diff --git a/Makefile b/Makefile
index e75c75f0ec35..41efc3d9f2e0 100644
--- a/Makefile
+++ b/Makefile
@@ -1,6 +1,6 @@
 VERSION = 3
 PATCHLEVEL = 16
-SUBLEVEL = 4
+SUBLEVEL = 5
 EXTRAVERSION =
 NAME = Museum of Fishiegoodies
 
diff --git a/arch/ia64/pci/fixup.c b/arch/ia64/pci/fixup.c
index 1fe9aa5068ea..fc505d58f078 100644
--- a/arch/ia64/pci/fixup.c
+++ b/arch/ia64/pci/fixup.c
@@ -6,6 +6,7 @@
 #include <linux/pci.h>
 #include <linux/init.h>
 #include <linux/vgaarb.h>
+#include <linux/screen_info.h>
 
 #include <asm/machvec.h>
 
@@ -61,8 +62,7 @@ static void pci_fixup_video(struct pci_dev *pdev)
 		pci_read_config_word(pdev, PCI_COMMAND, &config);
 		if (config & (PCI_COMMAND_IO | PCI_COMMAND_MEMORY)) {
 			pdev->resource[PCI_ROM_RESOURCE].flags |= IORESOURCE_ROM_SHADOW;
-			dev_printk(KERN_DEBUG, &pdev->dev, "Boot video device\n");
-			vga_set_default_device(pdev);
+			dev_printk(KERN_DEBUG, &pdev->dev, "Video device with shadowed ROM\n");
 		}
 	}
 }
diff --git a/arch/x86/include/asm/vga.h b/arch/x86/include/asm/vga.h
index 44282fbf7bf9..c4b9dc2f67c5 100644
--- a/arch/x86/include/asm/vga.h
+++ b/arch/x86/include/asm/vga.h
@@ -17,10 +17,4 @@
 #define vga_readb(x) (*(x))
 #define vga_writeb(x, y) (*(y) = (x))
 
-#ifdef CONFIG_FB_EFI
-#define __ARCH_HAS_VGA_DEFAULT_DEVICE
-extern struct pci_dev *vga_default_device(void);
-extern void vga_set_default_device(struct pci_dev *pdev);
-#endif
-
 #endif /* _ASM_X86_VGA_H */
diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c
index b5e60268d93f..9a2b7101ae8a 100644
--- a/arch/x86/pci/fixup.c
+++ b/arch/x86/pci/fixup.c
@@ -350,8 +350,7 @@ static void pci_fixup_video(struct pci_dev *pdev)
 		pci_read_config_word(pdev, PCI_COMMAND, &config);
 		if (config & (PCI_COMMAND_IO | PCI_COMMAND_MEMORY)) {
 			pdev->resource[PCI_ROM_RESOURCE].flags |= IORESOURCE_ROM_SHADOW;
-			dev_printk(KERN_DEBUG, &pdev->dev, "Boot video device\n");
-			vga_set_default_device(pdev);
+			dev_printk(KERN_DEBUG, &pdev->dev, "Video device with shadowed ROM\n");
 		}
 	}
 }
diff --git a/drivers/cpufreq/integrator-cpufreq.c b/drivers/cpufreq/integrator-cpufreq.c
index e5122f1bfe78..302eb5c55d01 100644
--- a/drivers/cpufreq/integrator-cpufreq.c
+++ b/drivers/cpufreq/integrator-cpufreq.c
@@ -213,9 +213,9 @@ static int __init integrator_cpufreq_probe(struct platform_device *pdev)
 	return cpufreq_register_driver(&integrator_driver);
 }
 
-static void __exit integrator_cpufreq_remove(struct platform_device *pdev)
+static int __exit integrator_cpufreq_remove(struct platform_device *pdev)
 {
-	cpufreq_unregister_driver(&integrator_driver);
+	return cpufreq_unregister_driver(&integrator_driver);
 }
 
 static const struct of_device_id integrator_cpufreq_match[] = {
diff --git a/drivers/cpufreq/pcc-cpufreq.c b/drivers/cpufreq/pcc-cpufreq.c
index 728a2d879499..4d2c8e861089 100644
--- a/drivers/cpufreq/pcc-cpufreq.c
+++ b/drivers/cpufreq/pcc-cpufreq.c
@@ -204,7 +204,6 @@ static int pcc_cpufreq_target(struct cpufreq_policy *policy,
 	u32 input_buffer;
 	int cpu;
 
-	spin_lock(&pcc_lock);
 	cpu = policy->cpu;
 	pcc_cpu_data = per_cpu_ptr(pcc_cpu_info, cpu);
 
@@ -216,6 +215,7 @@ static int pcc_cpufreq_target(struct cpufreq_policy *policy,
 	freqs.old = policy->cur;
 	freqs.new = target_freq;
 	cpufreq_freq_transition_begin(policy, &freqs);
+	spin_lock(&pcc_lock);
 
 	input_buffer = 0x1 | (((target_freq * 100)
 			       / (ioread32(&pcch_hdr->nominal) * 1000)) << 8);
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 8b3cde703364..8faabb95cd65 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -1297,6 +1297,16 @@ void i915_check_and_clear_faults(struct drm_device *dev)
 	POSTING_READ(RING_FAULT_REG(&dev_priv->ring[RCS]));
 }
 
