Re: Linux 3.13.3

[Greg KH]

diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index 22d89aa37218..d49f0bea4292 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -1377,8 +1377,8 @@ may allocate from based on an estimation of its current memory and swap use.
 For example, if a task is using all allowed memory, its badness score will be
 1000.  If it is using half of its allowed memory, its score will be 500.
 
-There is an additional factor included in the badness score: root
-processes are given 3% extra memory over other tasks.
+There is an additional factor included in the badness score: the current memory
+and swap usage is discounted by 3% for root processes.
 
 The amount of "allowed" memory depends on the context in which the oom killer
 was called.  If it is due to the memory assigned to the allocating task's cpuset
diff --git a/Makefile b/Makefile
index a7fd5d9e752f..704b508df625 100644
--- a/Makefile
+++ b/Makefile
@@ -1,6 +1,6 @@
 VERSION = 3
 PATCHLEVEL = 13
-SUBLEVEL = 2
+SUBLEVEL = 3
 EXTRAVERSION =
 NAME = One Giant Leap for Frogkind
 
diff --git a/arch/arm/mach-mvebu/mvebu-soc-id.c b/arch/arm/mach-mvebu/mvebu-soc-id.c
index fe4fc1cbdfaf..f3b325f6cbd4 100644
--- a/arch/arm/mach-mvebu/mvebu-soc-id.c
+++ b/arch/arm/mach-mvebu/mvebu-soc-id.c
@@ -88,7 +88,7 @@ static int __init mvebu_soc_id_init(void)
 	}
 
 	pci_base = of_iomap(child, 0);
-	if (IS_ERR(pci_base)) {
+	if (pci_base == NULL) {
 		pr_err("cannot map registers\n");
 		ret = -ENOMEM;
 		goto res_ioremap;
diff --git a/arch/arm/plat-orion/irq.c b/arch/arm/plat-orion/irq.c
index c492e1b3dfdb..807df142444b 100644
--- a/arch/arm/plat-orion/irq.c
+++ b/arch/arm/plat-orion/irq.c
@@ -15,8 +15,51 @@
 #include <linux/io.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
+#include <asm/exception.h>
 #include <plat/irq.h>
 #include <plat/orion-gpio.h>
+#include <mach/bridge-regs.h>
+
+#ifdef CONFIG_MULTI_IRQ_HANDLER
+/*
+ * Compiling with both non-DT and DT support enabled, will
+ * break asm irq handler used by non-DT boards. Therefore,
+ * we provide a C-style irq handler even for non-DT boards,
+ * if MULTI_IRQ_HANDLER is set.
+ *
+ * Notes:
+ * - this is prepared for Kirkwood and Dove only, update
+ *   accordingly if you add Orion5x or MV78x00.
+ * - Orion5x uses different macro names and has only one
+ *   set of CAUSE/MASK registers.
+ * - MV78x00 uses the same macro names but has a third
+ *   set of CAUSE/MASK registers.
+ *
+ */
+
+static void __iomem *orion_irq_base = IRQ_VIRT_BASE;
+
+asmlinkage void
+__exception_irq_entry orion_legacy_handle_irq(struct pt_regs *regs)
+{
+	u32 stat;
+
+	stat = readl_relaxed(orion_irq_base + IRQ_CAUSE_LOW_OFF);
+	stat &= readl_relaxed(orion_irq_base + IRQ_MASK_LOW_OFF);
+	if (stat) {
+		unsigned int hwirq = __fls(stat);
+		handle_IRQ(hwirq, regs);
+		return;
+	}
+	stat = readl_relaxed(orion_irq_base + IRQ_CAUSE_HIGH_OFF);
+	stat &= readl_relaxed(orion_irq_base + IRQ_MASK_HIGH_OFF);
+	if (stat) {
+		unsigned int hwirq = 32 + __fls(stat);
+		handle_IRQ(hwirq, regs);
+		return;
+	}
+}
+#endif
 
 void __init orion_irq_init(unsigned int irq_start, void __iomem *maskaddr)
 {
@@ -35,6 +78,10 @@ void __init orion_irq_init(unsigned int irq_start, void __iomem *maskaddr)
 	ct->chip.irq_unmask = irq_gc_mask_set_bit;
 	irq_setup_generic_chip(gc, IRQ_MSK(32), IRQ_GC_INIT_MASK_CACHE,
 			       IRQ_NOREQUEST, IRQ_LEVEL | IRQ_NOPROBE);
+
+#ifdef CONFIG_MULTI_IRQ_HANDLER
+	set_handle_irq(orion_legacy_handle_irq);
+#endif
 }
 
 #ifdef CONFIG_OF
diff --git a/arch/powerpc/include/asm/pgtable-ppc64.h b/arch/powerpc/include/asm/pgtable-ppc64.h
index 4a191c472867..bc141c950b1e 100644
--- a/arch/powerpc/include/asm/pgtable-ppc64.h
+++ b/arch/powerpc/include/asm/pgtable-ppc64.h
@@ -558,5 +558,19 @@ extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp);
 #define __HAVE_ARCH_PMDP_INVALIDATE
 extern void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
 			    pmd_t *pmdp);
+
+#define pmd_move_must_withdraw pmd_move_must_withdraw
+struct spinlock;
+static inline int pmd_move_must_withdraw(struct spinlock *new_pmd_ptl,
+					 struct spinlock *old_pmd_ptl)
+{
+	/*
+	 * Archs like ppc64 use pgtable to store per pmd
+	 * specific information. So when we switch the pmd,
+	 * we should also withdraw and deposit the pgtable
+	 */
+	return true;
+}
+
 #endif /* __ASSEMBLY__ */
 #endif /* _ASM_POWERPC_PGTABLE_PPC64_H_ */
diff --git a/arch/sh/kernel/kgdb.c b/arch/sh/kernel/kgdb.c
index 38b313909ac9..adad46e41a1d 100644
--- a/arch/sh/kernel/kgdb.c
+++ b/arch/sh/kernel/kgdb.c
@@ -13,6 +13,7 @@
 #include <linux/kdebug.h>
 #include <linux/irq.h>
 #include <linux/io.h>
+#include <linux/sched.h>
 #include <asm/cacheflush.h>
 #include <asm/traps.h>
 
diff --git a/arch/tile/include/asm/compat.h b/arch/tile/include/asm/compat.h
index 78f1f2ded86c..ffd4493efc78 100644
--- a/arch/tile/include/asm/compat.h
+++ b/arch/tile/include/asm/compat.h
@@ -281,7 +281,6 @@ long compat_sys_pread64(unsigned int fd, char __user *ubuf, size_t count,
 			u32 dummy, u32 low, u32 high);
 long compat_sys_pwrite64(unsigned int fd, char __user *ubuf, size_t count,
 			 u32 dummy, u32 low, u32 high);
-long compat_sys_lookup_dcookie(u32 low, u32 high, char __user *buf, size_t len);
 long compat_sys_sync_file_range2(int fd, unsigned int flags,
 				 u32 offset_lo, u32 offset_hi,
 				 u32 nbytes_lo, u32 nbytes_hi);
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index 0ecac257fb26..840c127a938e 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -121,7 +121,8 @@
 
 /* Set of bits not changed in pte_modify */
 #define _PAGE_CHG_MASK	(PTE_PFN_MASK | _PAGE_PCD | _PAGE_PWT |		\
-			 _PAGE_SPECIAL | _PAGE_ACCESSED | _PAGE_DIRTY)
+			 _PAGE_SPECIAL | _PAGE_ACCESSED | _PAGE_DIRTY |	\
+			 _PAGE_SOFT_DIRTY)
 #define _HPAGE_CHG_MASK (_PAGE_CHG_MASK | _PAGE_PSE)
 
 #define _PAGE_CACHE_MASK	(_PAGE_PCD | _PAGE_PWT)
diff --git a/arch/x86/xen/platform-pci-unplug.c b/arch/x86/xen/platform-pci-unplug.c
index 0a7852483ffe..ab84ac198a9a 100644
--- a/arch/x86/xen/platform-pci-unplug.c
+++ b/arch/x86/xen/platform-pci-unplug.c
@@ -69,6 +69,80 @@ static int check_platform_magic(void)
 	return 0;
 }
 
+bool xen_has_pv_devices()
+{
+	if (!xen_domain())
+		return false;
+
+	/* PV domains always have them. */
+	if (xen_pv_domain())
+		return true;
+
+	/* And user has xen_platform_pci=0 set in guest config as
+	 * driver did not modify the value. */
+	if (xen_platform_pci_unplug == 0)
+		return false;
+
+	if (xen_platform_pci_unplug & XEN_UNPLUG_NEVER)
+		return false;
+
+	if (xen_platform_pci_unplug & XEN_UNPLUG_ALL)
+		return true;
+
+	/* This is an odd one - we are going to run legacy
+	 * and PV drivers at the same time. */
+	if (xen_platform_pci_unplug & XEN_UNPLUG_UNNECESSARY)
+		return true;
+
+	/* And the caller has to follow with xen_pv_{disk,nic}_devices
+	 * to be certain which driver can load. */
+	return false;
+}
+EXPORT_SYMBOL_GPL(xen_has_pv_devices);
+
+static bool __xen_has_pv_device(int state)
+{
+	/* HVM domains might or might not */
+	if (xen_hvm_domain() && (xen_platform_pci_unplug & state))
+		return true;
+
+	return xen_has_pv_devices();
+}
+
+bool xen_has_pv_nic_devices(void)
+{
+	return __xen_has_pv_device(XEN_UNPLUG_ALL_NICS | XEN_UNPLUG_ALL);
+}
+EXPORT_SYMBOL_GPL(xen_has_pv_nic_devices);
+
+bool xen_has_pv_disk_devices(void)
+{
+	return __xen_has_pv_device(XEN_UNPLUG_ALL_IDE_DISKS |
+				   XEN_UNPLUG_AUX_IDE_DISKS | XEN_UNPLUG_ALL);
+}
+EXPORT_SYMBOL_GPL(xen_has_pv_disk_devices);
+
+/*
+ * This one is odd - it determines whether you want to run PV _and_
+ * legacy (IDE) drivers together. This combination is only possible
+ * under HVM.
+ */
+bool xen_has_pv_and_legacy_disk_devices(void)
+{
+	if (!xen_domain())
+		return false;
+
+	/* N.B. This is only ever used in HVM mode */
+	if (xen_pv_domain())
+		return false;
+
+	if (xen_platform_pci_unplug & XEN_UNPLUG_UNNECESSARY)
+		return true;
+
+	return false;
+}
+EXPORT_SYMBOL_GPL(xen_has_pv_and_legacy_disk_devices);
+
 void xen_unplug_emulated_devices(void)
 {
 	int r;
diff --git a/arch/xtensa/platforms/xtfpga/setup.c b/arch/xtensa/platforms/xtfpga/setup.c
index 74bb74fa3f87..ea2d39dd912a 100644
--- a/arch/xtensa/platforms/xtfpga/setup.c
+++ b/arch/xtensa/platforms/xtfpga/setup.c
@@ -194,7 +194,7 @@ void __init platform_calibrate_ccount(void)
  *  Ethernet -- OpenCores Ethernet MAC (ethoc driver)
  */
 
-static struct resource ethoc_res[] __initdata = {
+static struct resource ethoc_res[] = {
 	[0] = { /* register space */
 		.start = OETH_REGS_PADDR,
 		.end   = OETH_REGS_PADDR + OETH_REGS_SIZE - 1,
@@ -212,7 +212,7 @@ static struct resource ethoc_res[] __initdata = {
 	},
 };
 
-static struct ethoc_platform_data ethoc_pdata __initdata = {
+static struct ethoc_platform_data ethoc_pdata = {
 	/*
 	 * The MAC address for these boards is 00:50:c2:13:6f:xx.
 	 * The last byte (here as zero) is read from the DIP switches on the
@@ -222,7 +222,7 @@ static struct ethoc_platform_data ethoc_pdata __initdata = {
 	.phy_id = -1,
 };
 
-static struct platform_device ethoc_device __initdata = {
+static struct platform_device ethoc_device = {
 	.name = "ethoc",
 	.id = -1,
 	.num_resources = ARRAY_SIZE(ethoc_res),
@@ -236,13 +236,13 @@ static struct platform_device ethoc_device __initdata = {
  *  UART
  */
 
-static struct resource serial_resource __initdata = {
+static struct resource serial_resource = {
 	.start	= DUART16552_PADDR,
 	.end	= DUART16552_PADDR + 0x1f,
 	.flags	= IORESOURCE_MEM,
 };
 
-static struct plat_serial8250_port serial_platform_data[] __initdata = {
+static struct plat_serial8250_port serial_platform_data[] = {
 	[0] = {
 		.mapbase	= DUART16552_PADDR,
 		.irq		= DUART16552_INTNUM,
@@ -255,7 +255,7 @@ static struct plat_serial8250_port serial_platform_data[] __initdata = {
 	{ },
 };
 
-static struct platform_device xtavnet_uart __initdata = {
+static struct platform_device xtavnet_uart = {
 	.name		= "serial8250",
 	.id		= PLAT8250_DEV_PLATFORM,
 	.dev		= {
diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index d64a02fb1f73..5d70edc9855f 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -36,7 +36,8 @@ static unsigned int __blk_mq_get_tag(struct blk_mq_tags *tags, gfp_t gfp)
 {
 	int tag;
 
-	tag = percpu_ida_alloc(&tags->free_tags, gfp);
+	tag = percpu_ida_alloc(&tags->free_tags, (gfp & __GFP_WAIT) ?
+			       TASK_UNINTERRUPTIBLE : TASK_RUNNING);
 	if (tag < 0)
 		return BLK_MQ_TAG_FAIL;
 	return tag + tags->nr_reserved_tags;
@@ -52,7 +53,8 @@ static unsigned int __blk_mq_get_reserved_tag(struct blk_mq_tags *tags,
 		return BLK_MQ_TAG_FAIL;
 	}
 
-	tag = percpu_ida_alloc(&tags->reserved_tags, gfp);
+	tag = percpu_ida_alloc(&tags->reserved_tags, (gfp & __GFP_WAIT) ?
+			       TASK_UNINTERRUPTIBLE : TASK_RUNNING);
 	if (tag < 0)
 		return BLK_MQ_TAG_FAIL;
 	return tag;
diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c
index 0710004055c8..296bec89f4a1 100644
--- a/drivers/acpi/bus.c
+++ b/drivers/acpi/bus.c
@@ -33,6 +33,7 @@
 #include <linux/proc_fs.h>
 #include <linux/acpi.h>
 #include <linux/slab.h>
+#include <linux/regulator/machine.h>
 #ifdef CONFIG_X86
 #include <asm/mpspec.h>
 #endif
@@ -576,6 +577,14 @@ void __init acpi_early_init(void)
 		goto error0;
 	}
 
+	/*
+	 * If the system is using ACPI then we can be reasonably
+	 * confident that any regulators are managed by the firmware
+	 * so tell the regulator core it has everything it needs to
+	 * know.
+	 */
+	regulator_has_full_constraints();
+
 	return;
 
       error0:
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index c4a4c9006288..f9c43f91f03e 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -1356,7 +1356,7 @@ static int blkfront_probe(struct xenbus_device *dev,
 		char *type;
 		int len;
 		/* no unplug has been done: do not hook devices != xen vbds */
-		if (xen_platform_pci_unplug & XEN_UNPLUG_UNNECESSARY) {
+		if (xen_has_pv_and_legacy_disk_devices()) {
 			int major;
 
 			if (!VDEV_IS_EXTENDED(vdevice))
@@ -2079,7 +2079,7 @@ static int __init xlblk_init(void)
 	if (!xen_domain())
 		return -ENODEV;
 
-	if (xen_hvm_domain() && !xen_platform_pci_unplug)
+	if (!xen_has_pv_disk_devices())
 		return -ENODEV;
 
 	if (register_blkdev(XENVBD_MAJOR, DEV_NAME)) {
diff --git a/drivers/char/tpm/xen-tpmfront.c b/drivers/char/tpm/xen-tpmfront.c
index c8ff4df81779..62e7d383fa64 100644
--- a/drivers/char/tpm/xen-tpmfront.c
+++ b/drivers/char/tpm/xen-tpmfront.c
@@ -17,6 +17,7 @@
 #include <xen/xenbus.h>
 #include <xen/page.h>
 #include "tpm.h"
+#include <xen/platform_pci.h>
 
 struct tpm_private {
 	struct tpm_chip *chip;
@@ -421,6 +422,9 @@ static int __init xen_tpmfront_init(void)
 	if (!xen_domain())
 		return -ENODEV;
 
+	if (!xen_has_pv_devices())
+		return -ENODEV;
+
 	return xenbus_register_frontend(&tpmfront_driver);
 }
 module_init(xen_tpmfront_init);
diff --git a/drivers/eisa/eisa-bus.c b/drivers/eisa/eisa-bus.c
index 272a3ec35957..0314dde18a5d 100644
--- a/drivers/eisa/eisa-bus.c
+++ b/drivers/eisa/eisa-bus.c
@@ -275,11 +275,13 @@ static int __init eisa_request_resources(struct eisa_root_device *root,
 		}
 		
 		if (slot) {
+			edev->res[i].name  = NULL;
 			edev->res[i].start = SLOT_ADDRESS(root, slot)
 					     + (i * 0x400);
 			edev->res[i].end   = edev->res[i].start + 0xff;
 			edev->res[i].flags = IORESOURCE_IO;
 		} else {
+			edev->res[i].name  = NULL;
 			edev->res[i].start = SLOT_ADDRESS(root, slot)
 					     + EISA_VENDOR_ID_OFFSET;
 			edev->res[i].end   = edev->res[i].start + 3;
@@ -326,19 +328,20 @@ static int __init eisa_probe(struct eisa_root_device *root)
 		return -ENOMEM;
 	}
 		
-	if (eisa_init_device(root, edev, 0)) {
+	if (eisa_request_resources(root, edev, 0)) {
+		dev_warn(root->dev,
+		         "EISA: Cannot allocate resource for mainboard\n");
 		kfree(edev);
 		if (!root->force_probe)
-			return -ENODEV;
+			return -EBUSY;
 		goto force_probe;
 	}
 
-	if (eisa_request_resources(root, edev, 0)) {
-		dev_warn(root->dev,
-		         "EISA: Cannot allocate resource for mainboard\n");
+	if (eisa_init_device(root, edev, 0)) {
+		eisa_release_resources(edev);
 		kfree(edev);
 		if (!root->force_probe)
-			return -EBUSY;
+			return -ENODEV;
 		goto force_probe;
 	}
 
@@ -361,11 +364,6 @@ static int __init eisa_probe(struct eisa_root_device *root)
 			continue;
 		}
 
-		if (eisa_init_device(root, edev, i)) {
-			kfree(edev);
-			continue;
-		}
-
 		if (eisa_request_resources(root, edev, i)) {
 			dev_warn(root->dev,
 			         "Cannot allocate resource for EISA slot %d\n",
@@ -374,6 +372,12 @@ static int __init eisa_probe(struct eisa_root_device *root)
 			continue;
 		}
 
+		if (eisa_init_device(root, edev, i)) {
+			eisa_release_resources(edev);
+			kfree(edev);
+			continue;
+		}
+
 		if (edev->state == (EISA_CONFIG_ENABLED | EISA_CONFIG_FORCED))
 			enabled_str = " (forced enabled)";
 		else if (edev->state == EISA_CONFIG_FORCED)
diff --git a/drivers/gpu/drm/ast/ast_fb.c b/drivers/gpu/drm/ast/ast_fb.c
index 7b33e14e44aa..a28640f47c27 100644
--- a/drivers/gpu/drm/ast/ast_fb.c
+++ b/drivers/gpu/drm/ast/ast_fb.c
@@ -65,7 +65,7 @@ static void ast_dirty_update(struct ast_fbdev *afbdev,
 	 * then the BO is being moved and we should
 	 * store up the damage until later.
 	 */
-	if (!in_interrupt())
+	if (drm_can_sleep())
 		ret = ast_bo_reserve(bo, true);
 	if (ret) {
 		if (ret != -EBUSY)
diff --git a/drivers/gpu/drm/cirrus/cirrus_fbdev.c b/drivers/gpu/drm/cirrus/cirrus_fbdev.c
index b27e95666fab..86d779a9c245 100644
--- a/drivers/gpu/drm/cirrus/cirrus_fbdev.c
+++ b/drivers/gpu/drm/cirrus/cirrus_fbdev.c
@@ -39,7 +39,7 @@ static void cirrus_dirty_update(struct cirrus_fbdev *afbdev,
 	 * then the BO is being moved and we should
 	 * store up the damage until later.
 	 */
-	if (!in_interrupt())
+	if (drm_can_sleep())
 		ret = cirrus_bo_reserve(bo, true);
 	if (ret) {
 		if (ret != -EBUSY)
diff --git a/drivers/gpu/drm/cirrus/cirrus_mode.c b/drivers/gpu/drm/cirrus/cirrus_mode.c
index adabc3daaa5b..3592616d484b 100644
--- a/drivers/gpu/drm/cirrus/cirrus_mode.c
+++ b/drivers/gpu/drm/cirrus/cirrus_mode.c
@@ -273,8 +273,8 @@ static int cirrus_crtc_mode_set(struct drm_crtc *crtc,
 		sr07 |= 0x11;
 		break;
 	case 16:
-		sr07 |= 0xc1;
-		hdr = 0xc0;
+		sr07 |= 0x17;
+		hdr = 0xc1;
 		break;
 	case 24:
 		sr07 |= 0x15;
diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c
index 4761adedad2a..cfd77081fa0b 100644
--- a/drivers/gpu/drm/drm_gem.c
+++ b/drivers/gpu/drm/drm_gem.c
@@ -129,11 +129,12 @@ int drm_gem_object_init(struct drm_device *dev,
 {
 	struct file *filp;
 
+	drm_gem_private_object_init(dev, obj, size);
+
 	filp = shmem_file_setup("drm mm object", size, VM_NORESERVE);
 	if (IS_ERR(filp))
 		return PTR_ERR(filp);
 
-	drm_gem_private_object_init(dev, obj, size);
 	obj->filp = filp;
 
 	return 0;
diff --git a/drivers/gpu/drm/gma500/gma_display.c b/drivers/gpu/drm/gma500/gma_display.c
index 24e8af3d22bf..386de2c9dc86 100644
--- a/drivers/gpu/drm/gma500/gma_display.c
+++ b/drivers/gpu/drm/gma500/gma_display.c
@@ -349,6 +349,7 @@ int gma_crtc_cursor_set(struct drm_crtc *crtc,
 	/* If we didn't get a handle then turn the cursor off */
 	if (!handle) {
 		temp = CURSOR_MODE_DISABLE;
+		mutex_lock(&dev->struct_mutex);
 
 		if (gma_power_begin(dev, false)) {
 			REG_WRITE(control, temp);
@@ -365,6 +366,7 @@ int gma_crtc_cursor_set(struct drm_crtc *crtc,
 			gma_crtc->cursor_obj = NULL;
 		}
 
+		mutex_unlock(&dev->struct_mutex);
 		return 0;
 	}
 
@@ -374,9 +376,12 @@ int gma_crtc_cursor_set(struct drm_crtc *crtc,
 		return -EINVAL;
 	}
 
+	mutex_lock(&dev->struct_mutex);
 	obj = drm_gem_object_lookup(dev, file_priv, handle);
-	if (!obj)
-		return -ENOENT;
+	if (!obj) {
+		ret = -ENOENT;
+		goto unlock;
+	}
 
 	if (obj->size < width * height * 4) {
 		dev_dbg(dev->dev, "Buffer is too small\n");
@@ -440,10 +445,13 @@ int gma_crtc_cursor_set(struct drm_crtc *crtc,
 	}
 
 	gma_crtc->cursor_obj = obj;
+unlock:
+	mutex_unlock(&dev->struct_mutex);
 	return ret;
 
 unref_cursor:
 	drm_gem_object_unreference(obj);
+	mutex_unlock(&dev->struct_mutex);
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c
index 5c648425c1e0..e02266afb901 100644
--- a/drivers/gpu/drm/i915/i915_dma.c
+++ b/drivers/gpu/drm/i915/i915_dma.c
@@ -1679,6 +1679,7 @@ out_gem_unload:
 
 	intel_teardown_gmbus(dev);
 	intel_teardown_mchbar(dev);
+	pm_qos_remove_request(&dev_priv->pm_qos);
 	destroy_workqueue(dev_priv->wq);
 out_mtrrfree:
 	arch_phys_wc_del(dev_priv->gtt.mtrr);
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 90fcccba17b0..221ac62b5736 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -317,6 +317,7 @@ struct drm_i915_error_state {
 	u64 fence[I915_MAX_NUM_FENCES];
 	struct timeval time;
 	struct drm_i915_error_ring {
+		bool valid;
 		struct drm_i915_error_object {
 			int page_count;
 			u32 gtt_offset;
diff --git a/drivers/gpu/drm/i915/i915_gem_stolen.c b/drivers/gpu/drm/i915/i915_gem_stolen.c
index d284d892ed94..61c09101ed18 100644
--- a/drivers/gpu/drm/i915/i915_gem_stolen.c
+++ b/drivers/gpu/drm/i915/i915_gem_stolen.c
@@ -250,7 +250,7 @@ i915_pages_create_for_stolen(struct drm_device *dev,
 	}
 
 	sg = st->sgl;
-	sg->offset = offset;
+	sg->offset = 0;
 	sg->length = size;
 
 	sg_dma_address(sg) = (dma_addr_t)dev_priv->mm.stolen_base + offset;
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 79dcb8f896c6..6705f3bc1768 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -239,6 +239,9 @@ static void i915_ring_error_state(struct drm_i915_error_state_buf *m,
 				  unsigned ring)
 {
 	BUG_ON(ring >= I915_NUM_RINGS); /* shut up confused gcc */
+	if (!error->ring[ring].valid)
+		return;
+
 	err_printf(m, "%s command stream:\n", ring_str(ring));
 	err_printf(m, "  HEAD: 0x%08x\n", error->head[ring]);
 	err_printf(m, "  TAIL: 0x%08x\n", error->tail[ring]);
@@ -294,7 +297,6 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
 	struct drm_device *dev = error_priv->dev;
 	drm_i915_private_t *dev_priv = dev->dev_private;
 	struct drm_i915_error_state *error = error_priv->error;
-	struct intel_ring_buffer *ring;
 	int i, j, page, offset, elt;
 
 	if (!error) {
@@ -329,7 +331,7 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
 	if (INTEL_INFO(dev)->gen == 7)
 		err_printf(m, "ERR_INT: 0x%08x\n", error->err_int);
 
-	for_each_ring(ring, dev_priv, i)
+	for (i = 0; i < ARRAY_SIZE(error->ring); i++)
 		i915_ring_error_state(m, dev, error, i);
 
 	if (error->active_bo)
@@ -386,8 +388,7 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
 			}
 		}
 
-		obj = error->ring[i].ctx;
-		if (obj) {
+		if ((obj = error->ring[i].ctx)) {
 			err_printf(m, "%s --- HW Context = 0x%08x\n",
 				   dev_priv->ring[i].name,
 				   obj->gtt_offset);
@@ -668,7 +669,8 @@ i915_error_first_batchbuffer(struct drm_i915_private *dev_priv,
 			return NULL;
 
 		obj = ring->scratch.obj;
-		if (acthd >= i915_gem_obj_ggtt_offset(obj) &&
+		if (obj != NULL &&
+		    acthd >= i915_gem_obj_ggtt_offset(obj) &&
 		    acthd < i915_gem_obj_ggtt_offset(obj) + obj->base.size)
 			return i915_error_object_create(dev_priv, obj);
 	}
@@ -775,11 +777,17 @@ static void i915_gem_record_rings(struct drm_device *dev,
 				  struct drm_i915_error_state *error)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_ring_buffer *ring;
 	struct drm_i915_gem_request *request;
 	int i, count;
 
