6.1.124-rc1 review

@@ -152,6 +152,63 @@ static void hv_machine_crash_shutdown(st
 	hyperv_cleanup();
 }
 #endif /* CONFIG_KEXEC_CORE */
+
+static u64 hv_ref_counter_at_suspend;
+static void (*old_save_sched_clock_state)(void);
+static void (*old_restore_sched_clock_state)(void);
+
+/*
+ * Hyper-V clock counter resets during hibernation. Save and restore clock
+ * offset during suspend/resume, while also considering the time passed
+ * before suspend. This is to make sure that sched_clock using hv tsc page
+ * based clocksource, proceeds from where it left off during suspend and
+ * it shows correct time for the timestamps of kernel messages after resume.
+ */
+static void save_hv_clock_tsc_state(void)
+{
+	hv_ref_counter_at_suspend = hv_read_reference_counter();
+}
+
+static void restore_hv_clock_tsc_state(void)
+{
+	/*
+	 * Adjust the offsets used by hv tsc clocksource to
+	 * account for the time spent before hibernation.
+	 * adjusted value = reference counter (time) at suspend
+	 *                - reference counter (time) now.
+	 */
+	hv_adj_sched_clock_offset(hv_ref_counter_at_suspend - hv_read_reference_counter());
+}
+
+/*
+ * Functions to override save_sched_clock_state and restore_sched_clock_state
+ * functions of x86_platform. The Hyper-V clock counter is reset during
+ * suspend-resume and the offset used to measure time needs to be
+ * corrected, post resume.
+ */
+static void hv_save_sched_clock_state(void)
+{
+	old_save_sched_clock_state();
+	save_hv_clock_tsc_state();
+}
+
+static void hv_restore_sched_clock_state(void)
+{
+	restore_hv_clock_tsc_state();
+	old_restore_sched_clock_state();
+}
+
+static void __init x86_setup_ops_for_tsc_pg_clock(void)
+{
+	if (!(ms_hyperv.features & HV_MSR_REFERENCE_TSC_AVAILABLE))
+		return;
+
+	old_save_sched_clock_state = x86_platform.save_sched_clock_state;
+	x86_platform.save_sched_clock_state = hv_save_sched_clock_state;
+
+	old_restore_sched_clock_state = x86_platform.restore_sched_clock_state;
+	x86_platform.restore_sched_clock_state = hv_restore_sched_clock_state;
+}
 #endif /* CONFIG_HYPERV */
 
 static uint32_t  __init ms_hyperv_platform(void)

@@ -454,6 +511,7 @@ static void __init ms_hyperv_init_platfo
 
 	/* Register Hyper-V specific clocksource */
 	hv_init_clocksource();
+	x86_setup_ops_for_tsc_pg_clock();
 #endif
 	/*
 	 * TSC should be marked as unstable only after Hyper-V

@@ -27,7 +27,8 @@
 #include <asm/mshyperv.h>
 
 static struct clock_event_device __percpu *hv_clock_event;
-static u64 hv_sched_clock_offset __ro_after_init;
+/* Note: offset can hold negative values after hibernation. */
+static u64 hv_sched_clock_offset __read_mostly;
 
 /*
  * If false, we're using the old mechanism for stimer0 interrupts

@@ -417,6 +418,17 @@ static void resume_hv_clock_tsc(struct c
 	hv_set_register(HV_REGISTER_REFERENCE_TSC, tsc_msr.as_uint64);
 }
 
+/*
+ * Called during resume from hibernation, from overridden
+ * x86_platform.restore_sched_clock_state routine. This is to adjust offsets
+ * used to calculate time for hv tsc page based sched_clock, to account for
+ * time spent before hibernation.
+ */
+void hv_adj_sched_clock_offset(u64 offset)
+{
+	hv_sched_clock_offset -= offset;
+}
+
 #ifdef HAVE_VDSO_CLOCKMODE_HVCLOCK
 static int hv_cs_enable(struct clocksource *cs)
 {

@@ -34,6 +34,8 @@ extern void hv_init_clocksource(void);
 
 extern struct ms_hyperv_tsc_page *hv_get_tsc_page(void);
 
+extern void hv_adj_sched_clock_offset(u64 offset);
+
 static inline notrace u64
 hv_read_tsc_page_tsc(const struct ms_hyperv_tsc_page *tsc_pg, u64 *cur_tsc)
 {

@@ -969,7 +969,10 @@ void services_compute_xperms_decision(st
 					xpermd->driver))
 			return;
 	} else {
-		BUG();
+		pr_warn_once(
+			"SELinux: unknown extended permission (%u) will be ignored\n",
+			node->datum.u.xperms->specified);
+		return;
 	}
 
 	if (node->key.specified == AVTAB_XPERMS_ALLOWED) {

@@ -1006,7 +1009,8 @@ void services_compute_xperms_decision(st
 					node->datum.u.xperms->perms.p[i];
 		}
 	} else {
-		BUG();
+		pr_warn_once("SELinux: unknown specified key (%u)\n",
+			     node->key.specified);
 	}
 }
 

@@ -10469,7 +10469,7 @@ static void btrfs_encoded_read_endio(str
 		 */
 		WRITE_ONCE(priv->status, status);
 	}
-	if (!atomic_dec_return(&priv->pending))
+	if (atomic_dec_and_test(&priv->pending))
 		wake_up(&priv->wait);
 	btrfs_bio_free_csum(bbio);
 	bio_put(&bbio->bio);

@@ -359,6 +359,18 @@ static bool process_string(const char *f
 	} while (s < e);
 
 	/*
+	 * Check for arrays. If the argument has: foo[REC->val]
+	 * then it is very likely that foo is an array of strings
+	 * that are safe to use.
+	 */
+	r = strstr(s, "[");
+	if (r && r < e) {
+		r = strstr(r, "REC->");
+		if (r && r < e)
+			return true;
+	}
+
+	/*
 	 * If there's any strings in the argument consider this arg OK as it
 	 * could be: REC->field ? "foo" : "bar" and we don't want to get into
 	 * verifying that logic here.

index 288aaa05d007..5301effa6ab0 100644
@@ -1479,6 +1479,10 @@ static struct pci_device_id nhi_ids[] = {
 	  .driver_data = (kernel_ulong_t)&icl_nhi_ops },
 	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_MTL_P_NHI1),
 	  .driver_data = (kernel_ulong_t)&icl_nhi_ops },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_LNL_NHI0),
+	  .driver_data = (kernel_ulong_t)&icl_nhi_ops },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_LNL_NHI1),
+	  .driver_data = (kernel_ulong_t)&icl_nhi_ops },
 	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_BARLOW_RIDGE_HOST_80G_NHI) },
 	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_BARLOW_RIDGE_HOST_40G_NHI) },
 

index 0f029ce75882..7a07c7c1a9c2 100644
@@ -90,6 +90,8 @@ extern const struct tb_nhi_ops icl_nhi_ops;
 #define PCI_DEVICE_ID_INTEL_TGL_H_NHI1			0x9a21
 #define PCI_DEVICE_ID_INTEL_RPL_NHI0			0xa73e
 #define PCI_DEVICE_ID_INTEL_RPL_NHI1			0xa76d
+#define PCI_DEVICE_ID_INTEL_LNL_NHI0			0xa833
+#define PCI_DEVICE_ID_INTEL_LNL_NHI1			0xa834
 
 #define PCI_CLASS_SERIAL_USB_USB4			0x0c0340
 

index 5301effa6ab0..56a9222b439a 100644
@@ -1483,6 +1483,14 @@ static struct pci_device_id nhi_ids[] = {
 	  .driver_data = (kernel_ulong_t)&icl_nhi_ops },
 	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_LNL_NHI1),
 	  .driver_data = (kernel_ulong_t)&icl_nhi_ops },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_PTL_M_NHI0),
+	  .driver_data = (kernel_ulong_t)&icl_nhi_ops },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_PTL_M_NHI1),
+	  .driver_data = (kernel_ulong_t)&icl_nhi_ops },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_PTL_P_NHI0),
+	  .driver_data = (kernel_ulong_t)&icl_nhi_ops },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_PTL_P_NHI1),
+	  .driver_data = (kernel_ulong_t)&icl_nhi_ops },
 	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_BARLOW_RIDGE_HOST_80G_NHI) },
 	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_BARLOW_RIDGE_HOST_40G_NHI) },
 

index 7a07c7c1a9c2..16744f25a9a0 100644
@@ -92,6 +92,10 @@ extern const struct tb_nhi_ops icl_nhi_ops;
 #define PCI_DEVICE_ID_INTEL_RPL_NHI1			0xa76d
 #define PCI_DEVICE_ID_INTEL_LNL_NHI0			0xa833
 #define PCI_DEVICE_ID_INTEL_LNL_NHI1			0xa834
+#define PCI_DEVICE_ID_INTEL_PTL_M_NHI0			0xe333
+#define PCI_DEVICE_ID_INTEL_PTL_M_NHI1			0xe334
+#define PCI_DEVICE_ID_INTEL_PTL_P_NHI0			0xe433
+#define PCI_DEVICE_ID_INTEL_PTL_P_NHI1			0xe434
 
 #define PCI_CLASS_SERIAL_USB_USB4			0x0c0340
 

index edbd92435b41..5bd5c22a5085 100644
@@ -98,6 +98,7 @@ static int tb_retimer_nvm_add(struct tb_retimer *rt)
 
 err_nvm:
 	dev_dbg(&rt->dev, "NVM upgrade disabled\n");
+	rt->no_nvm_upgrade = true;
 	if (!IS_ERR(nvm))
 		tb_nvm_free(nvm);
 

@@ -177,8 +178,6 @@ static ssize_t nvm_authenticate_show(struct device *dev,
 
 	if (!rt->nvm)
 		ret = -EAGAIN;
-	else if (rt->no_nvm_upgrade)
-		ret = -EOPNOTSUPP;
 	else
 		ret = sysfs_emit(buf, "%#x\n", rt->auth_status);
 

@@ -304,6 +303,19 @@ static ssize_t vendor_show(struct device *dev, struct device_attribute *attr,
 }
 static DEVICE_ATTR_RO(vendor);
 
+static umode_t retimer_is_visible(struct kobject *kobj, struct attribute *attr,
+				  int n)
+{
+	struct device *dev = kobj_to_dev(kobj);
+	struct tb_retimer *rt = tb_to_retimer(dev);
+
+	if (attr == &dev_attr_nvm_authenticate.attr ||
+	    attr == &dev_attr_nvm_version.attr)
+		return rt->no_nvm_upgrade ? 0 : attr->mode;
+
+	return attr->mode;
+}
+
 static struct attribute *retimer_attrs[] = {
 	&dev_attr_device.attr,
 	&dev_attr_nvm_authenticate.attr,

@@ -313,6 +325,7 @@ static struct attribute *retimer_attrs[] = {
 };
 
 static const struct attribute_group retimer_group = {
+	.is_visible = retimer_is_visible,
 	.attrs = retimer_attrs,
 };
 

index 975d825091cb..d193d5ad8789 100644
@@ -1141,6 +1141,15 @@ static void xhci_handle_cmd_stop_ep(struct xhci_hcd *xhci, int slot_id,
 				break;
 			ep->ep_state &= ~EP_STOP_CMD_PENDING;
 			return;
+		case EP_STATE_STOPPED:
+			/*
+			 * NEC uPD720200 sometimes sets this state and fails with
+			 * Context Error while continuing to process TRBs.
+			 * Be conservative and trust EP_CTX_STATE on other chips.
+			 */
+			if (!(xhci->quirks & XHCI_NEC_HOST))
+				break;
+			fallthrough;
 		case EP_STATE_RUNNING:
 			/* Race, HW handled stop ep cmd before ep was running */
 			xhci_dbg(xhci, "Stop ep completion ctx error, ep is running\n");

index d193d5ad8789..4a3a8a3fa69d 100644
@@ -52,6 +52,7 @@
  *   endpoint rings; it generates events on the event ring for these.
  */
 
