diff --git a/Makefile b/Makefile
index 10314ba3c7bc5..7537adc4e237d 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 VERSION = 4
 PATCHLEVEL = 14
-SUBLEVEL = 215
+SUBLEVEL = 216
 EXTRAVERSION =
 NAME = Petit Gorille
 
diff --git a/arch/arm/mach-omap2/omap_device.c b/arch/arm/mach-omap2/omap_device.c
index acbede082b5b5..79a59fe0e773b 100644
--- a/arch/arm/mach-omap2/omap_device.c
+++ b/arch/arm/mach-omap2/omap_device.c
@@ -224,10 +224,12 @@ static int _omap_device_notifier_call(struct notifier_block *nb,
 		break;
 	case BUS_NOTIFY_BIND_DRIVER:
 		od = to_omap_device(pdev);
-		if (od && (od->_state == OMAP_DEVICE_STATE_ENABLED) &&
-		    pm_runtime_status_suspended(dev)) {
+		if (od) {
 			od->_driver_status = BUS_NOTIFY_BIND_DRIVER;
-			pm_runtime_set_active(dev);
+			if (od->_state == OMAP_DEVICE_STATE_ENABLED &&
+			    pm_runtime_status_suspended(dev)) {
+				pm_runtime_set_active(dev);
+			}
 		}
 		break;
 	case BUS_NOTIFY_ADD_DEVICE:
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index c553f9883194f..1a006101f527a 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -470,6 +470,10 @@ static void reset_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 {
 	u64 pmcr, val;
 
+	/* No PMU available, PMCR_EL0 may UNDEF... */
+	if (!kvm_arm_support_pmu_v3())
+		return;
+
 	pmcr = read_sysreg(pmcr_el0);
 	/*
 	 * Writable bits of PMCR_EL0 (ARMV8_PMU_PMCR_MASK) are reset to UNKNOWN
diff --git a/arch/powerpc/include/asm/book3s/32/pgtable.h b/arch/powerpc/include/asm/book3s/32/pgtable.h
index 016579ef16d3d..ec98abca0df03 100644
--- a/arch/powerpc/include/asm/book3s/32/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/32/pgtable.h
@@ -414,9 +414,9 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr,
 	if (pte_val(*ptep) & _PAGE_HASHPTE)
 		flush_hash_entry(mm, ptep, addr);
 	__asm__ __volatile__("\
-		stw%U0%X0 %2,%0\n\
+		stw%X0 %2,%0\n\
 		eieio\n\
-		stw%U0%X0 %L2,%1"
+		stw%X1 %L2,%1"
 	: "=m" (*ptep), "=m" (*((unsigned char *)ptep+4))
 	: "r" (pte) : "memory");
 
diff --git a/arch/powerpc/include/asm/nohash/pgtable.h b/arch/powerpc/include/asm/nohash/pgtable.h
index 5c68f4a59f758..e9171b8242e4b 100644
--- a/arch/powerpc/include/asm/nohash/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/pgtable.h
@@ -157,9 +157,9 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr,
 		flush_hash_entry(mm, ptep, addr);
 #endif
 	__asm__ __volatile__("\
-		stw%U0%X0 %2,%0\n\
+		stw%X0 %2,%0\n\
 		eieio\n\
-		stw%U0%X0 %L2,%1"
+		stw%X1 %L2,%1"
 	: "=m" (*ptep), "=m" (*((unsigned char *)ptep+4))
 	: "r" (pte) : "memory");
 
diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
index bb33888151fb0..10d8f5cbb5107 100644
--- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
+++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
@@ -411,82 +411,68 @@ static void rdtgroup_remove(struct rdtgroup *rdtgrp)
 	kfree(rdtgrp);
 }
 
