1 files changed, 119 insertions, 73 deletions

diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 515dfe9d3bcf..fab4d3790578 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -702,30 +702,31 @@ static void kvm_mmu_notifier_change_pte(struct mmu_notifier *mn,
 
 	/*
 	 * .change_pte() must be surrounded by .invalidate_range_{start,end}().
-	 * If mmu_notifier_count is zero, then no in-progress invalidations,
-	 * including this one, found a relevant memslot at start(); rechecking
-	 * memslots here is unnecessary.  Note, a false positive (count elevated
-	 * by a different invalidation) is sub-optimal but functionally ok.
+	 * If mmu_invalidate_in_progress is zero, then no in-progress
+	 * invalidations, including this one, found a relevant memslot at
+	 * start(); rechecking memslots here is unnecessary.  Note, a false
+	 * positive (count elevated by a different invalidation) is sub-optimal
+	 * but functionally ok.
 	 */
 	WARN_ON_ONCE(!READ_ONCE(kvm->mn_active_invalidate_count));
-	if (!READ_ONCE(kvm->mmu_notifier_count))
+	if (!READ_ONCE(kvm->mmu_invalidate_in_progress))
 		return;
 
 	kvm_handle_hva_range(mn, address, address + 1, pte, kvm_set_spte_gfn);
 }
 
-void kvm_inc_notifier_count(struct kvm *kvm, unsigned long start,
-				   unsigned long end)
+void kvm_mmu_invalidate_begin(struct kvm *kvm, unsigned long start,
+			      unsigned long end)
 {
 	/*
 	 * The count increase must become visible at unlock time as no
 	 * spte can be established without taking the mmu_lock and
 	 * count is also read inside the mmu_lock critical section.
 	 */
-	kvm->mmu_notifier_count++;
-	if (likely(kvm->mmu_notifier_count == 1)) {
-		kvm->mmu_notifier_range_start = start;
-		kvm->mmu_notifier_range_end = end;
+	kvm->mmu_invalidate_in_progress++;
+	if (likely(kvm->mmu_invalidate_in_progress == 1)) {
+		kvm->mmu_invalidate_range_start = start;
+		kvm->mmu_invalidate_range_end = end;
 	} else {
 		/*
 		 * Fully tracking multiple concurrent ranges has diminishing
@@ -736,10 +737,10 @@ void kvm_inc_notifier_count(struct kvm *kvm, unsigned long start,
 		 * accumulate and persist until all outstanding invalidates
 		 * complete.
 		 */
-		kvm->mmu_notifier_range_start =
-			min(kvm->mmu_notifier_range_start, start);
-		kvm->mmu_notifier_range_end =
-			max(kvm->mmu_notifier_range_end, end);
+		kvm->mmu_invalidate_range_start =
+			min(kvm->mmu_invalidate_range_start, start);
+		kvm->mmu_invalidate_range_end =
+			max(kvm->mmu_invalidate_range_end, end);
 	}
 }
 
@@ -752,7 +753,7 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
 		.end		= range->end,
 		.pte		= __pte(0),
 		.handler	= kvm_unmap_gfn_range,
-		.on_lock	= kvm_inc_notifier_count,
+		.on_lock	= kvm_mmu_invalidate_begin,
 		.on_unlock	= kvm_arch_guest_memory_reclaimed,
 		.flush_on_ret	= true,
 		.may_block	= mmu_notifier_range_blockable(range),
@@ -763,7 +764,7 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
 	/*
 	 * Prevent memslot modification between range_start() and range_end()
 	 * so that conditionally locking provides the same result in both
-	 * functions.  Without that guarantee, the mmu_notifier_count
+	 * functions.  Without that guarantee, the mmu_invalidate_in_progress
 	 * adjustments will be imbalanced.
 	 *
 	 * Pairs with the decrement in range_end().
@@ -779,7 +780,8 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
 	 * any given time, and the caches themselves can check for hva overlap,
 	 * i.e. don't need to rely on memslot overlap checks for performance.
 	 * Because this runs without holding mmu_lock, the pfn caches must use
-	 * mn_active_invalidate_count (see above) instead of mmu_notifier_count.
+	 * mn_active_invalidate_count (see above) instead of
+	 * mmu_invalidate_in_progress.
 	 */
 	gfn_to_pfn_cache_invalidate_start(kvm, range->start, range->end,
 					  hva_range.may_block);
@@ -789,22 +791,22 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
 	return 0;
 }
 
