[Intel-wired-lan] [PATCH net-next v3 0/6] net: napi: add CPU affinity to napi->config

[Intel-wired-lan] [PATCH net-next v3 0/6] net: napi: add CPU affinity to napi->config

[Ahmed Zaki]

Move the IRQ affinity management to the napi struct. Since there can only
be one IRQ affinity notifier, the ARFS rmap management is moved to CORE
(patches 1 and 2), then the new notifier is extended to save the user-set
IRQ affinity mask in napi_config.

Tested on bnxt, ice and idpf.

v3:
    - Assign one cpu per mask starting from local NUMA node (Shay Drori).
    - Keep the new ARFS and Affinity flags per nedev (Jakub).

v2:
    - https://lore.kernel.org/netdev/202412190454.nwvp3hU2-lkp@intel.com/T/
    - Also move the ARFS IRQ affinity management from drivers to core. Via
      netif_napi_set_irq(), drivers can ask the core to add the IRQ to the
      ARFS rmap (already allocated by the driver).

RFC -> v1:
    - https://lore.kernel.org/netdev/20241210002626.366878-1-ahmed.zaki@intel.com/
    - move static inline affinity functions to net/dev/core.c
    - add the new napi->irq_flags (patch 1)
    - add code changes to bnxt, mlx4 and ice.

Ahmed Zaki (6):
  net: move ARFS rmap management to core
  net: napi: add internal ARFS rmap management
  net: napi: add CPU affinity to napi_config
  bnxt: use napi's irq affinity
  ice: use napi's irq affinity
  idpf: use napi's irq affinity

 drivers/net/ethernet/amazon/ena/ena_netdev.c |  38 +----
 drivers/net/ethernet/broadcom/bnxt/bnxt.c    |  53 ++-----
 drivers/net/ethernet/broadcom/bnxt/bnxt.h    |   2 -
 drivers/net/ethernet/intel/ice/ice.h         |   3 -
 drivers/net/ethernet/intel/ice/ice_arfs.c    |  17 +--
 drivers/net/ethernet/intel/ice/ice_base.c    |   7 +-
 drivers/net/ethernet/intel/ice/ice_lib.c     |   6 -
 drivers/net/ethernet/intel/ice/ice_main.c    |  47 +------
 drivers/net/ethernet/intel/idpf/idpf_lib.c   |   1 +
 drivers/net/ethernet/intel/idpf/idpf_txrx.c  |  22 +--
 drivers/net/ethernet/intel/idpf/idpf_txrx.h  |   6 +-
 include/linux/cpu_rmap.h                     |   1 +
 include/linux/netdevice.h                    |  23 ++-
 lib/cpu_rmap.c                               |   2 +-
 net/core/dev.c                               | 139 ++++++++++++++++++-
 15 files changed, 186 insertions(+), 181 deletions(-)

-- 
2.43.0

[Intel-wired-lan] [PATCH net-next v3 1/6] net: move ARFS rmap management to core

[Ahmed Zaki]

Add a new netdev flag "rx_cpu_rmap_auto". Drivers supporting ARFS should
set the flag via netif_enable_cpu_rmap() and core will allocate and manage
the ARFS rmap. Freeing the rmap is also done by core when the netdev is
freed.

Signed-off-by: Ahmed Zaki <ahmed.zaki@intel.com>
---
 drivers/net/ethernet/amazon/ena/ena_netdev.c | 38 ++---------------
 drivers/net/ethernet/broadcom/bnxt/bnxt.c    | 27 ++----------
 drivers/net/ethernet/intel/ice/ice_arfs.c    | 17 +-------
 include/linux/netdevice.h                    | 12 ++++--
 net/core/dev.c                               | 44 ++++++++++++++++++++
 5 files changed, 60 insertions(+), 78 deletions(-)

diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index c1295dfad0d0..ef1e1b37a60a 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -5,9 +5,6 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
-#ifdef CONFIG_RFS_ACCEL
-#include <linux/cpu_rmap.h>
-#endif /* CONFIG_RFS_ACCEL */
 #include <linux/ethtool.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
@@ -165,25 +162,10 @@ int ena_xmit_common(struct ena_adapter *adapter,
 static int ena_init_rx_cpu_rmap(struct ena_adapter *adapter)
 {
 #ifdef CONFIG_RFS_ACCEL
-	u32 i;
-	int rc;
-
-	adapter->netdev->rx_cpu_rmap = alloc_irq_cpu_rmap(adapter->num_io_queues);
-	if (!adapter->netdev->rx_cpu_rmap)
-		return -ENOMEM;
-	for (i = 0; i < adapter->num_io_queues; i++) {
-		int irq_idx = ENA_IO_IRQ_IDX(i);
-
-		rc = irq_cpu_rmap_add(adapter->netdev->rx_cpu_rmap,
-				      pci_irq_vector(adapter->pdev, irq_idx));
-		if (rc) {
-			free_irq_cpu_rmap(adapter->netdev->rx_cpu_rmap);
-			adapter->netdev->rx_cpu_rmap = NULL;
-			return rc;
-		}
-	}
-#endif /* CONFIG_RFS_ACCEL */
+	return netif_enable_cpu_rmap(adapter->netdev);
+#else
 	return 0;
+#endif /* CONFIG_RFS_ACCEL */
 }
 
 static void ena_init_io_rings_common(struct ena_adapter *adapter,
@@ -1742,13 +1724,6 @@ static void ena_free_io_irq(struct ena_adapter *adapter)
 	struct ena_irq *irq;
 	int i;
 
-#ifdef CONFIG_RFS_ACCEL
-	if (adapter->msix_vecs >= 1) {
-		free_irq_cpu_rmap(adapter->netdev->rx_cpu_rmap);
-		adapter->netdev->rx_cpu_rmap = NULL;
-	}
-#endif /* CONFIG_RFS_ACCEL */
-
 	for (i = ENA_IO_IRQ_FIRST_IDX; i < ENA_MAX_MSIX_VEC(io_queue_count); i++) {
 		irq = &adapter->irq_tbl[i];
 		irq_set_affinity_hint(irq->vector, NULL);
@@ -4131,13 +4106,6 @@ static void __ena_shutoff(struct pci_dev *pdev, bool shutdown)
 	ena_dev = adapter->ena_dev;
 	netdev = adapter->netdev;
 
-#ifdef CONFIG_RFS_ACCEL
-	if ((adapter->msix_vecs >= 1) && (netdev->rx_cpu_rmap)) {
-		free_irq_cpu_rmap(netdev->rx_cpu_rmap);
-		netdev->rx_cpu_rmap = NULL;
-	}
-
-#endif /* CONFIG_RFS_ACCEL */
 	/* Make sure timer and reset routine won't be called after
 	 * freeing device resources.
 	 */
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 46edea75e062..cc3ca3440b0a 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -49,7 +49,6 @@
 #include <linux/cache.h>
 #include <linux/log2.h>
 #include <linux/bitmap.h>
-#include <linux/cpu_rmap.h>
 #include <linux/cpumask.h>
 #include <net/pkt_cls.h>
 #include <net/page_pool/helpers.h>
@@ -10833,7 +10832,7 @@ static int bnxt_set_real_num_queues(struct bnxt *bp)
 