-struct task_move_callback {
-	struct callback_head	work;
-	struct rdtgroup		*rdtgrp;
-};
-
-static void move_myself(struct callback_head *head)
+static void _update_task_closid_rmid(void *task)
 {
-	struct task_move_callback *callback;
-	struct rdtgroup *rdtgrp;
-
-	callback = container_of(head, struct task_move_callback, work);
-	rdtgrp = callback->rdtgrp;
-
 	/*
-	 * If resource group was deleted before this task work callback
-	 * was invoked, then assign the task to root group and free the
-	 * resource group.
+	 * If the task is still current on this CPU, update PQR_ASSOC MSR.
+	 * Otherwise, the MSR is updated when the task is scheduled in.
 	 */
-	if (atomic_dec_and_test(&rdtgrp->waitcount) &&
-	    (rdtgrp->flags & RDT_DELETED)) {
-		current->closid = 0;
-		current->rmid = 0;
-		rdtgroup_remove(rdtgrp);
-	}
-
-	preempt_disable();
-	/* update PQR_ASSOC MSR to make resource group go into effect */
-	intel_rdt_sched_in();
-	preempt_enable();
+	if (task == current)
+		intel_rdt_sched_in();
+}
 
-	kfree(callback);
+static void update_task_closid_rmid(struct task_struct *t)
+{
+	if (IS_ENABLED(CONFIG_SMP) && task_curr(t))
+		smp_call_function_single(task_cpu(t), _update_task_closid_rmid, t, 1);
+	else
+		_update_task_closid_rmid(t);
 }
 
 static int __rdtgroup_move_task(struct task_struct *tsk,
 				struct rdtgroup *rdtgrp)
 {
-	struct task_move_callback *callback;
-	int ret;
-
-	callback = kzalloc(sizeof(*callback), GFP_KERNEL);
-	if (!callback)
-		return -ENOMEM;
-	callback->work.func = move_myself;
-	callback->rdtgrp = rdtgrp;
+	/* If the task is already in rdtgrp, no need to move the task. */
+	if ((rdtgrp->type == RDTCTRL_GROUP && tsk->closid == rdtgrp->closid &&
+	     tsk->rmid == rdtgrp->mon.rmid) ||
+	    (rdtgrp->type == RDTMON_GROUP && tsk->rmid == rdtgrp->mon.rmid &&
+	     tsk->closid == rdtgrp->mon.parent->closid))
+		return 0;
 
 	/*
-	 * Take a refcount, so rdtgrp cannot be freed before the
-	 * callback has been invoked.
+	 * Set the task's closid/rmid before the PQR_ASSOC MSR can be
+	 * updated by them.
+	 *
+	 * For ctrl_mon groups, move both closid and rmid.
+	 * For monitor groups, can move the tasks only from
+	 * their parent CTRL group.
 	 */
-	atomic_inc(&rdtgrp->waitcount);
-	ret = task_work_add(tsk, &callback->work, true);
-	if (ret) {
-		/*
-		 * Task is exiting. Drop the refcount and free the callback.
-		 * No need to check the refcount as the group cannot be
-		 * deleted before the write function unlocks rdtgroup_mutex.
-		 */
-		atomic_dec(&rdtgrp->waitcount);
-		kfree(callback);
-	} else {
-		/*
-		 * For ctrl_mon groups move both closid and rmid.
-		 * For monitor groups, can move the tasks only from
-		 * their parent CTRL group.
-		 */
-		if (rdtgrp->type == RDTCTRL_GROUP) {
-			tsk->closid = rdtgrp->closid;
+
+	if (rdtgrp->type == RDTCTRL_GROUP) {
+		tsk->closid = rdtgrp->closid;
+		tsk->rmid = rdtgrp->mon.rmid;
+	} else if (rdtgrp->type == RDTMON_GROUP) {
+		if (rdtgrp->mon.parent->closid == tsk->closid)
 			tsk->rmid = rdtgrp->mon.rmid;
-		} else if (rdtgrp->type == RDTMON_GROUP) {
-			if (rdtgrp->mon.parent->closid == tsk->closid)
-				tsk->rmid = rdtgrp->mon.rmid;
-			else
-				ret = -EINVAL;
-		}
+		else
+			return -EINVAL;
 	}
-	return ret;
+
+	/*
+	 * Ensure the task's closid and rmid are written before determining if
+	 * the task is current that will decide if it will be interrupted.
+	 */
+	barrier();
+
+	/*
+	 * By now, the task's closid and rmid are set. If the task is current
+	 * on a CPU, the PQR_ASSOC MSR needs to be updated to make the resource
+	 * group go into effect. If the task is not current, the MSR will be
+	 * updated when the task is scheduled in.
+	 */
+	update_task_closid_rmid(tsk);
+
+	return 0;
 }
 
 static int rdtgroup_task_write_permission(struct task_struct *task,
diff --git a/block/genhd.c b/block/genhd.c
index 449ef56bba708..3958ae39daebf 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -208,14 +208,17 @@ struct hd_struct *disk_part_iter_next(struct disk_part_iter *piter)
 		part = rcu_dereference(ptbl->part[piter->idx]);
 		if (!part)
 			continue;
+		get_device(part_to_dev(part));
+		piter->part = part;
 		if (!part_nr_sects_read(part) &&
 		    !(piter->flags & DISK_PITER_INCL_EMPTY) &&
 		    !(piter->flags & DISK_PITER_INCL_EMPTY_PART0 &&
-		      piter->idx == 0))
+		      piter->idx == 0)) {
+			put_device(part_to_dev(part));
+			piter->part = NULL;
 			continue;
+		}
 
-		get_device(part_to_dev(part));
-		piter->part = part;
 		piter->idx += inc;
 		break;
 	}
diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig
index 7b2df7a54d875..01091c08e9999 100644
--- a/drivers/block/Kconfig
+++ b/drivers/block/Kconfig
@@ -477,6 +477,7 @@ config BLK_DEV_RBD
 config BLK_DEV_RSXX
 	tristate "IBM Flash Adapter 900GB Full Height PCIe Device Driver"
 	depends on PCI
+	select CRC32
 	help
 	  Device driver for IBM's high speed PCIe SSD
 	  storage device: Flash Adapter 900GB Full Height.
diff --git a/drivers/cpufreq/powernow-k8.c b/drivers/cpufreq/powernow-k8.c
index 062d71434e470..32bb00a6fe099 100644
--- a/drivers/cpufreq/powernow-k8.c
+++ b/drivers/cpufreq/powernow-k8.c
@@ -887,9 +887,9 @@ static int get_transition_latency(struct powernow_k8_data *data)
 
 /* Take a frequency, and issue the fid/vid transition command */
 static int transition_frequency_fidvid(struct powernow_k8_data *data,
-		unsigned int index)
+		unsigned int index,
+		struct cpufreq_policy *policy)
 {
-	struct cpufreq_policy *policy;
 	u32 fid = 0;
 	u32 vid = 0;
 	int res;
@@ -921,9 +921,6 @@ static int transition_frequency_fidvid(struct powernow_k8_data *data,
 	freqs.old = find_khz_freq_from_fid(data->currfid);
 	freqs.new = find_khz_freq_from_fid(fid);
 
-	policy = cpufreq_cpu_get(smp_processor_id());
-	cpufreq_cpu_put(policy);
-
 	cpufreq_freq_transition_begin(policy, &freqs);
 	res = transition_fid_vid(data, fid, vid);
 	cpufreq_freq_transition_end(policy, &freqs, res);
@@ -978,7 +975,7 @@ static long powernowk8_target_fn(void *arg)
 
 	powernow_k8_acpi_pst_values(data, newstate);
 
-	ret = transition_frequency_fidvid(data, newstate);
+	ret = transition_frequency_fidvid(data, newstate, pol);
 
 	if (ret) {
 		pr_err("transition frequency failed\n");
diff --git a/drivers/dma/xilinx/xilinx_dma.c b/drivers/dma/xilinx/xilinx_dma.c
index 314f175cf8d05..21203e3a54fda 100644
--- a/drivers/dma/xilinx/xilinx_dma.c
+++ b/drivers/dma/xilinx/xilinx_dma.c
@@ -2360,7 +2360,7 @@ static int xilinx_dma_chan_probe(struct xilinx_dma_device *xdev,
 		has_dre = false;
 
 	if (!has_dre)
-		xdev->common.copy_align = fls(width - 1);
+		xdev->common.copy_align = (enum dmaengine_alignment)fls(width - 1);
 
 	if (of_device_is_compatible(node, "xlnx,axi-vdma-mm2s-channel") ||
 	    of_device_is_compatible(node, "xlnx,axi-dma-mm2s-channel") ||
@@ -2637,7 +2637,11 @@ static int xilinx_dma_probe(struct platform_device *pdev)
 	}
 