-	for_each_ring(ring, dev_priv, i) {
+	for (i = 0; i < I915_NUM_RINGS; i++) {
+		struct intel_ring_buffer *ring = &dev_priv->ring[i];
+
+		if (ring->dev == NULL)
+			continue;
+
+		error->ring[i].valid = true;
+
 		i915_record_ring_state(dev, error, ring);
 
 		error->ring[i].batchbuffer =
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index ee2742122a02..9a1a96a0a720 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -2117,9 +2117,13 @@
  * Please check the detailed lore in the commit message for for experimental
  * evidence.
  */
-#define   PORTD_HOTPLUG_LIVE_STATUS               (1 << 29)
-#define   PORTC_HOTPLUG_LIVE_STATUS               (1 << 28)
-#define   PORTB_HOTPLUG_LIVE_STATUS               (1 << 27)
+#define   PORTD_HOTPLUG_LIVE_STATUS_G4X		(1 << 29)
+#define   PORTC_HOTPLUG_LIVE_STATUS_G4X		(1 << 28)
+#define   PORTB_HOTPLUG_LIVE_STATUS_G4X		(1 << 27)
+/* VLV DP/HDMI bits again match Bspec */
+#define   PORTD_HOTPLUG_LIVE_STATUS_VLV		(1 << 27)
+#define   PORTC_HOTPLUG_LIVE_STATUS_VLV		(1 << 28)
+#define   PORTB_HOTPLUG_LIVE_STATUS_VLV		(1 << 29)
 #define   PORTD_HOTPLUG_INT_STATUS		(3 << 21)
 #define   PORTC_HOTPLUG_INT_STATUS		(3 << 19)
 #define   PORTB_HOTPLUG_INT_STATUS		(3 << 17)
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 30c627c7b7ba..45e82db42903 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -3020,18 +3020,34 @@ g4x_dp_detect(struct intel_dp *intel_dp)
 		return status;
 	}
 
-	switch (intel_dig_port->port) {
-	case PORT_B:
-		bit = PORTB_HOTPLUG_LIVE_STATUS;
-		break;
-	case PORT_C:
-		bit = PORTC_HOTPLUG_LIVE_STATUS;
-		break;
-	case PORT_D:
-		bit = PORTD_HOTPLUG_LIVE_STATUS;
-		break;
-	default:
-		return connector_status_unknown;
+	if (IS_VALLEYVIEW(dev)) {
+		switch (intel_dig_port->port) {
+		case PORT_B:
+			bit = PORTB_HOTPLUG_LIVE_STATUS_VLV;
+			break;
+		case PORT_C:
+			bit = PORTC_HOTPLUG_LIVE_STATUS_VLV;
+			break;
+		case PORT_D:
+			bit = PORTD_HOTPLUG_LIVE_STATUS_VLV;
+			break;
+		default:
+			return connector_status_unknown;
+		}
+	} else {
+		switch (intel_dig_port->port) {
+		case PORT_B:
+			bit = PORTB_HOTPLUG_LIVE_STATUS_G4X;
+			break;
+		case PORT_C:
+			bit = PORTC_HOTPLUG_LIVE_STATUS_G4X;
+			break;
+		case PORT_D:
+			bit = PORTD_HOTPLUG_LIVE_STATUS_G4X;
+			break;
+		default:
+			return connector_status_unknown;
+		}
 	}
 
 	if ((I915_READ(PORT_HOTPLUG_STAT) & bit) == 0)
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index c2f09d456300..c7f33971a35b 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -1611,8 +1611,8 @@ intel_ring_alloc_seqno(struct intel_ring_buffer *ring)
 	return i915_gem_get_seqno(ring->dev, &ring->outstanding_lazy_seqno);
 }
 
-static int __intel_ring_begin(struct intel_ring_buffer *ring,
-			      int bytes)
+static int __intel_ring_prepare(struct intel_ring_buffer *ring,
+				int bytes)
 {
 	int ret;
 
@@ -1628,7 +1628,6 @@ static int __intel_ring_begin(struct intel_ring_buffer *ring,
 			return ret;
 	}
 
-	ring->space -= bytes;
 	return 0;
 }
 
@@ -1643,12 +1642,17 @@ int intel_ring_begin(struct intel_ring_buffer *ring,
 	if (ret)
 		return ret;
 
+	ret = __intel_ring_prepare(ring, num_dwords * sizeof(uint32_t));
+	if (ret)
+		return ret;
+
 	/* Preallocate the olr before touching the ring */
 	ret = intel_ring_alloc_seqno(ring);
 	if (ret)
 		return ret;
 
-	return __intel_ring_begin(ring, num_dwords * sizeof(uint32_t));
+	ring->space -= num_dwords * sizeof(uint32_t);
+	return 0;
 }
 
 void intel_ring_init_seqno(struct intel_ring_buffer *ring, u32 seqno)
diff --git a/drivers/gpu/drm/mgag200/mgag200_cursor.c b/drivers/gpu/drm/mgag200/mgag200_cursor.c
index 801731aeab61..9f9780b7ddf0 100644
--- a/drivers/gpu/drm/mgag200/mgag200_cursor.c
+++ b/drivers/gpu/drm/mgag200/mgag200_cursor.c
@@ -22,8 +22,10 @@ static void mga_hide_cursor(struct mga_device *mdev)
 {
 	WREG8(MGA_CURPOSXL, 0);
 	WREG8(MGA_CURPOSXH, 0);
-	mgag200_bo_unpin(mdev->cursor.pixels_1);
-	mgag200_bo_unpin(mdev->cursor.pixels_2);
+	if (mdev->cursor.pixels_1->pin_count)
+		mgag200_bo_unpin(mdev->cursor.pixels_1);
+	if (mdev->cursor.pixels_2->pin_count)
+		mgag200_bo_unpin(mdev->cursor.pixels_2);
 }
 
 int mga_crtc_cursor_set(struct drm_crtc *crtc,
@@ -32,7 +34,7 @@ int mga_crtc_cursor_set(struct drm_crtc *crtc,
 			uint32_t width,
 			uint32_t height)
 {
-	struct drm_device *dev = (struct drm_device *)file_priv->minor->dev;
+	struct drm_device *dev = crtc->dev;
 	struct mga_device *mdev = (struct mga_device *)dev->dev_private;
 	struct mgag200_bo *pixels_1 = mdev->cursor.pixels_1;
 	struct mgag200_bo *pixels_2 = mdev->cursor.pixels_2;
diff --git a/drivers/gpu/drm/mgag200/mgag200_fb.c b/drivers/gpu/drm/mgag200/mgag200_fb.c
index 964f58cee5ea..d29bb335cccc 100644
--- a/drivers/gpu/drm/mgag200/mgag200_fb.c
+++ b/drivers/gpu/drm/mgag200/mgag200_fb.c
@@ -41,7 +41,7 @@ static void mga_dirty_update(struct mga_fbdev *mfbdev,
 	 * then the BO is being moved and we should
 	 * store up the damage until later.
 	 */
-	if (!in_interrupt())
+	if (drm_can_sleep())
 		ret = mgag200_bo_reserve(bo, true);
 	if (ret) {
 		if (ret != -EBUSY)
diff --git a/drivers/gpu/drm/mgag200/mgag200_mode.c b/drivers/gpu/drm/mgag200/mgag200_mode.c
index ee6ed633b7b1..ee3465f21eb9 100644
--- a/drivers/gpu/drm/mgag200/mgag200_mode.c
+++ b/drivers/gpu/drm/mgag200/mgag200_mode.c
@@ -1519,11 +1519,11 @@ static int mga_vga_mode_valid(struct drm_connector *connector,
 		(mga_vga_calculate_mode_bandwidth(mode, bpp)
 			> (32700 * 1024))) {
 		return MODE_BANDWIDTH;
-	} else if (mode->type == G200_EH &&
+	} else if (mdev->type == G200_EH &&
 		(mga_vga_calculate_mode_bandwidth(mode, bpp)
 			> (37500 * 1024))) {
 		return MODE_BANDWIDTH;
-	} else if (mode->type == G200_ER &&
+	} else if (mdev->type == G200_ER &&
 		(mga_vga_calculate_mode_bandwidth(mode,
 			bpp) > (55000 * 1024))) {
 		return MODE_BANDWIDTH;
diff --git a/drivers/gpu/drm/nouveau/core/engine/falcon.c b/drivers/gpu/drm/nouveau/core/engine/falcon.c
index e03fc8e4dc1d..5e077e4ed7f6 100644
--- a/drivers/gpu/drm/nouveau/core/engine/falcon.c
+++ b/drivers/gpu/drm/nouveau/core/engine/falcon.c
@@ -56,6 +56,16 @@ _nouveau_falcon_wr32(struct nouveau_object *object, u64 addr, u32 data)
 	nv_wr32(falcon, falcon->addr + addr, data);
 }
 
+static void *
+vmemdup(const void *src, size_t len)
+{
+	void *p = vmalloc(len);
+
+	if (p)
+		memcpy(p, src, len);
+	return p;
+}
+
 int
 _nouveau_falcon_init(struct nouveau_object *object)
 {
@@ -111,7 +121,7 @@ _nouveau_falcon_init(struct nouveau_object *object)
 
 		ret = request_firmware(&fw, name, &device->pdev->dev);
 		if (ret == 0) {
-			falcon->code.data = kmemdup(fw->data, fw->size, GFP_KERNEL);
+			falcon->code.data = vmemdup(fw->data, fw->size);
 			falcon->code.size = fw->size;
 			falcon->data.data = NULL;
 			falcon->data.size = 0;
@@ -134,7 +144,7 @@ _nouveau_falcon_init(struct nouveau_object *object)
 			return ret;
 		}
 
-		falcon->data.data = kmemdup(fw->data, fw->size, GFP_KERNEL);
+		falcon->data.data = vmemdup(fw->data, fw->size);
 		falcon->data.size = fw->size;
 		release_firmware(fw);
 		if (!falcon->data.data)
@@ -149,7 +159,7 @@ _nouveau_falcon_init(struct nouveau_object *object)
 			return ret;
 		}
 
-		falcon->code.data = kmemdup(fw->data, fw->size, GFP_KERNEL);
+		falcon->code.data = vmemdup(fw->data, fw->size);
 		falcon->code.size = fw->size;
 		release_firmware(fw);
 		if (!falcon->code.data)
@@ -235,8 +245,8 @@ _nouveau_falcon_fini(struct nouveau_object *object, bool suspend)
 	if (!suspend) {
 		nouveau_gpuobj_ref(NULL, &falcon->core);
 		if (falcon->external) {
-			kfree(falcon->data.data);
-			kfree(falcon->code.data);
+			vfree(falcon->data.data);
+			vfree(falcon->code.data);
 			falcon->code.data = NULL;
 		}
 	}
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index c0fde6b9393c..a79037128730 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -798,25 +798,25 @@ nv50_bo_move_m2mf(struct nouveau_channel *chan, struct ttm_buffer_object *bo,
 		  struct ttm_mem_reg *old_mem, struct ttm_mem_reg *new_mem)
 {
 	struct nouveau_mem *node = old_mem->mm_node;
-	struct nouveau_bo *nvbo = nouveau_bo(bo);
 	u64 length = (new_mem->num_pages << PAGE_SHIFT);
 	u64 src_offset = node->vma[0].offset;
 	u64 dst_offset = node->vma[1].offset;
+	int src_tiled = !!node->memtype;
+	int dst_tiled = !!((struct nouveau_mem *)new_mem->mm_node)->memtype;
 	int ret;
 
 	while (length) {
 		u32 amount, stride, height;
 
+		ret = RING_SPACE(chan, 18 + 6 * (src_tiled + dst_tiled));
+		if (ret)
+			return ret;
+
 		amount  = min(length, (u64)(4 * 1024 * 1024));
 		stride  = 16 * 4;
 		height  = amount / stride;
 
-		if (old_mem->mem_type == TTM_PL_VRAM &&
-		    nouveau_bo_tile_layout(nvbo)) {
-			ret = RING_SPACE(chan, 8);
-			if (ret)
-				return ret;
-
+		if (src_tiled) {
 			BEGIN_NV04(chan, NvSubCopy, 0x0200, 7);
 			OUT_RING  (chan, 0);
 			OUT_RING  (chan, 0);
@@ -826,19 +826,10 @@ nv50_bo_move_m2mf(struct nouveau_channel *chan, struct ttm_buffer_object *bo,
 			OUT_RING  (chan, 0);
 			OUT_RING  (chan, 0);
 		} else {
-			ret = RING_SPACE(chan, 2);
-			if (ret)
-				return ret;
-
 			BEGIN_NV04(chan, NvSubCopy, 0x0200, 1);
 			OUT_RING  (chan, 1);
 		}
-		if (new_mem->mem_type == TTM_PL_VRAM &&
-		    nouveau_bo_tile_layout(nvbo)) {
-			ret = RING_SPACE(chan, 8);
-			if (ret)
-				return ret;
-
+		if (dst_tiled) {
 			BEGIN_NV04(chan, NvSubCopy, 0x021c, 7);
 			OUT_RING  (chan, 0);
 			OUT_RING  (chan, 0);
@@ -848,18 +839,10 @@ nv50_bo_move_m2mf(struct nouveau_channel *chan, struct ttm_buffer_object *bo,
 			OUT_RING  (chan, 0);
 			OUT_RING  (chan, 0);
 		} else {
-			ret = RING_SPACE(chan, 2);
-			if (ret)
-				return ret;
-
 			BEGIN_NV04(chan, NvSubCopy, 0x021c, 1);
 			OUT_RING  (chan, 1);
 		}
 
-		ret = RING_SPACE(chan, 14);
-		if (ret)
-			return ret;
-
 		BEGIN_NV04(chan, NvSubCopy, 0x0238, 2);
 		OUT_RING  (chan, upper_32_bits(src_offset));
 		OUT_RING  (chan, upper_32_bits(dst_offset));
diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c
index 25ea82f8def3..91c826c6eb89 100644
--- a/drivers/gpu/drm/nouveau/nouveau_display.c
+++ b/drivers/gpu/drm/nouveau/nouveau_display.c
@@ -603,6 +603,14 @@ nouveau_crtc_page_flip(struct drm_crtc *crtc, struct drm_framebuffer *fb,
 	if (!s)
 		return -ENOMEM;
 
+	if (new_bo != old_bo) {
+		ret = nouveau_bo_pin(new_bo, TTM_PL_FLAG_VRAM);
+		if (ret)
+			goto fail_free;
+	}
+
+	mutex_lock(&chan->cli->mutex);
+
 	/* synchronise rendering channel with the kernel's channel */
 	spin_lock(&new_bo->bo.bdev->fence_lock);
 	fence = nouveau_fence_ref(new_bo->bo.sync_obj);
@@ -610,15 +618,8 @@ nouveau_crtc_page_flip(struct drm_crtc *crtc, struct drm_framebuffer *fb,
 	ret = nouveau_fence_sync(fence, chan);
 	nouveau_fence_unref(&fence);
 	if (ret)
-		goto fail_free;
-
-	if (new_bo != old_bo) {
-		ret = nouveau_bo_pin(new_bo, TTM_PL_FLAG_VRAM);
-		if (ret)
-			goto fail_free;
-	}
+		goto fail_unpin;
 
-	mutex_lock(&chan->cli->mutex);
 	ret = ttm_bo_reserve(&old_bo->bo, true, false, false, NULL);
 	if (ret)
 		goto fail_unpin;
diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c
index 0b9621c9aeea..358d14a9ed30 100644
--- a/drivers/gpu/drm/radeon/atombios_crtc.c
+++ b/drivers/gpu/drm/radeon/atombios_crtc.c
@@ -209,6 +209,16 @@ static void atombios_enable_crtc_memreq(struct drm_crtc *crtc, int state)
 	atom_execute_table(rdev->mode_info.atom_context, index, (uint32_t *)&args);
 }
 
+static const u32 vga_control_regs[6] =
+{
+	AVIVO_D1VGA_CONTROL,
+	AVIVO_D2VGA_CONTROL,
+	EVERGREEN_D3VGA_CONTROL,
+	EVERGREEN_D4VGA_CONTROL,
+	EVERGREEN_D5VGA_CONTROL,
+	EVERGREEN_D6VGA_CONTROL,
+};
+
 static void atombios_blank_crtc(struct drm_crtc *crtc, int state)
 {
 	struct radeon_crtc *radeon_crtc = to_radeon_crtc(crtc);
@@ -216,13 +226,23 @@ static void atombios_blank_crtc(struct drm_crtc *crtc, int state)
 	struct radeon_device *rdev = dev->dev_private;
 	int index = GetIndexIntoMasterTable(COMMAND, BlankCRTC);
 	BLANK_CRTC_PS_ALLOCATION args;
+	u32 vga_control = 0;
 
 	memset(&args, 0, sizeof(args));
 
+	if (ASIC_IS_DCE8(rdev)) {
+		vga_control = RREG32(vga_control_regs[radeon_crtc->crtc_id]);
+		WREG32(vga_control_regs[radeon_crtc->crtc_id], vga_control | 1);
+	}
+
 	args.ucCRTC = radeon_crtc->crtc_id;
 	args.ucBlanking = state;
 
 	atom_execute_table(rdev->mode_info.atom_context, index, (uint32_t *)&args);
+
+	if (ASIC_IS_DCE8(rdev)) {
+		WREG32(vga_control_regs[radeon_crtc->crtc_id], vga_control);
+	}
 }
 
 static void atombios_powergate_crtc(struct drm_crtc *crtc, int state)
@@ -938,11 +958,14 @@ static bool atombios_crtc_prepare_pll(struct drm_crtc *crtc, struct drm_display_
 							radeon_atombios_get_ppll_ss_info(rdev,
 											 &radeon_crtc->ss,
 											 ATOM_DP_SS_ID1);
-				} else
+				} else {
 					radeon_crtc->ss_enabled =
 						radeon_atombios_get_ppll_ss_info(rdev,
 										 &radeon_crtc->ss,
 										 ATOM_DP_SS_ID1);
+				}
+				/* disable spread spectrum on DCE3 DP */
+				radeon_crtc->ss_enabled = false;
 			}
 			break;
 		case ATOM_ENCODER_MODE_LVDS:
diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c
index e950fabd7f5e..e9cde26088a0 100644
--- a/drivers/gpu/drm/radeon/cik.c
+++ b/drivers/gpu/drm/radeon/cik.c
@@ -3566,8 +3566,6 @@ bool cik_semaphore_ring_emit(struct radeon_device *rdev,
 			     struct radeon_semaphore *semaphore,
 			     bool emit_wait)
 {
-/* TODO: figure out why semaphore cause lockups */
-#if 0
 	uint64_t addr = semaphore->gpu_addr;
 	unsigned sel = emit_wait ? PACKET3_SEM_SEL_WAIT : PACKET3_SEM_SEL_SIGNAL;
 
@@ -3576,9 +3574,6 @@ bool cik_semaphore_ring_emit(struct radeon_device *rdev,
 	radeon_ring_write(ring, (upper_32_bits(addr) & 0xffff) | sel);
 
 	return true;
-#else
-	return false;
-#endif
 }
 
 /**
diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index 9702e55e924e..95ffe2a36a59 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -4298,8 +4298,8 @@ void evergreen_disable_interrupt_state(struct radeon_device *rdev)
 		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC5_REGISTER_OFFSET, 0);
 	}
 
-	/* only one DAC on DCE6 */
-	if (!ASIC_IS_DCE6(rdev))
+	/* only one DAC on DCE5 */
+	if (!ASIC_IS_DCE5(rdev))
 		WREG32(DACA_AUTODETECT_INT_CONTROL, 0);
 	WREG32(DACB_AUTODETECT_INT_CONTROL, 0);
 
diff --git a/drivers/gpu/drm/radeon/evergreen_cs.c b/drivers/gpu/drm/radeon/evergreen_cs.c
index eb8ac315f92f..c7cac07f139b 100644
--- a/drivers/gpu/drm/radeon/evergreen_cs.c
+++ b/drivers/gpu/drm/radeon/evergreen_cs.c
@@ -967,7 +967,10 @@ static int evergreen_cs_track_check(struct radeon_cs_parser *p)
 	if (track->cb_dirty) {
 		tmp = track->cb_target_mask;
 		for (i = 0; i < 8; i++) {
-			if ((tmp >> (i * 4)) & 0xF) {
+			u32 format = G_028C70_FORMAT(track->cb_color_info[i]);
+
+			if (format != V_028C70_COLOR_INVALID &&
+			    (tmp >> (i * 4)) & 0xF) {
 				/* at least one component is enabled */
 				if (track->cb_color_bo[i] == NULL) {
 					dev_warn(p->dev, "%s:%d mask 0x%08X | 0x%08X no cb for %d\n",
diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c
index f59a9e9fccf8..9eeb2a9689cf 100644
--- a/drivers/gpu/drm/radeon/ni.c
+++ b/drivers/gpu/drm/radeon/ni.c
@@ -1330,13 +1330,12 @@ void cayman_fence_ring_emit(struct radeon_device *rdev,
 {
 	struct radeon_ring *ring = &rdev->ring[fence->ring];
 	u64 addr = rdev->fence_drv[fence->ring].gpu_addr;
+	u32 cp_coher_cntl = PACKET3_FULL_CACHE_ENA | PACKET3_TC_ACTION_ENA |
+		PACKET3_SH_ACTION_ENA;
 
 	/* flush read cache over gart for this vmid */
-	radeon_ring_write(ring, PACKET3(PACKET3_SET_CONFIG_REG, 1));
-	radeon_ring_write(ring, (CP_COHER_CNTL2 - PACKET3_SET_CONFIG_REG_START) >> 2);
-	radeon_ring_write(ring, 0);
 	radeon_ring_write(ring, PACKET3(PACKET3_SURFACE_SYNC, 3));
-	radeon_ring_write(ring, PACKET3_TC_ACTION_ENA | PACKET3_SH_ACTION_ENA);
+	radeon_ring_write(ring, PACKET3_ENGINE_ME | cp_coher_cntl);
 	radeon_ring_write(ring, 0xFFFFFFFF);
 	radeon_ring_write(ring, 0);
 	radeon_ring_write(ring, 10); /* poll interval */
@@ -1352,6 +1351,8 @@ void cayman_fence_ring_emit(struct radeon_device *rdev,
 void cayman_ring_ib_execute(struct radeon_device *rdev, struct radeon_ib *ib)
 {
 	struct radeon_ring *ring = &rdev->ring[ib->ring];
+	u32 cp_coher_cntl = PACKET3_FULL_CACHE_ENA | PACKET3_TC_ACTION_ENA |
+		PACKET3_SH_ACTION_ENA;
 
 	/* set to DX10/11 mode */
 	radeon_ring_write(ring, PACKET3(PACKET3_MODE_CONTROL, 0));
@@ -1376,14 +1377,11 @@ void cayman_ring_ib_execute(struct radeon_device *rdev, struct radeon_ib *ib)
 			  (ib->vm ? (ib->vm->id << 24) : 0));
 
 	/* flush read cache over gart for this vmid */
-	radeon_ring_write(ring, PACKET3(PACKET3_SET_CONFIG_REG, 1));
-	radeon_ring_write(ring, (CP_COHER_CNTL2 - PACKET3_SET_CONFIG_REG_START) >> 2);
-	radeon_ring_write(ring, ib->vm ? ib->vm->id : 0);
 	radeon_ring_write(ring, PACKET3(PACKET3_SURFACE_SYNC, 3));
-	radeon_ring_write(ring, PACKET3_TC_ACTION_ENA | PACKET3_SH_ACTION_ENA);
+	radeon_ring_write(ring, PACKET3_ENGINE_ME | cp_coher_cntl);
 	radeon_ring_write(ring, 0xFFFFFFFF);
 	radeon_ring_write(ring, 0);
-	radeon_ring_write(ring, 10); /* poll interval */
+	radeon_ring_write(ring, ((ib->vm ? ib->vm->id : 0) << 24) | 10); /* poll interval */
 }
 
 static void cayman_cp_enable(struct radeon_device *rdev, bool enable)
diff --git a/drivers/gpu/drm/radeon/nid.h b/drivers/gpu/drm/radeon/nid.h
index 22421bc80c0d..d996033c243e 100644
--- a/drivers/gpu/drm/radeon/nid.h
+++ b/drivers/gpu/drm/radeon/nid.h
@@ -1154,6 +1154,7 @@
 #              define PACKET3_DB_ACTION_ENA        (1 << 26)
 #              define PACKET3_SH_ACTION_ENA        (1 << 27)
 #              define PACKET3_SX_ACTION_ENA        (1 << 28)
+#              define PACKET3_ENGINE_ME            (1 << 31)
 #define	PACKET3_ME_INITIALIZE				0x44
 #define		PACKET3_ME_INITIALIZE_DEVICE_ID(x) ((x) << 16)
 #define	PACKET3_COND_WRITE				0x45
diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index 9ad06732a78b..260b41902431 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -2607,14 +2607,17 @@ void r600_fence_ring_emit(struct radeon_device *rdev,
 			  struct radeon_fence *fence)
 {
 	struct radeon_ring *ring = &rdev->ring[fence->ring];
+	u32 cp_coher_cntl = PACKET3_TC_ACTION_ENA | PACKET3_VC_ACTION_ENA |
+		PACKET3_SH_ACTION_ENA;
+
+	if (rdev->family >= CHIP_RV770)
+		cp_coher_cntl |= PACKET3_FULL_CACHE_ENA;
 
 	if (rdev->wb.use_event) {
 		u64 addr = rdev->fence_drv[fence->ring].gpu_addr;
 		/* flush read cache over gart */
 		radeon_ring_write(ring, PACKET3(PACKET3_SURFACE_SYNC, 3));
-		radeon_ring_write(ring, PACKET3_TC_ACTION_ENA |
-					PACKET3_VC_ACTION_ENA |
-					PACKET3_SH_ACTION_ENA);
+		radeon_ring_write(ring, cp_coher_cntl);
 		radeon_ring_write(ring, 0xFFFFFFFF);
 		radeon_ring_write(ring, 0);
 		radeon_ring_write(ring, 10); /* poll interval */
@@ -2628,9 +2631,7 @@ void r600_fence_ring_emit(struct radeon_device *rdev,
 	} else {
 		/* flush read cache over gart */
 		radeon_ring_write(ring, PACKET3(PACKET3_SURFACE_SYNC, 3));
-		radeon_ring_write(ring, PACKET3_TC_ACTION_ENA |
-					PACKET3_VC_ACTION_ENA |
-					PACKET3_SH_ACTION_ENA);
+		radeon_ring_write(ring, cp_coher_cntl);
 		radeon_ring_write(ring, 0xFFFFFFFF);
 		radeon_ring_write(ring, 0);
 		radeon_ring_write(ring, 10); /* poll interval */
diff --git a/drivers/gpu/drm/radeon/r600_cs.c b/drivers/gpu/drm/radeon/r600_cs.c
index 5dceea6f71ae..56130bf6b9e3 100644
--- a/drivers/gpu/drm/radeon/r600_cs.c
+++ b/drivers/gpu/drm/radeon/r600_cs.c
@@ -749,7 +749,10 @@ static int r600_cs_track_check(struct radeon_cs_parser *p)
 		}
 
 		for (i = 0; i < 8; i++) {
-			if ((tmp >> (i * 4)) & 0xF) {
+			u32 format = G_0280A0_FORMAT(track->cb_color_info[i]);
+
+			if (format != V_0280A0_COLOR_INVALID &&
+			    (tmp >> (i * 4)) & 0xF) {
 				/* at least one component is enabled */
 				if (track->cb_color_bo[i] == NULL) {
 					dev_warn(p->dev, "%s:%d mask 0x%08X | 0x%08X no cb for %d\n",
diff --git a/drivers/gpu/drm/radeon/r600d.h b/drivers/gpu/drm/radeon/r600d.h
index ebe38724a976..ca92f4874c02 100644
--- a/drivers/gpu/drm/radeon/r600d.h
+++ b/drivers/gpu/drm/radeon/r600d.h
@@ -1575,6 +1575,7 @@
 #              define PACKET3_CP_DMA_CMD_DAIC      (1 << 29)
 #define	PACKET3_SURFACE_SYNC				0x43
 #              define PACKET3_CB0_DEST_BASE_ENA    (1 << 6)
+#              define PACKET3_FULL_CACHE_ENA       (1 << 20) /* r7xx+ only */
 #              define PACKET3_TC_ACTION_ENA        (1 << 23)
 #              define PACKET3_VC_ACTION_ENA        (1 << 24)
 #              define PACKET3_CB_ACTION_ENA        (1 << 25)
diff --git a/drivers/gpu/drm/radeon/radeon_atombios.c b/drivers/gpu/drm/radeon/radeon_atombios.c
index 5c39bf7c3d88..dfa641277175 100644
--- a/drivers/gpu/drm/radeon/radeon_atombios.c
+++ b/drivers/gpu/drm/radeon/radeon_atombios.c
@@ -3944,6 +3944,10 @@ void radeon_atom_initialize_bios_scratch_regs(struct drm_device *dev)
 	/* tell the bios not to handle mode switching */
 	bios_6_scratch |= ATOM_S6_ACC_BLOCK_DISPLAY_SWITCH;
 