-void kvm_dec_notifier_count(struct kvm *kvm, unsigned long start,
-				   unsigned long end)
+void kvm_mmu_invalidate_end(struct kvm *kvm, unsigned long start,
+			    unsigned long end)
 {
 	/*
 	 * This sequence increase will notify the kvm page fault that
 	 * the page that is going to be mapped in the spte could have
 	 * been freed.
 	 */
-	kvm->mmu_notifier_seq++;
+	kvm->mmu_invalidate_seq++;
 	smp_wmb();
 	/*
 	 * The above sequence increase must be visible before the
 	 * below count decrease, which is ensured by the smp_wmb above
-	 * in conjunction with the smp_rmb in mmu_notifier_retry().
+	 * in conjunction with the smp_rmb in mmu_invalidate_retry().
 	 */
-	kvm->mmu_notifier_count--;
+	kvm->mmu_invalidate_in_progress--;
 }
 
 static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn,
@@ -816,7 +818,7 @@ static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn,
 		.end		= range->end,
 		.pte		= __pte(0),
 		.handler	= (void *)kvm_null_fn,
-		.on_lock	= kvm_dec_notifier_count,
+		.on_lock	= kvm_mmu_invalidate_end,
 		.on_unlock	= (void *)kvm_null_fn,
 		.flush_on_ret	= false,
 		.may_block	= mmu_notifier_range_blockable(range),
@@ -837,7 +839,7 @@ static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn,
 	if (wake)
 		rcuwait_wake_up(&kvm->mn_memslots_update_rcuwait);
 
-	BUG_ON(kvm->mmu_notifier_count < 0);
+	BUG_ON(kvm->mmu_invalidate_in_progress < 0);
 }
 
 static int kvm_mmu_notifier_clear_flush_young(struct mmu_notifier *mn,
@@ -1134,6 +1136,9 @@ static struct kvm *kvm_create_vm(unsigned long type, const char *fdname)
 	if (!kvm)
 		return ERR_PTR(-ENOMEM);
 
+	/* KVM is pinned via open("/dev/kvm"), the fd passed to this ioctl(). */
+	__module_get(kvm_chardev_ops.owner);
+
 	KVM_MMU_LOCK_INIT(kvm);
 	mmgrab(current->mm);
 	kvm->mm = current->mm;
@@ -1193,8 +1198,6 @@ static struct kvm *kvm_create_vm(unsigned long type, const char *fdname)
 			goto out_err_no_arch_destroy_vm;
 	}
 
-	kvm->max_halt_poll_ns = halt_poll_ns;
-
 	r = kvm_arch_init_vm(kvm, type);
 	if (r)
 		goto out_err_no_arch_destroy_vm;
@@ -1211,9 +1214,17 @@ static struct kvm *kvm_create_vm(unsigned long type, const char *fdname)
 	if (r)
 		goto out_err_no_mmu_notifier;
 
+	r = kvm_coalesced_mmio_init(kvm);
+	if (r < 0)
+		goto out_no_coalesced_mmio;
+
+	r = kvm_create_vm_debugfs(kvm, fdname);
+	if (r)
+		goto out_err_no_debugfs;
+
 	r = kvm_arch_post_init_vm(kvm);
 	if (r)
-		goto out_err_mmu_notifier;
+		goto out_err;
 
 	mutex_lock(&kvm_lock);
 	list_add(&kvm->vm_list, &vm_list);
@@ -1222,25 +1233,13 @@ static struct kvm *kvm_create_vm(unsigned long type, const char *fdname)
 	preempt_notifier_inc();
 	kvm_init_pm_notifier(kvm);
 