 	/* Register the DMA engine with the core */
-	dma_async_device_register(&xdev->common);
+	err = dma_async_device_register(&xdev->common);
+	if (err) {
+		dev_err(xdev->dev, "failed to register the dma device\n");
+		goto error;
+	}
 
 	err = of_dma_controller_register(node, of_dma_xilinx_xlate,
 					 xdev);
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index bf13299ebb558..d94fb7acfa556 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -341,7 +341,7 @@ eb_vma_misplaced(const struct drm_i915_gem_exec_object2 *entry,
 		return true;
 
 	if (!(flags & EXEC_OBJECT_SUPPORTS_48B_ADDRESS) &&
-	    (vma->node.start + vma->node.size - 1) >> 32)
+	    (vma->node.start + vma->node.size + 4095) >> 32)
 		return true;
 
 	if (flags & __EXEC_OBJECT_NEEDS_MAP &&
diff --git a/drivers/i2c/busses/i2c-sprd.c b/drivers/i2c/busses/i2c-sprd.c
index 4053259bccb8d..1925c89381194 100644
--- a/drivers/i2c/busses/i2c-sprd.c
+++ b/drivers/i2c/busses/i2c-sprd.c
@@ -71,6 +71,8 @@
 
 /* timeout (ms) for pm runtime autosuspend */
 #define SPRD_I2C_PM_TIMEOUT	1000
+/* timeout (ms) for transfer message */
+#define I2C_XFER_TIMEOUT	1000
 
 /* SPRD i2c data structure */
 struct sprd_i2c {
@@ -244,6 +246,7 @@ static int sprd_i2c_handle_msg(struct i2c_adapter *i2c_adap,
 			       struct i2c_msg *msg, bool is_last_msg)
 {
 	struct sprd_i2c *i2c_dev = i2c_adap->algo_data;
+	unsigned long time_left;
 
 	i2c_dev->msg = msg;
 	i2c_dev->buf = msg->buf;
@@ -273,7 +276,10 @@ static int sprd_i2c_handle_msg(struct i2c_adapter *i2c_adap,
 
 	sprd_i2c_opt_start(i2c_dev);
 
-	wait_for_completion(&i2c_dev->complete);
+	time_left = wait_for_completion_timeout(&i2c_dev->complete,
+				msecs_to_jiffies(I2C_XFER_TIMEOUT));
+	if (!time_left)
+		return -ETIMEDOUT;
 
 	return i2c_dev->err;
 }
diff --git a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c
index e2737dc71b677..0a2c2eace3a25 100644
--- a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c
+++ b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c
@@ -395,13 +395,29 @@ static irqreturn_t st_lsm6dsx_handler_irq(int irq, void *private)
 static irqreturn_t st_lsm6dsx_handler_thread(int irq, void *private)
 {
 	struct st_lsm6dsx_hw *hw = private;
-	int count;
+	int fifo_len = 0, len;
 
-	mutex_lock(&hw->fifo_lock);
-	count = st_lsm6dsx_read_fifo(hw);
-	mutex_unlock(&hw->fifo_lock);
+	/*
+	 * If we are using edge IRQs, new samples can arrive while
+	 * processing current interrupt since there are no hw
+	 * guarantees the irq line stays "low" long enough to properly
+	 * detect the new interrupt. In this case the new sample will
+	 * be missed.
+	 * Polling FIFO status register allow us to read new
+	 * samples even if the interrupt arrives while processing
+	 * previous data and the timeslot where the line is "low" is
+	 * too short to be properly detected.
+	 */
+	do {
+		mutex_lock(&hw->fifo_lock);
+		len = st_lsm6dsx_read_fifo(hw);
+		mutex_unlock(&hw->fifo_lock);
+
+		if (len > 0)
+			fifo_len += len;
+	} while (len > 0);
 