+static void i915_ggtt_flush(struct drm_i915_private *dev_priv)
+{
+	if (INTEL_INFO(dev_priv->dev)->gen < 6) {
+		intel_gtt_chipset_flush();
+	} else {
+		I915_WRITE(GFX_FLSH_CNTL_GEN6, GFX_FLSH_CNTL_EN);
+		POSTING_READ(GFX_FLSH_CNTL_GEN6);
+	}
+}
+
 void i915_gem_suspend_gtt_mappings(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -1313,6 +1323,8 @@ void i915_gem_suspend_gtt_mappings(struct drm_device *dev)
 				       dev_priv->gtt.base.start,
 				       dev_priv->gtt.base.total,
 				       true);
+
+	i915_ggtt_flush(dev_priv);
 }
 
 void i915_gem_restore_gtt_mappings(struct drm_device *dev)
@@ -1365,7 +1377,7 @@ void i915_gem_restore_gtt_mappings(struct drm_device *dev)
 		gen6_write_pdes(container_of(vm, struct i915_hw_ppgtt, base));
 	}
 
-	i915_gem_chipset_flush(dev);
+	i915_ggtt_flush(dev_priv);
 }
 
 int i915_gem_gtt_prepare_object(struct drm_i915_gem_object *obj)
diff --git a/drivers/gpu/drm/i915/intel_opregion.c b/drivers/gpu/drm/i915/intel_opregion.c
index 4f6b53998d79..b9135dc3fe5d 100644
--- a/drivers/gpu/drm/i915/intel_opregion.c
+++ b/drivers/gpu/drm/i915/intel_opregion.c
@@ -395,6 +395,16 @@ int intel_opregion_notify_adapter(struct drm_device *dev, pci_power_t state)
 	return -EINVAL;
 }
 
+/*
+ * If the vendor backlight interface is not in use and ACPI backlight interface
+ * is broken, do not bother processing backlight change requests from firmware.
+ */
+static bool should_ignore_backlight_request(void)
+{
+	return acpi_video_backlight_support() &&
+	       !acpi_video_verify_backlight_support();
+}
+
 static u32 asle_set_backlight(struct drm_device *dev, u32 bclp)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -403,11 +413,7 @@ static u32 asle_set_backlight(struct drm_device *dev, u32 bclp)
 
 	DRM_DEBUG_DRIVER("bclp = 0x%08x\n", bclp);
 
-	/*
-	 * If the acpi_video interface is not supposed to be used, don't
-	 * bother processing backlight level change requests from firmware.
-	 */
-	if (!acpi_video_verify_backlight_support()) {
+	if (should_ignore_backlight_request()) {
 		DRM_DEBUG_KMS("opregion backlight request ignored\n");
 		return 0;
 	}
diff --git a/drivers/gpu/vga/vgaarb.c b/drivers/gpu/vga/vgaarb.c
index af0259708358..366641d0483f 100644
--- a/drivers/gpu/vga/vgaarb.c
+++ b/drivers/gpu/vga/vgaarb.c
@@ -41,6 +41,7 @@
 #include <linux/poll.h>
 #include <linux/miscdevice.h>
 #include <linux/slab.h>
+#include <linux/screen_info.h>
 
 #include <linux/uaccess.h>
 
@@ -580,8 +581,11 @@ static bool vga_arbiter_add_pci_device(struct pci_dev *pdev)
 	 */
 #ifndef __ARCH_HAS_VGA_DEFAULT_DEVICE
 	if (vga_default == NULL &&
-	    ((vgadev->owns & VGA_RSRC_LEGACY_MASK) == VGA_RSRC_LEGACY_MASK))
+	    ((vgadev->owns & VGA_RSRC_LEGACY_MASK) == VGA_RSRC_LEGACY_MASK)) {
+		pr_info("vgaarb: setting as boot device: PCI:%s\n",
+			pci_name(pdev));
 		vga_set_default_device(pdev);
+	}
 #endif
 
 	vga_arbiter_check_bridge_sharing(vgadev);
@@ -1316,6 +1320,38 @@ static int __init vga_arb_device_init(void)
 	pr_info("vgaarb: loaded\n");
 
 	list_for_each_entry(vgadev, &vga_list, list) {
+#if defined(CONFIG_X86) || defined(CONFIG_IA64)
+		/* Override I/O based detection done by vga_arbiter_add_pci_device()
+		 * as it may take the wrong device (e.g. on Apple system under EFI).
+		 *
+		 * Select the device owning the boot framebuffer if there is one.
+		 */
+		resource_size_t start, end;
+		int i;
+
+		/* Does firmware framebuffer belong to us? */
+		for (i = 0; i < DEVICE_COUNT_RESOURCE; i++) {
+			if (!(pci_resource_flags(vgadev->pdev, i) & IORESOURCE_MEM))
+				continue;
+
+			start = pci_resource_start(vgadev->pdev, i);
+			end  = pci_resource_end(vgadev->pdev, i);
+
+			if (!start || !end)
+				continue;
+
+			if (screen_info.lfb_base < start ||
+			    (screen_info.lfb_base + screen_info.lfb_size) >= end)
+				continue;
+			if (!vga_default_device())
+				pr_info("vgaarb: setting as boot device: PCI:%s\n",
+					pci_name(vgadev->pdev));
+			else if (vgadev->pdev != vga_default_device())
+				pr_info("vgaarb: overriding boot device: PCI:%s\n",
+					pci_name(vgadev->pdev));
+			vga_set_default_device(vgadev->pdev);
+		}
+#endif
 		if (vgadev->bridge_has_one_vga)
 			pr_info("vgaarb: bridge control possible %s\n", pci_name(vgadev->pdev));
 		else
diff --git a/drivers/i2c/busses/i2c-qup.c b/drivers/i2c/busses/i2c-qup.c
index 2a5efb5b487c..eb47c98131ec 100644
--- a/drivers/i2c/busses/i2c-qup.c
+++ b/drivers/i2c/busses/i2c-qup.c
@@ -670,16 +670,20 @@ static int qup_i2c_probe(struct platform_device *pdev)
 	qup->adap.dev.of_node = pdev->dev.of_node;
 	strlcpy(qup->adap.name, "QUP I2C adapter", sizeof(qup->adap.name));
 
-	ret = i2c_add_adapter(&qup->adap);
-	if (ret)
-		goto fail;
-
 	pm_runtime_set_autosuspend_delay(qup->dev, MSEC_PER_SEC);
 	pm_runtime_use_autosuspend(qup->dev);
 	pm_runtime_set_active(qup->dev);
 	pm_runtime_enable(qup->dev);
+
+	ret = i2c_add_adapter(&qup->adap);
+	if (ret)
+		goto fail_runtime;
+
 	return 0;
 
+fail_runtime:
+	pm_runtime_disable(qup->dev);
+	pm_runtime_set_suspended(qup->dev);
 fail:
 	qup_i2c_disable_clocks(qup);
 	return ret;
diff --git a/drivers/i2c/busses/i2c-rk3x.c b/drivers/i2c/busses/i2c-rk3x.c
index 93cfc837200b..b38b0529946a 100644
--- a/drivers/i2c/busses/i2c-rk3x.c
+++ b/drivers/i2c/busses/i2c-rk3x.c
@@ -238,7 +238,7 @@ static void rk3x_i2c_fill_transmit_buf(struct rk3x_i2c *i2c)
 	for (i = 0; i < 8; ++i) {
 		val = 0;
 		for (j = 0; j < 4; ++j) {
-			if (i2c->processed == i2c->msg->len)
+			if ((i2c->processed == i2c->msg->len) && (cnt != 0))
 				break;
 
 			if (i2c->processed == 0 && cnt == 0)
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 183588b11fc1..9f0fbecd1eb5 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -64,6 +64,10 @@
 #define cpu_to_group(cpu) cpu_to_node(cpu)
 #define ANY_GROUP NUMA_NO_NODE
 
+static bool devices_handle_discard_safely = false;
+module_param(devices_handle_discard_safely, bool, 0644);
+MODULE_PARM_DESC(devices_handle_discard_safely,
+		 "Set to Y if all devices in each array reliably return zeroes on reads from discarded regions");
 static struct workqueue_struct *raid5_wq;
 /*
  * Stripe cache
@@ -6208,7 +6212,7 @@ static int run(struct mddev *mddev)
 		mddev->queue->limits.discard_granularity = stripe;
 		/*
 		 * unaligned part of discard request will be ignored, so can't
-		 * guarantee discard_zerors_data
+		 * guarantee discard_zeroes_data
 		 */
 		mddev->queue->limits.discard_zeroes_data = 0;
 
@@ -6233,6 +6237,18 @@ static int run(struct mddev *mddev)
 			    !bdev_get_queue(rdev->bdev)->
 						limits.discard_zeroes_data)
 				discard_supported = false;
+			/* Unfortunately, discard_zeroes_data is not currently
+			 * a guarantee - just a hint.  So we only allow DISCARD
+			 * if the sysadmin has confirmed that only safe devices
+			 * are in use by setting a module parameter.
+			 */
+			if (!devices_handle_discard_safely) {
+				if (discard_supported) {
+					pr_info("md/raid456: discard support disabled due to uncertainty.\n");
+					pr_info("Set raid456.devices_handle_discard_safely=Y to override.\n");
+				}
+				discard_supported = false;
+			}
 		}
 
 		if (discard_supported &&
diff --git a/drivers/media/v4l2-core/videobuf2-core.c b/drivers/media/v4l2-core/videobuf2-core.c
index dcdceae30ab0..a946523772d6 100644
--- a/drivers/media/v4l2-core/videobuf2-core.c
+++ b/drivers/media/v4l2-core/videobuf2-core.c
@@ -967,6 +967,7 @@ static int __reqbufs(struct vb2_queue *q, struct v4l2_requestbuffers *req)
 	 * to the userspace.
 	 */
 	req->count = allocated_buffers;
+	q->waiting_for_buffers = !V4L2_TYPE_IS_OUTPUT(q->type);
 
 	return 0;
 }
@@ -1014,6 +1015,7 @@ static int __create_bufs(struct vb2_queue *q, struct v4l2_create_buffers *create
 		memset(q->plane_sizes, 0, sizeof(q->plane_sizes));
 		memset(q->alloc_ctx, 0, sizeof(q->alloc_ctx));
 		q->memory = create->memory;
+		q->waiting_for_buffers = !V4L2_TYPE_IS_OUTPUT(q->type);
 	}
 
 	num_buffers = min(create->count, VIDEO_MAX_FRAME - q->num_buffers);
@@ -1812,6 +1814,7 @@ static int vb2_internal_qbuf(struct vb2_queue *q, struct v4l2_buffer *b)
 	 */
 	list_add_tail(&vb->queued_entry, &q->queued_list);
 	q->queued_count++;
+	q->waiting_for_buffers = false;
 	vb->state = VB2_BUF_STATE_QUEUED;
 	if (V4L2_TYPE_IS_OUTPUT(q->type)) {
 		/*
@@ -2244,6 +2247,7 @@ static int vb2_internal_streamoff(struct vb2_queue *q, enum v4l2_buf_type type)
 	 * their normal dequeued state.
 	 */
 	__vb2_queue_cancel(q);
+	q->waiting_for_buffers = !V4L2_TYPE_IS_OUTPUT(q->type);
 
 	dprintk(3, "successful\n");
 	return 0;
@@ -2562,9 +2566,16 @@ unsigned int vb2_poll(struct vb2_queue *q, struct file *file, poll_table *wait)
 	}
 
 	/*
-	 * There is nothing to wait for if no buffers have already been queued.
+	 * There is nothing to wait for if the queue isn't streaming.
 	 */
-	if (list_empty(&q->queued_list))
+	if (!vb2_is_streaming(q))
+		return res | POLLERR;
+	/*
+	 * For compatibility with vb1: if QBUF hasn't been called yet, then
+	 * return POLLERR as well. This only affects capture queues, output
+	 * queues will always initialize waiting_for_buffers to false.
+	 */
+	if (q->waiting_for_buffers)
 		return res | POLLERR;
 
 	if (list_empty(&q->done_list))
diff --git a/drivers/usb/storage/uas-detect.h b/drivers/usb/storage/uas-detect.h
index bb05b984d5f6..8a6f371ed6e7 100644
--- a/drivers/usb/storage/uas-detect.h
+++ b/drivers/usb/storage/uas-detect.h
@@ -9,32 +9,15 @@ static int uas_is_interface(struct usb_host_interface *intf)
 		intf->desc.bInterfaceProtocol == USB_PR_UAS);
 }
 
-static int uas_isnt_supported(struct usb_device *udev)
-{
-	struct usb_hcd *hcd = bus_to_hcd(udev->bus);
-
-	dev_warn(&udev->dev, "The driver for the USB controller %s does not "
-			"support scatter-gather which is\n",
-			hcd->driver->description);
-	dev_warn(&udev->dev, "required by the UAS driver. Please try an"
-			"alternative USB controller if you wish to use UAS.\n");
-	return -ENODEV;
-}
-
 static int uas_find_uas_alt_setting(struct usb_interface *intf)
 {
 	int i;
-	struct usb_device *udev = interface_to_usbdev(intf);
-	int sg_supported = udev->bus->sg_tablesize != 0;
 
 	for (i = 0; i < intf->num_altsetting; i++) {
 		struct usb_host_interface *alt = &intf->altsetting[i];
 
-		if (uas_is_interface(alt)) {
-			if (!sg_supported)
-				return uas_isnt_supported(udev);
+		if (uas_is_interface(alt))
 			return alt->desc.bAlternateSetting;
-		}
 	}
 
 	return -ENODEV;
@@ -76,13 +59,6 @@ static int uas_use_uas_driver(struct usb_interface *intf,
 	unsigned long flags = id->driver_info;
 	int r, alt;
 
-	usb_stor_adjust_quirks(udev, &flags);
-
-	if (flags & US_FL_IGNORE_UAS)
-		return 0;
-
-	if (udev->speed >= USB_SPEED_SUPER && !hcd->can_do_streams)
-		return 0;
 
 	alt = uas_find_uas_alt_setting(intf);
 	if (alt < 0)
@@ -92,5 +68,46 @@ static int uas_use_uas_driver(struct usb_interface *intf,
 	if (r < 0)
 		return 0;
 
+	/*
+	 * ASM1051 and older ASM1053 devices have the same usb-id, and UAS is
+	 * broken on the ASM1051, use the number of streams to differentiate.
+	 * New ASM1053-s also support 32 streams, but have a different prod-id.
+	 */
+	if (le16_to_cpu(udev->descriptor.idVendor) == 0x174c &&
+			le16_to_cpu(udev->descriptor.idProduct) == 0x55aa) {
+		if (udev->speed < USB_SPEED_SUPER) {
+			/* No streams info, assume ASM1051 */
+			flags |= US_FL_IGNORE_UAS;
+		} else if (usb_ss_max_streams(&eps[1]->ss_ep_comp) == 32) {
+			flags |= US_FL_IGNORE_UAS;
+		}
+	}
+
+	usb_stor_adjust_quirks(udev, &flags);
+
+	if (flags & US_FL_IGNORE_UAS) {
+		dev_warn(&udev->dev,
+			"UAS is blacklisted for this device, using usb-storage instead\n");
+		return 0;
+	}
+
+	if (udev->bus->sg_tablesize == 0) {
+		dev_warn(&udev->dev,
+			"The driver for the USB controller %s does not support scatter-gather which is\n",
+			hcd->driver->description);
+		dev_warn(&udev->dev,
+			"required by the UAS driver. Please try an other USB controller if you wish to use UAS.\n");
+		return 0;
+	}
+
+	if (udev->speed >= USB_SPEED_SUPER && !hcd->can_do_streams) {
+		dev_warn(&udev->dev,
+			"USB controller %s does not support streams, which are required by the UAS driver.\n",
+			hcd_to_bus(hcd)->bus_name);
+		dev_warn(&udev->dev,
+			"Please try an other USB controller if you wish to use UAS.\n");
+		return 0;
+	}
+
 	return 1;
 }
diff --git a/drivers/video/fbdev/efifb.c b/drivers/video/fbdev/efifb.c
index ae9618ff6735..982f6abe6faf 100644
--- a/drivers/video/fbdev/efifb.c
+++ b/drivers/video/fbdev/efifb.c
@@ -19,8 +19,6 @@
 
 static bool request_mem_succeeded = false;
 