-	/*
-	 * When the fd passed to this ioctl() is opened it pins the module,
-	 * but try_module_get() also prevents getting a reference if the module
-	 * is in MODULE_STATE_GOING (e.g. if someone ran "rmmod --wait").
-	 */
-	if (!try_module_get(kvm_chardev_ops.owner)) {
-		r = -ENODEV;
-		goto out_err_mmu_notifier;
-	}
-
-	r = kvm_create_vm_debugfs(kvm, fdname);
-	if (r)
-		goto out_err;
-
 	return kvm;
 
 out_err:
-	module_put(kvm_chardev_ops.owner);
-out_err_mmu_notifier:
+	kvm_destroy_vm_debugfs(kvm);
+out_err_no_debugfs:
+	kvm_coalesced_mmio_free(kvm);
+out_no_coalesced_mmio:
 #if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
 	if (kvm->mmu_notifier.ops)
 		mmu_notifier_unregister(&kvm->mmu_notifier, current->mm);
@@ -1259,6 +1258,7 @@ out_err_no_irq_srcu:
 out_err_no_srcu:
 	kvm_arch_free_vm(kvm);
 	mmdrop(current->mm);
+	module_put(kvm_chardev_ops.owner);
 	return ERR_PTR(r);
 }
 
@@ -2516,7 +2516,7 @@ static int hva_to_pfn_slow(unsigned long addr, bool *async, bool write_fault,
 {
 	unsigned int flags = FOLL_HWPOISON;
 	struct page *page;
-	int npages = 0;
+	int npages;
 
 	might_sleep();
 
@@ -3375,9 +3375,6 @@ static void grow_halt_poll_ns(struct kvm_vcpu *vcpu)
 	if (val < grow_start)
 		val = grow_start;
 
-	if (val > vcpu->kvm->max_halt_poll_ns)
-		val = vcpu->kvm->max_halt_poll_ns;
-
 	vcpu->halt_poll_ns = val;
 out:
 	trace_kvm_halt_poll_ns_grow(vcpu->vcpu_id, val, old);
@@ -3407,10 +3404,8 @@ static int kvm_vcpu_check_block(struct kvm_vcpu *vcpu)
 	int ret = -EINTR;
 	int idx = srcu_read_lock(&vcpu->kvm->srcu);
 
-	if (kvm_arch_vcpu_runnable(vcpu)) {
-		kvm_make_request(KVM_REQ_UNHALT, vcpu);
+	if (kvm_arch_vcpu_runnable(vcpu))
 		goto out;
-	}
 	if (kvm_cpu_has_pending_timer(vcpu))
 		goto out;
 	if (signal_pending(current))
@@ -3483,6 +3478,24 @@ static inline void update_halt_poll_stats(struct kvm_vcpu *vcpu, ktime_t start,
 	}
 }
 
+static unsigned int kvm_vcpu_max_halt_poll_ns(struct kvm_vcpu *vcpu)
+{
+	struct kvm *kvm = vcpu->kvm;
+
+	if (kvm->override_halt_poll_ns) {
+		/*
+		 * Ensure kvm->max_halt_poll_ns is not read before
+		 * kvm->override_halt_poll_ns.
+		 *
+		 * Pairs with the smp_wmb() when enabling KVM_CAP_HALT_POLL.
+		 */
+		smp_rmb();
+		return READ_ONCE(kvm->max_halt_poll_ns);
+	}
+
+	return READ_ONCE(halt_poll_ns);
+}
+
 /*
  * Emulate a vCPU halt condition, e.g. HLT on x86, WFI on arm, etc...  If halt
  * polling is enabled, busy wait for a short time before blocking to avoid the
@@ -3491,12 +3504,18 @@ static inline void update_halt_poll_stats(struct kvm_vcpu *vcpu, ktime_t start,
  */
 void kvm_vcpu_halt(struct kvm_vcpu *vcpu)
 {
+	unsigned int max_halt_poll_ns = kvm_vcpu_max_halt_poll_ns(vcpu);
 	bool halt_poll_allowed = !kvm_arch_no_poll(vcpu);
-	bool do_halt_poll = halt_poll_allowed && vcpu->halt_poll_ns;
 	ktime_t start, cur, poll_end;
 	bool waited = false;
+	bool do_halt_poll;
 	u64 halt_ns;
 
