Merge tag 'riscv-mw1-6.15-rc1' of ssh://gitolite.kernel.org/pub/scm/linux/kernel/git/alexghiti/linux into for-next

riscv patches for 6.15-rc1

* A bunch of fixes:
  - We were missing a secondary mmu notifier call when flushing the tlb which is required for IOMMU
  - Fix ftrace panics by saving the registers as expected by ftrace
  - Fix a couple of stimecmp usage related to cpu hotplug
  - Fix a bunch of issues in the misaligned probing handling

* Perf improvements:
  - Introduce support for runtime constant improving perf of d_hash()
  - Add support for huge pfnmaps to improve tlb utilization
  - Use Zawrs to improve smp_cond_load8/16() used by the queued spinlocks

* Hwprobe additions:
  - Add support for Zicntr and Zihpm
  - Add support for Zaamo and Zalrsc
  - Add support for bfloat16 extensiosn
  - Add support for Zicbom (only enabling clean and flush, not inval for security reasons)

* Misc:
  - Add a kernel parameter to bypass the misaligned speed probing since we can't rely on Zicclsm

* tag 'riscv-mw1-6.15-rc1' of ssh://gitolite.kernel.org/pub/scm/linux/kernel/git/alexghiti/linux: (1585 commits)
  riscv: Add runtime constant support
  riscv: Move nop definition to insn-def.h
  Documentation/kernel-parameters: Add riscv unaligned speed parameters
  riscv: Add parameter for skipping access speed tests
  riscv: Fix set up of vector cpu hotplug callback
  riscv: Fix set up of cpu hotplug callbacks
  riscv: Change check_unaligned_access_speed_all_cpus to void
  riscv: Fix check_unaligned_access_all_cpus
  riscv: Fix riscv_online_cpu_vec
  riscv: Annotate unaligned access init functions
  KVM: riscv: selftests: Add Zaamo/Zalrsc extensions to get-reg-list test
  RISC-V: KVM: Allow Zaamo/Zalrsc extensions for Guest/VM
  riscv: hwprobe: export Zaamo and Zalrsc extensions
  riscv: add parsing for Zaamo and Zalrsc extensions
  dt-bindings: riscv: add Zaamo and Zalrsc ISA extension description
  riscv: fgraph: Fix stack layout to match __arch_ftrace_regs argument of ftrace_return_to_handler
  riscv: fgraph: Select HAVE_FUNCTION_GRAPH_TRACER depends on HAVE_DYNAMIC_FTRACE_WITH_ARGS
  riscv: Fix missing __free_pages() in check_vector_unaligned_access()
  riscv: Fix the __riscv_copy_vec_words_unaligned implementation
  riscv: mm: Don't use %pK through printk
  ...

1 files changed, 113 insertions, 16 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index c0021cbd28fc..2f7f5fd9ffec 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1121,6 +1121,12 @@ out:
 	return ret;
 }
 
+static bool dev_addr_cmp(struct net_device *dev, unsigned short type,
+			 const char *ha)
+{
+	return dev->type == type && !memcmp(dev->dev_addr, ha, dev->addr_len);
+}
+
 /**
  *	dev_getbyhwaddr_rcu - find a device by its hardware address
  *	@net: the applicable net namespace
@@ -1129,7 +1135,7 @@ out:
  *
  *	Search for an interface by MAC address. Returns NULL if the device
  *	is not found or a pointer to the device.
- *	The caller must hold RCU or RTNL.
+ *	The caller must hold RCU.
  *	The returned device has not had its ref count increased
  *	and the caller must therefore be careful about locking
  *
@@ -1141,14 +1147,39 @@ struct net_device *dev_getbyhwaddr_rcu(struct net *net, unsigned short type,
 	struct net_device *dev;
 
 	for_each_netdev_rcu(net, dev)
-		if (dev->type == type &&
-		    !memcmp(dev->dev_addr, ha, dev->addr_len))
+		if (dev_addr_cmp(dev, type, ha))
 			return dev;
 
 	return NULL;
 }
 EXPORT_SYMBOL(dev_getbyhwaddr_rcu);
 
+/**
+ * dev_getbyhwaddr() - find a device by its hardware address
+ * @net: the applicable net namespace
+ * @type: media type of device
+ * @ha: hardware address
+ *
+ * Similar to dev_getbyhwaddr_rcu(), but the owner needs to hold
+ * rtnl_lock.
+ *
+ * Context: rtnl_lock() must be held.
+ * Return: pointer to the net_device, or NULL if not found
+ */
+struct net_device *dev_getbyhwaddr(struct net *net, unsigned short type,
+				   const char *ha)
+{
+	struct net_device *dev;
+
+	ASSERT_RTNL();
+	for_each_netdev(net, dev)
+		if (dev_addr_cmp(dev, type, ha))
+			return dev;
+
+	return NULL;
+}
+EXPORT_SYMBOL(dev_getbyhwaddr);
+
 struct net_device *dev_getfirstbyhwtype(struct net *net, unsigned short type)
 {
 	struct net_device *dev, *ret = NULL;
@@ -2070,20 +2101,55 @@ static void __move_netdevice_notifier_net(struct net *src_net,
 	__register_netdevice_notifier_net(dst_net, nb, true);
 }
 
