Merge tag 'regulator-fix-v4.0-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/broonie/regulator

Pull regulator fixes from Mark Brown:
 "The two main fixes here from Javier and Doug both fix issues seen on
  the Exynos-based ARM Chromebooks with reference counting of GPIO
  regulators over system suspend.  The GPIO enable code didn't properly
  take account of this case (a full analysis is in Doug's commit log).

  This is fixed by both fixing the reference counting directly and by
  making the resume code skip enables it doesn't need to do.  We could
  skip the change in the resume code but it's a very simple change and
  adds extra robustness against problems in other drivers"

* tag 'regulator-fix-v4.0-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/broonie/regulator:
  regulator: tps65910: Add missing #include <linux/of.h>
  regulator: core: Fix enable GPIO reference counting
  regulator: Only enable disabled regulators on resume
diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h
index bf0fe99..4cf48c3 100644
--- a/arch/arm/include/asm/kvm_mmu.h
+++ b/arch/arm/include/asm/kvm_mmu.h
@@ -149,31 +149,30 @@
 	(__boundary - 1 < (end) - 1)? __boundary: (end);		\
 })
 
+#define kvm_pgd_index(addr)			pgd_index(addr)
+
 static inline bool kvm_page_empty(void *ptr)
 {
 	struct page *ptr_page = virt_to_page(ptr);
 	return page_count(ptr_page) == 1;
 }
 
-
 #define kvm_pte_table_empty(kvm, ptep) kvm_page_empty(ptep)
 #define kvm_pmd_table_empty(kvm, pmdp) kvm_page_empty(pmdp)
 #define kvm_pud_table_empty(kvm, pudp) (0)
 
 #define KVM_PREALLOC_LEVEL	0
 
-static inline int kvm_prealloc_hwpgd(struct kvm *kvm, pgd_t *pgd)
-{
-	return 0;
-}
-
-static inline void kvm_free_hwpgd(struct kvm *kvm) { }
-
 static inline void *kvm_get_hwpgd(struct kvm *kvm)
 {
 	return kvm->arch.pgd;
 }
 
+static inline unsigned int kvm_get_hwpgd_size(void)
+{
+	return PTRS_PER_S2_PGD * sizeof(pgd_t);
+}
+
 struct kvm;
 
 #define kvm_flush_dcache_to_poc(a,l)	__cpuc_flush_dcache_area((a), (l))
diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c
index 3e6859b..5656d79 100644
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -290,7 +290,7 @@
 	phys_addr_t addr = start, end = start + size;
 	phys_addr_t next;
 
-	pgd = pgdp + pgd_index(addr);
+	pgd = pgdp + kvm_pgd_index(addr);
 	do {
 		next = kvm_pgd_addr_end(addr, end);
 		if (!pgd_none(*pgd))
@@ -355,7 +355,7 @@
 	phys_addr_t next;
 	pgd_t *pgd;
 
-	pgd = kvm->arch.pgd + pgd_index(addr);
+	pgd = kvm->arch.pgd + kvm_pgd_index(addr);
 	do {
 		next = kvm_pgd_addr_end(addr, end);
 		stage2_flush_puds(kvm, pgd, addr, next);
@@ -632,6 +632,20 @@
 				     __phys_to_pfn(phys_addr), PAGE_HYP_DEVICE);
 }
 
+/* Free the HW pgd, one page at a time */
+static void kvm_free_hwpgd(void *hwpgd)
+{
+	free_pages_exact(hwpgd, kvm_get_hwpgd_size());
+}
+
+/* Allocate the HW PGD, making sure that each page gets its own refcount */
+static void *kvm_alloc_hwpgd(void)
+{
+	unsigned int size = kvm_get_hwpgd_size();
+
+	return alloc_pages_exact(size, GFP_KERNEL | __GFP_ZERO);
+}
+
 /**
  * kvm_alloc_stage2_pgd - allocate level-1 table for stage-2 translation.
  * @kvm:	The KVM struct pointer for the VM.
@@ -645,15 +659,31 @@
  */
 int kvm_alloc_stage2_pgd(struct kvm *kvm)
 {
-	int ret;
 	pgd_t *pgd;
+	void *hwpgd;
 
 	if (kvm->arch.pgd != NULL) {
 		kvm_err("kvm_arch already initialized?\n");
 		return -EINVAL;
 	}
 
+	hwpgd = kvm_alloc_hwpgd();
+	if (!hwpgd)
+		return -ENOMEM;
+
+	/* When the kernel uses more levels of page tables than the
+	 * guest, we allocate a fake PGD and pre-populate it to point
+	 * to the next-level page table, which will be the real
+	 * initial page table pointed to by the VTTBR.
+	 *
+	 * When KVM_PREALLOC_LEVEL==2, we allocate a single page for
+	 * the PMD and the kernel will use folded pud.
+	 * When KVM_PREALLOC_LEVEL==1, we allocate 2 consecutive PUD
+	 * pages.
+	 */
 	if (KVM_PREALLOC_LEVEL > 0) {
+		int i;
+
 		/*
 		 * Allocate fake pgd for the page table manipulation macros to
 		 * work.  This is not used by the hardware and we have no
@@ -661,30 +691,32 @@
 		 */
 		pgd = (pgd_t *)kmalloc(PTRS_PER_S2_PGD * sizeof(pgd_t),
 				       GFP_KERNEL | __GFP_ZERO);
+
+		if (!pgd) {
+			kvm_free_hwpgd(hwpgd);
+			return -ENOMEM;
+		}
+
+		/* Plug the HW PGD into the fake one. */
+		for (i = 0; i < PTRS_PER_S2_PGD; i++) {
+			if (KVM_PREALLOC_LEVEL == 1)
+				pgd_populate(NULL, pgd + i,
+					     (pud_t *)hwpgd + i * PTRS_PER_PUD);
+			else if (KVM_PREALLOC_LEVEL == 2)
+				pud_populate(NULL, pud_offset(pgd, 0) + i,
+					     (pmd_t *)hwpgd + i * PTRS_PER_PMD);
+		}
 	} else {
 		/*
 		 * Allocate actual first-level Stage-2 page table used by the
 		 * hardware for Stage-2 page table walks.
 		 */
-		pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, S2_PGD_ORDER);
+		pgd = (pgd_t *)hwpgd;
 	}
 
-	if (!pgd)
-		return -ENOMEM;
-
-	ret = kvm_prealloc_hwpgd(kvm, pgd);
-	if (ret)
-		goto out_err;
-
 	kvm_clean_pgd(pgd);
 	kvm->arch.pgd = pgd;
 	return 0;
-out_err:
-	if (KVM_PREALLOC_LEVEL > 0)
-		kfree(pgd);
-	else
-		free_pages((unsigned long)pgd, S2_PGD_ORDER);
-	return ret;
 }
 
 /**
@@ -785,11 +817,10 @@
 		return;
 
 	unmap_stage2_range(kvm, 0, KVM_PHYS_SIZE);
-	kvm_free_hwpgd(kvm);
+	kvm_free_hwpgd(kvm_get_hwpgd(kvm));
 	if (KVM_PREALLOC_LEVEL > 0)
 		kfree(kvm->arch.pgd);
-	else
-		free_pages((unsigned long)kvm->arch.pgd, S2_PGD_ORDER);
+
 	kvm->arch.pgd = NULL;
 }
 
@@ -799,7 +830,7 @@
 	pgd_t *pgd;
 	pud_t *pud;
 
-	pgd = kvm->arch.pgd + pgd_index(addr);
+	pgd = kvm->arch.pgd + kvm_pgd_index(addr);
 	if (WARN_ON(pgd_none(*pgd))) {
 		if (!cache)
 			return NULL;
@@ -1089,7 +1120,7 @@
 	pgd_t *pgd;
 	phys_addr_t next;
 
-	pgd = kvm->arch.pgd + pgd_index(addr);
+	pgd = kvm->arch.pgd + kvm_pgd_index(addr);
 	do {
 		/*
 		 * Release kvm_mmu_lock periodically if the memory region is
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 94674eb..54bb4ba 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -129,6 +129,9 @@
  * 40 bits wide (T0SZ = 24).  Systems with a PARange smaller than 40 bits are
  * not known to exist and will break with this configuration.
  *
+ * VTCR_EL2.PS is extracted from ID_AA64MMFR0_EL1.PARange at boot time
+ * (see hyp-init.S).
+ *
  * Note that when using 4K pages, we concatenate two first level page tables
  * together.
  *
@@ -138,7 +141,6 @@
 #ifdef CONFIG_ARM64_64K_PAGES
 /*
  * Stage2 translation configuration:
- * 40bits output (PS = 2)
  * 40bits input  (T0SZ = 24)
  * 64kB pages (TG0 = 1)
  * 2 level page tables (SL = 1)
@@ -150,7 +152,6 @@
 #else
 /*
  * Stage2 translation configuration:
- * 40bits output (PS = 2)
  * 40bits input  (T0SZ = 24)
  * 4kB pages (TG0 = 0)
  * 3 level page tables (SL = 1)
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index 6458b53..bbfb600 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -158,6 +158,8 @@
 #define PTRS_PER_S2_PGD		(1 << PTRS_PER_S2_PGD_SHIFT)
 #define S2_PGD_ORDER		get_order(PTRS_PER_S2_PGD * sizeof(pgd_t))
 
