diff --git a/arch/powerpc/include/asm/book3s/64/hash-4k.h b/arch/powerpc/include/asm/book3s/64/hash-4k.h
index b6ac4f86c87b..433d164374cb 100644
--- a/arch/powerpc/include/asm/book3s/64/hash-4k.h
+++ b/arch/powerpc/include/asm/book3s/64/hash-4k.h
@@ -89,6 +89,34 @@ static inline int hash__hugepd_ok(hugepd_t hpd)
 }
 #endif
 
+/*
+ * With 4K page size the real_pte machinery is all nops.
+ */
+static inline real_pte_t __real_pte(pte_t pte, pte_t *ptep, int offset)
+{
+	return (real_pte_t){pte};
+}
+
+#define __rpte_to_pte(r)	((r).pte)
+
+static inline unsigned long __rpte_to_hidx(real_pte_t rpte, unsigned long index)
+{
+	return pte_val(__rpte_to_pte(rpte)) >> H_PAGE_F_GIX_SHIFT;
+}
+
+#define pte_iterate_hashed_subpages(rpte, psize, va, index, shift)       \
+	do {							         \
+		index = 0;					         \
+		shift = mmu_psize_defs[psize].shift;		         \
+
+#define pte_iterate_hashed_end() } while(0)
+
+/*
+ * We expect this to be called only for user addresses or kernel virtual
+ * addresses other than the linear mapping.
+ */
+#define pte_pagesize_index(mm, addr, pte)	MMU_PAGE_4K
+
 /*
  * 4K PTE format is different from 64K PTE format. Saving the hash_slot is just
  * a matter of returning the PTE bits that need to be modified. On 64K PTE,
diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index c436d8422654..fdbe0b381f3a 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -318,32 +318,6 @@ extern unsigned long pci_io_base;
 
 #ifndef __ASSEMBLY__
 
-/*
- * This is the default implementation of various PTE accessors, it's
- * used in all cases except Book3S with 64K pages where we have a
- * concept of sub-pages
- */
-#ifndef __real_pte
-
-#define __real_pte(e, p, o)		((real_pte_t){(e)})
-#define __rpte_to_pte(r)	((r).pte)
-#define __rpte_to_hidx(r,index)	(pte_val(__rpte_to_pte(r)) >> H_PAGE_F_GIX_SHIFT)
-
-#define pte_iterate_hashed_subpages(rpte, psize, va, index, shift)       \
-	do {							         \
-		index = 0;					         \
-		shift = mmu_psize_defs[psize].shift;		         \
-
-#define pte_iterate_hashed_end() } while(0)
-
-/*
- * We expect this to be called only for user addresses or kernel virtual
- * addresses other than the linear mapping.
- */
-#define pte_pagesize_index(mm, addr, pte)	MMU_PAGE_4K
-
-#endif /* __real_pte */
-
 static inline unsigned long pte_update(struct mm_struct *mm, unsigned long addr,
 				       pte_t *ptep, unsigned long clr,
 				       unsigned long set, int huge)
diff --git a/arch/powerpc/lib/code-patching.c b/arch/powerpc/lib/code-patching.c
index ad0cf3108dd0..65353cf2b0a8 100644
--- a/arch/powerpc/lib/code-patching.c
+++ b/arch/powerpc/lib/code-patching.c
@@ -53,7 +53,7 @@ static int text_area_cpu_up(unsigned int cpu)
 	unsigned long addr;
 	int err;
 