+	if (vcpu->halt_poll_ns > max_halt_poll_ns)
+		vcpu->halt_poll_ns = max_halt_poll_ns;
+
+	do_halt_poll = halt_poll_allowed && vcpu->halt_poll_ns;
+
 	start = cur = poll_end = ktime_get();
 	if (do_halt_poll) {
 		ktime_t stop = ktime_add_ns(start, vcpu->halt_poll_ns);
@@ -3535,18 +3554,21 @@ out:
 		update_halt_poll_stats(vcpu, start, poll_end, !waited);
 
 	if (halt_poll_allowed) {
+		/* Recompute the max halt poll time in case it changed. */
+		max_halt_poll_ns = kvm_vcpu_max_halt_poll_ns(vcpu);
+
 		if (!vcpu_valid_wakeup(vcpu)) {
 			shrink_halt_poll_ns(vcpu);
-		} else if (vcpu->kvm->max_halt_poll_ns) {
+		} else if (max_halt_poll_ns) {
 			if (halt_ns <= vcpu->halt_poll_ns)
 				;
 			/* we had a long block, shrink polling */
 			else if (vcpu->halt_poll_ns &&
-				 halt_ns > vcpu->kvm->max_halt_poll_ns)
+				 halt_ns > max_halt_poll_ns)
 				shrink_halt_poll_ns(vcpu);
 			/* we had a short halt and our poll time is too small */
-			else if (vcpu->halt_poll_ns < vcpu->kvm->max_halt_poll_ns &&
-				 halt_ns < vcpu->kvm->max_halt_poll_ns)
+			else if (vcpu->halt_poll_ns < max_halt_poll_ns &&
+				 halt_ns < max_halt_poll_ns)
 				grow_halt_poll_ns(vcpu);
 		} else {
 			vcpu->halt_poll_ns = 0;
@@ -4378,7 +4400,7 @@ void kvm_unregister_device_ops(u32 type)
 static int kvm_ioctl_create_device(struct kvm *kvm,
 				   struct kvm_create_device *cd)
 {
-	const struct kvm_device_ops *ops = NULL;
+	const struct kvm_device_ops *ops;
 	struct kvm_device *dev;
 	bool test = cd->flags & KVM_CREATE_DEVICE_TEST;
 	int type;
@@ -4473,7 +4495,13 @@ static long kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg)
 	case KVM_CAP_NR_MEMSLOTS:
 		return KVM_USER_MEM_SLOTS;
 	case KVM_CAP_DIRTY_LOG_RING:
-#ifdef CONFIG_HAVE_KVM_DIRTY_RING
+#ifdef CONFIG_HAVE_KVM_DIRTY_RING_TSO
+		return KVM_DIRTY_RING_MAX_ENTRIES * sizeof(struct kvm_dirty_gfn);
+#else
+		return 0;
+#endif
+	case KVM_CAP_DIRTY_LOG_RING_ACQ_REL:
+#ifdef CONFIG_HAVE_KVM_DIRTY_RING_ACQ_REL
 		return KVM_DIRTY_RING_MAX_ENTRIES * sizeof(struct kvm_dirty_gfn);
 #else
 		return 0;
@@ -4575,9 +4603,23 @@ static int kvm_vm_ioctl_enable_cap_generic(struct kvm *kvm,
 			return -EINVAL;
 