+#define kvm_pgd_index(addr)	(((addr) >> PGDIR_SHIFT) & (PTRS_PER_S2_PGD - 1))
+
 /*
  * If we are concatenating first level stage-2 page tables, we would have less
  * than or equal to 16 pointers in the fake PGD, because that's what the
@@ -171,43 +173,6 @@
 #define KVM_PREALLOC_LEVEL	(0)
 #endif
 
-/**
- * kvm_prealloc_hwpgd - allocate inital table for VTTBR
- * @kvm:	The KVM struct pointer for the VM.
- * @pgd:	The kernel pseudo pgd
- *
- * When the kernel uses more levels of page tables than the guest, we allocate
- * a fake PGD and pre-populate it to point to the next-level page table, which
- * will be the real initial page table pointed to by the VTTBR.
- *
- * When KVM_PREALLOC_LEVEL==2, we allocate a single page for the PMD and
- * the kernel will use folded pud.  When KVM_PREALLOC_LEVEL==1, we
- * allocate 2 consecutive PUD pages.
- */
-static inline int kvm_prealloc_hwpgd(struct kvm *kvm, pgd_t *pgd)
-{
-	unsigned int i;
-	unsigned long hwpgd;
-
-	if (KVM_PREALLOC_LEVEL == 0)
-		return 0;
-
-	hwpgd = __get_free_pages(GFP_KERNEL | __GFP_ZERO, PTRS_PER_S2_PGD_SHIFT);
-	if (!hwpgd)
-		return -ENOMEM;
-
-	for (i = 0; i < PTRS_PER_S2_PGD; i++) {
-		if (KVM_PREALLOC_LEVEL == 1)
-			pgd_populate(NULL, pgd + i,
-				     (pud_t *)hwpgd + i * PTRS_PER_PUD);
-		else if (KVM_PREALLOC_LEVEL == 2)
-			pud_populate(NULL, pud_offset(pgd, 0) + i,
-				     (pmd_t *)hwpgd + i * PTRS_PER_PMD);
-	}
-
-	return 0;
-}
-
 static inline void *kvm_get_hwpgd(struct kvm *kvm)
 {
 	pgd_t *pgd = kvm->arch.pgd;
@@ -224,12 +189,11 @@
 	return pmd_offset(pud, 0);
 }
 
-static inline void kvm_free_hwpgd(struct kvm *kvm)
+static inline unsigned int kvm_get_hwpgd_size(void)
 {
-	if (KVM_PREALLOC_LEVEL > 0) {
-		unsigned long hwpgd = (unsigned long)kvm_get_hwpgd(kvm);
-		free_pages(hwpgd, PTRS_PER_S2_PGD_SHIFT);
-	}
+	if (KVM_PREALLOC_LEVEL > 0)
+		return PTRS_PER_S2_PGD * PAGE_SIZE;
+	return PTRS_PER_S2_PGD * sizeof(pgd_t);
 }
 
 static inline bool kvm_page_empty(void *ptr)
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index f6579cf..19e17bd 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -165,7 +165,6 @@
 	case KVM_CAP_ONE_REG:
 	case KVM_CAP_ENABLE_CAP:
 	case KVM_CAP_S390_CSS_SUPPORT:
-	case KVM_CAP_IRQFD:
 	case KVM_CAP_IOEVENTFD:
 	case KVM_CAP_DEVICE_CTRL:
 	case KVM_CAP_ENABLE_CAP_VM:
diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c
index cc31f7c..9541ba3 100644
--- a/arch/x86/kvm/i8259.c
+++ b/arch/x86/kvm/i8259.c
@@ -507,6 +507,7 @@
 		return -EOPNOTSUPP;
 
 	if (len != 1) {
+		memset(val, 0, len);
 		pr_pic_unimpl("non byte read\n");
 		return 0;
 	}
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index f7b20b4..10a481b 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2168,7 +2168,10 @@
 {
 	unsigned long *msr_bitmap;
 
-	if (irqchip_in_kernel(vcpu->kvm) && apic_x2apic_mode(vcpu->arch.apic)) {
+	if (is_guest_mode(vcpu))
+		msr_bitmap = vmx_msr_bitmap_nested;
+	else if (irqchip_in_kernel(vcpu->kvm) &&
+		apic_x2apic_mode(vcpu->arch.apic)) {
 		if (is_long_mode(vcpu))
 			msr_bitmap = vmx_msr_bitmap_longmode_x2apic;
 		else
@@ -9218,9 +9221,9 @@
 	}
 