+	/* clear the vbios dpms state */
+	if (ASIC_IS_DCE4(rdev))
+		bios_2_scratch &= ~ATOM_S2_DEVICE_DPMS_STATE;
+
 	if (rdev->family >= CHIP_R600) {
 		WREG32(R600_BIOS_2_SCRATCH, bios_2_scratch);
 		WREG32(R600_BIOS_6_SCRATCH, bios_6_scratch);
diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c
index db39ea36bf22..5fa8196c03e3 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.c
+++ b/drivers/gpu/drm/radeon/radeon_drv.c
@@ -400,6 +400,9 @@ static int radeon_pmops_runtime_suspend(struct device *dev)
 	if (radeon_runtime_pm == 0)
 		return -EINVAL;
 
+	if (radeon_runtime_pm == -1 && !radeon_is_px())
+		return -EINVAL;
+
 	drm_dev->switch_power_state = DRM_SWITCH_POWER_CHANGING;
 	drm_kms_helper_poll_disable(drm_dev);
 	vga_switcheroo_set_dynamic_switch(pdev, VGA_SWITCHEROO_OFF);
@@ -422,6 +425,9 @@ static int radeon_pmops_runtime_resume(struct device *dev)
 	if (radeon_runtime_pm == 0)
 		return -EINVAL;
 
+	if (radeon_runtime_pm == -1 && !radeon_is_px())
+		return -EINVAL;
+
 	drm_dev->switch_power_state = DRM_SWITCH_POWER_CHANGING;
 
 	pci_set_power_state(pdev, PCI_D0);
diff --git a/drivers/gpu/drm/radeon/radeon_i2c.c b/drivers/gpu/drm/radeon/radeon_i2c.c
index fc60b74ee304..e24ca6ab96de 100644
--- a/drivers/gpu/drm/radeon/radeon_i2c.c
+++ b/drivers/gpu/drm/radeon/radeon_i2c.c
@@ -1020,6 +1020,9 @@ void radeon_i2c_destroy(struct radeon_i2c_chan *i2c)
 /* Add the default buses */
 void radeon_i2c_init(struct radeon_device *rdev)
 {
+	if (radeon_hw_i2c)
+		DRM_INFO("hw_i2c forced on, you may experience display detection problems!\n");
+
 	if (rdev->is_atom_bios)
 		radeon_atombios_i2c_init(rdev);
 	else
diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c
index 984097b907ef..524b0914d13a 100644
--- a/drivers/gpu/drm/radeon/radeon_pm.c
+++ b/drivers/gpu/drm/radeon/radeon_pm.c
@@ -1010,8 +1010,10 @@ static void radeon_pm_resume_old(struct radeon_device *rdev)
 	rdev->pm.current_clock_mode_index = 0;
 	rdev->pm.current_sclk = rdev->pm.default_sclk;
 	rdev->pm.current_mclk = rdev->pm.default_mclk;
-	rdev->pm.current_vddc = rdev->pm.power_state[rdev->pm.default_power_state_index].clock_info[0].voltage.voltage;
-	rdev->pm.current_vddci = rdev->pm.power_state[rdev->pm.default_power_state_index].clock_info[0].voltage.vddci;
+	if (rdev->pm.power_state) {
+		rdev->pm.current_vddc = rdev->pm.power_state[rdev->pm.default_power_state_index].clock_info[0].voltage.voltage;
+		rdev->pm.current_vddci = rdev->pm.power_state[rdev->pm.default_power_state_index].clock_info[0].voltage.vddci;
+	}
 	if (rdev->pm.pm_method == PM_METHOD_DYNPM
 	    && rdev->pm.dynpm_state == DYNPM_STATE_SUSPENDED) {
 		rdev->pm.dynpm_state = DYNPM_STATE_ACTIVE;
@@ -1228,6 +1230,9 @@ int radeon_pm_init(struct radeon_device *rdev)
 	case CHIP_RV670:
 	case CHIP_RS780:
 	case CHIP_RS880:
+	case CHIP_BARTS:
+	case CHIP_TURKS:
+	case CHIP_CAICOS:
 	case CHIP_CAYMAN:
 	case CHIP_BONAIRE:
 	case CHIP_KABINI:
@@ -1257,9 +1262,6 @@ int radeon_pm_init(struct radeon_device *rdev)
 	case CHIP_PALM:
 	case CHIP_SUMO:
 	case CHIP_SUMO2:
-	case CHIP_BARTS:
-	case CHIP_TURKS:
-	case CHIP_CAICOS:
 	case CHIP_ARUBA:
 	case CHIP_TAHITI:
 	case CHIP_PITCAIRN:
diff --git a/drivers/gpu/drm/radeon/radeon_uvd.c b/drivers/gpu/drm/radeon/radeon_uvd.c
index b9c0529b4a2e..3d288a71978c 100644
--- a/drivers/gpu/drm/radeon/radeon_uvd.c
+++ b/drivers/gpu/drm/radeon/radeon_uvd.c
@@ -91,6 +91,7 @@ int radeon_uvd_init(struct radeon_device *rdev)
 	case CHIP_VERDE:
 	case CHIP_PITCAIRN:
 	case CHIP_ARUBA:
+	case CHIP_OLAND:
 		fw_name = FIRMWARE_TAHITI;
 		break;
 
diff --git a/drivers/gpu/drm/radeon/rv770_dpm.c b/drivers/gpu/drm/radeon/rv770_dpm.c
index 374499db20c7..a239b30aaf9d 100644
--- a/drivers/gpu/drm/radeon/rv770_dpm.c
+++ b/drivers/gpu/drm/radeon/rv770_dpm.c
@@ -2531,6 +2531,12 @@ bool rv770_dpm_vblank_too_short(struct radeon_device *rdev)
 	    (rdev->pdev->subsystem_device == 0x1c42))
 		switch_limit = 200;
 
+	/* RV770 */
+	/* mclk switching doesn't seem to work reliably on desktop RV770s */
+	if ((rdev->family == CHIP_RV770) &&
+	    !(rdev->flags & RADEON_IS_MOBILITY))
+		switch_limit = 0xffffffff; /* disable mclk switching */
+
 	if (vblank_time < switch_limit)
 		return true;
 	else
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index 85e1edfaa3be..398d0168e562 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -5566,7 +5566,7 @@ static void si_disable_interrupt_state(struct radeon_device *rdev)
 	}
 
 	if (!ASIC_IS_NODCE(rdev)) {
-		WREG32(DACA_AUTODETECT_INT_CONTROL, 0);
+		WREG32(DAC_AUTODETECT_INT_CONTROL, 0);
 
 		tmp = RREG32(DC_HPD1_INT_CONTROL) & DC_HPDx_INT_POLARITY;
 		WREG32(DC_HPD1_INT_CONTROL, tmp);
diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c
index 0b00c790fb77..0db9ce189a1d 100644
--- a/drivers/gpu/drm/radeon/si_dpm.c
+++ b/drivers/gpu/drm/radeon/si_dpm.c
@@ -3591,10 +3591,9 @@ static void si_program_display_gap(struct radeon_device *rdev)
 
 	/* Setting this to false forces the performance state to low if the crtcs are disabled.
 	 * This can be a problem on PowerXpress systems or if you want to use the card
-	 * for offscreen rendering or compute if there are no crtcs enabled.  Set it to
-	 * true for now so that performance scales even if the displays are off.
+	 * for offscreen rendering or compute if there are no crtcs enabled.
 	 */
-	si_notify_smc_display_change(rdev, true /*rdev->pm.dpm.new_active_crtc_count > 0*/);
+	si_notify_smc_display_change(rdev, rdev->pm.dpm.new_active_crtc_count > 0);
 }
 
 static void si_enable_spread_spectrum(struct radeon_device *rdev, bool enable)
diff --git a/drivers/gpu/drm/radeon/sid.h b/drivers/gpu/drm/radeon/sid.h
index b322acc48097..9a68e760a847 100644
--- a/drivers/gpu/drm/radeon/sid.h
+++ b/drivers/gpu/drm/radeon/sid.h
@@ -815,7 +815,7 @@
 #       define GRPH_PFLIP_INT_MASK                      (1 << 0)
 #       define GRPH_PFLIP_INT_TYPE                      (1 << 8)
 
-#define	DACA_AUTODETECT_INT_CONTROL			0x66c8
+#define	DAC_AUTODETECT_INT_CONTROL			0x67c8
 
 #define DC_HPD1_INT_STATUS                              0x601c
 #define DC_HPD2_INT_STATUS                              0x6028
diff --git a/drivers/gpu/drm/radeon/uvd_v2_2.c b/drivers/gpu/drm/radeon/uvd_v2_2.c
index b19ef4951085..824550db3fed 100644
--- a/drivers/gpu/drm/radeon/uvd_v2_2.c
+++ b/drivers/gpu/drm/radeon/uvd_v2_2.c
@@ -153,6 +153,7 @@ int uvd_v2_2_resume(struct radeon_device *rdev)
 		chip_id = 0x01000015;
 		break;
 	case CHIP_PITCAIRN:
+	case CHIP_OLAND:
 		chip_id = 0x01000016;
 		break;
 	case CHIP_ARUBA:
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_crtc.c b/drivers/gpu/drm/rcar-du/rcar_du_crtc.c
index a9d24e4bf792..c9511fd2f501 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_crtc.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_crtc.c
@@ -371,7 +371,6 @@ static int rcar_du_crtc_mode_set(struct drm_crtc *crtc,
 		goto error;
 
 	rcrtc->plane->format = format;
-	rcrtc->plane->pitch = crtc->fb->pitches[0];
 
 	rcrtc->plane->src_x = x;
 	rcrtc->plane->src_y = y;
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_plane.c b/drivers/gpu/drm/rcar-du/rcar_du_plane.c
index 53000644733f..3fb69d9ae61b 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_plane.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_plane.c
@@ -104,6 +104,15 @@ void rcar_du_plane_update_base(struct rcar_du_plane *plane)
 {
 	struct rcar_du_group *rgrp = plane->group;
 	unsigned int index = plane->hwindex;
+	u32 mwr;
+
+	/* Memory pitch (expressed in pixels) */
+	if (plane->format->planes == 2)
+		mwr = plane->pitch;
+	else
+		mwr = plane->pitch * 8 / plane->format->bpp;
+
+	rcar_du_plane_write(rgrp, index, PnMWR, mwr);
 
 	/* The Y position is expressed in raster line units and must be doubled
 	 * for 32bpp formats, according to the R8A7790 datasheet. No mention of
@@ -133,6 +142,8 @@ void rcar_du_plane_compute_base(struct rcar_du_plane *plane,
 {
 	struct drm_gem_cma_object *gem;
 
+	plane->pitch = fb->pitches[0];
+
 	gem = drm_fb_cma_get_gem_obj(fb, 0);
 	plane->dma[0] = gem->paddr + fb->offsets[0];
 
@@ -209,7 +220,6 @@ static void __rcar_du_plane_setup(struct rcar_du_plane *plane,
 	struct rcar_du_group *rgrp = plane->group;
 	u32 ddcr2 = PnDDCR2_CODE;
 	u32 ddcr4;
-	u32 mwr;
 
 	/* Data format
 	 *
@@ -240,14 +250,6 @@ static void __rcar_du_plane_setup(struct rcar_du_plane *plane,
 	rcar_du_plane_write(rgrp, index, PnDDCR2, ddcr2);
 	rcar_du_plane_write(rgrp, index, PnDDCR4, ddcr4);
 
-	/* Memory pitch (expressed in pixels) */
-	if (plane->format->planes == 2)
-		mwr = plane->pitch;
-	else
-		mwr = plane->pitch * 8 / plane->format->bpp;
-
-	rcar_du_plane_write(rgrp, index, PnMWR, mwr);
-
 	/* Destination position and size */
 	rcar_du_plane_write(rgrp, index, PnDSXR, plane->width);
 	rcar_du_plane_write(rgrp, index, PnDSYR, plane->height);
@@ -309,7 +311,6 @@ rcar_du_plane_update(struct drm_plane *plane, struct drm_crtc *crtc,
 
 	rplane->crtc = crtc;
 	rplane->format = format;
-	rplane->pitch = fb->pitches[0];
 
 	rplane->src_x = src_x >> 16;
 	rplane->src_y = src_y >> 16;
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
index c7a549694e59..6c792f714908 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
@@ -189,6 +189,7 @@ static int enable_fbdev = IS_ENABLED(CONFIG_DRM_VMWGFX_FBCON);
 static int vmw_force_iommu;
 static int vmw_restrict_iommu;
 static int vmw_force_coherent;
+static int vmw_restrict_dma_mask;
 
 static int vmw_probe(struct pci_dev *, const struct pci_device_id *);
 static void vmw_master_init(struct vmw_master *);
@@ -203,6 +204,8 @@ MODULE_PARM_DESC(restrict_iommu, "Try to limit IOMMU usage for TTM pages");
 module_param_named(restrict_iommu, vmw_restrict_iommu, int, 0600);
 MODULE_PARM_DESC(force_coherent, "Force coherent TTM pages");
 module_param_named(force_coherent, vmw_force_coherent, int, 0600);
+MODULE_PARM_DESC(restrict_dma_mask, "Restrict DMA mask to 44 bits with IOMMU");
+module_param_named(restrict_dma_mask, vmw_restrict_dma_mask, int, 0600);
 
 
 static void vmw_print_capabilities(uint32_t capabilities)
@@ -510,6 +513,33 @@ out_fixup:
 	return 0;
 }
 
+/**
+ * vmw_dma_masks - set required page- and dma masks
+ *
+ * @dev: Pointer to struct drm-device
+ *
+ * With 32-bit we can only handle 32 bit PFNs. Optionally set that
+ * restriction also for 64-bit systems.
+ */
+#ifdef CONFIG_INTEL_IOMMU
+static int vmw_dma_masks(struct vmw_private *dev_priv)
+{
+	struct drm_device *dev = dev_priv->dev;
+
+	if (intel_iommu_enabled &&
+	    (sizeof(unsigned long) == 4 || vmw_restrict_dma_mask)) {
+		DRM_INFO("Restricting DMA addresses to 44 bits.\n");
+		return dma_set_mask(dev->dev, DMA_BIT_MASK(44));
+	}
+	return 0;
+}
+#else
+static int vmw_dma_masks(struct vmw_private *dev_priv)
+{
+	return 0;
+}
+#endif
+
 static int vmw_driver_load(struct drm_device *dev, unsigned long chipset)
 {
 	struct vmw_private *dev_priv;
@@ -578,14 +608,9 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset)
 
 	vmw_get_initial_size(dev_priv);
 
-	if (dev_priv->capabilities & SVGA_CAP_GMR) {
-		dev_priv->max_gmr_descriptors =
-			vmw_read(dev_priv,
-				 SVGA_REG_GMR_MAX_DESCRIPTOR_LENGTH);
+	if (dev_priv->capabilities & SVGA_CAP_GMR2) {
 		dev_priv->max_gmr_ids =
 			vmw_read(dev_priv, SVGA_REG_GMR_MAX_IDS);
-	}
-	if (dev_priv->capabilities & SVGA_CAP_GMR2) {
 		dev_priv->max_gmr_pages =
 			vmw_read(dev_priv, SVGA_REG_GMRS_MAX_PAGES);
 		dev_priv->memory_size =
@@ -599,17 +624,17 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset)
 		dev_priv->memory_size = 512*1024*1024;
 	}
 
+	ret = vmw_dma_masks(dev_priv);
+	if (unlikely(ret != 0))
+		goto out_err0;
+
 	mutex_unlock(&dev_priv->hw_mutex);
 
 	vmw_print_capabilities(dev_priv->capabilities);
 
-	if (dev_priv->capabilities & SVGA_CAP_GMR) {
+	if (dev_priv->capabilities & SVGA_CAP_GMR2) {
 		DRM_INFO("Max GMR ids is %u\n",
 			 (unsigned)dev_priv->max_gmr_ids);
-		DRM_INFO("Max GMR descriptors is %u\n",
-			 (unsigned)dev_priv->max_gmr_descriptors);
-	}
-	if (dev_priv->capabilities & SVGA_CAP_GMR2) {
 		DRM_INFO("Max number of GMR pages is %u\n",
 			 (unsigned)dev_priv->max_gmr_pages);
 		DRM_INFO("Max dedicated hypervisor surface memory is %u kiB\n",
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
index 20890ad8408b..c0b73b9f437b 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
@@ -290,7 +290,6 @@ struct vmw_private {
 	__le32 __iomem *mmio_virt;
 	int mmio_mtrr;
 	uint32_t capabilities;
-	uint32_t max_gmr_descriptors;
 	uint32_t max_gmr_ids;
 	uint32_t max_gmr_pages;
 	uint32_t memory_size;
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
index 599f6469a1eb..8b059eb09d9b 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
@@ -1483,11 +1483,11 @@ int vmw_execbuf_process(struct drm_file *file_priv,
 	ret = vmw_cmd_check_all(dev_priv, sw_context, kernel_commands,
 				command_size);
 	if (unlikely(ret != 0))
-		goto out_err;
+		goto out_err_nores;
 
 	ret = vmw_resources_reserve(sw_context);
 	if (unlikely(ret != 0))
-		goto out_err;
+		goto out_err_nores;
 
 	ret = ttm_eu_reserve_buffers(&ticket, &sw_context->validate_nodes);
 	if (unlikely(ret != 0))
@@ -1569,10 +1569,11 @@ int vmw_execbuf_process(struct drm_file *file_priv,
 	return 0;
 
 out_err:
-	vmw_resource_relocations_free(&sw_context->res_relocations);
-	vmw_free_relocations(sw_context);
 	ttm_eu_backoff_reservation(&ticket, &sw_context->validate_nodes);
+out_err_nores:
 	vmw_resource_list_unreserve(&sw_context->resource_list, true);
+	vmw_resource_relocations_free(&sw_context->res_relocations);
+	vmw_free_relocations(sw_context);
 	vmw_clear_validations(sw_context);
 	if (unlikely(dev_priv->pinned_bo != NULL &&
 		     !dev_priv->query_cid_valid))
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_gmr.c b/drivers/gpu/drm/vmwgfx/vmwgfx_gmr.c
index 6ef0b035becb..61d8d803199f 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_gmr.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_gmr.c
@@ -125,181 +125,27 @@ static void vmw_gmr2_unbind(struct vmw_private *dev_priv,
 }
 
 
-static void vmw_gmr_free_descriptors(struct device *dev, dma_addr_t desc_dma,
-				     struct list_head *desc_pages)
-{
-	struct page *page, *next;
-	struct svga_guest_mem_descriptor *page_virtual;
-	unsigned int desc_per_page = PAGE_SIZE /
-		sizeof(struct svga_guest_mem_descriptor) - 1;
-
-	if (list_empty(desc_pages))
-		return;
-
-	list_for_each_entry_safe(page, next, desc_pages, lru) {
-		list_del_init(&page->lru);
-
-		if (likely(desc_dma != DMA_ADDR_INVALID)) {
-			dma_unmap_page(dev, desc_dma, PAGE_SIZE,
-				       DMA_TO_DEVICE);
-		}
-
-		page_virtual = kmap_atomic(page);
-		desc_dma = (dma_addr_t)
-			le32_to_cpu(page_virtual[desc_per_page].ppn) <<
-			PAGE_SHIFT;
-		kunmap_atomic(page_virtual);
-
-		__free_page(page);
-	}
-}
-
-/**
- * FIXME: Adjust to the ttm lowmem / highmem storage to minimize
- * the number of used descriptors.
- *
- */
-
-static int vmw_gmr_build_descriptors(struct device *dev,
-				     struct list_head *desc_pages,
-				     struct vmw_piter *iter,
-				     unsigned long num_pages,
-				     dma_addr_t *first_dma)
-{
-	struct page *page;
-	struct svga_guest_mem_descriptor *page_virtual = NULL;
-	struct svga_guest_mem_descriptor *desc_virtual = NULL;
-	unsigned int desc_per_page;
-	unsigned long prev_pfn;
-	unsigned long pfn;
-	int ret;
-	dma_addr_t desc_dma;
-
-	desc_per_page = PAGE_SIZE /
-	    sizeof(struct svga_guest_mem_descriptor) - 1;
-
-	while (likely(num_pages != 0)) {
-		page = alloc_page(__GFP_HIGHMEM);
-		if (unlikely(page == NULL)) {
-			ret = -ENOMEM;
-			goto out_err;
-		}
-
-		list_add_tail(&page->lru, desc_pages);
-		page_virtual = kmap_atomic(page);
-		desc_virtual = page_virtual - 1;
-		prev_pfn = ~(0UL);
-
-		while (likely(num_pages != 0)) {
-			pfn = vmw_piter_dma_addr(iter) >> PAGE_SHIFT;
-
-			if (pfn != prev_pfn + 1) {
-
-				if (desc_virtual - page_virtual ==
-				    desc_per_page - 1)
-					break;
-
-				(++desc_virtual)->ppn = cpu_to_le32(pfn);
-				desc_virtual->num_pages = cpu_to_le32(1);
-			} else {
-				uint32_t tmp =
-				    le32_to_cpu(desc_virtual->num_pages);
-				desc_virtual->num_pages = cpu_to_le32(tmp + 1);
-			}
-			prev_pfn = pfn;
-			--num_pages;
-			vmw_piter_next(iter);
-		}
-
-		(++desc_virtual)->ppn = DMA_PAGE_INVALID;
-		desc_virtual->num_pages = cpu_to_le32(0);
-		kunmap_atomic(page_virtual);
-	}
-
-	desc_dma = 0;
-	list_for_each_entry_reverse(page, desc_pages, lru) {
-		page_virtual = kmap_atomic(page);
-		page_virtual[desc_per_page].ppn = cpu_to_le32
-			(desc_dma >> PAGE_SHIFT);
-		kunmap_atomic(page_virtual);
-		desc_dma = dma_map_page(dev, page, 0, PAGE_SIZE,
-					DMA_TO_DEVICE);
-
-		if (unlikely(dma_mapping_error(dev, desc_dma)))
-			goto out_err;
-	}
-	*first_dma = desc_dma;
-
-	return 0;
-out_err:
-	vmw_gmr_free_descriptors(dev, DMA_ADDR_INVALID, desc_pages);
-	return ret;
-}
-
-static void vmw_gmr_fire_descriptors(struct vmw_private *dev_priv,
-				     int gmr_id, dma_addr_t desc_dma)
-{
-	mutex_lock(&dev_priv->hw_mutex);
-
-	vmw_write(dev_priv, SVGA_REG_GMR_ID, gmr_id);
-	wmb();
-	vmw_write(dev_priv, SVGA_REG_GMR_DESCRIPTOR, desc_dma >> PAGE_SHIFT);
-	mb();
-
-	mutex_unlock(&dev_priv->hw_mutex);
-
-}
-
 int vmw_gmr_bind(struct vmw_private *dev_priv,
 		 const struct vmw_sg_table *vsgt,
 		 unsigned long num_pages,
 		 int gmr_id)
 {
-	struct list_head desc_pages;
-	dma_addr_t desc_dma = 0;
-	struct device *dev = dev_priv->dev->dev;
 	struct vmw_piter data_iter;
-	int ret;
 
 	vmw_piter_start(&data_iter, vsgt, 0);
 
 	if (unlikely(!vmw_piter_next(&data_iter)))
 		return 0;
 
-	if (likely(dev_priv->capabilities & SVGA_CAP_GMR2))
-		return vmw_gmr2_bind(dev_priv, &data_iter, num_pages, gmr_id);
-
-	if (unlikely(!(dev_priv->capabilities & SVGA_CAP_GMR)))
-		return -EINVAL;
-
-	if (vsgt->num_regions > dev_priv->max_gmr_descriptors)
+	if (unlikely(!(dev_priv->capabilities & SVGA_CAP_GMR2)))
 		return -EINVAL;
 
-	INIT_LIST_HEAD(&desc_pages);
-
-	ret = vmw_gmr_build_descriptors(dev, &desc_pages, &data_iter,
-					num_pages, &desc_dma);
-	if (unlikely(ret != 0))
-		return ret;
-
-	vmw_gmr_fire_descriptors(dev_priv, gmr_id, desc_dma);
-	vmw_gmr_free_descriptors(dev, desc_dma, &desc_pages);
-
-	return 0;
+	return vmw_gmr2_bind(dev_priv, &data_iter, num_pages, gmr_id);
 }
 
 
 void vmw_gmr_unbind(struct vmw_private *dev_priv, int gmr_id)
 {
-	if (likely(dev_priv->capabilities & SVGA_CAP_GMR2)) {
+	if (likely(dev_priv->capabilities & SVGA_CAP_GMR2))
 		vmw_gmr2_unbind(dev_priv, gmr_id);
-		return;
-	}
-
-	mutex_lock(&dev_priv->hw_mutex);
-	vmw_write(dev_priv, SVGA_REG_GMR_ID, gmr_id);
-	wmb();
-	vmw_write(dev_priv, SVGA_REG_GMR_DESCRIPTOR, 0);
-	mb();
-	mutex_unlock(&dev_priv->hw_mutex);
 }
diff --git a/drivers/infiniband/hw/qib/qib_ud.c b/drivers/infiniband/hw/qib/qib_ud.c
index d6c7fe7f88d5..3ad651c3356c 100644
--- a/drivers/infiniband/hw/qib/qib_ud.c
+++ b/drivers/infiniband/hw/qib/qib_ud.c
@@ -57,13 +57,20 @@ static void qib_ud_loopback(struct qib_qp *sqp, struct qib_swqe *swqe)
 	struct qib_sge *sge;
 	struct ib_wc wc;
 	u32 length;
+	enum ib_qp_type sqptype, dqptype;
 
 	qp = qib_lookup_qpn(ibp, swqe->wr.wr.ud.remote_qpn);
 	if (!qp) {
 		ibp->n_pkt_drops++;
 		return;
 	}
-	if (qp->ibqp.qp_type != sqp->ibqp.qp_type ||
+
+	sqptype = sqp->ibqp.qp_type == IB_QPT_GSI ?
+			IB_QPT_UD : sqp->ibqp.qp_type;
+	dqptype = qp->ibqp.qp_type == IB_QPT_GSI ?
+			IB_QPT_UD : qp->ibqp.qp_type;
+
+	if (dqptype != sqptype ||
 	    !(ib_qib_state_ops[qp->state] & QIB_PROCESS_RECV_OK)) {
 		ibp->n_pkt_drops++;
 		goto drop;
diff --git a/drivers/input/misc/xen-kbdfront.c b/drivers/input/misc/xen-kbdfront.c
index e21c1816a8f9..fbfdc10573be 100644
--- a/drivers/input/misc/xen-kbdfront.c
+++ b/drivers/input/misc/xen-kbdfront.c
@@ -29,6 +29,7 @@
 #include <xen/interface/io/fbif.h>
 #include <xen/interface/io/kbdif.h>
 #include <xen/xenbus.h>
+#include <xen/platform_pci.h>
 
 struct xenkbd_info {
 	struct input_dev *kbd;
@@ -380,6 +381,9 @@ static int __init xenkbd_init(void)
 	if (xen_initial_domain())
 		return -ENODEV;
 
+	if (!xen_has_pv_devices())
+		return -ENODEV;
+
 	return xenbus_register_frontend(&xenkbd_driver);
 }
 
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 43b9bfea48fa..59779e19315e 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -917,7 +917,7 @@ static void dma_pte_free_level(struct dmar_domain *domain, int level,
 
 		/* If range covers entire pagetable, free it */
 		if (!(start_pfn > level_pfn ||
-		      last_pfn < level_pfn + level_size(level))) {
+		      last_pfn < level_pfn + level_size(level) - 1)) {
 			dma_clear_pte(pte);
 			domain_flush_cache(domain, pte, sizeof(*pte));
 			free_pgtable_page(level_pte);
diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig
index f2ccbc3b9fe4..006e57bd4f53 100644
--- a/drivers/md/Kconfig
+++ b/drivers/md/Kconfig
@@ -176,8 +176,12 @@ config MD_FAULTY
 
 source "drivers/md/bcache/Kconfig"
 
