Merge: CNB97: net: Add support for per-NAPI config via netlink

MR: https://gitlab.com/redhat/centos-stream/src/kernel/centos-stream-9/-/merge_requests/6687

JIRA: https://issues.redhat.com/browse/RHEL-77816
Upstream Status: all mainline in net-next.git
Tested: boot-tested only
Conflicts: see individual patches

Signed-off-by: Davide Caratti <dcaratti@redhat.com>

Approved-by: Sabrina Dubroca <sdubroca@redhat.com>
Approved-by: Ivan Vecera <ivecera@redhat.com>
Approved-by: mheib <mheib@redhat.com>
Approved-by: CKI KWF Bot <cki-ci-bot+kwf-gitlab-com@redhat.com>

Merged-by: Augusto Caringi <acaringi@redhat.com>

Author: caringi

Documentation/netlink/specs/netdev.yaml

@@ -244,6 +244,21 @@ attribute-sets:
              threaded mode. If NAPI is not in threaded mode (i.e. uses normal
              softirq context), the attribute will be absent.
         type: u32
+      -
+        name: defer-hard-irqs
+        doc: The number of consecutive empty polls before IRQ deferral ends
+             and hardware IRQs are re-enabled.
+        type: u32
+        checks:
+          max: s32-max
+      -
+        name: gro-flush-timeout
+        doc: The timeout, in nanoseconds, of when to trigger the NAPI watchdog
+             timer which schedules NAPI processing. Additionally, a non-zero
+             value will also prevent GRO from flushing recent super-frames at
+             the end of a NAPI cycle. This may add receive latency in exchange
+             for reducing the number of frames processed by the network stack.
+        type: uint
   -
     name: queue
     attributes:
@@ -593,6 +608,8 @@ operations:
             - ifindex
             - irq
             - pid
+            - defer-hard-irqs
+            - gro-flush-timeout
       dump:
         request:
           attributes:
@@ -619,6 +636,17 @@ operations:
             - rx-bytes
             - tx-packets
             - tx-bytes
+    -
+      name: napi-set
+      doc: Set configurable NAPI instance settings.
+      attribute-set: napi
+      flags: [ admin-perm ]
+      do:
+        request:
+          attributes:
+            - id
+            - defer-hard-irqs
+            - gro-flush-timeout
 
 mcast-groups:
   list:

Documentation/networking/net_cachelines/net_device.rst

@@ -181,3 +181,6 @@ netdevice_tracker                   dev_registered_tracker
 struct_rtnl_hw_stats64*             offload_xstats_l3                                               
 struct_devlink_port*                devlink_port                                                    
 struct_dpll_pin*                    dpll_pin                                                        
+struct_napi_config*                 napi_config
+unsigned_long                       gro_flush_timeout
+u32                                 napi_defer_hard_irqs

drivers/net/ethernet/broadcom/bnxt/bnxt.c

@@ -11021,7 +11021,8 @@ static void bnxt_init_napi(struct bnxt *bp)
 		cp_nr_rings--;
 	for (i = 0; i < cp_nr_rings; i++) {
 		bnapi = bp->bnapi[i];
-		netif_napi_add(bp->dev, &bnapi->napi, poll_fn);
+		netif_napi_add_config(bp->dev, &bnapi->napi, poll_fn,
+				      bnapi->index);
 	}
 	if (BNXT_CHIP_TYPE_NITRO_A0(bp)) {
 		bnapi = bp->bnapi[cp_nr_rings];

drivers/net/ethernet/mellanox/mlx4/en_cq.c

@@ -156,7 +156,8 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq,
 		break;
 	case RX:
 		cq->mcq.comp = mlx4_en_rx_irq;
-		netif_napi_add(cq->dev, &cq->napi, mlx4_en_poll_rx_cq);
+		netif_napi_add_config(cq->dev, &cq->napi, mlx4_en_poll_rx_cq,
+				      cq_idx);
 		netif_napi_set_irq(&cq->napi, irq);
 		napi_enable(&cq->napi);
 		netif_queue_set_napi(cq->dev, cq_idx, NETDEV_QUEUE_TYPE_RX, &cq->napi);

drivers/net/ethernet/mellanox/mlx5/core/en_main.c

@@ -2704,7 +2704,7 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
 	c->aff_mask = irq_get_effective_affinity_mask(irq);
 	c->lag_port = mlx5e_enumerate_lag_port(mdev, ix);
 
-	netif_napi_add(netdev, &c->napi, mlx5e_napi_poll);
+	netif_napi_add_config(netdev, &c->napi, mlx5e_napi_poll, ix);
 	netif_napi_set_irq(&c->napi, irq);
 
 	err = mlx5e_open_queues(c, params, cparam);

include/linux/netdevice.h

@@ -333,6 +333,15 @@ struct gro_list {
  */
 #define GRO_HASH_BUCKETS	8
 
+/*
+ * Structure for per-NAPI config
+ */
+struct napi_config {
+	u64 gro_flush_timeout;
+	u32 defer_hard_irqs;
+	unsigned int napi_id;
+};
+
 /*
  * Structure for NAPI scheduling similar to tasklet but with weighting
  */
@@ -364,10 +373,14 @@ struct napi_struct {
 	unsigned int		napi_id;
 	struct hrtimer		timer;
 	struct task_struct	*thread;
+	unsigned long		gro_flush_timeout;
+	u32			defer_hard_irqs;
 	/* control-path-only fields follow */
 	struct list_head	dev_list;
 	struct hlist_node	napi_hash_node;
 	int			irq;
+	int			index;
+	struct napi_config	*config;
 