 	if (cpu_has_vmx_msr_bitmap() &&
-	    exec_control & CPU_BASED_USE_MSR_BITMAPS &&
-	    nested_vmx_merge_msr_bitmap(vcpu, vmcs12)) {
-		vmcs_write64(MSR_BITMAP, __pa(vmx_msr_bitmap_nested));
+	    exec_control & CPU_BASED_USE_MSR_BITMAPS) {
+		nested_vmx_merge_msr_bitmap(vcpu, vmcs12);
+		/* MSR_BITMAP will be set by following vmx_set_efer. */
 	} else
 		exec_control &= ~CPU_BASED_USE_MSR_BITMAPS;
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index bd7a70b..32bf19e 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2744,7 +2744,6 @@
 	case KVM_CAP_USER_NMI:
 	case KVM_CAP_REINJECT_CONTROL:
 	case KVM_CAP_IRQ_INJECT_STATUS:
-	case KVM_CAP_IRQFD:
 	case KVM_CAP_IOEVENTFD:
 	case KVM_CAP_IOEVENTFD_NO_LENGTH:
 	case KVM_CAP_PIT2:
diff --git a/drivers/base/regmap/regcache-rbtree.c b/drivers/base/regmap/regcache-rbtree.c
index d453a2c..81751a4 100644
--- a/drivers/base/regmap/regcache-rbtree.c
+++ b/drivers/base/regmap/regcache-rbtree.c
@@ -307,7 +307,7 @@
 	if (pos == 0) {
 		memmove(blk + offset * map->cache_word_size,
 			blk, rbnode->blklen * map->cache_word_size);
-		bitmap_shift_right(present, present, offset, blklen);
+		bitmap_shift_left(present, present, offset, blklen);
 	}
 
 	/* update the rbnode block, its size and the base register */
diff --git a/drivers/base/regmap/regcache.c b/drivers/base/regmap/regcache.c
index f373c35..da84f54 100644
--- a/drivers/base/regmap/regcache.c
+++ b/drivers/base/regmap/regcache.c
@@ -608,7 +608,8 @@
 	for (i = start; i < end; i++) {
 		regtmp = block_base + (i * map->reg_stride);
 
-		if (!regcache_reg_present(cache_present, i))
+		if (!regcache_reg_present(cache_present, i) ||
+		    !regmap_writeable(map, regtmp))
 			continue;
 
 		val = regcache_get_val(map, block, i);
@@ -677,7 +678,8 @@
 	for (i = start; i < end; i++) {
 		regtmp = block_base + (i * map->reg_stride);
 
-		if (!regcache_reg_present(cache_present, i)) {
+		if (!regcache_reg_present(cache_present, i) ||
+		    !regmap_writeable(map, regtmp)) {
 			ret = regcache_sync_block_raw_flush(map, &data,
 							    base, regtmp);
 			if (ret != 0)
diff --git a/drivers/base/regmap/regmap-irq.c b/drivers/base/regmap/regmap-irq.c
index 6299a50..a6c3f75 100644
--- a/drivers/base/regmap/regmap-irq.c
+++ b/drivers/base/regmap/regmap-irq.c
@@ -499,7 +499,8 @@
 		goto err_alloc;
 	}
 
-	ret = request_threaded_irq(irq, NULL, regmap_irq_thread, irq_flags,
+	ret = request_threaded_irq(irq, NULL, regmap_irq_thread,
+				   irq_flags | IRQF_ONESHOT,
 				   chip->name, d);
 	if (ret != 0) {
 		dev_err(map->dev, "Failed to request IRQ %d for %s: %d\n",
diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c
index fae2dbb..72d7028 100644
--- a/drivers/char/virtio_console.c
+++ b/drivers/char/virtio_console.c
@@ -142,6 +142,7 @@
 	 * notification
 	 */
 	struct work_struct control_work;
+	struct work_struct config_work;
 
 	struct list_head ports;
 
@@ -1837,10 +1838,21 @@
 
 	portdev = vdev->priv;
 
+	if (!use_multiport(portdev))
+		schedule_work(&portdev->config_work);
+}
+
+static void config_work_handler(struct work_struct *work)
+{
+	struct ports_device *portdev;
+
+	portdev = container_of(work, struct ports_device, control_work);
 	if (!use_multiport(portdev)) {
+		struct virtio_device *vdev;
 		struct port *port;
 		u16 rows, cols;
 
+		vdev = portdev->vdev;
 		virtio_cread(vdev, struct virtio_console_config, cols, &cols);
 		virtio_cread(vdev, struct virtio_console_config, rows, &rows);
 
@@ -2040,12 +2052,14 @@
 
 	virtio_device_ready(portdev->vdev);
 