-	return !count ? IRQ_NONE : IRQ_HANDLED;
+	return fifo_len ? IRQ_HANDLED : IRQ_NONE;
 }
 
 static int st_lsm6dsx_buffer_preenable(struct iio_dev *iio_dev)
diff --git a/drivers/iommu/intel_irq_remapping.c b/drivers/iommu/intel_irq_remapping.c
index 09c6b17aaf80e..25e85fdfb9d49 100644
--- a/drivers/iommu/intel_irq_remapping.c
+++ b/drivers/iommu/intel_irq_remapping.c
@@ -1367,6 +1367,8 @@ static int intel_irq_remapping_alloc(struct irq_domain *domain,
 		irq_data = irq_domain_get_irq_data(domain, virq + i);
 		irq_cfg = irqd_cfg(irq_data);
 		if (!irq_data || !irq_cfg) {
+			if (!i)
+				kfree(data);
 			ret = -EINVAL;
 			goto out_free_data;
 		}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
index 4837045ffba37..a53d0c16668a7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
@@ -961,6 +961,7 @@ static int mlx5e_create_inner_ttc_table_groups(struct mlx5e_ttc_table *ttc)
 	in = kvzalloc(inlen, GFP_KERNEL);
 	if (!in) {
 		kfree(ft->g);
+		ft->g = NULL;
 		return -ENOMEM;
 	}
 
@@ -1181,6 +1182,7 @@ static int mlx5e_create_l2_table_groups(struct mlx5e_l2_table *l2_table)
 	in = kvzalloc(inlen, GFP_KERNEL);
 	if (!in) {
 		kfree(ft->g);
+		ft->g = NULL;
 		return -ENOMEM;
 	}
 
@@ -1226,6 +1228,7 @@ err_destroy_groups:
 	ft->g[ft->num_groups] = NULL;
 	mlx5e_destroy_groups(ft);
 	kvfree(in);
+	kfree(ft->g);
 
 	return err;
 }
diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index 97c4c301166c5..eef1412c058d3 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -1128,7 +1128,10 @@ cdc_ncm_fill_tx_frame(struct usbnet *dev, struct sk_buff *skb, __le32 sign)
 	 * accordingly. Otherwise, we should check here.
 	 */
 	if (ctx->drvflags & CDC_NCM_FLAG_NDP_TO_END)
-		delayed_ndp_size = ALIGN(ctx->max_ndp_size, ctx->tx_ndp_modulus);
+		delayed_ndp_size = ctx->max_ndp_size +
+			max_t(u32,
+			      ctx->tx_ndp_modulus,
+			      ctx->tx_modulus + ctx->tx_remainder) - 1;
 	else
 		delayed_ndp_size = 0;
 
@@ -1309,7 +1312,8 @@ cdc_ncm_fill_tx_frame(struct usbnet *dev, struct sk_buff *skb, __le32 sign)
 	if (!(dev->driver_info->flags & FLAG_SEND_ZLP) &&
 	    skb_out->len > ctx->min_tx_pkt) {
 		padding_count = ctx->tx_curr_size - skb_out->len;
-		skb_put_zero(skb_out, padding_count);
+		if (!WARN_ON(padding_count > ctx->tx_curr_size))
+			skb_put_zero(skb_out, padding_count);
 	} else if (skb_out->len < ctx->tx_curr_size &&
 		   (skb_out->len % dev->maxpacket) == 0) {
 		skb_put_u8(skb_out, 0);	/* force short packet */
diff --git a/drivers/net/wan/Kconfig b/drivers/net/wan/Kconfig
index 4e9fe75d70675..069f933b0add2 100644
--- a/drivers/net/wan/Kconfig
+++ b/drivers/net/wan/Kconfig
@@ -295,6 +295,7 @@ config SLIC_DS26522
 	tristate "Slic Maxim ds26522 card support"
 	depends on SPI
 	depends on FSL_SOC || ARCH_MXC || ARCH_LAYERSCAPE || COMPILE_TEST
+	select BITREVERSE
 	help
 	  This module initializes and configures the slic maxim card
 	  in T1 or E1 mode.
diff --git a/drivers/net/wireless/ath/wil6210/Kconfig b/drivers/net/wireless/ath/wil6210/Kconfig
index b448926b0c0ff..27cef55d17a75 100644
--- a/drivers/net/wireless/ath/wil6210/Kconfig
+++ b/drivers/net/wireless/ath/wil6210/Kconfig
@@ -1,6 +1,7 @@
 config WIL6210
 	tristate "Wilocity 60g WiFi card wil6210 support"
 	select WANT_DEV_COREDUMP
+	select CRC32
 	depends on CFG80211
 	depends on PCI
 	default n
diff --git a/drivers/spi/spi-pxa2xx.c b/drivers/spi/spi-pxa2xx.c
index 1579eb2bc29f7..06eb7d259b7f5 100644
--- a/drivers/spi/spi-pxa2xx.c
+++ b/drivers/spi/spi-pxa2xx.c
@@ -1660,7 +1660,7 @@ static int pxa2xx_spi_probe(struct platform_device *pdev)
 		return -ENODEV;
 	}
 