-static struct pci_dev *default_vga;
-
 static struct fb_var_screeninfo efifb_defined = {
 	.activate		= FB_ACTIVATE_NOW,
 	.height			= -1,
@@ -84,23 +82,10 @@ static struct fb_ops efifb_ops = {
 	.fb_imageblit	= cfb_imageblit,
 };
 
-struct pci_dev *vga_default_device(void)
-{
-	return default_vga;
-}
-
-EXPORT_SYMBOL_GPL(vga_default_device);
-
-void vga_set_default_device(struct pci_dev *pdev)
-{
-	default_vga = pdev;
-}
-
 static int efifb_setup(char *options)
 {
 	char *this_opt;
 	int i;
-	struct pci_dev *dev = NULL;
 
 	if (options && *options) {
 		while ((this_opt = strsep(&options, ",")) != NULL) {
@@ -126,30 +111,6 @@ static int efifb_setup(char *options)
 		}
 	}
 
-	for_each_pci_dev(dev) {
-		int i;
-
-		if ((dev->class >> 8) != PCI_CLASS_DISPLAY_VGA)
-			continue;
-
-		for (i=0; i < DEVICE_COUNT_RESOURCE; i++) {
-			resource_size_t start, end;
-
-			if (!(pci_resource_flags(dev, i) & IORESOURCE_MEM))
-				continue;
-
-			start = pci_resource_start(dev, i);
-			end  = pci_resource_end(dev, i);
-
-			if (!start || !end)
-				continue;
-
-			if (screen_info.lfb_base >= start &&
-			    (screen_info.lfb_base + screen_info.lfb_size) < end)
-				default_vga = dev;
-		}
-	}
-
 	return 0;
 }
 
diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c
index 84ca0a4caaeb..e9ad8d37bb00 100644
--- a/fs/cifs/smb1ops.c
+++ b/fs/cifs/smb1ops.c
@@ -586,7 +586,7 @@ cifs_query_path_info(const unsigned int xid, struct cifs_tcon *tcon,
 		tmprc = CIFS_open(xid, &oparms, &oplock, NULL);
 		if (tmprc == -EOPNOTSUPP)
 			*symlink = true;
-		else
+		else if (tmprc == 0)
 			CIFSSMBClose(xid, tcon, fid.netfid);
 	}
 
diff --git a/fs/cifs/smb2maperror.c b/fs/cifs/smb2maperror.c
index a689514e260f..a491814cb2c0 100644
--- a/fs/cifs/smb2maperror.c
+++ b/fs/cifs/smb2maperror.c
@@ -256,6 +256,8 @@ static const struct status_to_posix_error smb2_error_map_table[] = {
 	{STATUS_DLL_MIGHT_BE_INCOMPATIBLE, -EIO,
 	"STATUS_DLL_MIGHT_BE_INCOMPATIBLE"},
 	{STATUS_STOPPED_ON_SYMLINK, -EOPNOTSUPP, "STATUS_STOPPED_ON_SYMLINK"},
+	{STATUS_IO_REPARSE_TAG_NOT_HANDLED, -EOPNOTSUPP,
+	"STATUS_REPARSE_NOT_HANDLED"},
 	{STATUS_DEVICE_REQUIRES_CLEANING, -EIO,
 	"STATUS_DEVICE_REQUIRES_CLEANING"},
 	{STATUS_DEVICE_DOOR_OPEN, -EIO, "STATUS_DEVICE_DOOR_OPEN"},
diff --git a/fs/udf/inode.c b/fs/udf/inode.c
index 236cd48184c2..a932f7740b51 100644
--- a/fs/udf/inode.c
+++ b/fs/udf/inode.c
@@ -1271,13 +1271,22 @@ update_time:
 	return 0;
 }
 
+/*
+ * Maximum length of linked list formed by ICB hierarchy. The chosen number is
+ * arbitrary - just that we hopefully don't limit any real use of rewritten
+ * inode on write-once media but avoid looping for too long on corrupted media.
+ */
+#define UDF_MAX_ICB_NESTING 1024
+
 static void __udf_read_inode(struct inode *inode)
 {
 	struct buffer_head *bh = NULL;
 	struct fileEntry *fe;
 	uint16_t ident;
 	struct udf_inode_info *iinfo = UDF_I(inode);
+	unsigned int indirections = 0;
 