+config BLK_DEV_DM_BUILTIN
+	boolean
+
 config BLK_DEV_DM
 	tristate "Device mapper support"
+	select BLK_DEV_DM_BUILTIN
 	---help---
 	  Device-mapper is a low level volume manager.  It works by allowing
 	  people to specify mappings for ranges of logical sectors.  Various
diff --git a/drivers/md/Makefile b/drivers/md/Makefile
index 2acc43fe0229..f26d83292579 100644
--- a/drivers/md/Makefile
+++ b/drivers/md/Makefile
@@ -32,6 +32,7 @@ obj-$(CONFIG_MD_FAULTY)		+= faulty.o
 obj-$(CONFIG_BCACHE)		+= bcache/
 obj-$(CONFIG_BLK_DEV_MD)	+= md-mod.o
 obj-$(CONFIG_BLK_DEV_DM)	+= dm-mod.o
+obj-$(CONFIG_BLK_DEV_DM_BUILTIN) += dm-builtin.o
 obj-$(CONFIG_DM_BUFIO)		+= dm-bufio.o
 obj-$(CONFIG_DM_BIO_PRISON)	+= dm-bio-prison.o
 obj-$(CONFIG_DM_CRYPT)		+= dm-crypt.o
diff --git a/drivers/md/dm-builtin.c b/drivers/md/dm-builtin.c
new file mode 100644
index 000000000000..6c9049c51b2b
--- /dev/null
+++ b/drivers/md/dm-builtin.c
@@ -0,0 +1,48 @@
+#include "dm.h"
+
+/*
+ * The kobject release method must not be placed in the module itself,
+ * otherwise we are subject to module unload races.
+ *
+ * The release method is called when the last reference to the kobject is
+ * dropped. It may be called by any other kernel code that drops the last
+ * reference.
+ *
+ * The release method suffers from module unload race. We may prevent the
+ * module from being unloaded at the start of the release method (using
+ * increased module reference count or synchronizing against the release
+ * method), however there is no way to prevent the module from being
+ * unloaded at the end of the release method.
+ *
+ * If this code were placed in the dm module, the following race may
+ * happen:
+ *  1. Some other process takes a reference to dm kobject
+ *  2. The user issues ioctl function to unload the dm device
+ *  3. dm_sysfs_exit calls kobject_put, however the object is not released
+ *     because of the other reference taken at step 1
+ *  4. dm_sysfs_exit waits on the completion
+ *  5. The other process that took the reference in step 1 drops it,
+ *     dm_kobject_release is called from this process
+ *  6. dm_kobject_release calls complete()
+ *  7. a reschedule happens before dm_kobject_release returns
+ *  8. dm_sysfs_exit continues, the dm device is unloaded, module reference
+ *     count is decremented
+ *  9. The user unloads the dm module
+ * 10. The other process that was rescheduled in step 7 continues to run,
+ *     it is now executing code in unloaded module, so it crashes
+ *
+ * Note that if the process that takes the foreign reference to dm kobject
+ * has a low priority and the system is sufficiently loaded with
+ * higher-priority processes that prevent the low-priority process from
+ * being scheduled long enough, this bug may really happen.
+ *
+ * In order to fix this module unload race, we place the release method
+ * into a helper code that is compiled directly into the kernel.
+ */
+
+void dm_kobject_release(struct kobject *kobj)
+{
+	complete(dm_get_completion_from_kobject(kobj));
+}
+
+EXPORT_SYMBOL(dm_kobject_release);
diff --git a/drivers/md/dm-sysfs.c b/drivers/md/dm-sysfs.c
index 84d2b91e4efb..c62c5ab6aed5 100644
--- a/drivers/md/dm-sysfs.c
+++ b/drivers/md/dm-sysfs.c
@@ -86,6 +86,7 @@ static const struct sysfs_ops dm_sysfs_ops = {
 static struct kobj_type dm_ktype = {
 	.sysfs_ops	= &dm_sysfs_ops,
 	.default_attrs	= dm_attrs,
+	.release	= dm_kobject_release,
 };
 
 /*
@@ -104,5 +105,7 @@ int dm_sysfs_init(struct mapped_device *md)
  */
 void dm_sysfs_exit(struct mapped_device *md)
 {
-	kobject_put(dm_kobject(md));
+	struct kobject *kobj = dm_kobject(md);
+	kobject_put(kobj);
+	wait_for_completion(dm_get_completion_from_kobject(kobj));
 }
diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c
index 8a30ad54bd46..7da347665552 100644
--- a/drivers/md/dm-thin-metadata.c
+++ b/drivers/md/dm-thin-metadata.c
@@ -1349,6 +1349,12 @@ dm_thin_id dm_thin_dev_id(struct dm_thin_device *td)
 	return td->id;
 }
 
+/*
+ * Check whether @time (of block creation) is older than @td's last snapshot.
+ * If so then the associated block is shared with the last snapshot device.
+ * Any block on a device created *after* the device last got snapshotted is
+ * necessarily not shared.
+ */
 static bool __snapshotted_since(struct dm_thin_device *td, uint32_t time)
 {
 	return td->snapshotted_time > time;
@@ -1458,6 +1464,20 @@ int dm_thin_remove_block(struct dm_thin_device *td, dm_block_t block)
 	return r;
 }
 
+int dm_pool_block_is_used(struct dm_pool_metadata *pmd, dm_block_t b, bool *result)
+{
+	int r;
+	uint32_t ref_count;
+
+	down_read(&pmd->root_lock);
+	r = dm_sm_get_count(pmd->data_sm, b, &ref_count);
+	if (!r)
+		*result = (ref_count != 0);
+	up_read(&pmd->root_lock);
+
+	return r;
+}
+
 bool dm_thin_changed_this_transaction(struct dm_thin_device *td)
 {
 	int r;
diff --git a/drivers/md/dm-thin-metadata.h b/drivers/md/dm-thin-metadata.h
index 7bcc0e1d6238..2edf5dbac76a 100644
--- a/drivers/md/dm-thin-metadata.h
+++ b/drivers/md/dm-thin-metadata.h
@@ -181,6 +181,8 @@ int dm_pool_get_data_block_size(struct dm_pool_metadata *pmd, sector_t *result);
 
 int dm_pool_get_data_dev_size(struct dm_pool_metadata *pmd, dm_block_t *result);
 
+int dm_pool_block_is_used(struct dm_pool_metadata *pmd, dm_block_t b, bool *result);
+
 /*
  * Returns -ENOSPC if the new size is too small and already allocated
  * blocks would be lost.
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index ee29037ffc2e..bc0c97d7921e 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -512,6 +512,7 @@ struct dm_thin_new_mapping {
 	unsigned quiesced:1;
 	unsigned prepared:1;
 	unsigned pass_discard:1;
+	unsigned definitely_not_shared:1;
 
 	struct thin_c *tc;
 	dm_block_t virt_block;
@@ -683,7 +684,15 @@ static void process_prepared_discard_passdown(struct dm_thin_new_mapping *m)
 	cell_defer_no_holder(tc, m->cell2);
 
 	if (m->pass_discard)
-		remap_and_issue(tc, m->bio, m->data_block);
+		if (m->definitely_not_shared)
+			remap_and_issue(tc, m->bio, m->data_block);
+		else {
+			bool used = false;
+			if (dm_pool_block_is_used(tc->pool->pmd, m->data_block, &used) || used)
+				bio_endio(m->bio, 0);
+			else
+				remap_and_issue(tc, m->bio, m->data_block);
+		}
 	else
 		bio_endio(m->bio, 0);
 
@@ -751,13 +760,17 @@ static int ensure_next_mapping(struct pool *pool)
 
 static struct dm_thin_new_mapping *get_next_mapping(struct pool *pool)
 {
-	struct dm_thin_new_mapping *r = pool->next_mapping;
+	struct dm_thin_new_mapping *m = pool->next_mapping;
 
 	BUG_ON(!pool->next_mapping);
 
+	memset(m, 0, sizeof(struct dm_thin_new_mapping));
+	INIT_LIST_HEAD(&m->list);
+	m->bio = NULL;
+
 	pool->next_mapping = NULL;
 
-	return r;
+	return m;
 }
 
 static void schedule_copy(struct thin_c *tc, dm_block_t virt_block,
@@ -769,15 +782,10 @@ static void schedule_copy(struct thin_c *tc, dm_block_t virt_block,
 	struct pool *pool = tc->pool;
 	struct dm_thin_new_mapping *m = get_next_mapping(pool);
 
-	INIT_LIST_HEAD(&m->list);
-	m->quiesced = 0;
-	m->prepared = 0;
 	m->tc = tc;
 	m->virt_block = virt_block;
 	m->data_block = data_dest;
 	m->cell = cell;
-	m->err = 0;
-	m->bio = NULL;
 
 	if (!dm_deferred_set_add_work(pool->shared_read_ds, &m->list))
 		m->quiesced = 1;
@@ -840,15 +848,12 @@ static void schedule_zero(struct thin_c *tc, dm_block_t virt_block,
 	struct pool *pool = tc->pool;
 	struct dm_thin_new_mapping *m = get_next_mapping(pool);
 
-	INIT_LIST_HEAD(&m->list);
 	m->quiesced = 1;
 	m->prepared = 0;
 	m->tc = tc;
 	m->virt_block = virt_block;
 	m->data_block = data_block;
 	m->cell = cell;
-	m->err = 0;
-	m->bio = NULL;
 
 	/*
 	 * If the whole block of data is being overwritten or we are not
@@ -1040,12 +1045,12 @@ static void process_discard(struct thin_c *tc, struct bio *bio)
 			 */
 			m = get_next_mapping(pool);
 			m->tc = tc;
-			m->pass_discard = (!lookup_result.shared) && pool->pf.discard_passdown;
+			m->pass_discard = pool->pf.discard_passdown;
+			m->definitely_not_shared = !lookup_result.shared;
 			m->virt_block = block;
 			m->data_block = lookup_result.block;
 			m->cell = cell;
 			m->cell2 = cell2;
-			m->err = 0;
 			m->bio = bio;
 
 			if (!dm_deferred_set_add_work(pool->all_io_ds, &m->list)) {
@@ -1390,16 +1395,16 @@ static enum pool_mode get_pool_mode(struct pool *pool)
 	return pool->pf.mode;
 }
 
-static void set_pool_mode(struct pool *pool, enum pool_mode mode)
+static void set_pool_mode(struct pool *pool, enum pool_mode new_mode)
 {
 	int r;
+	enum pool_mode old_mode = pool->pf.mode;
 
-	pool->pf.mode = mode;
-
-	switch (mode) {
+	switch (new_mode) {
 	case PM_FAIL:
-		DMERR("%s: switching pool to failure mode",
-		      dm_device_name(pool->pool_md));
+		if (old_mode != new_mode)
+			DMERR("%s: switching pool to failure mode",
+			      dm_device_name(pool->pool_md));
 		dm_pool_metadata_read_only(pool->pmd);
 		pool->process_bio = process_bio_fail;
 		pool->process_discard = process_bio_fail;
@@ -1408,13 +1413,15 @@ static void set_pool_mode(struct pool *pool, enum pool_mode mode)
 		break;
 
 	case PM_READ_ONLY:
-		DMERR("%s: switching pool to read-only mode",
-		      dm_device_name(pool->pool_md));
+		if (old_mode != new_mode)
+			DMERR("%s: switching pool to read-only mode",
+			      dm_device_name(pool->pool_md));
 		r = dm_pool_abort_metadata(pool->pmd);
 		if (r) {
 			DMERR("%s: aborting transaction failed",
 			      dm_device_name(pool->pool_md));
-			set_pool_mode(pool, PM_FAIL);
+			new_mode = PM_FAIL;
+			set_pool_mode(pool, new_mode);
 		} else {
 			dm_pool_metadata_read_only(pool->pmd);
 			pool->process_bio = process_bio_read_only;
@@ -1425,6 +1432,9 @@ static void set_pool_mode(struct pool *pool, enum pool_mode mode)
 		break;
 
 	case PM_WRITE:
+		if (old_mode != new_mode)
+			DMINFO("%s: switching pool to write mode",
+			       dm_device_name(pool->pool_md));
 		dm_pool_metadata_read_write(pool->pmd);
 		pool->process_bio = process_bio;
 		pool->process_discard = process_discard;
@@ -1432,6 +1442,8 @@ static void set_pool_mode(struct pool *pool, enum pool_mode mode)
 		pool->process_prepared_discard = process_prepared_discard;
 		break;
 	}
+
+	pool->pf.mode = new_mode;
 }
 
 /*----------------------------------------------------------------*/
@@ -1648,6 +1660,17 @@ static int bind_control_target(struct pool *pool, struct dm_target *ti)
 	enum pool_mode new_mode = pt->adjusted_pf.mode;
 
 	/*
+	 * Don't change the pool's mode until set_pool_mode() below.
+	 * Otherwise the pool's process_* function pointers may
+	 * not match the desired pool mode.
+	 */
+	pt->adjusted_pf.mode = old_mode;
+
+	pool->ti = ti;
+	pool->pf = pt->adjusted_pf;
+	pool->low_water_blocks = pt->low_water_blocks;
+
+	/*
 	 * If we were in PM_FAIL mode, rollback of metadata failed.  We're
 	 * not going to recover without a thin_repair.  So we never let the
 	 * pool move out of the old mode.  On the other hand a PM_READ_ONLY
@@ -1657,10 +1680,6 @@ static int bind_control_target(struct pool *pool, struct dm_target *ti)
 	if (old_mode == PM_FAIL)
 		new_mode = old_mode;
 
-	pool->ti = ti;
-	pool->low_water_blocks = pt->low_water_blocks;
-	pool->pf = pt->adjusted_pf;
-
 	set_pool_mode(pool, new_mode);
 
 	return 0;
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 0704c523a76b..b49c76284241 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -200,8 +200,8 @@ struct mapped_device {
 	/* forced geometry settings */
 	struct hd_geometry geometry;
 
-	/* sysfs handle */
-	struct kobject kobj;
+	/* kobject and completion */
+	struct dm_kobject_holder kobj_holder;
 
 	/* zero-length flush that will be cloned and submitted to targets */
 	struct bio flush_bio;
@@ -2041,6 +2041,7 @@ static struct mapped_device *alloc_dev(int minor)
 	init_waitqueue_head(&md->wait);
 	INIT_WORK(&md->work, dm_wq_work);
 	init_waitqueue_head(&md->eventq);
+	init_completion(&md->kobj_holder.completion);
 
 	md->disk->major = _major;
 	md->disk->first_minor = minor;
@@ -2902,20 +2903,14 @@ struct gendisk *dm_disk(struct mapped_device *md)
 
 struct kobject *dm_kobject(struct mapped_device *md)
 {
-	return &md->kobj;
+	return &md->kobj_holder.kobj;
 }
 
-/*
- * struct mapped_device should not be exported outside of dm.c
- * so use this check to verify that kobj is part of md structure
- */
 struct mapped_device *dm_get_from_kobject(struct kobject *kobj)
 {
 	struct mapped_device *md;
 
-	md = container_of(kobj, struct mapped_device, kobj);
-	if (&md->kobj != kobj)
-		return NULL;
+	md = container_of(kobj, struct mapped_device, kobj_holder.kobj);
 
 	if (test_bit(DMF_FREEING, &md->flags) ||
 	    dm_deleting_md(md))
diff --git a/drivers/md/dm.h b/drivers/md/dm.h
index c57ba550f69e..c4569f02f50f 100644
--- a/drivers/md/dm.h
+++ b/drivers/md/dm.h
@@ -15,6 +15,8 @@
 #include <linux/list.h>
 #include <linux/blkdev.h>
 #include <linux/hdreg.h>
+#include <linux/completion.h>
+#include <linux/kobject.h>
 
 #include "dm-stats.h"
 
@@ -148,12 +150,27 @@ void dm_interface_exit(void);
 /*
  * sysfs interface
  */
+struct dm_kobject_holder {
+	struct kobject kobj;
+	struct completion completion;
+};
+
+static inline struct completion *dm_get_completion_from_kobject(struct kobject *kobj)
+{
+	return &container_of(kobj, struct dm_kobject_holder, kobj)->completion;
+}
+
 int dm_sysfs_init(struct mapped_device *md);
 void dm_sysfs_exit(struct mapped_device *md);
 struct kobject *dm_kobject(struct mapped_device *md);
 struct mapped_device *dm_get_from_kobject(struct kobject *kobj);
 
 /*
+ * The kobject helper
+ */
+void dm_kobject_release(struct kobject *kobj);
+
+/*
  * Targets for linear and striped mappings
  */
 int dm_linear_init(void);
diff --git a/drivers/md/persistent-data/dm-space-map-common.c b/drivers/md/persistent-data/dm-space-map-common.c
index 466a60bbd716..aacbe70c2c2e 100644
--- a/drivers/md/persistent-data/dm-space-map-common.c
+++ b/drivers/md/persistent-data/dm-space-map-common.c
@@ -245,6 +245,10 @@ int sm_ll_extend(struct ll_disk *ll, dm_block_t extra_blocks)
 		return -EINVAL;
 	}
 
+	/*
+	 * We need to set this before the dm_tm_new_block() call below.
+	 */
+	ll->nr_blocks = nr_blocks;
 	for (i = old_blocks; i < blocks; i++) {
 		struct dm_block *b;
 		struct disk_index_entry idx;
@@ -252,6 +256,7 @@ int sm_ll_extend(struct ll_disk *ll, dm_block_t extra_blocks)
 		r = dm_tm_new_block(ll->tm, &dm_sm_bitmap_validator, &b);
 		if (r < 0)
 			return r;
+
 		idx.blocknr = cpu_to_le64(dm_block_location(b));
 
 		r = dm_tm_unlock(ll->tm, b);
@@ -266,7 +271,6 @@ int sm_ll_extend(struct ll_disk *ll, dm_block_t extra_blocks)
 			return r;
 	}
 
-	ll->nr_blocks = nr_blocks;
 	return 0;
 }
 
diff --git a/drivers/md/persistent-data/dm-space-map-metadata.c b/drivers/md/persistent-data/dm-space-map-metadata.c
index 58fc1eef7499..afb419e514bf 100644
--- a/drivers/md/persistent-data/dm-space-map-metadata.c
+++ b/drivers/md/persistent-data/dm-space-map-metadata.c
@@ -608,20 +608,38 @@ static int sm_metadata_extend(struct dm_space_map *sm, dm_block_t extra_blocks)
 	 * Flick into a mode where all blocks get allocated in the new area.
 	 */
 	smm->begin = old_len;
-	memcpy(&smm->sm, &bootstrap_ops, sizeof(smm->sm));
+	memcpy(sm, &bootstrap_ops, sizeof(*sm));
 
 	/*
 	 * Extend.
 	 */
 	r = sm_ll_extend(&smm->ll, extra_blocks);
+	if (r)
+		goto out;
 
 	/*
-	 * Switch back to normal behaviour.
+	 * We repeatedly increment then commit until the commit doesn't
+	 * allocate any new blocks.
 	 */
-	memcpy(&smm->sm, &ops, sizeof(smm->sm));
-	for (i = old_len; !r && i < smm->begin; i++)
-		r = sm_ll_inc(&smm->ll, i, &ev);
+	do {
+		for (i = old_len; !r && i < smm->begin; i++) {
+			r = sm_ll_inc(&smm->ll, i, &ev);
+			if (r)
+				goto out;
+		}
+		old_len = smm->begin;
+
+		r = sm_ll_commit(&smm->ll);
+		if (r)
+			goto out;
+
+	} while (old_len != smm->begin);
 
+out:
+	/*
+	 * Switch back to normal behaviour.
+	 */
+	memcpy(sm, &ops, sizeof(*sm));
 	return r;
 }
 
diff --git a/drivers/media/dvb-core/dvb-usb-ids.h b/drivers/media/dvb-core/dvb-usb-ids.h
index 419a2d6b4349..7e0f61930a12 100644
--- a/drivers/media/dvb-core/dvb-usb-ids.h
+++ b/drivers/media/dvb-core/dvb-usb-ids.h
@@ -239,6 +239,7 @@
 #define USB_PID_AVERMEDIA_A835B_4835			0x4835
 #define USB_PID_AVERMEDIA_1867				0x1867
 #define USB_PID_AVERMEDIA_A867				0xa867
+#define USB_PID_AVERMEDIA_H335				0x0335
 #define USB_PID_AVERMEDIA_TWINSTAR			0x0825
 #define USB_PID_TECHNOTREND_CONNECT_S2400               0x3006
 #define USB_PID_TECHNOTREND_CONNECT_S2400_8KEEPROM	0x3009
diff --git a/drivers/media/dvb-frontends/dib8000.c b/drivers/media/dvb-frontends/dib8000.c
index 6dbbee453ee1..36c839cabe82 100644
--- a/drivers/media/dvb-frontends/dib8000.c
+++ b/drivers/media/dvb-frontends/dib8000.c
@@ -157,15 +157,10 @@ static u16 dib8000_i2c_read16(struct i2c_device *i2c, u16 reg)
 	return ret;
 }
 
-static u16 dib8000_read_word(struct dib8000_state *state, u16 reg)
+static u16 __dib8000_read_word(struct dib8000_state *state, u16 reg)
 {
 	u16 ret;
 
-	if (mutex_lock_interruptible(&state->i2c_buffer_lock) < 0) {
-		dprintk("could not acquire lock");
-		return 0;
-	}
-
 	state->i2c_write_buffer[0] = reg >> 8;
 	state->i2c_write_buffer[1] = reg & 0xff;
 
@@ -183,6 +178,21 @@ static u16 dib8000_read_word(struct dib8000_state *state, u16 reg)
 		dprintk("i2c read error on %d", reg);
 
 	ret = (state->i2c_read_buffer[0] << 8) | state->i2c_read_buffer[1];
+
+	return ret;
+}
+
+static u16 dib8000_read_word(struct dib8000_state *state, u16 reg)
+{
+	u16 ret;
+
+	if (mutex_lock_interruptible(&state->i2c_buffer_lock) < 0) {
+		dprintk("could not acquire lock");
+		return 0;
+	}
+
+	ret = __dib8000_read_word(state, reg);
+
 	mutex_unlock(&state->i2c_buffer_lock);
 
 	return ret;
@@ -192,8 +202,15 @@ static u32 dib8000_read32(struct dib8000_state *state, u16 reg)
 {
 	u16 rw[2];
 
-	rw[0] = dib8000_read_word(state, reg + 0);
-	rw[1] = dib8000_read_word(state, reg + 1);
+	if (mutex_lock_interruptible(&state->i2c_buffer_lock) < 0) {
+		dprintk("could not acquire lock");
+		return 0;
+	}
+
+	rw[0] = __dib8000_read_word(state, reg + 0);
+	rw[1] = __dib8000_read_word(state, reg + 1);
+
+	mutex_unlock(&state->i2c_buffer_lock);
 
 	return ((rw[0] << 16) | (rw[1]));
 }
@@ -2445,7 +2462,8 @@ static int dib8000_autosearch_start(struct dvb_frontend *fe)
 	if (state->revision == 0x8090)
 		internal = dib8000_read32(state, 23) / 1000;
 
-	if (state->autosearch_state == AS_SEARCHING_FFT) {
+	if ((state->revision >= 0x8002) &&
+	    (state->autosearch_state == AS_SEARCHING_FFT)) {
 		dib8000_write_word(state,  37, 0x0065); /* P_ctrl_pha_off_max default values */
 		dib8000_write_word(state, 116, 0x0000); /* P_ana_gain to 0 */
 
@@ -2481,7 +2499,8 @@ static int dib8000_autosearch_start(struct dvb_frontend *fe)
 		dib8000_write_word(state, 770, (dib8000_read_word(state, 770) & 0xdfff) | (1 << 13)); /* P_restart_ccg = 1 */
 		dib8000_write_word(state, 770, (dib8000_read_word(state, 770) & 0xdfff) | (0 << 13)); /* P_restart_ccg = 0 */
 		dib8000_write_word(state, 0, (dib8000_read_word(state, 0) & 0x7ff) | (0 << 15) | (1 << 13)); /* P_restart_search = 0; */
-	} else if (state->autosearch_state == AS_SEARCHING_GUARD) {
+	} else if ((state->revision >= 0x8002) &&
+		   (state->autosearch_state == AS_SEARCHING_GUARD)) {
 		c->transmission_mode = TRANSMISSION_MODE_8K;
 		c->guard_interval = GUARD_INTERVAL_1_8;
 		c->inversion = 0;
@@ -2583,7 +2602,8 @@ static int dib8000_autosearch_irq(struct dvb_frontend *fe)
 	struct dib8000_state *state = fe->demodulator_priv;
 	u16 irq_pending = dib8000_read_word(state, 1284);
 
-	if (state->autosearch_state == AS_SEARCHING_FFT) {
+	if ((state->revision >= 0x8002) &&
+	    (state->autosearch_state == AS_SEARCHING_FFT)) {
 		if (irq_pending & 0x1) {
 			dprintk("dib8000_autosearch_irq: max correlation result available");
 			return 3;
diff --git a/drivers/media/dvb-frontends/m88rs2000.c b/drivers/media/dvb-frontends/m88rs2000.c
index 4da5272075cb..02699c111019 100644
--- a/drivers/media/dvb-frontends/m88rs2000.c
+++ b/drivers/media/dvb-frontends/m88rs2000.c
@@ -110,28 +110,94 @@ static u8 m88rs2000_readreg(struct m88rs2000_state *state, u8 reg)
 	return b1[0];
 }
 
+static u32 m88rs2000_get_mclk(struct dvb_frontend *fe)
+{
+	struct m88rs2000_state *state = fe->demodulator_priv;
+	u32 mclk;
+	u8 reg;
+	/* Must not be 0x00 or 0xff */
+	reg = m88rs2000_readreg(state, 0x86);
+	if (!reg || reg == 0xff)
+		return 0;
+
+	reg /= 2;
+	reg += 1;
+
+	mclk = (u32)(reg * RS2000_FE_CRYSTAL_KHZ + 28 / 2) / 28;
+
+	return mclk;
+}
+
+static int m88rs2000_set_carrieroffset(struct dvb_frontend *fe, s16 offset)
+{
+	struct m88rs2000_state *state = fe->demodulator_priv;
+	u32 mclk;
+	s32 tmp;
+	u8 reg;
+	int ret;
+
+	mclk = m88rs2000_get_mclk(fe);
+	if (!mclk)
+		return -EINVAL;
+
+	tmp = (offset * 4096 + (s32)mclk / 2) / (s32)mclk;
+	if (tmp < 0)
+		tmp += 4096;
+
+	/* Carrier Offset */
+	ret = m88rs2000_writereg(state, 0x9c, (u8)(tmp >> 4));
+
+	reg = m88rs2000_readreg(state, 0x9d);
+	reg &= 0xf;
+	reg |= (u8)(tmp & 0xf) << 4;
+
+	ret |= m88rs2000_writereg(state, 0x9d, reg);
+
+	return ret;
+}
+
 static int m88rs2000_set_symbolrate(struct dvb_frontend *fe, u32 srate)
 {
 	struct m88rs2000_state *state = fe->demodulator_priv;
 	int ret;
-	u32 temp;
+	u64 temp;
+	u32 mclk;
 	u8 b[3];
 
 	if ((srate < 1000000) || (srate > 45000000))
 		return -EINVAL;
 
+	mclk = m88rs2000_get_mclk(fe);
+	if (!mclk)
+		return -EINVAL;
+
 	temp = srate / 1000;
-	temp *= 11831;
-	temp /= 68;
-	temp -= 3;
+	temp *= 1 << 24;
+
+	do_div(temp, mclk);
 
 	b[0] = (u8) (temp >> 16) & 0xff;
 	b[1] = (u8) (temp >> 8) & 0xff;
 	b[2] = (u8) temp & 0xff;
+
 	ret = m88rs2000_writereg(state, 0x93, b[2]);
 	ret |= m88rs2000_writereg(state, 0x94, b[1]);
 	ret |= m88rs2000_writereg(state, 0x95, b[0]);
 