-	area = get_vm_area(PAGE_SIZE, VM_ALLOC);
+	area = get_vm_area(PAGE_SIZE, 0);
 	if (!area) {
 		WARN_ONCE(1, "Failed to create text area for cpu %d\n",
 			cpu);
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index 6d17738c1c53..44991cae9404 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -116,6 +116,7 @@ static void free_long_term_buff(struct ibmvnic_adapter *adapter,
 				struct ibmvnic_long_term_buff *ltb);
 static void ibmvnic_disable_irqs(struct ibmvnic_adapter *adapter);
 static void flush_reset_queue(struct ibmvnic_adapter *adapter);
+static void print_subcrq_error(struct device *dev, int rc, const char *func);
 
 struct ibmvnic_stat {
 	char name[ETH_GSTRING_LEN];
@@ -2135,7 +2136,7 @@ static void ibmvnic_tx_scrq_clean_buffer(struct ibmvnic_adapter *adapter,
 		tx_buff = &tx_pool->tx_buff[index];
 		adapter->netdev->stats.tx_packets--;
 		adapter->netdev->stats.tx_bytes -= tx_buff->skb->len;
-		adapter->tx_stats_buffers[queue_num].packets--;
+		adapter->tx_stats_buffers[queue_num].batched_packets--;
 		adapter->tx_stats_buffers[queue_num].bytes -=
 						tx_buff->skb->len;
 		dev_kfree_skb_any(tx_buff->skb);
@@ -2160,8 +2161,29 @@ static void ibmvnic_tx_scrq_clean_buffer(struct ibmvnic_adapter *adapter,
 	}
 }
 
+static int send_subcrq_direct(struct ibmvnic_adapter *adapter,
+			      u64 remote_handle, u64 *entry)
+{
+	unsigned int ua = adapter->vdev->unit_address;
+	struct device *dev = &adapter->vdev->dev;
+	int rc;
+
+	/* Make sure the hypervisor sees the complete request */
+	dma_wmb();
+	rc = plpar_hcall_norets(H_SEND_SUB_CRQ, ua,
+				cpu_to_be64(remote_handle),
+				cpu_to_be64(entry[0]), cpu_to_be64(entry[1]),
+				cpu_to_be64(entry[2]), cpu_to_be64(entry[3]));
+
+	if (rc)
+		print_subcrq_error(dev, rc, __func__);
+
+	return rc;
+}
+
 static int ibmvnic_tx_scrq_flush(struct ibmvnic_adapter *adapter,
-				 struct ibmvnic_sub_crq_queue *tx_scrq)
+				 struct ibmvnic_sub_crq_queue *tx_scrq,
+				 bool indirect)
 {
 	struct ibmvnic_ind_xmit_queue *ind_bufp;
 	u64 dma_addr;
@@ -2176,12 +2198,18 @@ static int ibmvnic_tx_scrq_flush(struct ibmvnic_adapter *adapter,
 
 	if (!entries)
 		return 0;
-	rc = send_subcrq_indirect(adapter, handle, dma_addr, entries);
+
+	if (indirect)
+		rc = send_subcrq_indirect(adapter, handle, dma_addr, entries);
+	else
+		rc = send_subcrq_direct(adapter, handle,
+					(u64 *)ind_bufp->indir_arr);
+
 	if (rc)
 		ibmvnic_tx_scrq_clean_buffer(adapter, tx_scrq);
 	else
 		ind_bufp->index = 0;
-	return 0;
+	return rc;
 }
 
 static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
@@ -2200,11 +2228,13 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
 	unsigned int tx_map_failed = 0;
 	union sub_crq indir_arr[16];
 	unsigned int tx_dropped = 0;
-	unsigned int tx_packets = 0;
+	unsigned int tx_dpackets = 0;
+	unsigned int tx_bpackets = 0;
 	unsigned int tx_bytes = 0;
 	dma_addr_t data_dma_addr;
 	struct netdev_queue *txq;
 	unsigned long lpar_rc;
+	unsigned int skblen;
 	union sub_crq tx_crq;
 	unsigned int offset;
 	int num_entries = 1;
@@ -2234,7 +2264,9 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
 		tx_dropped++;
 		tx_send_failed++;
 		ret = NETDEV_TX_OK;
-		ibmvnic_tx_scrq_flush(adapter, tx_scrq);
+		lpar_rc = ibmvnic_tx_scrq_flush(adapter, tx_scrq, true);
+		if (lpar_rc != H_SUCCESS)
+			goto tx_err;
 		goto out;
 	}
 