+reread:
 	/*
 	 * Set defaults, but the inode is still incomplete!
 	 * Note: get_new_inode() sets the following on a new inode:
@@ -1314,28 +1323,26 @@ static void __udf_read_inode(struct inode *inode)
 		ibh = udf_read_ptagged(inode->i_sb, &iinfo->i_location, 1,
 					&ident);
 		if (ident == TAG_IDENT_IE && ibh) {
-			struct buffer_head *nbh = NULL;
 			struct kernel_lb_addr loc;
 			struct indirectEntry *ie;
 
 			ie = (struct indirectEntry *)ibh->b_data;
 			loc = lelb_to_cpu(ie->indirectICB.extLocation);
 
-			if (ie->indirectICB.extLength &&
-				(nbh = udf_read_ptagged(inode->i_sb, &loc, 0,
-							&ident))) {
-				if (ident == TAG_IDENT_FE ||
-					ident == TAG_IDENT_EFE) {
-					memcpy(&iinfo->i_location,
-						&loc,
-						sizeof(struct kernel_lb_addr));
-					brelse(bh);
-					brelse(ibh);
-					brelse(nbh);
-					__udf_read_inode(inode);
+			if (ie->indirectICB.extLength) {
+				brelse(bh);
+				brelse(ibh);
+				memcpy(&iinfo->i_location, &loc,
+				       sizeof(struct kernel_lb_addr));
+				if (++indirections > UDF_MAX_ICB_NESTING) {
+					udf_err(inode->i_sb,
+						"too many ICBs in ICB hierarchy"
+						" (max %d supported)\n",
+						UDF_MAX_ICB_NESTING);
+					make_bad_inode(inode);
 					return;
 				}
-				brelse(nbh);
+				goto reread;
 			}
 		}
 		brelse(ibh);
diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h
index 1f44466c1e9d..c367cbdf73ab 100644
--- a/include/linux/jiffies.h
+++ b/include/linux/jiffies.h
@@ -258,23 +258,11 @@ extern unsigned long preset_lpj;
 #define SEC_JIFFIE_SC (32 - SHIFT_HZ)
 #endif
 #define NSEC_JIFFIE_SC (SEC_JIFFIE_SC + 29)
-#define USEC_JIFFIE_SC (SEC_JIFFIE_SC + 19)
 #define SEC_CONVERSION ((unsigned long)((((u64)NSEC_PER_SEC << SEC_JIFFIE_SC) +\
                                 TICK_NSEC -1) / (u64)TICK_NSEC))
 
 #define NSEC_CONVERSION ((unsigned long)((((u64)1 << NSEC_JIFFIE_SC) +\
                                         TICK_NSEC -1) / (u64)TICK_NSEC))
-#define USEC_CONVERSION  \
-                    ((unsigned long)((((u64)NSEC_PER_USEC << USEC_JIFFIE_SC) +\
-                                        TICK_NSEC -1) / (u64)TICK_NSEC))
-/*
- * USEC_ROUND is used in the timeval to jiffie conversion.  See there
- * for more details.  It is the scaled resolution rounding value.  Note
- * that it is a 64-bit value.  Since, when it is applied, we are already
- * in jiffies (albit scaled), it is nothing but the bits we will shift
- * off.
- */
-#define USEC_ROUND (u64)(((u64)1 << USEC_JIFFIE_SC) - 1)
 /*
  * The maximum jiffie value is (MAX_INT >> 1).  Here we translate that
  * into seconds.  The 64-bit case will overflow if we are not careful,
diff --git a/include/media/videobuf2-core.h b/include/media/videobuf2-core.h
index 8fab6fa0dbfb..d6f010c17f4a 100644
--- a/include/media/videobuf2-core.h
+++ b/include/media/videobuf2-core.h
@@ -375,6 +375,9 @@ struct v4l2_fh;
  * @streaming:	current streaming state
  * @start_streaming_called: start_streaming() was called successfully and we
  *		started streaming.
+ * @waiting_for_buffers: used in poll() to check if vb2 is still waiting for
+ *		buffers. Only set for capture queues if qbuf has not yet been
+ *		called since poll() needs to return POLLERR in that situation.
  * @fileio:	file io emulator internal data, used only if emulator is active
  * @threadio:	thread io internal data, used only if thread is active
  */
@@ -411,6 +414,7 @@ struct vb2_queue {
 
 	unsigned int			streaming:1;
 	unsigned int			start_streaming_called:1;
+	unsigned int			waiting_for_buffers:1;
 
 	struct vb2_fileio_data		*fileio;
 	struct vb2_threadio_data	*threadio;
diff --git a/init/Kconfig b/init/Kconfig
index 9d76b99af1b9..35685a46e4da 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1432,6 +1432,7 @@ config FUTEX
 
 config HAVE_FUTEX_CMPXCHG
 	bool
+	depends on FUTEX
 	help
 	  Architectures should select this if futex_atomic_cmpxchg_inatomic()
 	  is implemented and always working. This removes a couple of runtime
diff --git a/kernel/events/core.c b/kernel/events/core.c
index f626c9f1f3c0..2065959042ea 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7921,8 +7921,10 @@ int perf_event_init_task(struct task_struct *child)
 
 	for_each_task_context_nr(ctxn) {
 		ret = perf_event_init_context(child, ctxn);
-		if (ret)
+		if (ret) {
+			perf_event_free_task(child);
 			return ret;
+		}
 	}
 
