdev_set_ml_priv(struct net_device 
*dev,
        dev->ml_priv_type = type;
 }
 
+static inline void netif_enable_irq_affinity(struct net_device *dev)
+{
+       dev->irq_affinity_auto = true;
+}
+
 /*
  * Net namespace inlines
  */
diff --git a/net/core/dev.c b/net/core/dev.c
index c965d947b33d..1fb850322868 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -6776,27 +6776,36 @@ int netif_enable_cpu_rmap(struct net_device *dev, 
unsigned int num_irqs)
        return 0;
 }
 EXPORT_SYMBOL(netif_enable_cpu_rmap);
+#endif
 
 static void
-netif_irq_cpu_rmap_notify(struct irq_affinity_notify *notify,
-                         const cpumask_t *mask)
+netif_napi_irq_notify(struct irq_affinity_notify *notify,
+                     const cpumask_t *mask)
 {
        struct napi_struct *napi =
                container_of(notify, struct napi_struct, notify);
+#ifdef CONFIG_RFS_ACCEL
        struct cpu_rmap *rmap = napi->dev->rx_cpu_rmap;
        int err;
+#endif
 
+       if (napi->config && napi->dev->irq_affinity_auto)
+               cpumask_copy(&napi->config->affinity_mask, mask);
+
+#ifdef CONFIG_RFS_ACCEL
        if (rmap && napi->dev->rx_cpu_rmap_auto) {
                err = cpu_rmap_update(rmap, napi->napi_rmap_idx, mask);
                if (err)
                        pr_warn("%s: RMAP update failed (%d)\n",
                                __func__, err);
        }
+#endif
 }
 
 static void
 netif_napi_affinity_release(struct kref *ref)
 {
+#ifdef CONFIG_RFS_ACCEL
        struct napi_struct *napi =
                container_of(ref, struct napi_struct, notify.kref);
        struct cpu_rmap *rmap = napi->dev->rx_cpu_rmap;
@@ -6806,8 +6815,10 @@ netif_napi_affinity_release(struct kref *ref)
 
        rmap->obj[napi->napi_rmap_idx] = NULL;
        cpu_rmap_put(rmap);
+#endif
 }
 
+#ifdef CONFIG_RFS_ACCEL
 static int napi_irq_cpu_rmap_add(struct napi_struct *napi, int irq)
 {
        struct cpu_rmap *rmap = napi->dev->rx_cpu_rmap;
@@ -6816,7 +6827,7 @@ static int napi_irq_cpu_rmap_add(struct napi_struct 
*napi, int irq)
        if (!rmap)
                return -EINVAL;
 
-       napi->notify.notify = netif_irq_cpu_rmap_notify;
+       napi->notify.notify = netif_napi_irq_notify;
        napi->notify.release = netif_napi_affinity_release;
        cpu_rmap_get(rmap);
        rc = cpu_rmap_add(rmap, napi);
@@ -6840,9 +6851,8 @@ static int napi_irq_cpu_rmap_add(struct napi_struct 
*napi, int irq)
 
 void netif_napi_set_irq(struct napi_struct *napi, int irq)
 {
-#ifdef CONFIG_RFS_ACCEL
        int rc;
-#endif
+
        napi->irq = irq;
 
 #ifdef CONFIG_RFS_ACCEL
@@ -6853,8 +6863,18 @@ void netif_napi_set_irq(struct napi_struct *napi, int 
irq)
                                    rc);
                        netif_disable_cpu_rmap(napi->dev);
                }
-       }
+       } else if (irq > 0 && napi->config && napi->dev->irq_affinity_auto) {
+#else
+       if (irq > 0 && napi->config && napi->dev->irq_affinity_auto) {
 #endif
+               napi->notify.notify = netif_napi_irq_notify;
+               napi->notify.release = netif_napi_affinity_release;
+
+               rc = irq_set_affinity_notifier(irq, &napi->notify);
+               if (rc)
+                       netdev_warn(napi->dev, "Unable to set IRQ notifier 
(%d)\n",
+                                   rc);
+       }
 }
 EXPORT_SYMBOL(netif_napi_set_irq);
 
@@ -6863,6 +6883,10 @@ static void napi_restore_config(struct napi_struct *n)
        n->defer_hard_irqs = n->config->defer_hard_irqs;
        n->gro_flush_timeout = n->config->gro_flush_timeout;
        n->irq_suspend_timeout = n->config->irq_suspend_timeout;
+
+       if (n->irq > 0 && n->dev->irq_affinity_auto)
+               irq_set_affinity(n->irq, &n->config->affinity_mask);
+
        /* a NAPI ID might be stored in the config, if so use it. if not, use
         * napi_hash_add to generate one for us.
         */
@@ -6879,6 +6903,10 @@ static void napi_save_config(struct napi_struct *n)
        n->config->defer_hard_irqs = n->defer_hard_irqs;
        n->config->gro_flush_timeout = n->gro_flush_timeout;
        n->config->irq_suspend_timeout = n->irq_suspend_timeout;
+
+       if (n->irq > 0 && n->dev->irq_affinity_auto)
+               irq_set_affinity_notifier(n->irq, NULL);
+
        napi_hash_del(n);
 }
 
@@ -11377,7 +11405,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, 
const char *name,
 {
        struct net_device *dev;
        size_t napi_config_sz;
-       unsigned int maxqs;
+       unsigned int maxqs, i, numa;
 
        BUG_ON(strlen(name) >= sizeof(dev->name));
 
@@ -11473,6 +11501,10 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, 
const char *name,
        dev->napi_config = kvzalloc(napi_config_sz, GFP_KERNEL_ACCOUNT);
        if (!dev->napi_config)
                goto free_all;
+       numa = dev_to_node(&dev->dev);
+       for (i = 0; i < maxqs; i++)
+               cpumask_set_cpu(cpumask_local_spread(i, numa),
+                               &dev->napi_config[i].affinity_mask);
 
        strscpy(dev->name, name);
        dev->name_assign_type = name_assign_type;
-- 
2.43.0

Reply via email to