+#include <linux/jiffies.h>
 #include <linux/scatterlist.h>
 #include <linux/slab.h>
 #include <linux/dma-mapping.h>

@@ -1143,16 +1144,35 @@ static void xhci_handle_cmd_stop_ep(struct xhci_hcd *xhci, int slot_id,
 			return;
 		case EP_STATE_STOPPED:
 			/*
-			 * NEC uPD720200 sometimes sets this state and fails with
-			 * Context Error while continuing to process TRBs.
-			 * Be conservative and trust EP_CTX_STATE on other chips.
+			 * Per xHCI 4.6.9, Stop Endpoint command on a Stopped
+			 * EP is a Context State Error, and EP stays Stopped.
+			 *
+			 * But maybe it failed on Halted, and somebody ran Reset
+			 * Endpoint later. EP state is now Stopped and EP_HALTED
+			 * still set because Reset EP handler will run after us.
+			 */
+			if (ep->ep_state & EP_HALTED)
+				break;
+			/*
+			 * On some HCs EP state remains Stopped for some tens of
+			 * us to a few ms or more after a doorbell ring, and any
+			 * new Stop Endpoint fails without aborting the restart.
+			 * This handler may run quickly enough to still see this
+			 * Stopped state, but it will soon change to Running.
+			 *
+			 * Assume this bug on unexpected Stop Endpoint failures.
+			 * Keep retrying until the EP starts and stops again, on
+			 * chips where this is known to help. Wait for 100ms.
 			 */
 			if (!(xhci->quirks & XHCI_NEC_HOST))
 				break;
+			if (time_is_before_jiffies(ep->stop_time + msecs_to_jiffies(100)))
+				break;
 			fallthrough;
 		case EP_STATE_RUNNING:
 			/* Race, HW handled stop ep cmd before ep was running */
-			xhci_dbg(xhci, "Stop ep completion ctx error, ep is running\n");
+			xhci_dbg(xhci, "Stop ep completion ctx error, ctx_state %d\n",
+					GET_EP_CTX_STATE(ep_ctx));
 
 			command = xhci_alloc_command(xhci, false, GFP_ATOMIC);
 			if (!command) {

index b072154badf3..ae14c7ade9bc 100644
@@ -8,6 +8,7 @@
  * Some code borrowed from the Linux EHCI driver.
  */
 
+#include <linux/jiffies.h>
 #include <linux/pci.h>
 #include <linux/iommu.h>
 #include <linux/iopoll.h>

@@ -1911,6 +1912,7 @@ static int xhci_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, int status)
 			ret = -ENOMEM;
 			goto done;
 		}
+		ep->stop_time = jiffies;
 		ep->ep_state |= EP_STOP_CMD_PENDING;
 		xhci_queue_stop_endpoint(xhci, command, urb->dev->slot_id,
 					 ep_index, 0);

index 0b526edf636f..a75b8122538d 100644
@@ -717,6 +717,7 @@ struct xhci_virt_ep {
 	/* Bandwidth checking storage */
 	struct xhci_bw_info	bw_info;
 	struct list_head	bw_endpoint_list;
+	unsigned long		stop_time;
 	/* Isoch Frame ID checking storage */
 	int			next_frame_id;
 	/* Use new Isoch TRB layout needed for extended TBC support */

index 4a3a8a3fa69d..e5b2a3b551e3 100644
@@ -1164,8 +1164,6 @@ static void xhci_handle_cmd_stop_ep(struct xhci_hcd *xhci, int slot_id,
 			 * Keep retrying until the EP starts and stops again, on
 			 * chips where this is known to help. Wait for 100ms.
 			 */
-			if (!(xhci->quirks & XHCI_NEC_HOST))
-				break;
 			if (time_is_before_jiffies(ep->stop_time + msecs_to_jiffies(100)))
 				break;
 			fallthrough;

index ea7cb9973128..e72cdd4ce588 100644
@@ -334,8 +334,13 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb)
 	msk = NULL;
 	rc = -EINVAL;
 
-	/* we may be receiving a locally-routed packet; drop source sk
-	 * accounting
+	/* We may be receiving a locally-routed packet; drop source sk
+	 * accounting.
+	 *
+	 * From here, we will either queue the skb - either to a frag_queue, or
+	 * to a receiving socket. When that succeeds, we clear the skb pointer;
+	 * a non-NULL skb on exit will be otherwise unowned, and hence
+	 * kfree_skb()-ed.
 	 */
 	skb_orphan(skb);
 

@@ -389,7 +394,9 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb)
 		 * pending key.
 		 */
 		if (flags & MCTP_HDR_FLAG_EOM) {
-			sock_queue_rcv_skb(&msk->sk, skb);
+			rc = sock_queue_rcv_skb(&msk->sk, skb);
+			if (!rc)
+				skb = NULL;
 			if (key) {
 				/* we've hit a pending reassembly; not much we
 				 * can do but drop it

@@ -398,7 +405,6 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb)
 						   MCTP_TRACE_KEY_REPLIED);
 				key = NULL;
 			}
-			rc = 0;
 			goto out_unlock;
 		}
 

@@ -425,8 +431,10 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb)
 			 * this function.
 			 */
 			rc = mctp_key_add(key, msk);
-			if (!rc)
+			if (!rc) {
 				trace_mctp_key_acquire(key);
+				skb = NULL;
+			}
 
 			/* we don't need to release key->lock on exit, so
 			 * clean up here and suppress the unlock via

@@ -444,6 +452,8 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb)
 				key = NULL;
 			} else {
 				rc = mctp_frag_queue(key, skb);
+				if (!rc)
+					skb = NULL;
 			}
 		}
 

@@ -458,12 +468,19 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb)
 		else
 			rc = mctp_frag_queue(key, skb);
 
+		if (rc)
+			goto out_unlock;
+
+		/* we've queued; the queue owns the skb now */
+		skb = NULL;
+
 		/* end of message? deliver to socket, and we're done with
 		 * the reassembly/response key
 		 */
-		if (!rc && flags & MCTP_HDR_FLAG_EOM) {
-			sock_queue_rcv_skb(key->sk, key->reasm_head);
-			key->reasm_head = NULL;
+		if (flags & MCTP_HDR_FLAG_EOM) {
+			rc = sock_queue_rcv_skb(key->sk, key->reasm_head);
+			if (!rc)
+				key->reasm_head = NULL;
 			__mctp_key_done_in(key, net, f, MCTP_TRACE_KEY_REPLIED);
 			key = NULL;
 		}

@@ -482,8 +499,7 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb)
 	if (any_key)
 		mctp_key_unref(any_key);
 out:
-	if (rc)
-		kfree_skb(skb);
+	kfree_skb(skb);
 	return rc;
 }
 

index bce31e28eb30..45a414e8d35f 100644
@@ -3265,7 +3265,8 @@ static int mlx5_ib_init_multiport_master(struct mlx5_ib_dev *dev)
 		list_for_each_entry(mpi, &mlx5_ib_unaffiliated_port_list,
 				    list) {
 			if (dev->sys_image_guid == mpi->sys_image_guid &&
-			    (mlx5_core_native_port_num(mpi->mdev) - 1) == i) {
+			    (mlx5_core_native_port_num(mpi->mdev) - 1) == i &&
+			    mlx5_core_same_coredev_type(dev->mdev, mpi->mdev)) {
 				bound = mlx5_ib_bind_slave_port(dev, mpi);
 			}
 

@@ -4280,7 +4281,8 @@ static int mlx5r_mp_probe(struct auxiliary_device *adev,
 
 	mutex_lock(&mlx5_ib_multiport_mutex);
 	list_for_each_entry(dev, &mlx5_ib_dev_list, ib_dev_list) {
-		if (dev->sys_image_guid == mpi->sys_image_guid)
+		if (dev->sys_image_guid == mpi->sys_image_guid &&
+		    mlx5_core_same_coredev_type(dev->mdev, mpi->mdev))
 			bound = mlx5_ib_bind_slave_port(dev, mpi);
 
 		if (bound) {

index 1cae12185cf0..2588ddd3512b 100644
@@ -1212,6 +1212,12 @@ static inline bool mlx5_core_is_vf(const struct mlx5_core_dev *dev)
 	return dev->coredev_type == MLX5_COREDEV_VF;
 }
 
+static inline bool mlx5_core_same_coredev_type(const struct mlx5_core_dev *dev1,
+					       const struct mlx5_core_dev *dev2)
+{
+	return dev1->coredev_type == dev2->coredev_type;
+}
+
 static inline bool mlx5_core_is_ecpf(const struct mlx5_core_dev *dev)
 {
 	return dev->caps.embedded_cpu;

index 13102ba93847..01883d67a48e 100644
@@ -1940,18 +1940,20 @@ int bnxt_re_modify_qp(struct ib_qp *ib_qp, struct ib_qp_attr *qp_attr,
 		}
 	}
 
-	if (qp_attr_mask & IB_QP_PATH_MTU) {
-		qp->qplib_qp.modify_flags |=
-				CMDQ_MODIFY_QP_MODIFY_MASK_PATH_MTU;
-		qp->qplib_qp.path_mtu = __from_ib_mtu(qp_attr->path_mtu);
-		qp->qplib_qp.mtu = ib_mtu_enum_to_int(qp_attr->path_mtu);
-	} else if (qp_attr->qp_state == IB_QPS_RTR) {
-		qp->qplib_qp.modify_flags |=
-			CMDQ_MODIFY_QP_MODIFY_MASK_PATH_MTU;
-		qp->qplib_qp.path_mtu =
-			__from_ib_mtu(iboe_get_mtu(rdev->netdev->mtu));
-		qp->qplib_qp.mtu =
-			ib_mtu_enum_to_int(iboe_get_mtu(rdev->netdev->mtu));
+	if (qp_attr->qp_state == IB_QPS_RTR) {
+		enum ib_mtu qpmtu;
+
+		qpmtu = iboe_get_mtu(rdev->netdev->mtu);
+		if (qp_attr_mask & IB_QP_PATH_MTU) {
+			if (ib_mtu_enum_to_int(qp_attr->path_mtu) >
+			    ib_mtu_enum_to_int(qpmtu))
+				return -EINVAL;
+			qpmtu = qp_attr->path_mtu;
+		}
+
+		qp->qplib_qp.modify_flags |= CMDQ_MODIFY_QP_MODIFY_MASK_PATH_MTU;
+		qp->qplib_qp.path_mtu = __from_ib_mtu(qpmtu);
+		qp->qplib_qp.mtu = ib_mtu_enum_to_int(qpmtu);
 	}
 
 	if (qp_attr_mask & IB_QP_TIMEOUT) {

index 01883d67a48e..94c34ba103ea 100644
@@ -138,7 +138,7 @@ int bnxt_re_query_device(struct ib_device *ibdev,
 
 	ib_attr->vendor_id = rdev->en_dev->pdev->vendor;
 	ib_attr->vendor_part_id = rdev->en_dev->pdev->device;
-	ib_attr->hw_ver = rdev->en_dev->pdev->subsystem_device;
+	ib_attr->hw_ver = rdev->en_dev->pdev->revision;
 	ib_attr->max_qp = dev_attr->max_qp;
 	ib_attr->max_qp_wr = dev_attr->max_qp_wqes;
 	ib_attr->device_cap_flags =