 #ifdef CONFIG_RFS_ACCEL
 	if (bp->flags & BNXT_FLAG_RFS)
-		dev->rx_cpu_rmap = alloc_irq_cpu_rmap(bp->rx_nr_rings);
+		return netif_enable_cpu_rmap(dev, bp->rx_nr_rings);
 #endif
 
 	return rc;
@@ -11187,10 +11186,6 @@ static void bnxt_free_irq(struct bnxt *bp)
 	struct bnxt_irq *irq;
 	int i;
 
-#ifdef CONFIG_RFS_ACCEL
-	free_irq_cpu_rmap(bp->dev->rx_cpu_rmap);
-	bp->dev->rx_cpu_rmap = NULL;
-#endif
 	if (!bp->irq_tbl || !bp->bnapi)
 		return;
 
@@ -11213,11 +11208,8 @@ static void bnxt_free_irq(struct bnxt *bp)
 
 static int bnxt_request_irq(struct bnxt *bp)
 {
-	int i, j, rc = 0;
+	int i, rc = 0;
 	unsigned long flags = 0;
-#ifdef CONFIG_RFS_ACCEL
-	struct cpu_rmap *rmap;
-#endif
 
 	rc = bnxt_setup_int_mode(bp);
 	if (rc) {
@@ -11225,22 +11217,11 @@ static int bnxt_request_irq(struct bnxt *bp)
 			   rc);
 		return rc;
 	}
-#ifdef CONFIG_RFS_ACCEL
-	rmap = bp->dev->rx_cpu_rmap;
-#endif
-	for (i = 0, j = 0; i < bp->cp_nr_rings; i++) {
+
+	for (i = 0; i < bp->cp_nr_rings; i++) {
 		int map_idx = bnxt_cp_num_to_irq_num(bp, i);
 		struct bnxt_irq *irq = &bp->irq_tbl[map_idx];
 
-#ifdef CONFIG_RFS_ACCEL
-		if (rmap && bp->bnapi[i]->rx_ring) {
-			rc = irq_cpu_rmap_add(rmap, irq->vector);
-			if (rc)
-				netdev_warn(bp->dev, "failed adding irq rmap for ring %d\n",
-					    j);
-			j++;
-		}
-#endif
 		rc = request_irq(irq->vector, irq->handler, flags, irq->name,
 				 bp->bnapi[i]);
 		if (rc)
diff --git a/drivers/net/ethernet/intel/ice/ice_arfs.c b/drivers/net/ethernet/intel/ice/ice_arfs.c
index 7cee365cc7d1..3b1b892e6958 100644
--- a/drivers/net/ethernet/intel/ice/ice_arfs.c
+++ b/drivers/net/ethernet/intel/ice/ice_arfs.c
@@ -584,9 +584,6 @@ void ice_free_cpu_rx_rmap(struct ice_vsi *vsi)
 	netdev = vsi->netdev;
 	if (!netdev || !netdev->rx_cpu_rmap)
 		return;
-
-	free_irq_cpu_rmap(netdev->rx_cpu_rmap);
-	netdev->rx_cpu_rmap = NULL;
 }
 
 /**
@@ -597,7 +594,6 @@ int ice_set_cpu_rx_rmap(struct ice_vsi *vsi)
 {
 	struct net_device *netdev;
 	struct ice_pf *pf;
-	int i;
 
 	if (!vsi || vsi->type != ICE_VSI_PF)
 		return 0;
@@ -610,18 +606,7 @@ int ice_set_cpu_rx_rmap(struct ice_vsi *vsi)
 	netdev_dbg(netdev, "Setup CPU RMAP: vsi type 0x%x, ifname %s, q_vectors %d\n",
 		   vsi->type, netdev->name, vsi->num_q_vectors);
 
-	netdev->rx_cpu_rmap = alloc_irq_cpu_rmap(vsi->num_q_vectors);
-	if (unlikely(!netdev->rx_cpu_rmap))
-		return -EINVAL;
-
-	ice_for_each_q_vector(vsi, i)
-		if (irq_cpu_rmap_add(netdev->rx_cpu_rmap,
-				     vsi->q_vectors[i]->irq.virq)) {
-			ice_free_cpu_rx_rmap(vsi);
-			return -EINVAL;
-		}
-
-	return 0;
+	return netif_enable_cpu_rmap(netdev, vsi->num_q_vectors);
 }
 
 /**
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 2593019ad5b1..7adea7088e08 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2398,6 +2398,9 @@ struct net_device {
 	struct lock_class_key	*qdisc_tx_busylock;
 	bool			proto_down;
 	bool			threaded;
+#ifdef CONFIG_RFS_ACCEL
+	bool			rx_cpu_rmap_auto;
+#endif
 
 	/* priv_flags_slow, ungrouped to save space */
 	unsigned long		see_all_hwtstamp_requests:1;
@@ -2671,10 +2674,7 @@ void netif_queue_set_napi(struct net_device *dev, unsigned int queue_index,
 			  enum netdev_queue_type type,
 			  struct napi_struct *napi);
 
-static inline void netif_napi_set_irq(struct napi_struct *napi, int irq)
-{
-	napi->irq = irq;
-}
+void netif_napi_set_irq(struct napi_struct *napi, int irq);
 
 /* Default NAPI poll() weight
  * Device drivers are strongly advised to not use bigger value
@@ -2765,6 +2765,10 @@ static inline void netif_napi_del(struct napi_struct *napi)
 	synchronize_net();
 }
 
+#ifdef CONFIG_RFS_ACCEL
+int netif_enable_cpu_rmap(struct net_device *dev, unsigned int num_irqs);
+
+#endif
 struct packet_type {
 	__be16			type;	/* This is really htons(ether_type). */
 	bool			ignore_outgoing;
diff --git a/net/core/dev.c b/net/core/dev.c
index c7f3dea3e0eb..4ebe8865833e 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -6705,6 +6705,46 @@ void netif_queue_set_napi(struct net_device *dev, unsigned int queue_index,
 }
 EXPORT_SYMBOL(netif_queue_set_napi);
 
