Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM updates from Paolo Bonzini:
 "ARM:
   - some cleanups
   - direct physical timer assignment
   - cache sanitization for 32-bit guests

  s390:
   - interrupt cleanup
   - introduction of the Guest Information Block
   - preparation for processor subfunctions in cpu models

  PPC:
   - bug fixes and improvements, especially related to machine checks
     and protection keys

  x86:
   - many, many cleanups, including removing a bunch of MMU code for
     unnecessary optimizations
   - AVIC fixes

  Generic:
   - memcg accounting"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (147 commits)
  kvm: vmx: fix formatting of a comment
  KVM: doc: Document the life cycle of a VM and its resources
  MAINTAINERS: Add KVM selftests to existing KVM entry
  Revert "KVM/MMU: Flush tlb directly in the kvm_zap_gfn_range()"
  KVM: PPC: Book3S: Add count cache flush parameters to kvmppc_get_cpu_char()
  KVM: PPC: Fix compilation when KVM is not enabled
  KVM: Minor cleanups for kvm_main.c
  KVM: s390: add debug logging for cpu model subfunctions
  KVM: s390: implement subfunction processor calls
  arm64: KVM: Fix architecturally invalid reset value for FPEXC32_EL2
  KVM: arm/arm64: Remove unused timer variable
  KVM: PPC: Book3S: Improve KVM reference counting
  KVM: PPC: Book3S HV: Fix build failure without IOMMU support
  Revert "KVM: Eliminate extra function calls in kvm_get_dirty_log_protect()"
  x86: kvmguest: use TSC clocksource if invariant TSC is exposed
  KVM: Never start grow vCPU halt_poll_ns from value below halt_poll_ns_grow_start
  KVM: Expose the initial start value in grow_halt_poll_ns() as a module parameter
  KVM: grow_halt_poll_ns() should never shrink vCPU halt_poll_ns
  KVM: x86/mmu: Consolidate kvm_mmu_zap_all() and kvm_mmu_zap_mmio_sptes()
  KVM: x86/mmu: WARN if zapping a MMIO spte results in zapping children
  ...

1 files changed, 54 insertions, 49 deletions

diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index d237d3350a99..f25aa98a94df 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -81,6 +81,11 @@ unsigned int halt_poll_ns_grow = 2;
 module_param(halt_poll_ns_grow, uint, 0644);
 EXPORT_SYMBOL_GPL(halt_poll_ns_grow);
 
+/* The start value to grow halt_poll_ns from */
+unsigned int halt_poll_ns_grow_start = 10000; /* 10us */
+module_param(halt_poll_ns_grow_start, uint, 0644);
+EXPORT_SYMBOL_GPL(halt_poll_ns_grow_start);
+
 /* Default resets per-vcpu halt_poll_ns . */
 unsigned int halt_poll_ns_shrink;
 module_param(halt_poll_ns_shrink, uint, 0644);
@@ -525,7 +530,7 @@ static struct kvm_memslots *kvm_alloc_memslots(void)
 	int i;
 	struct kvm_memslots *slots;
 
-	slots = kvzalloc(sizeof(struct kvm_memslots), GFP_KERNEL);
+	slots = kvzalloc(sizeof(struct kvm_memslots), GFP_KERNEL_ACCOUNT);
 	if (!slots)
 		return NULL;
 
@@ -601,12 +606,12 @@ static int kvm_create_vm_debugfs(struct kvm *kvm, int fd)
 
 	kvm->debugfs_stat_data = kcalloc(kvm_debugfs_num_entries,
 					 sizeof(*kvm->debugfs_stat_data),
-					 GFP_KERNEL);
+					 GFP_KERNEL_ACCOUNT);
 	if (!kvm->debugfs_stat_data)
 		return -ENOMEM;
 
 	for (p = debugfs_entries; p->name; p++) {
-		stat_data = kzalloc(sizeof(*stat_data), GFP_KERNEL);
+		stat_data = kzalloc(sizeof(*stat_data), GFP_KERNEL_ACCOUNT);
 		if (!stat_data)
 			return -ENOMEM;
 
@@ -656,12 +661,8 @@ static struct kvm *kvm_create_vm(unsigned long type)
 		struct kvm_memslots *slots = kvm_alloc_memslots();
 		if (!slots)
 			goto out_err_no_srcu;
-		/*
-		 * Generations must be different for each address space.
-		 * Init kvm generation close to the maximum to easily test the
-		 * code of handling generation number wrap-around.
-		 */
-		slots->generation = i * 2 - 150;
+		/* Generations must be different for each address space. */
+		slots->generation = i;
 		rcu_assign_pointer(kvm->memslots[i], slots);
 	}
 