+static void rtnl_net_dev_lock(struct net_device *dev)
+{
+	bool again;
+
+	do {
+		struct net *net;
+
+		again = false;
+
+		/* netns might be being dismantled. */
+		rcu_read_lock();
+		net = dev_net_rcu(dev);
+		net_passive_inc(net);
+		rcu_read_unlock();
+
+		rtnl_net_lock(net);
+
+#ifdef CONFIG_NET_NS
+		/* dev might have been moved to another netns. */
+		if (!net_eq(net, rcu_access_pointer(dev->nd_net.net))) {
+			rtnl_net_unlock(net);
+			net_passive_dec(net);
+			again = true;
+		}
+#endif
+	} while (again);
+}
+
+static void rtnl_net_dev_unlock(struct net_device *dev)
+{
+	struct net *net = dev_net(dev);
+
+	rtnl_net_unlock(net);
+	net_passive_dec(net);
+}
+
 int register_netdevice_notifier_dev_net(struct net_device *dev,
 					struct notifier_block *nb,
 					struct netdev_net_notifier *nn)
 {
-	struct net *net = dev_net(dev);
 	int err;
 
-	rtnl_net_lock(net);
-	err = __register_netdevice_notifier_net(net, nb, false);
+	rtnl_net_dev_lock(dev);
+	err = __register_netdevice_notifier_net(dev_net(dev), nb, false);
 	if (!err) {
 		nn->nb = nb;
 		list_add(&nn->list, &dev->net_notifier_list);
 	}
-	rtnl_net_unlock(net);
+	rtnl_net_dev_unlock(dev);
 
 	return err;
 }
@@ -2093,13 +2159,12 @@ int unregister_netdevice_notifier_dev_net(struct net_device *dev,
 					  struct notifier_block *nb,
 					  struct netdev_net_notifier *nn)
 {
-	struct net *net = dev_net(dev);
 	int err;
 
-	rtnl_net_lock(net);
+	rtnl_net_dev_lock(dev);
 	list_del(&nn->list);
-	err = __unregister_netdevice_notifier_net(net, nb);
-	rtnl_net_unlock(net);
+	err = __unregister_netdevice_notifier_net(dev_net(dev), nb);
+	rtnl_net_dev_unlock(dev);
 
 	return err;
 }
@@ -3807,6 +3872,9 @@ static struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct net_device
 {
 	netdev_features_t features;
 
+	if (!skb_frags_readable(skb))
+		goto out_kfree_skb;
+
 	features = netif_skb_features(skb);
 	skb = validate_xmit_vlan(skb, features);
 	if (unlikely(!skb))
@@ -4692,7 +4760,7 @@ use_local_napi:
 	 * we have to raise NET_RX_SOFTIRQ.
 	 */
 	if (!sd->in_net_rx_action)
-		__raise_softirq_irqoff(NET_RX_SOFTIRQ);
+		raise_softirq_irqoff(NET_RX_SOFTIRQ);
 }
 
 #ifdef CONFIG_RPS
@@ -6920,6 +6988,23 @@ netif_napi_dev_list_add(struct net_device *dev, struct napi_struct *napi)
 	list_add_rcu(&napi->dev_list, higher); /* adds after higher */
 }
 
+/* Double check that napi_get_frags() allocates skbs with
+ * skb->head being backed by slab, not a page fragment.
+ * This is to make sure bug fixed in 3226b158e67c
+ * ("net: avoid 32 x truesize under-estimation for tiny skbs")
+ * does not accidentally come back.
+ */
+static void napi_get_frags_check(struct napi_struct *napi)
+{
+	struct sk_buff *skb;
+
+	local_bh_disable();
+	skb = napi_get_frags(napi);
+	WARN_ON_ONCE(skb && skb->head_frag);
+	napi_free_frags(napi);
+	local_bh_enable();
+}
+
 void netif_napi_add_weight_locked(struct net_device *dev,
 				  struct napi_struct *napi,
 				  int (*poll)(struct napi_struct *, int),
@@ -11286,6 +11371,20 @@ struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev,
 	const struct net_device_ops *ops = dev->netdev_ops;
 	const struct net_device_core_stats __percpu *p;
 
+	/*
+	 * IPv{4,6} and udp tunnels share common stat helpers and use
+	 * different stat type (NETDEV_PCPU_STAT_TSTATS vs
+	 * NETDEV_PCPU_STAT_DSTATS). Ensure the accounting is consistent.
+	 */
+	BUILD_BUG_ON(offsetof(struct pcpu_sw_netstats, rx_bytes) !=
+		     offsetof(struct pcpu_dstats, rx_bytes));
+	BUILD_BUG_ON(offsetof(struct pcpu_sw_netstats, rx_packets) !=
+		     offsetof(struct pcpu_dstats, rx_packets));
+	BUILD_BUG_ON(offsetof(struct pcpu_sw_netstats, tx_bytes) !=
+		     offsetof(struct pcpu_dstats, tx_bytes));
+	BUILD_BUG_ON(offsetof(struct pcpu_sw_netstats, tx_packets) !=
+		     offsetof(struct pcpu_dstats, tx_packets));
+
 	if (ops->ndo_get_stats64) {
 		memset(storage, 0, sizeof(*storage));
 		ops->ndo_get_stats64(dev, storage);
@@ -11866,11 +11965,9 @@ EXPORT_SYMBOL(unregister_netdevice_many);
  */
 void unregister_netdev(struct net_device *dev)
 {
-	struct net *net = dev_net(dev);
-
-	rtnl_net_lock(net);
+	rtnl_net_dev_lock(dev);
 	unregister_netdevice(dev);
-	rtnl_net_unlock(net);
+	rtnl_net_dev_unlock(dev);
 }
 EXPORT_SYMBOL(unregister_netdev);