+	INIT_WORK(&portdev->config_work, &config_work_handler);
+	INIT_WORK(&portdev->control_work, &control_work_handler);
+
 	if (multiport) {
 		unsigned int nr_added_bufs;
 
 		spin_lock_init(&portdev->c_ivq_lock);
 		spin_lock_init(&portdev->c_ovq_lock);
-		INIT_WORK(&portdev->control_work, &control_work_handler);
 
 		nr_added_bufs = fill_queue(portdev->c_ivq,
 					   &portdev->c_ivq_lock);
@@ -2113,6 +2127,8 @@
 	/* Finish up work that's lined up */
 	if (use_multiport(portdev))
 		cancel_work_sync(&portdev->control_work);
+	else
+		cancel_work_sync(&portdev->config_work);
 
 	list_for_each_entry_safe(port, port2, &portdev->ports, list)
 		unplug_port(port);
@@ -2164,6 +2180,7 @@
 
 	virtqueue_disable_cb(portdev->c_ivq);
 	cancel_work_sync(&portdev->control_work);
+	cancel_work_sync(&portdev->config_work);
 	/*
 	 * Once more: if control_work_handler() was running, it would
 	 * enable the cb as the last step.
diff --git a/drivers/rpmsg/virtio_rpmsg_bus.c b/drivers/rpmsg/virtio_rpmsg_bus.c
index 92f6af6..73354ee 100644
--- a/drivers/rpmsg/virtio_rpmsg_bus.c
+++ b/drivers/rpmsg/virtio_rpmsg_bus.c
@@ -951,6 +951,7 @@
 	void *bufs_va;
 	int err = 0, i;
 	size_t total_buf_space;
+	bool notify;
 
 	vrp = kzalloc(sizeof(*vrp), GFP_KERNEL);
 	if (!vrp)
@@ -1030,8 +1031,22 @@
 		}
 	}
 
+	/*
+	 * Prepare to kick but don't notify yet - we can't do this before
+	 * device is ready.
+	 */
+	notify = virtqueue_kick_prepare(vrp->rvq);
+
+	/* From this point on, we can notify and get callbacks. */
+	virtio_device_ready(vdev);
+
 	/* tell the remote processor it can start sending messages */
-	virtqueue_kick(vrp->rvq);
+	/*
+	 * this might be concurrent with callbacks, but we are only
+	 * doing notify, not a full kick here, so that's ok.
+	 */
+	if (notify)
+		virtqueue_notify(vrp->rvq);
 
 	dev_info(&vdev->dev, "rpmsg host is online\n");
 
diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
index 0413157..6a356e3 100644
--- a/drivers/virtio/virtio_balloon.c
+++ b/drivers/virtio/virtio_balloon.c
@@ -29,6 +29,7 @@
 #include <linux/module.h>
 #include <linux/balloon_compaction.h>
 #include <linux/oom.h>
+#include <linux/wait.h>
 
 /*
  * Balloon device works in 4K page units.  So each page is pointed to by
@@ -334,17 +335,25 @@
 static int balloon(void *_vballoon)
 {
 	struct virtio_balloon *vb = _vballoon;
+	DEFINE_WAIT_FUNC(wait, woken_wake_function);
 
 	set_freezable();
 	while (!kthread_should_stop()) {
 		s64 diff;
 
 		try_to_freeze();
-		wait_event_interruptible(vb->config_change,
-					 (diff = towards_target(vb)) != 0
-					 || vb->need_stats_update
-					 || kthread_should_stop()
-					 || freezing(current));
+
+		add_wait_queue(&vb->config_change, &wait);
+		for (;;) {
+			if ((diff = towards_target(vb)) != 0 ||
+			    vb->need_stats_update ||
+			    kthread_should_stop() ||
+			    freezing(current))
+				break;
+			wait_woken(&wait, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
+		}
+		remove_wait_queue(&vb->config_change, &wait);
+
 		if (vb->need_stats_update)
 			stats_handle_request(vb);
 		if (diff > 0)
@@ -499,6 +508,8 @@
 	if (err < 0)
 		goto out_oom_notify;
 
+	virtio_device_ready(vdev);
+
 	vb->thread = kthread_run(balloon, vb, "vballoon");
 	if (IS_ERR(vb->thread)) {
 		err = PTR_ERR(vb->thread);
diff --git a/drivers/virtio/virtio_mmio.c b/drivers/virtio/virtio_mmio.c
index cad5698..6010d7e 100644
--- a/drivers/virtio/virtio_mmio.c
+++ b/drivers/virtio/virtio_mmio.c
@@ -156,22 +156,95 @@
 		   void *buf, unsigned len)
 {
 	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
-	u8 *ptr = buf;
-	int i;
+	void __iomem *base = vm_dev->base + VIRTIO_MMIO_CONFIG;
+	u8 b;
+	__le16 w;
+	__le32 l;
 