@@ -2249,8 +2281,10 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
 		dev_kfree_skb_any(skb);
 		tx_send_failed++;
 		tx_dropped++;
-		ibmvnic_tx_scrq_flush(adapter, tx_scrq);
 		ret = NETDEV_TX_OK;
+		lpar_rc = ibmvnic_tx_scrq_flush(adapter, tx_scrq, true);
+		if (lpar_rc != H_SUCCESS)
+			goto tx_err;
 		goto out;
 	}
 
@@ -2303,6 +2337,7 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
 	tx_buff->skb = skb;
 	tx_buff->index = bufidx;
 	tx_buff->pool_index = queue_num;
+	skblen = skb->len;
 
 	memset(&tx_crq, 0, sizeof(tx_crq));
 	tx_crq.v1.first = IBMVNIC_CRQ_CMD;
@@ -2346,6 +2381,17 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
 		tx_crq.v1.flags1 |= IBMVNIC_TX_LSO;
 		tx_crq.v1.mss = cpu_to_be16(skb_shinfo(skb)->gso_size);
 		hdrs += 2;
+	} else if (!ind_bufp->index && !netdev_xmit_more()) {
+		ind_bufp->indir_arr[0] = tx_crq;
+		ind_bufp->index = 1;
+		tx_buff->num_entries = 1;
+		netdev_tx_sent_queue(txq, skb->len);
+		lpar_rc = ibmvnic_tx_scrq_flush(adapter, tx_scrq, false);
+		if (lpar_rc != H_SUCCESS)
+			goto tx_err;
+
+		tx_dpackets++;
+		goto early_exit;
 	}
 
 	if ((*hdrs >> 7) & 1)
@@ -2355,7 +2401,7 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
 	tx_buff->num_entries = num_entries;
 	/* flush buffer if current entry can not fit */
 	if (num_entries + ind_bufp->index > IBMVNIC_MAX_IND_DESCS) {
-		lpar_rc = ibmvnic_tx_scrq_flush(adapter, tx_scrq);
+		lpar_rc = ibmvnic_tx_scrq_flush(adapter, tx_scrq, true);
 		if (lpar_rc != H_SUCCESS)
 			goto tx_flush_err;
 	}
@@ -2363,23 +2409,26 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
 	indir_arr[0] = tx_crq;
 	memcpy(&ind_bufp->indir_arr[ind_bufp->index], &indir_arr[0],
 	       num_entries * sizeof(struct ibmvnic_generic_scrq));
+
 	ind_bufp->index += num_entries;
 	if (__netdev_tx_sent_queue(txq, skb->len,
 				   netdev_xmit_more() &&
 				   ind_bufp->index < IBMVNIC_MAX_IND_DESCS)) {
-		lpar_rc = ibmvnic_tx_scrq_flush(adapter, tx_scrq);
+		lpar_rc = ibmvnic_tx_scrq_flush(adapter, tx_scrq, true);
 		if (lpar_rc != H_SUCCESS)
 			goto tx_err;
 	}
 
+	tx_bpackets++;
+
+early_exit:
 	if (atomic_add_return(num_entries, &tx_scrq->used)
 					>= adapter->req_tx_entries_per_subcrq) {
 		netdev_dbg(netdev, "Stopping queue %d\n", queue_num);
 		netif_stop_subqueue(netdev, queue_num);
 	}
 