+#ifdef CONFIG_RFS_ACCEL
+static void netif_disable_cpu_rmap(struct net_device *dev)
+{
+	free_irq_cpu_rmap(dev->rx_cpu_rmap);
+	dev->rx_cpu_rmap = NULL;
+	dev->rx_cpu_rmap_auto = false;
+}
+
+int netif_enable_cpu_rmap(struct net_device *dev, unsigned int num_irqs)
+{
+	dev->rx_cpu_rmap = alloc_irq_cpu_rmap(num_irqs);
+	if (!dev->rx_cpu_rmap)
+		return -ENOMEM;
+
+	dev->rx_cpu_rmap_auto = true;
+	return 0;
+}
+EXPORT_SYMBOL(netif_enable_cpu_rmap);
+#endif
+
+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
+	if (napi->dev->rx_cpu_rmap && napi->dev->rx_cpu_rmap_auto) {
+		rc = irq_cpu_rmap_add(napi->dev->rx_cpu_rmap, irq);
+		if (rc) {
+			netdev_warn(napi->dev, "Unable to update ARFS map (%d)\n",
+				    rc);
+			netif_disable_cpu_rmap(napi->dev);
+		}
+	}
+#endif
+}
+EXPORT_SYMBOL(netif_napi_set_irq);
+
 static void napi_restore_config(struct napi_struct *n)
 {
 	n->defer_hard_irqs = n->config->defer_hard_irqs;
@@ -11347,6 +11387,10 @@ void free_netdev(struct net_device *dev)
 	/* Flush device addresses */
 	dev_addr_flush(dev);
 
+#ifdef CONFIG_RFS_ACCEL
+	if (dev->rx_cpu_rmap && dev->rx_cpu_rmap_auto)
+		netif_disable_cpu_rmap(dev);
+#endif
 	list_for_each_entry_safe(p, n, &dev->napi_list, dev_list)
 		netif_napi_del(p);
 
-- 
2.43.0

Re: [Intel-wired-lan] [PATCH net-next v3 1/6] net: move ARFS rmap management to core

[kernel test robot]

Hi Ahmed,

kernel test robot noticed the following build errors:

[auto build test ERROR on net-next/main]

url:    https://github.com/intel-lab-lkp/linux/commits/Ahmed-Zaki/net-move-ARFS-rmap-management-to-core/20250104-084501
base:   net-next/main
patch link:    https://lore.kernel.org/r/20250104004314.208259-2-ahmed.zaki%40intel.com
patch subject: [PATCH net-next v3 1/6] net: move ARFS rmap management to core
config: arm64-randconfig-002-20250104 (https://download.01.org/0day-ci/archive/20250104/202501041245.SDb1oN01-lkp@intel.com/config)
compiler: clang version 16.0.6 (https://github.com/llvm/llvm-project 7cbf1a2591520c2491aa35339f227775f4d3adf6)
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20250104/202501041245.SDb1oN01-lkp@intel.com/reproduce)

If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202501041245.SDb1oN01-lkp@intel.com/

All errors (new ones prefixed by >>):

>> drivers/net/ethernet/amazon/ena/ena_netdev.c:165:46: error: too few arguments to function call, expected 2, have 1
           return netif_enable_cpu_rmap(adapter->netdev);
                  ~~~~~~~~~~~~~~~~~~~~~                ^
   include/linux/netdevice.h:2769:5: note: 'netif_enable_cpu_rmap' declared here
   int netif_enable_cpu_rmap(struct net_device *dev, unsigned int num_irqs);
       ^
   1 error generated.


vim +165 drivers/net/ethernet/amazon/ena/ena_netdev.c

   161	
   162	static int ena_init_rx_cpu_rmap(struct ena_adapter *adapter)
   163	{
   164	#ifdef CONFIG_RFS_ACCEL
 > 165		return netif_enable_cpu_rmap(adapter->netdev);
   166	#else
   167		return 0;
   168	#endif /* CONFIG_RFS_ACCEL */
   169	}
   170	

-- 
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki

Re: [Intel-wired-lan] [PATCH net-next v3 1/6] net: move ARFS rmap management to core

[kernel test robot]

Hi Ahmed,

kernel test robot noticed the following build warnings:

[auto build test WARNING on net-next/main]

url:    https://github.com/intel-lab-lkp/linux/commits/Ahmed-Zaki/net-move-ARFS-rmap-management-to-core/20250104-084501
base:   net-next/main
patch link:    https://lore.kernel.org/r/20250104004314.208259-2-ahmed.zaki%40intel.com
patch subject: [PATCH net-next v3 1/6] net: move ARFS rmap management to core
config: arm-allmodconfig (https://download.01.org/0day-ci/archive/20250104/202501042007.PjCFMiMs-lkp@intel.com/config)
compiler: arm-linux-gnueabi-gcc (GCC) 14.2.0
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20250104/202501042007.PjCFMiMs-lkp@intel.com/reproduce)

If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202501042007.PjCFMiMs-lkp@intel.com/

All warnings (new ones prefixed by >>):

   drivers/net/ethernet/amazon/ena/ena_netdev.c: In function 'ena_init_rx_cpu_rmap':
   drivers/net/ethernet/amazon/ena/ena_netdev.c:165:16: error: too few arguments to function 'netif_enable_cpu_rmap'
     165 |         return netif_enable_cpu_rmap(adapter->netdev);
         |                ^~~~~~~~~~~~~~~~~~~~~
   In file included from include/net/inet_sock.h:19,
                    from include/net/ip.h:29,
                    from drivers/net/ethernet/amazon/ena/ena_netdev.c:16:
   include/linux/netdevice.h:2769:5: note: declared here
    2769 | int netif_enable_cpu_rmap(struct net_device *dev, unsigned int num_irqs);
         |     ^~~~~~~~~~~~~~~~~~~~~
>> drivers/net/ethernet/amazon/ena/ena_netdev.c:169:1: warning: control reaches end of non-void function [-Wreturn-type]
     169 | }
         | ^


vim +169 drivers/net/ethernet/amazon/ena/ena_netdev.c

548c4940b9f1f5 Sameeh Jubran    2019-12-10  161  
1738cd3ed34229 Netanel Belgazal 2016-08-10  162  static int ena_init_rx_cpu_rmap(struct ena_adapter *adapter)
1738cd3ed34229 Netanel Belgazal 2016-08-10  163  {
1738cd3ed34229 Netanel Belgazal 2016-08-10  164  #ifdef CONFIG_RFS_ACCEL
4f6e7588aa8a24 Ahmed Zaki       2025-01-03  165  	return netif_enable_cpu_rmap(adapter->netdev);
4f6e7588aa8a24 Ahmed Zaki       2025-01-03  166  #else
1738cd3ed34229 Netanel Belgazal 2016-08-10  167  	return 0;
4f6e7588aa8a24 Ahmed Zaki       2025-01-03  168  #endif /* CONFIG_RFS_ACCEL */
1738cd3ed34229 Netanel Belgazal 2016-08-10 @169  }
1738cd3ed34229 Netanel Belgazal 2016-08-10  170  

