Merge tag 'v5.13-rc7' into usb-next

We need the USB fixes in here as well.

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

91 files changed, 867 insertions, 615 deletions

diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm
index a5c5f70acfc9..e65e0a43be64 100644
--- a/drivers/cpufreq/Kconfig.arm
+++ b/drivers/cpufreq/Kconfig.arm
@@ -19,16 +19,6 @@ config ACPI_CPPC_CPUFREQ
 
 	  If in doubt, say N.
 
-config ACPI_CPPC_CPUFREQ_FIE
-	bool "Frequency Invariance support for CPPC cpufreq driver"
-	depends on ACPI_CPPC_CPUFREQ && GENERIC_ARCH_TOPOLOGY
-	default y
-	help
-	  This extends frequency invariance support in the CPPC cpufreq driver,
-	  by using CPPC delivered and reference performance counters.
-
-	  If in doubt, say N.
-
 config ARM_ALLWINNER_SUN50I_CPUFREQ_NVMEM
 	tristate "Allwinner nvmem based SUN50I CPUFreq driver"
 	depends on ARCH_SUNXI
diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c
index 3848b4c222e1..2f769b1630c5 100644
--- a/drivers/cpufreq/cppc_cpufreq.c
+++ b/drivers/cpufreq/cppc_cpufreq.c
@@ -10,18 +10,14 @@
 
 #define pr_fmt(fmt)	"CPPC Cpufreq:"	fmt
 
-#include <linux/arch_topology.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/delay.h>
 #include <linux/cpu.h>
 #include <linux/cpufreq.h>
 #include <linux/dmi.h>
-#include <linux/irq_work.h>
-#include <linux/kthread.h>
 #include <linux/time.h>
 #include <linux/vmalloc.h>
-#include <uapi/linux/sched/types.h>
 
 #include <asm/unaligned.h>
 
@@ -61,204 +57,6 @@ static struct cppc_workaround_oem_info wa_info[] = {
 	}
 };
 
-#ifdef CONFIG_ACPI_CPPC_CPUFREQ_FIE
-
-/* Frequency invariance support */
-struct cppc_freq_invariance {
-	int cpu;
-	struct irq_work irq_work;
-	struct kthread_work work;
-	struct cppc_perf_fb_ctrs prev_perf_fb_ctrs;
-	struct cppc_cpudata *cpu_data;
-};
-
-static DEFINE_PER_CPU(struct cppc_freq_invariance, cppc_freq_inv);
-static struct kthread_worker *kworker_fie;
-static bool fie_disabled;
-
-static struct cpufreq_driver cppc_cpufreq_driver;
-static unsigned int hisi_cppc_cpufreq_get_rate(unsigned int cpu);
-static int cppc_perf_from_fbctrs(struct cppc_cpudata *cpu_data,
-				 struct cppc_perf_fb_ctrs fb_ctrs_t0,
-				 struct cppc_perf_fb_ctrs fb_ctrs_t1);
-
-/**
- * cppc_scale_freq_workfn - CPPC arch_freq_scale updater for frequency invariance
- * @work: The work item.
- *
- * The CPPC driver register itself with the topology core to provide its own
- * implementation (cppc_scale_freq_tick()) of topology_scale_freq_tick() which
- * gets called by the scheduler on every tick.
- *
- * Note that the arch specific counters have higher priority than CPPC counters,
- * if available, though the CPPC driver doesn't need to have any special
- * handling for that.
- *
- * On an invocation of cppc_scale_freq_tick(), we schedule an irq work (since we
- * reach here from hard-irq context), which then schedules a normal work item
- * and cppc_scale_freq_workfn() updates the per_cpu arch_freq_scale variable
- * based on the counter updates since the last tick.
- */
-static void cppc_scale_freq_workfn(struct kthread_work *work)
-{
-	struct cppc_freq_invariance *cppc_fi;
-	struct cppc_perf_fb_ctrs fb_ctrs = {0};
-	struct cppc_cpudata *cpu_data;
-	unsigned long local_freq_scale;
-	u64 perf;
-
-	cppc_fi = container_of(work, struct cppc_freq_invariance, work);
-	cpu_data = cppc_fi->cpu_data;
-
-	if (cppc_get_perf_ctrs(cppc_fi->cpu, &fb_ctrs)) {
-		pr_warn("%s: failed to read perf counters\n", __func__);
-		return;
-	}
-
-	cppc_fi->prev_perf_fb_ctrs = fb_ctrs;
-	perf = cppc_perf_from_fbctrs(cpu_data, cppc_fi->prev_perf_fb_ctrs,
-				     fb_ctrs);
-
-	perf <<= SCHED_CAPACITY_SHIFT;
-	local_freq_scale = div64_u64(perf, cpu_data->perf_caps.highest_perf);
-	if (WARN_ON(local_freq_scale > 1024))
-		local_freq_scale = 1024;
-
-	per_cpu(arch_freq_scale, cppc_fi->cpu) = local_freq_scale;
-}
-
-static void cppc_irq_work(struct irq_work *irq_work)
-{
-	struct cppc_freq_invariance *cppc_fi;
-
-	cppc_fi = container_of(irq_work, struct cppc_freq_invariance, irq_work);
-	kthread_queue_work(kworker_fie, &cppc_fi->work);
-}
-
-static void cppc_scale_freq_tick(void)
-{
-	struct cppc_freq_invariance *cppc_fi = &per_cpu(cppc_freq_inv, smp_processor_id());
-
-	/*
-	 * cppc_get_perf_ctrs() can potentially sleep, call that from the right
-	 * context.
-	 */
-	irq_work_queue(&cppc_fi->irq_work);
-}
-
-static struct scale_freq_data cppc_sftd = {
-	.source = SCALE_FREQ_SOURCE_CPPC,
-	.set_freq_scale = cppc_scale_freq_tick,
-};
-
-static void cppc_freq_invariance_policy_init(struct cpufreq_policy *policy,
-					     struct cppc_cpudata *cpu_data)
-{
-	struct cppc_perf_fb_ctrs fb_ctrs = {0};
-	struct cppc_freq_invariance *cppc_fi;
-	int i, ret;
-
-	if (cppc_cpufreq_driver.get == hisi_cppc_cpufreq_get_rate)
-		return;
-
-	if (fie_disabled)
-		return;
-
-	for_each_cpu(i, policy->cpus) {
-		cppc_fi = &per_cpu(cppc_freq_inv, i);
-		cppc_fi->cpu = i;
-		cppc_fi->cpu_data = cpu_data;
-		kthread_init_work(&cppc_fi->work, cppc_scale_freq_workfn);
-		init_irq_work(&cppc_fi->irq_work, cppc_irq_work);
-
-		ret = cppc_get_perf_ctrs(i, &fb_ctrs);
-		if (ret) {
-			pr_warn("%s: failed to read perf counters: %d\n",
-				__func__, ret);
-			fie_disabled = true;
-		} else {
-			cppc_fi->prev_perf_fb_ctrs = fb_ctrs;
-		}
-	}
-}
-
-static void __init cppc_freq_invariance_init(void)
-{
-	struct sched_attr attr = {
-		.size		= sizeof(struct sched_attr),
-		.sched_policy	= SCHED_DEADLINE,
-		.sched_nice	= 0,
-		.sched_priority	= 0,
-		/*
-		 * Fake (unused) bandwidth; workaround to "fix"
-		 * priority inheritance.
-		 */
-		.sched_runtime	= 1000000,
-		.sched_deadline = 10000000,
-		.sched_period	= 10000000,
-	};
-	int ret;
-
-	if (cppc_cpufreq_driver.get == hisi_cppc_cpufreq_get_rate)
-		return;
-
-	if (fie_disabled)
-		return;
-
-	kworker_fie = kthread_create_worker(0, "cppc_fie");
-	if (IS_ERR(kworker_fie))
-		return;
-
-	ret = sched_setattr_nocheck(kworker_fie->task, &attr);
-	if (ret) {
-		pr_warn("%s: failed to set SCHED_DEADLINE: %d\n", __func__,
-			ret);
-		kthread_destroy_worker(kworker_fie);
-		return;
-	}
-
-	/* Register for freq-invariance */
-	topology_set_scale_freq_source(&cppc_sftd, cpu_present_mask);
-}
-
-static void cppc_freq_invariance_exit(void)
-{
-	struct cppc_freq_invariance *cppc_fi;
-	int i;
-
-	if (cppc_cpufreq_driver.get == hisi_cppc_cpufreq_get_rate)
-		return;
-
-	if (fie_disabled)
-		return;
-
-	topology_clear_scale_freq_source(SCALE_FREQ_SOURCE_CPPC, cpu_present_mask);
-
-	for_each_possible_cpu(i) {
-		cppc_fi = &per_cpu(cppc_freq_inv, i);
-		irq_work_sync(&cppc_fi->irq_work);
-	}
-
-	kthread_destroy_worker(kworker_fie);
-	kworker_fie = NULL;
-}
-
-#else
-static inline void
-cppc_freq_invariance_policy_init(struct cpufreq_policy *policy,
-				 struct cppc_cpudata *cpu_data)
-{
-}
-
-static inline void cppc_freq_invariance_init(void)
-{
-}
-
-static inline void cppc_freq_invariance_exit(void)
-{
-}
-#endif /* CONFIG_ACPI_CPPC_CPUFREQ_FIE */
-
 /* Callback function used to retrieve the max frequency from DMI */
 static void cppc_find_dmi_mhz(const struct dmi_header *dm, void *private)
 {
@@ -547,12 +345,9 @@ static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	cpu_data->perf_ctrls.desired_perf =  caps->highest_perf;
 
 	ret = cppc_set_perf(cpu, &cpu_data->perf_ctrls);
-	if (ret) {
+	if (ret)
 		pr_debug("Err setting perf value:%d on CPU:%d. ret:%d\n",
 			 caps->highest_perf, cpu, ret);
-	} else {
-		cppc_freq_invariance_policy_init(policy, cpu_data);
-	}
 
 	return ret;
 }
@@ -565,12 +360,12 @@ static inline u64 get_delta(u64 t1, u64 t0)
 	return (u32)t1 - (u32)t0;
 }
 
-static int cppc_perf_from_fbctrs(struct cppc_cpudata *cpu_data,
-				 struct cppc_perf_fb_ctrs fb_ctrs_t0,
-				 struct cppc_perf_fb_ctrs fb_ctrs_t1)
+static int cppc_get_rate_from_fbctrs(struct cppc_cpudata *cpu_data,
+				     struct cppc_perf_fb_ctrs fb_ctrs_t0,
+				     struct cppc_perf_fb_ctrs fb_ctrs_t1)
 {
 	u64 delta_reference, delta_delivered;
-	u64 reference_perf;
+	u64 reference_perf, delivered_perf;
 
 	reference_perf = fb_ctrs_t0.reference_perf;
 
@@ -579,21 +374,12 @@ static int cppc_perf_from_fbctrs(struct cppc_cpudata *cpu_data,
 	delta_delivered = get_delta(fb_ctrs_t1.delivered,
 				    fb_ctrs_t0.delivered);
 
-	/* Check to avoid divide-by zero and invalid delivered_perf */
-	if (!delta_reference || !delta_delivered)
-		return cpu_data->perf_ctrls.desired_perf;
-
-	return (reference_perf * delta_delivered) / delta_reference;
-}
-
-static int cppc_get_rate_from_fbctrs(struct cppc_cpudata *cpu_data,
-				     struct cppc_perf_fb_ctrs fb_ctrs_t0,
-				     struct cppc_perf_fb_ctrs fb_ctrs_t1)
-{
-	u64 delivered_perf;
-
-	delivered_perf = cppc_perf_from_fbctrs(cpu_data, fb_ctrs_t0,
-					       fb_ctrs_t1);
+	/* Check to avoid divide-by zero */
+	if (delta_reference || delta_delivered)
+		delivered_perf = (reference_perf * delta_delivered) /
+					delta_reference;
+	else
+		delivered_perf = cpu_data->perf_ctrls.desired_perf;
 
 	return cppc_cpufreq_perf_to_khz(cpu_data, delivered_perf);
 }
@@ -718,8 +504,6 @@ static void cppc_check_hisi_workaround(void)
 
 static int __init cppc_cpufreq_init(void)
 {
-	int ret;
-
 	if ((acpi_disabled) || !acpi_cpc_valid())
 		return -ENODEV;
 
@@ -727,11 +511,7 @@ static int __init cppc_cpufreq_init(void)
 
 	cppc_check_hisi_workaround();
 
-	ret = cpufreq_register_driver(&cppc_cpufreq_driver);
-	if (!ret)
-		cppc_freq_invariance_init();
-
-	return ret;
+	return cpufreq_register_driver(&cppc_cpufreq_driver);
 }
 
 static inline void free_cpu_data(void)
@@ -748,7 +528,6 @@ static inline void free_cpu_data(void)
 
 static void __exit cppc_cpufreq_exit(void)
 {
-	cppc_freq_invariance_exit();
 	cpufreq_unregister_driver(&cppc_cpufreq_driver);
 
 	free_cpu_data();
diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index 6ab9d9a488a6..39b5b46e880f 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -59,6 +59,7 @@ config DMA_OF
 #devices
 config ALTERA_MSGDMA
 	tristate "Altera / Intel mSGDMA Engine"
+	depends on HAS_IOMEM
 	select DMA_ENGINE
 	help
 	  Enable support for Altera / Intel mSGDMA controller.
@@ -701,6 +702,7 @@ config XILINX_ZYNQMP_DMA
 
 config XILINX_ZYNQMP_DPDMA
 	tristate "Xilinx DPDMA Engine"
+	depends on HAS_IOMEM && OF
 	select DMA_ENGINE
 	select DMA_VIRTUAL_CHANNELS
 	help
diff --git a/drivers/dma/fsl-dpaa2-qdma/dpaa2-qdma.c b/drivers/dma/fsl-dpaa2-qdma/dpaa2-qdma.c
index 4ec909e0b810..4ae057922ef1 100644
--- a/drivers/dma/fsl-dpaa2-qdma/dpaa2-qdma.c
+++ b/drivers/dma/fsl-dpaa2-qdma/dpaa2-qdma.c
@@ -332,6 +332,7 @@ static int __cold dpaa2_qdma_setup(struct fsl_mc_device *ls_dev)
 	}
 
 	if (priv->dpdmai_attr.version.major > DPDMAI_VER_MAJOR) {
+		err = -EINVAL;
 		dev_err(dev, "DPDMAI major version mismatch\n"
 			     "Found %u.%u, supported version is %u.%u\n",
 				priv->dpdmai_attr.version.major,
@@ -341,6 +342,7 @@ static int __cold dpaa2_qdma_setup(struct fsl_mc_device *ls_dev)
 	}
 
 	if (priv->dpdmai_attr.version.minor > DPDMAI_VER_MINOR) {
+		err = -EINVAL;
 		dev_err(dev, "DPDMAI minor version mismatch\n"
 			     "Found %u.%u, supported version is %u.%u\n",
 				priv->dpdmai_attr.version.major,
@@ -475,6 +477,7 @@ static int __cold dpaa2_qdma_dpio_setup(struct dpaa2_qdma_priv *priv)
 		ppriv->store =
 			dpaa2_io_store_create(DPAA2_QDMA_STORE_SIZE, dev);
 		if (!ppriv->store) {
+			err = -ENOMEM;
 			dev_err(dev, "dpaa2_io_store_create() failed\n");
 			goto err_store;
 		}
diff --git a/drivers/dma/idxd/cdev.c b/drivers/dma/idxd/cdev.c
index 302cba5ff779..d4419bf1fede 100644
--- a/drivers/dma/idxd/cdev.c
+++ b/drivers/dma/idxd/cdev.c
@@ -110,6 +110,7 @@ static int idxd_cdev_open(struct inode *inode, struct file *filp)
 		pasid = iommu_sva_get_pasid(sva);
 		if (pasid == IOMMU_PASID_INVALID) {
 			iommu_sva_unbind_device(sva);
+			rc = -EINVAL;
 			goto failed;
 		}
 
diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c
index 776fd44aff5f..442d55c11a5f 100644
--- a/drivers/dma/idxd/init.c
+++ b/drivers/dma/idxd/init.c
@@ -168,6 +168,32 @@ static int idxd_setup_interrupts(struct idxd_device *idxd)
 	return rc;
 }
 
+static void idxd_cleanup_interrupts(struct idxd_device *idxd)
+{
+	struct pci_dev *pdev = idxd->pdev;
+	struct idxd_irq_entry *irq_entry;
+	int i, msixcnt;
+
+	msixcnt = pci_msix_vec_count(pdev);
+	if (msixcnt <= 0)
+		return;
+
+	irq_entry = &idxd->irq_entries[0];
+	free_irq(irq_entry->vector, irq_entry);
+
+	for (i = 1; i < msixcnt; i++) {
+
+		irq_entry = &idxd->irq_entries[i];
+		if (idxd->hw.cmd_cap & BIT(IDXD_CMD_RELEASE_INT_HANDLE))
+			idxd_device_release_int_handle(idxd, idxd->int_handles[i],
+						       IDXD_IRQ_MSIX);
+		free_irq(irq_entry->vector, irq_entry);
+	}
+
+	idxd_mask_error_interrupts(idxd);
+	pci_free_irq_vectors(pdev);
+}
+
 static int idxd_setup_wqs(struct idxd_device *idxd)
 {
 	struct device *dev = &idxd->pdev->dev;
@@ -242,6 +268,7 @@ static int idxd_setup_engines(struct idxd_device *idxd)
 		engine->idxd = idxd;
 		device_initialize(&engine->conf_dev);
 		engine->conf_dev.parent = &idxd->conf_dev;
+		engine->conf_dev.bus = &dsa_bus_type;
 		engine->conf_dev.type = &idxd_engine_device_type;
 		rc = dev_set_name(&engine->conf_dev, "engine%d.%d", idxd->id, engine->id);
 		if (rc < 0) {
@@ -303,6 +330,19 @@ static int idxd_setup_groups(struct idxd_device *idxd)
 	return rc;
 }
 
+static void idxd_cleanup_internals(struct idxd_device *idxd)
+{
+	int i;
+
+	for (i = 0; i < idxd->max_groups; i++)
+		put_device(&idxd->groups[i]->conf_dev);
+	for (i = 0; i < idxd->max_engines; i++)
+		put_device(&idxd->engines[i]->conf_dev);
+	for (i = 0; i < idxd->max_wqs; i++)
+		put_device(&idxd->wqs[i]->conf_dev);
+	destroy_workqueue(idxd->wq);
+}
+
 static int idxd_setup_internals(struct idxd_device *idxd)
 {
 	struct device *dev = &idxd->pdev->dev;
@@ -531,12 +571,12 @@ static int idxd_probe(struct idxd_device *idxd)
 		dev_dbg(dev, "Loading RO device config\n");
 		rc = idxd_device_load_config(idxd);
 		if (rc < 0)
-			goto err;
+			goto err_config;
 	}
 
 	rc = idxd_setup_interrupts(idxd);
 	if (rc)
-		goto err;
+		goto err_config;
 
 	dev_dbg(dev, "IDXD interrupt setup complete.\n");
 