+	if (srate > 10000000)
+		ret |= m88rs2000_writereg(state, 0xa0, 0x20);
+	else
+		ret |= m88rs2000_writereg(state, 0xa0, 0x60);
+
+	ret |= m88rs2000_writereg(state, 0xa1, 0xe0);
+
+	if (srate > 12000000)
+		ret |= m88rs2000_writereg(state, 0xa3, 0x20);
+	else if (srate > 2800000)
+		ret |= m88rs2000_writereg(state, 0xa3, 0x98);
+	else
+		ret |= m88rs2000_writereg(state, 0xa3, 0x90);
+
 	deb_info("m88rs2000: m88rs2000_set_symbolrate\n");
 	return ret;
 }
@@ -261,8 +327,6 @@ struct inittab m88rs2000_shutdown[] = {
 
 struct inittab fe_reset[] = {
 	{DEMOD_WRITE, 0x00, 0x01},
-	{DEMOD_WRITE, 0xf1, 0xbf},
-	{DEMOD_WRITE, 0x00, 0x01},
 	{DEMOD_WRITE, 0x20, 0x81},
 	{DEMOD_WRITE, 0x21, 0x80},
 	{DEMOD_WRITE, 0x10, 0x33},
@@ -305,9 +369,6 @@ struct inittab fe_trigger[] = {
 	{DEMOD_WRITE, 0x9b, 0x64},
 	{DEMOD_WRITE, 0x9e, 0x00},
 	{DEMOD_WRITE, 0x9f, 0xf8},
-	{DEMOD_WRITE, 0xa0, 0x20},
-	{DEMOD_WRITE, 0xa1, 0xe0},
-	{DEMOD_WRITE, 0xa3, 0x38},
 	{DEMOD_WRITE, 0x98, 0xff},
 	{DEMOD_WRITE, 0xc0, 0x0f},
 	{DEMOD_WRITE, 0x89, 0x01},
@@ -540,9 +601,8 @@ static int m88rs2000_set_frontend(struct dvb_frontend *fe)
 	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
 	fe_status_t status;
 	int i, ret = 0;
-	s32 tmp;
 	u32 tuner_freq;
-	u16 offset = 0;
+	s16 offset = 0;
 	u8 reg;
 
 	state->no_lock_count = 0;
@@ -567,29 +627,26 @@ static int m88rs2000_set_frontend(struct dvb_frontend *fe)
 	if (ret < 0)
 		return -ENODEV;
 
-	offset = tuner_freq - c->frequency;
-
-	/* calculate offset assuming 96000kHz*/
-	tmp = offset;
-	tmp *= 65536;
-
-	tmp = (2 * tmp + 96000) / (2 * 96000);
-	if (tmp < 0)
-		tmp += 65536;
+	offset = (s16)((s32)tuner_freq - c->frequency);
 
-	offset = tmp & 0xffff;
+	/* default mclk value 96.4285 * 2 * 1000 = 192857 */
+	if (((c->frequency % 192857) >= (192857 - 3000)) ||
+				(c->frequency % 192857) <= 3000)
+		ret = m88rs2000_writereg(state, 0x86, 0xc2);
+	else
+		ret = m88rs2000_writereg(state, 0x86, 0xc6);
 
-	ret = m88rs2000_writereg(state, 0x9a, 0x30);
-	/* Unknown usually 0xc6 sometimes 0xc1 */
-	reg = m88rs2000_readreg(state, 0x86);
-	ret |= m88rs2000_writereg(state, 0x86, reg);
-	/* Offset lower nibble always 0 */
-	ret |= m88rs2000_writereg(state, 0x9c, (offset >> 8));
-	ret |= m88rs2000_writereg(state, 0x9d, offset & 0xf0);
+	ret |= m88rs2000_set_carrieroffset(fe, offset);
+	if (ret < 0)
+		return -ENODEV;
 
+	/* Reset demod by symbol rate */
+	if (c->symbol_rate > 27500000)
+		ret = m88rs2000_writereg(state, 0xf1, 0xa4);
+	else
+		ret = m88rs2000_writereg(state, 0xf1, 0xbf);
 
-	/* Reset Demod */
-	ret = m88rs2000_tab_set(state, fe_reset);
+	ret |= m88rs2000_tab_set(state, fe_reset);
 	if (ret < 0)
 		return -ENODEV;
 
diff --git a/drivers/media/dvb-frontends/m88rs2000.h b/drivers/media/dvb-frontends/m88rs2000.h
index 14ce31e76ae6..0a50ea90736b 100644
--- a/drivers/media/dvb-frontends/m88rs2000.h
+++ b/drivers/media/dvb-frontends/m88rs2000.h
@@ -53,6 +53,8 @@ static inline struct dvb_frontend *m88rs2000_attach(
 }
 #endif /* CONFIG_DVB_M88RS2000 */
 
+#define RS2000_FE_CRYSTAL_KHZ 27000
+
 enum {
 	DEMOD_WRITE = 0x1,
 	WRITE_DELAY = 0x10,
diff --git a/drivers/media/dvb-frontends/nxt200x.c b/drivers/media/dvb-frontends/nxt200x.c
index fbca9856313a..4bf057544607 100644
--- a/drivers/media/dvb-frontends/nxt200x.c
+++ b/drivers/media/dvb-frontends/nxt200x.c
@@ -40,7 +40,7 @@
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 /* Max transfer size done by I2C transfer functions */
-#define MAX_XFER_SIZE  64
+#define MAX_XFER_SIZE  256
 
 #define NXT2002_DEFAULT_FIRMWARE "dvb-fe-nxt2002.fw"
 #define NXT2004_DEFAULT_FIRMWARE "dvb-fe-nxt2004.fw"
diff --git a/drivers/media/platform/s5p-mfc/s5p_mfc.c b/drivers/media/platform/s5p-mfc/s5p_mfc.c
index e46067a57853..e2aac592d29f 100644
--- a/drivers/media/platform/s5p-mfc/s5p_mfc.c
+++ b/drivers/media/platform/s5p-mfc/s5p_mfc.c
@@ -177,21 +177,6 @@ unlock:
 		mutex_unlock(&dev->mfc_mutex);
 }
 
-static enum s5p_mfc_node_type s5p_mfc_get_node_type(struct file *file)
-{
-	struct video_device *vdev = video_devdata(file);
-
-	if (!vdev) {
-		mfc_err("failed to get video_device");
-		return MFCNODE_INVALID;
-	}
-	if (vdev->index == 0)
-		return MFCNODE_DECODER;
-	else if (vdev->index == 1)
-		return MFCNODE_ENCODER;
-	return MFCNODE_INVALID;
-}
-
 static void s5p_mfc_clear_int_flags(struct s5p_mfc_dev *dev)
 {
 	mfc_write(dev, 0, S5P_FIMV_RISC_HOST_INT);
@@ -705,6 +690,7 @@ irq_cleanup_hw:
 /* Open an MFC node */
 static int s5p_mfc_open(struct file *file)
 {
+	struct video_device *vdev = video_devdata(file);
 	struct s5p_mfc_dev *dev = video_drvdata(file);
 	struct s5p_mfc_ctx *ctx = NULL;
 	struct vb2_queue *q;
@@ -742,7 +728,7 @@ static int s5p_mfc_open(struct file *file)
 	/* Mark context as idle */
 	clear_work_bit_irqsave(ctx);
 	dev->ctx[ctx->num] = ctx;
-	if (s5p_mfc_get_node_type(file) == MFCNODE_DECODER) {
+	if (vdev == dev->vfd_dec) {
 		ctx->type = MFCINST_DECODER;
 		ctx->c_ops = get_dec_codec_ops();
 		s5p_mfc_dec_init(ctx);
@@ -752,7 +738,7 @@ static int s5p_mfc_open(struct file *file)
 			mfc_err("Failed to setup mfc controls\n");
 			goto err_ctrls_setup;
 		}
-	} else if (s5p_mfc_get_node_type(file) == MFCNODE_ENCODER) {
+	} else if (vdev == dev->vfd_enc) {
 		ctx->type = MFCINST_ENCODER;
 		ctx->c_ops = get_enc_codec_ops();
 		/* only for encoder */
@@ -797,10 +783,10 @@ static int s5p_mfc_open(struct file *file)
 	q = &ctx->vq_dst;
 	q->type = V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE;
 	q->drv_priv = &ctx->fh;
-	if (s5p_mfc_get_node_type(file) == MFCNODE_DECODER) {
+	if (vdev == dev->vfd_dec) {
 		q->io_modes = VB2_MMAP;
 		q->ops = get_dec_queue_ops();
-	} else if (s5p_mfc_get_node_type(file) == MFCNODE_ENCODER) {
+	} else if (vdev == dev->vfd_enc) {
 		q->io_modes = VB2_MMAP | VB2_USERPTR;
 		q->ops = get_enc_queue_ops();
 	} else {
@@ -819,10 +805,10 @@ static int s5p_mfc_open(struct file *file)
 	q->type = V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE;
 	q->io_modes = VB2_MMAP;
 	q->drv_priv = &ctx->fh;
-	if (s5p_mfc_get_node_type(file) == MFCNODE_DECODER) {
+	if (vdev == dev->vfd_dec) {
 		q->io_modes = VB2_MMAP;
 		q->ops = get_dec_queue_ops();
-	} else if (s5p_mfc_get_node_type(file) == MFCNODE_ENCODER) {
+	} else if (vdev == dev->vfd_enc) {
 		q->io_modes = VB2_MMAP | VB2_USERPTR;
 		q->ops = get_enc_queue_ops();
 	} else {
diff --git a/drivers/media/platform/s5p-mfc/s5p_mfc_common.h b/drivers/media/platform/s5p-mfc/s5p_mfc_common.h
index 6920b546181a..823812c6b9b0 100644
--- a/drivers/media/platform/s5p-mfc/s5p_mfc_common.h
+++ b/drivers/media/platform/s5p-mfc/s5p_mfc_common.h
@@ -115,15 +115,6 @@ enum s5p_mfc_fmt_type {
 };
 
 /**
- * enum s5p_mfc_node_type - The type of an MFC device node.
- */
-enum s5p_mfc_node_type {
-	MFCNODE_INVALID = -1,
-	MFCNODE_DECODER = 0,
-	MFCNODE_ENCODER = 1,
-};
-
-/**
  * enum s5p_mfc_inst_type - The type of an MFC instance.
  */
 enum s5p_mfc_inst_type {
diff --git a/drivers/media/usb/dvb-usb-v2/anysee.c b/drivers/media/usb/dvb-usb-v2/anysee.c
index 90cfa35ef6e6..eeab79bdd2aa 100644
--- a/drivers/media/usb/dvb-usb-v2/anysee.c
+++ b/drivers/media/usb/dvb-usb-v2/anysee.c
@@ -442,6 +442,7 @@ static struct cxd2820r_config anysee_cxd2820r_config = {
  * IOD[0] ZL10353 1=enabled
  * IOE[0] tuner 0=enabled
  * tuner is behind ZL10353 I2C-gate
+ * tuner is behind TDA10023 I2C-gate
  *
  * E7 TC VID=1c73 PID=861f HW=18 FW=0.7 AMTCI=0.5 "anysee-E7TC(LP)"
  * PCB: 508TC (rev0.6)
@@ -956,7 +957,7 @@ static int anysee_tuner_attach(struct dvb_usb_adapter *adap)
 
 		if (fe && adap->fe[1]) {
 			/* attach tuner for 2nd FE */
-			fe = dvb_attach(dvb_pll_attach, adap->fe[0],
+			fe = dvb_attach(dvb_pll_attach, adap->fe[1],
 					(0xc0 >> 1), &d->i2c_adap,
 					DVB_PLL_SAMSUNG_DTOS403IH102A);
 		}
diff --git a/drivers/media/usb/dvb-usb-v2/it913x.c b/drivers/media/usb/dvb-usb-v2/it913x.c
index 1cb6899cf797..fe95a586dd5d 100644
--- a/drivers/media/usb/dvb-usb-v2/it913x.c
+++ b/drivers/media/usb/dvb-usb-v2/it913x.c
@@ -799,6 +799,9 @@ static const struct usb_device_id it913x_id_table[] = {
 	{ DVB_USB_DEVICE(USB_VID_KWORLD_2, USB_PID_CTVDIGDUAL_V2,
 		&it913x_properties, "Digital Dual TV Receiver CTVDIGDUAL_V2",
 			RC_MAP_IT913X_V1) },
+	{ DVB_USB_DEVICE(USB_VID_AVERMEDIA, USB_PID_AVERMEDIA_H335,
+		&it913x_properties, "Avermedia H335",
+			RC_MAP_IT913X_V2) },
 	{}		/* Terminating entry */
 };
 
diff --git a/drivers/media/v4l2-core/v4l2-dev.c b/drivers/media/v4l2-core/v4l2-dev.c
index b5aaaac427ad..0a30dbf3d05c 100644
--- a/drivers/media/v4l2-core/v4l2-dev.c
+++ b/drivers/media/v4l2-core/v4l2-dev.c
@@ -872,8 +872,8 @@ int __video_register_device(struct video_device *vdev, int type, int nr,
 
 	/* Should not happen since we thought this minor was free */
 	WARN_ON(video_device[vdev->minor] != NULL);
-	video_device[vdev->minor] = vdev;
 	vdev->index = get_index(vdev);
+	video_device[vdev->minor] = vdev;
 	mutex_unlock(&videodev_lock);
 
 	if (vdev->ioctl_ops)
diff --git a/drivers/misc/mei/hbm.c b/drivers/misc/mei/hbm.c
index 5d9e687a866c..7ba6c4cd026a 100644
--- a/drivers/misc/mei/hbm.c
+++ b/drivers/misc/mei/hbm.c
@@ -593,7 +593,7 @@ void mei_hbm_dispatch(struct mei_device *dev, struct mei_msg_hdr *hdr)
 	 */
 	if (dev->hbm_state == MEI_HBM_IDLE) {
 		dev_dbg(&dev->pdev->dev, "hbm: state is idle ignore spurious messages\n");
-		return 0;
+		return;
 	}
 
 	switch (mei_msg->hbm_cmd) {
diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c
index 29d5d988a51c..7b5424f398ac 100644
--- a/drivers/mmc/card/block.c
+++ b/drivers/mmc/card/block.c
@@ -1959,6 +1959,7 @@ static int mmc_blk_issue_rq(struct mmc_queue *mq, struct request *req)
 	struct mmc_card *card = md->queue.card;
 	struct mmc_host *host = card->host;
 	unsigned long flags;
+	unsigned int cmd_flags = req ? req->cmd_flags : 0;
 
 	if (req && !mq->mqrq_prev->req)
 		/* claim host only for the first request */
@@ -1974,7 +1975,7 @@ static int mmc_blk_issue_rq(struct mmc_queue *mq, struct request *req)
 	}
 
 	mq->flags &= ~MMC_QUEUE_NEW_REQUEST;
-	if (req && req->cmd_flags & REQ_DISCARD) {
+	if (cmd_flags & REQ_DISCARD) {
 		/* complete ongoing async transfer before issuing discard */
 		if (card->host->areq)
 			mmc_blk_issue_rw_rq(mq, NULL);
@@ -1983,7 +1984,7 @@ static int mmc_blk_issue_rq(struct mmc_queue *mq, struct request *req)
 			ret = mmc_blk_issue_secdiscard_rq(mq, req);
 		else
 			ret = mmc_blk_issue_discard_rq(mq, req);
-	} else if (req && req->cmd_flags & REQ_FLUSH) {
+	} else if (cmd_flags & REQ_FLUSH) {
 		/* complete ongoing async transfer before issuing flush */
 		if (card->host->areq)
 			mmc_blk_issue_rw_rq(mq, NULL);
@@ -1999,7 +2000,7 @@ static int mmc_blk_issue_rq(struct mmc_queue *mq, struct request *req)
 
 out:
 	if ((!req && !(mq->flags & MMC_QUEUE_NEW_REQUEST)) ||
-	     (req && (req->cmd_flags & MMC_REQ_SPECIAL_MASK)))
+	     (cmd_flags & MMC_REQ_SPECIAL_MASK))
 		/*
 		 * Release host when there are no more requests
 		 * and after special request(discard, flush) is done.
diff --git a/drivers/mmc/core/sd.c b/drivers/mmc/core/sd.c
index 6f42050b7ccc..692fdb177294 100644
--- a/drivers/mmc/core/sd.c
+++ b/drivers/mmc/core/sd.c
@@ -11,6 +11,7 @@
  */
 
 #include <linux/err.h>
+#include <linux/sizes.h>
 #include <linux/slab.h>
 #include <linux/stat.h>
 #include <linux/pm_runtime.h>
@@ -45,6 +46,13 @@ static const unsigned int tacc_mant[] = {
 	35,	40,	45,	50,	55,	60,	70,	80,
 };
 
+static const unsigned int sd_au_size[] = {
+	0,		SZ_16K / 512,		SZ_32K / 512,	SZ_64K / 512,
+	SZ_128K / 512,	SZ_256K / 512,		SZ_512K / 512,	SZ_1M / 512,
+	SZ_2M / 512,	SZ_4M / 512,		SZ_8M / 512,	(SZ_8M + SZ_4M) / 512,
+	SZ_16M / 512,	(SZ_16M + SZ_8M) / 512,	SZ_32M / 512,	SZ_64M / 512,
+};
+
 #define UNSTUFF_BITS(resp,start,size)					\
 	({								\
 		const int __size = size;				\
@@ -216,7 +224,7 @@ static int mmc_decode_scr(struct mmc_card *card)
 static int mmc_read_ssr(struct mmc_card *card)
 {
 	unsigned int au, es, et, eo;
-	int err, i, max_au;
+	int err, i;
 	u32 *ssr;
 
 	if (!(card->csd.cmdclass & CCC_APP_SPEC)) {
@@ -240,26 +248,25 @@ static int mmc_read_ssr(struct mmc_card *card)
 	for (i = 0; i < 16; i++)
 		ssr[i] = be32_to_cpu(ssr[i]);
 
-	/* SD3.0 increases max AU size to 64MB (0xF) from 4MB (0x9) */
-	max_au = card->scr.sda_spec3 ? 0xF : 0x9;
-
 	/*
 	 * UNSTUFF_BITS only works with four u32s so we have to offset the
 	 * bitfield positions accordingly.
 	 */
 	au = UNSTUFF_BITS(ssr, 428 - 384, 4);
-	if (au > 0 && au <= max_au) {
-		card->ssr.au = 1 << (au + 4);
-		es = UNSTUFF_BITS(ssr, 408 - 384, 16);
-		et = UNSTUFF_BITS(ssr, 402 - 384, 6);
-		eo = UNSTUFF_BITS(ssr, 400 - 384, 2);
-		if (es && et) {
-			card->ssr.erase_timeout = (et * 1000) / es;
-			card->ssr.erase_offset = eo * 1000;
+	if (au) {
+		if (au <= 9 || card->scr.sda_spec3) {
+			card->ssr.au = sd_au_size[au];
+			es = UNSTUFF_BITS(ssr, 408 - 384, 16);
+			et = UNSTUFF_BITS(ssr, 402 - 384, 6);
+			if (es && et) {
+				eo = UNSTUFF_BITS(ssr, 400 - 384, 2);
+				card->ssr.erase_timeout = (et * 1000) / es;
+				card->ssr.erase_offset = eo * 1000;
+			}
+		} else {
+			pr_warning("%s: SD Status: Invalid Allocation Unit size.\n",
+				   mmc_hostname(card->host));
 		}
-	} else {
-		pr_warning("%s: SD Status: Invalid Allocation Unit "
-			"size.\n", mmc_hostname(card->host));
 	}
 out:
 	kfree(ssr);
diff --git a/drivers/mmc/host/atmel-mci.c b/drivers/mmc/host/atmel-mci.c
index 2cbb4516d353..945a31d77364 100644
--- a/drivers/mmc/host/atmel-mci.c
+++ b/drivers/mmc/host/atmel-mci.c
@@ -1192,11 +1192,22 @@ static void atmci_start_request(struct atmel_mci *host,
 	iflags |= ATMCI_CMDRDY;
 	cmd = mrq->cmd;
 	cmdflags = atmci_prepare_command(slot->mmc, cmd);
-	atmci_send_command(host, cmd, cmdflags);
+
+	/*
+	 * DMA transfer should be started before sending the command to avoid
+	 * unexpected errors especially for read operations in SDIO mode.
+	 * Unfortunately, in PDC mode, command has to be sent before starting
+	 * the transfer.
+	 */
+	if (host->submit_data != &atmci_submit_data_dma)
+		atmci_send_command(host, cmd, cmdflags);
 
 	if (data)
 		host->submit_data(host, data);
 
+	if (host->submit_data == &atmci_submit_data_dma)
+		atmci_send_command(host, cmd, cmdflags);
+
 	if (mrq->stop) {
 		host->stop_cmdr = atmci_prepare_command(slot->mmc, mrq->stop);
 		host->stop_cmdr |= ATMCI_CMDR_STOP_XFER;
diff --git a/drivers/mmc/host/sdhci-pci.c b/drivers/mmc/host/sdhci-pci.c
index c377c16ab0a2..cc05051fac99 100644
--- a/drivers/mmc/host/sdhci-pci.c
+++ b/drivers/mmc/host/sdhci-pci.c
@@ -65,6 +65,7 @@ struct sdhci_pci_fixes {
 	unsigned int		quirks;
 	unsigned int		quirks2;
 	bool			allow_runtime_pm;
+	bool			own_cd_for_runtime_pm;
 
 	int			(*probe) (struct sdhci_pci_chip *);
 
@@ -296,6 +297,7 @@ static const struct sdhci_pci_fixes sdhci_intel_mrst_hc1_hc2 = {
 static const struct sdhci_pci_fixes sdhci_intel_mfd_sd = {
 	.quirks		= SDHCI_QUIRK_NO_ENDATTR_IN_NOPDESC,
 	.allow_runtime_pm = true,
+	.own_cd_for_runtime_pm = true,
 };
 
 static const struct sdhci_pci_fixes sdhci_intel_mfd_sdio = {
@@ -360,6 +362,7 @@ static const struct sdhci_pci_fixes sdhci_intel_byt_sdio = {
 static const struct sdhci_pci_fixes sdhci_intel_byt_sd = {
 	.quirks2	= SDHCI_QUIRK2_CARD_ON_NEEDS_BUS_ON,
 	.allow_runtime_pm = true,
+	.own_cd_for_runtime_pm = true,
 };
 
 /* Define Host controllers for Intel Merrifield platform */
@@ -1458,6 +1461,15 @@ static struct sdhci_pci_slot *sdhci_pci_probe_slot(
 
 	sdhci_pci_add_own_cd(slot);
 
+	/*
+	 * Check if the chip needs a separate GPIO for card detect to wake up
+	 * from runtime suspend.  If it is not there, don't allow runtime PM.
+	 * Note sdhci_pci_add_own_cd() sets slot->cd_gpio to -EINVAL on failure.
+	 */
+	if (chip->fixes && chip->fixes->own_cd_for_runtime_pm &&
+	    !gpio_is_valid(slot->cd_gpio))
+		chip->allow_runtime_pm = false;
+
 	return slot;
 
 remove:
diff --git a/drivers/mtd/nand/mxc_nand.c b/drivers/mtd/nand/mxc_nand.c
index 9dfdb06c508b..a4bad1165c2a 100644
--- a/drivers/mtd/nand/mxc_nand.c
+++ b/drivers/mtd/nand/mxc_nand.c
@@ -677,7 +677,6 @@ static int mxc_nand_correct_data_v2_v3(struct mtd_info *mtd, u_char *dat,
 		ecc_stat >>= 4;
 	} while (--no_subpages);
 
-	mtd->ecc_stats.corrected += ret;
 	pr_debug("%d Symbol Correctable RS-ECC Error\n", ret);
 
 	return ret;
diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index 657f7c588d17..3c67863a657b 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -2079,7 +2079,7 @@ static int __init netif_init(void)
 	if (!xen_domain())
 		return -ENODEV;
 
-	if (xen_hvm_domain() && !xen_platform_pci_unplug)
+	if (!xen_has_pv_nic_devices())
 		return -ENODEV;
 
 	pr_info("Initialising Xen virtual ethernet driver\n");
diff --git a/drivers/pci/xen-pcifront.c b/drivers/pci/xen-pcifront.c
index f7197a790341..eae7cd9fde7b 100644
--- a/drivers/pci/xen-pcifront.c
+++ b/drivers/pci/xen-pcifront.c
@@ -20,6 +20,7 @@
 #include <linux/workqueue.h>
 #include <linux/bitops.h>
 #include <linux/time.h>
+#include <xen/platform_pci.h>
 
 #include <asm/xen/swiotlb-xen.h>
 #define INVALID_GRANT_REF (0)
@@ -1138,6 +1139,9 @@ static int __init pcifront_init(void)
 	if (!xen_pv_domain() || xen_initial_domain())
 		return -ENODEV;
 
+	if (!xen_has_pv_devices())
+		return -ENODEV;
+
 	pci_frontend_registrar(1 /* enable */);
 
 	return xenbus_register_frontend(&xenpci_driver);
diff --git a/drivers/rtc/rtc-cmos.c b/drivers/rtc/rtc-cmos.c
index f14876256a4a..a2325bc5e497 100644
--- a/drivers/rtc/rtc-cmos.c
+++ b/drivers/rtc/rtc-cmos.c
@@ -34,11 +34,11 @@
 #include <linux/interrupt.h>
 #include <linux/spinlock.h>
 #include <linux/platform_device.h>
-#include <linux/mod_devicetable.h>
 #include <linux/log2.h>
 #include <linux/pm.h>
 #include <linux/of.h>
 #include <linux/of_platform.h>
+#include <linux/dmi.h>
 
 /* this is for "generic access to PC-style RTC" using CMOS_READ/CMOS_WRITE */
 #include <asm-generic/rtc.h>
@@ -377,6 +377,51 @@ static int cmos_set_alarm(struct device *dev, struct rtc_wkalrm *t)
 	return 0;
 }
 
+/*
+ * Do not disable RTC alarm on shutdown - workaround for b0rked BIOSes.
+ */
+static bool alarm_disable_quirk;
+
+static int __init set_alarm_disable_quirk(const struct dmi_system_id *id)
+{
+	alarm_disable_quirk = true;
+	pr_info("rtc-cmos: BIOS has alarm-disable quirk. ");
+	pr_info("RTC alarms disabled\n");
+	return 0;
+}
+
+static const struct dmi_system_id rtc_quirks[] __initconst = {
+	/* https://bugzilla.novell.com/show_bug.cgi?id=805740 */
+	{
+		.callback = set_alarm_disable_quirk,
+		.ident    = "IBM Truman",
+		.matches  = {
+			DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "4852570"),
+		},
+	},
+	/* https://bugzilla.novell.com/show_bug.cgi?id=812592 */
+	{
+		.callback = set_alarm_disable_quirk,
+		.ident    = "Gigabyte GA-990XA-UD3",
+		.matches  = {
+			DMI_MATCH(DMI_SYS_VENDOR,
+					"Gigabyte Technology Co., Ltd."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "GA-990XA-UD3"),
+		},
+	},
+	/* http://permalink.gmane.org/gmane.linux.kernel/1604474 */
+	{
+		.callback = set_alarm_disable_quirk,
+		.ident    = "Toshiba Satellite L300",
+		.matches  = {
+			DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Satellite L300"),
+		},
+	},
+	{}
+};
+
 static int cmos_alarm_irq_enable(struct device *dev, unsigned int enabled)
 {
 	struct cmos_rtc	*cmos = dev_get_drvdata(dev);
@@ -385,6 +430,9 @@ static int cmos_alarm_irq_enable(struct device *dev, unsigned int enabled)
 	if (!is_valid_irq(cmos->irq))
 		return -EINVAL;
 
+	if (alarm_disable_quirk)
+		return 0;
+
 	spin_lock_irqsave(&rtc_lock, flags);
 
 	if (enabled)
@@ -1157,6 +1205,8 @@ static int __init cmos_init(void)
 			platform_driver_registered = true;
 	}
 
+	dmi_check_system(rtc_quirks);
+
 	if (retval == 0)
 		return 0;
 
diff --git a/drivers/spi/spi-bcm63xx.c b/drivers/spi/spi-bcm63xx.c
index 469ecd876358..dceb7b216f46 100644
--- a/drivers/spi/spi-bcm63xx.c
+++ b/drivers/spi/spi-bcm63xx.c
@@ -169,8 +169,6 @@ static int bcm63xx_txrx_bufs(struct spi_device *spi, struct spi_transfer *first,
 			       transfer_list);
 	}
 
-	len -= prepend_len;
-
 	init_completion(&bs->done);
 