index bae7d8926143..f59e8755f611 100644
@@ -124,7 +124,7 @@ int bnxt_qplib_get_dev_attr(struct bnxt_qplib_rcfw *rcfw,
 	attr->max_qp_init_rd_atom =
 		sb->max_qp_init_rd_atom > BNXT_QPLIB_MAX_OUT_RD_ATOM ?
 		BNXT_QPLIB_MAX_OUT_RD_ATOM : sb->max_qp_init_rd_atom;
-	attr->max_qp_wqes = le16_to_cpu(sb->max_qp_wr);
+	attr->max_qp_wqes = le16_to_cpu(sb->max_qp_wr) - 1;
 	/*
 	 * 128 WQEs needs to be reserved for the HW (8916). Prevent
 	 * reporting the max number

index 7bd7ac8d52e6..23f9a48828dc 100644
@@ -1149,9 +1149,11 @@ int bnxt_qplib_create_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp)
 		rq->dbinfo.db = qp->dpi->dbr;
 		rq->dbinfo.max_slot = bnxt_qplib_set_rq_max_slot(rq->wqe_size);
 	}
+	spin_lock_bh(&rcfw->tbl_lock);
 	tbl_indx = map_qp_id_to_tbl_indx(qp->id, rcfw);
 	rcfw->qp_tbl[tbl_indx].qp_id = qp->id;
 	rcfw->qp_tbl[tbl_indx].qp_handle = (void *)qp;
+	spin_unlock_bh(&rcfw->tbl_lock);
 
 	return 0;
 fail:

index 61f4a38e7d2b..8f786592143b 100644
@@ -153,7 +153,16 @@ static int adv7511_hdmi_hw_params(struct device *dev, void *data,
 			   ADV7511_AUDIO_CFG3_LEN_MASK, len);
 	regmap_update_bits(adv7511->regmap, ADV7511_REG_I2C_FREQ_ID_CFG,
 			   ADV7511_I2C_FREQ_ID_CFG_RATE_MASK, rate << 4);
-	regmap_write(adv7511->regmap, 0x73, 0x1);
+
+	/* send current Audio infoframe values while updating */
+	regmap_update_bits(adv7511->regmap, ADV7511_REG_INFOFRAME_UPDATE,
+			   BIT(5), BIT(5));
+
+	regmap_write(adv7511->regmap, ADV7511_REG_AUDIO_INFOFRAME(0), 0x1);
+
+	/* use Audio infoframe updated info */
+	regmap_update_bits(adv7511->regmap, ADV7511_REG_INFOFRAME_UPDATE,
+			   BIT(5), 0);
 
 	return 0;
 }

@@ -184,8 +193,9 @@ static int audio_startup(struct device *dev, void *data)
 	regmap_update_bits(adv7511->regmap, ADV7511_REG_GC(0),
 				BIT(7) | BIT(6), BIT(7));
 	/* use Audio infoframe updated info */
-	regmap_update_bits(adv7511->regmap, ADV7511_REG_GC(1),
+	regmap_update_bits(adv7511->regmap, ADV7511_REG_INFOFRAME_UPDATE,
 				BIT(5), 0);
+
 	/* enable SPDIF receiver */
 	if (adv7511->audio_source == ADV7511_AUDIO_SOURCE_SPDIF)
 		regmap_update_bits(adv7511->regmap, ADV7511_REG_AUDIO_CONFIG,

index e9fa92a83322..b854ee425fcd 100644
@@ -2,7 +2,7 @@
 /*
  * Microchip KSZ9477 switch driver main logic
  *
- * Copyright (C) 2017-2019 Microchip Technology Inc.
+ * Copyright (C) 2017-2024 Microchip Technology Inc.
  */
 
 #include <linux/kernel.h>

@@ -964,26 +964,51 @@ void ksz9477_get_caps(struct ksz_device *dev, int port,
 int ksz9477_set_ageing_time(struct ksz_device *dev, unsigned int msecs)
 {
 	u32 secs = msecs / 1000;
-	u8 value;
-	u8 data;
+	u8 data, mult, value;
+	u32 max_val;
 	int ret;
 
-	value = FIELD_GET(SW_AGE_PERIOD_7_0_M, secs);
+#define MAX_TIMER_VAL	((1 << 8) - 1)
 
-	ret = ksz_write8(dev, REG_SW_LUE_CTRL_3, value);
-	if (ret < 0)
-		return ret;
+	/* The aging timer comprises a 3-bit multiplier and an 8-bit second
+	 * value.  Either of them cannot be zero.  The maximum timer is then
+	 * 7 * 255 = 1785 seconds.
+	 */
+	if (!secs)
+		secs = 1;
 
-	data = FIELD_GET(SW_AGE_PERIOD_10_8_M, secs);
+	/* Return error if too large. */
+	else if (secs > 7 * MAX_TIMER_VAL)
+		return -EINVAL;
 
 	ret = ksz_read8(dev, REG_SW_LUE_CTRL_0, &value);
 	if (ret < 0)
 		return ret;
 
-	value &= ~SW_AGE_CNT_M;
-	value |= FIELD_PREP(SW_AGE_CNT_M, data);
+	/* Check whether there is need to update the multiplier. */
+	mult = FIELD_GET(SW_AGE_CNT_M, value);
+	max_val = MAX_TIMER_VAL;
+	if (mult > 0) {
+		/* Try to use the same multiplier already in the register as
+		 * the hardware default uses multiplier 4 and 75 seconds for
+		 * 300 seconds.
+		 */
+		max_val = DIV_ROUND_UP(secs, mult);
+		if (max_val > MAX_TIMER_VAL || max_val * mult != secs)
+			max_val = MAX_TIMER_VAL;
+	}
+
+	data = DIV_ROUND_UP(secs, max_val);
+	if (mult != data) {
+		value &= ~SW_AGE_CNT_M;
+		value |= FIELD_PREP(SW_AGE_CNT_M, data);
+		ret = ksz_write8(dev, REG_SW_LUE_CTRL_0, value);
+		if (ret < 0)
+			return ret;
+	}
 
-	return ksz_write8(dev, REG_SW_LUE_CTRL_0, value);
+	value = DIV_ROUND_UP(secs, data);
+	return ksz_write8(dev, REG_SW_LUE_CTRL_3, value);
 }
 
 void ksz9477_port_setup(struct ksz_device *dev, int port, bool cpu_port)

index 04086e9ab0a0..ffb9484018ed 100644
@@ -2,7 +2,7 @@
 /*
  * Microchip KSZ9477 register definitions
  *
- * Copyright (C) 2017-2018 Microchip Technology Inc.
+ * Copyright (C) 2017-2024 Microchip Technology Inc.
  */
 
 #ifndef __KSZ9477_REGS_H

@@ -190,8 +190,6 @@
 #define SW_VLAN_ENABLE			BIT(7)
 #define SW_DROP_INVALID_VID		BIT(6)
 #define SW_AGE_CNT_M			GENMASK(5, 3)
-#define SW_AGE_CNT_S			3
-#define SW_AGE_PERIOD_10_8_M		GENMASK(10, 8)
 #define SW_RESV_MCAST_ENABLE		BIT(2)
 #define SW_HASH_OPTION_M		0x03
 #define SW_HASH_OPTION_CRC		1

index d1b2db8e6533..a3a7a90dad96 100644
@@ -454,6 +454,11 @@ static inline int ksz_write64(struct ksz_device *dev, u32 reg, u64 value)
 	return regmap_bulk_write(dev->regmap[2], reg, val, 2);
 }
 
+static inline int ksz_rmw8(struct ksz_device *dev, int offset, u8 mask, u8 val)
+{
+	return regmap_update_bits(dev->regmap[0], offset, mask, val);
+}
+
 static inline int ksz_pread8(struct ksz_device *dev, int port, int offset,
 			     u8 *data)
 {

index 7e4f307a0387..338eff0818df 100644
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Microchip LAN937X switch driver main logic
- * Copyright (C) 2019-2022 Microchip Technology Inc.
+ * Copyright (C) 2019-2024 Microchip Technology Inc.
  */
 #include <linux/kernel.h>
 #include <linux/module.h>

@@ -249,10 +249,66 @@ int lan937x_change_mtu(struct ksz_device *dev, int port, int new_mtu)
 
 int lan937x_set_ageing_time(struct ksz_device *dev, unsigned int msecs)
 {
-	u32 secs = msecs / 1000;
-	u32 value;
+	u8 data, mult, value8;
+	bool in_msec = false;
+	u32 max_val, value;
+	u32 secs = msecs;
 	int ret;
 
+#define MAX_TIMER_VAL	((1 << 20) - 1)
+
+	/* The aging timer comprises a 3-bit multiplier and a 20-bit second
+	 * value.  Either of them cannot be zero.  The maximum timer is then
+	 * 7 * 1048575 = 7340025 seconds.  As this value is too large for
+	 * practical use it can be interpreted as microseconds, making the
+	 * maximum timer 7340 seconds with finer control.  This allows for
+	 * maximum 122 minutes compared to 29 minutes in KSZ9477 switch.
+	 */
+	if (msecs % 1000)
+		in_msec = true;
+	else
+		secs /= 1000;
+	if (!secs)
+		secs = 1;
+
+	/* Return error if too large. */
+	else if (secs > 7 * MAX_TIMER_VAL)
+		return -EINVAL;
+
+	/* Configure how to interpret the number value. */
+	ret = ksz_rmw8(dev, REG_SW_LUE_CTRL_2, SW_AGE_CNT_IN_MICROSEC,
+		       in_msec ? SW_AGE_CNT_IN_MICROSEC : 0);
+	if (ret < 0)
+		return ret;
+
+	ret = ksz_read8(dev, REG_SW_LUE_CTRL_0, &value8);
+	if (ret < 0)
+		return ret;
+
+	/* Check whether there is need to update the multiplier. */
+	mult = FIELD_GET(SW_AGE_CNT_M, value8);
+	max_val = MAX_TIMER_VAL;
+	if (mult > 0) {
+		/* Try to use the same multiplier already in the register as
+		 * the hardware default uses multiplier 4 and 75 seconds for
+		 * 300 seconds.
+		 */
+		max_val = DIV_ROUND_UP(secs, mult);
+		if (max_val > MAX_TIMER_VAL || max_val * mult != secs)
+			max_val = MAX_TIMER_VAL;
+	}
+
+	data = DIV_ROUND_UP(secs, max_val);
+	if (mult != data) {
+		value8 &= ~SW_AGE_CNT_M;
+		value8 |= FIELD_PREP(SW_AGE_CNT_M, data);
+		ret = ksz_write8(dev, REG_SW_LUE_CTRL_0, value8);
+		if (ret < 0)
+			return ret;
+	}
+
+	secs = DIV_ROUND_UP(secs, data);
+
 	value = FIELD_GET(SW_AGE_PERIOD_7_0_M, secs);
 
 	ret = ksz_write8(dev, REG_SW_AGE_PERIOD__1, value);

index 5bc16a4c4441..f36ef2ce4065 100644
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 /* Microchip LAN937X switch register definitions
- * Copyright (C) 2019-2021 Microchip Technology Inc.
+ * Copyright (C) 2019-2024 Microchip Technology Inc.
  */
 #ifndef __LAN937X_REG_H
 #define __LAN937X_REG_H