-	master = spi_alloc_master(dev, sizeof(struct driver_data));
+	master = devm_spi_alloc_master(dev, sizeof(*drv_data));
 	if (!master) {
 		dev_err(&pdev->dev, "cannot alloc spi_master\n");
 		pxa_ssp_free(ssp);
@@ -1841,7 +1841,6 @@ out_error_clock_enabled:
 	free_irq(ssp->irq, drv_data);
 
 out_error_master_alloc:
-	spi_master_put(master);
 	pxa_ssp_free(ssp);
 	return status;
 }
diff --git a/drivers/spi/spi-stm32.c b/drivers/spi/spi-stm32.c
index 179749f354c33..d919803540510 100644
--- a/drivers/spi/spi-stm32.c
+++ b/drivers/spi/spi-stm32.c
@@ -299,9 +299,9 @@ static u32 stm32_spi_prepare_fthlv(struct stm32_spi *spi)
 
 	/* align packet size with data registers access */
 	if (spi->cur_bpw > 8)
-		fthlv -= (fthlv % 2); /* multiple of 2 */
+		fthlv += (fthlv % 2) ? 1 : 0;
 	else
-		fthlv -= (fthlv % 4); /* multiple of 4 */
+		fthlv += (fthlv % 4) ? (4 - (fthlv % 4)) : 0;
 
 	return fthlv;
 }
diff --git a/fs/ubifs/io.c b/fs/ubifs/io.c
index 135e95950f513..5b4d4b1087c4d 100644
--- a/fs/ubifs/io.c
+++ b/fs/ubifs/io.c
@@ -331,7 +331,7 @@ void ubifs_pad(const struct ubifs_info *c, void *buf, int pad)
 {
 	uint32_t crc;
 
-	ubifs_assert(pad >= 0 && !(pad & 7));
+	ubifs_assert(pad >= 0);
 
 	if (pad >= UBIFS_PAD_NODE_SZ) {
 		struct ubifs_ch *ch = buf;
@@ -727,6 +727,10 @@ int ubifs_wbuf_write_nolock(struct ubifs_wbuf *wbuf, void *buf, int len)
 		 * write-buffer.
 		 */
 		memcpy(wbuf->buf + wbuf->used, buf, len);
+		if (aligned_len > len) {
+			ubifs_assert(aligned_len - len < 8);
+			ubifs_pad(c, wbuf->buf + wbuf->used + len, aligned_len - len);
+		}
 
 		if (aligned_len == wbuf->avail) {
 			dbg_io("flush jhead %s wbuf to LEB %d:%d",
@@ -819,13 +823,18 @@ int ubifs_wbuf_write_nolock(struct ubifs_wbuf *wbuf, void *buf, int len)
 	}
 