@@ -549,6 +589,8 @@ static int idxd_probe(struct idxd_device *idxd)
 	dev_dbg(dev, "IDXD device %d probed successfully\n", idxd->id);
 	return 0;
 
+ err_config:
+	idxd_cleanup_internals(idxd);
  err:
 	if (device_pasid_enabled(idxd))
 		idxd_disable_system_pasid(idxd);
@@ -556,6 +598,18 @@ static int idxd_probe(struct idxd_device *idxd)
 	return rc;
 }
 
+static void idxd_cleanup(struct idxd_device *idxd)
+{
+	struct device *dev = &idxd->pdev->dev;
+
+	perfmon_pmu_remove(idxd);
+	idxd_cleanup_interrupts(idxd);
+	idxd_cleanup_internals(idxd);
+	if (device_pasid_enabled(idxd))
+		idxd_disable_system_pasid(idxd);
+	iommu_dev_disable_feature(dev, IOMMU_DEV_FEAT_SVA);
+}
+
 static int idxd_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
 	struct device *dev = &pdev->dev;
@@ -608,7 +662,7 @@ static int idxd_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	rc = idxd_register_devices(idxd);
 	if (rc) {
 		dev_err(dev, "IDXD sysfs setup failed\n");
-		goto err;
+		goto err_dev_register;
 	}
 
 	idxd->state = IDXD_DEV_CONF_READY;
@@ -618,6 +672,8 @@ static int idxd_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	return 0;
 
+ err_dev_register:
+	idxd_cleanup(idxd);
  err:
 	pci_iounmap(pdev, idxd->reg_base);
  err_iomap:
@@ -787,6 +843,7 @@ module_init(idxd_init_module);
 
 static void __exit idxd_exit_module(void)
 {
+	idxd_unregister_driver();
 	pci_unregister_driver(&idxd_pci_driver);
 	idxd_cdev_remove();
 	idxd_unregister_bus_type();
diff --git a/drivers/dma/ipu/ipu_irq.c b/drivers/dma/ipu/ipu_irq.c
index 0d5c42f7bfa4..97d9a6f04f2a 100644
--- a/drivers/dma/ipu/ipu_irq.c
+++ b/drivers/dma/ipu/ipu_irq.c
@@ -230,7 +230,7 @@ out:
 }
 
 /**
- * ipu_irq_map() - map an IPU interrupt source to an IRQ number
+ * ipu_irq_unmap() - unmap an IPU interrupt source
  * @source:	interrupt source bit position (see ipu_irq_map())
  * @return:	0 or negative error code
  */
diff --git a/drivers/dma/mediatek/mtk-uart-apdma.c b/drivers/dma/mediatek/mtk-uart-apdma.c
index 27c07350971d..375e7e647df6 100644
--- a/drivers/dma/mediatek/mtk-uart-apdma.c
+++ b/drivers/dma/mediatek/mtk-uart-apdma.c
@@ -131,10 +131,7 @@ static unsigned int mtk_uart_apdma_read(struct mtk_chan *c, unsigned int reg)
 
 static void mtk_uart_apdma_desc_free(struct virt_dma_desc *vd)
 {
-	struct dma_chan *chan = vd->tx.chan;
-	struct mtk_chan *c = to_mtk_uart_apdma_chan(chan);
-
-	kfree(c->desc);
+	kfree(container_of(vd, struct mtk_uart_apdma_desc, vd));
 }
 
 static void mtk_uart_apdma_start_tx(struct mtk_chan *c)
@@ -207,14 +204,9 @@ static void mtk_uart_apdma_start_rx(struct mtk_chan *c)
 
 static void mtk_uart_apdma_tx_handler(struct mtk_chan *c)
 {
-	struct mtk_uart_apdma_desc *d = c->desc;
-
 	mtk_uart_apdma_write(c, VFF_INT_FLAG, VFF_TX_INT_CLR_B);
 	mtk_uart_apdma_write(c, VFF_INT_EN, VFF_INT_EN_CLR_B);
 	mtk_uart_apdma_write(c, VFF_EN, VFF_EN_CLR_B);
-
-	list_del(&d->vd.node);
-	vchan_cookie_complete(&d->vd);
 }
 
 static void mtk_uart_apdma_rx_handler(struct mtk_chan *c)
@@ -245,9 +237,17 @@ static void mtk_uart_apdma_rx_handler(struct mtk_chan *c)
 
 	c->rx_status = d->avail_len - cnt;
 	mtk_uart_apdma_write(c, VFF_RPT, wg);
+}
 
-	list_del(&d->vd.node);
-	vchan_cookie_complete(&d->vd);
+static void mtk_uart_apdma_chan_complete_handler(struct mtk_chan *c)
+{
+	struct mtk_uart_apdma_desc *d = c->desc;
+
+	if (d) {
+		list_del(&d->vd.node);
+		vchan_cookie_complete(&d->vd);
+		c->desc = NULL;
+	}
 }
 
 static irqreturn_t mtk_uart_apdma_irq_handler(int irq, void *dev_id)
@@ -261,6 +261,7 @@ static irqreturn_t mtk_uart_apdma_irq_handler(int irq, void *dev_id)
 		mtk_uart_apdma_rx_handler(c);
 	else if (c->dir == DMA_MEM_TO_DEV)
 		mtk_uart_apdma_tx_handler(c);
+	mtk_uart_apdma_chan_complete_handler(c);
 	spin_unlock_irqrestore(&c->vc.lock, flags);
 
 	return IRQ_HANDLED;
@@ -348,7 +349,7 @@ static struct dma_async_tx_descriptor *mtk_uart_apdma_prep_slave_sg
 		return NULL;
 
 	/* Now allocate and setup the descriptor */
-	d = kzalloc(sizeof(*d), GFP_ATOMIC);
+	d = kzalloc(sizeof(*d), GFP_NOWAIT);
 	if (!d)
 		return NULL;
 
@@ -366,7 +367,7 @@ static void mtk_uart_apdma_issue_pending(struct dma_chan *chan)
 	unsigned long flags;
 
 	spin_lock_irqsave(&c->vc.lock, flags);
-	if (vchan_issue_pending(&c->vc)) {
+	if (vchan_issue_pending(&c->vc) && !c->desc) {
 		vd = vchan_next_desc(&c->vc);
 		c->desc = to_mtk_uart_apdma_desc(&vd->tx);
 
diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c
index fd8d2bc3be9f..110de8a60058 100644
--- a/drivers/dma/pl330.c
+++ b/drivers/dma/pl330.c
@@ -2694,13 +2694,15 @@ static struct dma_async_tx_descriptor *pl330_prep_dma_cyclic(
 	for (i = 0; i < len / period_len; i++) {
 		desc = pl330_get_desc(pch);
 		if (!desc) {
+			unsigned long iflags;
+
 			dev_err(pch->dmac->ddma.dev, "%s:%d Unable to fetch desc\n",
 				__func__, __LINE__);
 
 			if (!first)
 				return NULL;
 
-			spin_lock_irqsave(&pl330->pool_lock, flags);
+			spin_lock_irqsave(&pl330->pool_lock, iflags);
 
 			while (!list_empty(&first->node)) {
 				desc = list_entry(first->node.next,
@@ -2710,7 +2712,7 @@ static struct dma_async_tx_descriptor *pl330_prep_dma_cyclic(
 
 			list_move_tail(&first->node, &pl330->desc_pool);
 
-			spin_unlock_irqrestore(&pl330->pool_lock, flags);
+			spin_unlock_irqrestore(&pl330->pool_lock, iflags);
 
 			return NULL;
 		}
diff --git a/drivers/dma/qcom/Kconfig b/drivers/dma/qcom/Kconfig
index 365f94eb3b08..3f926a653bd8 100644
--- a/drivers/dma/qcom/Kconfig
+++ b/drivers/dma/qcom/Kconfig
@@ -33,6 +33,7 @@ config QCOM_GPI_DMA
 
 config QCOM_HIDMA_MGMT
 	tristate "Qualcomm Technologies HIDMA Management support"
+	depends on HAS_IOMEM
 	select DMA_ENGINE
 	help
 	  Enable support for the Qualcomm Technologies HIDMA Management.
diff --git a/drivers/dma/sf-pdma/Kconfig b/drivers/dma/sf-pdma/Kconfig
index f8ffa02e279f..ba46a0a15a93 100644
--- a/drivers/dma/sf-pdma/Kconfig
+++ b/drivers/dma/sf-pdma/Kconfig
@@ -1,5 +1,6 @@
 config SF_PDMA
 	tristate "Sifive PDMA controller driver"
+	depends on HAS_IOMEM
 	select DMA_ENGINE
 	select DMA_VIRTUAL_CHANNELS
 	help
diff --git a/drivers/dma/sh/rcar-dmac.c b/drivers/dma/sh/rcar-dmac.c
index d530c1bf11d9..6885b3dcd7a9 100644
--- a/drivers/dma/sh/rcar-dmac.c
+++ b/drivers/dma/sh/rcar-dmac.c
@@ -1913,7 +1913,7 @@ static int rcar_dmac_probe(struct platform_device *pdev)
 
 	/* Enable runtime PM and initialize the device. */
 	pm_runtime_enable(&pdev->dev);
-	ret = pm_runtime_get_sync(&pdev->dev);
+	ret = pm_runtime_resume_and_get(&pdev->dev);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "runtime PM get sync failed (%d)\n", ret);
 		return ret;
diff --git a/drivers/dma/ste_dma40.c b/drivers/dma/ste_dma40.c
index 265d7c07b348..e1827393143f 100644
--- a/drivers/dma/ste_dma40.c
+++ b/drivers/dma/ste_dma40.c
@@ -3675,6 +3675,9 @@ static int __init d40_probe(struct platform_device *pdev)
 
 	kfree(base->lcla_pool.base_unaligned);
 
+	if (base->lcpa_base)
+		iounmap(base->lcpa_base);
+
 	if (base->phy_lcpa)
 		release_mem_region(base->phy_lcpa,
 				   base->lcpa_size);
diff --git a/drivers/dma/stm32-mdma.c b/drivers/dma/stm32-mdma.c
index 36ba8b43e78d..18cbd1e43c2e 100644
--- a/drivers/dma/stm32-mdma.c
+++ b/drivers/dma/stm32-mdma.c
@@ -1452,7 +1452,7 @@ static int stm32_mdma_alloc_chan_resources(struct dma_chan *c)
 		return -ENOMEM;
 	}
 
-	ret = pm_runtime_get_sync(dmadev->ddev.dev);
+	ret = pm_runtime_resume_and_get(dmadev->ddev.dev);
 	if (ret < 0)
 		return ret;
 
@@ -1718,7 +1718,7 @@ static int stm32_mdma_pm_suspend(struct device *dev)
 	u32 ccr, id;
 	int ret;
 
-	ret = pm_runtime_get_sync(dev);
+	ret = pm_runtime_resume_and_get(dev);
 	if (ret < 0)
 		return ret;
 
diff --git a/drivers/dma/xilinx/xilinx_dpdma.c b/drivers/dma/xilinx/xilinx_dpdma.c
index 70b29bd079c9..6c709803203a 100644
--- a/drivers/dma/xilinx/xilinx_dpdma.c
+++ b/drivers/dma/xilinx/xilinx_dpdma.c
@@ -113,6 +113,7 @@
 #define XILINX_DPDMA_CH_VDO				0x020
 #define XILINX_DPDMA_CH_PYLD_SZ				0x024
 #define XILINX_DPDMA_CH_DESC_ID				0x028
+#define XILINX_DPDMA_CH_DESC_ID_MASK			GENMASK(15, 0)
 
 /* DPDMA descriptor fields */
 #define XILINX_DPDMA_DESC_CONTROL_PREEMBLE		0xa5
@@ -866,7 +867,8 @@ static void xilinx_dpdma_chan_queue_transfer(struct xilinx_dpdma_chan *chan)
 	 * will be used, but it should be enough.
 	 */
 	list_for_each_entry(sw_desc, &desc->descriptors, node)
-		sw_desc->hw.desc_id = desc->vdesc.tx.cookie;
+		sw_desc->hw.desc_id = desc->vdesc.tx.cookie
+				    & XILINX_DPDMA_CH_DESC_ID_MASK;
 
 	sw_desc = list_first_entry(&desc->descriptors,
 				   struct xilinx_dpdma_sw_desc, node);
@@ -1086,7 +1088,8 @@ static void xilinx_dpdma_chan_vsync_irq(struct  xilinx_dpdma_chan *chan)
 	if (!chan->running || !pending)
 		goto out;
 
-	desc_id = dpdma_read(chan->reg, XILINX_DPDMA_CH_DESC_ID);
+	desc_id = dpdma_read(chan->reg, XILINX_DPDMA_CH_DESC_ID)
+		& XILINX_DPDMA_CH_DESC_ID_MASK;
 
 	/* If the retrigger raced with vsync, retry at the next frame. */
 	sw_desc = list_first_entry(&pending->descriptors,
@@ -1459,7 +1462,7 @@ static void xilinx_dpdma_enable_irq(struct xilinx_dpdma_device *xdev)
  */
 static void xilinx_dpdma_disable_irq(struct xilinx_dpdma_device *xdev)
 {
-	dpdma_write(xdev->reg, XILINX_DPDMA_IDS, XILINX_DPDMA_INTR_ERR_ALL);
+	dpdma_write(xdev->reg, XILINX_DPDMA_IDS, XILINX_DPDMA_INTR_ALL);
 	dpdma_write(xdev->reg, XILINX_DPDMA_EIDS, XILINX_DPDMA_EINTR_ALL);
 }
 
@@ -1596,6 +1599,26 @@ static struct dma_chan *of_dma_xilinx_xlate(struct of_phandle_args *dma_spec,
 	return dma_get_slave_channel(&xdev->chan[chan_id]->vchan.chan);
 }
 
+static void dpdma_hw_init(struct xilinx_dpdma_device *xdev)
+{
+	unsigned int i;
+	void __iomem *reg;
+
+	/* Disable all interrupts */
+	xilinx_dpdma_disable_irq(xdev);
+
+	/* Stop all channels */
+	for (i = 0; i < ARRAY_SIZE(xdev->chan); i++) {
+		reg = xdev->reg + XILINX_DPDMA_CH_BASE
+				+ XILINX_DPDMA_CH_OFFSET * i;
+		dpdma_clr(reg, XILINX_DPDMA_CH_CNTL, XILINX_DPDMA_CH_CNTL_ENABLE);
+	}
+
+	/* Clear the interrupt status registers */
+	dpdma_write(xdev->reg, XILINX_DPDMA_ISR, XILINX_DPDMA_INTR_ALL);
+	dpdma_write(xdev->reg, XILINX_DPDMA_EISR, XILINX_DPDMA_EINTR_ALL);
+}
+
 static int xilinx_dpdma_probe(struct platform_device *pdev)
 {
 	struct xilinx_dpdma_device *xdev;
@@ -1622,6 +1645,8 @@ static int xilinx_dpdma_probe(struct platform_device *pdev)
 	if (IS_ERR(xdev->reg))
 		return PTR_ERR(xdev->reg);
 
+	dpdma_hw_init(xdev);
+
 	xdev->irq = platform_get_irq(pdev, 0);
 	if (xdev->irq < 0) {
 		dev_err(xdev->dev, "failed to get platform irq\n");
diff --git a/drivers/dma/xilinx/zynqmp_dma.c b/drivers/dma/xilinx/zynqmp_dma.c
index d8419565b92c..5fecf5aa6e85 100644
--- a/drivers/dma/xilinx/zynqmp_dma.c
+++ b/drivers/dma/xilinx/zynqmp_dma.c
@@ -468,7 +468,7 @@ static int zynqmp_dma_alloc_chan_resources(struct dma_chan *dchan)
 	struct zynqmp_dma_desc_sw *desc;
 	int i, ret;
 
-	ret = pm_runtime_get_sync(chan->dev);
+	ret = pm_runtime_resume_and_get(chan->dev);
 	if (ret < 0)
 		return ret;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index 0597aeb5f0e8..327b1f8213a8 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -6871,8 +6871,12 @@ static int gfx_v10_0_kiq_init_register(struct amdgpu_ring *ring)
 	if (ring->use_doorbell) {
 		WREG32_SOC15(GC, 0, mmCP_MEC_DOORBELL_RANGE_LOWER,
 			(adev->doorbell_index.kiq * 2) << 2);
+		/* If GC has entered CGPG, ringing doorbell > first page doesn't
+		 * wakeup GC. Enlarge CP_MEC_DOORBELL_RANGE_UPPER to workaround
+		 * this issue.
+		 */
 		WREG32_SOC15(GC, 0, mmCP_MEC_DOORBELL_RANGE_UPPER,
-			(adev->doorbell_index.userqueue_end * 2) << 2);
+			(adev->doorbell.size - 4));
 	}
 
 	WREG32_SOC15(GC, 0, mmCP_HQD_PQ_DOORBELL_CONTROL,
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index 516467e962b7..c09225d065c2 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -3673,8 +3673,12 @@ static int gfx_v9_0_kiq_init_register(struct amdgpu_ring *ring)
 	if (ring->use_doorbell) {
 		WREG32_SOC15(GC, 0, mmCP_MEC_DOORBELL_RANGE_LOWER,
 					(adev->doorbell_index.kiq * 2) << 2);
+		/* If GC has entered CGPG, ringing doorbell > first page doesn't
+		 * wakeup GC. Enlarge CP_MEC_DOORBELL_RANGE_UPPER to workaround
+		 * this issue.
+		 */
 		WREG32_SOC15(GC, 0, mmCP_MEC_DOORBELL_RANGE_UPPER,
-					(adev->doorbell_index.userqueue_end * 2) << 2);
+					(adev->doorbell.size - 4));
 	}
 
 	WREG32_SOC15_RLC(GC, 0, mmCP_HQD_PQ_DOORBELL_CONTROL,
diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c
index 37a23aa6de37..66d623f91678 100644
--- a/drivers/irqchip/irq-gic-v3.c
+++ b/drivers/irqchip/irq-gic-v3.c
@@ -642,11 +642,45 @@ static inline void gic_handle_nmi(u32 irqnr, struct pt_regs *regs)
 		nmi_exit();
 }
 
+static u32 do_read_iar(struct pt_regs *regs)
+{
+	u32 iar;
+
+	if (gic_supports_nmi() && unlikely(!interrupts_enabled(regs))) {
+		u64 pmr;
+
+		/*
+		 * We were in a context with IRQs disabled. However, the
+		 * entry code has set PMR to a value that allows any
+		 * interrupt to be acknowledged, and not just NMIs. This can
+		 * lead to surprising effects if the NMI has been retired in
+		 * the meantime, and that there is an IRQ pending. The IRQ
+		 * would then be taken in NMI context, something that nobody
+		 * wants to debug twice.
+		 *
+		 * Until we sort this, drop PMR again to a level that will
+		 * actually only allow NMIs before reading IAR, and then
+		 * restore it to what it was.
+		 */
+		pmr = gic_read_pmr();
+		gic_pmr_mask_irqs();
+		isb();
+
+		iar = gic_read_iar();
+
+		gic_write_pmr(pmr);
+	} else {
+		iar = gic_read_iar();
+	}
+
+	return iar;
+}
+
 static asmlinkage void __exception_irq_entry gic_handle_irq(struct pt_regs *regs)
 {
 	u32 irqnr;
 