 	/* Fill in the Message control register */
diff --git a/drivers/spi/spi-pxa2xx.c b/drivers/spi/spi-pxa2xx.c
index 7765b1999537..cbc68848789d 100644
--- a/drivers/spi/spi-pxa2xx.c
+++ b/drivers/spi/spi-pxa2xx.c
@@ -1066,6 +1066,8 @@ pxa2xx_spi_acpi_get_pdata(struct platform_device *pdev)
 
 	pdata->num_chipselect = 1;
 	pdata->enable_dma = true;
+	pdata->tx_chan_id = -1;
+	pdata->rx_chan_id = -1;
 
 	return pdata;
 }
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 349ebba4b199..d745f95eaf06 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -735,7 +735,9 @@ static void spi_pump_messages(struct kthread_work *work)
 	ret = master->transfer_one_message(master, master->cur_msg);
 	if (ret) {
 		dev_err(&master->dev,
-			"failed to transfer one message from queue\n");
+			"failed to transfer one message from queue: %d\n", ret);
+		master->cur_msg->status = ret;
+		spi_finalize_current_message(master);
 		return;
 	}
 }
diff --git a/drivers/target/iscsi/iscsi_target_util.c b/drivers/target/iscsi/iscsi_target_util.c
index 0819e688a398..5477ecabc00e 100644
--- a/drivers/target/iscsi/iscsi_target_util.c
+++ b/drivers/target/iscsi/iscsi_target_util.c
@@ -156,9 +156,13 @@ struct iscsi_cmd *iscsit_allocate_cmd(struct iscsi_conn *conn, gfp_t gfp_mask)
 {
 	struct iscsi_cmd *cmd;
 	struct se_session *se_sess = conn->sess->se_sess;
-	int size, tag;
+	int size, tag, state = (gfp_mask & __GFP_WAIT) ? TASK_INTERRUPTIBLE :
+				TASK_RUNNING;
+
+	tag = percpu_ida_alloc(&se_sess->sess_tag_pool, state);
+	if (tag < 0)
+		return NULL;
 
-	tag = percpu_ida_alloc(&se_sess->sess_tag_pool, gfp_mask);
 	size = sizeof(struct iscsi_cmd) + conn->conn_transport->priv_size;
 	cmd = (struct iscsi_cmd *)(se_sess->sess_cmd_map + (tag * size));
 	memset(cmd, 0, size);
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index 91953da0f623..dee2be1f9171 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -568,10 +568,11 @@ static void transport_lun_remove_cmd(struct se_cmd *cmd)
 {
 	struct se_lun *lun = cmd->se_lun;
 
-	if (!lun || !cmd->lun_ref_active)
+	if (!lun)
 		return;
 
-	percpu_ref_put(&lun->lun_ref);
+	if (cmpxchg(&cmd->lun_ref_active, true, false))
+		percpu_ref_put(&lun->lun_ref);
 }
 
 void transport_cmd_finish_abort(struct se_cmd *cmd, int remove)
diff --git a/drivers/target/tcm_fc/tfc_cmd.c b/drivers/target/tcm_fc/tfc_cmd.c
index 479ec5621a4e..8b2c1aaf81de 100644
--- a/drivers/target/tcm_fc/tfc_cmd.c
+++ b/drivers/target/tcm_fc/tfc_cmd.c
@@ -438,7 +438,7 @@ static void ft_recv_cmd(struct ft_sess *sess, struct fc_frame *fp)
 	struct se_session *se_sess = sess->se_sess;
 	int tag;
 
-	tag = percpu_ida_alloc(&se_sess->sess_tag_pool, GFP_ATOMIC);
+	tag = percpu_ida_alloc(&se_sess->sess_tag_pool, TASK_RUNNING);
 	if (tag < 0)
 		goto busy;
 
diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c
index f175629513ed..1d0196edcd62 100644
--- a/drivers/vhost/scsi.c
+++ b/drivers/vhost/scsi.c
@@ -728,7 +728,7 @@ vhost_scsi_get_tag(struct vhost_virtqueue *vq,
 	}
 	se_sess = tv_nexus->tvn_se_sess;
 
-	tag = percpu_ida_alloc(&se_sess->sess_tag_pool, GFP_ATOMIC);
+	tag = percpu_ida_alloc(&se_sess->sess_tag_pool, TASK_RUNNING);
 	if (tag < 0) {
 		pr_err("Unable to obtain tag for tcm_vhost_cmd\n");
 		return ERR_PTR(-ENOMEM);
diff --git a/drivers/video/xen-fbfront.c b/drivers/video/xen-fbfront.c
index cd005c227a23..4b2d3ab870f3 100644
--- a/drivers/video/xen-fbfront.c
+++ b/drivers/video/xen-fbfront.c
@@ -35,6 +35,7 @@
 #include <xen/interface/io/fbif.h>
 #include <xen/interface/io/protocols.h>
 #include <xen/xenbus.h>
+#include <xen/platform_pci.h>
 
 struct xenfb_info {
 	unsigned char		*fb;
@@ -699,6 +700,9 @@ static int __init xenfb_init(void)
 	if (xen_initial_domain())
 		return -ENODEV;
 
+	if (!xen_has_pv_devices())
+		return -ENODEV;
+
 	return xenbus_register_frontend(&xenfb_driver);
 }
 
diff --git a/drivers/xen/xenbus/xenbus_probe_frontend.c b/drivers/xen/xenbus/xenbus_probe_frontend.c
index 129bf84c19ec..cb385c10d2b1 100644
--- a/drivers/xen/xenbus/xenbus_probe_frontend.c
+++ b/drivers/xen/xenbus/xenbus_probe_frontend.c
@@ -496,7 +496,7 @@ subsys_initcall(xenbus_probe_frontend_init);
 #ifndef MODULE
 static int __init boot_wait_for_devices(void)
 {
-	if (xen_hvm_domain() && !xen_platform_pci_unplug)
+	if (!xen_has_pv_devices())
 		return -ENODEV;
 
 	ready_to_wait_for_devices = 1;
diff --git a/fs/dcookies.c b/fs/dcookies.c
index ab5954b50267..ac44a69fbea9 100644
--- a/fs/dcookies.c
+++ b/fs/dcookies.c
@@ -204,7 +204,7 @@ out:
 }
 
 #ifdef CONFIG_COMPAT
-COMPAT_SYSCALL_DEFINE4(lookup_dcookie, u32, w0, u32, w1, char __user *, buf, size_t, len)
+COMPAT_SYSCALL_DEFINE4(lookup_dcookie, u32, w0, u32, w1, char __user *, buf, compat_size_t, len)
 {
 #ifdef __BIG_ENDIAN
 	return sys_lookup_dcookie(((u64)w0 << 32) | w1, buf, len);
diff --git a/fs/exofs/ore.c b/fs/exofs/ore.c
index b74422888604..85cde3e76290 100644
--- a/fs/exofs/ore.c
+++ b/fs/exofs/ore.c
@@ -103,7 +103,7 @@ int ore_verify_layout(unsigned total_comps, struct ore_layout *layout)
 
 	layout->max_io_length =
 		(BIO_MAX_PAGES_KMALLOC * PAGE_SIZE - layout->stripe_unit) *
-							layout->group_width;
+					(layout->group_width - layout->parity);
 	if (layout->parity) {
 		unsigned stripe_length =
 				(layout->group_width - layout->parity) *
@@ -286,7 +286,8 @@ int  ore_get_rw_state(struct ore_layout *layout, struct ore_components *oc,
 	if (length) {
 		ore_calc_stripe_info(layout, offset, length, &ios->si);
 		ios->length = ios->si.length;
-		ios->nr_pages = (ios->length + PAGE_SIZE - 1) / PAGE_SIZE;
+		ios->nr_pages = ((ios->offset & (PAGE_SIZE - 1)) +
+				 ios->length + PAGE_SIZE - 1) / PAGE_SIZE;
 		if (layout->parity)
 			_ore_post_alloc_raid_stuff(ios);
 	}
@@ -536,6 +537,7 @@ void ore_calc_stripe_info(struct ore_layout *layout, u64 file_offset,
 	u64	H = LmodS - G * T;
 
 	u32	N = div_u64(H, U);
+	u32	Nlast;
 
 	/* "H - (N * U)" is just "H % U" so it's bound to u32 */
 	u32	C = (u32)(H - (N * U)) / stripe_unit + G * group_width;
@@ -568,6 +570,10 @@ void ore_calc_stripe_info(struct ore_layout *layout, u64 file_offset,
 	si->length = T - H;
 	if (si->length > length)
 		si->length = length;
+
+	Nlast = div_u64(H + si->length + U - 1, U);
+	si->maxdevUnits = Nlast - N;
+
 	si->M = M;
 }
 EXPORT_SYMBOL(ore_calc_stripe_info);
@@ -583,13 +589,16 @@ int _ore_add_stripe_unit(struct ore_io_state *ios,  unsigned *cur_pg,
 	int ret;
 
 	if (per_dev->bio == NULL) {
-		unsigned pages_in_stripe = ios->layout->group_width *
-					(ios->layout->stripe_unit / PAGE_SIZE);
-		unsigned nr_pages = ios->nr_pages * ios->layout->group_width /
-					(ios->layout->group_width -
-					 ios->layout->parity);
-		unsigned bio_size = (nr_pages + pages_in_stripe) /
-					ios->layout->group_width;
+		unsigned bio_size;
+
+		if (!ios->reading) {
+			bio_size = ios->si.maxdevUnits;
+		} else {
+			bio_size = (ios->si.maxdevUnits + 1) *
+			     (ios->layout->group_width - ios->layout->parity) /
+			     ios->layout->group_width;
+		}
+		bio_size *= (ios->layout->stripe_unit / PAGE_SIZE);
 
 		per_dev->bio = bio_kmalloc(GFP_KERNEL, bio_size);
 		if (unlikely(!per_dev->bio)) {
@@ -609,8 +618,12 @@ int _ore_add_stripe_unit(struct ore_io_state *ios,  unsigned *cur_pg,
 		added_len = bio_add_pc_page(q, per_dev->bio, pages[pg],
 					    pglen, pgbase);
 		if (unlikely(pglen != added_len)) {
-			ORE_DBGMSG("Failed bio_add_pc_page bi_vcnt=%u\n",
-				   per_dev->bio->bi_vcnt);
+			/* If bi_vcnt == bi_max then this is a SW BUG */
+			ORE_DBGMSG("Failed bio_add_pc_page bi_vcnt=0x%x "
+				   "bi_max=0x%x BIO_MAX=0x%x cur_len=0x%x\n",
+				   per_dev->bio->bi_vcnt,
+				   per_dev->bio->bi_max_vecs,
+				   BIO_MAX_PAGES_KMALLOC, cur_len);
 			ret = -ENOMEM;
 			goto out;
 		}
@@ -1098,7 +1111,7 @@ int ore_truncate(struct ore_layout *layout, struct ore_components *oc,
 		size_attr->attr = g_attr_logical_length;
 		size_attr->attr.val_ptr = &size_attr->newsize;
 
-		ORE_DBGMSG("trunc(0x%llx) obj_offset=0x%llx dev=%d\n",
+		ORE_DBGMSG2("trunc(0x%llx) obj_offset=0x%llx dev=%d\n",
 			     _LLU(oc->comps->obj.id), _LLU(obj_size), i);
 		ret = _truncate_mirrors(ios, i * ios->layout->mirrors_p1,
 					&size_attr->attr);
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index ef74ad5fd362..fa8cb4b7b8fe 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -1296,22 +1296,6 @@ static ssize_t fuse_dev_read(struct kiocb *iocb, const struct iovec *iov,
 	return fuse_dev_do_read(fc, file, &cs, iov_length(iov, nr_segs));
 }
 
-static int fuse_dev_pipe_buf_steal(struct pipe_inode_info *pipe,
-				   struct pipe_buffer *buf)
-{
-	return 1;
-}
-
-static const struct pipe_buf_operations fuse_dev_pipe_buf_ops = {
-	.can_merge = 0,
-	.map = generic_pipe_buf_map,
-	.unmap = generic_pipe_buf_unmap,
-	.confirm = generic_pipe_buf_confirm,
-	.release = generic_pipe_buf_release,
-	.steal = fuse_dev_pipe_buf_steal,
-	.get = generic_pipe_buf_get,
-};
-
 static ssize_t fuse_dev_splice_read(struct file *in, loff_t *ppos,
 				    struct pipe_inode_info *pipe,
 				    size_t len, unsigned int flags)
@@ -1358,7 +1342,11 @@ static ssize_t fuse_dev_splice_read(struct file *in, loff_t *ppos,
 		buf->page = bufs[page_nr].page;
 		buf->offset = bufs[page_nr].offset;
 		buf->len = bufs[page_nr].len;
-		buf->ops = &fuse_dev_pipe_buf_ops;
+		/*
+		 * Need to be careful about this.  Having buf->ops in module
+		 * code can Oops if the buffer persists after module unload.
+		 */
+		buf->ops = &nosteal_pipe_buf_ops;
 
 		pipe->nrbufs++;
 		page_nr++;
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index b4a160a405ce..2b9bfbaab504 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -409,13 +409,11 @@ struct nfs_client *nfs4_init_client(struct nfs_client *clp,
 	error = nfs4_discover_server_trunking(clp, &old);
 	if (error < 0)
 		goto error;
-	nfs_put_client(clp);
-	if (clp != old) {
-		clp->cl_preserve_clid = true;
-		clp = old;
-	}
 
-	return clp;
+	if (clp != old)
+		clp->cl_preserve_clid = true;
+	nfs_put_client(clp);
+	return old;
 
 error:
 	nfs_mark_client_ready(clp, error);
@@ -493,9 +491,10 @@ int nfs40_walk_client_list(struct nfs_client *new,
 			prev = pos;
 
 			status = nfs_wait_client_init_complete(pos);
-			spin_lock(&nn->nfs_client_lock);
 			if (status < 0)
-				continue;
+				goto out;
+			status = -NFS4ERR_STALE_CLIENTID;
+			spin_lock(&nn->nfs_client_lock);
 		}
 		if (pos->cl_cons_state != NFS_CS_READY)
 			continue;
@@ -633,7 +632,8 @@ int nfs41_walk_client_list(struct nfs_client *new,
 			}
 			spin_lock(&nn->nfs_client_lock);
 			if (status < 0)
-				continue;
+				break;
+			status = -NFS4ERR_STALE_CLIENTID;
 		}
 		if (pos->cl_cons_state != NFS_CS_READY)
 			continue;
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 15052b81df42..96721814104c 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -539,7 +539,7 @@ static int nfs40_sequence_done(struct rpc_task *task,
 	struct nfs4_slot *slot = res->sr_slot;
 	struct nfs4_slot_table *tbl;
 
-	if (!RPC_WAS_SENT(task))
+	if (slot == NULL)
 		goto out;
 
 	tbl = slot->table;
@@ -7409,9 +7409,9 @@ static void nfs4_layoutget_done(struct rpc_task *task, void *calldata)
 	struct nfs_server *server = NFS_SERVER(inode);
 	struct pnfs_layout_hdr *lo;
 	struct nfs4_state *state = NULL;
-	unsigned long timeo, giveup;
+	unsigned long timeo, now, giveup;
 
-	dprintk("--> %s\n", __func__);
+	dprintk("--> %s tk_status => %d\n", __func__, -task->tk_status);
 
 	if (!nfs41_sequence_done(task, &lgp->res.seq_res))
 		goto out;
@@ -7419,12 +7419,38 @@ static void nfs4_layoutget_done(struct rpc_task *task, void *calldata)
 	switch (task->tk_status) {
 	case 0:
 		goto out;
+	/*
+	 * NFS4ERR_LAYOUTTRYLATER is a conflict with another client
+	 * (or clients) writing to the same RAID stripe
+	 */
 	case -NFS4ERR_LAYOUTTRYLATER:
+	/*
+	 * NFS4ERR_RECALLCONFLICT is when conflict with self (must recall
+	 * existing layout before getting a new one).
+	 */
 	case -NFS4ERR_RECALLCONFLICT:
 		timeo = rpc_get_timeout(task->tk_client);
 		giveup = lgp->args.timestamp + timeo;
-		if (time_after(giveup, jiffies))
-			task->tk_status = -NFS4ERR_DELAY;
+		now = jiffies;
+		if (time_after(giveup, now)) {
+			unsigned long delay;
+
+			/* Delay for:
+			 * - Not less then NFS4_POLL_RETRY_MIN.
+			 * - One last time a jiffie before we give up
+			 * - exponential backoff (time_now minus start_attempt)
+			 */
+			delay = max_t(unsigned long, NFS4_POLL_RETRY_MIN,
+				    min((giveup - now - 1),
+					now - lgp->args.timestamp));
+
+			dprintk("%s: NFS4ERR_RECALLCONFLICT waiting %lu\n",
+				__func__, delay);
+			rpc_delay(task, delay);
+			task->tk_status = 0;
+			rpc_restart_call_prepare(task);
+			goto out; /* Do not call nfs4_async_handle_error() */
+		}
 		break;
 	case -NFS4ERR_EXPIRED:
 	case -NFS4ERR_BAD_STATEID:
@@ -7920,7 +7946,7 @@ nfs41_proc_secinfo_no_name(struct nfs_server *server, struct nfs_fh *fhandle,
 		switch (err) {
 		case 0:
 		case -NFS4ERR_WRONGSEC:
-		case -NFS4ERR_NOTSUPP:
+		case -ENOTSUPP:
 			goto out;
 		default:
 			err = nfs4_handle_exception(server, err, &exception);
@@ -7954,7 +7980,7 @@ nfs41_find_root_sec(struct nfs_server *server, struct nfs_fh *fhandle,
 	 * Fall back on "guess and check" method if
 	 * the server doesn't support SECINFO_NO_NAME
 	 */
-	if (err == -NFS4ERR_WRONGSEC || err == -NFS4ERR_NOTSUPP) {
+	if (err == -NFS4ERR_WRONGSEC || err == -ENOTSUPP) {
 		err = nfs4_find_root_sec(server, fhandle, info);
 		goto out_freepage;
 	}
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 5be2868c02f1..8c21d69a9dc1 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -3097,7 +3097,8 @@ out_overflow:
 	return -EIO;
 }
 
-static int decode_op_hdr(struct xdr_stream *xdr, enum nfs_opnum4 expected)
+static bool __decode_op_hdr(struct xdr_stream *xdr, enum nfs_opnum4 expected,
+		int *nfs_retval)
 {
 	__be32 *p;
 	uint32_t opnum;
@@ -3107,19 +3108,32 @@ static int decode_op_hdr(struct xdr_stream *xdr, enum nfs_opnum4 expected)
 	if (unlikely(!p))
 		goto out_overflow;
 	opnum = be32_to_cpup(p++);
-	if (opnum != expected) {
-		dprintk("nfs: Server returned operation"
-			" %d but we issued a request for %d\n",
-				opnum, expected);
-		return -EIO;
-	}
+	if (unlikely(opnum != expected))
+		goto out_bad_operation;
 	nfserr = be32_to_cpup(p);
-	if (nfserr != NFS_OK)
-		return nfs4_stat_to_errno(nfserr);
-	return 0;
+	if (nfserr == NFS_OK)
+		*nfs_retval = 0;
+	else
+		*nfs_retval = nfs4_stat_to_errno(nfserr);
+	return true;
+out_bad_operation:
+	dprintk("nfs: Server returned operation"
+		" %d but we issued a request for %d\n",
+			opnum, expected);
+	*nfs_retval = -EREMOTEIO;
+	return false;
 out_overflow:
 	print_overflow_msg(__func__, xdr);
-	return -EIO;
+	*nfs_retval = -EIO;
+	return false;
+}
+
+static int decode_op_hdr(struct xdr_stream *xdr, enum nfs_opnum4 expected)
+{
+	int retval;
+
+	__decode_op_hdr(xdr, expected, &retval);
+	return retval;
 }
 
 /* Dummy routine */
@@ -5001,11 +5015,12 @@ static int decode_open(struct xdr_stream *xdr, struct nfs_openres *res)
 	uint32_t savewords, bmlen, i;
 	int status;
 
-	status = decode_op_hdr(xdr, OP_OPEN);
-	if (status != -EIO)
-		nfs_increment_open_seqid(status, res->seqid);
-	if (!status)
-		status = decode_stateid(xdr, &res->stateid);
+	if (!__decode_op_hdr(xdr, OP_OPEN, &status))
+		return status;
+	nfs_increment_open_seqid(status, res->seqid);
+	if (status)
+		return status;
+	status = decode_stateid(xdr, &res->stateid);
 	if (unlikely(status))
 		return status;
 
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index c1d548211c31..6a850381b23b 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -922,19 +922,20 @@ out:
  * extend the write to cover the entire page in order to avoid fragmentation
  * inefficiencies.
  *
- * If the file is opened for synchronous writes or if we have a write delegation
- * from the server then we can just skip the rest of the checks.
+ * If the file is opened for synchronous writes then we can just skip the rest
+ * of the checks.
  */
 static int nfs_can_extend_write(struct file *file, struct page *page, struct inode *inode)
 {
 	if (file->f_flags & O_DSYNC)
 		return 0;
+	if (!nfs_write_pageuptodate(page, inode))
+		return 0;
 	if (NFS_PROTO(inode)->have_delegation(inode, FMODE_WRITE))
 		return 1;
-	if (nfs_write_pageuptodate(page, inode) && (inode->i_flock == NULL ||
-			(inode->i_flock->fl_start == 0 &&
+	if (inode->i_flock == NULL || (inode->i_flock->fl_start == 0 &&
 			inode->i_flock->fl_end == OFFSET_MAX &&
-			inode->i_flock->fl_type != F_RDLCK)))
+			inode->i_flock->fl_type != F_RDLCK))
 		return 1;
 	return 0;
 }
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index e44cb6427df3..6663511ab33a 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -888,9 +888,9 @@ COMPAT_SYSCALL_DEFINE6(fanotify_mark,
 {
 	return sys_fanotify_mark(fanotify_fd, flags,
 #ifdef __BIG_ENDIAN
-				((__u64)mask1 << 32) | mask0,
-#else
 				((__u64)mask0 << 32) | mask1,
+#else
+				((__u64)mask1 << 32) | mask0,
 #endif
 				 dfd, pathname);
 }
diff --git a/fs/read_write.c b/fs/read_write.c
index 58e440df1bc6..cfa18df30f5b 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -968,9 +968,9 @@ out:
 	return ret;
 }
 
-COMPAT_SYSCALL_DEFINE3(readv, unsigned long, fd,
+COMPAT_SYSCALL_DEFINE3(readv, compat_ulong_t, fd,
 		const struct compat_iovec __user *,vec,
-		unsigned long, vlen)
+		compat_ulong_t, vlen)
 {
 	struct fd f = fdget(fd);
 	ssize_t ret;
@@ -1005,9 +1005,9 @@ COMPAT_SYSCALL_DEFINE4(preadv64, unsigned long, fd,
 	return ret;
 }
 
-COMPAT_SYSCALL_DEFINE5(preadv, unsigned long, fd,
+COMPAT_SYSCALL_DEFINE5(preadv, compat_ulong_t, fd,
 		const struct compat_iovec __user *,vec,
-		unsigned long, vlen, u32, pos_low, u32, pos_high)
+		compat_ulong_t, vlen, u32, pos_low, u32, pos_high)
 {
 	loff_t pos = ((loff_t)pos_high << 32) | pos_low;
 	return compat_sys_preadv64(fd, vec, vlen, pos);
@@ -1035,9 +1035,9 @@ out:
 	return ret;
 }
 
-COMPAT_SYSCALL_DEFINE3(writev, unsigned long, fd,
+COMPAT_SYSCALL_DEFINE3(writev, compat_ulong_t, fd,
 		const struct compat_iovec __user *, vec,
-		unsigned long, vlen)
+		compat_ulong_t, vlen)
 {
 	struct fd f = fdget(fd);
 	ssize_t ret;
@@ -1072,9 +1072,9 @@ COMPAT_SYSCALL_DEFINE4(pwritev64, unsigned long, fd,
 	return ret;
 }
 
-COMPAT_SYSCALL_DEFINE5(pwritev, unsigned long, fd,
+COMPAT_SYSCALL_DEFINE5(pwritev, compat_ulong_t, fd,
 		const struct compat_iovec __user *,vec,
-		unsigned long, vlen, u32, pos_low, u32, pos_high)
+		compat_ulong_t, vlen, u32, pos_low, u32, pos_high)
 {
 	loff_t pos = ((loff_t)pos_high << 32) | pos_low;
 	return compat_sys_pwritev64(fd, vec, vlen, pos);
diff --git a/fs/splice.c b/fs/splice.c
index 46a08f772d7d..12028fa41def 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -555,6 +555,24 @@ static const struct pipe_buf_operations default_pipe_buf_ops = {
 	.get = generic_pipe_buf_get,
 };
 
+static int generic_pipe_buf_nosteal(struct pipe_inode_info *pipe,
+				    struct pipe_buffer *buf)
+{
+	return 1;
+}
+
+/* Pipe buffer operations for a socket and similar. */
+const struct pipe_buf_operations nosteal_pipe_buf_ops = {
+	.can_merge = 0,
+	.map = generic_pipe_buf_map,
+	.unmap = generic_pipe_buf_unmap,
+	.confirm = generic_pipe_buf_confirm,
+	.release = generic_pipe_buf_release,
+	.steal = generic_pipe_buf_nosteal,
+	.get = generic_pipe_buf_get,
+};
+EXPORT_SYMBOL(nosteal_pipe_buf_ops);
+
 static ssize_t kernel_readv(struct file *file, const struct iovec *vec,
 			    unsigned long vlen, loff_t offset)
 {
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index db0923458940..8e4f41d9af4d 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -558,6 +558,18 @@ static inline pmd_t pmd_read_atomic(pmd_t *pmdp)
 }
 #endif
 
+#ifndef pmd_move_must_withdraw
+static inline int pmd_move_must_withdraw(spinlock_t *new_pmd_ptl,
+					 spinlock_t *old_pmd_ptl)
+{
+	/*
+	 * With split pmd lock we also need to move preallocated
+	 * PTE page table if new_pmd is on different PMD page table.
+	 */
+	return new_pmd_ptl != old_pmd_ptl;
+}
+#endif
+
 /*
  * This function is meant to be used by sites walking pagetables with
  * the mmap_sem hold in read mode to protect against MADV_DONTNEED and
diff --git a/include/linux/audit.h b/include/linux/audit.h
index a40641954c29..bf1ef223bc1f 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -137,7 +137,7 @@ static inline void audit_syscall_exit(void *pt_regs)
 {
 	if (unlikely(current->audit_context)) {
 		int success = is_syscall_success(pt_regs);
-		int return_code = regs_return_value(pt_regs);
+		long return_code = regs_return_value(pt_regs);
 
 		__audit_syscall_exit(success, return_code);
 	}
diff --git a/include/linux/compat.h b/include/linux/compat.h
index eb8a49d75ab3..19f6003291de 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -327,16 +327,16 @@ asmlinkage long compat_sys_keyctl(u32 option,
 			      u32 arg2, u32 arg3, u32 arg4, u32 arg5);
 asmlinkage long compat_sys_ustat(unsigned dev, struct compat_ustat __user *u32);
 
-asmlinkage ssize_t compat_sys_readv(unsigned long fd,
-		const struct compat_iovec __user *vec, unsigned long vlen);
-asmlinkage ssize_t compat_sys_writev(unsigned long fd,
-		const struct compat_iovec __user *vec, unsigned long vlen);
-asmlinkage ssize_t compat_sys_preadv(unsigned long fd,
+asmlinkage ssize_t compat_sys_readv(compat_ulong_t fd,
+		const struct compat_iovec __user *vec, compat_ulong_t vlen);
+asmlinkage ssize_t compat_sys_writev(compat_ulong_t fd,
+		const struct compat_iovec __user *vec, compat_ulong_t vlen);
+asmlinkage ssize_t compat_sys_preadv(compat_ulong_t fd,
 		const struct compat_iovec __user *vec,
-		unsigned long vlen, u32 pos_low, u32 pos_high);
-asmlinkage ssize_t compat_sys_pwritev(unsigned long fd,
+		compat_ulong_t vlen, u32 pos_low, u32 pos_high);
+asmlinkage ssize_t compat_sys_pwritev(compat_ulong_t fd,
 		const struct compat_iovec __user *vec,
-		unsigned long vlen, u32 pos_low, u32 pos_high);
+		compat_ulong_t vlen, u32 pos_low, u32 pos_high);
 asmlinkage long comat_sys_lseek(unsigned int, compat_off_t, unsigned int);
 
 asmlinkage long compat_sys_execve(const char __user *filename, const compat_uptr_t __user *argv,
@@ -422,7 +422,7 @@ extern long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
 asmlinkage long compat_sys_ptrace(compat_long_t request, compat_long_t pid,
 				  compat_long_t addr, compat_long_t data);
 