 	spin_lock(&wbuf->lock);
-	if (aligned_len)
+	if (aligned_len) {
 		/*
 		 * And now we have what's left and what does not take whole
 		 * max. write unit, so write it to the write-buffer and we are
 		 * done.
 		 */
 		memcpy(wbuf->buf, buf + written, len);
+		if (aligned_len > len) {
+			ubifs_assert(aligned_len - len < 8);
+			ubifs_pad(c, wbuf->buf + len, aligned_len - len);
+		}
+	}
 
 	if (c->leb_size - wbuf->offs >= c->max_write_size)
 		wbuf->size = c->max_write_size;
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 48e618b20d34b..404a19923ea76 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -459,7 +459,10 @@
  */
 #define TEXT_TEXT							\
 		ALIGN_FUNCTION();					\
-		*(.text.hot TEXT_MAIN .text.fixup .text.unlikely)	\
+		*(.text.hot .text.hot.*)				\
+		*(TEXT_MAIN .text.fixup)				\
+		*(.text.unlikely .text.unlikely.*)			\
+		*(.text.unknown .text.unknown.*)			\
 		*(.text..refcount)					\
 		*(.ref.text)						\
 	MEM_KEEP(init.text)						\
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index cf82d970b0e48..0efdf83f78e7a 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -272,7 +272,8 @@ static int register_vlan_device(struct net_device *real_dev, u16 vlan_id)
 	return 0;
 
 out_free_newdev:
-	if (new_dev->reg_state == NETREG_UNINITIALIZED)
+	if (new_dev->reg_state == NETREG_UNINITIALIZED ||
+	    new_dev->reg_state == NETREG_UNREGISTERED)
 		free_netdev(new_dev);
 	return err;
 }
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index c4f412526dfeb..c062d340cd409 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -1850,6 +1850,12 @@ int pskb_trim_rcsum_slow(struct sk_buff *skb, unsigned int len)
 		skb->csum = csum_block_sub(skb->csum,
 					   skb_checksum(skb, len, delta, 0),
 					   len);
+	} else if (skb->ip_summed == CHECKSUM_PARTIAL) {
+		int hdlen = (len > skb_headlen(skb)) ? skb_headlen(skb) : len;
+		int offset = skb_checksum_start_offset(skb) + skb->csum_offset;
+
+		if (offset + sizeof(__sum16) > hdlen)
+			return -EINVAL;
 	}
 	return __pskb_trim(skb, len);
 }
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 819d51101cbd9..5ec185a9dcaba 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -312,7 +312,7 @@ static int ip_finish_output(struct net *net, struct sock *sk, struct sk_buff *sk
 	if (skb_is_gso(skb))
 		return ip_finish_output_gso(net, sk, skb, mtu);
 
-	if (skb->len > mtu || (IPCB(skb)->flags & IPSKB_FRAG_PMTU))
+	if (skb->len > mtu || IPCB(skb)->frag_max_size)
 		return ip_fragment(net, sk, skb, mtu, ip_finish_output2);
 
 	return ip_finish_output2(net, sk, skb);
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 44cc17c43a6b5..e9cf0d1854595 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -752,7 +752,11 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 		goto tx_error;
 	}
 
-	if (tnl_update_pmtu(dev, skb, rt, tnl_params->frag_off, inner_iph)) {
+	df = tnl_params->frag_off;
+	if (skb->protocol == htons(ETH_P_IP) && !tunnel->ignore_df)
+		df |= (inner_iph->frag_off & htons(IP_DF));
+
+	if (tnl_update_pmtu(dev, skb, rt, df, inner_iph)) {
 		ip_rt_put(rt);
 		goto tx_error;
 	}
@@ -780,10 +784,6 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 			ttl = ip4_dst_hoplimit(&rt->dst);
 	}
 
-	df = tnl_params->frag_off;
-	if (skb->protocol == htons(ETH_P_IP) && !tunnel->ignore_df)
-		df |= (inner_iph->frag_off&htons(IP_DF));
-
 	max_headroom = LL_RESERVED_SPACE(rt->dst.dev) + sizeof(struct iphdr)
 			+ rt->dst.header_len + ip_encap_hlen(&tunnel->encap);
 	if (max_headroom > dev->needed_headroom)