-	irqnr = gic_read_iar();
+	irqnr = do_read_iar(regs);
 
 	/* Check for special IDs first */
 	if ((irqnr >= 1020 && irqnr <= 1023))
diff --git a/drivers/net/caif/caif_serial.c b/drivers/net/caif/caif_serial.c
index d17482395a4d..4ffbfd534f18 100644
--- a/drivers/net/caif/caif_serial.c
+++ b/drivers/net/caif/caif_serial.c
@@ -350,6 +350,7 @@ static int ldisc_open(struct tty_struct *tty)
 	rtnl_lock();
 	result = register_netdevice(dev);
 	if (result) {
+		tty_kref_put(tty);
 		rtnl_unlock();
 		free_netdev(dev);
 		return -ENODEV;
diff --git a/drivers/net/can/usb/mcba_usb.c b/drivers/net/can/usb/mcba_usb.c
index 029e77dfa773..a45865bd7254 100644
--- a/drivers/net/can/usb/mcba_usb.c
+++ b/drivers/net/can/usb/mcba_usb.c
@@ -82,6 +82,8 @@ struct mcba_priv {
 	bool can_ka_first_pass;
 	bool can_speed_check;
 	atomic_t free_ctx_cnt;
+	void *rxbuf[MCBA_MAX_RX_URBS];
+	dma_addr_t rxbuf_dma[MCBA_MAX_RX_URBS];
 };
 
 /* CAN frame */
@@ -633,6 +635,7 @@ static int mcba_usb_start(struct mcba_priv *priv)
 	for (i = 0; i < MCBA_MAX_RX_URBS; i++) {
 		struct urb *urb = NULL;
 		u8 *buf;
+		dma_addr_t buf_dma;
 
 		/* create a URB, and a buffer for it */
 		urb = usb_alloc_urb(0, GFP_KERNEL);
@@ -642,7 +645,7 @@ static int mcba_usb_start(struct mcba_priv *priv)
 		}
 
 		buf = usb_alloc_coherent(priv->udev, MCBA_USB_RX_BUFF_SIZE,
-					 GFP_KERNEL, &urb->transfer_dma);
+					 GFP_KERNEL, &buf_dma);
 		if (!buf) {
 			netdev_err(netdev, "No memory left for USB buffer\n");
 			usb_free_urb(urb);
@@ -661,11 +664,14 @@ static int mcba_usb_start(struct mcba_priv *priv)
 		if (err) {
 			usb_unanchor_urb(urb);
 			usb_free_coherent(priv->udev, MCBA_USB_RX_BUFF_SIZE,
-					  buf, urb->transfer_dma);
+					  buf, buf_dma);
 			usb_free_urb(urb);
 			break;
 		}
 
+		priv->rxbuf[i] = buf;
+		priv->rxbuf_dma[i] = buf_dma;
+
 		/* Drop reference, USB core will take care of freeing it */
 		usb_free_urb(urb);
 	}
@@ -708,7 +714,14 @@ static int mcba_usb_open(struct net_device *netdev)
 
 static void mcba_urb_unlink(struct mcba_priv *priv)
 {
+	int i;
+
 	usb_kill_anchored_urbs(&priv->rx_submitted);
+
+	for (i = 0; i < MCBA_MAX_RX_URBS; ++i)
+		usb_free_coherent(priv->udev, MCBA_USB_RX_BUFF_SIZE,
+				  priv->rxbuf[i], priv->rxbuf_dma[i]);
+
 	usb_kill_anchored_urbs(&priv->tx_submitted);
 }
 
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index 881f88754bf6..52571486705e 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -236,36 +236,48 @@ static int ena_xdp_io_poll(struct napi_struct *napi, int budget)
 static int ena_xdp_tx_map_frame(struct ena_ring *xdp_ring,
 				struct ena_tx_buffer *tx_info,
 				struct xdp_frame *xdpf,
-				void **push_hdr,
-				u32 *push_len)
+				struct ena_com_tx_ctx *ena_tx_ctx)
 {
 	struct ena_adapter *adapter = xdp_ring->adapter;
 	struct ena_com_buf *ena_buf;
-	dma_addr_t dma = 0;
+	int push_len = 0;
+	dma_addr_t dma;
+	void *data;
 	u32 size;
 
 	tx_info->xdpf = xdpf;
+	data = tx_info->xdpf->data;
 	size = tx_info->xdpf->len;
-	ena_buf = tx_info->bufs;
 
-	/* llq push buffer */
-	*push_len = min_t(u32, size, xdp_ring->tx_max_header_size);
-	*push_hdr = tx_info->xdpf->data;
+	if (xdp_ring->tx_mem_queue_type == ENA_ADMIN_PLACEMENT_POLICY_DEV) {
+		/* Designate part of the packet for LLQ */
+		push_len = min_t(u32, size, xdp_ring->tx_max_header_size);
+
+		ena_tx_ctx->push_header = data;
+
+		size -= push_len;
+		data += push_len;
+	}
+
+	ena_tx_ctx->header_len = push_len;
 
-	if (size - *push_len > 0) {
+	if (size > 0) {
 		dma = dma_map_single(xdp_ring->dev,
-				     *push_hdr + *push_len,
-				     size - *push_len,
+				     data,
+				     size,
 				     DMA_TO_DEVICE);
 		if (unlikely(dma_mapping_error(xdp_ring->dev, dma)))
 			goto error_report_dma_error;
 
-		tx_info->map_linear_data = 1;
-		tx_info->num_of_bufs = 1;
-	}
+		tx_info->map_linear_data = 0;
 
-	ena_buf->paddr = dma;
-	ena_buf->len = size;
+		ena_buf = tx_info->bufs;
+		ena_buf->paddr = dma;
+		ena_buf->len = size;
+
+		ena_tx_ctx->ena_bufs = ena_buf;
+		ena_tx_ctx->num_bufs = tx_info->num_of_bufs = 1;
+	}
 
 	return 0;
 
@@ -274,10 +286,6 @@ error_report_dma_error:
 			  &xdp_ring->syncp);
 	netif_warn(adapter, tx_queued, adapter->netdev, "Failed to map xdp buff\n");
 
-	xdp_return_frame_rx_napi(tx_info->xdpf);
-	tx_info->xdpf = NULL;
-	tx_info->num_of_bufs = 0;
-
 	return -EINVAL;
 }
 
@@ -289,8 +297,6 @@ static int ena_xdp_xmit_frame(struct ena_ring *xdp_ring,
 	struct ena_com_tx_ctx ena_tx_ctx = {};
 	struct ena_tx_buffer *tx_info;
 	u16 next_to_use, req_id;
-	void *push_hdr;
-	u32 push_len;
 	int rc;
 
 	next_to_use = xdp_ring->next_to_use;
@@ -298,15 +304,11 @@ static int ena_xdp_xmit_frame(struct ena_ring *xdp_ring,
 	tx_info = &xdp_ring->tx_buffer_info[req_id];
 	tx_info->num_of_bufs = 0;
 
-	rc = ena_xdp_tx_map_frame(xdp_ring, tx_info, xdpf, &push_hdr, &push_len);
+	rc = ena_xdp_tx_map_frame(xdp_ring, tx_info, xdpf, &ena_tx_ctx);
 	if (unlikely(rc))
 		return rc;
 
-	ena_tx_ctx.ena_bufs = tx_info->bufs;
-	ena_tx_ctx.push_header = push_hdr;
-	ena_tx_ctx.num_bufs = tx_info->num_of_bufs;
 	ena_tx_ctx.req_id = req_id;
-	ena_tx_ctx.header_len = push_len;
 
 	rc = ena_xmit_common(dev,
 			     xdp_ring,
diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c
index b3d74332ed33..7748b276e5fd 100644
--- a/drivers/net/ethernet/atheros/alx/main.c
+++ b/drivers/net/ethernet/atheros/alx/main.c
@@ -1849,6 +1849,7 @@ out_free_netdev:
 	free_netdev(netdev);
 out_pci_release:
 	pci_release_mem_regions(pdev);
+	pci_disable_pcie_error_reporting(pdev);
 out_pci_disable:
 	pci_disable_device(pdev);
 	return err;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index fcc729d52b17..aef3fccc27a9 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -7308,7 +7308,7 @@ skip_rdma:
 	entries_sp = ctx->vnic_max_vnic_entries + ctx->qp_max_l2_entries +
 		     2 * (extra_qps + ctx->qp_min_qp1_entries) + min;
 	entries_sp = roundup(entries_sp, ctx->tqm_entries_multiple);
-	entries = ctx->qp_max_l2_entries + extra_qps + ctx->qp_min_qp1_entries;
+	entries = ctx->qp_max_l2_entries + 2 * (extra_qps + ctx->qp_min_qp1_entries);
 	entries = roundup(entries, ctx->tqm_entries_multiple);
 	entries = clamp_t(u32, entries, min, ctx->tqm_max_entries_per_ring);
 	for (i = 0; i < ctx->tqm_fp_rings_count + 1; i++) {
@@ -11750,6 +11750,8 @@ static void bnxt_fw_init_one_p3(struct bnxt *bp)
 	bnxt_hwrm_coal_params_qcaps(bp);
 }
 
+static int bnxt_probe_phy(struct bnxt *bp, bool fw_dflt);
+
 static int bnxt_fw_init_one(struct bnxt *bp)
 {
 	int rc;
@@ -11764,6 +11766,9 @@ static int bnxt_fw_init_one(struct bnxt *bp)
 		netdev_err(bp->dev, "Firmware init phase 2 failed\n");
 		return rc;
 	}
+	rc = bnxt_probe_phy(bp, false);
+	if (rc)
+		return rc;
 	rc = bnxt_approve_mac(bp, bp->dev->dev_addr, false);
 	if (rc)
 		return rc;
@@ -13155,6 +13160,7 @@ init_err_pci_clean:
 	bnxt_hwrm_func_drv_unrgtr(bp);
 	bnxt_free_hwrm_short_cmd_req(bp);
 	bnxt_free_hwrm_resources(bp);
+	bnxt_ethtool_free(bp);
 	kfree(bp->fw_health);
 	bp->fw_health = NULL;
 	bnxt_cleanup_pci(bp);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c
index 61ea3ec5c3fc..83ed10ac8660 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c
@@ -1337,13 +1337,27 @@ static int cxgb4_ethtool_flash_phy(struct net_device *netdev,
 		return ret;
 	}
 
-	spin_lock_bh(&adap->win0_lock);
+	/* We have to RESET the chip/firmware because we need the
+	 * chip in uninitialized state for loading new PHY image.
+	 * Otherwise, the running firmware will only store the PHY
+	 * image in local RAM which will be lost after next reset.
+	 */
+	ret = t4_fw_reset(adap, adap->mbox, PIORSTMODE_F | PIORST_F);
+	if (ret < 0) {
+		dev_err(adap->pdev_dev,
+			"Set FW to RESET for flashing PHY FW failed. ret: %d\n",
+			ret);
+		return ret;
+	}
+
 	ret = t4_load_phy_fw(adap, MEMWIN_NIC, NULL, data, size);
-	spin_unlock_bh(&adap->win0_lock);
-	if (ret)
-		dev_err(adap->pdev_dev, "Failed to load PHY FW\n");
+	if (ret < 0) {
+		dev_err(adap->pdev_dev, "Failed to load PHY FW. ret: %d\n",
+			ret);
+		return ret;
+	}
 
-	return ret;
+	return 0;
 }
 
 static int cxgb4_ethtool_flash_fw(struct net_device *netdev,
@@ -1610,16 +1624,14 @@ static struct filter_entry *cxgb4_get_filter_entry(struct adapter *adap,
 						   u32 ftid)
 {
 	struct tid_info *t = &adap->tids;
-	struct filter_entry *f;
 
-	if (ftid < t->nhpftids)
-		f = &adap->tids.hpftid_tab[ftid];
-	else if (ftid < t->nftids)
-		f = &adap->tids.ftid_tab[ftid - t->nhpftids];
-	else
-		f = lookup_tid(&adap->tids, ftid);
+	if (ftid >= t->hpftid_base && ftid < t->hpftid_base + t->nhpftids)
+		return &t->hpftid_tab[ftid - t->hpftid_base];
 
-	return f;
+	if (ftid >= t->ftid_base && ftid < t->ftid_base + t->nftids)
+		return &t->ftid_tab[ftid - t->ftid_base];
+
+	return lookup_tid(t, ftid);
 }
 
 static void cxgb4_fill_filter_rule(struct ethtool_rx_flow_spec *fs,
@@ -1826,6 +1838,11 @@ static int cxgb4_ntuple_del_filter(struct net_device *dev,
 	filter_id = filter_info->loc_array[cmd->fs.location];
 	f = cxgb4_get_filter_entry(adapter, filter_id);
 
+	if (f->fs.prio)
+		filter_id -= adapter->tids.hpftid_base;
+	else if (!f->fs.hash)
+		filter_id -= (adapter->tids.ftid_base - adapter->tids.nhpftids);
+
 	ret = cxgb4_flow_rule_destroy(dev, f->fs.tc_prio, &f->fs, filter_id);
 	if (ret)
 		goto err;
@@ -1885,6 +1902,11 @@ static int cxgb4_ntuple_set_filter(struct net_device *netdev,
 
 	filter_info = &adapter->ethtool_filters->port[pi->port_id];
 
+	if (fs.prio)
+		tid += adapter->tids.hpftid_base;
+	else if (!fs.hash)
+		tid += (adapter->tids.ftid_base - adapter->tids.nhpftids);
+
 	filter_info->loc_array[cmd->fs.location] = tid;
 	set_bit(cmd->fs.location, filter_info->bmap);
 	filter_info->in_use++;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c
index 22c9ac922eba..6260b3bebd2b 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c
@@ -198,7 +198,7 @@ static void set_nat_params(struct adapter *adap, struct filter_entry *f,
 				      WORD_MASK, f->fs.nat_lip[3] |
 				      f->fs.nat_lip[2] << 8 |
 				      f->fs.nat_lip[1] << 16 |
-				      (u64)f->fs.nat_lip[0] << 25, 1);
+				      (u64)f->fs.nat_lip[0] << 24, 1);
 		}
 	}
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index 1f601de02e70..762113a04dde 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -4424,10 +4424,8 @@ static int adap_init0_phy(struct adapter *adap)
 
 	/* Load PHY Firmware onto adapter.
 	 */
-	spin_lock_bh(&adap->win0_lock);
 	ret = t4_load_phy_fw(adap, MEMWIN_NIC, phy_info->phy_fw_version,
 			     (u8 *)phyf->data, phyf->size);
-	spin_unlock_bh(&adap->win0_lock);
 	if (ret < 0)
 		dev_err(adap->pdev_dev, "PHY Firmware transfer error %d\n",
 			-ret);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
index 9428ef1f04a8..a0555f4d76fc 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
@@ -3060,16 +3060,19 @@ int t4_read_flash(struct adapter *adapter, unsigned int addr,
  *	@addr: the start address to write
  *	@n: length of data to write in bytes
  *	@data: the data to write
+ *	@byte_oriented: whether to store data as bytes or as words
  *
  *	Writes up to a page of data (256 bytes) to the serial flash starting
  *	at the given address.  All the data must be written to the same page.
+ *	If @byte_oriented is set the write data is stored as byte stream
+ *	(i.e. matches what on disk), otherwise in big-endian.
  */
 static int t4_write_flash(struct adapter *adapter, unsigned int addr,
-			  unsigned int n, const u8 *data)
+			  unsigned int n, const u8 *data, bool byte_oriented)
 {
-	int ret;
-	u32 buf[64];
 	unsigned int i, c, left, val, offset = addr & 0xff;
+	u32 buf[64];
+	int ret;
 
 	if (addr >= adapter->params.sf_size || offset + n > SF_PAGE_SIZE)
 		return -EINVAL;
@@ -3080,10 +3083,14 @@ static int t4_write_flash(struct adapter *adapter, unsigned int addr,
 	    (ret = sf1_write(adapter, 4, 1, 1, val)) != 0)
 		goto unlock;
 
-	for (left = n; left; left -= c) {
+	for (left = n; left; left -= c, data += c) {
 		c = min(left, 4U);
-		for (val = 0, i = 0; i < c; ++i)
-			val = (val << 8) + *data++;
+		for (val = 0, i = 0; i < c; ++i) {
+			if (byte_oriented)
+				val = (val << 8) + data[i];
+			else
+				val = (val << 8) + data[c - i - 1];
+		}
 
 		ret = sf1_write(adapter, c, c != left, 1, val);
 		if (ret)
@@ -3096,7 +3103,8 @@ static int t4_write_flash(struct adapter *adapter, unsigned int addr,
 	t4_write_reg(adapter, SF_OP_A, 0);    /* unlock SF */
 
 	/* Read the page to verify the write succeeded */
-	ret = t4_read_flash(adapter, addr & ~0xff, ARRAY_SIZE(buf), buf, 1);
+	ret = t4_read_flash(adapter, addr & ~0xff, ARRAY_SIZE(buf), buf,
+			    byte_oriented);
 	if (ret)
 		return ret;
 
@@ -3692,7 +3700,7 @@ int t4_load_fw(struct adapter *adap, const u8 *fw_data, unsigned int size)
 	 */
 	memcpy(first_page, fw_data, SF_PAGE_SIZE);
 	((struct fw_hdr *)first_page)->fw_ver = cpu_to_be32(0xffffffff);
-	ret = t4_write_flash(adap, fw_start, SF_PAGE_SIZE, first_page);
+	ret = t4_write_flash(adap, fw_start, SF_PAGE_SIZE, first_page, true);
 	if (ret)
 		goto out;
 
@@ -3700,14 +3708,14 @@ int t4_load_fw(struct adapter *adap, const u8 *fw_data, unsigned int size)
 	for (size -= SF_PAGE_SIZE; size; size -= SF_PAGE_SIZE) {
 		addr += SF_PAGE_SIZE;
 		fw_data += SF_PAGE_SIZE;
-		ret = t4_write_flash(adap, addr, SF_PAGE_SIZE, fw_data);
+		ret = t4_write_flash(adap, addr, SF_PAGE_SIZE, fw_data, true);
 		if (ret)
 			goto out;
 	}
 
-	ret = t4_write_flash(adap,
-			     fw_start + offsetof(struct fw_hdr, fw_ver),
-			     sizeof(hdr->fw_ver), (const u8 *)&hdr->fw_ver);
+	ret = t4_write_flash(adap, fw_start + offsetof(struct fw_hdr, fw_ver),
+			     sizeof(hdr->fw_ver), (const u8 *)&hdr->fw_ver,
+			     true);
 out:
 	if (ret)
 		dev_err(adap->pdev_dev, "firmware download failed, error %d\n",
@@ -3812,9 +3820,11 @@ int t4_load_phy_fw(struct adapter *adap, int win,
 	/* Copy the supplied PHY Firmware image to the adapter memory location
 	 * allocated by the adapter firmware.
 	 */
+	spin_lock_bh(&adap->win0_lock);
 	ret = t4_memory_rw(adap, win, mtype, maddr,
 			   phy_fw_size, (__be32 *)phy_fw_data,
 			   T4_MEMORY_WRITE);
+	spin_unlock_bh(&adap->win0_lock);
 	if (ret)
 		return ret;
 