 	return 0;
diff --git a/kernel/fork.c b/kernel/fork.c
index 6a13c46cd87d..b41958b0cb67 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1326,7 +1326,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 		goto bad_fork_cleanup_policy;
 	retval = audit_alloc(p);
 	if (retval)
-		goto bad_fork_cleanup_policy;
+		goto bad_fork_cleanup_perf;
 	/* copy all the process information */
 	retval = copy_semundo(clone_flags, p);
 	if (retval)
@@ -1525,8 +1525,9 @@ bad_fork_cleanup_semundo:
 	exit_sem(p);
 bad_fork_cleanup_audit:
 	audit_free(p);
-bad_fork_cleanup_policy:
+bad_fork_cleanup_perf:
 	perf_event_free_task(p);
+bad_fork_cleanup_policy:
 #ifdef CONFIG_NUMA
 	mpol_put(p->mempolicy);
 bad_fork_cleanup_threadgroup_lock:
diff --git a/kernel/time.c b/kernel/time.c
index 7c7964c33ae7..3c49ab45f822 100644
--- a/kernel/time.c
+++ b/kernel/time.c
@@ -496,17 +496,20 @@ EXPORT_SYMBOL(usecs_to_jiffies);
  * that a remainder subtract here would not do the right thing as the
  * resolution values don't fall on second boundries.  I.e. the line:
  * nsec -= nsec % TICK_NSEC; is NOT a correct resolution rounding.
+ * Note that due to the small error in the multiplier here, this
+ * rounding is incorrect for sufficiently large values of tv_nsec, but
+ * well formed timespecs should have tv_nsec < NSEC_PER_SEC, so we're
+ * OK.
  *
  * Rather, we just shift the bits off the right.
  *
  * The >> (NSEC_JIFFIE_SC - SEC_JIFFIE_SC) converts the scaled nsec
  * value to a scaled second value.
  */
-unsigned long
-timespec_to_jiffies(const struct timespec *value)
+static unsigned long
+__timespec_to_jiffies(unsigned long sec, long nsec)
 {
-	unsigned long sec = value->tv_sec;
-	long nsec = value->tv_nsec + TICK_NSEC - 1;
+	nsec = nsec + TICK_NSEC - 1;
 
 	if (sec >= MAX_SEC_IN_JIFFIES){
 		sec = MAX_SEC_IN_JIFFIES;
@@ -517,6 +520,13 @@ timespec_to_jiffies(const struct timespec *value)
 		 (NSEC_JIFFIE_SC - SEC_JIFFIE_SC))) >> SEC_JIFFIE_SC;
 
 }
+
+unsigned long
+timespec_to_jiffies(const struct timespec *value)
+{
+	return __timespec_to_jiffies(value->tv_sec, value->tv_nsec);
+}
+
 EXPORT_SYMBOL(timespec_to_jiffies);
 
 void
@@ -533,31 +543,27 @@ jiffies_to_timespec(const unsigned long jiffies, struct timespec *value)
 }
 EXPORT_SYMBOL(jiffies_to_timespec);
 
-/* Same for "timeval"
+/*
+ * We could use a similar algorithm to timespec_to_jiffies (with a
+ * different multiplier for usec instead of nsec). But this has a
+ * problem with rounding: we can't exactly add TICK_NSEC - 1 to the
+ * usec value, since it's not necessarily integral.
  *
- * Well, almost.  The problem here is that the real system resolution is
- * in nanoseconds and the value being converted is in micro seconds.
- * Also for some machines (those that use HZ = 1024, in-particular),
- * there is a LARGE error in the tick size in microseconds.
-
- * The solution we use is to do the rounding AFTER we convert the
- * microsecond part.  Thus the USEC_ROUND, the bits to be shifted off.
- * Instruction wise, this should cost only an additional add with carry
- * instruction above the way it was done above.
+ * We could instead round in the intermediate scaled representation
+ * (i.e. in units of 1/2^(large scale) jiffies) but that's also
+ * perilous: the scaling introduces a small positive error, which
+ * combined with a division-rounding-upward (i.e. adding 2^(scale) - 1
+ * units to the intermediate before shifting) leads to accidental
+ * overflow and overestimates.
+ *
+ * At the cost of one additional multiplication by a constant, just
+ * use the timespec implementation.
  */
 unsigned long
 timeval_to_jiffies(const struct timeval *value)
 {
-	unsigned long sec = value->tv_sec;
-	long usec = value->tv_usec;
-
-	if (sec >= MAX_SEC_IN_JIFFIES){
-		sec = MAX_SEC_IN_JIFFIES;
-		usec = 0;
-	}
-	return (((u64)sec * SEC_CONVERSION) +
-		(((u64)usec * USEC_CONVERSION + USEC_ROUND) >>
-		 (USEC_JIFFIE_SC - SEC_JIFFIE_SC))) >> SEC_JIFFIE_SC;
+	return __timespec_to_jiffies(value->tv_sec,
+				     value->tv_usec * NSEC_PER_USEC);
 }
 EXPORT_SYMBOL(timeval_to_jiffies);
 