@@ -671,7 +672,7 @@ static struct kvm *kvm_create_vm(unsigned long type)
 		goto out_err_no_irq_srcu;
 	for (i = 0; i < KVM_NR_BUSES; i++) {
 		rcu_assign_pointer(kvm->buses[i],
-			kzalloc(sizeof(struct kvm_io_bus), GFP_KERNEL));
+			kzalloc(sizeof(struct kvm_io_bus), GFP_KERNEL_ACCOUNT));
 		if (!kvm->buses[i])
 			goto out_err;
 	}
@@ -789,7 +790,7 @@ static int kvm_create_dirty_bitmap(struct kvm_memory_slot *memslot)
 {
 	unsigned long dirty_bytes = 2 * kvm_dirty_bitmap_bytes(memslot);
 
-	memslot->dirty_bitmap = kvzalloc(dirty_bytes, GFP_KERNEL);
+	memslot->dirty_bitmap = kvzalloc(dirty_bytes, GFP_KERNEL_ACCOUNT);
 	if (!memslot->dirty_bitmap)
 		return -ENOMEM;
 
@@ -874,31 +875,34 @@ static struct kvm_memslots *install_new_memslots(struct kvm *kvm,
 		int as_id, struct kvm_memslots *slots)
 {
 	struct kvm_memslots *old_memslots = __kvm_memslots(kvm, as_id);
+	u64 gen = old_memslots->generation;
 
-	/*
-	 * Set the low bit in the generation, which disables SPTE caching
-	 * until the end of synchronize_srcu_expedited.
-	 */
-	WARN_ON(old_memslots->generation & 1);
-	slots->generation = old_memslots->generation + 1;
+	WARN_ON(gen & KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS);
+	slots->generation = gen | KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS;
 
 	rcu_assign_pointer(kvm->memslots[as_id], slots);
 	synchronize_srcu_expedited(&kvm->srcu);
 
 	/*
-	 * Increment the new memslot generation a second time. This prevents
-	 * vm exits that race with memslot updates from caching a memslot
-	 * generation that will (potentially) be valid forever.
-	 *
+	 * Increment the new memslot generation a second time, dropping the
+	 * update in-progress flag and incrementing then generation based on
+	 * the number of address spaces.  This provides a unique and easily
+	 * identifiable generation number while the memslots are in flux.
+	 */
+	gen = slots->generation & ~KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS;
+
+	/*
 	 * Generations must be unique even across address spaces.  We do not need
 	 * a global counter for that, instead the generation space is evenly split
 	 * across address spaces.  For example, with two address spaces, address
-	 * space 0 will use generations 0, 4, 8, ... while * address space 1 will
-	 * use generations 2, 6, 10, 14, ...
+	 * space 0 will use generations 0, 2, 4, ... while address space 1 will
+	 * use generations 1, 3, 5, ...
 	 */
-	slots->generation += KVM_ADDRESS_SPACE_NUM * 2 - 1;
+	gen += KVM_ADDRESS_SPACE_NUM;
+
+	kvm_arch_memslots_updated(kvm, gen);
 
-	kvm_arch_memslots_updated(kvm, slots);
+	slots->generation = gen;
 
 	return old_memslots;
 }
@@ -1018,7 +1022,7 @@ int __kvm_set_memory_region(struct kvm *kvm,
 			goto out_free;
 	}
 
-	slots = kvzalloc(sizeof(struct kvm_memslots), GFP_KERNEL);
+	slots = kvzalloc(sizeof(struct kvm_memslots), GFP_KERNEL_ACCOUNT);
 	if (!slots)
 		goto out_free;
 	memcpy(slots, __kvm_memslots(kvm, as_id), sizeof(struct kvm_memslots));
@@ -1201,11 +1205,9 @@ int kvm_get_dirty_log_protect(struct kvm *kvm,
 			mask = xchg(&dirty_bitmap[i], 0);
 			dirty_bitmap_buffer[i] = mask;
 
-			if (mask) {
-				offset = i * BITS_PER_LONG;
-				kvm_arch_mmu_enable_log_dirty_pt_masked(kvm, memslot,
-									offset, mask);
-			}
+			offset = i * BITS_PER_LONG;
+			kvm_arch_mmu_enable_log_dirty_pt_masked(kvm, memslot,
+								offset, mask);
 		}
 		spin_unlock(&kvm->mmu_lock);
 	}
@@ -2185,20 +2187,23 @@ void kvm_sigset_deactivate(struct kvm_vcpu *vcpu)
 
 static void grow_halt_poll_ns(struct kvm_vcpu *vcpu)
 {
-	unsigned int old, val, grow;
+	unsigned int old, val, grow, grow_start;
 
 	old = val = vcpu->halt_poll_ns;
+	grow_start = READ_ONCE(halt_poll_ns_grow_start);
 	grow = READ_ONCE(halt_poll_ns_grow);
-	/* 10us base */
-	if (val == 0 && grow)
-		val = 10000;
-	else
-		val *= grow;
+	if (!grow)
+		goto out;
+
+	val *= grow;
+	if (val < grow_start)
+		val = grow_start;
 
 	if (val > halt_poll_ns)
 		val = halt_poll_ns;
 
 	vcpu->halt_poll_ns = val;
+out:
 	trace_kvm_halt_poll_ns_grow(vcpu->vcpu_id, val, old);
 }
 
@@ -2683,7 +2688,7 @@ static long kvm_vcpu_ioctl(struct file *filp,
 		struct kvm_regs *kvm_regs;
 
 		r = -ENOMEM;
-		kvm_regs = kzalloc(sizeof(struct kvm_regs), GFP_KERNEL);
+		kvm_regs = kzalloc(sizeof(struct kvm_regs), GFP_KERNEL_ACCOUNT);
 		if (!kvm_regs)
 			goto out;
 		r = kvm_arch_vcpu_ioctl_get_regs(vcpu, kvm_regs);
@@ -2711,7 +2716,8 @@ out_free1:
 		break;
 	}
 	case KVM_GET_SREGS: {
-		kvm_sregs = kzalloc(sizeof(struct kvm_sregs), GFP_KERNEL);
+		kvm_sregs = kzalloc(sizeof(struct kvm_sregs),
+				    GFP_KERNEL_ACCOUNT);
 		r = -ENOMEM;
 		if (!kvm_sregs)
 			goto out;
@@ -2803,7 +2809,7 @@ out_free1:
 		break;
 	}
 	case KVM_GET_FPU: {
-		fpu = kzalloc(sizeof(struct kvm_fpu), GFP_KERNEL);
+		fpu = kzalloc(sizeof(struct kvm_fpu), GFP_KERNEL_ACCOUNT);
 		r = -ENOMEM;
 		if (!fpu)
 			goto out;
@@ -2980,7 +2986,7 @@ static int kvm_ioctl_create_device(struct kvm *kvm,
 	if (test)
 		return 0;
 
-	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
+	dev = kzalloc(sizeof(*dev), GFP_KERNEL_ACCOUNT);
 	if (!dev)
 		return -ENOMEM;
 
@@ -3625,6 +3631,7 @@ int kvm_io_bus_write(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr,
 	r = __kvm_io_bus_write(vcpu, bus, &range, val);
 	return r < 0 ? r : 0;
 }
+EXPORT_SYMBOL_GPL(kvm_io_bus_write);
 
 /* kvm_io_bus_write_cookie - called under kvm->slots_lock */
 int kvm_io_bus_write_cookie(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx,
@@ -3675,7 +3682,6 @@ static int __kvm_io_bus_read(struct kvm_vcpu *vcpu, struct kvm_io_bus *bus,
 
 	return -EOPNOTSUPP;
 }
-EXPORT_SYMBOL_GPL(kvm_io_bus_write);
 
 /* kvm_io_bus_read - called under kvm->slots_lock */
 int kvm_io_bus_read(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr,
@@ -3697,7 +3703,6 @@ int kvm_io_bus_read(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr,
 	return r < 0 ? r : 0;
 }
 
-
 /* Caller must hold slots_lock. */
 int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
 			    int len, struct kvm_io_device *dev)
@@ -3714,8 +3719,8 @@ int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
 	if (bus->dev_count - bus->ioeventfd_count > NR_IOBUS_DEVS - 1)
 		return -ENOSPC;
 
-	new_bus = kmalloc(sizeof(*bus) + ((bus->dev_count + 1) *
-			  sizeof(struct kvm_io_range)), GFP_KERNEL);
+	new_bus = kmalloc(struct_size(bus, range, bus->dev_count + 1),
+			  GFP_KERNEL_ACCOUNT);
 	if (!new_bus)
 		return -ENOMEM;
 
@@ -3760,8 +3765,8 @@ void kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx,
 	if (i == bus->dev_count)
 		return;
 
-	new_bus = kmalloc(sizeof(*bus) + ((bus->dev_count - 1) *
-			  sizeof(struct kvm_io_range)), GFP_KERNEL);
+	new_bus = kmalloc(struct_size(bus, range, bus->dev_count - 1),
+			  GFP_KERNEL_ACCOUNT);
 	if (!new_bus)  {
 		pr_err("kvm: failed to shrink bus, removing it completely\n");
 		goto broken;
@@ -4029,7 +4034,7 @@ static void kvm_uevent_notify_change(unsigned int type, struct kvm *kvm)
 	active = kvm_active_vms;
 	spin_unlock(&kvm_lock);
 
-	env = kzalloc(sizeof(*env), GFP_KERNEL);
+	env = kzalloc(sizeof(*env), GFP_KERNEL_ACCOUNT);
 	if (!env)
 		return;
 
@@ -4045,7 +4050,7 @@ static void kvm_uevent_notify_change(unsigned int type, struct kvm *kvm)
 	add_uevent_var(env, "PID=%d", kvm->userspace_pid);
 
 	if (!IS_ERR_OR_NULL(kvm->debugfs_dentry)) {
-		char *tmp, *p = kmalloc(PATH_MAX, GFP_KERNEL);
+		char *tmp, *p = kmalloc(PATH_MAX, GFP_KERNEL_ACCOUNT);
 
 		if (p) {
 			tmp = dentry_path_raw(kvm->debugfs_dentry, p, PATH_MAX);