@@ -10208,7 +10218,7 @@ int t4_load_cfg(struct adapter *adap, const u8 *cfg_data, unsigned int size)
 			n = size - i;
 		else
 			n = SF_PAGE_SIZE;
-		ret = t4_write_flash(adap, addr, n, cfg_data);
+		ret = t4_write_flash(adap, addr, n, cfg_data, true);
 		if (ret)
 			goto out;
 
@@ -10677,13 +10687,14 @@ int t4_load_boot(struct adapter *adap, u8 *boot_data,
 	for (size -= SF_PAGE_SIZE; size; size -= SF_PAGE_SIZE) {
 		addr += SF_PAGE_SIZE;
 		boot_data += SF_PAGE_SIZE;
-		ret = t4_write_flash(adap, addr, SF_PAGE_SIZE, boot_data);
+		ret = t4_write_flash(adap, addr, SF_PAGE_SIZE, boot_data,
+				     false);
 		if (ret)
 			goto out;
 	}
 
 	ret = t4_write_flash(adap, boot_sector, SF_PAGE_SIZE,
-			     (const u8 *)header);
+			     (const u8 *)header, false);
 
 out:
 	if (ret)
@@ -10758,7 +10769,7 @@ int t4_load_bootcfg(struct adapter *adap, const u8 *cfg_data, unsigned int size)
 	for (i = 0; i < size; i += SF_PAGE_SIZE) {
 		n = min_t(u32, size - i, SF_PAGE_SIZE);
 
-		ret = t4_write_flash(adap, addr, n, cfg_data);
+		ret = t4_write_flash(adap, addr, n, cfg_data, false);
 		if (ret)
 			goto out;
 
@@ -10770,7 +10781,8 @@ int t4_load_bootcfg(struct adapter *adap, const u8 *cfg_data, unsigned int size)
 	for (i = 0; i < npad; i++) {
 		u8 data = 0;
 
-		ret = t4_write_flash(adap, cfg_addr + size + i, 1, &data);
+		ret = t4_write_flash(adap, cfg_addr + size + i, 1, &data,
+				     false);
 		if (ret)
 			goto out;
 	}
diff --git a/drivers/net/ethernet/ec_bhf.c b/drivers/net/ethernet/ec_bhf.c
index 46b0dbab8aad..7c992172933b 100644
--- a/drivers/net/ethernet/ec_bhf.c
+++ b/drivers/net/ethernet/ec_bhf.c
@@ -576,10 +576,12 @@ static void ec_bhf_remove(struct pci_dev *dev)
 	struct ec_bhf_priv *priv = netdev_priv(net_dev);
 
 	unregister_netdev(net_dev);
-	free_netdev(net_dev);
 
 	pci_iounmap(dev, priv->dma_io);
 	pci_iounmap(dev, priv->io);
+
+	free_netdev(net_dev);
+
 	pci_release_regions(dev);
 	pci_clear_master(dev);
 	pci_disable_device(dev);
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index b6eba29d8e99..7968568bbe21 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -5897,6 +5897,7 @@ drv_cleanup:
 unmap_bars:
 	be_unmap_pci_bars(adapter);
 free_netdev:
+	pci_disable_pcie_error_reporting(pdev);
 	free_netdev(netdev);
 rel_reg:
 	pci_release_regions(pdev);
diff --git a/drivers/net/ethernet/freescale/fec_ptp.c b/drivers/net/ethernet/freescale/fec_ptp.c
index 1753807cbf97..d71eac7e1924 100644
--- a/drivers/net/ethernet/freescale/fec_ptp.c
+++ b/drivers/net/ethernet/freescale/fec_ptp.c
@@ -215,15 +215,13 @@ static u64 fec_ptp_read(const struct cyclecounter *cc)
 {
 	struct fec_enet_private *fep =
 		container_of(cc, struct fec_enet_private, cc);
-	const struct platform_device_id *id_entry =
-		platform_get_device_id(fep->pdev);
 	u32 tempval;
 
 	tempval = readl(fep->hwp + FEC_ATIME_CTRL);
 	tempval |= FEC_T_CTRL_CAPTURE;
 	writel(tempval, fep->hwp + FEC_ATIME_CTRL);
 
-	if (id_entry->driver_data & FEC_QUIRK_BUG_CAPTURE)
+	if (fep->quirks & FEC_QUIRK_BUG_CAPTURE)
 		udelay(1);
 
 	return readl(fep->hwp + FEC_ATIME);
@@ -604,6 +602,10 @@ void fec_ptp_init(struct platform_device *pdev, int irq_idx)
 	fep->ptp_caps.enable = fec_ptp_enable;
 
 	fep->cycle_speed = clk_get_rate(fep->clk_ptp);
+	if (!fep->cycle_speed) {
+		fep->cycle_speed = NSEC_PER_SEC;
+		dev_err(&fep->pdev->dev, "clk_ptp clock rate is zero\n");
+	}
 	fep->ptp_inc = NSEC_PER_SEC / fep->cycle_speed;
 
 	spin_lock_init(&fep->tmreg_lock);
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index d70ee573fde5..27f9dac8719c 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -1717,12 +1717,13 @@ setup_rings:
  * ice_vsi_cfg_txqs - Configure the VSI for Tx
  * @vsi: the VSI being configured
  * @rings: Tx ring array to be configured
+ * @count: number of Tx ring array elements
  *
  * Return 0 on success and a negative value on error
  * Configure the Tx VSI for operation.
  */
 static int
-ice_vsi_cfg_txqs(struct ice_vsi *vsi, struct ice_ring **rings)
+ice_vsi_cfg_txqs(struct ice_vsi *vsi, struct ice_ring **rings, u16 count)
 {
 	struct ice_aqc_add_tx_qgrp *qg_buf;
 	u16 q_idx = 0;
@@ -1734,7 +1735,7 @@ ice_vsi_cfg_txqs(struct ice_vsi *vsi, struct ice_ring **rings)
 
 	qg_buf->num_txqs = 1;
 
-	for (q_idx = 0; q_idx < vsi->num_txq; q_idx++) {
+	for (q_idx = 0; q_idx < count; q_idx++) {
 		err = ice_vsi_cfg_txq(vsi, rings[q_idx], qg_buf);
 		if (err)
 			goto err_cfg_txqs;
@@ -1754,7 +1755,7 @@ err_cfg_txqs:
  */
 int ice_vsi_cfg_lan_txqs(struct ice_vsi *vsi)
 {
-	return ice_vsi_cfg_txqs(vsi, vsi->tx_rings);
+	return ice_vsi_cfg_txqs(vsi, vsi->tx_rings, vsi->num_txq);
 }
 
 /**
@@ -1769,7 +1770,7 @@ int ice_vsi_cfg_xdp_txqs(struct ice_vsi *vsi)
 	int ret;
 	int i;
 
-	ret = ice_vsi_cfg_txqs(vsi, vsi->xdp_rings);
+	ret = ice_vsi_cfg_txqs(vsi, vsi->xdp_rings, vsi->num_xdp_txq);
 	if (ret)
 		return ret;
 
@@ -2009,17 +2010,18 @@ int ice_vsi_stop_all_rx_rings(struct ice_vsi *vsi)
  * @rst_src: reset source
  * @rel_vmvf_num: Relative ID of VF/VM
  * @rings: Tx ring array to be stopped
+ * @count: number of Tx ring array elements
  */
 static int
 ice_vsi_stop_tx_rings(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src,
-		      u16 rel_vmvf_num, struct ice_ring **rings)
+		      u16 rel_vmvf_num, struct ice_ring **rings, u16 count)
 {
 	u16 q_idx;
 
 	if (vsi->num_txq > ICE_LAN_TXQ_MAX_QDIS)
 		return -EINVAL;
 
-	for (q_idx = 0; q_idx < vsi->num_txq; q_idx++) {
+	for (q_idx = 0; q_idx < count; q_idx++) {
 		struct ice_txq_meta txq_meta = { };
 		int status;
 
@@ -2047,7 +2049,7 @@ int
 ice_vsi_stop_lan_tx_rings(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src,
 			  u16 rel_vmvf_num)
 {
-	return ice_vsi_stop_tx_rings(vsi, rst_src, rel_vmvf_num, vsi->tx_rings);
+	return ice_vsi_stop_tx_rings(vsi, rst_src, rel_vmvf_num, vsi->tx_rings, vsi->num_txq);
 }
 
 /**
@@ -2056,7 +2058,7 @@ ice_vsi_stop_lan_tx_rings(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src,
  */
 int ice_vsi_stop_xdp_tx_rings(struct ice_vsi *vsi)
 {
-	return ice_vsi_stop_tx_rings(vsi, ICE_NO_RESET, 0, vsi->xdp_rings);
+	return ice_vsi_stop_tx_rings(vsi, ICE_NO_RESET, 0, vsi->xdp_rings, vsi->num_xdp_txq);
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 4ee85a217c6f..0eb2307325d3 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -2556,6 +2556,20 @@ ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog,
 }
 
 /**
+ * ice_xdp_safe_mode - XDP handler for safe mode
+ * @dev: netdevice
+ * @xdp: XDP command
+ */
+static int ice_xdp_safe_mode(struct net_device __always_unused *dev,
+			     struct netdev_bpf *xdp)
+{
+	NL_SET_ERR_MSG_MOD(xdp->extack,
+			   "Please provide working DDP firmware package in order to use XDP\n"
+			   "Refer to Documentation/networking/device_drivers/ethernet/intel/ice.rst");
+	return -EOPNOTSUPP;
+}
+
+/**
  * ice_xdp - implements XDP handler
  * @dev: netdevice
  * @xdp: XDP command
@@ -6937,6 +6951,7 @@ static const struct net_device_ops ice_netdev_safe_mode_ops = {
 	.ndo_change_mtu = ice_change_mtu,
 	.ndo_get_stats64 = ice_get_stats64,
 	.ndo_tx_timeout = ice_tx_timeout,
+	.ndo_bpf = ice_xdp_safe_mode,
 };
 
 static const struct net_device_ops ice_netdev_ops = {
diff --git a/drivers/net/ethernet/lantiq_xrx200.c b/drivers/net/ethernet/lantiq_xrx200.c
index 36dc3e5f6218..21ef2f128070 100644
--- a/drivers/net/ethernet/lantiq_xrx200.c
+++ b/drivers/net/ethernet/lantiq_xrx200.c
@@ -154,6 +154,7 @@ static int xrx200_close(struct net_device *net_dev)
 
 static int xrx200_alloc_skb(struct xrx200_chan *ch)
 {
+	struct sk_buff *skb = ch->skb[ch->dma.desc];
 	dma_addr_t mapping;
 	int ret = 0;
 
@@ -168,6 +169,7 @@ static int xrx200_alloc_skb(struct xrx200_chan *ch)
 				 XRX200_DMA_DATA_LEN, DMA_FROM_DEVICE);
 	if (unlikely(dma_mapping_error(ch->priv->dev, mapping))) {
 		dev_kfree_skb_any(ch->skb[ch->dma.desc]);
+		ch->skb[ch->dma.desc] = skb;
 		ret = -ENOMEM;
 		goto skip;
 	}
@@ -198,7 +200,6 @@ static int xrx200_hw_receive(struct xrx200_chan *ch)
 	ch->dma.desc %= LTQ_DESC_NUM;
 
 	if (ret) {
-		ch->skb[ch->dma.desc] = skb;
 		net_dev->stats.rx_dropped++;
 		netdev_err(net_dev, "failed to allocate new rx buffer\n");
 		return ret;
@@ -352,8 +353,8 @@ static irqreturn_t xrx200_dma_irq(int irq, void *ptr)
 	struct xrx200_chan *ch = ptr;
 
 	if (napi_schedule_prep(&ch->napi)) {
-		__napi_schedule(&ch->napi);
 		ltq_dma_disable_irq(&ch->dma);
+		__napi_schedule(&ch->napi);
 	}
 
 	ltq_dma_ack_irq(&ch->dma);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/dev.c
index a9166cd85013..ceebfc20f65e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/dev.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/dev.c
@@ -303,6 +303,7 @@ int mlx5_attach_device(struct mlx5_core_dev *dev)
 	int ret = 0, i;
 
 	mutex_lock(&mlx5_intf_mutex);
+	priv->flags &= ~MLX5_PRIV_FLAGS_DETACH;
 	for (i = 0; i < ARRAY_SIZE(mlx5_adev_devices); i++) {
 		if (!priv->adev[i]) {
 			bool is_supported = false;
@@ -320,6 +321,16 @@ int mlx5_attach_device(struct mlx5_core_dev *dev)
 			}
 		} else {
 			adev = &priv->adev[i]->adev;
+
+			/* Pay attention that this is not PCI driver that
+			 * mlx5_core_dev is connected, but auxiliary driver.
+			 *
+			 * Here we can race of module unload with devlink
+			 * reload, but we don't need to take extra lock because
+			 * we are holding global mlx5_intf_mutex.
+			 */
+			if (!adev->dev.driver)
+				continue;
 			adrv = to_auxiliary_drv(adev->dev.driver);
 
 			if (adrv->resume)
@@ -350,6 +361,10 @@ void mlx5_detach_device(struct mlx5_core_dev *dev)
 			continue;
 
 		adev = &priv->adev[i]->adev;
+		/* Auxiliary driver was unbind manually through sysfs */
+		if (!adev->dev.driver)
+			goto skip_suspend;
+
 		adrv = to_auxiliary_drv(adev->dev.driver);
 
 		if (adrv->suspend) {
@@ -357,9 +372,11 @@ void mlx5_detach_device(struct mlx5_core_dev *dev)
 			continue;
 		}
 
+skip_suspend:
 		del_adev(&priv->adev[i]->adev);
 		priv->adev[i] = NULL;
 	}
+	priv->flags |= MLX5_PRIV_FLAGS_DETACH;
 	mutex_unlock(&mlx5_intf_mutex);
 }
 
@@ -448,6 +465,8 @@ int mlx5_rescan_drivers_locked(struct mlx5_core_dev *dev)
 	struct mlx5_priv *priv = &dev->priv;
 
 	lockdep_assert_held(&mlx5_intf_mutex);
+	if (priv->flags & MLX5_PRIV_FLAGS_DETACH)
+		return 0;
 
 	delete_drivers(dev);
 	if (priv->flags & MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c
index 0dd7615e5931..bc33eaada3b9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c
@@ -64,6 +64,8 @@ struct devlink_port *mlx5e_get_devlink_port(struct net_device *dev)
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	struct devlink_port *port;
 
+	if (!netif_device_present(dev))
+		return NULL;
 	port = mlx5e_devlink_get_dl_port(priv);
 	if (port->registered)
 		return port;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
index d907c1acd4d5..778e229310a9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
@@ -1,7 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
 // Copyright (c) 2020 Mellanox Technologies
 
-#include <linux/ptp_classify.h>
 #include "en/ptp.h"
 #include "en/txrx.h"
 #include "en/params.h"
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h
index ab935cce952b..c96668bd701c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h
@@ -6,6 +6,7 @@
 
 #include "en.h"
 #include "en_stats.h"
+#include <linux/ptp_classify.h>
 
 struct mlx5e_ptpsq {
 	struct mlx5e_txqsq       txqsq;
@@ -43,6 +44,27 @@ struct mlx5e_ptp {
 	DECLARE_BITMAP(state, MLX5E_PTP_STATE_NUM_STATES);
 };
 
+static inline bool mlx5e_use_ptpsq(struct sk_buff *skb)
+{
+	struct flow_keys fk;
+
+	if (!(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP))
+		return false;
+
+	if (!skb_flow_dissect_flow_keys(skb, &fk, 0))
+		return false;
+
+	if (fk.basic.n_proto == htons(ETH_P_1588))
+		return true;
+
+	if (fk.basic.n_proto != htons(ETH_P_IP) &&
+	    fk.basic.n_proto != htons(ETH_P_IPV6))
+		return false;
+
+	return (fk.basic.ip_proto == IPPROTO_UDP &&
+		fk.ports.dst == htons(PTP_EV_PORT));
+}
+
 int mlx5e_ptp_open(struct mlx5e_priv *priv, struct mlx5e_params *params,
 		   u8 lag_port, struct mlx5e_ptp **cp);
 void mlx5e_ptp_close(struct mlx5e_ptp *c);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/neigh.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/neigh.c
index be0ee03de721..2e9bee4e5209 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/neigh.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/neigh.c
@@ -129,10 +129,9 @@ static void mlx5e_rep_neigh_update(struct work_struct *work)
 							     work);
 	struct mlx5e_neigh_hash_entry *nhe = update_work->nhe;
 	struct neighbour *n = update_work->n;
+	struct mlx5e_encap_entry *e = NULL;
 	bool neigh_connected, same_dev;
-	struct mlx5e_encap_entry *e;
 	unsigned char ha[ETH_ALEN];
-	struct mlx5e_priv *priv;
 	u8 nud_state, dead;
 
 	rtnl_lock();
@@ -156,14 +155,12 @@ static void mlx5e_rep_neigh_update(struct work_struct *work)
 	if (!same_dev)
 		goto out;
 
-	list_for_each_entry(e, &nhe->encap_list, encap_list) {
-		if (!mlx5e_encap_take(e))
-			continue;
+	/* mlx5e_get_next_init_encap() releases previous encap before returning
+	 * the next one.
+	 */
+	while ((e = mlx5e_get_next_init_encap(nhe, e)) != NULL)
+		mlx5e_rep_update_flows(netdev_priv(e->out_dev), e, neigh_connected, ha);
 
-		priv = netdev_priv(e->out_dev);
-		mlx5e_rep_update_flows(priv, e, neigh_connected, ha);
-		mlx5e_encap_put(priv, e);
-	}
 out:
 	rtnl_unlock();
 	mlx5e_release_neigh_update_work(update_work);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c
index 311382261840..85eaadc989df 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c
@@ -94,13 +94,9 @@ void mlx5e_rep_update_flows(struct mlx5e_priv *priv,
 
 	ASSERT_RTNL();
 
-	/* wait for encap to be fully initialized */
-	wait_for_completion(&e->res_ready);
-
 	mutex_lock(&esw->offloads.encap_tbl_lock);
 	encap_connected = !!(e->flags & MLX5_ENCAP_ENTRY_VALID);
-	if (e->compl_result < 0 || (encap_connected == neigh_connected &&
-				    ether_addr_equal(e->h_dest, ha)))
+	if (encap_connected == neigh_connected && ether_addr_equal(e->h_dest, ha))
 		goto unlock;
 
 	mlx5e_take_all_encap_flows(e, &flow_list);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c
index f1fb11680d20..490131e06efb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c
@@ -251,9 +251,12 @@ static void mlx5e_take_all_route_decap_flows(struct mlx5e_route_entry *r,
 		mlx5e_take_tmp_flow(flow, flow_list, 0);
 }
 
