Merge tag 'kvmarm-5.19' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD

KVM/arm64 updates for 5.19

- Add support for the ARMv8.6 WFxT extension

- Guard pages for the EL2 stacks

- Trap and emulate AArch32 ID registers to hide unsupported features

- Ability to select and save/restore the set of hypercalls exposed
  to the guest

- Support for PSCI-initiated suspend in collaboration with userspace

- GICv3 register-based LPI invalidation support

- Move host PMU event merging into the vcpu data structure

- GICv3 ITS save/restore fixes

- The usual set of small-scale cleanups and fixes

[Due to the conflict, KVM_SYSTEM_EVENT_SEV_TERM is relocated
 from 4 to 6. - Paolo]

1 files changed, 32 insertions, 11 deletions

diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 655365b2cbe8..342043b30125 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -164,6 +164,10 @@ __weak void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm,
 {
 }
 
+__weak void kvm_arch_guest_memory_reclaimed(struct kvm *kvm)
+{
+}
+
 bool kvm_is_zone_device_pfn(kvm_pfn_t pfn)
 {
 	/*
@@ -357,6 +361,12 @@ void kvm_flush_remote_tlbs(struct kvm *kvm)
 EXPORT_SYMBOL_GPL(kvm_flush_remote_tlbs);
 #endif
 
+static void kvm_flush_shadow_all(struct kvm *kvm)
+{
+	kvm_arch_flush_shadow_all(kvm);
+	kvm_arch_guest_memory_reclaimed(kvm);
+}
+
 #ifdef KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE
 static inline void *mmu_memory_cache_alloc_obj(struct kvm_mmu_memory_cache *mc,
 					       gfp_t gfp_flags)
@@ -485,12 +495,15 @@ typedef bool (*hva_handler_t)(struct kvm *kvm, struct kvm_gfn_range *range);
 typedef void (*on_lock_fn_t)(struct kvm *kvm, unsigned long start,
 			     unsigned long end);
 
+typedef void (*on_unlock_fn_t)(struct kvm *kvm);
+
 struct kvm_hva_range {
 	unsigned long start;
 	unsigned long end;
 	pte_t pte;
 	hva_handler_t handler;
 	on_lock_fn_t on_lock;
+	on_unlock_fn_t on_unlock;
 	bool flush_on_ret;
 	bool may_block;
 };
@@ -578,8 +591,11 @@ static __always_inline int __kvm_handle_hva_range(struct kvm *kvm,
 	if (range->flush_on_ret && ret)
 		kvm_flush_remote_tlbs(kvm);
 
-	if (locked)
+	if (locked) {
 		KVM_MMU_UNLOCK(kvm);
+		if (!IS_KVM_NULL_FN(range->on_unlock))
+			range->on_unlock(kvm);
+	}
 
 	srcu_read_unlock(&kvm->srcu, idx);
 