-	tx_packets++;
-	tx_bytes += skb->len;
+	tx_bytes += skblen;
 	txq_trans_cond_update(txq);
 	ret = NETDEV_TX_OK;
 	goto out;
@@ -2408,10 +2457,11 @@ out:
 	rcu_read_unlock();
 	netdev->stats.tx_dropped += tx_dropped;
 	netdev->stats.tx_bytes += tx_bytes;
-	netdev->stats.tx_packets += tx_packets;
+	netdev->stats.tx_packets += tx_bpackets + tx_dpackets;
 	adapter->tx_send_failed += tx_send_failed;
 	adapter->tx_map_failed += tx_map_failed;
-	adapter->tx_stats_buffers[queue_num].packets += tx_packets;
+	adapter->tx_stats_buffers[queue_num].batched_packets += tx_bpackets;
+	adapter->tx_stats_buffers[queue_num].direct_packets += tx_dpackets;
 	adapter->tx_stats_buffers[queue_num].bytes += tx_bytes;
 	adapter->tx_stats_buffers[queue_num].dropped_packets += tx_dropped;
 
@@ -3577,7 +3627,10 @@ static void ibmvnic_get_strings(struct net_device *dev, u32 stringset, u8 *data)
 		memcpy(data, ibmvnic_stats[i].name, ETH_GSTRING_LEN);
 
 	for (i = 0; i < adapter->req_tx_queues; i++) {
-		snprintf(data, ETH_GSTRING_LEN, "tx%d_packets", i);
+		snprintf(data, ETH_GSTRING_LEN, "tx%d_batched_packets", i);
+		data += ETH_GSTRING_LEN;
+
+		snprintf(data, ETH_GSTRING_LEN, "tx%d_direct_packets", i);
 		data += ETH_GSTRING_LEN;
 
 		snprintf(data, ETH_GSTRING_LEN, "tx%d_bytes", i);
@@ -3642,7 +3695,9 @@ static void ibmvnic_get_ethtool_stats(struct net_device *dev,
 				      (adapter, ibmvnic_stats[i].offset));
 
 	for (j = 0; j < adapter->req_tx_queues; j++) {
-		data[i] = adapter->tx_stats_buffers[j].packets;
+		data[i] = adapter->tx_stats_buffers[j].batched_packets;
+		i++;
+		data[i] = adapter->tx_stats_buffers[j].direct_packets;
 		i++;
 		data[i] = adapter->tx_stats_buffers[j].bytes;
 		i++;
diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h
index e5c6ff3d0c47..f923cdab03f5 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.h
+++ b/drivers/net/ethernet/ibm/ibmvnic.h
@@ -213,7 +213,8 @@ struct ibmvnic_statistics {
 
 #define NUM_TX_STATS 3
 struct ibmvnic_tx_queue_stats {
-	u64 packets;
+	u64 batched_packets;
+	u64 direct_packets;
 	u64 bytes;
 	u64 dropped_packets;
 };
diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
index a95772158176..f227ed8e9934 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
@@ -2159,6 +2159,7 @@ static int axienet_probe(struct platform_device *pdev)
 
 	lp->phylink_config.dev = &ndev->dev;
 	lp->phylink_config.type = PHYLINK_NETDEV;
+	lp->phylink_config.mac_managed_pm = true;
 	lp->phylink_config.mac_capabilities = MAC_SYM_PAUSE | MAC_ASYM_PAUSE |
 		MAC_10FD | MAC_100FD | MAC_1000FD;
 
diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 27b570678c9f..3dd5c69b05cb 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -1965,21 +1965,9 @@ static void geneve_destroy_tunnels(struct net *net, struct list_head *head)
 {
 	struct geneve_net *gn = net_generic(net, geneve_net_id);
 	struct geneve_dev *geneve, *next;
-	struct net_device *dev, *aux;
 
