24 files changed, 292 insertions, 108 deletions

diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h
index bf0fe99e8ca9..4cf48c3aca13 100644
--- a/arch/arm/include/asm/kvm_mmu.h
+++ b/arch/arm/include/asm/kvm_mmu.h
@@ -149,29 +149,28 @@ static inline bool kvm_s2pmd_readonly(pmd_t *pmd)
 	(__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)
+static inline void *kvm_get_hwpgd(struct kvm *kvm)
 {
-	return 0;
+	return kvm->arch.pgd;
 }
 
-static inline void kvm_free_hwpgd(struct kvm *kvm) { }
-
-static inline void *kvm_get_hwpgd(struct kvm *kvm)
+static inline unsigned int kvm_get_hwpgd_size(void)
 {
-	return kvm->arch.pgd;
+	return PTRS_PER_S2_PGD * sizeof(pgd_t);
 }
 
 struct kvm;
diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c
index 3e6859bc3e11..5656d79c5a44 100644
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -290,7 +290,7 @@ static void unmap_range(struct kvm *kvm, pgd_t *pgdp,
 	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 @@ static void stage2_flush_memslot(struct kvm *kvm,
 	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 @@ int create_hyp_io_mappings(void *from, void *to, phys_addr_t phys_addr)
 				     __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 create_hyp_io_mappings(void *from, void *to, phys_addr_t phys_addr)
  */
 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 @@ int kvm_alloc_stage2_pgd(struct kvm *kvm)
 		 */
 		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 @@ void kvm_free_stage2_pgd(struct kvm *kvm)
 		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 @@ static pud_t *stage2_get_pud(struct kvm *kvm, struct kvm_mmu_memory_cache *cache
 	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 @@ static void stage2_wp_range(struct kvm *kvm, phys_addr_t addr, phys_addr_t end)
 	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 94674eb7e7bb..54bb4ba97441 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 6458b5373142..bbfb600fa822 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -158,6 +158,8 @@ static inline bool kvm_s2pmd_readonly(pmd_t *pmd)
 #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 @@ static inline bool kvm_s2pmd_readonly(pmd_t *pmd)
 #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 @@ static inline void *kvm_get_hwpgd(struct kvm *kvm)
 	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 f6579cfde2df..19e17bd7aec0 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -165,7 +165,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	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 cc31f7c06d3d..9541ba34126b 100644
--- a/arch/x86/kvm/i8259.c
+++ b/arch/x86/kvm/i8259.c
@@ -507,6 +507,7 @@ static int picdev_read(struct kvm_pic *s,
 		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 f7b20b417a3a..10a481b7674d 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2168,7 +2168,10 @@ static void vmx_set_msr_bitmap(struct kvm_vcpu *vcpu)
 {
 	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 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 	}
 
 	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 bd7a70be41b3..32bf19ef3115 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2744,7 +2744,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	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 d453a2c98ad0..81751a49d8bf 100644
--- a/drivers/base/regmap/regcache-rbtree.c
+++ b/drivers/base/regmap/regcache-rbtree.c
@@ -307,7 +307,7 @@ static int regcache_rbtree_insert_to_block(struct regmap *map,
 	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 f373c35f9e1d..da84f544c544 100644
--- a/drivers/base/regmap/regcache.c
+++ b/drivers/base/regmap/regcache.c
@@ -608,7 +608,8 @@ static int regcache_sync_block_single(struct regmap *map, void *block,
 	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 @@ static int regcache_sync_block_raw(struct regmap *map, void *block,
 	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 6299a50a5960..a6c3f75b4b01 100644
--- a/drivers/base/regmap/regmap-irq.c
+++ b/drivers/base/regmap/regmap-irq.c
@@ -499,7 +499,8 @@ int regmap_add_irq_chip(struct regmap *map, int irq, int irq_flags,
 		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 fae2dbbf5745..72d7028f779b 100644
--- a/drivers/char/virtio_console.c
+++ b/drivers/char/virtio_console.c
@@ -142,6 +142,7 @@ struct ports_device {
 	 * notification
 	 */
 	struct work_struct control_work;
+	struct work_struct config_work;
 
 	struct list_head ports;
 
@@ -1837,10 +1838,21 @@ static void config_intr(struct virtio_device *vdev)
 