+typedef bool (match_cb)(struct mlx5e_encap_entry *);
+
 static struct mlx5e_encap_entry *
-mlx5e_get_next_valid_encap(struct mlx5e_neigh_hash_entry *nhe,
-			   struct mlx5e_encap_entry *e)
+mlx5e_get_next_matching_encap(struct mlx5e_neigh_hash_entry *nhe,
+			      struct mlx5e_encap_entry *e,
+			      match_cb match)
 {
 	struct mlx5e_encap_entry *next = NULL;
 
@@ -288,7 +291,7 @@ retry:
 	/* wait for encap to be fully initialized */
 	wait_for_completion(&next->res_ready);
 	/* continue searching if encap entry is not in valid state after completion */
-	if (!(next->flags & MLX5_ENCAP_ENTRY_VALID)) {
+	if (!match(next)) {
 		e = next;
 		goto retry;
 	}
@@ -296,6 +299,30 @@ retry:
 	return next;
 }
 
+static bool mlx5e_encap_valid(struct mlx5e_encap_entry *e)
+{
+	return e->flags & MLX5_ENCAP_ENTRY_VALID;
+}
+
+static struct mlx5e_encap_entry *
+mlx5e_get_next_valid_encap(struct mlx5e_neigh_hash_entry *nhe,
+			   struct mlx5e_encap_entry *e)
+{
+	return mlx5e_get_next_matching_encap(nhe, e, mlx5e_encap_valid);
+}
+
+static bool mlx5e_encap_initialized(struct mlx5e_encap_entry *e)
+{
+	return e->compl_result >= 0;
+}
+
+struct mlx5e_encap_entry *
+mlx5e_get_next_init_encap(struct mlx5e_neigh_hash_entry *nhe,
+			  struct mlx5e_encap_entry *e)
+{
+	return mlx5e_get_next_matching_encap(nhe, e, mlx5e_encap_initialized);
+}
+
 void mlx5e_tc_update_neigh_used_value(struct mlx5e_neigh_hash_entry *nhe)
 {
 	struct mlx5e_neigh *m_neigh = &nhe->m_neigh;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
index 3d45341e2216..26f7fab109d9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
@@ -532,9 +532,6 @@ void mlx5e_ipsec_build_netdev(struct mlx5e_priv *priv)
 	struct mlx5_core_dev *mdev = priv->mdev;
 	struct net_device *netdev = priv->netdev;
 
-	if (!priv->ipsec)
-		return;
-
 	if (!(mlx5_accel_ipsec_device_caps(mdev) & MLX5_ACCEL_IPSEC_CAP_ESP) ||
 	    !MLX5_CAP_ETH(mdev, swp)) {
 		mlx5_core_dbg(mdev, "mlx5e: ESP and SWP offload not supported\n");
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
index 5cd466ec6492..25403af32859 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
@@ -356,7 +356,7 @@ err:
 
 int mlx5e_arfs_create_tables(struct mlx5e_priv *priv)
 {
-	int err = 0;
+	int err = -ENOMEM;
 	int i;
 
 	if (!(priv->netdev->hw_features & NETIF_F_NTUPLE))
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index ec6bafe7a2e5..d26b8ed51195 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -2705,8 +2705,6 @@ static int mlx5e_update_netdev_queues(struct mlx5e_priv *priv)
 	nch = priv->channels.params.num_channels;
 	ntc = priv->channels.params.num_tc;
 	num_rxqs = nch * priv->profile->rq_groups;
-	if (priv->channels.params.ptp_rx)
-		num_rxqs++;
 
 	mlx5e_netdev_set_tcs(netdev, nch, ntc);
 
@@ -4824,22 +4822,15 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
 	}
 
 	if (mlx5_vxlan_allowed(mdev->vxlan) || mlx5_geneve_tx_allowed(mdev)) {
-		netdev->hw_features     |= NETIF_F_GSO_UDP_TUNNEL |
-					   NETIF_F_GSO_UDP_TUNNEL_CSUM;
-		netdev->hw_enc_features |= NETIF_F_GSO_UDP_TUNNEL |
-					   NETIF_F_GSO_UDP_TUNNEL_CSUM;
-		netdev->gso_partial_features = NETIF_F_GSO_UDP_TUNNEL_CSUM;
-		netdev->vlan_features |= NETIF_F_GSO_UDP_TUNNEL |
-					 NETIF_F_GSO_UDP_TUNNEL_CSUM;
+		netdev->hw_features     |= NETIF_F_GSO_UDP_TUNNEL;
+		netdev->hw_enc_features |= NETIF_F_GSO_UDP_TUNNEL;
+		netdev->vlan_features |= NETIF_F_GSO_UDP_TUNNEL;
 	}
 
 	if (mlx5e_tunnel_proto_supported_tx(mdev, IPPROTO_GRE)) {
-		netdev->hw_features     |= NETIF_F_GSO_GRE |
-					   NETIF_F_GSO_GRE_CSUM;
-		netdev->hw_enc_features |= NETIF_F_GSO_GRE |
-					   NETIF_F_GSO_GRE_CSUM;
-		netdev->gso_partial_features |= NETIF_F_GSO_GRE |
-						NETIF_F_GSO_GRE_CSUM;
+		netdev->hw_features     |= NETIF_F_GSO_GRE;
+		netdev->hw_enc_features |= NETIF_F_GSO_GRE;
+		netdev->gso_partial_features |= NETIF_F_GSO_GRE;
 	}
 
 	if (mlx5e_tunnel_proto_supported_tx(mdev, IPPROTO_IPIP)) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index dd64878e5b38..d4b0f270b6bb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -4765,7 +4765,7 @@ static void mlx5e_tc_hairpin_update_dead_peer(struct mlx5e_priv *priv,
 	list_for_each_entry_safe(hpe, tmp, &init_wait_list, dead_peer_wait_list) {
 		wait_for_completion(&hpe->res_ready);
 		if (!IS_ERR_OR_NULL(hpe->hp) && hpe->peer_vhca_id == peer_vhca_id)
-			hpe->hp->pair->peer_gone = true;
+			mlx5_core_hairpin_clear_dead_peer(hpe->hp->pair);
 
 		mlx5e_hairpin_put(priv, hpe);
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
index 25c091795bcd..17027536efba 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
@@ -178,6 +178,9 @@ void mlx5e_take_all_encap_flows(struct mlx5e_encap_entry *e, struct list_head *f
 void mlx5e_put_flow_list(struct mlx5e_priv *priv, struct list_head *flow_list);
 
 struct mlx5e_neigh_hash_entry;
+struct mlx5e_encap_entry *
+mlx5e_get_next_init_encap(struct mlx5e_neigh_hash_entry *nhe,
+			  struct mlx5e_encap_entry *e);
 void mlx5e_tc_update_neigh_used_value(struct mlx5e_neigh_hash_entry *nhe);
 
 void mlx5e_tc_reoffload_flows_work(struct work_struct *work);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index 8ba62671f5f1..320fe0cda917 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -32,7 +32,6 @@
 
 #include <linux/tcp.h>
 #include <linux/if_vlan.h>
-#include <linux/ptp_classify.h>
 #include <net/geneve.h>
 #include <net/dsfield.h>
 #include "en.h"
@@ -67,24 +66,6 @@ static inline int mlx5e_get_dscp_up(struct mlx5e_priv *priv, struct sk_buff *skb
 }
 #endif
 
-static bool mlx5e_use_ptpsq(struct sk_buff *skb)
-{
-	struct flow_keys fk;
-
-	if (!skb_flow_dissect_flow_keys(skb, &fk, 0))
-		return false;
-
-	if (fk.basic.n_proto == htons(ETH_P_1588))
-		return true;
-
-	if (fk.basic.n_proto != htons(ETH_P_IP) &&
-	    fk.basic.n_proto != htons(ETH_P_IPV6))
-		return false;
-
-	return (fk.basic.ip_proto == IPPROTO_UDP &&
-		fk.ports.dst == htons(PTP_EV_PORT));
-}
-
 static u16 mlx5e_select_ptpsq(struct net_device *dev, struct sk_buff *skb)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
@@ -145,9 +126,9 @@ u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb,
 		}
 
 		ptp_channel = READ_ONCE(priv->channels.ptp);
-		if (unlikely(ptp_channel) &&
-		    test_bit(MLX5E_PTP_STATE_TX, ptp_channel->state) &&
-		    mlx5e_use_ptpsq(skb))
+		if (unlikely(ptp_channel &&
+			     test_bit(MLX5E_PTP_STATE_TX, ptp_channel->state) &&
+			     mlx5e_use_ptpsq(skb)))
 			return mlx5e_select_ptpsq(dev, skb);
 
 		txq_ix = netdev_pick_tx(dev, skb, NULL);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index 77c0ca655975..940333410267 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -136,7 +136,7 @@ static int mlx5_eq_comp_int(struct notifier_block *nb,
 
 	eqe = next_eqe_sw(eq);
 	if (!eqe)
-		return 0;
+		goto out;
 
 	do {
 		struct mlx5_core_cq *cq;
@@ -161,6 +161,8 @@ static int mlx5_eq_comp_int(struct notifier_block *nb,
 		++eq->cons_index;
 
 	} while ((++num_eqes < MLX5_EQ_POLLING_BUDGET) && (eqe = next_eqe_sw(eq)));
+
+out:
 	eq_update_ci(eq, 1);
 
 	if (cqn != -1)
@@ -248,9 +250,9 @@ static int mlx5_eq_async_int(struct notifier_block *nb,
 		++eq->cons_index;
 
 	} while ((++num_eqes < MLX5_EQ_POLLING_BUDGET) && (eqe = next_eqe_sw(eq)));
-	eq_update_ci(eq, 1);
 
 out:
+	eq_update_ci(eq, 1);
 	mlx5_eq_async_int_unlock(eq_async, recovery, &flags);
 
 	return unlikely(recovery) ? num_eqes : 0;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index b88705a3a1a8..97e6cb6f13c1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1054,6 +1054,12 @@ int mlx5_esw_vport_enable(struct mlx5_eswitch *esw, u16 vport_num,
 			goto err_vhca_mapping;
 	}
 
+	/* External controller host PF has factory programmed MAC.
+	 * Read it from the device.
+	 */
+	if (mlx5_core_is_ecpf(esw->dev) && vport_num == MLX5_VPORT_PF)
+		mlx5_query_nic_vport_mac_address(esw->dev, vport_num, true, vport->info.mac);
+
 	esw_vport_change_handle_locked(vport);
 
 	esw->enabled_vports++;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index a1d67bd7fb43..0d0f63a27aba 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1161,7 +1161,7 @@ static int mlx5_load(struct mlx5_core_dev *dev)
 	err = mlx5_core_set_hca_defaults(dev);
 	if (err) {
 		mlx5_core_err(dev, "Failed to set hca defaults\n");
-		goto err_sriov;
+		goto err_set_hca;
 	}
 
 	mlx5_vhca_event_start(dev);
@@ -1194,6 +1194,7 @@ err_ec:
 	mlx5_sf_hw_table_destroy(dev);
 err_vhca:
 	mlx5_vhca_event_stop(dev);
+err_set_hca:
 	mlx5_cleanup_fs(dev);
 err_fs:
 	mlx5_accel_tls_cleanup(dev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mr.c b/drivers/net/ethernet/mellanox/mlx5/core/mr.c
index 50af84e76fb6..174f71ed5280 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mr.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mr.c
@@ -54,7 +54,7 @@ int mlx5_core_create_mkey(struct mlx5_core_dev *dev,
 	mkey_index = MLX5_GET(create_mkey_out, lout, mkey_index);
 	mkey->iova = MLX5_GET64(mkc, mkc, start_addr);
 	mkey->size = MLX5_GET64(mkc, mkc, len);
-	mkey->key |= mlx5_idx_to_mkey(mkey_index);
+	mkey->key = (u32)mlx5_mkey_variant(mkey->key) | mlx5_idx_to_mkey(mkey_index);
 	mkey->pd = MLX5_GET(mkc, mkc, pd);
 	init_waitqueue_head(&mkey->wait);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/rdma.c b/drivers/net/ethernet/mellanox/mlx5/core/rdma.c
index 441b5453acae..540cf05f6373 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/rdma.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/rdma.c
@@ -156,6 +156,9 @@ void mlx5_rdma_enable_roce(struct mlx5_core_dev *dev)
 {
 	int err;
 
+	if (!MLX5_CAP_GEN(dev, roce))
+		return;
+
 	err = mlx5_nic_vport_enable_roce(dev);
 	if (err) {
 		mlx5_core_err(dev, "Failed to enable RoCE: %d\n", err);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c
index 6a0c6f965ad1..fa0288afc0dd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c
@@ -163,6 +163,7 @@ mlx5_sf_dev_state_change_handler(struct notifier_block *nb, unsigned long event_
 	sf_index = event->function_id - base_id;
 	sf_dev = xa_load(&table->devices, sf_index);
 	switch (event->new_vhca_state) {
+	case MLX5_VHCA_STATE_INVALID:
 	case MLX5_VHCA_STATE_ALLOCATED:
 		if (sf_dev)
 			mlx5_sf_dev_del(table->dev, sf_dev, sf_index);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c
index 054c2e2b6554..7466f016375c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c
@@ -694,7 +694,11 @@ static int dr_ste_v1_set_action_decap_l3_list(void *data,
 	if (hw_action_sz / DR_STE_ACTION_DOUBLE_SZ < DR_STE_DECAP_L3_ACTION_NUM)
 		return -EINVAL;
 
-	memcpy(padded_data, data, data_sz);
+	inline_data_sz =
+		MLX5_FLD_SZ_BYTES(ste_double_action_insert_with_inline_v1, inline_data);
+
+	/* Add an alignment padding  */
+	memcpy(padded_data + data_sz % inline_data_sz, data, data_sz);
 
 	/* Remove L2L3 outer headers */
 	MLX5_SET(ste_single_action_remove_header_v1, hw_action, action_id,
@@ -706,32 +710,34 @@ static int dr_ste_v1_set_action_decap_l3_list(void *data,
 	hw_action += DR_STE_ACTION_DOUBLE_SZ;
 	used_actions++; /* Remove and NOP are a single double action */
 
-	inline_data_sz =
-		MLX5_FLD_SZ_BYTES(ste_double_action_insert_with_inline_v1, inline_data);
+	/* Point to the last dword of the header */
+	data_ptr += (data_sz / inline_data_sz) * inline_data_sz;
 
-	/* Add the new header inline + 2 extra bytes */
+	/* Add the new header using inline action 4Byte at a time, the header
+	 * is added in reversed order to the beginning of the packet to avoid
+	 * incorrect parsing by the HW. Since header is 14B or 18B an extra
+	 * two bytes are padded and later removed.
+	 */
 	for (i = 0; i < data_sz / inline_data_sz + 1; i++) {
 		void *addr_inline;
 
 		MLX5_SET(ste_double_action_insert_with_inline_v1, hw_action, action_id,
 			 DR_STE_V1_ACTION_ID_INSERT_INLINE);
 		/* The hardware expects here offset to words (2 bytes) */
-		MLX5_SET(ste_double_action_insert_with_inline_v1, hw_action, start_offset,
-			 i * 2);
+		MLX5_SET(ste_double_action_insert_with_inline_v1, hw_action, start_offset, 0);
 
 		/* Copy bytes one by one to avoid endianness problem */
 		addr_inline = MLX5_ADDR_OF(ste_double_action_insert_with_inline_v1,
 					   hw_action, inline_data);
-		memcpy(addr_inline, data_ptr, inline_data_sz);
+		memcpy(addr_inline, data_ptr - i * inline_data_sz, inline_data_sz);
 		hw_action += DR_STE_ACTION_DOUBLE_SZ;
-		data_ptr += inline_data_sz;
 		used_actions++;
 	}
 
-	/* Remove 2 extra bytes */
+	/* Remove first 2 extra bytes */
 	MLX5_SET(ste_single_action_remove_header_size_v1, hw_action, action_id,
 		 DR_STE_V1_ACTION_ID_REMOVE_BY_SIZE);
-	MLX5_SET(ste_single_action_remove_header_size_v1, hw_action, start_offset, data_sz / 2);
+	MLX5_SET(ste_single_action_remove_header_size_v1, hw_action, start_offset, 0);
 	/* The hardware expects here size in words (2 bytes) */
 	MLX5_SET(ste_single_action_remove_header_size_v1, hw_action, remove_size, 1);
 	used_actions++;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h
index 612b0ac31db2..9737565cd8d4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h
@@ -124,10 +124,11 @@ int mlx5dr_action_destroy(struct mlx5dr_action *action);
 static inline bool
 mlx5dr_is_supported(struct mlx5_core_dev *dev)
 {
-	return MLX5_CAP_ESW_FLOWTABLE_FDB(dev, sw_owner) ||
-	       (MLX5_CAP_ESW_FLOWTABLE_FDB(dev, sw_owner_v2) &&
-		(MLX5_CAP_GEN(dev, steering_format_version) <=
-		 MLX5_STEERING_FORMAT_CONNECTX_6DX));
+	return MLX5_CAP_GEN(dev, roce) &&
+	       (MLX5_CAP_ESW_FLOWTABLE_FDB(dev, sw_owner) ||
+		(MLX5_CAP_ESW_FLOWTABLE_FDB(dev, sw_owner_v2) &&
+		 (MLX5_CAP_GEN(dev, steering_format_version) <=
+		  MLX5_STEERING_FORMAT_CONNECTX_6DX)));
 }
 
 /* buddy functions & structure */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/transobj.c b/drivers/net/ethernet/mellanox/mlx5/core/transobj.c
index 01cc00ad8acf..b6931bbe52d2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/transobj.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/transobj.c
@@ -424,6 +424,15 @@ err_modify_sq:
 	return err;
 }
 
+static void mlx5_hairpin_unpair_peer_sq(struct mlx5_hairpin *hp)
+{
+	int i;
+
+	for (i = 0; i < hp->num_channels; i++)
+		mlx5_hairpin_modify_sq(hp->peer_mdev, hp->sqn[i], MLX5_SQC_STATE_RDY,
+				       MLX5_SQC_STATE_RST, 0, 0);
+}
+
 static void mlx5_hairpin_unpair_queues(struct mlx5_hairpin *hp)
 {
 	int i;
@@ -432,13 +441,9 @@ static void mlx5_hairpin_unpair_queues(struct mlx5_hairpin *hp)
 	for (i = 0; i < hp->num_channels; i++)
 		mlx5_hairpin_modify_rq(hp->func_mdev, hp->rqn[i], MLX5_RQC_STATE_RDY,
 				       MLX5_RQC_STATE_RST, 0, 0);
-
 	/* unset peer SQs */
-	if (hp->peer_gone)
-		return;
-	for (i = 0; i < hp->num_channels; i++)
-		mlx5_hairpin_modify_sq(hp->peer_mdev, hp->sqn[i], MLX5_SQC_STATE_RDY,
-				       MLX5_SQC_STATE_RST, 0, 0);
+	if (!hp->peer_gone)
+		mlx5_hairpin_unpair_peer_sq(hp);
 }
 
 struct mlx5_hairpin *
@@ -485,3 +490,16 @@ void mlx5_core_hairpin_destroy(struct mlx5_hairpin *hp)
 	mlx5_hairpin_destroy_queues(hp);
 	kfree(hp);
 }
+
+void mlx5_core_hairpin_clear_dead_peer(struct mlx5_hairpin *hp)
+{
+	int i;
+
+	mlx5_hairpin_unpair_peer_sq(hp);
+
+	/* destroy peer SQ */
+	for (i = 0; i < hp->num_channels; i++)
+		mlx5_core_destroy_sq(hp->peer_mdev, hp->sqn[i]);
+
+	hp->peer_gone = true;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
index 457ad42eaa2a..4c1440a95ad7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
@@ -465,8 +465,6 @@ int mlx5_modify_nic_vport_node_guid(struct mlx5_core_dev *mdev,
 	void *in;
 	int err;
 