@@ -48,8 +48,7 @@
 
 #define SW_VLAN_ENABLE			BIT(7)
 #define SW_DROP_INVALID_VID		BIT(6)
-#define SW_AGE_CNT_M			0x7
-#define SW_AGE_CNT_S			3
+#define SW_AGE_CNT_M			GENMASK(5, 3)
 #define SW_RESV_MCAST_ENABLE		BIT(2)
 
 #define REG_SW_LUE_CTRL_1		0x0311

@@ -62,6 +61,10 @@
 #define SW_FAST_AGING			BIT(1)
 #define SW_LINK_AUTO_AGING		BIT(0)
 
+#define REG_SW_LUE_CTRL_2		0x0312
+
+#define SW_AGE_CNT_IN_MICROSEC		BIT(7)
+
 #define REG_SW_AGE_PERIOD__1		0x0313
 #define SW_AGE_PERIOD_7_0_M		GENMASK(7, 0)
 

index 9b91731a6207..5e0d78f4e545 100644
@@ -133,14 +133,12 @@ static int alloc_cqc(struct hns_roce_dev *hr_dev, struct hns_roce_cq *hr_cq)
 	struct hns_roce_cq_table *cq_table = &hr_dev->cq_table;
 	struct ib_device *ibdev = &hr_dev->ib_dev;
 	u64 mtts[MTT_MIN_COUNT] = {};
-	dma_addr_t dma_handle;
 	int ret;
 
-	ret = hns_roce_mtr_find(hr_dev, &hr_cq->mtr, 0, mtts, ARRAY_SIZE(mtts),
-				&dma_handle);
-	if (!ret) {
+	ret = hns_roce_mtr_find(hr_dev, &hr_cq->mtr, 0, mtts, ARRAY_SIZE(mtts));
+	if (ret) {
 		ibdev_err(ibdev, "failed to find CQ mtr, ret = %d.\n", ret);
-		return -EINVAL;
+		return ret;
 	}
 
 	/* Get CQC memory HEM(Hardware Entry Memory) table */

@@ -157,7 +155,8 @@ static int alloc_cqc(struct hns_roce_dev *hr_dev, struct hns_roce_cq *hr_cq)
 		goto err_put;
 	}
 
-	ret = hns_roce_create_cqc(hr_dev, hr_cq, mtts, dma_handle);
+	ret = hns_roce_create_cqc(hr_dev, hr_cq, mtts,
+				  hns_roce_get_mtr_ba(&hr_cq->mtr));
 	if (ret)
 		goto err_xa;
 

index 5b8b68b2d69c..461008bf0fcf 100644
@@ -1117,8 +1117,13 @@ void hns_roce_cmd_use_polling(struct hns_roce_dev *hr_dev);
 
 /* hns roce hw need current block and next block addr from mtt */
 #define MTT_MIN_COUNT	 2
+static inline dma_addr_t hns_roce_get_mtr_ba(struct hns_roce_mtr *mtr)
+{
+	return mtr->hem_cfg.root_ba;
+}
+
 int hns_roce_mtr_find(struct hns_roce_dev *hr_dev, struct hns_roce_mtr *mtr,
-		      u32 offset, u64 *mtt_buf, int mtt_max, u64 *base_addr);
+		      u32 offset, u64 *mtt_buf, int mtt_max);
 int hns_roce_mtr_create(struct hns_roce_dev *hr_dev, struct hns_roce_mtr *mtr,
 			struct hns_roce_buf_attr *buf_attr,
 			unsigned int page_shift, struct ib_udata *udata,

190 lines not on this page · raw message

115 lines not on this page · raw message

index 11a78ceae568..950c133d4220 100644
@@ -153,8 +153,7 @@ int hns_roce_get_kmem_bufs(struct hns_roce_dev *hr_dev, dma_addr_t *bufs,
 	return total;
 }
 
-int hns_roce_get_umem_bufs(struct hns_roce_dev *hr_dev, dma_addr_t *bufs,
-			   int buf_cnt, struct ib_umem *umem,
+int hns_roce_get_umem_bufs(dma_addr_t *bufs, int buf_cnt, struct ib_umem *umem,
 			   unsigned int page_shift)
 {
 	struct ib_block_iter biter;

index 461008bf0fcf..060797001353 100644
@@ -882,8 +882,7 @@ struct hns_roce_hw {
 	int (*rereg_write_mtpt)(struct hns_roce_dev *hr_dev,
 				struct hns_roce_mr *mr, int flags,
 				void *mb_buf);
-	int (*frmr_write_mtpt)(struct hns_roce_dev *hr_dev, void *mb_buf,
-			       struct hns_roce_mr *mr);
+	int (*frmr_write_mtpt)(void *mb_buf, struct hns_roce_mr *mr);
 	int (*mw_write_mtpt)(void *mb_buf, struct hns_roce_mw *mw);
 	void (*write_cqc)(struct hns_roce_dev *hr_dev,
 			  struct hns_roce_cq *hr_cq, void *mb_buf, u64 *mtts,

@@ -1182,7 +1181,7 @@ struct hns_roce_buf *hns_roce_buf_alloc(struct hns_roce_dev *hr_dev, u32 size,
 int hns_roce_get_kmem_bufs(struct hns_roce_dev *hr_dev, dma_addr_t *bufs,
 			   int buf_cnt, struct hns_roce_buf *buf,
 			   unsigned int page_shift);
-int hns_roce_get_umem_bufs(struct hns_roce_dev *hr_dev, dma_addr_t *bufs,
+int hns_roce_get_umem_bufs(dma_addr_t *bufs,
 			   int buf_cnt, struct ib_umem *umem,
 			   unsigned int page_shift);
 

index f605eb8fd13a..6e0ca8a4b2a8 100644
@@ -1043,15 +1043,13 @@ static void hem_list_free_all(struct hns_roce_dev *hr_dev,
 	}
 }
 
-static void hem_list_link_bt(struct hns_roce_dev *hr_dev, void *base_addr,
-			     u64 table_addr)
+static void hem_list_link_bt(void *base_addr, u64 table_addr)
 {
 	*(u64 *)(base_addr) = table_addr;
 }
 
 /* assign L0 table address to hem from root bt */
-static void hem_list_assign_bt(struct hns_roce_dev *hr_dev,
-			       struct hns_roce_hem_item *hem, void *cpu_addr,
+static void hem_list_assign_bt(struct hns_roce_hem_item *hem, void *cpu_addr,
 			       u64 phy_addr)
 {
 	hem->addr = cpu_addr;

@@ -1222,8 +1220,7 @@ static int hem_list_alloc_mid_bt(struct hns_roce_dev *hr_dev,
 		if (level > 1) {
 			pre = hem_ptrs[level - 1];
 			step = (cur->start - pre->start) / step * BA_BYTE_LEN;
-			hem_list_link_bt(hr_dev, pre->addr + step,
-					 cur->dma_addr);
+			hem_list_link_bt(pre->addr + step, cur->dma_addr);
 		}
 	}
 

@@ -1281,7 +1278,7 @@ static int alloc_fake_root_bt(struct hns_roce_dev *hr_dev, void *cpu_base,
 	if (!hem)
 		return -ENOMEM;
 
-	hem_list_assign_bt(hr_dev, hem, cpu_base, phy_base);
+	hem_list_assign_bt(hem, cpu_base, phy_base);
 	list_add(&hem->list, branch_head);
 	list_add(&hem->sibling, leaf_head);
 

@@ -1304,7 +1301,7 @@ static int setup_middle_bt(struct hns_roce_dev *hr_dev, void *cpu_base,
 	/* if exist mid bt, link L1 to L0 */
 	list_for_each_entry_safe(hem, temp_hem, branch_head, list) {
 		offset = (hem->start - r->offset) / step * BA_BYTE_LEN;
-		hem_list_link_bt(hr_dev, cpu_base + offset, hem->dma_addr);
+		hem_list_link_bt(cpu_base + offset, hem->dma_addr);
 		total++;
 	}
 

index 105ad0aec922..60628ef1c46e 100644
@@ -3400,8 +3400,7 @@ static int hns_roce_v2_rereg_write_mtpt(struct hns_roce_dev *hr_dev,
 	return ret;
 }
 
-static int hns_roce_v2_frmr_write_mtpt(struct hns_roce_dev *hr_dev,
-				       void *mb_buf, struct hns_roce_mr *mr)
+static int hns_roce_v2_frmr_write_mtpt(void *mb_buf, struct hns_roce_mr *mr)
 {
 	dma_addr_t pbl_ba = hns_roce_get_mtr_ba(&mr->pbl_mtr);
 	struct hns_roce_v2_mpt_entry *mpt_entry;

@@ -4367,8 +4366,7 @@ static void set_access_flags(struct hns_roce_qp *hr_qp,
 }
 
 static void set_qpc_wqe_cnt(struct hns_roce_qp *hr_qp,
-			    struct hns_roce_v2_qp_context *context,
-			    struct hns_roce_v2_qp_context *qpc_mask)
+			    struct hns_roce_v2_qp_context *context)
 {
 	hr_reg_write(context, QPC_SGE_SHIFT,
 		     to_hr_hem_entries_shift(hr_qp->sge.sge_cnt,

@@ -4390,7 +4388,6 @@ static inline int get_pdn(struct ib_pd *ib_pd)
 }
 
 static void modify_qp_reset_to_init(struct ib_qp *ibqp,
-				    const struct ib_qp_attr *attr,
 				    struct hns_roce_v2_qp_context *context,
 				    struct hns_roce_v2_qp_context *qpc_mask)
 {

@@ -4409,7 +4406,7 @@ static void modify_qp_reset_to_init(struct ib_qp *ibqp,
 
 	hr_reg_write(context, QPC_RQWS, ilog2(hr_qp->rq.max_gs));
 
-	set_qpc_wqe_cnt(hr_qp, context, qpc_mask);
+	set_qpc_wqe_cnt(hr_qp, context);
 
 	/* No VLAN need to set 0xFFF */
 	hr_reg_write(context, QPC_VLAN_ID, 0xfff);

@@ -4454,7 +4451,6 @@ static void modify_qp_reset_to_init(struct ib_qp *ibqp,
 }
 
 static void modify_qp_init_to_init(struct ib_qp *ibqp,
-				   const struct ib_qp_attr *attr,
 				   struct hns_roce_v2_qp_context *context,
 				   struct hns_roce_v2_qp_context *qpc_mask)
 {

@@ -4752,8 +4748,7 @@ static int modify_qp_init_to_rtr(struct ib_qp *ibqp,
 	return 0;
 }
 
-static int modify_qp_rtr_to_rts(struct ib_qp *ibqp,
-				const struct ib_qp_attr *attr, int attr_mask,
+static int modify_qp_rtr_to_rts(struct ib_qp *ibqp, int attr_mask,
 				struct hns_roce_v2_qp_context *context,
 				struct hns_roce_v2_qp_context *qpc_mask)
 {

@@ -5121,15 +5116,14 @@ static int hns_roce_v2_set_abs_fields(struct ib_qp *ibqp,
 
 	if (cur_state == IB_QPS_RESET && new_state == IB_QPS_INIT) {
 		memset(qpc_mask, 0, hr_dev->caps.qpc_sz);
-		modify_qp_reset_to_init(ibqp, attr, context, qpc_mask);
+		modify_qp_reset_to_init(ibqp, context, qpc_mask);
 	} else if (cur_state == IB_QPS_INIT && new_state == IB_QPS_INIT) {
-		modify_qp_init_to_init(ibqp, attr, context, qpc_mask);
+		modify_qp_init_to_init(ibqp, context, qpc_mask);
 	} else if (cur_state == IB_QPS_INIT && new_state == IB_QPS_RTR) {
 		ret = modify_qp_init_to_rtr(ibqp, attr, attr_mask, context,
 					    qpc_mask);
 	} else if (cur_state == IB_QPS_RTR && new_state == IB_QPS_RTS) {
-		ret = modify_qp_rtr_to_rts(ibqp, attr, attr_mask, context,
-					   qpc_mask);
+		ret = modify_qp_rtr_to_rts(ibqp, attr_mask, context, qpc_mask);
 	}
 
 	return ret;

index 7b59b95f87c2..acdcd5c9f42f 100644
@@ -154,7 +154,7 @@ static int hns_roce_mr_enable(struct hns_roce_dev *hr_dev,
 	if (mr->type != MR_TYPE_FRMR)
 		ret = hr_dev->hw->write_mtpt(hr_dev, mailbox->buf, mr);
 	else
-		ret = hr_dev->hw->frmr_write_mtpt(hr_dev, mailbox->buf, mr);
+		ret = hr_dev->hw->frmr_write_mtpt(mailbox->buf, mr);
 	if (ret) {
 		dev_err(dev, "failed to write mtpt, ret = %d.\n", ret);
 		goto err_page;

@@ -714,7 +714,7 @@ static int mtr_map_bufs(struct hns_roce_dev *hr_dev, struct hns_roce_mtr *mtr,
 		return -ENOMEM;
 
 	if (mtr->umem)
-		npage = hns_roce_get_umem_bufs(hr_dev, pages, page_count,
+		npage = hns_roce_get_umem_bufs(pages, page_count,
 					       mtr->umem, page_shift);
 	else
 		npage = hns_roce_get_kmem_bufs(hr_dev, pages, page_count,

index 7af663176104..19136cb16960 100644
@@ -1139,7 +1139,6 @@ static int set_qp_param(struct hns_roce_dev *hr_dev, struct hns_roce_qp *hr_qp,
 }
 
 static int hns_roce_create_qp_common(struct hns_roce_dev *hr_dev,
-				     struct ib_pd *ib_pd,
 				     struct ib_qp_init_attr *init_attr,
 				     struct ib_udata *udata,
 				     struct hns_roce_qp *hr_qp)

@@ -1293,7 +1292,6 @@ int hns_roce_create_qp(struct ib_qp *qp, struct ib_qp_init_attr *init_attr,
 	struct ib_device *ibdev = qp->device;
 	struct hns_roce_dev *hr_dev = to_hr_dev(ibdev);
 	struct hns_roce_qp *hr_qp = to_hr_qp(qp);
-	struct ib_pd *pd = qp->pd;
 	int ret;
 
 	ret = check_qp_type(hr_dev, init_attr->qp_type, !!udata);

@@ -1308,7 +1306,7 @@ int hns_roce_create_qp(struct ib_qp *qp, struct ib_qp_init_attr *init_attr,
 		hr_qp->phy_port = hr_dev->iboe.phy_port[hr_qp->port];
 	}
 
-	ret = hns_roce_create_qp_common(hr_dev, pd, init_attr, udata, hr_qp);
+	ret = hns_roce_create_qp_common(hr_dev, init_attr, udata, hr_qp);
 	if (ret)
 		ibdev_err(ibdev, "create QP type 0x%x failed(%d)\n",
 			  init_attr->qp_type, ret);

index 652508b660a0..80fcb1b0e8fd 100644
@@ -249,7 +249,7 @@ static void free_srq_wqe_buf(struct hns_roce_dev *hr_dev,
 	hns_roce_mtr_destroy(hr_dev, &srq->buf_mtr);
 }
 
-static int alloc_srq_wrid(struct hns_roce_dev *hr_dev, struct hns_roce_srq *srq)
+static int alloc_srq_wrid(struct hns_roce_srq *srq)
 {
 	srq->wrid = kvmalloc_array(srq->wqe_cnt, sizeof(u64), GFP_KERNEL);
 	if (!srq->wrid)

@@ -365,7 +365,7 @@ static int alloc_srq_buf(struct hns_roce_dev *hr_dev, struct hns_roce_srq *srq,
 		goto err_idx;
 
 	if (!udata) {
-		ret = alloc_srq_wrid(hr_dev, srq);
+		ret = alloc_srq_wrid(srq);
 		if (ret)
 			goto err_wqe_buf;
 	}

index 6e0ca8a4b2a8..f1de497fc977 100644
@@ -986,6 +986,7 @@ struct hns_roce_hem_item {
 	size_t count; /* max ba numbers */
 	int start; /* start buf offset in this hem */
 	int end; /* end buf offset in this hem */
+	bool exist_bt;
 };
 
 /* All HEM items are linked in a tree structure */

@@ -1014,6 +1015,7 @@ hem_list_alloc_item(struct hns_roce_dev *hr_dev, int start, int end, int count,
 		}
 	}
 
+	hem->exist_bt = exist_bt;
 	hem->count = count;
 	hem->start = start;
 	hem->end = end;

@@ -1024,22 +1026,22 @@ hem_list_alloc_item(struct hns_roce_dev *hr_dev, int start, int end, int count,
 }
 
 static void hem_list_free_item(struct hns_roce_dev *hr_dev,
-			       struct hns_roce_hem_item *hem, bool exist_bt)
+			       struct hns_roce_hem_item *hem)
 {
-	if (exist_bt)
+	if (hem->exist_bt)
 		dma_free_coherent(hr_dev->dev, hem->count * BA_BYTE_LEN,
 				  hem->addr, hem->dma_addr);
 	kfree(hem);
 }
 
 static void hem_list_free_all(struct hns_roce_dev *hr_dev,
-			      struct list_head *head, bool exist_bt)
+			      struct list_head *head)
 {
 	struct hns_roce_hem_item *hem, *temp_hem;
 
 	list_for_each_entry_safe(hem, temp_hem, head, list) {
 		list_del(&hem->list);
-		hem_list_free_item(hr_dev, hem, exist_bt);
+		hem_list_free_item(hr_dev, hem);
 	}
 }
 

@@ -1139,6 +1141,10 @@ int hns_roce_hem_list_calc_root_ba(const struct hns_roce_buf_region *regions,
 
 	for (i = 0; i < region_cnt; i++) {
 		r = (struct hns_roce_buf_region *)&regions[i];
+		/* when r->hopnum = 0, the region should not occupy root_ba. */
+		if (!r->hopnum)
+			continue;
+
 		if (r->hopnum > 1) {
 			step = hem_list_calc_ba_range(r->hopnum, 1, unit);
 			if (step > 0)

@@ -1232,7 +1238,7 @@ static int hem_list_alloc_mid_bt(struct hns_roce_dev *hr_dev,
 
 err_exit:
 	for (level = 1; level < hopnum; level++)
-		hem_list_free_all(hr_dev, &temp_list[level], true);
+		hem_list_free_all(hr_dev, &temp_list[level]);
 
 	return ret;
 }

@@ -1273,16 +1279,26 @@ static int alloc_fake_root_bt(struct hns_roce_dev *hr_dev, void *cpu_base,
 {
 	struct hns_roce_hem_item *hem;
 
+	/* This is on the has_mtt branch, if r->hopnum
+	 * is 0, there is no root_ba to reuse for the
+	 * region's fake hem, so a dma_alloc request is
+	 * necessary here.
+	 */
 	hem = hem_list_alloc_item(hr_dev, r->offset, r->offset + r->count - 1,
-				  r->count, false);
+				  r->count, !r->hopnum);
 	if (!hem)
 		return -ENOMEM;
 
-	hem_list_assign_bt(hem, cpu_base, phy_base);
+	/* The root_ba can be reused only when r->hopnum > 0. */
+	if (r->hopnum)
+		hem_list_assign_bt(hem, cpu_base, phy_base);
 	list_add(&hem->list, branch_head);
 	list_add(&hem->sibling, leaf_head);
 
-	return r->count;
+	/* If r->hopnum == 0, 0 is returned,
+	 * so that the root_bt entry is not occupied.
+	 */
+	return r->hopnum ? r->count : 0;
 }
 
 static int setup_middle_bt(struct hns_roce_dev *hr_dev, void *cpu_base,

@@ -1326,7 +1342,7 @@ setup_root_hem(struct hns_roce_dev *hr_dev, struct hns_roce_hem_list *hem_list,
 		return -ENOMEM;
 
 	total = 0;
-	for (i = 0; i < region_cnt && total < max_ba_num; i++) {
+	for (i = 0; i < region_cnt && total <= max_ba_num; i++) {
 		r = &regions[i];
 		if (!r->count)
 			continue;

@@ -1392,9 +1408,9 @@ static int hem_list_alloc_root_bt(struct hns_roce_dev *hr_dev,
 			     region_cnt);
 	if (ret) {
 		for (i = 0; i < region_cnt; i++)
-			hem_list_free_all(hr_dev, &head.branch[i], false);
+			hem_list_free_all(hr_dev, &head.branch[i]);
 
-		hem_list_free_all(hr_dev, &head.root, true);
+		hem_list_free_all(hr_dev, &head.root);
 	}
 
 	return ret;

@@ -1457,10 +1473,9 @@ void hns_roce_hem_list_release(struct hns_roce_dev *hr_dev,
 
 	for (i = 0; i < HNS_ROCE_MAX_BT_REGION; i++)
 		for (j = 0; j < HNS_ROCE_MAX_BT_LEVEL; j++)
-			hem_list_free_all(hr_dev, &hem_list->mid_bt[i][j],
-					  j != 0);
+			hem_list_free_all(hr_dev, &hem_list->mid_bt[i][j]);
 
-	hem_list_free_all(hr_dev, &hem_list->root_bt, true);
+	hem_list_free_all(hr_dev, &hem_list->root_bt);
 	INIT_LIST_HEAD(&hem_list->btm_bt);
 	hem_list->root_ba = 0;
 }

index acdcd5c9f42f..408ef2a96149 100644
@@ -767,11 +767,6 @@ int hns_roce_mtr_map(struct hns_roce_dev *hr_dev, struct hns_roce_mtr *mtr,
 	for (i = 0, mapped_cnt = 0; i < mtr->hem_cfg.region_count &&
 	     mapped_cnt < page_cnt; i++) {
 		r = &mtr->hem_cfg.region[i];
-		/* if hopnum is 0, no need to map pages in this region */
-		if (!r->hopnum) {
-			mapped_cnt += r->count;
-			continue;
-		}
 
 		if (r->offset + r->count > page_cnt) {
 			ret = -EINVAL;

index 60628ef1c46e..23667cfbf8e7 100644
@@ -471,7 +471,7 @@ static inline int set_ud_wqe(struct hns_roce_qp *qp,
 	valid_num_sge = calc_wr_sge_num(wr, &msg_len);
 
 	ret = set_ud_opcode(ud_sq_wqe, wr);
-	if (WARN_ON(ret))
+	if (WARN_ON_ONCE(ret))
 		return ret;
 
 	ud_sq_wqe->msg_len = cpu_to_le32(msg_len);

@@ -575,7 +575,7 @@ static inline int set_rc_wqe(struct hns_roce_qp *qp,
 	rc_sq_wqe->msg_len = cpu_to_le32(msg_len);
 
 	ret = set_rc_opcode(hr_dev, rc_sq_wqe, wr);
-	if (WARN_ON(ret))
+	if (WARN_ON_ONCE(ret))
 		return ret;
 
 	hr_reg_write(rc_sq_wqe, RC_SEND_WQE_SO,

index 23667cfbf8e7..ab0dca9d199a 100644
@@ -673,6 +673,10 @@ static void write_dwqe(struct hns_roce_dev *hr_dev, struct hns_roce_qp *qp,
 #define HNS_ROCE_SL_SHIFT 2
 	struct hns_roce_v2_rc_send_wqe *rc_sq_wqe = wqe;
 
+	if (unlikely(qp->state == IB_QPS_ERR)) {
+		flush_cqe(hr_dev, qp);
+		return;
+	}
 	/* All kinds of DirectWQE have the same header field layout */
 	hr_reg_enable(rc_sq_wqe, RC_SEND_WQE_FLAG);
 	hr_reg_write(rc_sq_wqe, RC_SEND_WQE_DB_SL_L, qp->sl);

index 0046a4ee6e64..5b4517b0ca08 100644
@@ -8,6 +8,7 @@
   Author: Giuseppe Cavallaro <[email protected]>
 *******************************************************************************/
 
+#include <linux/device.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
 #include <linux/module.h>

@@ -628,6 +629,39 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac)
 	return ret;
 }
 
+static void devm_stmmac_remove_config_dt(void *data)
+{
+	struct plat_stmmacenet_data *plat = data;
+
+	/* Platform data argument is unused */
+	stmmac_remove_config_dt(NULL, plat);
+}
+
+/**
+ * devm_stmmac_probe_config_dt
+ * @pdev: platform_device structure
+ * @mac: MAC address to use
+ * Description: Devres variant of stmmac_probe_config_dt(). Does not require
+ * the user to call stmmac_remove_config_dt() at driver detach.
+ */
+struct plat_stmmacenet_data *
+devm_stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac)
+{
+	struct plat_stmmacenet_data *plat;
+	int ret;
+
+	plat = stmmac_probe_config_dt(pdev, mac);
+	if (IS_ERR(plat))
+		return plat;
+
+	ret = devm_add_action_or_reset(&pdev->dev,
+				       devm_stmmac_remove_config_dt, plat);
+	if (ret)
+		return ERR_PTR(ret);
+
+	return plat;
+}
+
 /**
  * stmmac_remove_config_dt - undo the effects of stmmac_probe_config_dt()
  * @pdev: platform_device structure

@@ -650,12 +684,19 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac)
 	return ERR_PTR(-EINVAL);
 }
 
+struct plat_stmmacenet_data *
+devm_stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac)
+{
+	return ERR_PTR(-EINVAL);
+}
+
 void stmmac_remove_config_dt(struct platform_device *pdev,
 			     struct plat_stmmacenet_data *plat)
 {
 }
 #endif /* CONFIG_OF */
 EXPORT_SYMBOL_GPL(stmmac_probe_config_dt);
+EXPORT_SYMBOL_GPL(devm_stmmac_probe_config_dt);
 EXPORT_SYMBOL_GPL(stmmac_remove_config_dt);
 
 int stmmac_get_platform_resources(struct platform_device *pdev,

index 3fff3f59d73d..2102c6d41464 100644
@@ -13,6 +13,8 @@
 
 struct plat_stmmacenet_data *
 stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac);
+struct plat_stmmacenet_data *
+devm_stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac);
 void stmmac_remove_config_dt(struct platform_device *pdev,
 			     struct plat_stmmacenet_data *plat);
 

index 5b4517b0ca08..e7e7d388399d 100644
@@ -294,62 +294,80 @@ static int stmmac_mtl_setup(struct platform_device *pdev,
 }
 
 /**
- * stmmac_dt_phy - parse device-tree driver parameters to allocate PHY resources
- * @plat: driver data platform structure
- * @np: device tree node
- * @dev: device pointer
- * Description:
- * The mdio bus will be allocated in case of a phy transceiver is on board;
- * it will be NULL if the fixed-link is configured.
- * If there is the "snps,dwmac-mdio" sub-node the mdio will be allocated
- * in any case (for DSA, mdio must be registered even if fixed-link).
- * The table below sums the supported configurations:
- *	-------------------------------
- *	snps,phy-addr	|     Y
- *	-------------------------------
- *	phy-handle	|     Y
- *	-------------------------------
- *	fixed-link	|     N
- *	-------------------------------
- *	snps,dwmac-mdio	|
- *	  even if	|     Y
- *	fixed-link	|
- *	-------------------------------
+ * stmmac_of_get_mdio() - Gets the MDIO bus from the devicetree.
+ * @np: devicetree node
  *
- * It returns 0 in case of success otherwise -ENODEV.
+ * The MDIO bus will be searched for in the following ways:
+ * 1. The compatible is "snps,dwc-qos-ethernet-4.10" && a "mdio" named
+ *    child node exists
+ * 2. A child node with the "snps,dwmac-mdio" compatible is present
+ *
+ * Return: The MDIO node if present otherwise NULL
  */
-static int stmmac_dt_phy(struct plat_stmmacenet_data *plat,
-			 struct device_node *np, struct device *dev)
+static struct device_node *stmmac_of_get_mdio(struct device_node *np)
 {
-	bool mdio = !of_phy_is_fixed_link(np);
 	static const struct of_device_id need_mdio_ids[] = {
 		{ .compatible = "snps,dwc-qos-ethernet-4.10" },
 		{},
 	};
+	struct device_node *mdio_node = NULL;
 
 	if (of_match_node(need_mdio_ids, np)) {
-		plat->mdio_node = of_get_child_by_name(np, "mdio");
+		mdio_node = of_get_child_by_name(np, "mdio");
 	} else {
 		/**
 		 * If snps,dwmac-mdio is passed from DT, always register
 		 * the MDIO
 		 */
-		for_each_child_of_node(np, plat->mdio_node) {
-			if (of_device_is_compatible(plat->mdio_node,
+		for_each_child_of_node(np, mdio_node) {
+			if (of_device_is_compatible(mdio_node,
 						    "snps,dwmac-mdio"))
 				break;
 		}
 	}
 
-	if (plat->mdio_node) {
+	return mdio_node;
+}
+
+/**
+ * stmmac_mdio_setup() - Populate platform related MDIO structures.
+ * @plat: driver data platform structure
+ * @np: devicetree node
+ * @dev: device pointer
+ *
+ * This searches for MDIO information from the devicetree.
+ * If an MDIO node is found, it's assigned to plat->mdio_node and
+ * plat->mdio_bus_data is allocated.
+ * If no connection can be determined, just plat->mdio_bus_data is allocated
+ * to indicate a bus should be created and scanned for a phy.
+ * If it's determined there's no MDIO bus needed, both are left NULL.
+ *
+ * This expects that plat->phy_node has already been searched for.
+ *
+ * Return: 0 on success, errno otherwise.
+ */
+static int stmmac_mdio_setup(struct plat_stmmacenet_data *plat,
+			     struct device_node *np, struct device *dev)
+{
+	bool legacy_mdio;
+
+	plat->mdio_node = stmmac_of_get_mdio(np);
+	if (plat->mdio_node)
 		dev_dbg(dev, "Found MDIO subnode\n");
-		mdio = true;
-	}
 
-	if (mdio) {
-		plat->mdio_bus_data =
-			devm_kzalloc(dev, sizeof(struct stmmac_mdio_bus_data),
-				     GFP_KERNEL);
+	/* Legacy devicetrees allowed for no MDIO bus description and expect
+	 * the bus to be scanned for devices. If there's no phy or fixed-link
+	 * described assume this is the case since there must be something
+	 * connected to the MAC.
+	 */
+	legacy_mdio = !of_phy_is_fixed_link(np) && !plat->phy_node;
+	if (legacy_mdio)
+		dev_info(dev, "Deprecated MDIO bus assumption used\n");
+
+	if (plat->mdio_node || legacy_mdio) {
+		plat->mdio_bus_data = devm_kzalloc(dev,
+						   sizeof(*plat->mdio_bus_data),
+						   GFP_KERNEL);
 		if (!plat->mdio_bus_data)
 			return -ENOMEM;
 

@@ -454,8 +472,7 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac)
 	if (of_property_read_u32(np, "snps,phy-addr", &plat->phy_addr) == 0)
 		dev_warn(&pdev->dev, "snps,phy-addr property is deprecated\n");
 
-	/* To Configure PHY by using all device-tree supported properties */
-	rc = stmmac_dt_phy(plat, np, &pdev->dev);
+	rc = stmmac_mdio_setup(plat, np, &pdev->dev);
 	if (rc)
 		return ERR_PTR(rc);
 

index e7e7d388399d..c368ef3cd9cb 100644
@@ -473,8 +473,10 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac)
 		dev_warn(&pdev->dev, "snps,phy-addr property is deprecated\n");
 
 	rc = stmmac_mdio_setup(plat, np, &pdev->dev);
-	if (rc)
-		return ERR_PTR(rc);
+	if (rc) {
+		ret = ERR_PTR(rc);
+		goto error_put_phy;
+	}
 
 	of_property_read_u32(np, "tx-fifo-depth", &plat->tx_fifo_size);
 

@@ -560,8 +562,8 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac)
 	dma_cfg = devm_kzalloc(&pdev->dev, sizeof(*dma_cfg),
 			       GFP_KERNEL);
 	if (!dma_cfg) {
-		stmmac_remove_config_dt(pdev, plat);
-		return ERR_PTR(-ENOMEM);
+		ret = ERR_PTR(-ENOMEM);
+		goto error_put_mdio;
 	}
 	plat->dma_cfg = dma_cfg;
 

@@ -589,8 +591,8 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac)
 
 	rc = stmmac_mtl_setup(pdev, plat);
 	if (rc) {
-		stmmac_remove_config_dt(pdev, plat);
-		return ERR_PTR(rc);
+		ret = ERR_PTR(rc);
+		goto error_put_mdio;
 	}
 
 	/* clock setup */

@@ -642,6 +644,10 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac)
 	clk_disable_unprepare(plat->pclk);
 error_pclk_get:
 	clk_disable_unprepare(plat->stmmac_clk);
+error_put_mdio:
+	of_node_put(plat->mdio_node);
+error_put_phy:
+	of_node_put(plat->phy_node);
 
 	return ret;
 }

@@ -650,16 +656,17 @@ static void devm_stmmac_remove_config_dt(void *data)
 {
 	struct plat_stmmacenet_data *plat = data;
 
-	/* Platform data argument is unused */
-	stmmac_remove_config_dt(NULL, plat);
+	clk_disable_unprepare(plat->stmmac_clk);
+	clk_disable_unprepare(plat->pclk);
+	of_node_put(plat->mdio_node);
+	of_node_put(plat->phy_node);
 }
 
 /**
  * devm_stmmac_probe_config_dt
  * @pdev: platform_device structure
  * @mac: MAC address to use
- * Description: Devres variant of stmmac_probe_config_dt(). Does not require
- * the user to call stmmac_remove_config_dt() at driver detach.
+ * Description: Devres variant of stmmac_probe_config_dt().
  */
 struct plat_stmmacenet_data *
 devm_stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac)

index 9ac47ccfe120..2379ee551164 100644
@@ -7124,6 +7124,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 			if (unlikely(!inet_csk_reqsk_queue_hash_add(sk, req,
 								    req->timeout))) {
 				reqsk_free(req);
+				dst_release(dst);
 				return 0;
 			}
 

index f1ba369306fe..84751313b826 100644
@@ -57,6 +57,13 @@ struct ip_tunnel_key {
 	__u8			flow_flags;
 };
 
+struct ip_tunnel_encap {
+	u16			type;
+	u16			flags;
+	__be16			sport;
+	__be16			dport;
+};
+
 /* Flags for ip_tunnel_info mode. */
 #define IP_TUNNEL_INFO_TX	0x01	/* represents tx tunnel parameters */
 #define IP_TUNNEL_INFO_IPV6	0x02	/* key contains IPv6 addresses */