-- 
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki

Re: [Intel-wired-lan] [PATCH net-next v3 1/6] net: move ARFS rmap management to core

[kernel test robot]

Hi Ahmed,

kernel test robot noticed the following build errors:

[auto build test ERROR on net-next/main]

url:    https://github.com/intel-lab-lkp/linux/commits/Ahmed-Zaki/net-move-ARFS-rmap-management-to-core/20250104-084501
base:   net-next/main
patch link:    https://lore.kernel.org/r/20250104004314.208259-2-ahmed.zaki%40intel.com
patch subject: [PATCH net-next v3 1/6] net: move ARFS rmap management to core
config: arm-allyesconfig (https://download.01.org/0day-ci/archive/20250104/202501042032.NTXMscn3-lkp@intel.com/config)
compiler: arm-linux-gnueabi-gcc (GCC) 14.2.0
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20250104/202501042032.NTXMscn3-lkp@intel.com/reproduce)

If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202501042032.NTXMscn3-lkp@intel.com/

All errors (new ones prefixed by >>):

   drivers/net/ethernet/amazon/ena/ena_netdev.c: In function 'ena_init_rx_cpu_rmap':
>> drivers/net/ethernet/amazon/ena/ena_netdev.c:165:16: error: too few arguments to function 'netif_enable_cpu_rmap'
     165 |         return netif_enable_cpu_rmap(adapter->netdev);
         |                ^~~~~~~~~~~~~~~~~~~~~
   In file included from include/net/inet_sock.h:19,
                    from include/net/ip.h:29,
                    from drivers/net/ethernet/amazon/ena/ena_netdev.c:16:
   include/linux/netdevice.h:2769:5: note: declared here
    2769 | int netif_enable_cpu_rmap(struct net_device *dev, unsigned int num_irqs);
         |     ^~~~~~~~~~~~~~~~~~~~~
   drivers/net/ethernet/amazon/ena/ena_netdev.c:169:1: warning: control reaches end of non-void function [-Wreturn-type]
     169 | }
         | ^


vim +/netif_enable_cpu_rmap +165 drivers/net/ethernet/amazon/ena/ena_netdev.c

   161	
   162	static int ena_init_rx_cpu_rmap(struct ena_adapter *adapter)
   163	{
   164	#ifdef CONFIG_RFS_ACCEL
 > 165		return netif_enable_cpu_rmap(adapter->netdev);
   166	#else
   167		return 0;
   168	#endif /* CONFIG_RFS_ACCEL */
   169	}
   170	

-- 
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki

[Intel-wired-lan] [PATCH net-next v3 2/6] net: napi: add internal ARFS rmap management

[Ahmed Zaki]

For drivers using the netif_enable_cpu_rmap(), move the IRQ rmap notifier
inside the napi_struct.

Signed-off-by: Ahmed Zaki <ahmed.zaki@intel.com>
---
 include/linux/cpu_rmap.h  |  1 +
 include/linux/netdevice.h |  4 +++
 lib/cpu_rmap.c            |  2 +-
 net/core/dev.c            | 67 +++++++++++++++++++++++++++++++++++++--
 4 files changed, 71 insertions(+), 3 deletions(-)

diff --git a/include/linux/cpu_rmap.h b/include/linux/cpu_rmap.h
index 20b5729903d7..2fd7ba75362a 100644
--- a/include/linux/cpu_rmap.h
+++ b/include/linux/cpu_rmap.h
@@ -32,6 +32,7 @@ struct cpu_rmap {
 #define CPU_RMAP_DIST_INF 0xffff
 
 extern struct cpu_rmap *alloc_cpu_rmap(unsigned int size, gfp_t flags);
+extern void cpu_rmap_get(struct cpu_rmap *rmap);
 extern int cpu_rmap_put(struct cpu_rmap *rmap);
 
 extern int cpu_rmap_add(struct cpu_rmap *rmap, void *obj);
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 7adea7088e08..b0769f0a3795 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -392,6 +392,10 @@ 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;
+	int			napi_rmap_idx;
+#endif
 	int			index;
 	struct napi_config	*config;
 };
diff --git a/lib/cpu_rmap.c b/lib/cpu_rmap.c
index 4c348670da31..f03d9be3f06b 100644
--- a/lib/cpu_rmap.c
+++ b/lib/cpu_rmap.c
@@ -73,7 +73,7 @@ static void cpu_rmap_release(struct kref *ref)
  * cpu_rmap_get - internal helper to get new ref on a cpu_rmap
  * @rmap: reverse-map allocated with alloc_cpu_rmap()
  */
-static inline void cpu_rmap_get(struct cpu_rmap *rmap)
+void cpu_rmap_get(struct cpu_rmap *rmap)
 {
 	kref_get(&rmap->refcount);
 }
diff --git a/net/core/dev.c b/net/core/dev.c
index 4ebe8865833e..92b7a9d4c9b6 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -6708,7 +6708,20 @@ EXPORT_SYMBOL(netif_queue_set_napi);
 #ifdef CONFIG_RFS_ACCEL
 static void netif_disable_cpu_rmap(struct net_device *dev)
 {
-	free_irq_cpu_rmap(dev->rx_cpu_rmap);
+	struct cpu_rmap *rmap = dev->rx_cpu_rmap;
+	struct napi_struct *napi;
+	u16 index;
+
+	if (!rmap || !dev->rx_cpu_rmap_auto)
+		return;
+
+	for (index = 0; index < rmap->size; index++) {
+		napi = rmap->obj[index];
+		if (napi && napi->irq > 0)
+			irq_set_affinity_notifier(napi->irq, NULL);
+	}
+
+	cpu_rmap_put(rmap);
 	dev->rx_cpu_rmap = NULL;
 	dev->rx_cpu_rmap_auto = false;
 }
@@ -6723,6 +6736,56 @@ int netif_enable_cpu_rmap(struct net_device *dev, unsigned int num_irqs)
 	return 0;
 }
 EXPORT_SYMBOL(netif_enable_cpu_rmap);
+
+static void
+netif_irq_cpu_rmap_notify(struct irq_affinity_notify *notify,
+			  const cpumask_t *mask)
+{
+	struct napi_struct *napi =
+		container_of(notify, struct napi_struct, notify);
+	struct cpu_rmap *rmap = napi->dev->rx_cpu_rmap;
+	int err;
+
+	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);
+	}
+}
+
+static void
+netif_napi_affinity_release(struct kref __always_unused *ref)
+{
+}
+
+static int napi_irq_cpu_rmap_add(struct napi_struct *napi, int irq)
+{
+	struct cpu_rmap *rmap = napi->dev->rx_cpu_rmap;
+	int rc;
+
+	if (!napi || !rmap)
+		return -EINVAL;
+	napi->notify.notify = netif_irq_cpu_rmap_notify;
+	napi->notify.release = netif_napi_affinity_release;
+	cpu_rmap_get(rmap);
+	rc = cpu_rmap_add(rmap, napi);
+	if (rc < 0)
+		goto err_add;
+
+	napi->napi_rmap_idx = rc;
+	rc = irq_set_affinity_notifier(irq, &napi->notify);
+	if (rc)
+		goto err_set;
+
+	return 0;
+
+err_set:
+	rmap->obj[napi->napi_rmap_idx] = NULL;
+err_add:
+	cpu_rmap_put(rmap);
+	return rc;
+}
 #endif
 
 void netif_napi_set_irq(struct napi_struct *napi, int irq)
@@ -6734,7 +6797,7 @@ void netif_napi_set_irq(struct napi_struct *napi, int irq)
 
 #ifdef CONFIG_RFS_ACCEL
 	if (napi->dev->rx_cpu_rmap && napi->dev->rx_cpu_rmap_auto) {
-		rc = irq_cpu_rmap_add(napi->dev->rx_cpu_rmap, irq);
+		rc = napi_irq_cpu_rmap_add(napi, irq);
 		if (rc) {
 			netdev_warn(napi->dev, "Unable to update ARFS map (%d)\n",
 				    rc);
-- 
2.43.0

[Intel-wired-lan] [PATCH net-next v3 3/6] net: napi: add CPU affinity to napi_config

[Ahmed Zaki]

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.zaki@intel.com>
---
 include/linux/netdevice.h |  9 +++++++-
 net/core/dev.c            | 44 ++++++++++++++++++++++++++++++++-------
 2 files changed, 45 insertions(+), 8 deletions(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index b0769f0a3795..37d3f954ccf6 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;
@@ -2402,6 +2403,7 @@ 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
@@ -2637,6 +2639,11 @@ 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 92b7a9d4c9b6..86274d974ef4 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -6736,22 +6736,30 @@ 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
@@ -6759,6 +6767,7 @@ netif_napi_affinity_release(struct kref __always_unused *ref)
 {
 }
 
+#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;
@@ -6766,7 +6775,7 @@ static int napi_irq_cpu_rmap_add(struct napi_struct *napi, int irq)
 
 	if (!napi || !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);
@@ -6790,9 +6799,8 @@ 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
@@ -6803,8 +6811,18 @@ 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);
 
@@ -6813,6 +6831,10 @@ 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->config && 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. It will be saved to the config
 	 * in napi_disable.
@@ -6829,6 +6851,10 @@ static void napi_save_config(struct napi_struct *n)
 	n->config->gro_flush_timeout = n->gro_flush_timeout;
 	n->config->irq_suspend_timeout = n->irq_suspend_timeout;
 	n->config->napi_id = n->napi_id;
+
+	if (n->irq > 0 && n->config && n->dev->irq_affinity_auto)
+		irq_set_affinity_notifier(n->irq, NULL);
+
 	napi_hash_del(n);
 }
 
@@ -11293,7 +11319,7 @@ 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));
 
@@ -11389,6 +11415,10 @@ 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

Re: [Intel-wired-lan] [PATCH net-next v3 3/6] net: napi: add CPU affinity to napi_config

[Dan Carpenter]

Hi Ahmed,

kernel test robot noticed the following build warnings:

url:    https://github.com/intel-lab-lkp/linux/commits/Ahmed-Zaki/net-move-ARFS-rmap-management-to-core/20250104-084501
base:   net-next/main
patch link:    https://lore.kernel.org/r/20250104004314.208259-4-ahmed.zaki%40intel.com
patch subject: [Intel-wired-lan] [PATCH net-next v3 3/6] net: napi: add CPU affinity to napi_config
config: i386-randconfig-141-20250104 (https://download.01.org/0day-ci/archive/20250105/202501050625.nY1c97EX-lkp@intel.com/config)
compiler: clang version 19.1.3 (https://github.com/llvm/llvm-project ab51eccf88f5321e7c60591c5546b254b6afab99)

If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
| Closes: https://lore.kernel.org/r/202501050625.nY1c97EX-lkp@intel.com/

smatch warnings:
net/core/dev.c:6835 napi_restore_config() warn: variable dereferenced before check 'n->config' (see line 6831)
net/core/dev.c:6855 napi_save_config() warn: variable dereferenced before check 'n->config' (see line 6850)

vim +6835 net/core/dev.c

86e25f40aa1e9e5 Joe Damato     2024-10-11  6829  static void napi_restore_config(struct napi_struct *n)
86e25f40aa1e9e5 Joe Damato     2024-10-11  6830  {
86e25f40aa1e9e5 Joe Damato     2024-10-11 @6831  	n->defer_hard_irqs = n->config->defer_hard_irqs;
86e25f40aa1e9e5 Joe Damato     2024-10-11  6832  	n->gro_flush_timeout = n->config->gro_flush_timeout;
5dc51ec86df6e22 Martin Karsten 2024-11-09  6833  	n->irq_suspend_timeout = n->config->irq_suspend_timeout;
                                                                                 ^^^^^^^^^
These lines all dereference n->config.

d6b43b8a2e5297b Ahmed Zaki     2025-01-03  6834  
d6b43b8a2e5297b Ahmed Zaki     2025-01-03 @6835  	if (n->irq > 0 && n->config && n->dev->irq_affinity_auto)
                                                                          ^^^^^^^^^
This code assumes it can be NULL

d6b43b8a2e5297b Ahmed Zaki     2025-01-03  6836  		irq_set_affinity(n->irq, &n->config->affinity_mask);
d6b43b8a2e5297b Ahmed Zaki     2025-01-03  6837  
86e25f40aa1e9e5 Joe Damato     2024-10-11  6838  	/* a NAPI ID might be stored in the config, if so use it. if not, use
86e25f40aa1e9e5 Joe Damato     2024-10-11  6839  	 * napi_hash_add to generate one for us. It will be saved to the config
86e25f40aa1e9e5 Joe Damato     2024-10-11  6840  	 * in napi_disable.
86e25f40aa1e9e5 Joe Damato     2024-10-11  6841  	 */
86e25f40aa1e9e5 Joe Damato     2024-10-11  6842  	if (n->config->napi_id)
86e25f40aa1e9e5 Joe Damato     2024-10-11  6843  		napi_hash_add_with_id(n, n->config->napi_id);
86e25f40aa1e9e5 Joe Damato     2024-10-11  6844  	else
86e25f40aa1e9e5 Joe Damato     2024-10-11  6845  		napi_hash_add(n);
86e25f40aa1e9e5 Joe Damato     2024-10-11  6846  }
86e25f40aa1e9e5 Joe Damato     2024-10-11  6847  
86e25f40aa1e9e5 Joe Damato     2024-10-11  6848  static void napi_save_config(struct napi_struct *n)
86e25f40aa1e9e5 Joe Damato     2024-10-11  6849  {
86e25f40aa1e9e5 Joe Damato     2024-10-11 @6850  	n->config->defer_hard_irqs = n->defer_hard_irqs;
86e25f40aa1e9e5 Joe Damato     2024-10-11  6851  	n->config->gro_flush_timeout = n->gro_flush_timeout;
5dc51ec86df6e22 Martin Karsten 2024-11-09  6852  	n->config->irq_suspend_timeout = n->irq_suspend_timeout;
86e25f40aa1e9e5 Joe Damato     2024-10-11  6853  	n->config->napi_id = n->napi_id;
d6b43b8a2e5297b Ahmed Zaki     2025-01-03  6854  
d6b43b8a2e5297b Ahmed Zaki     2025-01-03 @6855  	if (n->irq > 0 && n->config && n->dev->irq_affinity_auto)

