[RFC net-next v3 1/9] net: napi: Make napi_defer_hard_irqs per-NAPI

[Joe Damato <jdamato@fastly.com>]

Allow per-NAPI defer_hard_irqs setting.

The existing sysfs parameter is respected; writes to sysfs will write to
all NAPI structs for the device and the net_device defer_hard_irq field.
Reads from sysfs will read from the net_device field.

sysfs code was updated to guard against what appears to be a potential
overflow as the field is an int, but the value passed in is an unsigned
long.

The ability to set defer_hard_irqs on specific NAPI instances will be
added in a later commit, via netdev-genl.

Signed-off-by: Joe Damato <jdamato@fastly.com>
---
 .../networking/net_cachelines/net_device.rst  |  2 +-
 include/linux/netdevice.h                     |  3 +-
 net/core/dev.c                                | 10 +++---
 net/core/dev.h                                | 36 +++++++++++++++++++
 net/core/net-sysfs.c                          |  2 +-
 5 files changed, 45 insertions(+), 8 deletions(-)

diff --git a/Documentation/networking/net_cachelines/net_device.rst b/Documentation/networking/net_cachelines/net_device.rst
index 22b07c814f4a..eeeb7c925ec5 100644
--- a/Documentation/networking/net_cachelines/net_device.rst
+++ b/Documentation/networking/net_cachelines/net_device.rst
@@ -99,7 +99,6 @@ unsigned_int                        num_rx_queues
 unsigned_int                        real_num_rx_queues      -                   read_mostly         get_rps_cpu
 struct_bpf_prog*                    xdp_prog                -                   read_mostly         netif_elide_gro()
 unsigned_long                       gro_flush_timeout       -                   read_mostly         napi_complete_done
-u32                                 napi_defer_hard_irqs    -                   read_mostly         napi_complete_done
 unsigned_int                        gro_max_size            -                   read_mostly         skb_gro_receive
 unsigned_int                        gro_ipv4_max_size       -                   read_mostly         skb_gro_receive
 rx_handler_func_t*                  rx_handler              read_mostly         -                   __netif_receive_skb_core
@@ -183,3 +182,4 @@ struct_devlink_port*                devlink_port
 struct_dpll_pin*                    dpll_pin                                                        
 struct hlist_head                   page_pools
 struct dim_irq_moder*               irq_moder
+u32                                 napi_defer_hard_irqs
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 2e40a137dc12..f28b96c95259 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -377,6 +377,7 @@ struct napi_struct {
 	struct list_head	dev_list;
 	struct hlist_node	napi_hash_node;
 	int			irq;
+	u32			defer_hard_irqs;
 };
 
 enum {
@@ -2075,7 +2076,6 @@ struct net_device {
 	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;
@@ -2398,6 +2398,7 @@ struct net_device {
 
 	/** @irq_moder: dim parameters used if IS_ENABLED(CONFIG_DIMLIB). */
 	struct dim_irq_moder	*irq_moder;
+	u32			napi_defer_hard_irqs;
 
 	u8			priv[] ____cacheline_aligned
 				       __counted_by(priv_len);
diff --git a/net/core/dev.c b/net/core/dev.c
index 8f4dead64284..d3d0680664b3 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -6221,7 +6221,7 @@ bool napi_complete_done(struct napi_struct *n, int work_done)
 	if (work_done) {
 		if (n->gro_bitmask)
 			timeout = READ_ONCE(n->dev->gro_flush_timeout);
-		n->defer_hard_irqs_count = READ_ONCE(n->dev->napi_defer_hard_irqs);
+		n->defer_hard_irqs_count = napi_get_defer_hard_irqs(n);
 	}
 	if (n->defer_hard_irqs_count > 0) {
 		n->defer_hard_irqs_count--;
@@ -6359,7 +6359,7 @@ static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock,
 	bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx);
 