-	if (!vport)
-		return -EINVAL;
 	if (!MLX5_CAP_GEN(mdev, vport_group_manager))
 		return -EACCES;
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
index dfea14399607..85f0ce285146 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
@@ -693,7 +693,8 @@ mlxsw_thermal_module_tz_init(struct mlxsw_thermal_module *module_tz)
 							MLXSW_THERMAL_TRIP_MASK,
 							module_tz,
 							&mlxsw_thermal_module_ops,
-							NULL, 0, 0);
+							NULL, 0,
+							module_tz->parent->polling_delay);
 	if (IS_ERR(module_tz->tzdev)) {
 		err = PTR_ERR(module_tz->tzdev);
 		return err;
@@ -815,7 +816,8 @@ mlxsw_thermal_gearbox_tz_init(struct mlxsw_thermal_module *gearbox_tz)
 						MLXSW_THERMAL_TRIP_MASK,
 						gearbox_tz,
 						&mlxsw_thermal_gearbox_ops,
-						NULL, 0, 0);
+						NULL, 0,
+						gearbox_tz->parent->polling_delay);
 	if (IS_ERR(gearbox_tz->tzdev))
 		return PTR_ERR(gearbox_tz->tzdev);
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index 900b4bf5bb5b..2bc5a9003c6d 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -3907,7 +3907,7 @@ MLXSW_ITEM32(reg, qeec, max_shaper_bs, 0x1C, 0, 6);
 #define MLXSW_REG_QEEC_HIGHEST_SHAPER_BS	25
 #define MLXSW_REG_QEEC_LOWEST_SHAPER_BS_SP1	5
 #define MLXSW_REG_QEEC_LOWEST_SHAPER_BS_SP2	11
-#define MLXSW_REG_QEEC_LOWEST_SHAPER_BS_SP3	5
+#define MLXSW_REG_QEEC_LOWEST_SHAPER_BS_SP3	11
 
 static inline void mlxsw_reg_qeec_pack(char *payload, u8 local_port,
 				       enum mlxsw_reg_qeec_hr hr, u8 index,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c
index 04672eb5c7f3..9958d503bf0e 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c
@@ -1332,6 +1332,7 @@ __mlxsw_sp_qdisc_ets_graft(struct mlxsw_sp_port *mlxsw_sp_port,
 			   u8 band, u32 child_handle)
 {
 	struct mlxsw_sp_qdisc *old_qdisc;
+	u32 parent;
 
 	if (band < mlxsw_sp_qdisc->num_classes &&
 	    mlxsw_sp_qdisc->qdiscs[band].handle == child_handle)
@@ -1352,7 +1353,9 @@ __mlxsw_sp_qdisc_ets_graft(struct mlxsw_sp_port *mlxsw_sp_port,
 	if (old_qdisc)
 		mlxsw_sp_qdisc_destroy(mlxsw_sp_port, old_qdisc);
 
-	mlxsw_sp_qdisc = mlxsw_sp_qdisc->ops->find_class(mlxsw_sp_qdisc, band);
+	parent = TC_H_MAKE(mlxsw_sp_qdisc->handle, band + 1);
+	mlxsw_sp_qdisc = mlxsw_sp_qdisc->ops->find_class(mlxsw_sp_qdisc,
+							 parent);
 	if (!WARN_ON(!mlxsw_sp_qdisc))
 		mlxsw_sp_qdisc_destroy(mlxsw_sp_port, mlxsw_sp_qdisc);
 
diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c
index 0c4283319d7f..adfb9781799e 100644
--- a/drivers/net/ethernet/mscc/ocelot.c
+++ b/drivers/net/ethernet/mscc/ocelot.c
@@ -379,6 +379,7 @@ static u32 ocelot_read_eq_avail(struct ocelot *ocelot, int port)
 
 int ocelot_port_flush(struct ocelot *ocelot, int port)
 {
+	unsigned int pause_ena;
 	int err, val;
 
 	/* Disable dequeuing from the egress queues */
@@ -387,6 +388,7 @@ int ocelot_port_flush(struct ocelot *ocelot, int port)
 		       QSYS_PORT_MODE, port);
 
 	/* Disable flow control */
+	ocelot_fields_read(ocelot, port, SYS_PAUSE_CFG_PAUSE_ENA, &pause_ena);
 	ocelot_fields_write(ocelot, port, SYS_PAUSE_CFG_PAUSE_ENA, 0);
 
 	/* Disable priority flow control */
@@ -422,6 +424,9 @@ int ocelot_port_flush(struct ocelot *ocelot, int port)
 	/* Clear flushing again. */
 	ocelot_rmw_gix(ocelot, 0, REW_PORT_CFG_FLUSH_ENA, REW_PORT_CFG, port);
 
+	/* Re-enable flow control */
+	ocelot_fields_write(ocelot, port, SYS_PAUSE_CFG_PAUSE_ENA, pause_ena);
+
 	return err;
 }
 EXPORT_SYMBOL(ocelot_port_flush);
diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c
index 7e6bac85495d..344ea1143454 100644
--- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c
+++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c
@@ -1602,6 +1602,8 @@ err_out_free_netdev:
 	free_netdev(netdev);
 
 err_out_free_res:
+	if (NX_IS_REVISION_P3(pdev->revision))
+		pci_disable_pcie_error_reporting(pdev);
 	pci_release_regions(pdev);
 
 err_out_disable_pdev:
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
index 17d5b649eb36..e81dd34a3cac 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
@@ -1266,9 +1266,11 @@ int qed_dcbx_get_config_params(struct qed_hwfn *p_hwfn,
 		p_hwfn->p_dcbx_info->set.ver_num |= DCBX_CONFIG_VERSION_STATIC;
 
 	p_hwfn->p_dcbx_info->set.enabled = dcbx_info->operational.enabled;
+	BUILD_BUG_ON(sizeof(dcbx_info->operational.params) !=
+		     sizeof(p_hwfn->p_dcbx_info->set.config.params));
 	memcpy(&p_hwfn->p_dcbx_info->set.config.params,
 	       &dcbx_info->operational.params,
-	       sizeof(struct qed_dcbx_admin_params));
+	       sizeof(p_hwfn->p_dcbx_info->set.config.params));
 	p_hwfn->p_dcbx_info->set.config.valid = true;
 
 	memcpy(params, &p_hwfn->p_dcbx_info->set, sizeof(struct qed_dcbx_set));
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
index 96b947fde646..3beafc60747e 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
@@ -2690,6 +2690,7 @@ err_out_free_hw_res:
 	kfree(ahw);
 
 err_out_free_res:
+	pci_disable_pcie_error_reporting(pdev);
 	pci_release_regions(pdev);
 
 err_out_disable_pdev:
diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c
index 41fbd2ceeede..ab1e0fcccabb 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c
@@ -126,24 +126,24 @@ static void rmnet_get_stats64(struct net_device *dev,
 			      struct rtnl_link_stats64 *s)
 {
 	struct rmnet_priv *priv = netdev_priv(dev);
-	struct rmnet_vnd_stats total_stats;
+	struct rmnet_vnd_stats total_stats = { };
 	struct rmnet_pcpu_stats *pcpu_ptr;
+	struct rmnet_vnd_stats snapshot;
 	unsigned int cpu, start;
 
-	memset(&total_stats, 0, sizeof(struct rmnet_vnd_stats));
-
 	for_each_possible_cpu(cpu) {
 		pcpu_ptr = per_cpu_ptr(priv->pcpu_stats, cpu);
 
 		do {
 			start = u64_stats_fetch_begin_irq(&pcpu_ptr->syncp);
-			total_stats.rx_pkts += pcpu_ptr->stats.rx_pkts;
-			total_stats.rx_bytes += pcpu_ptr->stats.rx_bytes;
-			total_stats.tx_pkts += pcpu_ptr->stats.tx_pkts;
-			total_stats.tx_bytes += pcpu_ptr->stats.tx_bytes;
+			snapshot = pcpu_ptr->stats;	/* struct assignment */
 		} while (u64_stats_fetch_retry_irq(&pcpu_ptr->syncp, start));
 
-		total_stats.tx_drops += pcpu_ptr->stats.tx_drops;
+		total_stats.rx_pkts += snapshot.rx_pkts;
+		total_stats.rx_bytes += snapshot.rx_bytes;
+		total_stats.tx_pkts += snapshot.tx_pkts;
+		total_stats.tx_bytes += snapshot.tx_bytes;
+		total_stats.tx_drops += snapshot.tx_drops;
 	}
 
 	s->rx_packets = total_stats.rx_pkts;
@@ -354,4 +354,4 @@ int rmnet_vnd_update_dev_mtu(struct rmnet_port *port,
 	}
 
 	return 0;
-}
\ No newline at end of file
+}
diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 2c89cde7da1e..2ee72dc431cd 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -1671,7 +1671,7 @@ static void rtl8169_get_strings(struct net_device *dev, u32 stringset, u8 *data)
 {
 	switch(stringset) {
 	case ETH_SS_STATS:
-		memcpy(data, *rtl8169_gstrings, sizeof(rtl8169_gstrings));
+		memcpy(data, rtl8169_gstrings, sizeof(rtl8169_gstrings));
 		break;
 	}
 }
diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
index c5b154868c1f..713d3629b4c1 100644
--- a/drivers/net/ethernet/renesas/sh_eth.c
+++ b/drivers/net/ethernet/renesas/sh_eth.c
@@ -2287,7 +2287,7 @@ static void sh_eth_get_strings(struct net_device *ndev, u32 stringset, u8 *data)
 {
 	switch (stringset) {
 	case ETH_SS_STATS:
-		memcpy(data, *sh_eth_gstrings_stats,
+		memcpy(data, sh_eth_gstrings_stats,
 		       sizeof(sh_eth_gstrings_stats));
 		break;
 	}
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h b/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h
index b70d44ac0990..3c73453725f9 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h
@@ -76,10 +76,10 @@ enum power_event {
 #define LPI_CTRL_STATUS_TLPIEN	0x00000001	/* Transmit LPI Entry */
 
 /* GMAC HW ADDR regs */
-#define GMAC_ADDR_HIGH(reg)	(((reg > 15) ? 0x00000800 : 0x00000040) + \
-				(reg * 8))
-#define GMAC_ADDR_LOW(reg)	(((reg > 15) ? 0x00000804 : 0x00000044) + \
-				(reg * 8))
+#define GMAC_ADDR_HIGH(reg)	((reg > 15) ? 0x00000800 + (reg - 16) * 8 : \
+				 0x00000040 + (reg * 8))
+#define GMAC_ADDR_LOW(reg)	((reg > 15) ? 0x00000804 + (reg - 16) * 8 : \
+				 0x00000044 + (reg * 8))
 #define GMAC_MAX_PERFECT_ADDRESSES	1
 
 #define GMAC_PCS_BASE		0x000000c0	/* PCS register base */
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
index 1e17a23d9118..a696ada013eb 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
@@ -622,6 +622,8 @@ error_pclk_get:
 void stmmac_remove_config_dt(struct platform_device *pdev,
 			     struct plat_stmmacenet_data *plat)
 {
+	clk_disable_unprepare(plat->stmmac_clk);
+	clk_disable_unprepare(plat->pclk);
 	of_node_put(plat->phy_node);
 	of_node_put(plat->mdio_node);
 }
diff --git a/drivers/net/ethernet/xilinx/ll_temac_main.c b/drivers/net/ethernet/xilinx/ll_temac_main.c
index a1f5f07f4ca9..9a13953ea70f 100644
--- a/drivers/net/ethernet/xilinx/ll_temac_main.c
+++ b/drivers/net/ethernet/xilinx/ll_temac_main.c
@@ -774,12 +774,15 @@ static void temac_start_xmit_done(struct net_device *ndev)
 	stat = be32_to_cpu(cur_p->app0);
 
 	while (stat & STS_CTRL_APP0_CMPLT) {
+		/* Make sure that the other fields are read after bd is
+		 * released by dma
+		 */
+		rmb();
 		dma_unmap_single(ndev->dev.parent, be32_to_cpu(cur_p->phys),
 				 be32_to_cpu(cur_p->len), DMA_TO_DEVICE);
 		skb = (struct sk_buff *)ptr_from_txbd(cur_p);
 		if (skb)
 			dev_consume_skb_irq(skb);
-		cur_p->app0 = 0;
 		cur_p->app1 = 0;
 		cur_p->app2 = 0;
 		cur_p->app3 = 0;
@@ -788,6 +791,12 @@ static void temac_start_xmit_done(struct net_device *ndev)
 		ndev->stats.tx_packets++;
 		ndev->stats.tx_bytes += be32_to_cpu(cur_p->len);
 
+		/* app0 must be visible last, as it is used to flag
+		 * availability of the bd
+		 */
+		smp_mb();
+		cur_p->app0 = 0;
+
 		lp->tx_bd_ci++;
 		if (lp->tx_bd_ci >= lp->tx_bd_num)
 			lp->tx_bd_ci = 0;
@@ -814,6 +823,9 @@ static inline int temac_check_tx_bd_space(struct temac_local *lp, int num_frag)
 		if (cur_p->app0)
 			return NETDEV_TX_BUSY;
 
+		/* Make sure to read next bd app0 after this one */
+		rmb();
+
 		tail++;
 		if (tail >= lp->tx_bd_num)
 			tail = 0;
@@ -849,7 +861,7 @@ temac_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 		smp_mb();
 
 		/* Space might have just been freed - check again */
-		if (temac_check_tx_bd_space(lp, num_frag))
+		if (temac_check_tx_bd_space(lp, num_frag + 1))
 			return NETDEV_TX_BUSY;
 
 		netif_wake_queue(ndev);
@@ -876,7 +888,6 @@ temac_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 		return NETDEV_TX_OK;
 	}
 	cur_p->phys = cpu_to_be32(skb_dma_addr);
-	ptr_to_txbd((void *)skb, cur_p);
 
 	for (ii = 0; ii < num_frag; ii++) {
 		if (++lp->tx_bd_tail >= lp->tx_bd_num)
@@ -915,6 +926,11 @@ temac_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	}
 	cur_p->app0 |= cpu_to_be32(STS_CTRL_APP0_EOP);
 
+	/* Mark last fragment with skb address, so it can be consumed
+	 * in temac_start_xmit_done()
+	 */
+	ptr_to_txbd((void *)skb, cur_p);
+
 	tail_p = lp->tx_bd_p + sizeof(*lp->tx_bd_v) * lp->tx_bd_tail;
 	lp->tx_bd_tail++;
 	if (lp->tx_bd_tail >= lp->tx_bd_num)
@@ -926,6 +942,11 @@ temac_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	wmb();
 	lp->dma_out(lp, TX_TAILDESC_PTR, tail_p); /* DMA start */
 
+	if (temac_check_tx_bd_space(lp, MAX_SKB_FRAGS + 1)) {
+		netdev_info(ndev, "%s -> netif_stop_queue\n", __func__);
+		netif_stop_queue(ndev);
+	}
+
 	return NETDEV_TX_OK;
 }
 
diff --git a/drivers/net/hamradio/mkiss.c b/drivers/net/hamradio/mkiss.c
index 65154224d5b8..7685a1721597 100644
--- a/drivers/net/hamradio/mkiss.c
+++ b/drivers/net/hamradio/mkiss.c
@@ -799,6 +799,7 @@ static void mkiss_close(struct tty_struct *tty)
 	ax->tty = NULL;
 
 	unregister_netdev(ax->dev);
+	free_netdev(ax->dev);
 }
 
 /* Perform I/O control on an active ax25 channel. */
diff --git a/drivers/net/mhi/net.c b/drivers/net/mhi/net.c
index 0d8293a47a56..b806f2f8f859 100644
--- a/drivers/net/mhi/net.c
+++ b/drivers/net/mhi/net.c
@@ -49,7 +49,7 @@ static int mhi_ndo_stop(struct net_device *ndev)
 	return 0;
 }
 
-static int mhi_ndo_xmit(struct sk_buff *skb, struct net_device *ndev)
+static netdev_tx_t mhi_ndo_xmit(struct sk_buff *skb, struct net_device *ndev)
 {
 	struct mhi_net_dev *mhi_netdev = netdev_priv(ndev);
 	const struct mhi_net_proto *proto = mhi_netdev->proto;
diff --git a/drivers/net/phy/dp83867.c b/drivers/net/phy/dp83867.c
index 9bd9a5c0b1db..6bbc81ad295f 100644
--- a/drivers/net/phy/dp83867.c
+++ b/drivers/net/phy/dp83867.c
@@ -826,16 +826,12 @@ static int dp83867_phy_reset(struct phy_device *phydev)
 {
 	int err;
 
-	err = phy_write(phydev, DP83867_CTRL, DP83867_SW_RESET);
+	err = phy_write(phydev, DP83867_CTRL, DP83867_SW_RESTART);
 	if (err < 0)
 		return err;
 
 	usleep_range(10, 20);
 
-	/* After reset FORCE_LINK_GOOD bit is set. Although the
-	 * default value should be unset. Disable FORCE_LINK_GOOD
-	 * for the phy to work properly.
-	 */
 	return phy_modify(phydev, MII_DP83867_PHYCTRL,
 			 DP83867_PHYCR_FORCE_LINK_GOOD, 0);
 }
diff --git a/drivers/net/usb/cdc_eem.c b/drivers/net/usb/cdc_eem.c
index 2e60bc1b9a6b..359ea0d10e59 100644
--- a/drivers/net/usb/cdc_eem.c
+++ b/drivers/net/usb/cdc_eem.c
@@ -123,10 +123,10 @@ static struct sk_buff *eem_tx_fixup(struct usbnet *dev, struct sk_buff *skb,
 	}
 
 	skb2 = skb_copy_expand(skb, EEM_HEAD, ETH_FCS_LEN + padlen, flags);
+	dev_kfree_skb_any(skb);
 	if (!skb2)
 		return NULL;
 