Same

d6b43b8a2e5297b Ahmed Zaki     2025-01-03  6856  		irq_set_affinity_notifier(n->irq, NULL);
d6b43b8a2e5297b Ahmed Zaki     2025-01-03  6857  
86e25f40aa1e9e5 Joe Damato     2024-10-11  6858  	napi_hash_del(n);
86e25f40aa1e9e5 Joe Damato     2024-10-11  6859  }

-- 
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki

[Intel-wired-lan] [PATCH net-next v3 4/6] bnxt: use napi's irq affinity

[Ahmed Zaki]

Delete the driver CPU affinity info and use the core's napi config
instead.

Signed-off-by: Ahmed Zaki <ahmed.zaki@intel.com>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 26 ++++-------------------
 drivers/net/ethernet/broadcom/bnxt/bnxt.h |  2 --
 2 files changed, 4 insertions(+), 24 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index cc3ca3440b0a..fcf230fde1ec 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -11193,14 +11193,8 @@ static void bnxt_free_irq(struct bnxt *bp)
 		int map_idx = bnxt_cp_num_to_irq_num(bp, i);
 
 		irq = &bp->irq_tbl[map_idx];
-		if (irq->requested) {
-			if (irq->have_cpumask) {
-				irq_update_affinity_hint(irq->vector, NULL);
-				free_cpumask_var(irq->cpu_mask);
-				irq->have_cpumask = 0;
-			}
+		if (irq->requested)
 			free_irq(irq->vector, bp->bnapi[i]);
-		}
 
 		irq->requested = 0;
 	}
@@ -11229,21 +11223,6 @@ static int bnxt_request_irq(struct bnxt *bp)
 
 		netif_napi_set_irq(&bp->bnapi[i]->napi, irq->vector);
 		irq->requested = 1;
-
-		if (zalloc_cpumask_var(&irq->cpu_mask, GFP_KERNEL)) {
-			int numa_node = dev_to_node(&bp->pdev->dev);
-
-			irq->have_cpumask = 1;
-			cpumask_set_cpu(cpumask_local_spread(i, numa_node),
-					irq->cpu_mask);
-			rc = irq_update_affinity_hint(irq->vector, irq->cpu_mask);
-			if (rc) {
-				netdev_warn(bp->dev,
-					    "Update affinity hint failed, IRQ = %d\n",
-					    irq->vector);
-				break;
-			}
-		}
 	}
 	return rc;
 }
@@ -13292,6 +13271,7 @@ static int bnxt_set_features(struct net_device *dev, netdev_features_t features)
 				bp->flags = old_flags;
 		}
 	}
+
 	return rc;
 }
 
@@ -16172,6 +16152,8 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	dev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
 			    NETDEV_XDP_ACT_RX_SG;
 
+	netif_enable_irq_affinity(dev);
+
 #ifdef CONFIG_BNXT_SRIOV
 	init_waitqueue_head(&bp->sriov_cfg_wait);
 #endif
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 094c9e95b463..7be2f90d0c05 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1228,9 +1228,7 @@ struct bnxt_irq {
 	irq_handler_t	handler;
 	unsigned int	vector;
 	u8		requested:1;
-	u8		have_cpumask:1;
 	char		name[IFNAMSIZ + BNXT_IRQ_NAME_EXTRA];
-	cpumask_var_t	cpu_mask;
 };
 
 #define HWRM_RING_ALLOC_TX	0x1
-- 
2.43.0

Re: [Intel-wired-lan] [PATCH net-next v3 4/6] bnxt: use napi's irq affinity

[Kalesh Anakkur Purayil]

[-- Attachment #1: Type: text/plain, Size: 3654 bytes --]

On Sat, Jan 4, 2025 at 6:13 AM Ahmed Zaki <ahmed.zaki@intel.com> wrote:
>
> Delete the driver CPU affinity info and use the core's napi config
> instead.
>
> Signed-off-by: Ahmed Zaki <ahmed.zaki@intel.com>
> ---
>  drivers/net/ethernet/broadcom/bnxt/bnxt.c | 26 ++++-------------------
>  drivers/net/ethernet/broadcom/bnxt/bnxt.h |  2 --
>  2 files changed, 4 insertions(+), 24 deletions(-)
>
> diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
> index cc3ca3440b0a..fcf230fde1ec 100644
> --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
> +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
> @@ -11193,14 +11193,8 @@ static void bnxt_free_irq(struct bnxt *bp)
>                 int map_idx = bnxt_cp_num_to_irq_num(bp, i);
>
>                 irq = &bp->irq_tbl[map_idx];
> -               if (irq->requested) {
> -                       if (irq->have_cpumask) {
> -                               irq_update_affinity_hint(irq->vector, NULL);
> -                               free_cpumask_var(irq->cpu_mask);
> -                               irq->have_cpumask = 0;
> -                       }
> +               if (irq->requested)
>                         free_irq(irq->vector, bp->bnapi[i]);
> -               }
>
>                 irq->requested = 0;
>         }
> @@ -11229,21 +11223,6 @@ static int bnxt_request_irq(struct bnxt *bp)
>
>                 netif_napi_set_irq(&bp->bnapi[i]->napi, irq->vector);
>                 irq->requested = 1;
> -
> -               if (zalloc_cpumask_var(&irq->cpu_mask, GFP_KERNEL)) {
> -                       int numa_node = dev_to_node(&bp->pdev->dev);
> -
> -                       irq->have_cpumask = 1;
> -                       cpumask_set_cpu(cpumask_local_spread(i, numa_node),
> -                                       irq->cpu_mask);
> -                       rc = irq_update_affinity_hint(irq->vector, irq->cpu_mask);
> -                       if (rc) {
> -                               netdev_warn(bp->dev,
> -                                           "Update affinity hint failed, IRQ = %d\n",
> -                                           irq->vector);
> -                               break;
> -                       }
> -               }
>         }
>         return rc;
>  }
> @@ -13292,6 +13271,7 @@ static int bnxt_set_features(struct net_device *dev, netdev_features_t features)
>                                 bp->flags = old_flags;
>                 }
>         }
> +
This change looks unrelated, please remove.
>         return rc;
>  }
>
> @@ -16172,6 +16152,8 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
>         dev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
>                             NETDEV_XDP_ACT_RX_SG;
>
> +       netif_enable_irq_affinity(dev);
> +
>  #ifdef CONFIG_BNXT_SRIOV
>         init_waitqueue_head(&bp->sriov_cfg_wait);
>  #endif
> diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
> index 094c9e95b463..7be2f90d0c05 100644
> --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
> +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
> @@ -1228,9 +1228,7 @@ struct bnxt_irq {
>         irq_handler_t   handler;
>         unsigned int    vector;
>         u8              requested:1;
> -       u8              have_cpumask:1;
>         char            name[IFNAMSIZ + BNXT_IRQ_NAME_EXTRA];
> -       cpumask_var_t   cpu_mask;
>  };
>
>  #define HWRM_RING_ALLOC_TX     0x1
> --
> 2.43.0
>
>