@@ -66,9 +73,9 @@ struct ip_tunnel_key {
 #define IP_TUNNEL_OPTS_MAX					\
 	GENMASK((sizeof_field(struct ip_tunnel_info,		\
 			      options_len) * BITS_PER_BYTE) - 1, 0)
-
 struct ip_tunnel_info {
 	struct ip_tunnel_key	key;
+	struct ip_tunnel_encap	encap;
 #ifdef CONFIG_DST_CACHE
 	struct dst_cache	dst_cache;
 #endif

@@ -86,13 +93,6 @@ struct ip_tunnel_6rd_parm {
 };
 #endif
 
-struct ip_tunnel_encap {
-	u16			type;
-	u16			flags;
-	__be16			sport;
-	__be16			dport;
-};
-
 struct ip_tunnel_prl_entry {
 	struct ip_tunnel_prl_entry __rcu *next;
 	__be32				addr;

@@ -293,6 +293,7 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn,
 				   __be32 remote, __be32 local,
 				   __be32 key);
 
+void ip_tunnel_md_udp_encap(struct sk_buff *skb, struct ip_tunnel_info *info);
 int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb,
 		  const struct tnl_ptk_info *tpi, struct metadata_dst *tun_dst,
 		  bool log_ecn_error);

@@ -405,22 +406,23 @@ static inline int ip_encap_hlen(struct ip_tunnel_encap *e)
 	return hlen;
 }
 
-static inline int ip_tunnel_encap(struct sk_buff *skb, struct ip_tunnel *t,
+static inline int ip_tunnel_encap(struct sk_buff *skb,
+				  struct ip_tunnel_encap *e,
 				  u8 *protocol, struct flowi4 *fl4)
 {
 	const struct ip_tunnel_encap_ops *ops;
 	int ret = -EINVAL;
 
-	if (t->encap.type == TUNNEL_ENCAP_NONE)
+	if (e->type == TUNNEL_ENCAP_NONE)
 		return 0;
 
-	if (t->encap.type >= MAX_IPTUN_ENCAP_OPS)
+	if (e->type >= MAX_IPTUN_ENCAP_OPS)
 		return -EINVAL;
 
 	rcu_read_lock();
-	ops = rcu_dereference(iptun_encaps[t->encap.type]);
+	ops = rcu_dereference(iptun_encaps[e->type]);
 	if (likely(ops && ops->build_header))
-		ret = ops->build_header(skb, &t->encap, protocol, fl4);
+		ret = ops->build_header(skb, e, protocol, fl4);
 	rcu_read_unlock();
 
 	return ret;

index 3445e576b05b..d56cfb6c3da4 100644
@@ -359,6 +359,20 @@ static struct ip_tunnel *ip_tunnel_create(struct net *net,
 	return ERR_PTR(err);
 }
 
+void ip_tunnel_md_udp_encap(struct sk_buff *skb, struct ip_tunnel_info *info)
+{
+	const struct iphdr *iph = ip_hdr(skb);
+	const struct udphdr *udph;
+
+	if (iph->protocol != IPPROTO_UDP)
+		return;
+
+	udph = (struct udphdr *)((__u8 *)iph + (iph->ihl << 2));
+	info->encap.sport = udph->source;
+	info->encap.dport = udph->dest;
+}
+EXPORT_SYMBOL(ip_tunnel_md_udp_encap);
+
 int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb,
 		  const struct tnl_ptk_info *tpi, struct metadata_dst *tun_dst,
 		  bool log_ecn_error)

@@ -599,7 +613,11 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 			    tunnel_id_to_key32(key->tun_id), RT_TOS(tos),
 			    dev_net(dev), 0, skb->mark, skb_get_hash(skb),
 			    key->flow_flags);
-	if (tunnel->encap.type != TUNNEL_ENCAP_NONE)
+
+	if (!tunnel_hlen)
+		tunnel_hlen = ip_encap_hlen(&tun_info->encap);
+
+	if (ip_tunnel_encap(skb, &tun_info->encap, &proto, &fl4) < 0)
 		goto tx_error;
 
 	use_cache = ip_tunnel_dst_cache_usable(skb, tun_info);

@@ -759,7 +777,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 			    dev_net(dev), tunnel->parms.link,
 			    tunnel->fwmark, skb_get_hash(skb), 0);
 
-	if (ip_tunnel_encap(skb, tunnel, &protocol, &fl4) < 0)
+	if (ip_tunnel_encap(skb, &tunnel->encap, &protocol, &fl4) < 0)
 		goto tx_error;
 
 	if (connected && md) {

index 180f9daf5bec..1cf35c50cdf4 100644
@@ -241,6 +241,7 @@ static int ipip_tunnel_rcv(struct sk_buff *skb, u8 ipproto)
 			tun_dst = ip_tun_rx_dst(skb, 0, 0, 0);
 			if (!tun_dst)
 				return 0;
+			ip_tunnel_md_udp_encap(skb, &tun_dst->u.tun_info);
 		}
 		skb_reset_mac_header(skb);
 

index 3ffb6a5b1f82..cc24cefdb85c 100644
@@ -1024,7 +1024,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 		ttl = iph6->hop_limit;
 	tos = INET_ECN_encapsulate(tos, ipv6_get_dsfield(iph6));
 
-	if (ip_tunnel_encap(skb, tunnel, &protocol, &fl4) < 0) {
+	if (ip_tunnel_encap(skb, &tunnel->encap, &protocol, &fl4) < 0) {
 		ip_rt_put(rt);
 		goto tx_error;
 	}

index d56cfb6c3da4..196fe734ad38 100644
@@ -102,10 +102,9 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn,
 		if (!ip_tunnel_key_match(&t->parms, flags, key))
 			continue;
 
-		if (t->parms.link == link)
+		if (READ_ONCE(t->parms.link) == link)
 			return t;
-		else
-			cand = t;
+		cand = t;
 	}
 
 	hlist_for_each_entry_rcu(t, head, hash_node) {

@@ -117,9 +116,9 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn,
 		if (!ip_tunnel_key_match(&t->parms, flags, key))
 			continue;
 
-		if (t->parms.link == link)
+		if (READ_ONCE(t->parms.link) == link)
 			return t;
-		else if (!cand)
+		if (!cand)
 			cand = t;
 	}
 

@@ -137,9 +136,9 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn,
 		if (!ip_tunnel_key_match(&t->parms, flags, key))
 			continue;
 
-		if (t->parms.link == link)
+		if (READ_ONCE(t->parms.link) == link)
 			return t;
-		else if (!cand)
+		if (!cand)
 			cand = t;
 	}
 

@@ -150,9 +149,9 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn,
 		    !(t->dev->flags & IFF_UP))
 			continue;
 
-		if (t->parms.link == link)
+		if (READ_ONCE(t->parms.link) == link)
 			return t;
-		else if (!cand)
+		if (!cand)
 			cand = t;
 	}
 

@@ -221,7 +220,7 @@ static struct ip_tunnel *ip_tunnel_find(struct ip_tunnel_net *itn,
 	hlist_for_each_entry_rcu(t, head, hash_node) {
 		if (local == t->parms.iph.saddr &&
 		    remote == t->parms.iph.daddr &&
-		    link == t->parms.link &&
+		    link == READ_ONCE(t->parms.link) &&
 		    type == t->dev->type &&
 		    ip_tunnel_key_match(&t->parms, flags, key))
 			break;

@@ -774,7 +773,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 
 	ip_tunnel_init_flow(&fl4, protocol, dst, tnl_params->saddr,
 			    tunnel->parms.o_key, RT_TOS(tos),
-			    dev_net(dev), tunnel->parms.link,
+			    dev_net(dev), READ_ONCE(tunnel->parms.link),
 			    tunnel->fwmark, skb_get_hash(skb), 0);
 
 	if (ip_tunnel_encap(skb, &tunnel->encap, &protocol, &fl4) < 0)

@@ -894,7 +893,7 @@ static void ip_tunnel_update(struct ip_tunnel_net *itn,
 	if (t->parms.link != p->link || t->fwmark != fwmark) {
 		int mtu;
 
-		t->parms.link = p->link;
+		WRITE_ONCE(t->parms.link, p->link);
 		t->fwmark = fwmark;
 		mtu = ip_tunnel_bind_dev(dev);
 		if (set_mtu)

@@ -1084,9 +1083,9 @@ EXPORT_SYMBOL(ip_tunnel_get_link_net);
 
 int ip_tunnel_get_iflink(const struct net_device *dev)
 {
-	struct ip_tunnel *tunnel = netdev_priv(dev);
+	const struct ip_tunnel *tunnel = netdev_priv(dev);
 
-	return tunnel->parms.link;
+	return READ_ONCE(tunnel->parms.link);
 }
 EXPORT_SYMBOL(ip_tunnel_get_iflink);
 

index 196fe734ad38..d3ad2c424fe9 100644
@@ -293,7 +293,7 @@ static int ip_tunnel_bind_dev(struct net_device *dev)
 
 		ip_tunnel_init_flow(&fl4, iph->protocol, iph->daddr,
 				    iph->saddr, tunnel->parms.o_key,
-				    RT_TOS(iph->tos), dev_net(dev),
+				    iph->tos & INET_DSCP_MASK, dev_net(dev),
 				    tunnel->parms.link, tunnel->fwmark, 0, 0);
 		rt = ip_route_output_key(tunnel->net, &fl4);
 

index d3ad2c424fe9..eb74e33ffb64 100644
@@ -43,6 +43,7 @@
 #include <net/rtnetlink.h>
 #include <net/udp.h>
 #include <net/dst_metadata.h>
+#include <net/inet_dscp.h>
 
 #if IS_ENABLED(CONFIG_IPV6)
 #include <net/ipv6.h>

@@ -609,9 +610,9 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 			tos = ipv6_get_dsfield((const struct ipv6hdr *)inner_iph);
 	}
 	ip_tunnel_init_flow(&fl4, proto, key->u.ipv4.dst, key->u.ipv4.src,
-			    tunnel_id_to_key32(key->tun_id), RT_TOS(tos),
-			    dev_net(dev), 0, skb->mark, skb_get_hash(skb),
-			    key->flow_flags);
+			    tunnel_id_to_key32(key->tun_id),
+			    tos & INET_DSCP_MASK, dev_net(dev), 0, skb->mark,
+			    skb_get_hash(skb), key->flow_flags);
 
 	if (!tunnel_hlen)
 		tunnel_hlen = ip_encap_hlen(&tun_info->encap);

index eb74e33ffb64..4f30ccf2d321 100644
@@ -773,7 +773,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 	}
 
 	ip_tunnel_init_flow(&fl4, protocol, dst, tnl_params->saddr,
-			    tunnel->parms.o_key, RT_TOS(tos),
+			    tunnel->parms.o_key, tos & INET_DSCP_MASK,
 			    dev_net(dev), READ_ONCE(tunnel->parms.link),
 			    tunnel->fwmark, skb_get_hash(skb), 0);
 

index b3472fb94617..8883ef012747 100644
@@ -423,8 +423,7 @@ mlxsw_sp_span_gretap4_route(const struct net_device *to_dev,
 
 	parms = mlxsw_sp_ipip_netdev_parms4(to_dev);
 	ip_tunnel_init_flow(&fl4, parms.iph.protocol, *daddrp, *saddrp,
-			    0, 0, dev_net(to_dev), parms.link, tun->fwmark, 0,
-			    0);
+			    0, 0, tun->net, parms.link, tun->fwmark, 0, 0);
 
 	rt = ip_route_output_key(tun->net, &fl4);
 	if (IS_ERR(rt))

index 4f30ccf2d321..67cabc40f1dc 100644
@@ -294,7 +294,7 @@ static int ip_tunnel_bind_dev(struct net_device *dev)
 
 		ip_tunnel_init_flow(&fl4, iph->protocol, iph->daddr,
 				    iph->saddr, tunnel->parms.o_key,
-				    iph->tos & INET_DSCP_MASK, dev_net(dev),
+				    iph->tos & INET_DSCP_MASK, tunnel->net,
 				    tunnel->parms.link, tunnel->fwmark, 0, 0);
 		rt = ip_route_output_key(tunnel->net, &fl4);
 