@@ -600,6 +616,7 @@ static __always_inline int kvm_handle_hva_range(struct mmu_notifier *mn,
 		.pte		= pte,
 		.handler	= handler,
 		.on_lock	= (void *)kvm_null_fn,
+		.on_unlock	= (void *)kvm_null_fn,
 		.flush_on_ret	= true,
 		.may_block	= false,
 	};
@@ -619,6 +636,7 @@ static __always_inline int kvm_handle_hva_range_no_flush(struct mmu_notifier *mn
 		.pte		= __pte(0),
 		.handler	= handler,
 		.on_lock	= (void *)kvm_null_fn,
+		.on_unlock	= (void *)kvm_null_fn,
 		.flush_on_ret	= false,
 		.may_block	= false,
 	};
@@ -662,7 +680,7 @@ void kvm_inc_notifier_count(struct kvm *kvm, unsigned long start,
 		kvm->mmu_notifier_range_end = end;
 	} else {
 		/*
-		 * Fully tracking multiple concurrent ranges has dimishing
+		 * Fully tracking multiple concurrent ranges has diminishing
 		 * returns. Keep things simple and just find the minimal range
 		 * which includes the current and new ranges. As there won't be
 		 * enough information to subtract a range after its invalidate
@@ -687,6 +705,7 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
 		.pte		= __pte(0),
 		.handler	= kvm_unmap_gfn_range,
 		.on_lock	= kvm_inc_notifier_count,
+		.on_unlock	= kvm_arch_guest_memory_reclaimed,
 		.flush_on_ret	= true,
 		.may_block	= mmu_notifier_range_blockable(range),
 	};
@@ -741,6 +760,7 @@ static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn,
 		.pte		= __pte(0),
 		.handler	= (void *)kvm_null_fn,
 		.on_lock	= kvm_dec_notifier_count,
+		.on_unlock	= (void *)kvm_null_fn,
 		.flush_on_ret	= false,
 		.may_block	= mmu_notifier_range_blockable(range),
 	};
@@ -813,7 +833,7 @@ static void kvm_mmu_notifier_release(struct mmu_notifier *mn,
 	int idx;
 
 	idx = srcu_read_lock(&kvm->srcu);
-	kvm_arch_flush_shadow_all(kvm);
+	kvm_flush_shadow_all(kvm);
 	srcu_read_unlock(&kvm->srcu, idx);
 }
 
@@ -955,12 +975,6 @@ static int kvm_create_vm_debugfs(struct kvm *kvm, int fd)
 	int kvm_debugfs_num_entries = kvm_vm_stats_header.num_desc +
 				      kvm_vcpu_stats_header.num_desc;
 
-	/*
-	 * Force subsequent debugfs file creations to fail if the VM directory
-	 * is not created.
-	 */
-	kvm->debugfs_dentry = ERR_PTR(-ENOENT);
-
 	if (!debugfs_initialized())
 		return 0;
 
@@ -1082,6 +1096,12 @@ static struct kvm *kvm_create_vm(unsigned long type)
 
 	BUILD_BUG_ON(KVM_MEM_SLOTS_NUM > SHRT_MAX);
 
+	/*
+	 * Force subsequent debugfs file creations to fail if the VM directory
+	 * is not created (by kvm_create_vm_debugfs()).
+	 */
+	kvm->debugfs_dentry = ERR_PTR(-ENOENT);
+
 	if (init_srcu_struct(&kvm->srcu))
 		goto out_err_no_srcu;
 	if (init_srcu_struct(&kvm->irq_srcu))
@@ -1226,7 +1246,7 @@ static void kvm_destroy_vm(struct kvm *kvm)
 	WARN_ON(rcuwait_active(&kvm->mn_memslots_update_rcuwait));
 	kvm->mn_active_invalidate_count = 0;
 #else
-	kvm_arch_flush_shadow_all(kvm);
+	kvm_flush_shadow_all(kvm);
 #endif
 	kvm_arch_destroy_vm(kvm);
 	kvm_destroy_devices(kvm);
@@ -1653,6 +1673,7 @@ static void kvm_invalidate_memslot(struct kvm *kvm,
 	 *	- kvm_is_visible_gfn (mmu_check_root)
 	 */
 	kvm_arch_flush_shadow_memslot(kvm, old);
+	kvm_arch_guest_memory_reclaimed(kvm);
 
 	/* Was released by kvm_swap_active_memslots, reacquire. */
 	mutex_lock(&kvm->slots_arch_lock);
@@ -1800,7 +1821,7 @@ static int kvm_set_memslot(struct kvm *kvm,
 
 	/*
 	 * No need to refresh new->arch, changes after dropping slots_arch_lock
-	 * will directly hit the final, active memsot.  Architectures are
+	 * will directly hit the final, active memslot.  Architectures are
 	 * responsible for knowing that new->arch may be stale.
 	 */
 	kvm_commit_memory_region(kvm, old, new, change);