-- 
Regards,
Kalesh AP

[-- Attachment #2: S/MIME Cryptographic Signature --]
[-- Type: application/pkcs7-signature, Size: 4239 bytes --]

[Intel-wired-lan] [PATCH net-next v3 5/6] ice: use napi's irq affinity

[Ahmed Zaki]

Delete the driver CPU affinity info and use the core's napi config
instead.

Signed-off-by: Ahmed Zaki <ahmed.zaki@intel.com>
---
 drivers/net/ethernet/intel/ice/ice.h      |  3 --
 drivers/net/ethernet/intel/ice/ice_base.c |  7 +---
 drivers/net/ethernet/intel/ice/ice_lib.c  |  6 ---
 drivers/net/ethernet/intel/ice/ice_main.c | 47 ++---------------------
 4 files changed, 5 insertions(+), 58 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index 71e05d30f0fd..a6e6c9e1edc1 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -478,9 +478,6 @@ struct ice_q_vector {
 	struct ice_ring_container rx;
 	struct ice_ring_container tx;
 
-	cpumask_t affinity_mask;
-	struct irq_affinity_notify affinity_notify;
-
 	struct ice_channel *ch;
 
 	char name[ICE_INT_NAME_STR_LEN];
diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c
index b2af8e3586f7..86cf715de00f 100644
--- a/drivers/net/ethernet/intel/ice/ice_base.c
+++ b/drivers/net/ethernet/intel/ice/ice_base.c
@@ -147,10 +147,6 @@ static int ice_vsi_alloc_q_vector(struct ice_vsi *vsi, u16 v_idx)
 	q_vector->reg_idx = q_vector->irq.index;
 	q_vector->vf_reg_idx = q_vector->irq.index;
 
-	/* only set affinity_mask if the CPU is online */
-	if (cpu_online(v_idx))
-		cpumask_set_cpu(v_idx, &q_vector->affinity_mask);
-
 	/* This will not be called in the driver load path because the netdev
 	 * will not be created yet. All other cases with register the NAPI
 	 * handler here (i.e. resume, reset/rebuild, etc.)
@@ -276,7 +272,8 @@ static void ice_cfg_xps_tx_ring(struct ice_tx_ring *ring)
 	if (test_and_set_bit(ICE_TX_XPS_INIT_DONE, ring->xps_state))
 		return;
 
-	netif_set_xps_queue(ring->netdev, &ring->q_vector->affinity_mask,
+	netif_set_xps_queue(ring->netdev,
+			    &ring->q_vector->napi.config->affinity_mask,
 			    ring->q_index);
 }
 
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index a7d45a8ce7ac..b5b93a426933 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -2589,12 +2589,6 @@ void ice_vsi_free_irq(struct ice_vsi *vsi)
 		      vsi->q_vectors[i]->num_ring_rx))
 			continue;
 
-		/* clear the affinity notifier in the IRQ descriptor */
-		if (!IS_ENABLED(CONFIG_RFS_ACCEL))
-			irq_set_affinity_notifier(irq_num, NULL);
-
-		/* clear the affinity_hint in the IRQ descriptor */
-		irq_update_affinity_hint(irq_num, NULL);
 		synchronize_irq(irq_num);
 		devm_free_irq(ice_pf_to_dev(pf), irq_num, vsi->q_vectors[i]);
 	}
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 1701f7143f24..8df7332fcbbb 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -2512,34 +2512,6 @@ int ice_schedule_reset(struct ice_pf *pf, enum ice_reset_req reset)
 	return 0;
 }
 
-/**
- * ice_irq_affinity_notify - Callback for affinity changes
- * @notify: context as to what irq was changed
- * @mask: the new affinity mask
- *
- * This is a callback function used by the irq_set_affinity_notifier function
- * so that we may register to receive changes to the irq affinity masks.
- */
-static void
-ice_irq_affinity_notify(struct irq_affinity_notify *notify,
-			const cpumask_t *mask)
-{
-	struct ice_q_vector *q_vector =
-		container_of(notify, struct ice_q_vector, affinity_notify);
-
-	cpumask_copy(&q_vector->affinity_mask, mask);
-}
-
-/**
- * ice_irq_affinity_release - Callback for affinity notifier release
- * @ref: internal core kernel usage
- *
- * This is a callback function used by the irq_set_affinity_notifier function
- * to inform the current notification subscriber that they will no longer
- * receive notifications.
- */
-static void ice_irq_affinity_release(struct kref __always_unused *ref) {}
-
 /**
  * ice_vsi_ena_irq - Enable IRQ for the given VSI
  * @vsi: the VSI being configured
@@ -2603,19 +2575,6 @@ static int ice_vsi_req_irq_msix(struct ice_vsi *vsi, char *basename)
 				   err);
 			goto free_q_irqs;
 		}
-
-		/* register for affinity change notifications */
-		if (!IS_ENABLED(CONFIG_RFS_ACCEL)) {
-			struct irq_affinity_notify *affinity_notify;
-
-			affinity_notify = &q_vector->affinity_notify;
-			affinity_notify->notify = ice_irq_affinity_notify;
-			affinity_notify->release = ice_irq_affinity_release;
-			irq_set_affinity_notifier(irq_num, affinity_notify);
-		}
-
-		/* assign the mask for this irq */
-		irq_update_affinity_hint(irq_num, &q_vector->affinity_mask);
 	}
 
 	err = ice_set_cpu_rx_rmap(vsi);
@@ -2631,9 +2590,6 @@ static int ice_vsi_req_irq_msix(struct ice_vsi *vsi, char *basename)
 free_q_irqs:
 	while (vector--) {
 		irq_num = vsi->q_vectors[vector]->irq.virq;
-		if (!IS_ENABLED(CONFIG_RFS_ACCEL))
-			irq_set_affinity_notifier(irq_num, NULL);
-		irq_update_affinity_hint(irq_num, NULL);
 		devm_free_irq(dev, irq_num, &vsi->q_vectors[vector]);
 	}
 	return err;
@@ -3674,6 +3630,9 @@ void ice_set_netdev_features(struct net_device *netdev)
 	 */
 	netdev->hw_features |= NETIF_F_RXFCS;
 
+	/* Allow core to manage IRQs affinity */
+	netif_enable_irq_affinity(netdev);
+
 	netif_set_tso_max_size(netdev, ICE_MAX_TSO_SIZE);
 }
 
-- 
2.43.0

[Intel-wired-lan] [PATCH net-next v3 6/6] idpf: use napi's irq affinity

[Ahmed Zaki]

Delete the driver CPU affinity info and use the core's napi config
instead.