@@ -611,7 +611,7 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 	}
 	ip_tunnel_init_flow(&fl4, proto, key->u.ipv4.dst, key->u.ipv4.src,
 			    tunnel_id_to_key32(key->tun_id),
-			    tos & INET_DSCP_MASK, dev_net(dev), 0, skb->mark,
+			    tos & INET_DSCP_MASK, tunnel->net, 0, skb->mark,
 			    skb_get_hash(skb), key->flow_flags);
 
 	if (!tunnel_hlen)

@@ -774,7 +774,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 
 	ip_tunnel_init_flow(&fl4, protocol, dst, tnl_params->saddr,
 			    tunnel->parms.o_key, tos & INET_DSCP_MASK,
-			    dev_net(dev), READ_ONCE(tunnel->parms.link),
+			    tunnel->net, READ_ONCE(tunnel->parms.link),
 			    tunnel->fwmark, skb_get_hash(skb), 0);
 
 	if (ip_tunnel_encap(skb, &tunnel->encap, &protocol, &fl4) < 0)

index bd2b17b219ae..0b270893ee14 100644
@@ -754,6 +754,12 @@ int nr_route_frame(struct sk_buff *skb, ax25_cb *ax25)
 	int ret;
 	struct sk_buff *skbn;
 
+	/*
+	 * Reject malformed packets early. Check that it contains at least 2
+	 * addresses and 1 byte more for Time-To-Live
+	 */
+	if (skb->len < 2 * sizeof(ax25_address) + 1)
+		return 0;
 
 	nr_src  = (ax25_address *)(skb->data + 0);
 	nr_dest = (ax25_address *)(skb->data + 7);

index f8d0523f4c18..d1dcb018117d 100644
@@ -134,7 +134,7 @@ static void gen11_rc6_enable(struct intel_rc6 *rc6)
 			GEN9_MEDIA_PG_ENABLE |
 			GEN11_MEDIA_SAMPLER_PG_ENABLE;
 
-	if (GRAPHICS_VER(gt->i915) >= 12) {
+	if (GRAPHICS_VER(gt->i915) >= 12 && !IS_DG1(gt->i915)) {
 		for (i = 0; i < I915_MAX_VCS; i++)
 			if (HAS_ENGINE(gt, _VCS(i)))
 				pg_enable |= (VDN_HCP_POWERGATE_ENABLE(i) |

index c24b04235d91..d11398aa642e 100644
@@ -706,15 +706,18 @@ struct nft_set_ext_tmpl {
 /**
  *	struct nft_set_ext - set extensions
  *
- *	@genmask: generation mask
+ *	@genmask: generation mask, but also flags (see NFT_SET_ELEM_DEAD_BIT)
  *	@offset: offsets of individual extension types
  *	@data: beginning of extension data
+ *
+ *	This structure must be aligned to word size, otherwise atomic bitops
+ *	on genmask field can cause alignment failure on some archs.
  */
 struct nft_set_ext {
 	u8	genmask;
 	u8	offset[NFT_SET_EXT_NUM];
 	char	data[];
-};
+} __aligned(BITS_PER_LONG / 8);
 
 static inline void nft_set_ext_prepare(struct nft_set_ext_tmpl *tmpl)
 {

index 51bccfb00a9c..61b0159b2fbe 100644
@@ -124,8 +124,8 @@ static inline int llc_fixup_skb(struct sk_buff *skb)
 	if (unlikely(!pskb_may_pull(skb, llc_len)))
 		return 0;
 
-	skb->transport_header += llc_len;
 	skb_pull(skb, llc_len);
+	skb_reset_transport_header(skb);
 	if (skb->protocol == htons(ETH_P_802_2)) {
 		__be16 pdulen;
 		s32 data_size;

index 6eb7d93b358d..20ac32635f1f 100644
@@ -687,7 +687,7 @@ static int snd_us16x08_meter_get(struct snd_kcontrol *kcontrol,
 	struct usb_mixer_elem_info *elem = kcontrol->private_data;
 	struct snd_usb_audio *chip = elem->head.mixer->chip;
 	struct snd_us16x08_meter_store *store = elem->private_data;
-	u8 meter_urb[64];
+	u8 meter_urb[64] = {0};
 
 	switch (kcontrol->private_value) {
 	case 0: {

index 1693f6c60efc..e53ab9b5482e 100644
@@ -1956,7 +1956,11 @@ static int bcm_sysport_open(struct net_device *dev)
 	unsigned int i;
 	int ret;
 
-	clk_prepare_enable(priv->clk);
+	ret = clk_prepare_enable(priv->clk);
+	if (ret) {
+		netdev_err(dev, "could not enable priv clock\n");
+		return ret;
+	}
 
 	/* Reset UniMAC */
 	umac_reset(priv);

@@ -2614,7 +2618,11 @@ static int bcm_sysport_probe(struct platform_device *pdev)
 		goto err_deregister_notifier;
 	}
 
-	clk_prepare_enable(priv->clk);
+	ret = clk_prepare_enable(priv->clk);
+	if (ret) {
+		dev_err(&pdev->dev, "could not enable priv clock\n");
+		goto err_deregister_netdev;
+	}
 
 	priv->rev = topctrl_readl(priv, REV_CNTL) & REV_MASK;
 	dev_info(&pdev->dev,

@@ -2628,6 +2636,8 @@ static int bcm_sysport_probe(struct platform_device *pdev)
 
 	return 0;
 
+err_deregister_netdev:
+	unregister_netdev(dev);
 err_deregister_notifier:
 	unregister_netdevice_notifier(&priv->netdev_notifier);
 err_deregister_fixed_link:

@@ -2799,7 +2809,12 @@ static int __maybe_unused bcm_sysport_resume(struct device *d)
 	if (!netif_running(dev))
 		return 0;
 
-	clk_prepare_enable(priv->clk);
+	ret = clk_prepare_enable(priv->clk);
+	if (ret) {
+		netdev_err(dev, "could not enable priv clock\n");
+		return ret;
+	}
+
 	if (priv->wolopts)
 		clk_disable_unprepare(priv->wol_clk);
 

index 8941f69d93e9..b9dda48326d5 100644
@@ -2707,9 +2707,15 @@ static struct platform_device *port_platdev[3];
 
 static void mv643xx_eth_shared_of_remove(void)
 {
+	struct mv643xx_eth_platform_data *pd;
 	int n;
 
 	for (n = 0; n < 3; n++) {
+		if (!port_platdev[n])
+			continue;
+		pd = dev_get_platdata(&port_platdev[n]->dev);
+		if (pd)
+			of_node_put(pd->phy_node);
 		platform_device_del(port_platdev[n]);
 		port_platdev[n] = NULL;
 	}

@@ -2770,8 +2776,10 @@ static int mv643xx_eth_shared_of_add_port(struct platform_device *pdev,
 	}
 
 	ppdev = platform_device_alloc(MV643XX_ETH_NAME, dev_num);
-	if (!ppdev)
-		return -ENOMEM;
+	if (!ppdev) {
+		ret = -ENOMEM;
+		goto put_err;
+	}
 	ppdev->dev.coherent_dma_mask = DMA_BIT_MASK(32);
 	ppdev->dev.of_node = pnp;
 

@@ -2793,6 +2801,8 @@ static int mv643xx_eth_shared_of_add_port(struct platform_device *pdev,
 
 port_err:
 	platform_device_put(ppdev);
+put_err:
+	of_node_put(ppd.phy_node);
 	return ret;
 }
 

index 0bcca08ff2bd..44a2081c5249 100644
@@ -97,14 +97,21 @@ void t7xx_fsm_broadcast_state(struct t7xx_fsm_ctl *ctl, enum md_state state)
 	fsm_state_notify(ctl->md, state);
 }
 
+static void fsm_release_command(struct kref *ref)
+{
+	struct t7xx_fsm_command *cmd = container_of(ref, typeof(*cmd), refcnt);
+
+	kfree(cmd);
+}
+
 static void fsm_finish_command(struct t7xx_fsm_ctl *ctl, struct t7xx_fsm_command *cmd, int result)
 {
 	if (cmd->flag & FSM_CMD_FLAG_WAIT_FOR_COMPLETION) {
-		*cmd->ret = result;
-		complete_all(cmd->done);
+		cmd->result = result;
+		complete_all(&cmd->done);
 	}
 
-	kfree(cmd);
+	kref_put(&cmd->refcnt, fsm_release_command);
 }
 
 static void fsm_del_kf_event(struct t7xx_fsm_event *event)

@@ -387,7 +394,6 @@ static int fsm_main_thread(void *data)
 
 int t7xx_fsm_append_cmd(struct t7xx_fsm_ctl *ctl, enum t7xx_fsm_cmd_state cmd_id, unsigned int flag)
 {
-	DECLARE_COMPLETION_ONSTACK(done);
 	struct t7xx_fsm_command *cmd;
 	unsigned long flags;
 	int ret;

@@ -399,11 +405,13 @@ int t7xx_fsm_append_cmd(struct t7xx_fsm_ctl *ctl, enum t7xx_fsm_cmd_state cmd_id
 	INIT_LIST_HEAD(&cmd->entry);
 	cmd->cmd_id = cmd_id;
 	cmd->flag = flag;
+	kref_init(&cmd->refcnt);
 	if (flag & FSM_CMD_FLAG_WAIT_FOR_COMPLETION) {
-		cmd->done = &done;
-		cmd->ret = &ret;
+		init_completion(&cmd->done);
+		kref_get(&cmd->refcnt);
 	}
 
+	kref_get(&cmd->refcnt);
 	spin_lock_irqsave(&ctl->command_lock, flags);
 	list_add_tail(&cmd->entry, &ctl->command_queue);
 	spin_unlock_irqrestore(&ctl->command_lock, flags);

@@ -413,11 +421,11 @@ int t7xx_fsm_append_cmd(struct t7xx_fsm_ctl *ctl, enum t7xx_fsm_cmd_state cmd_id
 	if (flag & FSM_CMD_FLAG_WAIT_FOR_COMPLETION) {
 		unsigned long wait_ret;
 
-		wait_ret = wait_for_completion_timeout(&done,
+		wait_ret = wait_for_completion_timeout(&cmd->done,
 						       msecs_to_jiffies(FSM_CMD_TIMEOUT_MS));
-		if (!wait_ret)
-			return -ETIMEDOUT;
 
+		ret = wait_ret ? cmd->result : -ETIMEDOUT;
+		kref_put(&cmd->refcnt, fsm_release_command);
 		return ret;
 	}
 

index b1af0259d4c5..d9f2522e6b2c 100644
@@ -107,8 +107,9 @@ struct t7xx_fsm_command {
 	struct list_head	entry;
 	enum t7xx_fsm_cmd_state	cmd_id;
 	unsigned int		flag;
-	struct completion	*done;
-	int			*ret;
+	struct completion	done;
+	int			result;
+	struct kref		refcnt;
 };
 
 struct t7xx_fsm_notifier {