-	for (i = 0; i < len; i++)
-		ptr[i] = readb(vm_dev->base + VIRTIO_MMIO_CONFIG + offset + i);
+	if (vm_dev->version == 1) {
+		u8 *ptr = buf;
+		int i;
+
+		for (i = 0; i < len; i++)
+			ptr[i] = readb(base + offset + i);
+		return;
+	}
+
+	switch (len) {
+	case 1:
+		b = readb(base + offset);
+		memcpy(buf, &b, sizeof b);
+		break;
+	case 2:
+		w = cpu_to_le16(readw(base + offset));
+		memcpy(buf, &w, sizeof w);
+		break;
+	case 4:
+		l = cpu_to_le32(readl(base + offset));
+		memcpy(buf, &l, sizeof l);
+		break;
+	case 8:
+		l = cpu_to_le32(readl(base + offset));
+		memcpy(buf, &l, sizeof l);
+		l = cpu_to_le32(ioread32(base + offset + sizeof l));
+		memcpy(buf + sizeof l, &l, sizeof l);
+		break;
+	default:
+		BUG();
+	}
 }
 
 static void vm_set(struct virtio_device *vdev, unsigned offset,
 		   const void *buf, unsigned len)
 {
 	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
-	const u8 *ptr = buf;
-	int i;
+	void __iomem *base = vm_dev->base + VIRTIO_MMIO_CONFIG;
+	u8 b;
+	__le16 w;
+	__le32 l;
 
-	for (i = 0; i < len; i++)
-		writeb(ptr[i], vm_dev->base + VIRTIO_MMIO_CONFIG + offset + i);
+	if (vm_dev->version == 1) {
+		const u8 *ptr = buf;
+		int i;
+
+		for (i = 0; i < len; i++)
+			writeb(ptr[i], base + offset + i);
+
+		return;
+	}
+
+	switch (len) {
+	case 1:
+		memcpy(&b, buf, sizeof b);
+		writeb(b, base + offset);
+		break;
+	case 2:
+		memcpy(&w, buf, sizeof w);
+		writew(le16_to_cpu(w), base + offset);
+		break;
+	case 4:
+		memcpy(&l, buf, sizeof l);
+		writel(le32_to_cpu(l), base + offset);
+		break;
+	case 8:
+		memcpy(&l, buf, sizeof l);
+		writel(le32_to_cpu(l), base + offset);
+		memcpy(&l, buf + sizeof l, sizeof l);
+		writel(le32_to_cpu(l), base + offset + sizeof l);
+		break;
+	default:
+		BUG();
+	}
+}
+
+static u32 vm_generation(struct virtio_device *vdev)
+{
+	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
+
+	if (vm_dev->version == 1)
+		return 0;
+	else
+		return readl(vm_dev->base + VIRTIO_MMIO_CONFIG_GENERATION);
 }
 
 static u8 vm_get_status(struct virtio_device *vdev)
@@ -440,6 +513,7 @@
 static const struct virtio_config_ops virtio_mmio_config_ops = {
 	.get		= vm_get,
 	.set		= vm_set,
+	.generation	= vm_generation,
 	.get_status	= vm_get_status,
 	.set_status	= vm_set_status,
 	.reset		= vm_reset,
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 956b75d..6dee68d 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -1325,6 +1325,9 @@
 
 static int pagemap_open(struct inode *inode, struct file *file)
 {
+	/* do not disclose physical addresses: attack vector */
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
 	pr_warn_once("Bits 55-60 of /proc/PID/pagemap entries are about "
 			"to stop being page-shift some time soon. See the "
 			"linux/Documentation/vm/pagemap.txt for details.\n");
diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index 7c55dd5..66203b2 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -114,6 +114,7 @@
 	void	(*sync_lr_elrsr)(struct kvm_vcpu *, int, struct vgic_lr);
 	u64	(*get_elrsr)(const struct kvm_vcpu *vcpu);
 	u64	(*get_eisr)(const struct kvm_vcpu *vcpu);
+	void	(*clear_eisr)(struct kvm_vcpu *vcpu);
 	u32	(*get_interrupt_status)(const struct kvm_vcpu *vcpu);
 	void	(*enable_underflow)(struct kvm_vcpu *vcpu);
 	void	(*disable_underflow)(struct kvm_vcpu *vcpu);
diff --git a/include/uapi/linux/virtio_blk.h b/include/uapi/linux/virtio_blk.h
index 3c53eec..19c66fc 100644
--- a/include/uapi/linux/virtio_blk.h
+++ b/include/uapi/linux/virtio_blk.h
@@ -60,7 +60,7 @@
 	__u32 size_max;
 	/* The maximum number of segments (if VIRTIO_BLK_F_SEG_MAX) */
 	__u32 seg_max;
-	/* geometry the device (if VIRTIO_BLK_F_GEOMETRY) */
+	/* geometry of the device (if VIRTIO_BLK_F_GEOMETRY) */
 	struct virtio_blk_geometry {
 		__u16 cylinders;
 		__u8 heads;
@@ -119,7 +119,11 @@
 #define VIRTIO_BLK_T_BARRIER	0x80000000
 #endif /* !VIRTIO_BLK_NO_LEGACY */
 