 	if (flags & NAPI_F_PREFER_BUSY_POLL) {
-		napi->defer_hard_irqs_count = READ_ONCE(napi->dev->napi_defer_hard_irqs);
+		napi->defer_hard_irqs_count = napi_get_defer_hard_irqs(napi);
 		timeout = READ_ONCE(napi->dev->gro_flush_timeout);
 		if (napi->defer_hard_irqs_count && timeout) {
 			hrtimer_start(&napi->timer, ns_to_ktime(timeout), HRTIMER_MODE_REL_PINNED);
@@ -6641,6 +6641,7 @@ void netif_napi_add_weight(struct net_device *dev, struct napi_struct *napi,
 	INIT_HLIST_NODE(&napi->napi_hash_node);
 	hrtimer_init(&napi->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED);
 	napi->timer.function = napi_watchdog;
+	napi_set_defer_hard_irqs(napi, READ_ONCE(dev->napi_defer_hard_irqs));
 	init_gro_hash(napi);
 	napi->skb = NULL;
 	INIT_LIST_HEAD(&napi->rx_list);
@@ -11023,7 +11024,7 @@ void netdev_sw_irq_coalesce_default_on(struct net_device *dev)
 
 	if (!IS_ENABLED(CONFIG_PREEMPT_RT)) {
 		dev->gro_flush_timeout = 20000;
-		dev->napi_defer_hard_irqs = 1;
+		netdev_set_defer_hard_irqs(dev, 1);
 	}
 }
 EXPORT_SYMBOL_GPL(netdev_sw_irq_coalesce_default_on);
@@ -11960,7 +11961,6 @@ static void __init net_dev_struct_check(void)
 	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, real_num_rx_queues);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, _rx);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, gro_flush_timeout);
-	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, napi_defer_hard_irqs);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, gro_max_size);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, gro_ipv4_max_size);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, rx_handler);
@@ -11972,7 +11972,7 @@ static void __init net_dev_struct_check(void)
 #ifdef CONFIG_NET_XGRESS
 	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, tcx_ingress);
 #endif
-	CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_rx, 104);
+	CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_rx, 100);
 }
 
 /*
diff --git a/net/core/dev.h b/net/core/dev.h
index 5654325c5b71..f24fa38a2cac 100644
--- a/net/core/dev.h
+++ b/net/core/dev.h
@@ -138,6 +138,42 @@ static inline void netif_set_gro_ipv4_max_size(struct net_device *dev,
 	WRITE_ONCE(dev->gro_ipv4_max_size, size);
 }
 
+/**
+ * napi_get_defer_hard_irqs - get the NAPI's defer_hard_irqs
+ * @n: napi struct to get the defer_hard_irqs field from
+ *
+ * Return: the per-NAPI value of the defar_hard_irqs field.
+ */
+static inline u32 napi_get_defer_hard_irqs(const struct napi_struct *n)
+{
+	return READ_ONCE(n->defer_hard_irqs);
+}
+
+/**
+ * napi_set_defer_hard_irqs - set the defer_hard_irqs for a napi
+ * @n: napi_struct to set the defer_hard_irqs field
+ * @defer: the value the field should be set to
+ */
+static inline void napi_set_defer_hard_irqs(struct napi_struct *n, u32 defer)
+{
+	WRITE_ONCE(n->defer_hard_irqs, defer);
+}
+
+/**
+ * netdev_set_defer_hard_irqs - set defer_hard_irqs for all NAPIs of a netdev
+ * @netdev: the net_device for which all NAPIs will have their defer_hard_irqs set
+ * @defer: the defer_hard_irqs value to set
+ */
+static inline void netdev_set_defer_hard_irqs(struct net_device *netdev,
+					      u32 defer)
+{
+	struct napi_struct *napi;
+
+	WRITE_ONCE(netdev->napi_defer_hard_irqs, defer);
+	list_for_each_entry(napi, &netdev->napi_list, dev_list)
+		napi_set_defer_hard_irqs(napi, defer);
+}
+
 int rps_cpumask_housekeeping(struct cpumask *mask);
 
 #if defined(CONFIG_DEBUG_NET) && defined(CONFIG_BPF_SYSCALL)
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 05cf5347f25e..25125f356a15 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -429,7 +429,7 @@ static int change_napi_defer_hard_irqs(struct net_device *dev, unsigned long val
 	if (val > S32_MAX)
 		return -ERANGE;
 
-	WRITE_ONCE(dev->napi_defer_hard_irqs, val);
+	netdev_set_defer_hard_irqs(dev, (u32)val);
 	return 0;
 }
 
-- 
2.25.1