Signed-off-by: Ahmed Zaki <ahmed.zaki@intel.com>
---
 drivers/net/ethernet/intel/idpf/idpf_lib.c  |  1 +
 drivers/net/ethernet/intel/idpf/idpf_txrx.c | 22 +++++++--------------
 drivers/net/ethernet/intel/idpf/idpf_txrx.h |  6 ++----
 3 files changed, 10 insertions(+), 19 deletions(-)

diff --git a/drivers/net/ethernet/intel/idpf/idpf_lib.c b/drivers/net/ethernet/intel/idpf/idpf_lib.c
index b4fbb99bfad2..d54be068f53f 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_lib.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_lib.c
@@ -814,6 +814,7 @@ static int idpf_cfg_netdev(struct idpf_vport *vport)
 	netdev->hw_features |= dflt_features | offloads;
 	netdev->hw_enc_features |= dflt_features | offloads;
 	idpf_set_ethtool_ops(netdev);
+	netif_enable_irq_affinity(netdev);
 	SET_NETDEV_DEV(netdev, &adapter->pdev->dev);
 
 	/* carrier off on init to avoid Tx hangs */
diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
index 2fa9c36e33c9..f6b5b45a061c 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
@@ -3554,8 +3554,6 @@ void idpf_vport_intr_rel(struct idpf_vport *vport)
 		q_vector->tx = NULL;
 		kfree(q_vector->rx);
 		q_vector->rx = NULL;
-
-		free_cpumask_var(q_vector->affinity_mask);
 	}
 
 	kfree(vport->q_vectors);
@@ -3582,8 +3580,6 @@ static void idpf_vport_intr_rel_irq(struct idpf_vport *vport)
 		vidx = vport->q_vector_idxs[vector];
 		irq_num = adapter->msix_entries[vidx].vector;
 
-		/* clear the affinity_mask in the IRQ descriptor */
-		irq_set_affinity_hint(irq_num, NULL);
 		kfree(free_irq(irq_num, q_vector));
 	}
 }
@@ -3771,8 +3767,6 @@ static int idpf_vport_intr_req_irq(struct idpf_vport *vport)
 				   "Request_irq failed, error: %d\n", err);
 			goto free_q_irqs;
 		}
-		/* assign the mask for this irq */
-		irq_set_affinity_hint(irq_num, q_vector->affinity_mask);
 	}
 
 	return 0;
@@ -4184,7 +4178,8 @@ static int idpf_vport_intr_init_vec_idx(struct idpf_vport *vport)
 static void idpf_vport_intr_napi_add_all(struct idpf_vport *vport)
 {
 	int (*napi_poll)(struct napi_struct *napi, int budget);
-	u16 v_idx;
+	u16 v_idx, qv_idx;
+	int irq_num;
 
 	if (idpf_is_queue_model_split(vport->txq_model))
 		napi_poll = idpf_vport_splitq_napi_poll;
@@ -4193,12 +4188,12 @@ static void idpf_vport_intr_napi_add_all(struct idpf_vport *vport)
 
 	for (v_idx = 0; v_idx < vport->num_q_vectors; v_idx++) {
 		struct idpf_q_vector *q_vector = &vport->q_vectors[v_idx];
+		qv_idx = vport->q_vector_idxs[v_idx];
+		irq_num = vport->adapter->msix_entries[qv_idx].vector;
 
-		netif_napi_add(vport->netdev, &q_vector->napi, napi_poll);
-
-		/* only set affinity_mask if the CPU is online */
-		if (cpu_online(v_idx))
-			cpumask_set_cpu(v_idx, q_vector->affinity_mask);
+		netif_napi_add_config(vport->netdev, &q_vector->napi,
+				      napi_poll, v_idx);
+		netif_napi_set_irq(&q_vector->napi, irq_num);
 	}
 }
 
@@ -4242,9 +4237,6 @@ int idpf_vport_intr_alloc(struct idpf_vport *vport)
 		q_vector->rx_intr_mode = IDPF_ITR_DYNAMIC;
 		q_vector->rx_itr_idx = VIRTCHNL2_ITR_IDX_0;
 
-		if (!zalloc_cpumask_var(&q_vector->affinity_mask, GFP_KERNEL))
-			goto error;
-
 		q_vector->tx = kcalloc(txqs_per_vector, sizeof(*q_vector->tx),
 				       GFP_KERNEL);
 		if (!q_vector->tx)
diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.h b/drivers/net/ethernet/intel/idpf/idpf_txrx.h
index 0f71a6f5557b..13251f63c7c3 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_txrx.h
+++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.h
@@ -401,7 +401,6 @@ struct idpf_intr_reg {
  * @rx_intr_mode: Dynamic ITR or not
  * @rx_itr_idx: RX ITR index
  * @v_idx: Vector index
- * @affinity_mask: CPU affinity mask
  */
 struct idpf_q_vector {
 	__cacheline_group_begin_aligned(read_mostly);
@@ -438,13 +437,12 @@ struct idpf_q_vector {
 	__cacheline_group_begin_aligned(cold);
 	u16 v_idx;
 
-	cpumask_var_t affinity_mask;
 	__cacheline_group_end_aligned(cold);
 };
 libeth_cacheline_set_assert(struct idpf_q_vector, 120,
 			    24 + sizeof(struct napi_struct) +
 			    2 * sizeof(struct dim),
-			    8 + sizeof(cpumask_var_t));
+			    8);
 
 struct idpf_rx_queue_stats {
 	u64_stats_t packets;
@@ -940,7 +938,7 @@ static inline int idpf_q_vector_to_mem(const struct idpf_q_vector *q_vector)
 	if (!q_vector)
 		return NUMA_NO_NODE;
 
-	cpu = cpumask_first(q_vector->affinity_mask);
+	cpu = cpumask_first(&q_vector->napi.config->affinity_mask);
 
 	return cpu < nr_cpu_ids ? cpu_to_mem(cpu) : NUMA_NO_NODE;
 }
-- 
2.43.0