-asmlinkage long compat_sys_lookup_dcookie(u32, u32, char __user *, size_t);
+asmlinkage long compat_sys_lookup_dcookie(u32, u32, char __user *, compat_size_t);
 /*
  * epoll (fs/eventpoll.c) compat bits follow ...
  */
diff --git a/include/linux/percpu_ida.h b/include/linux/percpu_ida.h
index 1900bd0fa639..f5cfdd6a5539 100644
--- a/include/linux/percpu_ida.h
+++ b/include/linux/percpu_ida.h
@@ -4,6 +4,7 @@
 #include <linux/types.h>
 #include <linux/bitops.h>
 #include <linux/init.h>
+#include <linux/sched.h>
 #include <linux/spinlock_types.h>
 #include <linux/wait.h>
 #include <linux/cpumask.h>
@@ -61,7 +62,7 @@ struct percpu_ida {
 /* Max size of percpu freelist, */
 #define IDA_DEFAULT_PCPU_SIZE	((IDA_DEFAULT_PCPU_BATCH_MOVE * 3) / 2)
 
-int percpu_ida_alloc(struct percpu_ida *pool, gfp_t gfp);
+int percpu_ida_alloc(struct percpu_ida *pool, int state);
 void percpu_ida_free(struct percpu_ida *pool, unsigned tag);
 
 void percpu_ida_destroy(struct percpu_ida *pool);
diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h
index b8809fef61f5..ab5752692113 100644
--- a/include/linux/pipe_fs_i.h
+++ b/include/linux/pipe_fs_i.h
@@ -157,6 +157,8 @@ int generic_pipe_buf_confirm(struct pipe_inode_info *, struct pipe_buffer *);
 int generic_pipe_buf_steal(struct pipe_inode_info *, struct pipe_buffer *);
 void generic_pipe_buf_release(struct pipe_inode_info *, struct pipe_buffer *);
 
+extern const struct pipe_buf_operations nosteal_pipe_buf_ops;
+
 /* for F_SETPIPE_SZ and F_GETPIPE_SZ */
 long pipe_fcntl(struct file *, unsigned int, unsigned long arg);
 struct pipe_inode_info *get_pipe_info(struct file *file);
diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h
index 41467f8ff8ec..e3347c518a9a 100644
--- a/include/linux/sched/sysctl.h
+++ b/include/linux/sched/sysctl.h
@@ -100,4 +100,8 @@ extern int sched_rt_handler(struct ctl_table *table, int write,
 		void __user *buffer, size_t *lenp,
 		loff_t *ppos);
 
+extern int sysctl_numa_balancing(struct ctl_table *table, int write,
+				 void __user *buffer, size_t *lenp,
+				 loff_t *ppos);
+
 #endif /* _SCHED_SYSCTL_H */
diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index e4b948080d20..a67b38415768 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -142,8 +142,6 @@ static inline unsigned long zone_page_state_snapshot(struct zone *zone,
 	return x;
 }
 
-extern unsigned long global_reclaimable_pages(void);
-
 #ifdef CONFIG_NUMA
 /*
  * Determine the per node value of a stat item. This function
diff --git a/include/scsi/osd_ore.h b/include/scsi/osd_ore.h
index a5f9b960dfc8..6ca3265a4dca 100644
--- a/include/scsi/osd_ore.h
+++ b/include/scsi/osd_ore.h
@@ -102,6 +102,7 @@ struct ore_striping_info {
 	unsigned unit_off;
 	unsigned cur_pg;
 	unsigned cur_comp;
+	unsigned maxdevUnits;
 };
 
 struct ore_io_state;
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index 321301c0a643..e3569f829f7e 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -497,7 +497,7 @@ struct se_cmd {
 	void			*priv;
 
 	/* Used for lun->lun_ref counting */
-	bool			lun_ref_active;
+	int			lun_ref_active;
 };
 
 struct se_ua {
diff --git a/include/xen/platform_pci.h b/include/xen/platform_pci.h
index 438c256c274b..b49eeab0262e 100644
--- a/include/xen/platform_pci.h
+++ b/include/xen/platform_pci.h
@@ -48,4 +48,27 @@ static inline int xen_must_unplug_disks(void) {
 
 extern int xen_platform_pci_unplug;
 
+#if defined(CONFIG_XEN_PVHVM)
+extern bool xen_has_pv_devices(void);
+extern bool xen_has_pv_disk_devices(void);
+extern bool xen_has_pv_nic_devices(void);
+extern bool xen_has_pv_and_legacy_disk_devices(void);
+#else
+static inline bool xen_has_pv_devices(void)
+{
+	return IS_ENABLED(CONFIG_XEN);
+}
+static inline bool xen_has_pv_disk_devices(void)
+{
+	return IS_ENABLED(CONFIG_XEN);
+}
+static inline bool xen_has_pv_nic_devices(void)
+{
+	return IS_ENABLED(CONFIG_XEN);
+}
+static inline bool xen_has_pv_and_legacy_disk_devices(void)
+{
+	return false;
+}
+#endif
 #endif /* _XEN_PLATFORM_PCI_H */
diff --git a/kernel/audit.c b/kernel/audit.c
index 906ae5a0233a..15ec13a14e4e 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -102,7 +102,8 @@ static int	audit_rate_limit;
 
 /* Number of outstanding audit_buffers allowed. */
 static int	audit_backlog_limit = 64;
-static int	audit_backlog_wait_time = 60 * HZ;
+#define AUDIT_BACKLOG_WAIT_TIME (60 * HZ)
+static int	audit_backlog_wait_time = AUDIT_BACKLOG_WAIT_TIME;
 static int	audit_backlog_wait_overflow = 0;
 
 /* The identity of the user shutting down the audit system. */
@@ -1239,6 +1240,8 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask,
 		return NULL;
 	}
 
+	audit_backlog_wait_time = AUDIT_BACKLOG_WAIT_TIME;
+
 	ab = audit_buffer_alloc(ctx, gfp_mask, type);
 	if (!ab) {
 		audit_log_lost("out of memory in audit_log_start");
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index a88f4a485c5e..c67751034bc9 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1763,7 +1763,29 @@ void set_numabalancing_state(bool enabled)
 	numabalancing_enabled = enabled;
 }
 #endif /* CONFIG_SCHED_DEBUG */
-#endif /* CONFIG_NUMA_BALANCING */
+
+#ifdef CONFIG_PROC_SYSCTL
+int sysctl_numa_balancing(struct ctl_table *table, int write,
+			 void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	struct ctl_table t;
+	int err;
+	int state = numabalancing_enabled;
+
+	if (write && !capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	t = *table;
+	t.data = &state;
+	err = proc_dointvec_minmax(&t, write, buffer, lenp, ppos);
+	if (err < 0)
+		return err;
+	if (write)
+		set_numabalancing_state(state);
+	return err;
+}
+#endif
+#endif
 
 /*
  * fork()/clone()-time setup:
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 34a604726d0b..06962ba94a66 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -398,6 +398,15 @@ static struct ctl_table kern_table[] = {
 		.mode           = 0644,
 		.proc_handler   = proc_dointvec,
 	},
+	{
+		.procname	= "numa_balancing",
+		.data		= NULL, /* filled in by handler */
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= sysctl_numa_balancing,
+		.extra1		= &zero,
+		.extra2		= &one,
+	},
 #endif /* CONFIG_NUMA_BALANCING */
 #endif /* CONFIG_SCHED_DEBUG */
 	{
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 87b4f00284c9..b4154577cf2e 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -77,7 +77,7 @@ static void tk_set_wall_to_mono(struct timekeeper *tk, struct timespec wtm)
 	tk->wall_to_monotonic = wtm;
 	set_normalized_timespec(&tmp, -wtm.tv_sec, -wtm.tv_nsec);
 	tk->offs_real = timespec_to_ktime(tmp);
-	tk->offs_tai = ktime_sub(tk->offs_real, ktime_set(tk->tai_offset, 0));
+	tk->offs_tai = ktime_add(tk->offs_real, ktime_set(tk->tai_offset, 0));
 }
 
 static void tk_set_sleep_time(struct timekeeper *tk, struct timespec t)
@@ -595,7 +595,7 @@ s32 timekeeping_get_tai_offset(void)
 static void __timekeeping_set_tai_offset(struct timekeeper *tk, s32 tai_offset)
 {
 	tk->tai_offset = tai_offset;
-	tk->offs_tai = ktime_sub(tk->offs_real, ktime_set(tai_offset, 0));
+	tk->offs_tai = ktime_add(tk->offs_real, ktime_set(tai_offset, 0));
 }
 
 /**
@@ -610,6 +610,7 @@ void timekeeping_set_tai_offset(s32 tai_offset)
 	raw_spin_lock_irqsave(&timekeeper_lock, flags);
 	write_seqcount_begin(&timekeeper_seq);
 	__timekeeping_set_tai_offset(tk, tai_offset);
+	timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET);
 	write_seqcount_end(&timekeeper_seq);
 	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
 	clock_was_set();
@@ -1023,6 +1024,8 @@ static int timekeeping_suspend(void)
 		timekeeping_suspend_time =
 			timespec_add(timekeeping_suspend_time, delta_delta);
 	}
+
+	timekeeping_update(tk, TK_MIRROR);
 	write_seqcount_end(&timekeeper_seq);
 	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
 
@@ -1255,7 +1258,7 @@ out_adjust:
 static inline unsigned int accumulate_nsecs_to_secs(struct timekeeper *tk)
 {
 	u64 nsecps = (u64)NSEC_PER_SEC << tk->shift;
-	unsigned int action = 0;
+	unsigned int clock_set = 0;
 
 	while (tk->xtime_nsec >= nsecps) {
 		int leap;
@@ -1277,11 +1280,10 @@ static inline unsigned int accumulate_nsecs_to_secs(struct timekeeper *tk)
 
 			__timekeeping_set_tai_offset(tk, tk->tai_offset - leap);
 
-			clock_was_set_delayed();
-			action = TK_CLOCK_WAS_SET;
+			clock_set = TK_CLOCK_WAS_SET;
 		}
 	}
-	return action;
+	return clock_set;
 }
 
 /**
@@ -1294,7 +1296,8 @@ static inline unsigned int accumulate_nsecs_to_secs(struct timekeeper *tk)
  * Returns the unconsumed cycles.
  */
 static cycle_t logarithmic_accumulation(struct timekeeper *tk, cycle_t offset,
-						u32 shift)
+						u32 shift,
+						unsigned int *clock_set)
 {
 	cycle_t interval = tk->cycle_interval << shift;
 	u64 raw_nsecs;
@@ -1308,7 +1311,7 @@ static cycle_t logarithmic_accumulation(struct timekeeper *tk, cycle_t offset,
 	tk->cycle_last += interval;
 
 	tk->xtime_nsec += tk->xtime_interval << shift;
-	accumulate_nsecs_to_secs(tk);
+	*clock_set |= accumulate_nsecs_to_secs(tk);
 
 	/* Accumulate raw time */
 	raw_nsecs = (u64)tk->raw_interval << shift;
@@ -1366,7 +1369,7 @@ static void update_wall_time(void)
 	struct timekeeper *tk = &shadow_timekeeper;
 	cycle_t offset;
 	int shift = 0, maxshift;
-	unsigned int action;
+	unsigned int clock_set = 0;
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&timekeeper_lock, flags);
@@ -1401,7 +1404,8 @@ static void update_wall_time(void)
 	maxshift = (64 - (ilog2(ntp_tick_length())+1)) - 1;
 	shift = min(shift, maxshift);
 	while (offset >= tk->cycle_interval) {
-		offset = logarithmic_accumulation(tk, offset, shift);
+		offset = logarithmic_accumulation(tk, offset, shift,
+							&clock_set);
 		if (offset < tk->cycle_interval<<shift)
 			shift--;
 	}
@@ -1419,7 +1423,7 @@ static void update_wall_time(void)
 	 * Finally, make sure that after the rounding
 	 * xtime_nsec isn't larger than NSEC_PER_SEC
 	 */
-	action = accumulate_nsecs_to_secs(tk);
+	clock_set |= accumulate_nsecs_to_secs(tk);
 
 	write_seqcount_begin(&timekeeper_seq);
 	/* Update clock->cycle_last with the new value */
@@ -1435,10 +1439,23 @@ static void update_wall_time(void)
 	 * updating.
 	 */
 	memcpy(real_tk, tk, sizeof(*tk));
-	timekeeping_update(real_tk, action);
+	timekeeping_update(real_tk, clock_set);
 	write_seqcount_end(&timekeeper_seq);
 out:
 	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
+	if (clock_set) {
+		/*
+		 * XXX -  I'd rather we just call clock_was_set(), but
+		 * since we're currently holding the jiffies lock, calling
+		 * clock_was_set would trigger an ipi which would then grab
+		 * the jiffies lock and we'd deadlock. :(
+		 * The right solution should probably be droping
+		 * the jiffies lock before calling update_wall_time
+		 * but that requires some rework of the tick sched
+		 * code.
+		 */
+		clock_was_set_delayed();
+	}
 }
 
 /**
@@ -1698,12 +1715,14 @@ int do_adjtimex(struct timex *txc)
 
 	if (tai != orig_tai) {
 		__timekeeping_set_tai_offset(tk, tai);
-		update_pvclock_gtod(tk, true);
-		clock_was_set_delayed();
+		timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET);
 	}
 	write_seqcount_end(&timekeeper_seq);
 	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
 
+	if (tai != orig_tai)
+		clock_was_set();
+
 	ntp_notify_cmos_timer();
 
 	return ret;
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 72a0f81dc5a8..38463d218c42 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -85,6 +85,8 @@ int function_trace_stop __read_mostly;
 
 /* Current function tracing op */
 struct ftrace_ops *function_trace_op __read_mostly = &ftrace_list_end;
+/* What to set function_trace_op to */
+static struct ftrace_ops *set_function_trace_op;
 
 /* List for set_ftrace_pid's pids. */
 LIST_HEAD(ftrace_pids);
@@ -278,6 +280,29 @@ static void update_global_ops(void)
 	global_ops.func = func;
 }
 
+static void ftrace_sync(struct work_struct *work)
+{
+	/*
+	 * This function is just a stub to implement a hard force
+	 * of synchronize_sched(). This requires synchronizing
+	 * tasks even in userspace and idle.
+	 *
+	 * Yes, function tracing is rude.
+	 */
+}
+
+static void ftrace_sync_ipi(void *data)
+{
+	/* Probably not needed, but do it anyway */
+	smp_rmb();
+}
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+static void update_function_graph_func(void);
+#else
+static inline void update_function_graph_func(void) { }
+#endif
+
 static void update_ftrace_function(void)
 {
 	ftrace_func_t func;
@@ -296,16 +321,61 @@ static void update_ftrace_function(void)
 	     !FTRACE_FORCE_LIST_FUNC)) {
 		/* Set the ftrace_ops that the arch callback uses */
 		if (ftrace_ops_list == &global_ops)
-			function_trace_op = ftrace_global_list;
+			set_function_trace_op = ftrace_global_list;
 		else
-			function_trace_op = ftrace_ops_list;
+			set_function_trace_op = ftrace_ops_list;
 		func = ftrace_ops_list->func;
 	} else {
 		/* Just use the default ftrace_ops */
-		function_trace_op = &ftrace_list_end;
+		set_function_trace_op = &ftrace_list_end;
 		func = ftrace_ops_list_func;
 	}
 
+	/* If there's no change, then do nothing more here */
+	if (ftrace_trace_function == func)
+		return;
+
+	update_function_graph_func();
+
+	/*
+	 * If we are using the list function, it doesn't care
+	 * about the function_trace_ops.
+	 */
+	if (func == ftrace_ops_list_func) {
+		ftrace_trace_function = func;
+		/*
+		 * Don't even bother setting function_trace_ops,
+		 * it would be racy to do so anyway.
+		 */
+		return;
+	}
+
+#ifndef CONFIG_DYNAMIC_FTRACE
+	/*
+	 * For static tracing, we need to be a bit more careful.
+	 * The function change takes affect immediately. Thus,
+	 * we need to coorditate the setting of the function_trace_ops
+	 * with the setting of the ftrace_trace_function.
+	 *
+	 * Set the function to the list ops, which will call the
+	 * function we want, albeit indirectly, but it handles the
+	 * ftrace_ops and doesn't depend on function_trace_op.
+	 */
+	ftrace_trace_function = ftrace_ops_list_func;
+	/*
+	 * Make sure all CPUs see this. Yes this is slow, but static
+	 * tracing is slow and nasty to have enabled.
+	 */
+	schedule_on_each_cpu(ftrace_sync);
+	/* Now all cpus are using the list ops. */
+	function_trace_op = set_function_trace_op;
+	/* Make sure the function_trace_op is visible on all CPUs */
+	smp_wmb();
+	/* Nasty way to force a rmb on all cpus */
+	smp_call_function(ftrace_sync_ipi, NULL, 1);
+	/* OK, we are all set to update the ftrace_trace_function now! */
+#endif /* !CONFIG_DYNAMIC_FTRACE */
+
 	ftrace_trace_function = func;
 }
 
@@ -410,17 +480,6 @@ static int __register_ftrace_function(struct ftrace_ops *ops)
 	return 0;
 }
 
-static void ftrace_sync(struct work_struct *work)
-{
-	/*
-	 * This function is just a stub to implement a hard force
-	 * of synchronize_sched(). This requires synchronizing
-	 * tasks even in userspace and idle.
-	 *
-	 * Yes, function tracing is rude.
-	 */
-}
-
 static int __unregister_ftrace_function(struct ftrace_ops *ops)
 {
 	int ret;
@@ -439,20 +498,6 @@ static int __unregister_ftrace_function(struct ftrace_ops *ops)
 	} else if (ops->flags & FTRACE_OPS_FL_CONTROL) {
 		ret = remove_ftrace_list_ops(&ftrace_control_list,
 					     &control_ops, ops);
-		if (!ret) {
-			/*
-			 * The ftrace_ops is now removed from the list,
-			 * so there'll be no new users. We must ensure
-			 * all current users are done before we free
-			 * the control data.
-			 * Note synchronize_sched() is not enough, as we
-			 * use preempt_disable() to do RCU, but the function
-			 * tracer can be called where RCU is not active
-			 * (before user_exit()).
-			 */
-			schedule_on_each_cpu(ftrace_sync);
-			control_ops_free(ops);
-		}
 	} else
 		ret = remove_ftrace_ops(&ftrace_ops_list, ops);
 
@@ -462,17 +507,6 @@ static int __unregister_ftrace_function(struct ftrace_ops *ops)
 	if (ftrace_enabled)
 		update_ftrace_function();
 
-	/*
-	 * Dynamic ops may be freed, we must make sure that all
-	 * callers are done before leaving this function.
-	 *
-	 * Again, normal synchronize_sched() is not good enough.
-	 * We need to do a hard force of sched synchronization.
-	 */
-	if (ops->flags & FTRACE_OPS_FL_DYNAMIC)
-		schedule_on_each_cpu(ftrace_sync);
-
-
 	return 0;
 }
 
@@ -1992,8 +2026,14 @@ void ftrace_modify_all_code(int command)
 	else if (command & FTRACE_DISABLE_CALLS)
 		ftrace_replace_code(0);
 
-	if (update && ftrace_trace_function != ftrace_ops_list_func)
+	if (update && ftrace_trace_function != ftrace_ops_list_func) {
+		function_trace_op = set_function_trace_op;
+		smp_wmb();
+		/* If irqs are disabled, we are in stop machine */
+		if (!irqs_disabled())
+			smp_call_function(ftrace_sync_ipi, NULL, 1);
 		ftrace_update_ftrace_func(ftrace_trace_function);
+	}
 
 	if (command & FTRACE_START_FUNC_RET)
 		ftrace_enable_ftrace_graph_caller();
@@ -2156,10 +2196,41 @@ static int ftrace_shutdown(struct ftrace_ops *ops, int command)
 		command |= FTRACE_UPDATE_TRACE_FUNC;
 	}
 
-	if (!command || !ftrace_enabled)
+	if (!command || !ftrace_enabled) {
+		/*
+		 * If these are control ops, they still need their
+		 * per_cpu field freed. Since, function tracing is
+		 * not currently active, we can just free them
+		 * without synchronizing all CPUs.
+		 */
+		if (ops->flags & FTRACE_OPS_FL_CONTROL)
+			control_ops_free(ops);
 		return 0;
+	}
 
 	ftrace_run_update_code(command);
+
+	/*
+	 * Dynamic ops may be freed, we must make sure that all
+	 * callers are done before leaving this function.
+	 * The same goes for freeing the per_cpu data of the control
+	 * ops.
+	 *
+	 * Again, normal synchronize_sched() is not good enough.
+	 * We need to do a hard force of sched synchronization.
+	 * This is because we use preempt_disable() to do RCU, but
+	 * the function tracers can be called where RCU is not watching
+	 * (like before user_exit()). We can not rely on the RCU
+	 * infrastructure to do the synchronization, thus we must do it
+	 * ourselves.
+	 */
+	if (ops->flags & (FTRACE_OPS_FL_DYNAMIC | FTRACE_OPS_FL_CONTROL)) {
+		schedule_on_each_cpu(ftrace_sync);
+
+		if (ops->flags & FTRACE_OPS_FL_CONTROL)
+			control_ops_free(ops);
+	}
+
 	return 0;
 }
 
@@ -4862,6 +4933,7 @@ int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace)
 trace_func_graph_ret_t ftrace_graph_return =
 			(trace_func_graph_ret_t)ftrace_stub;
 trace_func_graph_ent_t ftrace_graph_entry = ftrace_graph_entry_stub;
+static trace_func_graph_ent_t __ftrace_graph_entry = ftrace_graph_entry_stub;
 
 /* Try to assign a return stack array on FTRACE_RETSTACK_ALLOC_SIZE tasks. */
 static int alloc_retstack_tasklist(struct ftrace_ret_stack **ret_stack_list)
@@ -5003,6 +5075,30 @@ static struct ftrace_ops fgraph_ops __read_mostly = {
 				FTRACE_OPS_FL_RECURSION_SAFE,
 };
 
+static int ftrace_graph_entry_test(struct ftrace_graph_ent *trace)
+{
+	if (!ftrace_ops_test(&global_ops, trace->func, NULL))
+		return 0;
+	return __ftrace_graph_entry(trace);
+}
+
+/*
+ * The function graph tracer should only trace the functions defined
+ * by set_ftrace_filter and set_ftrace_notrace. If another function
+ * tracer ops is registered, the graph tracer requires testing the
+ * function against the global ops, and not just trace any function
+ * that any ftrace_ops registered.
+ */
+static void update_function_graph_func(void)
+{
+	if (ftrace_ops_list == &ftrace_list_end ||
+	    (ftrace_ops_list == &global_ops &&
+	     global_ops.next == &ftrace_list_end))
+		ftrace_graph_entry = __ftrace_graph_entry;
+	else
+		ftrace_graph_entry = ftrace_graph_entry_test;
+}
+
 int register_ftrace_graph(trace_func_graph_ret_t retfunc,
 			trace_func_graph_ent_t entryfunc)
 {
@@ -5027,7 +5123,16 @@ int register_ftrace_graph(trace_func_graph_ret_t retfunc,
 	}
 
 	ftrace_graph_return = retfunc;
-	ftrace_graph_entry = entryfunc;
+
+	/*
+	 * Update the indirect function to the entryfunc, and the
+	 * function that gets called to the entry_test first. Then
+	 * call the update fgraph entry function to determine if
+	 * the entryfunc should be called directly or not.
+	 */
+	__ftrace_graph_entry = entryfunc;
+	ftrace_graph_entry = ftrace_graph_entry_test;
+	update_function_graph_func();
 
 	ret = ftrace_startup(&fgraph_ops, FTRACE_START_FUNC_RET);
 
@@ -5046,6 +5151,7 @@ void unregister_ftrace_graph(void)
 	ftrace_graph_active--;
 	ftrace_graph_return = (trace_func_graph_ret_t)ftrace_stub;
 	ftrace_graph_entry = ftrace_graph_entry_stub;
+	__ftrace_graph_entry = ftrace_graph_entry_stub;
 	ftrace_shutdown(&fgraph_ops, FTRACE_STOP_FUNC_RET);
 	unregister_pm_notifier(&ftrace_suspend_notifier);
 	unregister_trace_sched_switch(ftrace_graph_probe_sched_switch, NULL);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 9d20cd9743ef..0a360ce6b7ea 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -455,6 +455,9 @@ int __trace_puts(unsigned long ip, const char *str, int size)
 	unsigned long irq_flags;
 	int alloc;
 
+	if (unlikely(tracing_selftest_running || tracing_disabled))
+		return 0;
+
 	alloc = sizeof(*entry) + size + 2; /* possible \n added */
 
 	local_save_flags(irq_flags);
@@ -495,6 +498,9 @@ int __trace_bputs(unsigned long ip, const char *str)
 	unsigned long irq_flags;
 	int size = sizeof(struct bputs_entry);
 
+	if (unlikely(tracing_selftest_running || tracing_disabled))
+		return 0;
+
 	local_save_flags(irq_flags);
 	buffer = global_trace.trace_buffer.buffer;
 	event = trace_buffer_lock_reserve(buffer, TRACE_BPUTS, size,
@@ -5883,6 +5889,8 @@ allocate_trace_buffer(struct trace_array *tr, struct trace_buffer *buf, int size
 
 	rb_flags = trace_flags & TRACE_ITER_OVERWRITE ? RB_FL_OVERWRITE : 0;
 
+	buf->tr = tr;
+
 	buf->buffer = ring_buffer_alloc(size, rb_flags);
 	if (!buf->buffer)
 		return -ENOMEM;
diff --git a/lib/genalloc.c b/lib/genalloc.c
index dda31168844f..bdb9a456bcbb 100644
--- a/lib/genalloc.c
+++ b/lib/genalloc.c
@@ -316,7 +316,7 @@ EXPORT_SYMBOL(gen_pool_alloc);
  * gen_pool_dma_alloc - allocate special memory from the pool for DMA usage
  * @pool: pool to allocate from
  * @size: number of bytes to allocate from the pool
- * @dma: dma-view physical address
+ * @dma: dma-view physical address return value.  Use NULL if unneeded.
  *
  * Allocate the requested number of bytes from the specified pool.
  * Uses the pool allocation function (with first-fit algorithm by default).
@@ -334,7 +334,8 @@ void *gen_pool_dma_alloc(struct gen_pool *pool, size_t size, dma_addr_t *dma)
 	if (!vaddr)
 		return NULL;
 
-	*dma = gen_pool_virt_to_phys(pool, vaddr);
+	if (dma)
+		*dma = gen_pool_virt_to_phys(pool, vaddr);
 
 	return (void *)vaddr;
 }
diff --git a/lib/percpu_ida.c b/lib/percpu_ida.c
index 9d054bf91d0f..7be235f1a70b 100644
--- a/lib/percpu_ida.c
+++ b/lib/percpu_ida.c
@@ -132,22 +132,22 @@ static inline unsigned alloc_local_tag(struct percpu_ida_cpu *tags)
 /**
  * percpu_ida_alloc - allocate a tag
  * @pool: pool to allocate from
- * @gfp: gfp flags
+ * @state: task state for prepare_to_wait
  *
  * Returns a tag - an integer in the range [0..nr_tags) (passed to
  * tag_pool_init()), or otherwise -ENOSPC on allocation failure.
  *
  * Safe to be called from interrupt context (assuming it isn't passed
- * __GFP_WAIT, of course).
+ * TASK_UNINTERRUPTIBLE | TASK_INTERRUPTIBLE, of course).
  *
  * @gfp indicates whether or not to wait until a free id is available (it's not
  * used for internal memory allocations); thus if passed __GFP_WAIT we may sleep
  * however long it takes until another thread frees an id (same semantics as a
  * mempool).
  *
- * Will not fail if passed __GFP_WAIT.
+ * Will not fail if passed TASK_UNINTERRUPTIBLE | TASK_INTERRUPTIBLE.
  */
-int percpu_ida_alloc(struct percpu_ida *pool, gfp_t gfp)
+int percpu_ida_alloc(struct percpu_ida *pool, int state)
 {
 	DEFINE_WAIT(wait);
 	struct percpu_ida_cpu *tags;
@@ -174,7 +174,8 @@ int percpu_ida_alloc(struct percpu_ida *pool, gfp_t gfp)
 		 *
 		 * global lock held and irqs disabled, don't need percpu lock
 		 */
-		prepare_to_wait(&pool->wait, &wait, TASK_UNINTERRUPTIBLE);
+		if (state != TASK_RUNNING)
+			prepare_to_wait(&pool->wait, &wait, state);
 
 		if (!tags->nr_free)
 			alloc_global_tags(pool, tags);
@@ -191,16 +192,22 @@ int percpu_ida_alloc(struct percpu_ida *pool, gfp_t gfp)
 		spin_unlock(&pool->lock);
 		local_irq_restore(flags);
 
-		if (tag >= 0 || !(gfp & __GFP_WAIT))
+		if (tag >= 0 || state == TASK_RUNNING)
 			break;
 
+		if (signal_pending_state(state, current)) {
+			tag = -ERESTARTSYS;
+			break;
+		}
+
 		schedule();
 
 		local_irq_save(flags);
 		tags = this_cpu_ptr(pool->tag_cpu);
 	}
+	if (state != TASK_RUNNING)
+		finish_wait(&pool->wait, &wait);
 
-	finish_wait(&pool->wait, &wait);
 	return tag;
 }
 EXPORT_SYMBOL_GPL(percpu_ida_alloc);
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 95d1acb0f3d2..5d80c53b87cb 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1502,19 +1502,15 @@ int move_huge_pmd(struct vm_area_struct *vma, struct vm_area_struct *new_vma,
 			spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING);
 		pmd = pmdp_get_and_clear(mm, old_addr, old_pmd);
 		VM_BUG_ON(!pmd_none(*new_pmd));
-		set_pmd_at(mm, new_addr, new_pmd, pmd_mksoft_dirty(pmd));
-		if (new_ptl != old_ptl) {
-			pgtable_t pgtable;
 
-			/*
-			 * Move preallocated PTE page table if new_pmd is on
-			 * different PMD page table.
-			 */
+		if (pmd_move_must_withdraw(new_ptl, old_ptl)) {
+			pgtable_t pgtable;
 			pgtable = pgtable_trans_huge_withdraw(mm, old_pmd);
 			pgtable_trans_huge_deposit(mm, new_pmd, pgtable);
-
-			spin_unlock(new_ptl);
 		}
+		set_pmd_at(mm, new_addr, new_pmd, pmd_mksoft_dirty(pmd));
+		if (new_ptl != old_ptl)
+			spin_unlock(new_ptl);
 		spin_unlock(old_ptl);
 	}
 out:
diff --git a/mm/internal.h b/mm/internal.h
index 684f7aa9692a..8b6cfd63b5a5 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -85,7 +85,6 @@ extern unsigned long highest_memmap_pfn;
  */
 extern int isolate_lru_page(struct page *page);
 extern void putback_lru_page(struct page *page);
-extern unsigned long zone_reclaimable_pages(struct zone *zone);
 extern bool zone_reclaimable(struct zone *zone);
 
 /*
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 7f1a356153c0..00fd7fd1b5a4 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1098,16 +1098,22 @@ skip_node:
 	 * skipped and we should continue the tree walk.
 	 * last_visited css is safe to use because it is
 	 * protected by css_get and the tree walk is rcu safe.
+	 *
+	 * We do not take a reference on the root of the tree walk
+	 * because we might race with the root removal when it would
+	 * be the only node in the iterated hierarchy and mem_cgroup_iter
+	 * would end up in an endless loop because it expects that at
+	 * least one valid node will be returned. Root cannot disappear
+	 * because caller of the iterator should hold it already so
+	 * skipping css reference should be safe.
 	 */
 	if (next_css) {
-		struct mem_cgroup *mem = mem_cgroup_from_css(next_css);
+		if ((next_css->flags & CSS_ONLINE) &&
+				(next_css == &root->css || css_tryget(next_css)))
+			return mem_cgroup_from_css(next_css);
 
-		if (css_tryget(&mem->css))
-			return mem;
-		else {
-			prev_css = next_css;
-			goto skip_node;
-		}
+		prev_css = next_css;
+		goto skip_node;
 	}
 
 	return NULL;
@@ -1141,7 +1147,15 @@ mem_cgroup_iter_load(struct mem_cgroup_reclaim_iter *iter,
 	if (iter->last_dead_count == *sequence) {
 		smp_rmb();
 		position = iter->last_visited;
-		if (position && !css_tryget(&position->css))
+
+		/*
+		 * We cannot take a reference to root because we might race
+		 * with root removal and returning NULL would end up in
+		 * an endless loop on the iterator user level when root
+		 * would be returned all the time.
+		 */
+		if (position && position != root &&
+				!css_tryget(&position->css))
 			position = NULL;
 	}
 	return position;
@@ -1150,9 +1164,11 @@ mem_cgroup_iter_load(struct mem_cgroup_reclaim_iter *iter,
 static void mem_cgroup_iter_update(struct mem_cgroup_reclaim_iter *iter,
 				   struct mem_cgroup *last_visited,
 				   struct mem_cgroup *new_position,
+				   struct mem_cgroup *root,
 				   int sequence)
 {
-	if (last_visited)
+	/* root reference counting symmetric to mem_cgroup_iter_load */
+	if (last_visited && last_visited != root)
 		css_put(&last_visited->css);
 	/*
 	 * We store the sequence count from the time @last_visited was
@@ -1227,7 +1243,8 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
 		memcg = __mem_cgroup_iter_next(root, last_visited);
 
 		if (reclaim) {
-			mem_cgroup_iter_update(iter, last_visited, memcg, seq);
+			mem_cgroup_iter_update(iter, last_visited, memcg, root,
+					seq);
 
 			if (!memcg)
 				iter->generation++;
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index fabe55046c1d..6420be516073 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -856,14 +856,14 @@ static int page_action(struct page_state *ps, struct page *p,
  * the pages and send SIGBUS to the processes if the data was dirty.
  */
 static int hwpoison_user_mappings(struct page *p, unsigned long pfn,
-				  int trapno, int flags)
+				  int trapno, int flags, struct page **hpagep)
 {
 	enum ttu_flags ttu = TTU_UNMAP | TTU_IGNORE_MLOCK | TTU_IGNORE_ACCESS;
 	struct address_space *mapping;
 	LIST_HEAD(tokill);
 	int ret;
 	int kill = 1, forcekill;
-	struct page *hpage = compound_head(p);
+	struct page *hpage = *hpagep;
 	struct page *ppage;
 
 	if (PageReserved(p) || PageSlab(p))
@@ -942,11 +942,14 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn,
 			 * We pinned the head page for hwpoison handling,
 			 * now we split the thp and we are interested in
 			 * the hwpoisoned raw page, so move the refcount
-			 * to it.
+			 * to it. Similarly, page lock is shifted.
 			 */
 			if (hpage != p) {
 				put_page(hpage);
 				get_page(p);
+				lock_page(p);
+				unlock_page(hpage);
+				*hpagep = p;
 			}
 			/* THP is split, so ppage should be the real poisoned page. */
 			ppage = p;
@@ -964,17 +967,11 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn,
 	if (kill)
 		collect_procs(ppage, &tokill);
 
-	if (hpage != ppage)
-		lock_page(ppage);
-
 	ret = try_to_unmap(ppage, ttu);
 	if (ret != SWAP_SUCCESS)
 		printk(KERN_ERR "MCE %#lx: failed to unmap page (mapcount=%d)\n",
 				pfn, page_mapcount(ppage));
 
-	if (hpage != ppage)
-		unlock_page(ppage);
-
 	/*
 	 * Now that the dirty bit has been propagated to the
 	 * struct page and all unmaps done we can decide if
@@ -1193,8 +1190,12 @@ int memory_failure(unsigned long pfn, int trapno, int flags)
 	/*
 	 * Now take care of user space mappings.
 	 * Abort on fail: __delete_from_page_cache() assumes unmapped page.
+	 *
+	 * When the raw error page is thp tail page, hpage points to the raw
+	 * page after thp split.
 	 */
-	if (hwpoison_user_mappings(p, pfn, trapno, flags) != SWAP_SUCCESS) {
+	if (hwpoison_user_mappings(p, pfn, trapno, flags, &hpage)
+	    != SWAP_SUCCESS) {
 		printk(KERN_ERR "MCE %#lx: cannot unmap page, give up\n", pfn);
 		res = -EBUSY;
 		goto out;
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index e1bd99778b9d..cb2f3dd9f1dd 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -2657,7 +2657,7 @@ void mpol_free_shared_policy(struct shared_policy *p)
 }
 
 #ifdef CONFIG_NUMA_BALANCING
-static bool __initdata numabalancing_override;
+static int __initdata numabalancing_override;
 
 static void __init check_numabalancing_enable(void)
 {
@@ -2666,9 +2666,15 @@ static void __init check_numabalancing_enable(void)
 	if (IS_ENABLED(CONFIG_NUMA_BALANCING_DEFAULT_ENABLED))
 		numabalancing_default = true;
 
+	/* Parsed by setup_numabalancing. override == 1 enables, -1 disables */
+	if (numabalancing_override)
+		set_numabalancing_state(numabalancing_override == 1);
+
 	if (nr_node_ids > 1 && !numabalancing_override) {
-		printk(KERN_INFO "Enabling automatic NUMA balancing. "
-			"Configure with numa_balancing= or sysctl");
+		printk(KERN_INFO "%s automatic NUMA balancing. "
+			"Configure with numa_balancing= or the "
+			"kernel.numa_balancing sysctl",
+			numabalancing_default ? "Enabling" : "Disabling");
 		set_numabalancing_state(numabalancing_default);
 	}
 }
@@ -2678,13 +2684,12 @@ static int __init setup_numabalancing(char *str)
 	int ret = 0;
 	if (!str)
 		goto out;
-	numabalancing_override = true;
 
 	if (!strcmp(str, "enable")) {
-		set_numabalancing_state(true);
+		numabalancing_override = 1;
 		ret = 1;
 	} else if (!strcmp(str, "disable")) {
-		set_numabalancing_state(false);
+		numabalancing_override = -1;
 		ret = 1;
 	}
 out:
diff --git a/mm/mmap.c b/mm/mmap.c
index 834b2d785f1e..546db7437f41 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -893,7 +893,15 @@ again:			remove_next = 1 + (end > next->vm_end);
 static inline int is_mergeable_vma(struct vm_area_struct *vma,
 			struct file *file, unsigned long vm_flags)
 {
-	if (vma->vm_flags ^ vm_flags)
+	/*
+	 * VM_SOFTDIRTY should not prevent from VMA merging, if we
+	 * match the flags but dirty bit -- the caller should mark
+	 * merged VMA as dirty. If dirty bit won't be excluded from
+	 * comparison, we increase pressue on the memory system forcing
+	 * the kernel to generate new VMAs when old one could be
+	 * extended instead.
+	 */
+	if ((vma->vm_flags ^ vm_flags) & ~VM_SOFTDIRTY)
 		return 0;
 	if (vma->vm_file != file)
 		return 0;
@@ -1082,7 +1090,7 @@ static int anon_vma_compatible(struct vm_area_struct *a, struct vm_area_struct *
 	return a->vm_end == b->vm_start &&
 		mpol_equal(vma_policy(a), vma_policy(b)) &&
 		a->vm_file == b->vm_file &&
-		!((a->vm_flags ^ b->vm_flags) & ~(VM_READ|VM_WRITE|VM_EXEC)) &&
+		!((a->vm_flags ^ b->vm_flags) & ~(VM_READ|VM_WRITE|VM_EXEC|VM_SOFTDIRTY)) &&
 		b->vm_pgoff == a->vm_pgoff + ((b->vm_start - a->vm_start) >> PAGE_SHIFT);
 }
 
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 1e4a600a6163..616b2eb9df8d 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -170,7 +170,7 @@ unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg,
 	 * implementation used by LSMs.
 	 */
 	if (has_capability_noaudit(p, CAP_SYS_ADMIN))
-		adj -= 30;
+		points -= (points * 3) / 100;
 
 	/* Normalize to oom_score_adj units */
 	adj *= totalpages / 1000;
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 63807583d8e8..2d30e2cfe804 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -191,6 +191,26 @@ static unsigned long writeout_period_time = 0;
  * global dirtyable memory first.
  */
 
+/**
+ * zone_dirtyable_memory - number of dirtyable pages in a zone
+ * @zone: the zone
+ *
+ * Returns the zone's number of pages potentially available for dirty
+ * page cache.  This is the base value for the per-zone dirty limits.
+ */
+static unsigned long zone_dirtyable_memory(struct zone *zone)
+{
+	unsigned long nr_pages;
+
+	nr_pages = zone_page_state(zone, NR_FREE_PAGES);
+	nr_pages -= min(nr_pages, zone->dirty_balance_reserve);
+
+	nr_pages += zone_page_state(zone, NR_INACTIVE_FILE);
+	nr_pages += zone_page_state(zone, NR_ACTIVE_FILE);
+
+	return nr_pages;
+}
+
 static unsigned long highmem_dirtyable_memory(unsigned long total)
 {
 #ifdef CONFIG_HIGHMEM
@@ -198,11 +218,9 @@ static unsigned long highmem_dirtyable_memory(unsigned long total)
 	unsigned long x = 0;
 
 	for_each_node_state(node, N_HIGH_MEMORY) {
-		struct zone *z =
-			&NODE_DATA(node)->node_zones[ZONE_HIGHMEM];
+		struct zone *z = &NODE_DATA(node)->node_zones[ZONE_HIGHMEM];
 
-		x += zone_page_state(z, NR_FREE_PAGES) +
-		     zone_reclaimable_pages(z) - z->dirty_balance_reserve;
+		x += zone_dirtyable_memory(z);
 	}
 	/*
 	 * Unreclaimable memory (kernel memory or anonymous memory
@@ -238,9 +256,12 @@ static unsigned long global_dirtyable_memory(void)
 {
 	unsigned long x;
 
-	x = global_page_state(NR_FREE_PAGES) + global_reclaimable_pages();
+	x = global_page_state(NR_FREE_PAGES);
 	x -= min(x, dirty_balance_reserve);
 
+	x += global_page_state(NR_INACTIVE_FILE);
+	x += global_page_state(NR_ACTIVE_FILE);
+
 	if (!vm_highmem_is_dirtyable)
 		x -= highmem_dirtyable_memory(x);
 
@@ -289,32 +310,6 @@ void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty)
 }
 
 /**
- * zone_dirtyable_memory - number of dirtyable pages in a zone
- * @zone: the zone
- *
- * Returns the zone's number of pages potentially available for dirty
- * page cache.  This is the base value for the per-zone dirty limits.
- */
-static unsigned long zone_dirtyable_memory(struct zone *zone)
-{
-	/*
-	 * The effective global number of dirtyable pages may exclude
-	 * highmem as a big-picture measure to keep the ratio between
-	 * dirty memory and lowmem reasonable.
-	 *
-	 * But this function is purely about the individual zone and a
-	 * highmem zone can hold its share of dirty pages, so we don't
-	 * care about vm_highmem_is_dirtyable here.
-	 */
-	unsigned long nr_pages = zone_page_state(zone, NR_FREE_PAGES) +
-		zone_reclaimable_pages(zone);
-
-	/* don't allow this to underflow */
-	nr_pages -= min(nr_pages, zone->dirty_balance_reserve);
-	return nr_pages;
-}
-
-/**
  * zone_dirty_limit - maximum number of dirty pages allowed in a zone
  * @zone: the zone
  *
diff --git a/mm/slub.c b/mm/slub.c
index 545a170ebf9f..89490d9d91e0 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -4299,7 +4299,13 @@ static ssize_t show_slab_objects(struct kmem_cache *s,
 
 			page = ACCESS_ONCE(c->partial);
 			if (page) {
-				x = page->pobjects;
+				node = page_to_nid(page);
+				if (flags & SO_TOTAL)
+					WARN_ON_ONCE(1);
+				else if (flags & SO_OBJECTS)
+					WARN_ON_ONCE(1);
+				else
+					x = page->pages;
 				total += x;
 				nodes[node] += x;
 			}
diff --git a/mm/vmscan.c b/mm/vmscan.c
index eea668d9cff6..05e6095159dc 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -147,7 +147,7 @@ static bool global_reclaim(struct scan_control *sc)
 }
 #endif
 
-unsigned long zone_reclaimable_pages(struct zone *zone)
+static unsigned long zone_reclaimable_pages(struct zone *zone)
 {
 	int nr;
 
@@ -3297,27 +3297,6 @@ void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx)
 	wake_up_interruptible(&pgdat->kswapd_wait);
 }
 
-/*
- * The reclaimable count would be mostly accurate.
- * The less reclaimable pages may be
- * - mlocked pages, which will be moved to unevictable list when encountered
- * - mapped pages, which may require several travels to be reclaimed
- * - dirty pages, which is not "instantly" reclaimable
- */
-unsigned long global_reclaimable_pages(void)
-{
-	int nr;
-
-	nr = global_page_state(NR_ACTIVE_FILE) +
-	     global_page_state(NR_INACTIVE_FILE);
-
-	if (get_nr_swap_pages() > 0)
-		nr += global_page_state(NR_ACTIVE_ANON) +
-		      global_page_state(NR_INACTIVE_ANON);
-
-	return nr;
-}
-
 #ifdef CONFIG_HIBERNATION
 /*
  * Try to free `nr_to_reclaim' of memory, system-wide, and return the number of
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 06e72d3cdf60..0b5149c5bc4a 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -74,36 +74,6 @@
 struct kmem_cache *skbuff_head_cache __read_mostly;
 static struct kmem_cache *skbuff_fclone_cache __read_mostly;
 
-static void sock_pipe_buf_release(struct pipe_inode_info *pipe,
-				  struct pipe_buffer *buf)
-{
-	put_page(buf->page);
-}
-
-static void sock_pipe_buf_get(struct pipe_inode_info *pipe,
-				struct pipe_buffer *buf)
-{
-	get_page(buf->page);
-}
-
-static int sock_pipe_buf_steal(struct pipe_inode_info *pipe,
-			       struct pipe_buffer *buf)
-{
-	return 1;
-}
-
-
-/* Pipe buffer operations for a socket. */
-static const struct pipe_buf_operations sock_pipe_buf_ops = {
-	.can_merge = 0,
-	.map = generic_pipe_buf_map,
-	.unmap = generic_pipe_buf_unmap,
-	.confirm = generic_pipe_buf_confirm,
-	.release = sock_pipe_buf_release,
-	.steal = sock_pipe_buf_steal,
-	.get = sock_pipe_buf_get,
-};
-
 /**
  *	skb_panic - private function for out-of-line support
  *	@skb:	buffer
@@ -1830,7 +1800,7 @@ int skb_splice_bits(struct sk_buff *skb, unsigned int offset,
 		.partial = partial,
 		.nr_pages_max = MAX_SKB_FRAGS,
 		.flags = flags,
-		.ops = &sock_pipe_buf_ops,
+		.ops = &nosteal_pipe_buf_ops,
 		.spd_release = sock_spd_release,
 	};
 	struct sk_buff *frag_iter;
diff --git a/net/sunrpc/auth_gss/gss_rpc_upcall.c b/net/sunrpc/auth_gss/gss_rpc_upcall.c
index 458f85e9b0ba..abbb7dcd1689 100644
--- a/net/sunrpc/auth_gss/gss_rpc_upcall.c
+++ b/net/sunrpc/auth_gss/gss_rpc_upcall.c
@@ -137,7 +137,6 @@ void init_gssp_clnt(struct sunrpc_net *sn)
 {
 	mutex_init(&sn->gssp_lock);
 	sn->gssp_clnt = NULL;
-	init_waitqueue_head(&sn->gssp_wq);
 }
 
 int set_gssp_clnt(struct net *net)
@@ -154,7 +153,6 @@ int set_gssp_clnt(struct net *net)
 		sn->gssp_clnt = clnt;
 	}
 	mutex_unlock(&sn->gssp_lock);
-	wake_up(&sn->gssp_wq);
 	return ret;
 }
 
diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c
index 008cdade5aae..1b94a9c8a242 100644
--- a/net/sunrpc/auth_gss/svcauth_gss.c
+++ b/net/sunrpc/auth_gss/svcauth_gss.c
@@ -1295,34 +1295,9 @@ static int set_gss_proxy(struct net *net, int type)
 	else
 		ret = -EBUSY;
 	spin_unlock(&use_gssp_lock);
-	wake_up(&sn->gssp_wq);
 	return ret;
 }
 
-static inline bool gssp_ready(struct sunrpc_net *sn)
-{
-	switch (sn->use_gss_proxy) {
-		case -1:
-			return false;
-		case 0:
-			return true;
-		case 1:
-			return sn->gssp_clnt;
-	}
-	WARN_ON_ONCE(1);
-	return false;
-}
-
-static int wait_for_gss_proxy(struct net *net, struct file *file)
-{
-	struct sunrpc_net *sn = net_generic(net, sunrpc_net_id);
-
-	if (file->f_flags & O_NONBLOCK && !gssp_ready(sn))
-		return -EAGAIN;
-	return wait_event_interruptible(sn->gssp_wq, gssp_ready(sn));
-}
-
-
 static ssize_t write_gssp(struct file *file, const char __user *buf,
 			 size_t count, loff_t *ppos)
 {
@@ -1355,16 +1330,12 @@ static ssize_t read_gssp(struct file *file, char __user *buf,
 			 size_t count, loff_t *ppos)
 {
 	struct net *net = PDE_DATA(file_inode(file));
+	struct sunrpc_net *sn = net_generic(net, sunrpc_net_id);
 	unsigned long p = *ppos;
 	char tbuf[10];
 	size_t len;
-	int ret;
-
-	ret = wait_for_gss_proxy(net, file);
-	if (ret)
-		return ret;
 
-	snprintf(tbuf, sizeof(tbuf), "%d\n", use_gss_proxy(net));
+	snprintf(tbuf, sizeof(tbuf), "%d\n", sn->use_gss_proxy);
 	len = strlen(tbuf);
 	if (p >= len)
 		return 0;
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index f09b7db2c492..e726e16cbc3c 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -1529,9 +1529,13 @@ call_refreshresult(struct rpc_task *task)
 	task->tk_action = call_refresh;
 	switch (status) {
 	case 0:
-		if (rpcauth_uptodatecred(task))
+		if (rpcauth_uptodatecred(task)) {
 			task->tk_action = call_allocate;
-		return;
+			return;
+		}
+		/* Use rate-limiting and a max number of retries if refresh
+		 * had status 0 but failed to update the cred.
+		 */
 	case -ETIMEDOUT:
 		rpc_delay(task, 3*HZ);
 	case -EAGAIN:
diff --git a/net/sunrpc/netns.h b/net/sunrpc/netns.h
index 779742cfc1ff..3a260e47fad2 100644
--- a/net/sunrpc/netns.h
+++ b/net/sunrpc/netns.h
@@ -26,7 +26,6 @@ struct sunrpc_net {
 	unsigned int rpcb_is_af_local : 1;
 
 	struct mutex gssp_lock;
-	wait_queue_head_t gssp_wq;
 	struct rpc_clnt *gssp_clnt;
 	int use_gss_proxy;
 	int pipe_version;
diff --git a/security/selinux/ss/policydb.c b/security/selinux/ss/policydb.c
index f6195ebde3c9..c8985db63880 100644
--- a/security/selinux/ss/policydb.c
+++ b/security/selinux/ss/policydb.c
@@ -1941,7 +1941,19 @@ static int filename_trans_read(struct policydb *p, void *fp)
 		if (rc)
 			goto out;
 
-		hashtab_insert(p->filename_trans, ft, otype);
+		rc = hashtab_insert(p->filename_trans, ft, otype);
+		if (rc) {
+			/*
+			 * Do not return -EEXIST to the caller, or the system
+			 * will not boot.
+			 */
+			if (rc != -EEXIST)
+				goto out;
+			/* But free memory to avoid memory leak. */
+			kfree(ft);
+			kfree(name);
+			kfree(otype);
+		}
 	}
 	hash_eval(p->filename_trans, "filenametr");
 	return 0;
diff --git a/tools/power/x86/turbostat/Makefile b/tools/power/x86/turbostat/Makefile
index f09641da40d4..d1b3a361e526 100644
--- a/tools/power/x86/turbostat/Makefile
+++ b/tools/power/x86/turbostat/Makefile
@@ -5,7 +5,7 @@ DESTDIR		:=
 
 turbostat : turbostat.c
 CFLAGS +=	-Wall
-CFLAGS +=	-I../../../../arch/x86/include/uapi/
+CFLAGS +=	-DMSRHEADER='"../../../../arch/x86/include/uapi/asm/msr-index.h"'
 
 %: %.c
 	@mkdir -p $(BUILD_OUTPUT)
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 9d77f13c2d25..bca2807bbb9f 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -20,7 +20,7 @@
  */
 
 #define _GNU_SOURCE
-#include <asm/msr.h>
+#include MSRHEADER
 #include <stdio.h>
 #include <unistd.h>
 #include <sys/types.h>
@@ -35,6 +35,7 @@
 #include <string.h>
 #include <ctype.h>
 #include <sched.h>
+#include <cpuid.h>
 
 char *proc_stat = "/proc/stat";
 unsigned int interval_sec = 5;	/* set with -i interval_sec */
@@ -1978,7 +1979,7 @@ void check_cpuid()
 
 	eax = ebx = ecx = edx = 0;
 
-	asm("cpuid" : "=a" (max_level), "=b" (ebx), "=c" (ecx), "=d" (edx) : "a" (0));
+	__get_cpuid(0, &max_level, &ebx, &ecx, &edx);
 
 	if (ebx == 0x756e6547 && edx == 0x49656e69 && ecx == 0x6c65746e)
 		genuine_intel = 1;
@@ -1987,7 +1988,7 @@ void check_cpuid()
 		fprintf(stderr, "CPUID(0): %.4s%.4s%.4s ",
 			(char *)&ebx, (char *)&edx, (char *)&ecx);
 
-	asm("cpuid" : "=a" (fms), "=c" (ecx), "=d" (edx) : "a" (1) : "ebx");
+	__get_cpuid(1, &fms, &ebx, &ecx, &edx);
 	family = (fms >> 8) & 0xf;
 	model = (fms >> 4) & 0xf;
 	stepping = fms & 0xf;
@@ -2009,7 +2010,7 @@ void check_cpuid()
 	 * This check is valid for both Intel and AMD.
 	 */
 	ebx = ecx = edx = 0;
-	asm("cpuid" : "=a" (max_level), "=b" (ebx), "=c" (ecx), "=d" (edx) : "a" (0x80000000));
+	__get_cpuid(0x80000000, &max_level, &ebx, &ecx, &edx);
 
 	if (max_level < 0x80000007) {
 		fprintf(stderr, "CPUID: no invariant TSC (max_level 0x%x)\n", max_level);
@@ -2020,7 +2021,7 @@ void check_cpuid()
 	 * Non-Stop TSC is advertised by CPUID.EAX=0x80000007: EDX.bit8
 	 * this check is valid for both Intel and AMD
 	 */
-	asm("cpuid" : "=a" (eax), "=b" (ebx), "=c" (ecx), "=d" (edx) : "a" (0x80000007));
+	__get_cpuid(0x80000007, &eax, &ebx, &ecx, &edx);
 	has_invariant_tsc = edx & (1 << 8);
 
 	if (!has_invariant_tsc) {
@@ -2033,7 +2034,7 @@ void check_cpuid()
 	 * this check is valid for both Intel and AMD
 	 */
 
-	asm("cpuid" : "=a" (eax), "=b" (ebx), "=c" (ecx), "=d" (edx) : "a" (0x6));
+	__get_cpuid(0x6, &eax, &ebx, &ecx, &edx);
 	has_aperf = ecx & (1 << 0);
 	do_dts = eax & (1 << 0);
 	do_ptm = eax & (1 << 6);
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/