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 2ff0580d3dcd..51862982e1e9 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -3375,7 +3375,7 @@ static void rb_iter_reset(struct ring_buffer_iter *iter)
 	iter->head = cpu_buffer->reader_page->read;
 
 	iter->cache_reader_page = iter->head_page;
-	iter->cache_read = iter->head;
+	iter->cache_read = cpu_buffer->read;
 
 	if (iter->head)
 		iter->read_stamp = cpu_buffer->read_stamp;
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 33514d88fef9..c9ef81e08e4a 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1775,21 +1775,24 @@ static int __split_huge_page_map(struct page *page,
 	if (pmd) {
 		pgtable = pgtable_trans_huge_withdraw(mm, pmd);
 		pmd_populate(mm, &_pmd, pgtable);
+		if (pmd_write(*pmd))
+			BUG_ON(page_mapcount(page) != 1);
 
 		haddr = address;
 		for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) {
 			pte_t *pte, entry;
 			BUG_ON(PageCompound(page+i));
+			/*
+			 * Note that pmd_numa is not transferred deliberately
+			 * to avoid any possibility that pte_numa leaks to
+			 * a PROT_NONE VMA by accident.
+			 */
 			entry = mk_pte(page + i, vma->vm_page_prot);
 			entry = maybe_mkwrite(pte_mkdirty(entry), vma);
 			if (!pmd_write(*pmd))
 				entry = pte_wrprotect(entry);
-			else
-				BUG_ON(page_mapcount(page) != 1);
 			if (!pmd_young(*pmd))
 				entry = pte_mkold(entry);
-			if (pmd_numa(*pmd))
-				entry = pte_mknuma(entry);
 			pte = pte_offset_map(&_pmd, haddr);
 			BUG_ON(!pte_none(*pte));
 			set_pte_at(mm, haddr, pte, entry);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 1f14a430c656..15fe66d83987 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -292,6 +292,9 @@ struct mem_cgroup {
 	/* vmpressure notifications */
 	struct vmpressure vmpressure;
 
+	/* css_online() has been completed */
+	int initialized;
+
 	/*
 	 * the counter to account for mem+swap usage.
 	 */
@@ -1106,10 +1109,21 @@ skip_node:
 	 * skipping css reference should be safe.
 	 */
 	if (next_css) {
-		if ((next_css == &root->css) ||
-		    ((next_css->flags & CSS_ONLINE) &&
-		     css_tryget_online(next_css)))
-			return mem_cgroup_from_css(next_css);
+		struct mem_cgroup *memcg = mem_cgroup_from_css(next_css);
+
+		if (next_css == &root->css)
+			return memcg;
+
+		if (css_tryget_online(next_css)) {
+			/*
+			 * Make sure the memcg is initialized:
+			 * mem_cgroup_css_online() orders the the
+			 * initialization against setting the flag.
+			 */
+			if (smp_load_acquire(&memcg->initialized))
+				return memcg;
+			css_put(next_css);
+		}
 
 		prev_css = next_css;
 		goto skip_node;
@@ -6277,6 +6291,7 @@ mem_cgroup_css_online(struct cgroup_subsys_state *css)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
 	struct mem_cgroup *parent = mem_cgroup_from_css(css->parent);
+	int ret;
 
 	if (css->id > MEM_CGROUP_ID_MAX)
 		return -ENOSPC;
@@ -6313,7 +6328,18 @@ mem_cgroup_css_online(struct cgroup_subsys_state *css)
 	}
 	mutex_unlock(&memcg_create_mutex);
 
-	return memcg_init_kmem(memcg, &memory_cgrp_subsys);
+	ret = memcg_init_kmem(memcg, &memory_cgrp_subsys);
+	if (ret)
+		return ret;
+
+	/*
+	 * Make sure the memcg is initialized: mem_cgroup_iter()
+	 * orders reading memcg->initialized against its callers
+	 * reading the memcg members.
+	 */
+	smp_store_release(&memcg->initialized, 1);
+
+	return 0;
 }
 
 /*
diff --git a/mm/migrate.c b/mm/migrate.c
index be6dbf995c0c..0bba97914af0 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -146,8 +146,11 @@ static int remove_migration_pte(struct page *new, struct vm_area_struct *vma,
 	pte = pte_mkold(mk_pte(new, vma->vm_page_prot));
 	if (pte_swp_soft_dirty(*ptep))
 		pte = pte_mksoft_dirty(pte);
+
+	/* Recheck VMA as permissions can change since migration started  */
 	if (is_write_migration_entry(entry))
-		pte = pte_mkwrite(pte);
+		pte = maybe_mkwrite(pte, vma);
+
 #ifdef CONFIG_HUGETLB_PAGE
 	if (PageHuge(new)) {
 		pte = pte_mkhuge(pte);
diff --git a/sound/soc/codecs/ssm2602.c b/sound/soc/codecs/ssm2602.c
index 97b0454eb346..eb1bb7414b8b 100644
--- a/sound/soc/codecs/ssm2602.c
+++ b/sound/soc/codecs/ssm2602.c
@@ -647,7 +647,7 @@ int ssm2602_probe(struct device *dev, enum ssm2602_type type,
 		return -ENOMEM;
 
 	dev_set_drvdata(dev, ssm2602);
-	ssm2602->type = SSM2602;
+	ssm2602->type = type;
 	ssm2602->regmap = regmap;
 
 	return snd_soc_register_codec(dev, &soc_codec_dev_ssm2602,
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index b87d7d882e6d..49acc989e452 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -3181,7 +3181,7 @@ int snd_soc_bytes_put(struct snd_kcontrol *kcontrol,
 	unsigned int val, mask;
 	void *data;
 
-	if (!component->regmap)
+	if (!component->regmap || !params->num_regs)
 		return -EINVAL;
 
 	len = params->num_regs * component->val_bytes;