 		kvm->max_halt_poll_ns = cap->args[0];
+
+		/*
+		 * Ensure kvm->override_halt_poll_ns does not become visible
+		 * before kvm->max_halt_poll_ns.
+		 *
+		 * Pairs with the smp_rmb() in kvm_vcpu_max_halt_poll_ns().
+		 */
+		smp_wmb();
+		kvm->override_halt_poll_ns = true;
+
 		return 0;
 	}
 	case KVM_CAP_DIRTY_LOG_RING:
+	case KVM_CAP_DIRTY_LOG_RING_ACQ_REL:
+		if (!kvm_vm_ioctl_check_extension_generic(kvm, cap->cap))
+			return -EINVAL;
+
 		return kvm_vm_ioctl_enable_dirty_log_ring(kvm, cap->args[0]);
 	default:
 		return kvm_vm_ioctl_enable_cap(kvm, cap);
@@ -4832,6 +4874,12 @@ struct compat_kvm_clear_dirty_log {
 	};
 };
 
+long __weak kvm_arch_vm_compat_ioctl(struct file *filp, unsigned int ioctl,
+				     unsigned long arg)
+{
+	return -ENOTTY;
+}
+
 static long kvm_vm_compat_ioctl(struct file *filp,
 			   unsigned int ioctl, unsigned long arg)
 {
@@ -4840,6 +4888,11 @@ static long kvm_vm_compat_ioctl(struct file *filp,
 
 	if (kvm->mm != current->mm || kvm->vm_dead)
 		return -EIO;
+
+	r = kvm_arch_vm_compat_ioctl(filp, ioctl, arg);
+	if (r != -ENOTTY)
+		return r;
+
 	switch (ioctl) {
 #ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT
 	case KVM_CLEAR_DIRTY_LOG: {
@@ -4913,11 +4966,6 @@ static int kvm_dev_ioctl_create_vm(unsigned long type)
 		goto put_fd;
 	}
 
-#ifdef CONFIG_KVM_MMIO
-	r = kvm_coalesced_mmio_init(kvm);
-	if (r < 0)
-		goto put_kvm;
-#endif
 	file = anon_inode_getfile("kvm-vm", &kvm_vm_fops, kvm, O_RDWR);
 	if (IS_ERR(file)) {
 		r = PTR_ERR(file);
@@ -5396,6 +5444,7 @@ static int kvm_debugfs_open(struct inode *inode, struct file *file,
 			   int (*get)(void *, u64 *), int (*set)(void *, u64),
 			   const char *fmt)
 {
+	int ret;
 	struct kvm_stat_data *stat_data = (struct kvm_stat_data *)
 					  inode->i_private;
 
@@ -5407,15 +5456,13 @@ static int kvm_debugfs_open(struct inode *inode, struct file *file,
 	if (!kvm_get_kvm_safe(stat_data->kvm))
 		return -ENOENT;
 
-	if (simple_attr_open(inode, file, get,
-		    kvm_stats_debugfs_mode(stat_data->desc) & 0222
-		    ? set : NULL,
-		    fmt)) {
+	ret = simple_attr_open(inode, file, get,
+			       kvm_stats_debugfs_mode(stat_data->desc) & 0222
+			       ? set : NULL, fmt);
+	if (ret)
 		kvm_put_kvm(stat_data->kvm);
-		return -ENOMEM;
-	}
 
-	return 0;
+	return ret;
 }
 
 static int kvm_debugfs_release(struct inode *inode, struct file *file)
@@ -5884,7 +5931,7 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align,
 
 	r = kvm_async_pf_init();
 	if (r)
-		goto out_free_5;
+		goto out_free_4;
 
 	kvm_chardev_ops.owner = module;
 
@@ -5908,10 +5955,9 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align,
 
 out_unreg:
 	kvm_async_pf_deinit();
-out_free_5:
+out_free_4:
 	for_each_possible_cpu(cpu)
 		free_cpumask_var(per_cpu(cpu_kick_mask, cpu));
-out_free_4:
 	kmem_cache_destroy(kvm_vcpu_cache);
 out_free_3:
 	unregister_reboot_notifier(&kvm_reboot_notifier);