 	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 @@ static int virtcons_probe(struct virtio_device *vdev)
 
 	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 @@ static void virtcons_remove(struct virtio_device *vdev)
 	/* 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 @@ static int virtcons_freeze(struct virtio_device *vdev)
 
 	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 92f6af6da699..73354ee27877 100644
--- a/drivers/rpmsg/virtio_rpmsg_bus.c
+++ b/drivers/rpmsg/virtio_rpmsg_bus.c
@@ -951,6 +951,7 @@ static int rpmsg_probe(struct virtio_device *vdev)
 	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 @@ static int rpmsg_probe(struct virtio_device *vdev)
 		}
 	}
 
+	/*
+	 * 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 0413157f3b49..6a356e344f82 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 virtballoon_oom_notify(struct notifier_block *self,
 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 @@ static int virtballoon_probe(struct virtio_device *vdev)
 	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 cad569890908..6010d7ec0a0f 100644
--- a/drivers/virtio/virtio_mmio.c
+++ b/drivers/virtio/virtio_mmio.c
@@ -156,22 +156,95 @@ static void vm_get(struct virtio_device *vdev, unsigned offset,
 		   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 char *vm_bus_name(struct virtio_device *vdev)
 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 956b75d61809..6dee68d013ff 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -1325,6 +1325,9 @@ out:
 
 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 7c55dd5dd2c9..66203b268984 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -114,6 +114,7 @@ struct vgic_ops {
 	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 3c53eec4ae22..19c66fcbab8a 100644
--- a/include/uapi/linux/virtio_blk.h
+++ b/include/uapi/linux/virtio_blk.h
@@ -60,7 +60,7 @@ struct virtio_blk_config {
 	__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 @@ struct virtio_blk_config {
 #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 42b9370771b0..cc18ef8825c0 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 d8e376a5f0f1..36a1a739ad68 100644
--- a/net/9p/trans_virtio.c
+++ b/net/9p/trans_virtio.c
@@ -658,14 +658,30 @@ p9_virtio_create(struct p9_client *client, const char *devname, char *args)
 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 a0a7b5d1a070..f9b9c7c51372 100644
--- a/virt/kvm/arm/vgic-v2.c
+++ b/virt/kvm/arm/vgic-v2.c
@@ -72,6 +72,8 @@ static void vgic_v2_sync_lr_elrsr(struct kvm_vcpu *vcpu, int lr,
 {
 	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 @@ static u64 vgic_v2_get_eisr(const struct kvm_vcpu *vcpu)
 	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 @@ static const struct vgic_ops vgic_v2_ops = {
 	.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 3a62d8a9a2c6..dff06021e748 100644
--- a/virt/kvm/arm/vgic-v3.c
+++ b/virt/kvm/arm/vgic-v3.c
@@ -104,6 +104,8 @@ static void vgic_v3_sync_lr_elrsr(struct kvm_vcpu *vcpu, int lr,
 {
 	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 @@ static u64 vgic_v3_get_eisr(const struct kvm_vcpu *vcpu)
 	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 @@ static const struct vgic_ops vgic_v3_ops = {
 	.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 0cc6ab6005a0..c9f60f524588 100644
--- a/virt/kvm/arm/vgic.c
+++ b/virt/kvm/arm/vgic.c
@@ -883,6 +883,11 @@ static inline u64 vgic_get_eisr(struct kvm_vcpu *vcpu)
 	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 @@ static void vgic_retire_lr(int lr_nr, int irq, struct kvm_vcpu *vcpu)
 	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 @@ bool vgic_queue_irq(struct kvm_vcpu *vcpu, u8 sgi_source_id, int irq)
 			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 @@ bool vgic_queue_irq(struct kvm_vcpu *vcpu, u8 sgi_source_id, int irq)
 		vlr.state |= LR_EOI_INT;
 
 	vgic_set_lr(vcpu, lr, vlr);
+	vgic_sync_lr_elrsr(vcpu, lr, vlr);
 
 	return true;
 }
@@ -1136,6 +1144,14 @@ static bool vgic_process_maintenance(struct kvm_vcpu *vcpu)
 	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 @@ int kvm_vgic_create(struct kvm *kvm, u32 type)
 	 * 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 a1093700f3a4..a2214d9609bd 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -2492,6 +2492,7 @@ static long kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg)
 	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: