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

Pull KVM updates from Paolo Bonzini:
 "At over 200 commits, covering almost all supported architectures, this
  was a pretty active cycle for KVM.  Changes include:

   - a lot of s390 changes: optimizations, support for migration, GDB
     support and more

   - ARM changes are pretty small: support for the PSCI 0.2 hypercall
     interface on both the guest and the host (the latter acked by
     Catalin)

   - initial POWER8 and little-endian host support

   - support for running u-boot on embedded POWER targets

   - pretty large changes to MIPS too, completing the userspace
     interface and improving the handling of virtualized timer hardware

   - for x86, a larger set of changes is scheduled for 3.17.  Still, we
     have a few emulator bugfixes and support for running nested
     fully-virtualized Xen guests (para-virtualized Xen guests have
     always worked).  And some optimizations too.

  The only missing architecture here is ia64.  It's not a coincidence
  that support for KVM on ia64 is scheduled for removal in 3.17"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (203 commits)
  KVM: add missing cleanup_srcu_struct
  KVM: PPC: Book3S PR: Rework SLB switching code
  KVM: PPC: Book3S PR: Use SLB entry 0
  KVM: PPC: Book3S HV: Fix machine check delivery to guest
  KVM: PPC: Book3S HV: Work around POWER8 performance monitor bugs
  KVM: PPC: Book3S HV: Make sure we don't miss dirty pages
  KVM: PPC: Book3S HV: Fix dirty map for hugepages
  KVM: PPC: Book3S HV: Put huge-page HPTEs in rmap chain for base address
  KVM: PPC: Book3S HV: Fix check for running inside guest in global_invalidates()
  KVM: PPC: Book3S: Move KVM_REG_PPC_WORT to an unused register number
  KVM: PPC: Book3S: Add ONE_REG register names that were missed
  KVM: PPC: Add CAP to indicate hcall fixes
  KVM: PPC: MPIC: Reset IRQ source private members
  KVM: PPC: Graciously fail broken LE hypercalls
  PPC: ePAPR: Fix hypercall on LE guest
  KVM: PPC: BOOK3S: Remove open coded make_dsisr in alignment handler
  KVM: PPC: BOOK3S: Always use the saved DAR value
  PPC: KVM: Make NX bit available with magic page
  KVM: PPC: Disable NX for old magic page using guests
  KVM: PPC: BOOK3S: HV: Add mixed page-size support for guest
  ...

5 files changed, 95 insertions, 50 deletions

diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c
index 06e6401..d6a3d09 100644
--- a/virt/kvm/async_pf.c
+++ b/virt/kvm/async_pf.c
@@ -80,12 +80,10 @@ static void async_pf_execute(struct work_struct *work)
 
 	might_sleep();
 
-	use_mm(mm);
 	down_read(&mm->mmap_sem);
-	get_user_pages(current, mm, addr, 1, 1, 0, NULL, NULL);
+	get_user_pages(NULL, mm, addr, 1, 1, 0, NULL, NULL);
 	up_read(&mm->mmap_sem);
 	kvm_async_page_present_sync(vcpu, apf);
-	unuse_mm(mm);
 
 	spin_lock(&vcpu->async_pf.lock);
 	list_add_tail(&apf->link, &vcpu->async_pf.done);
diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
index 29c2a04..20c3af7 100644
--- a/virt/kvm/eventfd.c
+++ b/virt/kvm/eventfd.c
@@ -31,6 +31,7 @@
 #include <linux/list.h>
 #include <linux/eventfd.h>
 #include <linux/kernel.h>
+#include <linux/srcu.h>
 #include <linux/slab.h>
 
 #include "iodev.h"
@@ -118,19 +119,22 @@ static void
 irqfd_resampler_ack(struct kvm_irq_ack_notifier *kian)
 {
 	struct _irqfd_resampler *resampler;
+	struct kvm *kvm;
 	struct _irqfd *irqfd;
+	int idx;
 
 	resampler = container_of(kian, struct _irqfd_resampler, notifier);
+	kvm = resampler->kvm;
 
-	kvm_set_irq(resampler->kvm, KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID,
+	kvm_set_irq(kvm, KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID,
 		    resampler->notifier.gsi, 0, false);
 
-	rcu_read_lock();
+	idx = srcu_read_lock(&kvm->irq_srcu);
 
 	list_for_each_entry_rcu(irqfd, &resampler->list, resampler_link)
 		eventfd_signal(irqfd->resamplefd, 1);
 