-	dev_kfree_skb_any(skb);
 	skb = skb2;
 
 done:
diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index b04055fd1b79..df0d1837e4ed 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -1880,7 +1880,7 @@ static void cdc_ncm_status(struct usbnet *dev, struct urb *urb)
 static const struct driver_info cdc_ncm_info = {
 	.description = "CDC NCM",
 	.flags = FLAG_POINTTOPOINT | FLAG_NO_SETINT | FLAG_MULTI_PACKET
-			| FLAG_LINK_INTR,
+			| FLAG_LINK_INTR | FLAG_ETHER,
 	.bind = cdc_ncm_bind,
 	.unbind = cdc_ncm_unbind,
 	.manage_power = usbnet_manage_power,
diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 6700f1970b24..bc55ec739af9 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -575,7 +575,7 @@ static int qmi_wwan_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
 
 	if (info->flags & QMI_WWAN_FLAG_PASS_THROUGH) {
 		skb->protocol = htons(ETH_P_MAP);
-		return (netif_rx(skb) == NET_RX_SUCCESS);
+		return 1;
 	}
 
 	switch (skb->data[0] & 0xf0) {
diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index f6abb2fbf972..e25bfb7021ed 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -8678,7 +8678,7 @@ static void rtl8152_get_strings(struct net_device *dev, u32 stringset, u8 *data)
 {
 	switch (stringset) {
 	case ETH_SS_STATS:
-		memcpy(data, *rtl8152_gstrings, sizeof(rtl8152_gstrings));
+		memcpy(data, rtl8152_gstrings, sizeof(rtl8152_gstrings));
 		break;
 	}
 }
diff --git a/drivers/net/usb/smsc75xx.c b/drivers/net/usb/smsc75xx.c
index b286993da67c..13141dbfa3a8 100644
--- a/drivers/net/usb/smsc75xx.c
+++ b/drivers/net/usb/smsc75xx.c
@@ -1483,7 +1483,7 @@ static int smsc75xx_bind(struct usbnet *dev, struct usb_interface *intf)
 	ret = smsc75xx_wait_ready(dev, 0);
 	if (ret < 0) {
 		netdev_warn(dev->net, "device not ready in smsc75xx_bind\n");
-		goto err;
+		goto free_pdata;
 	}
 
 	smsc75xx_init_mac_address(dev);
@@ -1492,7 +1492,7 @@ static int smsc75xx_bind(struct usbnet *dev, struct usb_interface *intf)
 	ret = smsc75xx_reset(dev);
 	if (ret < 0) {
 		netdev_warn(dev->net, "smsc75xx_reset error %d\n", ret);
-		goto err;
+		goto cancel_work;
 	}
 
 	dev->net->netdev_ops = &smsc75xx_netdev_ops;
@@ -1503,8 +1503,11 @@ static int smsc75xx_bind(struct usbnet *dev, struct usb_interface *intf)
 	dev->net->max_mtu = MAX_SINGLE_PACKET_SIZE;
 	return 0;
 
-err:
+cancel_work:
+	cancel_work_sync(&pdata->set_multicast);
+free_pdata:
 	kfree(pdata);
+	dev->data[0] = 0;
 	return ret;
 }
 
@@ -1515,7 +1518,6 @@ static void smsc75xx_unbind(struct usbnet *dev, struct usb_interface *intf)
 		cancel_work_sync(&pdata->set_multicast);
 		netif_dbg(dev, ifdown, dev->net, "free pdata\n");
 		kfree(pdata);
-		pdata = NULL;
 		dev->data[0] = 0;
 	}
 }
diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 503e2fd7ce51..28a6c4cfe9b8 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -1183,9 +1183,6 @@ static int vrf_dev_init(struct net_device *dev)
 
 	dev->flags = IFF_MASTER | IFF_NOARP;
 
-	/* MTU is irrelevant for VRF device; set to 64k similar to lo */
-	dev->mtu = 64 * 1024;
-
 	/* similarly, oper state is irrelevant; set to up to avoid confusion */
 	dev->operstate = IF_OPER_UP;
 	netdev_lockdep_set_classes(dev);
@@ -1685,7 +1682,8 @@ static void vrf_setup(struct net_device *dev)
 	 * which breaks networking.
 	 */
 	dev->min_mtu = IPV6_MIN_MTU;
-	dev->max_mtu = ETH_MAX_MTU;
+	dev->max_mtu = IP6_MAX_MTU;
+	dev->mtu = dev->max_mtu;
 }
 
 static int vrf_validate(struct nlattr *tb[], struct nlattr *data[],
diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c
index 51ce767eaf88..7a6fd46d0c6e 100644
--- a/drivers/net/wireless/mac80211_hwsim.c
+++ b/drivers/net/wireless/mac80211_hwsim.c
@@ -1693,8 +1693,13 @@ static int mac80211_hwsim_start(struct ieee80211_hw *hw)
 static void mac80211_hwsim_stop(struct ieee80211_hw *hw)
 {
 	struct mac80211_hwsim_data *data = hw->priv;
+
 	data->started = false;
 	hrtimer_cancel(&data->beacon_timer);
+
+	while (!skb_queue_empty(&data->pending))
+		ieee80211_free_txskb(hw, skb_dequeue(&data->pending));
+
 	wiphy_dbg(hw->wiphy, "%s\n", __func__);
 }
 
diff --git a/drivers/pci/controller/dwc/Makefile b/drivers/pci/controller/dwc/Makefile
index eca805c1a023..9e6ce0dc2f53 100644
--- a/drivers/pci/controller/dwc/Makefile
+++ b/drivers/pci/controller/dwc/Makefile
@@ -18,6 +18,7 @@ obj-$(CONFIG_PCIE_INTEL_GW) += pcie-intel-gw.o
 obj-$(CONFIG_PCIE_KIRIN) += pcie-kirin.o
 obj-$(CONFIG_PCIE_HISI_STB) += pcie-histb.o
 obj-$(CONFIG_PCI_MESON) += pci-meson.o
+obj-$(CONFIG_PCIE_TEGRA194) += pcie-tegra194.o
 obj-$(CONFIG_PCIE_UNIPHIER) += pcie-uniphier.o
 obj-$(CONFIG_PCIE_UNIPHIER_EP) += pcie-uniphier-ep.o
 
@@ -38,6 +39,6 @@ ifdef CONFIG_ACPI
 ifdef CONFIG_PCI_QUIRKS
 obj-$(CONFIG_ARM64) += pcie-al.o
 obj-$(CONFIG_ARM64) += pcie-hisi.o
-obj-$(CONFIG_ARM64) += pcie-tegra194.o
+obj-$(CONFIG_ARM64) += pcie-tegra194-acpi.o
 endif
 endif
diff --git a/drivers/pci/controller/dwc/pcie-tegra194-acpi.c b/drivers/pci/controller/dwc/pcie-tegra194-acpi.c
new file mode 100644
index 000000000000..c2de6ed4d86f
--- /dev/null
+++ b/drivers/pci/controller/dwc/pcie-tegra194-acpi.c
@@ -0,0 +1,108 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * ACPI quirks for Tegra194 PCIe host controller
+ *
+ * Copyright (C) 2021 NVIDIA Corporation.
+ *
+ * Author: Vidya Sagar <vidyas@nvidia.com>
+ */
+
+#include <linux/pci.h>
+#include <linux/pci-acpi.h>
+#include <linux/pci-ecam.h>
+
+#include "pcie-designware.h"
+
+struct tegra194_pcie_ecam  {
+	void __iomem *config_base;
+	void __iomem *iatu_base;
+	void __iomem *dbi_base;
+};
+
+static int tegra194_acpi_init(struct pci_config_window *cfg)
+{
+	struct device *dev = cfg->parent;
+	struct tegra194_pcie_ecam *pcie_ecam;
+
+	pcie_ecam = devm_kzalloc(dev, sizeof(*pcie_ecam), GFP_KERNEL);
+	if (!pcie_ecam)
+		return -ENOMEM;
+
+	pcie_ecam->config_base = cfg->win;
+	pcie_ecam->iatu_base = cfg->win + SZ_256K;
+	pcie_ecam->dbi_base = cfg->win + SZ_512K;
+	cfg->priv = pcie_ecam;
+
+	return 0;
+}
+
+static void atu_reg_write(struct tegra194_pcie_ecam *pcie_ecam, int index,
+			  u32 val, u32 reg)
+{
+	u32 offset = PCIE_GET_ATU_OUTB_UNR_REG_OFFSET(index);
+
+	writel(val, pcie_ecam->iatu_base + offset + reg);
+}
+
+static void program_outbound_atu(struct tegra194_pcie_ecam *pcie_ecam,
+				 int index, int type, u64 cpu_addr,
+				 u64 pci_addr, u64 size)
+{
+	atu_reg_write(pcie_ecam, index, lower_32_bits(cpu_addr),
+		      PCIE_ATU_LOWER_BASE);
+	atu_reg_write(pcie_ecam, index, upper_32_bits(cpu_addr),
+		      PCIE_ATU_UPPER_BASE);
+	atu_reg_write(pcie_ecam, index, lower_32_bits(pci_addr),
+		      PCIE_ATU_LOWER_TARGET);
+	atu_reg_write(pcie_ecam, index, lower_32_bits(cpu_addr + size - 1),
+		      PCIE_ATU_LIMIT);
+	atu_reg_write(pcie_ecam, index, upper_32_bits(pci_addr),
+		      PCIE_ATU_UPPER_TARGET);
+	atu_reg_write(pcie_ecam, index, type, PCIE_ATU_CR1);
+	atu_reg_write(pcie_ecam, index, PCIE_ATU_ENABLE, PCIE_ATU_CR2);
+}
+
+static void __iomem *tegra194_map_bus(struct pci_bus *bus,
+				      unsigned int devfn, int where)
+{
+	struct pci_config_window *cfg = bus->sysdata;
+	struct tegra194_pcie_ecam *pcie_ecam = cfg->priv;
+	u32 busdev;
+	int type;
+
+	if (bus->number < cfg->busr.start || bus->number > cfg->busr.end)
+		return NULL;
+
+	if (bus->number == cfg->busr.start) {
+		if (PCI_SLOT(devfn) == 0)
+			return pcie_ecam->dbi_base + where;
+		else
+			return NULL;
+	}
+
+	busdev = PCIE_ATU_BUS(bus->number) | PCIE_ATU_DEV(PCI_SLOT(devfn)) |
+		 PCIE_ATU_FUNC(PCI_FUNC(devfn));
+
+	if (bus->parent->number == cfg->busr.start) {
+		if (PCI_SLOT(devfn) == 0)
+			type = PCIE_ATU_TYPE_CFG0;
+		else
+			return NULL;
+	} else {
+		type = PCIE_ATU_TYPE_CFG1;
+	}
+
+	program_outbound_atu(pcie_ecam, 0, type, cfg->res.start, busdev,
+			     SZ_256K);
+
+	return pcie_ecam->config_base + where;
+}
+
+const struct pci_ecam_ops tegra194_pcie_ops = {
+	.init		= tegra194_acpi_init,
+	.pci_ops	= {
+		.map_bus	= tegra194_map_bus,
+		.read		= pci_generic_config_read,
+		.write		= pci_generic_config_write,
+	}
+};
diff --git a/drivers/pci/controller/dwc/pcie-tegra194.c b/drivers/pci/controller/dwc/pcie-tegra194.c
index bafd2c6ab3c2..504669e3afe0 100644
--- a/drivers/pci/controller/dwc/pcie-tegra194.c
+++ b/drivers/pci/controller/dwc/pcie-tegra194.c
@@ -22,8 +22,6 @@
 #include <linux/of_irq.h>
 #include <linux/of_pci.h>
 #include <linux/pci.h>
-#include <linux/pci-acpi.h>
-#include <linux/pci-ecam.h>
 #include <linux/phy/phy.h>
 #include <linux/pinctrl/consumer.h>
 #include <linux/platform_device.h>
@@ -247,24 +245,6 @@ static const unsigned int pcie_gen_freq[] = {
 	GEN4_CORE_CLK_FREQ
 };
 
-static const u32 event_cntr_ctrl_offset[] = {
-	0x1d8,
-	0x1a8,
-	0x1a8,
-	0x1a8,
-	0x1c4,
-	0x1d8
-};
-
-static const u32 event_cntr_data_offset[] = {
-	0x1dc,
-	0x1ac,
-	0x1ac,
-	0x1ac,
-	0x1c8,
-	0x1dc
-};
-
 struct tegra_pcie_dw {
 	struct device *dev;
 	struct resource *appl_res;
@@ -313,104 +293,6 @@ struct tegra_pcie_dw_of_data {
 	enum dw_pcie_device_mode mode;
 };
 
-#if defined(CONFIG_ACPI) && defined(CONFIG_PCI_QUIRKS)
-struct tegra194_pcie_ecam  {
-	void __iomem *config_base;
-	void __iomem *iatu_base;
-	void __iomem *dbi_base;
-};
-
-static int tegra194_acpi_init(struct pci_config_window *cfg)
-{
-	struct device *dev = cfg->parent;
-	struct tegra194_pcie_ecam *pcie_ecam;
-
-	pcie_ecam = devm_kzalloc(dev, sizeof(*pcie_ecam), GFP_KERNEL);
-	if (!pcie_ecam)
-		return -ENOMEM;
-
-	pcie_ecam->config_base = cfg->win;
-	pcie_ecam->iatu_base = cfg->win + SZ_256K;
-	pcie_ecam->dbi_base = cfg->win + SZ_512K;
-	cfg->priv = pcie_ecam;
-
-	return 0;
-}
-
-static void atu_reg_write(struct tegra194_pcie_ecam *pcie_ecam, int index,
-			  u32 val, u32 reg)
-{
-	u32 offset = PCIE_GET_ATU_OUTB_UNR_REG_OFFSET(index);
-
-	writel(val, pcie_ecam->iatu_base + offset + reg);
-}
-
-static void program_outbound_atu(struct tegra194_pcie_ecam *pcie_ecam,
-				 int index, int type, u64 cpu_addr,
-				 u64 pci_addr, u64 size)
-{
-	atu_reg_write(pcie_ecam, index, lower_32_bits(cpu_addr),
-		      PCIE_ATU_LOWER_BASE);
-	atu_reg_write(pcie_ecam, index, upper_32_bits(cpu_addr),
-		      PCIE_ATU_UPPER_BASE);
-	atu_reg_write(pcie_ecam, index, lower_32_bits(pci_addr),
-		      PCIE_ATU_LOWER_TARGET);
-	atu_reg_write(pcie_ecam, index, lower_32_bits(cpu_addr + size - 1),
-		      PCIE_ATU_LIMIT);
-	atu_reg_write(pcie_ecam, index, upper_32_bits(pci_addr),
-		      PCIE_ATU_UPPER_TARGET);
-	atu_reg_write(pcie_ecam, index, type, PCIE_ATU_CR1);
-	atu_reg_write(pcie_ecam, index, PCIE_ATU_ENABLE, PCIE_ATU_CR2);
-}
-
-static void __iomem *tegra194_map_bus(struct pci_bus *bus,
-				      unsigned int devfn, int where)
-{
-	struct pci_config_window *cfg = bus->sysdata;
-	struct tegra194_pcie_ecam *pcie_ecam = cfg->priv;
-	u32 busdev;
-	int type;
-
-	if (bus->number < cfg->busr.start || bus->number > cfg->busr.end)
-		return NULL;
-
-	if (bus->number == cfg->busr.start) {
-		if (PCI_SLOT(devfn) == 0)
-			return pcie_ecam->dbi_base + where;
-		else
-			return NULL;
-	}
-
-	busdev = PCIE_ATU_BUS(bus->number) | PCIE_ATU_DEV(PCI_SLOT(devfn)) |
-		 PCIE_ATU_FUNC(PCI_FUNC(devfn));
-
-	if (bus->parent->number == cfg->busr.start) {
-		if (PCI_SLOT(devfn) == 0)
-			type = PCIE_ATU_TYPE_CFG0;
-		else
-			return NULL;
-	} else {
-		type = PCIE_ATU_TYPE_CFG1;
-	}
-
-	program_outbound_atu(pcie_ecam, 0, type, cfg->res.start, busdev,
-			     SZ_256K);
-
-	return pcie_ecam->config_base + where;
-}
-
-const struct pci_ecam_ops tegra194_pcie_ops = {
-	.init		= tegra194_acpi_init,
-	.pci_ops	= {
-		.map_bus	= tegra194_map_bus,
-		.read		= pci_generic_config_read,
-		.write		= pci_generic_config_write,
-	}
-};
-#endif /* defined(CONFIG_ACPI) && defined(CONFIG_PCI_QUIRKS) */
-
-#ifdef CONFIG_PCIE_TEGRA194
-
 static inline struct tegra_pcie_dw *to_tegra_pcie(struct dw_pcie *pci)
 {
 	return container_of(pci, struct tegra_pcie_dw, pci);
@@ -694,6 +576,24 @@ static struct pci_ops tegra_pci_ops = {
 };
 
 #if defined(CONFIG_PCIEASPM)
+static const u32 event_cntr_ctrl_offset[] = {
+	0x1d8,
+	0x1a8,
+	0x1a8,
+	0x1a8,
+	0x1c4,
+	0x1d8
+};
+
+static const u32 event_cntr_data_offset[] = {
+	0x1dc,
+	0x1ac,
+	0x1ac,
+	0x1ac,
+	0x1c8,
+	0x1dc
+};
+
 static void disable_aspm_l11(struct tegra_pcie_dw *pcie)
 {
 	u32 val;
@@ -2411,5 +2311,3 @@ MODULE_DEVICE_TABLE(of, tegra_pcie_dw_of_match);
 MODULE_AUTHOR("Vidya Sagar <vidyas@nvidia.com>");
 MODULE_DESCRIPTION("NVIDIA PCIe host controller driver");
 MODULE_LICENSE("GPL v2");
-
-#endif /* CONFIG_PCIE_TEGRA194 */
diff --git a/drivers/pci/controller/pci-aardvark.c b/drivers/pci/controller/pci-aardvark.c
index 051b48bd7985..e3f5e7ab7606 100644
--- a/drivers/pci/controller/pci-aardvark.c
+++ b/drivers/pci/controller/pci-aardvark.c
@@ -514,7 +514,7 @@ static int advk_pcie_wait_pio(struct advk_pcie *pcie)
 		udelay(PIO_RETRY_DELAY);
 	}
 
-	dev_err(dev, "config read/write timed out\n");
+	dev_err(dev, "PIO read/write transfer time out\n");
 	return -ETIMEDOUT;
 }
 
@@ -657,6 +657,35 @@ static bool advk_pcie_valid_device(struct advk_pcie *pcie, struct pci_bus *bus,
 	return true;
 }
 