 	RH_KABI_RESERVE(1)
 	RH_KABI_RESERVE(2)
@@ -1928,9 +1941,6 @@ enum netdev_reg_state {
  *				allocated at register_netdev() time
  *	@real_num_rx_queues: 	Number of RX queues currently active in device
  *	@xdp_prog:		XDP sockets filter program pointer
- *	@gro_flush_timeout:	timeout for GRO layer in NAPI
- *	@napi_defer_hard_irqs:	If not zero, provides a counter that would
- *				allow to avoid NIC hard IRQ, on busy queues.
  *
  *	@rx_handler:		handler for received packets
  *	@rx_handler_data: 	XXX: need comments on this one
@@ -2078,6 +2088,12 @@ enum netdev_reg_state {
  *	@dpll_pin: Pointer to the SyncE source pin of a DPLL subsystem,
  *		   where the clock is recovered.
  *
+ *	@napi_config: An array of napi_config structures containing per-NAPI
+ *		      settings.
+ *	@gro_flush_timeout:	timeout for GRO layer in NAPI
+ *	@napi_defer_hard_irqs:	If not zero, provides a counter that would
+ *				allow to avoid NIC hard IRQ, on busy queues.
+ *
  *	FIXME: cleanup struct net_device such that network protocol info
  *	moves out.
  */
@@ -2143,8 +2159,6 @@ struct net_device {
 	int			ifindex;
 	unsigned int		real_num_rx_queues;
 	struct netdev_rx_queue	*_rx;
-	unsigned long		gro_flush_timeout;
-	u32			napi_defer_hard_irqs;
 	unsigned int		gro_max_size;
 	unsigned int		gro_ipv4_max_size;
 	rx_handler_func_t __rcu	*rx_handler;
@@ -2473,6 +2487,9 @@ struct net_device {
 
 	/** @irq_moder: dim parameters used if IS_ENABLED(CONFIG_DIMLIB). */
 	struct dim_irq_moder	*irq_moder;
+	struct napi_config	*napi_config;
+	unsigned long		gro_flush_timeout;
+	u32			napi_defer_hard_irqs;
 
 	RH_KABI_RESERVE(1)
 	RH_KABI_RESERVE(2)
@@ -2758,6 +2775,22 @@ netif_napi_add_tx_weight(struct net_device *dev,
 	netif_napi_add_weight(dev, napi, poll, weight);
 }
 
+/**
+ * netif_napi_add_config - initialize a NAPI context with persistent config
+ * @dev: network device
+ * @napi: NAPI context
+ * @poll: polling function
+ * @index: the NAPI index
+ */
+static inline void
+netif_napi_add_config(struct net_device *dev, struct napi_struct *napi,
+		      int (*poll)(struct napi_struct *, int), int index)
+{
+	napi->index = index;
+	napi->config = &dev->napi_config[index];
+	netif_napi_add_weight(dev, napi, poll, NAPI_POLL_WEIGHT);
+}
+
 /**
  * netif_napi_add_tx() - initialize a NAPI context to be used for Tx only
  * @dev:  network device
@@ -3251,7 +3284,6 @@ struct net_device *netdev_get_by_index(struct net *net, int ifindex,
 struct net_device *netdev_get_by_name(struct net *net, const char *name,
 				      netdevice_tracker *tracker, gfp_t gfp);
 struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex);
-struct net_device *dev_get_by_napi_id(unsigned int napi_id);
 void netdev_copy_name(struct net_device *dev, char *name);
 
 static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev,

include/net/busy_poll.h

@@ -156,12 +156,4 @@ static inline void sk_mark_napi_id_once(struct sock *sk,
 #endif
 }
 
-static inline void sk_mark_napi_id_once_xdp(struct sock *sk,
-					    const struct xdp_buff *xdp)
-{
-#ifdef CONFIG_NET_RX_BUSY_POLL
-	__sk_mark_napi_id_once(sk, xdp->rxq->napi_id);
-#endif
-}
-
 #endif /* _LINUX_NET_BUSY_POLL_H */

include/net/page_pool/types.h

@@ -232,7 +232,6 @@ struct page_pool {
 	struct {
 		struct hlist_node list;
 		u64 detach_time;
-		u32 napi_id;
 		u32 id;
 	} user;
 };

include/net/xdp.h

@@ -63,7 +63,6 @@ struct xdp_rxq_info {
 	u32 queue_index;
 	u32 reg_state;
 	struct xdp_mem_info mem;
-	unsigned int napi_id;
 	u32 frag_size;
 } ____cacheline_aligned; /* perf critical, avoid false-sharing */
 

include/net/xdp_sock_drv.h

@@ -59,15 +59,6 @@ static inline void xsk_pool_fill_cb(struct xsk_buff_pool *pool,
 	xp_fill_cb(pool, desc);
 }
 
-static inline unsigned int xsk_pool_get_napi_id(struct xsk_buff_pool *pool)
-{
-#ifdef CONFIG_NET_RX_BUSY_POLL
-	return pool->heads[0].xdp.rxq->napi_id;
-#else
-	return 0;
-#endif
-}
-
 static inline void xsk_pool_dma_unmap(struct xsk_buff_pool *pool,
 				      unsigned long attrs)
 {
@@ -306,11 +297,6 @@ static inline void xsk_pool_fill_cb(struct xsk_buff_pool *pool,
 {
 }
 
-static inline unsigned int xsk_pool_get_napi_id(struct xsk_buff_pool *pool)
-{
-	return 0;
-}
-
 static inline void xsk_pool_dma_unmap(struct xsk_buff_pool *pool,
 				      unsigned long attrs)
 {