-	rcu_read_unlock();
+	srcu_read_unlock(&kvm->irq_srcu, idx);
 }
 
 static void
@@ -142,7 +146,7 @@ irqfd_resampler_shutdown(struct _irqfd *irqfd)
 	mutex_lock(&kvm->irqfds.resampler_lock);
 
 	list_del_rcu(&irqfd->resampler_link);
-	synchronize_rcu();
+	synchronize_srcu(&kvm->irq_srcu);
 
 	if (list_empty(&resampler->list)) {
 		list_del(&resampler->link);
@@ -221,17 +225,18 @@ irqfd_wakeup(wait_queue_t *wait, unsigned mode, int sync, void *key)
 	unsigned long flags = (unsigned long)key;
 	struct kvm_kernel_irq_routing_entry *irq;
 	struct kvm *kvm = irqfd->kvm;
+	int idx;
 
 	if (flags & POLLIN) {
-		rcu_read_lock();
-		irq = rcu_dereference(irqfd->irq_entry);
+		idx = srcu_read_lock(&kvm->irq_srcu);
+		irq = srcu_dereference(irqfd->irq_entry, &kvm->irq_srcu);
 		/* An event has been signaled, inject an interrupt */
 		if (irq)
 			kvm_set_msi(irq, kvm, KVM_USERSPACE_IRQ_SOURCE_ID, 1,
 					false);
 		else
 			schedule_work(&irqfd->inject);
-		rcu_read_unlock();
+		srcu_read_unlock(&kvm->irq_srcu, idx);
 	}
 
 	if (flags & POLLHUP) {
@@ -363,7 +368,7 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args)
 		}
 
 		list_add_rcu(&irqfd->resampler_link, &irqfd->resampler->list);
-		synchronize_rcu();
+		synchronize_srcu(&kvm->irq_srcu);
 
 		mutex_unlock(&kvm->irqfds.resampler_lock);
 	}
@@ -465,7 +470,7 @@ kvm_irqfd_deassign(struct kvm *kvm, struct kvm_irqfd *args)
 			 * another thread calls kvm_irq_routing_update before
 			 * we flush workqueue below (we synchronize with
 			 * kvm_irq_routing_update using irqfds.lock).
-			 * It is paired with synchronize_rcu done by caller
+			 * It is paired with synchronize_srcu done by caller
 			 * of that function.
 			 */
 			rcu_assign_pointer(irqfd->irq_entry, NULL);
@@ -524,7 +529,7 @@ kvm_irqfd_release(struct kvm *kvm)
 
 /*
  * Change irq_routing and irqfd.
- * Caller must invoke synchronize_rcu afterwards.
+ * Caller must invoke synchronize_srcu(&kvm->irq_srcu) afterwards.
  */
 void kvm_irq_routing_update(struct kvm *kvm,
 			    struct kvm_irq_routing_table *irq_rt)
@@ -600,7 +605,15 @@ ioeventfd_in_range(struct _ioeventfd *p, gpa_t addr, int len, const void *val)
 {
 	u64 _val;
 
-	if (!(addr == p->addr && len == p->length))
+	if (addr != p->addr)
+		/* address must be precise for a hit */
+		return false;
+
+	if (!p->length)
+		/* length = 0 means only look at the address, so always a hit */
+		return true;
+
+	if (len != p->length)
 		/* address-range must be precise for a hit */
 		return false;
 
@@ -671,9 +684,11 @@ ioeventfd_check_collision(struct kvm *kvm, struct _ioeventfd *p)
 
 	list_for_each_entry(_p, &kvm->ioeventfds, list)
 		if (_p->bus_idx == p->bus_idx &&
-		    _p->addr == p->addr && _p->length == p->length &&
-		    (_p->wildcard || p->wildcard ||
-		     _p->datamatch == p->datamatch))
+		    _p->addr == p->addr &&
+		    (!_p->length || !p->length ||
+		     (_p->length == p->length &&
+		      (_p->wildcard || p->wildcard ||
+		       _p->datamatch == p->datamatch))))
 			return true;
 
 	return false;
@@ -697,8 +712,9 @@ kvm_assign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
 	int                       ret;
 
 	bus_idx = ioeventfd_bus_from_flags(args->flags);
-	/* must be natural-word sized */
+	/* must be natural-word sized, or 0 to ignore length */
 	switch (args->len) {
+	case 0:
 	case 1:
 	case 2:
 	case 4:
@@ -716,6 +732,12 @@ kvm_assign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
 	if (args->flags & ~KVM_IOEVENTFD_VALID_FLAG_MASK)
 		return -EINVAL;
 
+	/* ioeventfd with no length can't be combined with DATAMATCH */
+	if (!args->len &&
+	    args->flags & (KVM_IOEVENTFD_FLAG_PIO |
+			   KVM_IOEVENTFD_FLAG_DATAMATCH))
+		return -EINVAL;
+
 	eventfd = eventfd_ctx_fdget(args->fd);
 	if (IS_ERR(eventfd))
 		return PTR_ERR(eventfd);
@@ -753,6 +775,16 @@ kvm_assign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
 	if (ret < 0)
 		goto unlock_fail;
 
+	/* When length is ignored, MMIO is also put on a separate bus, for
+	 * faster lookups.
+	 */
+	if (!args->len && !(args->flags & KVM_IOEVENTFD_FLAG_PIO)) {
+		ret = kvm_io_bus_register_dev(kvm, KVM_FAST_MMIO_BUS,
+					      p->addr, 0, &p->dev);
+		if (ret < 0)
+			goto register_fail;
+	}
+
 	kvm->buses[bus_idx]->ioeventfd_count++;
 	list_add_tail(&p->list, &kvm->ioeventfds);
 
@@ -760,6 +792,8 @@ kvm_assign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
 
 	return 0;
 
+register_fail:
+	kvm_io_bus_unregister_dev(kvm, bus_idx, &p->dev);
 unlock_fail:
 	mutex_unlock(&kvm->slots_lock);
 
@@ -799,6 +833,10 @@ kvm_deassign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
 			continue;
 
 		kvm_io_bus_unregister_dev(kvm, bus_idx, &p->dev);
+		if (!p->length) {
+			kvm_io_bus_unregister_dev(kvm, KVM_FAST_MMIO_BUS,
+						  &p->dev);
+		}
 		kvm->buses[bus_idx]->ioeventfd_count--;
 		ioeventfd_release(p);
 		ret = 0;
diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c
index e2e6b44..ced4a54 100644
--- a/virt/kvm/irq_comm.c
+++ b/virt/kvm/irq_comm.c
@@ -163,6 +163,7 @@ int kvm_set_irq_inatomic(struct kvm *kvm, int irq_source_id, u32 irq, int level)
 	struct kvm_kernel_irq_routing_entry *e;
 	int ret = -EINVAL;
 	struct kvm_irq_routing_table *irq_rt;
+	int idx;
 
 	trace_kvm_set_irq(irq, level, irq_source_id);
 
@@ -174,8 +175,8 @@ int kvm_set_irq_inatomic(struct kvm *kvm, int irq_source_id, u32 irq, int level)
 	 * Since there's no easy way to do this, we only support injecting MSI
 	 * which is limited to 1:1 GSI mapping.
 	 */
-	rcu_read_lock();
-	irq_rt = rcu_dereference(kvm->irq_routing);
+	idx = srcu_read_lock(&kvm->irq_srcu);
+	irq_rt = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu);
 	if (irq < irq_rt->nr_rt_entries)
 		hlist_for_each_entry(e, &irq_rt->map[irq], link) {
 			if (likely(e->type == KVM_IRQ_ROUTING_MSI))
@@ -184,7 +185,7 @@ int kvm_set_irq_inatomic(struct kvm *kvm, int irq_source_id, u32 irq, int level)
 				ret = -EWOULDBLOCK;
 			break;
 		}
-	rcu_read_unlock();
+	srcu_read_unlock(&kvm->irq_srcu, idx);
 	return ret;
 }
 
@@ -253,22 +254,22 @@ void kvm_unregister_irq_mask_notifier(struct kvm *kvm, int irq,
 	mutex_lock(&kvm->irq_lock);
 	hlist_del_rcu(&kimn->link);
 	mutex_unlock(&kvm->irq_lock);
-	synchronize_rcu();
+	synchronize_srcu(&kvm->irq_srcu);
 }
 
 void kvm_fire_mask_notifiers(struct kvm *kvm, unsigned irqchip, unsigned pin,
 			     bool mask)
 {
 	struct kvm_irq_mask_notifier *kimn;
-	int gsi;
+	int idx, gsi;
 
-	rcu_read_lock();
-	gsi = rcu_dereference(kvm->irq_routing)->chip[irqchip][pin];
+	idx = srcu_read_lock(&kvm->irq_srcu);
+	gsi = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu)->chip[irqchip][pin];
 	if (gsi != -1)
 		hlist_for_each_entry_rcu(kimn, &kvm->mask_notifier_list, link)
 			if (kimn->irq == gsi)
 				kimn->func(kimn, mask);
-	rcu_read_unlock();
+	srcu_read_unlock(&kvm->irq_srcu, idx);
 }
 
 int kvm_set_routing_entry(struct kvm_irq_routing_table *rt,
diff --git a/virt/kvm/irqchip.c b/virt/kvm/irqchip.c
index 20dc9e4..b43c275 100644
--- a/virt/kvm/irqchip.c
+++ b/virt/kvm/irqchip.c
@@ -26,6 +26,7 @@
 
 #include <linux/kvm_host.h>
 #include <linux/slab.h>
+#include <linux/srcu.h>
 #include <linux/export.h>
 #include <trace/events/kvm.h>
 #include "irq.h"
@@ -33,19 +34,19 @@
 bool kvm_irq_has_notifier(struct kvm *kvm, unsigned irqchip, unsigned pin)
 {
 	struct kvm_irq_ack_notifier *kian;
-	int gsi;
+	int gsi, idx;
 
-	rcu_read_lock();
-	gsi = rcu_dereference(kvm->irq_routing)->chip[irqchip][pin];
+	idx = srcu_read_lock(&kvm->irq_srcu);
+	gsi = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu)->chip[irqchip][pin];
 	if (gsi != -1)
 		hlist_for_each_entry_rcu(kian, &kvm->irq_ack_notifier_list,
 					 link)
 			if (kian->gsi == gsi) {
-				rcu_read_unlock();
+				srcu_read_unlock(&kvm->irq_srcu, idx);
 				return true;
 			}
 
-	rcu_read_unlock();
+	srcu_read_unlock(&kvm->irq_srcu, idx);
 
 	return false;
 }
@@ -54,18 +55,18 @@ EXPORT_SYMBOL_GPL(kvm_irq_has_notifier);
 void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin)
 {
 	struct kvm_irq_ack_notifier *kian;
-	int gsi;
+	int gsi, idx;
 
 	trace_kvm_ack_irq(irqchip, pin);
 
-	rcu_read_lock();
-	gsi = rcu_dereference(kvm->irq_routing)->chip[irqchip][pin];
+	idx = srcu_read_lock(&kvm->irq_srcu);
+	gsi = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu)->chip[irqchip][pin];
 	if (gsi != -1)
 		hlist_for_each_entry_rcu(kian, &kvm->irq_ack_notifier_list,
 					 link)
 			if (kian->gsi == gsi)
 				kian->irq_acked(kian);
-	rcu_read_unlock();
+	srcu_read_unlock(&kvm->irq_srcu, idx);
 }
 
 void kvm_register_irq_ack_notifier(struct kvm *kvm,
@@ -85,7 +86,7 @@ void kvm_unregister_irq_ack_notifier(struct kvm *kvm,
 	mutex_lock(&kvm->irq_lock);
 	hlist_del_init_rcu(&kian->link);
 	mutex_unlock(&kvm->irq_lock);
-	synchronize_rcu();
+	synchronize_srcu(&kvm->irq_srcu);
 #ifdef __KVM_HAVE_IOAPIC
 	kvm_vcpu_request_scan_ioapic(kvm);
 #endif
@@ -115,7 +116,7 @@ int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level,
 		bool line_status)
 {
 	struct kvm_kernel_irq_routing_entry *e, irq_set[KVM_NR_IRQCHIPS];
-	int ret = -1, i = 0;
+	int ret = -1, i = 0, idx;
 	struct kvm_irq_routing_table *irq_rt;
 
 	trace_kvm_set_irq(irq, level, irq_source_id);
@@ -124,12 +125,12 @@ int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level,
 	 * IOAPIC.  So set the bit in both. The guest will ignore
 	 * writes to the unused one.
 	 */
-	rcu_read_lock();
-	irq_rt = rcu_dereference(kvm->irq_routing);
+	idx = srcu_read_lock(&kvm->irq_srcu);
+	irq_rt = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu);
 	if (irq < irq_rt->nr_rt_entries)
 		hlist_for_each_entry(e, &irq_rt->map[irq], link)
 			irq_set[i++] = *e;
-	rcu_read_unlock();
+	srcu_read_unlock(&kvm->irq_srcu, idx);
 
 	while(i--) {
 		int r;
@@ -226,7 +227,7 @@ int kvm_set_irq_routing(struct kvm *kvm,
 	kvm_irq_routing_update(kvm, new);
 	mutex_unlock(&kvm->irq_lock);
 
-	synchronize_rcu();
+	synchronize_srcu_expedited(&kvm->irq_srcu);
 
 	new = old;
 	r = 0;
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 56baae8..c86be0f 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -186,9 +186,12 @@ static bool make_all_cpus_request(struct kvm *kvm, unsigned int req)
 
 void kvm_flush_remote_tlbs(struct kvm *kvm)
 {
+	long dirty_count = kvm->tlbs_dirty;
+
+	smp_mb();
 	if (make_all_cpus_request(kvm, KVM_REQ_TLB_FLUSH))
 		++kvm->stat.remote_tlb_flush;
-	kvm->tlbs_dirty = false;
+	cmpxchg(&kvm->tlbs_dirty, dirty_count, 0);
 }
 EXPORT_SYMBOL_GPL(kvm_flush_remote_tlbs);
 
@@ -454,11 +457,11 @@ static struct kvm *kvm_create_vm(unsigned long type)
 
 	r = kvm_arch_init_vm(kvm, type);
 	if (r)
-		goto out_err_nodisable;
+		goto out_err_no_disable;
 
 	r = hardware_enable_all();
 	if (r)
-		goto out_err_nodisable;
+		goto out_err_no_disable;
 
 #ifdef CONFIG_HAVE_KVM_IRQCHIP
 	INIT_HLIST_HEAD(&kvm->mask_notifier_list);
@@ -470,10 +473,12 @@ static struct kvm *kvm_create_vm(unsigned long type)
 	r = -ENOMEM;
 	kvm->memslots = kzalloc(sizeof(struct kvm_memslots), GFP_KERNEL);
 	if (!kvm->memslots)
-		goto out_err_nosrcu;
+		goto out_err_no_srcu;
 	kvm_init_memslots_id(kvm);
 	if (init_srcu_struct(&kvm->srcu))
-		goto out_err_nosrcu;
+		goto out_err_no_srcu;
+	if (init_srcu_struct(&kvm->irq_srcu))
+		goto out_err_no_irq_srcu;
 	for (i = 0; i < KVM_NR_BUSES; i++) {
 		kvm->buses[i] = kzalloc(sizeof(struct kvm_io_bus),
 					GFP_KERNEL);
@@ -502,10 +507,12 @@ static struct kvm *kvm_create_vm(unsigned long type)
 	return kvm;
 
 out_err:
+	cleanup_srcu_struct(&kvm->irq_srcu);
+out_err_no_irq_srcu:
 	cleanup_srcu_struct(&kvm->srcu);
-out_err_nosrcu:
+out_err_no_srcu:
 	hardware_disable_all();
-out_err_nodisable:
+out_err_no_disable:
 	for (i = 0; i < KVM_NR_BUSES; i++)
 		kfree(kvm->buses[i]);
 	kfree(kvm->memslots);
@@ -601,6 +608,7 @@ static void kvm_destroy_vm(struct kvm *kvm)
 	kvm_arch_destroy_vm(kvm);
 	kvm_destroy_devices(kvm);
 	kvm_free_physmem(kvm);
+	cleanup_srcu_struct(&kvm->irq_srcu);
 	cleanup_srcu_struct(&kvm->srcu);
 	kvm_arch_free_vm(kvm);
 	hardware_disable_all();
@@ -637,14 +645,12 @@ static int kvm_vm_release(struct inode *inode, struct file *filp)
  */
 static int kvm_create_dirty_bitmap(struct kvm_memory_slot *memslot)
 {
-#ifndef CONFIG_S390
 	unsigned long dirty_bytes = 2 * kvm_dirty_bitmap_bytes(memslot);
 
 	memslot->dirty_bitmap = kvm_kvzalloc(dirty_bytes);
 	if (!memslot->dirty_bitmap)
 		return -ENOMEM;
 
-#endif /* !CONFIG_S390 */
 	return 0;
 }
 
@@ -2922,6 +2928,7 @@ static int __kvm_io_bus_read(struct kvm_io_bus *bus, struct kvm_io_range *range,
 
 	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 *kvm, enum kvm_bus bus_idx, gpa_t addr,