-	/* gather any geneve devices that were moved into this ns */
-	for_each_netdev_safe(net, dev, aux)
-		if (dev->rtnl_link_ops == &geneve_link_ops)
-			unregister_netdevice_queue(dev, head);
-
-	/* now gather any other geneve devices that were created in this ns */
-	list_for_each_entry_safe(geneve, next, &gn->geneve_list, next) {
-		/* If geneve->dev is in the same netns, it was already added
-		 * to the list by the previous loop.
-		 */
-		if (!net_eq(dev_net(geneve->dev), net))
-			unregister_netdevice_queue(geneve->dev, head);
-	}
+	list_for_each_entry_safe(geneve, next, &gn->geneve_list, next)
+		geneve_dellink(geneve->dev, head);
 }
 
 static void __net_exit geneve_exit_batch_net(struct list_head *net_list)
diff --git a/drivers/usb/gadget/function/f_midi.c b/drivers/usb/gadget/function/f_midi.c
index 90a40c3b494f..9c8d56a496c9 100644
--- a/drivers/usb/gadget/function/f_midi.c
+++ b/drivers/usb/gadget/function/f_midi.c
@@ -282,7 +282,7 @@ f_midi_complete(struct usb_ep *ep, struct usb_request *req)
 			/* Our transmit completed. See if there's more to go.
 			 * f_midi_transmit eats req, don't queue it again. */
 			req->length = 0;
-			f_midi_transmit(midi);
+			queue_work(system_highpri_wq, &midi->work);
 			return;
 		}
 		break;
diff --git a/drivers/usb/gadget/udc/core.c b/drivers/usb/gadget/udc/core.c
index 06bfad727d90..e096c9da5a0d 100644
--- a/drivers/usb/gadget/udc/core.c
+++ b/drivers/usb/gadget/udc/core.c
@@ -1511,8 +1511,8 @@ void usb_del_gadget(struct usb_gadget *gadget)
 
 	kobject_uevent(&udc->dev.kobj, KOBJ_REMOVE);
 	sysfs_remove_link(&udc->dev.kobj, "gadget");
-	flush_work(&gadget->work);
 	device_del(&gadget->dev);
+	flush_work(&gadget->work);
 	ida_free(&gadget_id_numbers, gadget->id_number);
 	cancel_work_sync(&udc->vbus_work);
 	device_unregister(&udc->dev);
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index c80c9c4a49b5..7c933f4c853b 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3044,6 +3044,8 @@ static inline struct net_device *first_net_device_rcu(struct net *net)
 }
 
 int netdev_boot_setup_check(struct net_device *dev);
+struct net_device *dev_getbyhwaddr(struct net *net, unsigned short type,
+				   const char *hwaddr);
 struct net_device *dev_getbyhwaddr_rcu(struct net *net, unsigned short type,
 				       const char *hwaddr);
 struct net_device *dev_getfirstbyhwtype(struct net *net, unsigned short type);
diff --git a/net/core/dev.c b/net/core/dev.c
index 12dd5f50cf00..fd407d141d1f 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -929,6 +929,12 @@ out:
 }
 EXPORT_SYMBOL_GPL(netdev_get_name);
 
+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
@@ -937,7 +943,7 @@ EXPORT_SYMBOL_GPL(netdev_get_name);
  *
  *	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
  *
@@ -949,14 +955,39 @@ 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;
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index de17f1323238..5f50e182acd5 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -751,23 +751,30 @@ __skb_flow_dissect_ports(const struct sk_buff *skb,
 			 void *target_container, const void *data,
 			 int nhoff, u8 ip_proto, int hlen)
 {
-	enum flow_dissector_key_id dissector_ports = FLOW_DISSECTOR_KEY_MAX;
-	struct flow_dissector_key_ports *key_ports;
+	struct flow_dissector_key_ports_range *key_ports_range = NULL;
+	struct flow_dissector_key_ports *key_ports = NULL;
+	__be32 ports;
 
 	if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS))
-		dissector_ports = FLOW_DISSECTOR_KEY_PORTS;
-	else if (dissector_uses_key(flow_dissector,
-				    FLOW_DISSECTOR_KEY_PORTS_RANGE))
-		dissector_ports = FLOW_DISSECTOR_KEY_PORTS_RANGE;
+		key_ports = skb_flow_dissector_target(flow_dissector,
+						      FLOW_DISSECTOR_KEY_PORTS,
+						      target_container);
 
-	if (dissector_ports == FLOW_DISSECTOR_KEY_MAX)
+	if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS_RANGE))
+		key_ports_range = skb_flow_dissector_target(flow_dissector,
+							    FLOW_DISSECTOR_KEY_PORTS_RANGE,
+							    target_container);
+
+	if (!key_ports && !key_ports_range)
 		return;
 
-	key_ports = skb_flow_dissector_target(flow_dissector,
-					      dissector_ports,
-					      target_container);
-	key_ports->ports = __skb_flow_get_ports(skb, nhoff, ip_proto,
-						data, hlen);
+	ports = __skb_flow_get_ports(skb, nhoff, ip_proto, data, hlen);
+
+	if (key_ports)
+		key_ports->ports = ports;
+
+	if (key_ports_range)
+		key_ports_range->tp.ports = ports;
 }
 
 static void
@@ -822,6 +829,7 @@ static void __skb_flow_bpf_to_target(const struct bpf_flow_keys *flow_keys,
 				     struct flow_dissector *flow_dissector,
 				     void *target_container)
 {
+	struct flow_dissector_key_ports_range *key_ports_range = NULL;
 	struct flow_dissector_key_ports *key_ports = NULL;
 	struct flow_dissector_key_control *key_control;
 	struct flow_dissector_key_basic *key_basic;
@@ -866,20 +874,21 @@ static void __skb_flow_bpf_to_target(const struct bpf_flow_keys *flow_keys,
 		key_control->addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
 	}
 
-	if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS))
+	if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS)) {
 		key_ports = skb_flow_dissector_target(flow_dissector,
 						      FLOW_DISSECTOR_KEY_PORTS,
 						      target_container);
-	else if (dissector_uses_key(flow_dissector,
-				    FLOW_DISSECTOR_KEY_PORTS_RANGE))
-		key_ports = skb_flow_dissector_target(flow_dissector,
-						      FLOW_DISSECTOR_KEY_PORTS_RANGE,
-						      target_container);
-
-	if (key_ports) {
 		key_ports->src = flow_keys->sport;
 		key_ports->dst = flow_keys->dport;
 	}
+	if (dissector_uses_key(flow_dissector,
+			       FLOW_DISSECTOR_KEY_PORTS_RANGE)) {
+		key_ports_range = skb_flow_dissector_target(flow_dissector,
+							    FLOW_DISSECTOR_KEY_PORTS_RANGE,
+							    target_container);
+		key_ports_range->tp.src = flow_keys->sport;
+		key_ports_range->tp.dst = flow_keys->dport;
+	}
 
 	if (dissector_uses_key(flow_dissector,
 			       FLOW_DISSECTOR_KEY_FLOW_LABEL)) {
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index d27de2bac1c5..c53ae2806f16 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -1030,7 +1030,7 @@ static int arp_req_set_public(struct net *net, struct arpreq *r,
 	if (mask && mask != htonl(0xFFFFFFFF))
 		return -EINVAL;
 	if (!dev && (r->arp_flags & ATF_COM)) {
-		dev = dev_getbyhwaddr_rcu(net, r->arp_ha.sa_family,
+		dev = dev_getbyhwaddr(net, r->arp_ha.sa_family,
 				      r->arp_ha.sa_data);
 		if (!dev)
 			return -ENODEV;
diff --git a/sound/pci/hda/patch_cs8409-tables.c b/sound/pci/hda/patch_cs8409-tables.c
index b288874e401e..b2e1856ab891 100644
--- a/sound/pci/hda/patch_cs8409-tables.c
+++ b/sound/pci/hda/patch_cs8409-tables.c
@@ -121,7 +121,7 @@ static const struct cs8409_i2c_param cs42l42_init_reg_seq[] = {
 	{ CS42L42_MIXER_CHA_VOL, 0x3F },
 	{ CS42L42_MIXER_CHB_VOL, 0x3F },
 	{ CS42L42_MIXER_ADC_VOL, 0x3f },
-	{ CS42L42_HP_CTL, 0x03 },
+	{ CS42L42_HP_CTL, 0x0D },
 	{ CS42L42_MIC_DET_CTL1, 0xB6 },
 	{ CS42L42_TIPSENSE_CTL, 0xC2 },
 	{ CS42L42_HS_CLAMP_DISABLE, 0x01 },
@@ -315,7 +315,7 @@ static const struct cs8409_i2c_param dolphin_c0_init_reg_seq[] = {
 	{ CS42L42_ASP_TX_SZ_EN, 0x01 },
 	{ CS42L42_PWR_CTL1, 0x0A },
 	{ CS42L42_PWR_CTL2, 0x84 },
-	{ CS42L42_HP_CTL, 0x03 },
+	{ CS42L42_HP_CTL, 0x0D },
 	{ CS42L42_MIXER_CHA_VOL, 0x3F },
 	{ CS42L42_MIXER_CHB_VOL, 0x3F },
 	{ CS42L42_MIXER_ADC_VOL, 0x3f },
@@ -371,7 +371,7 @@ static const struct cs8409_i2c_param dolphin_c1_init_reg_seq[] = {
 	{ CS42L42_ASP_TX_SZ_EN, 0x00 },
 	{ CS42L42_PWR_CTL1, 0x0E },
 	{ CS42L42_PWR_CTL2, 0x84 },
-	{ CS42L42_HP_CTL, 0x01 },
+	{ CS42L42_HP_CTL, 0x0D },
 	{ CS42L42_MIXER_CHA_VOL, 0x3F },
 	{ CS42L42_MIXER_CHB_VOL, 0x3F },
 	{ CS42L42_MIXER_ADC_VOL, 0x3f },
diff --git a/sound/pci/hda/patch_cs8409.c b/sound/pci/hda/patch_cs8409.c
index 892223d9e64a..b003ac1990ba 100644
--- a/sound/pci/hda/patch_cs8409.c
+++ b/sound/pci/hda/patch_cs8409.c
@@ -876,7 +876,7 @@ static void cs42l42_resume(struct sub_codec *cs42l42)
 		{ CS42L42_DET_INT_STATUS2, 0x00 },
 		{ CS42L42_TSRS_PLUG_STATUS, 0x00 },
 	};
-	int fsv_old, fsv_new;
+	unsigned int fsv;
 
 	/* Bring CS42L42 out of Reset */
 	spec->gpio_data = snd_hda_codec_read(codec, CS8409_PIN_AFG, 0, AC_VERB_GET_GPIO_DATA, 0);
@@ -893,13 +893,15 @@ static void cs42l42_resume(struct sub_codec *cs42l42)
 	/* Clear interrupts, by reading interrupt status registers */
 	cs8409_i2c_bulk_read(cs42l42, irq_regs, ARRAY_SIZE(irq_regs));
 
-	fsv_old = cs8409_i2c_read(cs42l42, CS42L42_HP_CTL);
-	if (cs42l42->full_scale_vol == CS42L42_FULL_SCALE_VOL_0DB)
-		fsv_new = fsv_old & ~CS42L42_FULL_SCALE_VOL_MASK;
-	else
-		fsv_new = fsv_old & CS42L42_FULL_SCALE_VOL_MASK;
-	if (fsv_new != fsv_old)
-		cs8409_i2c_write(cs42l42, CS42L42_HP_CTL, fsv_new);
+	fsv = cs8409_i2c_read(cs42l42, CS42L42_HP_CTL);
+	if (cs42l42->full_scale_vol) {
+		// Set the full scale volume bit
+		fsv |= CS42L42_FULL_SCALE_VOL_MASK;
+		cs8409_i2c_write(cs42l42, CS42L42_HP_CTL, fsv);
+	}
+	// Unmute analog channels A and B
+	fsv = (fsv & ~CS42L42_ANA_MUTE_AB);
+	cs8409_i2c_write(cs42l42, CS42L42_HP_CTL, fsv);
 
 	/* we have to explicitly allow unsol event handling even during the
 	 * resume phase so that the jack event is processed properly
@@ -921,7 +923,7 @@ static void cs42l42_suspend(struct sub_codec *cs42l42)
 		{ CS42L42_MIXER_CHA_VOL, 0x3F },
 		{ CS42L42_MIXER_ADC_VOL, 0x3F },
 		{ CS42L42_MIXER_CHB_VOL, 0x3F },
-		{ CS42L42_HP_CTL, 0x0F },
+		{ CS42L42_HP_CTL, 0x0D },
 		{ CS42L42_ASP_RX_DAI0_EN, 0x00 },
 		{ CS42L42_ASP_CLK_CFG, 0x00 },
 		{ CS42L42_PWR_CTL1, 0xFE },
diff --git a/sound/pci/hda/patch_cs8409.h b/sound/pci/hda/patch_cs8409.h
index 937e9387abdc..bca81d49f201 100644
--- a/sound/pci/hda/patch_cs8409.h
+++ b/sound/pci/hda/patch_cs8409.h
@@ -230,9 +230,10 @@ enum cs8409_coefficient_index_registers {
 #define CS42L42_PDN_TIMEOUT_US			(250000)
 #define CS42L42_PDN_SLEEP_US			(2000)
 #define CS42L42_INIT_TIMEOUT_MS			(45)
+#define CS42L42_ANA_MUTE_AB			(0x0C)
 #define CS42L42_FULL_SCALE_VOL_MASK		(2)
-#define CS42L42_FULL_SCALE_VOL_0DB		(1)
-#define CS42L42_FULL_SCALE_VOL_MINUS6DB		(0)
+#define CS42L42_FULL_SCALE_VOL_0DB		(0)
+#define CS42L42_FULL_SCALE_VOL_MINUS6DB		(1)
 
 /* Dell BULLSEYE / WARLOCK / CYBORG Specific Definitions */
 
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 183c8a587acf..96725b6599ec 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -3776,6 +3776,7 @@ static void alc225_init(struct hda_codec *codec)
 				    AC_VERB_SET_AMP_GAIN_MUTE, AMP_OUT_UNMUTE);
 
 		msleep(75);
+		alc_update_coef_idx(codec, 0x4a, 3 << 10, 0);
 		alc_update_coefex_idx(codec, 0x57, 0x04, 0x0007, 0x4); /* Hight power */
 	}
 }
diff --git a/sound/soc/rockchip/rockchip_i2s_tdm.c b/sound/soc/rockchip/rockchip_i2s_tdm.c
index d20438cf8fc4..ff743ba0a944 100644
--- a/sound/soc/rockchip/rockchip_i2s_tdm.c
+++ b/sound/soc/rockchip/rockchip_i2s_tdm.c
@@ -453,11 +453,11 @@ static int rockchip_i2s_tdm_set_fmt(struct snd_soc_dai *cpu_dai,
 			break;
 		case SND_SOC_DAIFMT_DSP_A:
 			val = I2S_TXCR_TFS_TDM_PCM;
-			tdm_val = TDM_SHIFT_CTRL(0);
+			tdm_val = TDM_SHIFT_CTRL(2);
 			break;
 		case SND_SOC_DAIFMT_DSP_B:
 			val = I2S_TXCR_TFS_TDM_PCM;
-			tdm_val = TDM_SHIFT_CTRL(2);
+			tdm_val = TDM_SHIFT_CTRL(4);
 			break;
 		default:
 			ret = -EINVAL;