+static bool advk_pcie_pio_is_running(struct advk_pcie *pcie)
+{
+	struct device *dev = &pcie->pdev->dev;
+
+	/*
+	 * Trying to start a new PIO transfer when previous has not completed
+	 * cause External Abort on CPU which results in kernel panic:
+	 *
+	 *     SError Interrupt on CPU0, code 0xbf000002 -- SError
+	 *     Kernel panic - not syncing: Asynchronous SError Interrupt
+	 *
+	 * Functions advk_pcie_rd_conf() and advk_pcie_wr_conf() are protected
+	 * by raw_spin_lock_irqsave() at pci_lock_config() level to prevent
+	 * concurrent calls at the same time. But because PIO transfer may take
+	 * about 1.5s when link is down or card is disconnected, it means that
+	 * advk_pcie_wait_pio() does not always have to wait for completion.
+	 *
+	 * Some versions of ARM Trusted Firmware handles this External Abort at
+	 * EL3 level and mask it to prevent kernel panic. Relevant TF-A commit:
+	 * https://git.trustedfirmware.org/TF-A/trusted-firmware-a.git/commit/?id=3c7dcdac5c50
+	 */
+	if (advk_readl(pcie, PIO_START)) {
+		dev_err(dev, "Previous PIO read/write transfer is still running\n");
+		return true;
+	}
+
+	return false;
+}
+
 static int advk_pcie_rd_conf(struct pci_bus *bus, u32 devfn,
 			     int where, int size, u32 *val)
 {
@@ -673,9 +702,10 @@ static int advk_pcie_rd_conf(struct pci_bus *bus, u32 devfn,
 		return pci_bridge_emul_conf_read(&pcie->bridge, where,
 						 size, val);
 
-	/* Start PIO */
-	advk_writel(pcie, 0, PIO_START);
-	advk_writel(pcie, 1, PIO_ISR);
+	if (advk_pcie_pio_is_running(pcie)) {
+		*val = 0xffffffff;
+		return PCIBIOS_SET_FAILED;
+	}
 
 	/* Program the control register */
 	reg = advk_readl(pcie, PIO_CTRL);
@@ -694,7 +724,8 @@ static int advk_pcie_rd_conf(struct pci_bus *bus, u32 devfn,
 	/* Program the data strobe */
 	advk_writel(pcie, 0xf, PIO_WR_DATA_STRB);
 
-	/* Start the transfer */
+	/* Clear PIO DONE ISR and start the transfer */
+	advk_writel(pcie, 1, PIO_ISR);
 	advk_writel(pcie, 1, PIO_START);
 
 	ret = advk_pcie_wait_pio(pcie);
@@ -734,9 +765,8 @@ static int advk_pcie_wr_conf(struct pci_bus *bus, u32 devfn,
 	if (where % size)
 		return PCIBIOS_SET_FAILED;
 
-	/* Start PIO */
-	advk_writel(pcie, 0, PIO_START);
-	advk_writel(pcie, 1, PIO_ISR);
+	if (advk_pcie_pio_is_running(pcie))
+		return PCIBIOS_SET_FAILED;
 
 	/* Program the control register */
 	reg = advk_readl(pcie, PIO_CTRL);
@@ -763,7 +793,8 @@ static int advk_pcie_wr_conf(struct pci_bus *bus, u32 devfn,
 	/* Program the data strobe */
 	advk_writel(pcie, data_strobe, PIO_WR_DATA_STRB);
 
-	/* Start the transfer */
+	/* Clear PIO DONE ISR and start the transfer */
+	advk_writel(pcie, 1, PIO_ISR);
 	advk_writel(pcie, 1, PIO_START);
 
 	ret = advk_pcie_wait_pio(pcie);
diff --git a/drivers/pci/of.c b/drivers/pci/of.c
index 85dcb7097da4..a143b02b2dcd 100644
--- a/drivers/pci/of.c
+++ b/drivers/pci/of.c
@@ -353,6 +353,8 @@ static int devm_of_pci_get_host_bridge_resources(struct device *dev,
 				dev_warn(dev, "More than one I/O resource converted for %pOF. CPU base address for old range lost!\n",
 					 dev_node);
 			*io_base = range.cpu_addr;
+		} else if (resource_type(res) == IORESOURCE_MEM) {
+			res->flags &= ~IORESOURCE_MEM_64;
 		}
 
 		pci_add_resource_offset(resources, res,	res->start - range.pci_addr);
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index dcb229de1acb..22b2bb1109c9 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -3547,6 +3547,18 @@ static void quirk_no_bus_reset(struct pci_dev *dev)
 }
 
 /*
+ * Some NVIDIA GPU devices do not work with bus reset, SBR needs to be
+ * prevented for those affected devices.
+ */
+static void quirk_nvidia_no_bus_reset(struct pci_dev *dev)
+{
+	if ((dev->device & 0xffc0) == 0x2340)
+		quirk_no_bus_reset(dev);
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NVIDIA, PCI_ANY_ID,
+			 quirk_nvidia_no_bus_reset);
+
+/*
  * Some Atheros AR9xxx and QCA988x chips do not behave after a bus reset.
  * The device will throw a Link Down error on AER-capable systems and
  * regardless of AER, config space of the device is never accessible again
@@ -3566,6 +3578,16 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_ATHEROS, 0x0034, quirk_no_bus_reset);
  */
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_CAVIUM, 0xa100, quirk_no_bus_reset);
 
+/*
+ * Some TI KeyStone C667X devices do not support bus/hot reset.  The PCIESS
+ * automatically disables LTSSM when Secondary Bus Reset is received and
+ * the device stops working.  Prevent bus reset for these devices.  With
+ * this change, the device can be assigned to VMs with VFIO, but it will
+ * leak state between VMs.  Reference
+ * https://e2e.ti.com/support/processors/f/791/t/954382
+ */
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_TI, 0xb005, quirk_no_bus_reset);
+
 static void quirk_no_pm_reset(struct pci_dev *dev)
 {
 	/*
@@ -3901,6 +3923,69 @@ static int delay_250ms_after_flr(struct pci_dev *dev, int probe)
 	return 0;
 }
 
+#define PCI_DEVICE_ID_HINIC_VF      0x375E
+#define HINIC_VF_FLR_TYPE           0x1000
+#define HINIC_VF_FLR_CAP_BIT        (1UL << 30)
+#define HINIC_VF_OP                 0xE80
+#define HINIC_VF_FLR_PROC_BIT       (1UL << 18)
+#define HINIC_OPERATION_TIMEOUT     15000	/* 15 seconds */
+
+/* Device-specific reset method for Huawei Intelligent NIC virtual functions */
+static int reset_hinic_vf_dev(struct pci_dev *pdev, int probe)
+{
+	unsigned long timeout;
+	void __iomem *bar;
+	u32 val;
+
+	if (probe)
+		return 0;
+
+	bar = pci_iomap(pdev, 0, 0);
+	if (!bar)
+		return -ENOTTY;
+
+	/* Get and check firmware capabilities */
+	val = ioread32be(bar + HINIC_VF_FLR_TYPE);
+	if (!(val & HINIC_VF_FLR_CAP_BIT)) {
+		pci_iounmap(pdev, bar);
+		return -ENOTTY;
+	}
+
+	/* Set HINIC_VF_FLR_PROC_BIT for the start of FLR */
+	val = ioread32be(bar + HINIC_VF_OP);
+	val = val | HINIC_VF_FLR_PROC_BIT;
+	iowrite32be(val, bar + HINIC_VF_OP);
+
+	pcie_flr(pdev);
+
+	/*
+	 * The device must recapture its Bus and Device Numbers after FLR
+	 * in order generate Completions.  Issue a config write to let the
+	 * device capture this information.
+	 */
+	pci_write_config_word(pdev, PCI_VENDOR_ID, 0);
+
+	/* Firmware clears HINIC_VF_FLR_PROC_BIT when reset is complete */
+	timeout = jiffies + msecs_to_jiffies(HINIC_OPERATION_TIMEOUT);
+	do {
+		val = ioread32be(bar + HINIC_VF_OP);
+		if (!(val & HINIC_VF_FLR_PROC_BIT))
+			goto reset_complete;
+		msleep(20);
+	} while (time_before(jiffies, timeout));
+
+	val = ioread32be(bar + HINIC_VF_OP);
+	if (!(val & HINIC_VF_FLR_PROC_BIT))
+		goto reset_complete;
+
+	pci_warn(pdev, "Reset dev timeout, FLR ack reg: %#010x\n", val);
+
+reset_complete:
+	pci_iounmap(pdev, bar);
+
+	return 0;
+}
+
 static const struct pci_dev_reset_methods pci_dev_reset_methods[] = {
 	{ PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82599_SFP_VF,
 		 reset_intel_82599_sfp_virtfn },
@@ -3913,6 +3998,8 @@ static const struct pci_dev_reset_methods pci_dev_reset_methods[] = {
 	{ PCI_VENDOR_ID_INTEL, 0x0a54, delay_250ms_after_flr },
 	{ PCI_VENDOR_ID_CHELSIO, PCI_ANY_ID,
 		reset_chelsio_generic_dev },
+	{ PCI_VENDOR_ID_HUAWEI, PCI_DEVICE_ID_HINIC_VF,
+		reset_hinic_vf_dev },
 	{ 0 }
 };
 
@@ -4753,6 +4840,8 @@ static const struct pci_dev_acs_enabled {
 	{ PCI_VENDOR_ID_AMPERE, 0xE00A, pci_quirk_xgene_acs },
 	{ PCI_VENDOR_ID_AMPERE, 0xE00B, pci_quirk_xgene_acs },
 	{ PCI_VENDOR_ID_AMPERE, 0xE00C, pci_quirk_xgene_acs },
+	/* Broadcom multi-function device */
+	{ PCI_VENDOR_ID_BROADCOM, 0x16D7, pci_quirk_mf_endpoint_acs },
 	{ PCI_VENDOR_ID_BROADCOM, 0xD714, pci_quirk_brcm_acs },
 	/* Amazon Annapurna Labs */
 	{ PCI_VENDOR_ID_AMAZON_ANNAPURNA_LABS, 0x0031, pci_quirk_al_acs },
@@ -5154,7 +5243,8 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_SERVERWORKS, 0x0422, quirk_no_ext_tags);
 static void quirk_amd_harvest_no_ats(struct pci_dev *pdev)
 {
 	if ((pdev->device == 0x7312 && pdev->revision != 0x00) ||
-	    (pdev->device == 0x7340 && pdev->revision != 0xc5))
+	    (pdev->device == 0x7340 && pdev->revision != 0xc5) ||
+	    (pdev->device == 0x7341 && pdev->revision != 0x00))
 		return;
 
 	if (pdev->device == 0x15d8) {
@@ -5181,6 +5271,7 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x6900, quirk_amd_harvest_no_ats);
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7312, quirk_amd_harvest_no_ats);
 /* AMD Navi14 dGPU */
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7340, quirk_amd_harvest_no_ats);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7341, quirk_amd_harvest_no_ats);
 /* AMD Raven platform iGPU */
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x15d8, quirk_amd_harvest_no_ats);
 #endif /* CONFIG_PCI_ATS */
diff --git a/drivers/ptp/ptp_clock.c b/drivers/ptp/ptp_clock.c
index 03a246e60fd9..21c4c34c52d8 100644
--- a/drivers/ptp/ptp_clock.c
+++ b/drivers/ptp/ptp_clock.c
@@ -63,7 +63,7 @@ static void enqueue_external_timestamp(struct timestamp_event_queue *queue,
 	spin_unlock_irqrestore(&queue->lock, flags);
 }
 
-s32 scaled_ppm_to_ppb(long ppm)
+long scaled_ppm_to_ppb(long ppm)
 {
 	/*
 	 * The 'freq' field in the 'struct timex' is in parts per
@@ -80,7 +80,7 @@ s32 scaled_ppm_to_ppb(long ppm)
 	s64 ppb = 1 + ppm;
 	ppb *= 125;
 	ppb >>= 13;
-	return (s32) ppb;
+	return (long) ppb;
 }
 EXPORT_SYMBOL(scaled_ppm_to_ppb);
 
@@ -138,7 +138,7 @@ static int ptp_clock_adjtime(struct posix_clock *pc, struct __kernel_timex *tx)
 		delta = ktime_to_ns(kt);
 		err = ops->adjtime(ops, delta);
 	} else if (tx->modes & ADJ_FREQUENCY) {
-		s32 ppb = scaled_ppm_to_ppb(tx->freq);
+		long ppb = scaled_ppm_to_ppb(tx->freq);
 		if (ppb > ops->max_adj || ppb < -ops->max_adj)
 			return -ERANGE;
 		if (ops->adjfine)
diff --git a/drivers/s390/crypto/ap_queue.c b/drivers/s390/crypto/ap_queue.c
index ecefc25eff0c..337353c9655e 100644
--- a/drivers/s390/crypto/ap_queue.c
+++ b/drivers/s390/crypto/ap_queue.c
@@ -135,12 +135,13 @@ static struct ap_queue_status ap_sm_recv(struct ap_queue *aq)
 {
 	struct ap_queue_status status;
 	struct ap_message *ap_msg;
+	bool found = false;
 
 	status = ap_dqap(aq->qid, &aq->reply->psmid,
 			 aq->reply->msg, aq->reply->len);
 	switch (status.response_code) {
 	case AP_RESPONSE_NORMAL:
-		aq->queue_count--;
+		aq->queue_count = max_t(int, 0, aq->queue_count - 1);
 		if (aq->queue_count > 0)
 			mod_timer(&aq->timeout,
 				  jiffies + aq->request_timeout);
@@ -150,8 +151,14 @@ static struct ap_queue_status ap_sm_recv(struct ap_queue *aq)
 			list_del_init(&ap_msg->list);
 			aq->pendingq_count--;
 			ap_msg->receive(aq, ap_msg, aq->reply);
+			found = true;
 			break;
 		}
+		if (!found) {
+			AP_DBF_WARN("%s unassociated reply psmid=0x%016llx on 0x%02x.%04x\n",
+				    __func__, aq->reply->psmid,
+				    AP_QID_CARD(aq->qid), AP_QID_QUEUE(aq->qid));
+		}
 		fallthrough;
 	case AP_RESPONSE_NO_PENDING_REPLY:
 		if (!status.queue_empty || aq->queue_count <= 0)
@@ -232,7 +239,7 @@ static enum ap_sm_wait ap_sm_write(struct ap_queue *aq)
 			   ap_msg->flags & AP_MSG_FLAG_SPECIAL);
 	switch (status.response_code) {
 	case AP_RESPONSE_NORMAL:
-		aq->queue_count++;
+		aq->queue_count = max_t(int, 1, aq->queue_count + 1);
 		if (aq->queue_count == 1)
 			mod_timer(&aq->timeout, jiffies + aq->request_timeout);
 		list_move_tail(&ap_msg->list, &aq->pendingq);
diff --git a/drivers/staging/rtl8723bs/os_dep/ioctl_cfg80211.c b/drivers/staging/rtl8723bs/os_dep/ioctl_cfg80211.c
index ffa1cf4f9a82..437859228371 100644
--- a/drivers/staging/rtl8723bs/os_dep/ioctl_cfg80211.c
+++ b/drivers/staging/rtl8723bs/os_dep/ioctl_cfg80211.c
@@ -2284,7 +2284,7 @@ static int rtw_cfg80211_add_monitor_if(struct adapter *padapter, char *name, str
 	mon_wdev->iftype = NL80211_IFTYPE_MONITOR;
 	mon_ndev->ieee80211_ptr = mon_wdev;
 
-	ret = register_netdevice(mon_ndev);
+	ret = cfg80211_register_netdevice(mon_ndev);
 	if (ret) {
 		goto out;
 	}
@@ -2360,7 +2360,7 @@ static int cfg80211_rtw_del_virtual_intf(struct wiphy *wiphy,
 	adapter = rtw_netdev_priv(ndev);
 	pwdev_priv = adapter_wdev_data(adapter);
 
-	unregister_netdevice(ndev);
+	cfg80211_unregister_netdevice(ndev);
 
 	if (ndev == pwdev_priv->pmon_ndev) {
 		pwdev_priv->pmon_ndev = NULL;
diff --git a/drivers/usb/chipidea/usbmisc_imx.c b/drivers/usb/chipidea/usbmisc_imx.c
index 4545b23bda3f..bac0f5458cab 100644
--- a/drivers/usb/chipidea/usbmisc_imx.c
+++ b/drivers/usb/chipidea/usbmisc_imx.c
@@ -686,6 +686,16 @@ static int imx7d_charger_secondary_detection(struct imx_usbmisc_data *data)
 	int val;
 	unsigned long flags;
 
+	/* Clear VDATSRCENB0 to disable VDP_SRC and IDM_SNK required by BC 1.2 spec */
+	spin_lock_irqsave(&usbmisc->lock, flags);
+	val = readl(usbmisc->base + MX7D_USB_OTG_PHY_CFG2);
+	val &= ~MX7D_USB_OTG_PHY_CFG2_CHRG_VDATSRCENB0;
+	writel(val, usbmisc->base + MX7D_USB_OTG_PHY_CFG2);
+	spin_unlock_irqrestore(&usbmisc->lock, flags);
+
+	/* TVDMSRC_DIS */
+	msleep(20);
+
 	/* VDM_SRC is connected to D- and IDP_SINK is connected to D+ */
 	spin_lock_irqsave(&usbmisc->lock, flags);
 	val = readl(usbmisc->base + MX7D_USB_OTG_PHY_CFG2);
@@ -695,7 +705,8 @@ static int imx7d_charger_secondary_detection(struct imx_usbmisc_data *data)
 				usbmisc->base + MX7D_USB_OTG_PHY_CFG2);
 	spin_unlock_irqrestore(&usbmisc->lock, flags);
 
-	usleep_range(1000, 2000);
+	/* TVDMSRC_ON */
+	msleep(40);
 
 	/*
 	 * Per BC 1.2, check voltage of D+:
@@ -798,7 +809,8 @@ static int imx7d_charger_primary_detection(struct imx_usbmisc_data *data)
 				usbmisc->base + MX7D_USB_OTG_PHY_CFG2);
 	spin_unlock_irqrestore(&usbmisc->lock, flags);
 
-	usleep_range(1000, 2000);
+	/* TVDPSRC_ON */
+	msleep(40);
 
 	/* Check if D- is less than VDAT_REF to determine an SDP per BC 1.2 */
 	val = readl(usbmisc->base + MX7D_USB_OTG_PHY_STATUS);
diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index 3bd379d5d1be..d1efc7141333 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -41,6 +41,8 @@
 #define USB_VENDOR_GENESYS_LOGIC		0x05e3
 #define USB_VENDOR_SMSC				0x0424
 #define USB_PRODUCT_USB5534B			0x5534
+#define USB_VENDOR_CYPRESS			0x04b4
+#define USB_PRODUCT_CY7C65632			0x6570
 #define HUB_QUIRK_CHECK_PORT_AUTOSUSPEND	0x01
 #define HUB_QUIRK_DISABLE_AUTOSUSPEND		0x02
 
@@ -5720,6 +5722,11 @@ static const struct usb_device_id hub_id_table[] = {
       .bInterfaceClass = USB_CLASS_HUB,
       .driver_info = HUB_QUIRK_DISABLE_AUTOSUSPEND},
     { .match_flags = USB_DEVICE_ID_MATCH_VENDOR
+                   | USB_DEVICE_ID_MATCH_PRODUCT,
+      .idVendor = USB_VENDOR_CYPRESS,
+      .idProduct = USB_PRODUCT_CY7C65632,
+      .driver_info = HUB_QUIRK_DISABLE_AUTOSUSPEND},
+    { .match_flags = USB_DEVICE_ID_MATCH_VENDOR
 			| USB_DEVICE_ID_MATCH_INT_CLASS,
       .idVendor = USB_VENDOR_GENESYS_LOGIC,
       .bInterfaceClass = USB_CLASS_HUB,