-/* This is the first element of the read scatter-gather list. */
+/*
+ * This comes first in the read scatter-gather list.
+ * For legacy virtio, if VIRTIO_F_ANY_LAYOUT is not negotiated,
+ * this is the first element of the read scatter-gather list.
+ */
 struct virtio_blk_outhdr {
 	/* VIRTIO_BLK_T* */
 	__virtio32 type;
diff --git a/include/uapi/linux/virtio_scsi.h b/include/uapi/linux/virtio_scsi.h
index 42b9370..cc18ef8 100644
--- a/include/uapi/linux/virtio_scsi.h
+++ b/include/uapi/linux/virtio_scsi.h
@@ -29,8 +29,16 @@
 
 #include <linux/virtio_types.h>
 
-#define VIRTIO_SCSI_CDB_SIZE   32
-#define VIRTIO_SCSI_SENSE_SIZE 96
+/* Default values of the CDB and sense data size configuration fields */
+#define VIRTIO_SCSI_CDB_DEFAULT_SIZE   32
+#define VIRTIO_SCSI_SENSE_DEFAULT_SIZE 96
+
+#ifndef VIRTIO_SCSI_CDB_SIZE
+#define VIRTIO_SCSI_CDB_SIZE VIRTIO_SCSI_CDB_DEFAULT_SIZE
+#endif
+#ifndef VIRTIO_SCSI_SENSE_SIZE
+#define VIRTIO_SCSI_SENSE_SIZE VIRTIO_SCSI_SENSE_DEFAULT_SIZE
+#endif
 
 /* SCSI command request, followed by data-out */
 struct virtio_scsi_cmd_req {
diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c
index d8e376a..36a1a73 100644
--- a/net/9p/trans_virtio.c
+++ b/net/9p/trans_virtio.c
@@ -658,14 +658,30 @@
 static void p9_virtio_remove(struct virtio_device *vdev)
 {
 	struct virtio_chan *chan = vdev->priv;
-
-	if (chan->inuse)
-		p9_virtio_close(chan->client);
-	vdev->config->del_vqs(vdev);
+	unsigned long warning_time;
 
 	mutex_lock(&virtio_9p_lock);
+
+	/* Remove self from list so we don't get new users. */
 	list_del(&chan->chan_list);
+	warning_time = jiffies;
+
+	/* Wait for existing users to close. */
+	while (chan->inuse) {
+		mutex_unlock(&virtio_9p_lock);
+		msleep(250);
+		if (time_after(jiffies, warning_time + 10 * HZ)) {
+			dev_emerg(&vdev->dev,
+				  "p9_virtio_remove: waiting for device in use.\n");
+			warning_time = jiffies;
+		}
+		mutex_lock(&virtio_9p_lock);
+	}
+
 	mutex_unlock(&virtio_9p_lock);
+
+	vdev->config->del_vqs(vdev);
+
 	sysfs_remove_file(&(vdev->dev.kobj), &dev_attr_mount_tag.attr);
 	kobject_uevent(&(vdev->dev.kobj), KOBJ_CHANGE);
 	kfree(chan->tag);
diff --git a/virt/kvm/arm/vgic-v2.c b/virt/kvm/arm/vgic-v2.c
index a0a7b5d..f9b9c7c 100644
--- a/virt/kvm/arm/vgic-v2.c
+++ b/virt/kvm/arm/vgic-v2.c
@@ -72,6 +72,8 @@
 {
 	if (!(lr_desc.state & LR_STATE_MASK))
 		vcpu->arch.vgic_cpu.vgic_v2.vgic_elrsr |= (1ULL << lr);
+	else
+		vcpu->arch.vgic_cpu.vgic_v2.vgic_elrsr &= ~(1ULL << lr);
 }
 
 static u64 vgic_v2_get_elrsr(const struct kvm_vcpu *vcpu)
@@ -84,6 +86,11 @@
 	return vcpu->arch.vgic_cpu.vgic_v2.vgic_eisr;
 }
 
+static void vgic_v2_clear_eisr(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.vgic_cpu.vgic_v2.vgic_eisr = 0;
+}
+
 static u32 vgic_v2_get_interrupt_status(const struct kvm_vcpu *vcpu)
 {
 	u32 misr = vcpu->arch.vgic_cpu.vgic_v2.vgic_misr;
@@ -148,6 +155,7 @@
 	.sync_lr_elrsr		= vgic_v2_sync_lr_elrsr,
 	.get_elrsr		= vgic_v2_get_elrsr,
 	.get_eisr		= vgic_v2_get_eisr,
+	.clear_eisr		= vgic_v2_clear_eisr,
 	.get_interrupt_status	= vgic_v2_get_interrupt_status,
 	.enable_underflow	= vgic_v2_enable_underflow,
 	.disable_underflow	= vgic_v2_disable_underflow,
diff --git a/virt/kvm/arm/vgic-v3.c b/virt/kvm/arm/vgic-v3.c
index 3a62d8a..dff0602 100644
--- a/virt/kvm/arm/vgic-v3.c
+++ b/virt/kvm/arm/vgic-v3.c
@@ -104,6 +104,8 @@
 {
 	if (!(lr_desc.state & LR_STATE_MASK))
 		vcpu->arch.vgic_cpu.vgic_v3.vgic_elrsr |= (1U << lr);
+	else
+		vcpu->arch.vgic_cpu.vgic_v3.vgic_elrsr &= ~(1U << lr);
 }
 
 static u64 vgic_v3_get_elrsr(const struct kvm_vcpu *vcpu)
@@ -116,6 +118,11 @@
 	return vcpu->arch.vgic_cpu.vgic_v3.vgic_eisr;
 }
 
+static void vgic_v3_clear_eisr(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.vgic_cpu.vgic_v3.vgic_eisr = 0;
+}
+
 static u32 vgic_v3_get_interrupt_status(const struct kvm_vcpu *vcpu)
 {
 	u32 misr = vcpu->arch.vgic_cpu.vgic_v3.vgic_misr;
@@ -192,6 +199,7 @@
 	.sync_lr_elrsr		= vgic_v3_sync_lr_elrsr,
 	.get_elrsr		= vgic_v3_get_elrsr,
 	.get_eisr		= vgic_v3_get_eisr,
+	.clear_eisr		= vgic_v3_clear_eisr,
 	.get_interrupt_status	= vgic_v3_get_interrupt_status,
 	.enable_underflow	= vgic_v3_enable_underflow,
 	.disable_underflow	= vgic_v3_disable_underflow,
diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c
index 0cc6ab6..c9f60f5 100644
--- a/virt/kvm/arm/vgic.c
+++ b/virt/kvm/arm/vgic.c
@@ -883,6 +883,11 @@
 	return vgic_ops->get_eisr(vcpu);
 }
 
+static inline void vgic_clear_eisr(struct kvm_vcpu *vcpu)
+{
+	vgic_ops->clear_eisr(vcpu);
+}
+
 static inline u32 vgic_get_interrupt_status(struct kvm_vcpu *vcpu)
 {
 	return vgic_ops->get_interrupt_status(vcpu);
@@ -922,6 +927,7 @@
 	vgic_set_lr(vcpu, lr_nr, vlr);
 	clear_bit(lr_nr, vgic_cpu->lr_used);
 	vgic_cpu->vgic_irq_lr_map[irq] = LR_EMPTY;
+	vgic_sync_lr_elrsr(vcpu, lr_nr, vlr);
 }
 
 /*
@@ -978,6 +984,7 @@
 			BUG_ON(!test_bit(lr, vgic_cpu->lr_used));
 			vlr.state |= LR_STATE_PENDING;
 			vgic_set_lr(vcpu, lr, vlr);
+			vgic_sync_lr_elrsr(vcpu, lr, vlr);
 			return true;
 		}
 	}
@@ -999,6 +1006,7 @@
 		vlr.state |= LR_EOI_INT;
 
 	vgic_set_lr(vcpu, lr, vlr);
+	vgic_sync_lr_elrsr(vcpu, lr, vlr);
 
 	return true;
 }
@@ -1136,6 +1144,14 @@
 	if (status & INT_STATUS_UNDERFLOW)
 		vgic_disable_underflow(vcpu);
 
+	/*
+	 * In the next iterations of the vcpu loop, if we sync the vgic state
+	 * after flushing it, but before entering the guest (this happens for
+	 * pending signals and vmid rollovers), then make sure we don't pick
+	 * up any old maintenance interrupts here.
+	 */
+	vgic_clear_eisr(vcpu);
+
 	return level_pending;
 }
 
@@ -1583,8 +1599,10 @@
 	 * emulation. So check this here again. KVM_CREATE_DEVICE does
 	 * the proper checks already.
 	 */
-	if (type == KVM_DEV_TYPE_ARM_VGIC_V2 && !vgic->can_emulate_gicv2)
-		return -ENODEV;
+	if (type == KVM_DEV_TYPE_ARM_VGIC_V2 && !vgic->can_emulate_gicv2) {
+		ret = -ENODEV;
+		goto out;
+	}
 
 	/*
 	 * Any time a vcpu is run, vcpu_load is called which tries to grab the
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index a109370..a2214d9 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -2492,6 +2492,7 @@
 	case KVM_CAP_SIGNAL_MSI:
 #endif
 #ifdef CONFIG_HAVE_KVM_IRQFD
+	case KVM_CAP_IRQFD:
 	case KVM_CAP_IRQFD_RESAMPLE:
 #endif
 	case KVM_CAP_CHECK_EXTENSION_VM: