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

Pull KVM update from Paolo Bonzini:
 "Fairly small update, but there are some interesting new features.

  Common:
     Optional support for adding a small amount of polling on each HLT
     instruction executed in the guest (or equivalent for other
     architectures).  This can improve latency up to 50% on some
     scenarios (e.g. O_DSYNC writes or TCP_RR netperf tests).  This
     also has to be enabled manually for now, but the plan is to
     auto-tune this in the future.

  ARM/ARM64:
     The highlights are support for GICv3 emulation and dirty page
     tracking

  s390:
     Several optimizations and bugfixes.  Also a first: a feature
     exposed by KVM (UUID and long guest name in /proc/sysinfo) before
     it is available in IBM's hypervisor! :)

  MIPS:
     Bugfixes.

  x86:
     Support for PML (page modification logging, a new feature in
     Broadwell Xeons that speeds up dirty page tracking), nested
     virtualization improvements (nested APICv---a nice optimization),
     usual round of emulation fixes.

     There is also a new option to reduce latency of the TSC deadline
     timer in the guest; this needs to be tuned manually.

     Some commits are common between this pull and Catalin's; I see you
     have already included his tree.

  Powerpc:
     Nothing yet.

     The KVM/PPC changes will come in through the PPC maintainers,
     because I haven't received them yet and I might end up being
     offline for some part of next week"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (130 commits)
  KVM: ia64: drop kvm.h from installed user headers
  KVM: x86: fix build with !CONFIG_SMP
  KVM: x86: emulate: correct page fault error code for NoWrite instructions
  KVM: Disable compat ioctl for s390
  KVM: s390: add cpu model support
  KVM: s390: use facilities and cpu_id per KVM
  KVM: s390/CPACF: Choose crypto control block format
  s390/kernel: Update /proc/sysinfo file with Extended Name and UUID
  KVM: s390: reenable LPP facility
  KVM: s390: floating irqs: fix user triggerable endless loop
  kvm: add halt_poll_ns module parameter
  kvm: remove KVM_MMIO_SIZE
  KVM: MIPS: Don't leak FPU/DSP to guest
  KVM: MIPS: Disable HTW while in guest
  KVM: nVMX: Enable nested posted interrupt processing
  KVM: nVMX: Enable nested virtual interrupt delivery
  KVM: nVMX: Enable nested apic register virtualization
  KVM: nVMX: Make nested control MSRs per-cpu
  KVM: nVMX: Enable nested virtualize x2apic mode
  KVM: nVMX: Prepare for using hardware MSR bitmap
  ...

1 files changed, 131 insertions, 13 deletions

diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 458b9b14b15c..a1093700f3a4 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -66,6 +66,9 @@
 MODULE_AUTHOR("Qumranet");
 MODULE_LICENSE("GPL");
 
+unsigned int halt_poll_ns = 0;
+module_param(halt_poll_ns, uint, S_IRUGO | S_IWUSR);
+
 /*
  * Ordering of locks:
  *
@@ -89,7 +92,7 @@ struct dentry *kvm_debugfs_dir;
 
 static long kvm_vcpu_ioctl(struct file *file, unsigned int ioctl,
 			   unsigned long arg);
-#ifdef CONFIG_COMPAT
+#ifdef CONFIG_KVM_COMPAT
 static long kvm_vcpu_compat_ioctl(struct file *file, unsigned int ioctl,
 				  unsigned long arg);
 #endif
@@ -176,6 +179,7 @@ bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req)
 	return called;
 }
 
+#ifndef CONFIG_HAVE_KVM_ARCH_TLB_FLUSH_ALL
 void kvm_flush_remote_tlbs(struct kvm *kvm)
 {
 	long dirty_count = kvm->tlbs_dirty;
@@ -186,6 +190,7 @@ void kvm_flush_remote_tlbs(struct kvm *kvm)
 	cmpxchg(&kvm->tlbs_dirty, dirty_count, 0);
 }
 EXPORT_SYMBOL_GPL(kvm_flush_remote_tlbs);
+#endif
 
 void kvm_reload_remote_mmus(struct kvm *kvm)
 {
@@ -673,6 +678,7 @@ static void update_memslots(struct kvm_memslots *slots,
 	if (!new->npages) {
 		WARN_ON(!mslots[i].npages);
 		new->base_gfn = 0;
+		new->flags = 0;
 		if (mslots[i].npages)
 			slots->used_slots--;
 	} else {
@@ -993,6 +999,86 @@ out:
 }
 EXPORT_SYMBOL_GPL(kvm_get_dirty_log);
 
+#ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT
+/**
+ * kvm_get_dirty_log_protect - get a snapshot of dirty pages, and if any pages
+ *	are dirty write protect them for next write.
+ * @kvm:	pointer to kvm instance
+ * @log:	slot id and address to which we copy the log
+ * @is_dirty:	flag set if any page is dirty
+ *
+ * We need to keep it in mind that VCPU threads can write to the bitmap
+ * concurrently. So, to avoid losing track of dirty pages we keep the
+ * following order:
+ *
+ *    1. Take a snapshot of the bit and clear it if needed.
+ *    2. Write protect the corresponding page.
+ *    3. Copy the snapshot to the userspace.
+ *    4. Upon return caller flushes TLB's if needed.
+ *
+ * Between 2 and 4, the guest may write to the page using the remaining TLB
+ * entry.  This is not a problem because the page is reported dirty using
+ * the snapshot taken before and step 4 ensures that writes done after
+ * exiting to userspace will be logged for the next call.
+ *
+ */
+int kvm_get_dirty_log_protect(struct kvm *kvm,
+			struct kvm_dirty_log *log, bool *is_dirty)
+{
+	struct kvm_memory_slot *memslot;
+	int r, i;
+	unsigned long n;
+	unsigned long *dirty_bitmap;
+	unsigned long *dirty_bitmap_buffer;
+
+	r = -EINVAL;
+	if (log->slot >= KVM_USER_MEM_SLOTS)
+		goto out;
+
+	memslot = id_to_memslot(kvm->memslots, log->slot);
+
+	dirty_bitmap = memslot->dirty_bitmap;
+	r = -ENOENT;
+	if (!dirty_bitmap)
+		goto out;
+
+	n = kvm_dirty_bitmap_bytes(memslot);
+
+	dirty_bitmap_buffer = dirty_bitmap + n / sizeof(long);
+	memset(dirty_bitmap_buffer, 0, n);
+
+	spin_lock(&kvm->mmu_lock);
+	*is_dirty = false;
+	for (i = 0; i < n / sizeof(long); i++) {
+		unsigned long mask;
+		gfn_t offset;
+
+		if (!dirty_bitmap[i])
+			continue;
+
+		*is_dirty = true;
+
+		mask = xchg(&dirty_bitmap[i], 0);
+		dirty_bitmap_buffer[i] = mask;
+
+		offset = i * BITS_PER_LONG;
+		kvm_arch_mmu_enable_log_dirty_pt_masked(kvm, memslot, offset,
+								mask);
+	}
+
+	spin_unlock(&kvm->mmu_lock);
+
+	r = -EFAULT;
+	if (copy_to_user(log->dirty_bitmap, dirty_bitmap_buffer, n))
+		goto out;
+
+	r = 0;
+out:
+	return r;
+}
+EXPORT_SYMBOL_GPL(kvm_get_dirty_log_protect);
+#endif
+
 bool kvm_largepages_enabled(void)
 {
 	return largepages_enabled;
@@ -1551,6 +1637,7 @@ int kvm_write_guest(struct kvm *kvm, gpa_t gpa, const void *data,
 	}
 	return 0;
 }
+EXPORT_SYMBOL_GPL(kvm_write_guest);
 
 int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
 			      gpa_t gpa, unsigned long len)
@@ -1687,29 +1774,60 @@ void mark_page_dirty(struct kvm *kvm, gfn_t gfn)
 }
 EXPORT_SYMBOL_GPL(mark_page_dirty);
 
+static int kvm_vcpu_check_block(struct kvm_vcpu *vcpu)
+{
+	if (kvm_arch_vcpu_runnable(vcpu)) {
+		kvm_make_request(KVM_REQ_UNHALT, vcpu);
+		return -EINTR;
+	}
+	if (kvm_cpu_has_pending_timer(vcpu))
+		return -EINTR;
+	if (signal_pending(current))
+		return -EINTR;
+
+	return 0;
+}
+
 /*
  * The vCPU has executed a HLT instruction with in-kernel mode enabled.
  */
 void kvm_vcpu_block(struct kvm_vcpu *vcpu)
 {
+	ktime_t start, cur;
 	DEFINE_WAIT(wait);
+	bool waited = false;
+
+	start = cur = ktime_get();
+	if (halt_poll_ns) {
+		ktime_t stop = ktime_add_ns(ktime_get(), halt_poll_ns);
+		do {
+			/*
+			 * This sets KVM_REQ_UNHALT if an interrupt
+			 * arrives.
+			 */
+			if (kvm_vcpu_check_block(vcpu) < 0) {
+				++vcpu->stat.halt_successful_poll;
+				goto out;
+			}
+			cur = ktime_get();
+		} while (single_task_running() && ktime_before(cur, stop));
+	}
 
 	for (;;) {
 		prepare_to_wait(&vcpu->wq, &wait, TASK_INTERRUPTIBLE);
 
-		if (kvm_arch_vcpu_runnable(vcpu)) {
-			kvm_make_request(KVM_REQ_UNHALT, vcpu);
-			break;
-		}
-		if (kvm_cpu_has_pending_timer(vcpu))
-			break;
-		if (signal_pending(current))
+		if (kvm_vcpu_check_block(vcpu) < 0)
 			break;
 
+		waited = true;
 		schedule();
 	}
 
 	finish_wait(&vcpu->wq, &wait);
+	cur = ktime_get();
+
+out:
+	trace_kvm_vcpu_wakeup(ktime_to_ns(cur) - ktime_to_ns(start), waited);
 }
 EXPORT_SYMBOL_GPL(kvm_vcpu_block);
 
@@ -1892,7 +2010,7 @@ static int kvm_vcpu_release(struct inode *inode, struct file *filp)
 static struct file_operations kvm_vcpu_fops = {
 	.release        = kvm_vcpu_release,
 	.unlocked_ioctl = kvm_vcpu_ioctl,
-#ifdef CONFIG_COMPAT
+#ifdef CONFIG_KVM_COMPAT
 	.compat_ioctl   = kvm_vcpu_compat_ioctl,
 #endif
 	.mmap           = kvm_vcpu_mmap,
@@ -2182,7 +2300,7 @@ out:
 	return r;
 }
 
-#ifdef CONFIG_COMPAT
+#ifdef CONFIG_KVM_COMPAT
 static long kvm_vcpu_compat_ioctl(struct file *filp,
 				  unsigned int ioctl, unsigned long arg)
 {
@@ -2274,7 +2392,7 @@ static int kvm_device_release(struct inode *inode, struct file *filp)
 
 static const struct file_operations kvm_device_fops = {
 	.unlocked_ioctl = kvm_device_ioctl,
-#ifdef CONFIG_COMPAT
+#ifdef CONFIG_KVM_COMPAT
 	.compat_ioctl = kvm_device_ioctl,
 #endif
 	.release = kvm_device_release,
@@ -2561,7 +2679,7 @@ out:
 	return r;
 }
 
-#ifdef CONFIG_COMPAT
+#ifdef CONFIG_KVM_COMPAT
 struct compat_kvm_dirty_log {
 	__u32 slot;
 	__u32 padding1;
@@ -2608,7 +2726,7 @@ out:
 static struct file_operations kvm_vm_fops = {
 	.release        = kvm_vm_release,
 	.unlocked_ioctl = kvm_vm_ioctl,
-#ifdef CONFIG_COMPAT
+#ifdef CONFIG_KVM_COMPAT
 	.compat_ioctl   = kvm_vm_compat_ioctl,
 #endif
 	.llseek		= noop_llseek,