1 files changed, 65 insertions, 100 deletions

diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 14a18ba5ff2c..2296b1ff1e02 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -295,7 +295,7 @@ static int kvm_clock_sync(struct notifier_block *notifier, unsigned long val,
 {
 	struct kvm *kvm;
 	struct kvm_vcpu *vcpu;
-	int i;
+	unsigned long i;
 	unsigned long long *delta = v;
 
 	list_for_each_entry(kvm, &vm_list, vm_list) {
@@ -682,7 +682,7 @@ out:
 
 static void icpt_operexc_on_all_vcpus(struct kvm *kvm)
 {
-	unsigned int i;
+	unsigned long i;
 	struct kvm_vcpu *vcpu;
 
 	kvm_for_each_vcpu(i, vcpu, kvm) {
@@ -936,7 +936,7 @@ static void kvm_s390_vcpu_crypto_setup(struct kvm_vcpu *vcpu);
 void kvm_s390_vcpu_crypto_reset_all(struct kvm *kvm)
 {
 	struct kvm_vcpu *vcpu;
-	int i;
+	unsigned long i;
 
 	kvm_s390_vcpu_block_all(kvm);
 
@@ -1021,7 +1021,7 @@ static int kvm_s390_vm_set_crypto(struct kvm *kvm, struct kvm_device_attr *attr)
 
 static void kvm_s390_sync_request_broadcast(struct kvm *kvm, int req)
 {
-	int cx;
+	unsigned long cx;
 	struct kvm_vcpu *vcpu;
 
 	kvm_for_each_vcpu(cx, vcpu, kvm)
@@ -1037,13 +1037,13 @@ static int kvm_s390_vm_start_migration(struct kvm *kvm)
 	struct kvm_memory_slot *ms;
 	struct kvm_memslots *slots;
 	unsigned long ram_pages = 0;
-	int slotnr;
+	int bkt;
 
 	/* migration mode already enabled */
 	if (kvm->arch.migration_mode)
 		return 0;
 	slots = kvm_memslots(kvm);
-	if (!slots || !slots->used_slots)
+	if (!slots || kvm_memslots_empty(slots))
 		return -EINVAL;
 
 	if (!kvm->arch.use_cmma) {
@@ -1051,8 +1051,7 @@ static int kvm_s390_vm_start_migration(struct kvm *kvm)
 		return 0;
 	}
 	/* mark all the pages in active slots as dirty */
-	for (slotnr = 0; slotnr < slots->used_slots; slotnr++) {
-		ms = slots->memslots + slotnr;
+	kvm_for_each_memslot(ms, bkt, slots) {
 		if (!ms->dirty_bitmap)
 			return -EINVAL;
 		/*
@@ -1943,41 +1942,6 @@ out:
 /* for consistency */
 #define KVM_S390_CMMA_SIZE_MAX ((u32)KVM_S390_SKEYS_MAX)
 
-/*
- * Similar to gfn_to_memslot, but returns the index of a memslot also when the
- * address falls in a hole. In that case the index of one of the memslots
- * bordering the hole is returned.
- */
-static int gfn_to_memslot_approx(struct kvm_memslots *slots, gfn_t gfn)
-{
-	int start = 0, end = slots->used_slots;
-	int slot = atomic_read(&slots->last_used_slot);
-	struct kvm_memory_slot *memslots = slots->memslots;
-
-	if (gfn >= memslots[slot].base_gfn &&
-	    gfn < memslots[slot].base_gfn + memslots[slot].npages)
-		return slot;
-
-	while (start < end) {
-		slot = start + (end - start) / 2;
-
-		if (gfn >= memslots[slot].base_gfn)
-			end = slot;
-		else
-			start = slot + 1;
-	}
-
-	if (start >= slots->used_slots)
-		return slots->used_slots - 1;
-
-	if (gfn >= memslots[start].base_gfn &&
-	    gfn < memslots[start].base_gfn + memslots[start].npages) {
-		atomic_set(&slots->last_used_slot, start);
-	}
-
-	return start;
-}
-
 static int kvm_s390_peek_cmma(struct kvm *kvm, struct kvm_s390_cmma_log *args,
 			      u8 *res, unsigned long bufsize)
 {
@@ -2001,27 +1965,32 @@ static int kvm_s390_peek_cmma(struct kvm *kvm, struct kvm_s390_cmma_log *args,
 	return 0;
 }
 
+static struct kvm_memory_slot *gfn_to_memslot_approx(struct kvm_memslots *slots,
+						     gfn_t gfn)
+{
+	return ____gfn_to_memslot(slots, gfn, true);
+}
+
 static unsigned long kvm_s390_next_dirty_cmma(struct kvm_memslots *slots,
 					      unsigned long cur_gfn)
 {
-	int slotidx = gfn_to_memslot_approx(slots, cur_gfn);
-	struct kvm_memory_slot *ms = slots->memslots + slotidx;
+	struct kvm_memory_slot *ms = gfn_to_memslot_approx(slots, cur_gfn);
 	unsigned long ofs = cur_gfn - ms->base_gfn;
+	struct rb_node *mnode = &ms->gfn_node[slots->node_idx];
 
 	if (ms->base_gfn + ms->npages <= cur_gfn) {
-		slotidx--;
+		mnode = rb_next(mnode);
 		/* If we are above the highest slot, wrap around */
-		if (slotidx < 0)
-			slotidx = slots->used_slots - 1;
+		if (!mnode)
+			mnode = rb_first(&slots->gfn_tree);
 
-		ms = slots->memslots + slotidx;
+		ms = container_of(mnode, struct kvm_memory_slot, gfn_node[slots->node_idx]);
 		ofs = 0;
 	}
 	ofs = find_next_bit(kvm_second_dirty_bitmap(ms), ms->npages, ofs);
-	while ((slotidx > 0) && (ofs >= ms->npages)) {
-		slotidx--;
-		ms = slots->memslots + slotidx;
-		ofs = find_next_bit(kvm_second_dirty_bitmap(ms), ms->npages, 0);
+	while (ofs >= ms->npages && (mnode = rb_next(mnode))) {
+		ms = container_of(mnode, struct kvm_memory_slot, gfn_node[slots->node_idx]);
+		ofs = find_first_bit(kvm_second_dirty_bitmap(ms), ms->npages);
 	}
 	return ms->base_gfn + ofs;
 }
@@ -2033,7 +2002,7 @@ static int kvm_s390_get_cmma(struct kvm *kvm, struct kvm_s390_cmma_log *args,
 	struct kvm_memslots *slots = kvm_memslots(kvm);
 	struct kvm_memory_slot *ms;
 
-	if (unlikely(!slots->used_slots))
+	if (unlikely(kvm_memslots_empty(slots)))
 		return 0;
 
 	cur_gfn = kvm_s390_next_dirty_cmma(slots, args->start_gfn);
@@ -2043,7 +2012,7 @@ static int kvm_s390_get_cmma(struct kvm *kvm, struct kvm_s390_cmma_log *args,
 	if (!ms)
 		return 0;
 	next_gfn = kvm_s390_next_dirty_cmma(slots, cur_gfn + 1);
-	mem_end = slots->memslots[0].base_gfn + slots->memslots[0].npages;
+	mem_end = kvm_s390_get_gfn_end(slots);
 
 	while (args->count < bufsize) {
 		hva = gfn_to_hva(kvm, cur_gfn);
@@ -2206,7 +2175,7 @@ static int kvm_s390_cpus_from_pv(struct kvm *kvm, u16 *rcp, u16 *rrcp)
 	struct kvm_vcpu *vcpu;
 	u16 rc, rrc;
 	int ret = 0;
-	int i;
+	unsigned long i;
 
 	/*
 	 * We ignore failures and try to destroy as many CPUs as possible.
@@ -2230,7 +2199,8 @@ static int kvm_s390_cpus_from_pv(struct kvm *kvm, u16 *rcp, u16 *rrcp)
 
 static int kvm_s390_cpus_to_pv(struct kvm *kvm, u16 *rc, u16 *rrc)
 {
-	int i, r = 0;
+	unsigned long i;
+	int r = 0;
 	u16 dummy;
 
 	struct kvm_vcpu *vcpu;
@@ -2821,27 +2791,11 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 	free_page((unsigned long)(vcpu->arch.sie_block));
 }
 
-static void kvm_free_vcpus(struct kvm *kvm)
-{
-	unsigned int i;
-	struct kvm_vcpu *vcpu;
-
-	kvm_for_each_vcpu(i, vcpu, kvm)
-		kvm_vcpu_destroy(vcpu);
-
-	mutex_lock(&kvm->lock);
-	for (i = 0; i < atomic_read(&kvm->online_vcpus); i++)
-		kvm->vcpus[i] = NULL;
-
-	atomic_set(&kvm->online_vcpus, 0);
-	mutex_unlock(&kvm->lock);
-}
-
 void kvm_arch_destroy_vm(struct kvm *kvm)
 {
 	u16 rc, rrc;
 
-	kvm_free_vcpus(kvm);
+	kvm_destroy_vcpus(kvm);
 	sca_dispose(kvm);
 	kvm_s390_gisa_destroy(kvm);
 	/*
@@ -2945,7 +2899,7 @@ static int sca_switch_to_extended(struct kvm *kvm)
 	struct bsca_block *old_sca = kvm->arch.sca;
 	struct esca_block *new_sca;
 	struct kvm_vcpu *vcpu;
-	unsigned int vcpu_idx;
+	unsigned long vcpu_idx;
 	u32 scaol, scaoh;
 
 	if (kvm->arch.use_esca)
@@ -3427,7 +3381,7 @@ static void kvm_gmap_notifier(struct gmap *gmap, unsigned long start,
 	struct kvm *kvm = gmap->private;
 	struct kvm_vcpu *vcpu;
 	unsigned long prefix;
-	int i;
+	unsigned long i;
 
 	if (gmap_is_shadow(gmap))
 		return;
@@ -3449,7 +3403,7 @@ bool kvm_arch_no_poll(struct kvm_vcpu *vcpu)
 {
 	/* do not poll with more than halt_poll_max_steal percent of steal time */
 	if (S390_lowcore.avg_steal_timer * 100 / (TICK_USEC << 12) >=
-	    halt_poll_max_steal) {
+	    READ_ONCE(halt_poll_max_steal)) {
 		vcpu->stat.halt_no_poll_steal++;
 		return true;
 	}
@@ -3920,7 +3874,7 @@ void kvm_s390_set_tod_clock(struct kvm *kvm,
 {
 	struct kvm_vcpu *vcpu;
 	union tod_clock clk;
-	int i;
+	unsigned long i;
 
 	mutex_lock(&kvm->lock);
 	preempt_disable();
@@ -4552,7 +4506,7 @@ static void __disable_ibs_on_vcpu(struct kvm_vcpu *vcpu)
 
 static void __disable_ibs_on_all_vcpus(struct kvm *kvm)
 {
-	unsigned int i;
+	unsigned long i;
 	struct kvm_vcpu *vcpu;
 
 	kvm_for_each_vcpu(i, vcpu, kvm) {
@@ -4590,7 +4544,7 @@ int kvm_s390_vcpu_start(struct kvm_vcpu *vcpu)
 	}
 
 	for (i = 0; i < online_vcpus; i++) {
-		if (!is_vcpu_stopped(vcpu->kvm->vcpus[i]))
+		if (!is_vcpu_stopped(kvm_get_vcpu(vcpu->kvm, i)))
 			started_vcpus++;
 	}
 
@@ -4645,16 +4599,23 @@ int kvm_s390_vcpu_stop(struct kvm_vcpu *vcpu)
 		}
 	}
 
-	/* SIGP STOP and SIGP STOP AND STORE STATUS has been fully processed */
+	/*
+	 * Set the VCPU to STOPPED and THEN clear the interrupt flag,
+	 * now that the SIGP STOP and SIGP STOP AND STORE STATUS orders
+	 * have been fully processed. This will ensure that the VCPU
+	 * is kept BUSY if another VCPU is inquiring with SIGP SENSE.
+	 */
+	kvm_s390_set_cpuflags(vcpu, CPUSTAT_STOPPED);
 	kvm_s390_clear_stop_irq(vcpu);
 
-	kvm_s390_set_cpuflags(vcpu, CPUSTAT_STOPPED);
 	__disable_ibs_on_vcpu(vcpu);
 
 	for (i = 0; i < online_vcpus; i++) {
-		if (!is_vcpu_stopped(vcpu->kvm->vcpus[i])) {
+		struct kvm_vcpu *tmp = kvm_get_vcpu(vcpu->kvm, i);
+
+		if (!is_vcpu_stopped(tmp)) {
 			started_vcpus++;
-			started_vcpu = vcpu->kvm->vcpus[i];
+			started_vcpu = tmp;
 		}
 	}
 
@@ -4706,6 +4667,8 @@ static long kvm_s390_guest_sida_op(struct kvm_vcpu *vcpu,
 		return -EINVAL;
 	if (mop->size + mop->sida_offset > sida_size(vcpu->arch.sie_block))
 		return -E2BIG;
+	if (!kvm_s390_pv_cpu_is_protected(vcpu))
+		return -EINVAL;
 
 	switch (mop->op) {
 	case KVM_S390_MEMOP_SIDA_READ:
@@ -5020,32 +4983,38 @@ vm_fault_t kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf)
 
 /* Section: memory related */
 int kvm_arch_prepare_memory_region(struct kvm *kvm,
-				   struct kvm_memory_slot *memslot,
-				   const struct kvm_userspace_memory_region *mem,
+				   const struct kvm_memory_slot *old,
+				   struct kvm_memory_slot *new,
 				   enum kvm_mr_change change)
 {
+	gpa_t size;
+
+	/* When we are protected, we should not change the memory slots */
+	if (kvm_s390_pv_get_handle(kvm))
+		return -EINVAL;
+
+	if (change == KVM_MR_DELETE || change == KVM_MR_FLAGS_ONLY)
+		return 0;
+
 	/* A few sanity checks. We can have memory slots which have to be
 	   located/ended at a segment boundary (1MB). The memory in userland is
 	   ok to be fragmented into various different vmas. It is okay to mmap()
 	   and munmap() stuff in this slot after doing this call at any time */
 
-	if (mem->userspace_addr & 0xffffful)
+	if (new->userspace_addr & 0xffffful)
 		return -EINVAL;
 
-	if (mem->memory_size & 0xffffful)
+	size = new->npages * PAGE_SIZE;
+	if (size & 0xffffful)
 		return -EINVAL;
 
-	if (mem->guest_phys_addr + mem->memory_size > kvm->arch.mem_limit)
+	if ((new->base_gfn * PAGE_SIZE) + size > kvm->arch.mem_limit)
 		return -EINVAL;
 
-	/* When we are protected, we should not change the memory slots */
-	if (kvm_s390_pv_get_handle(kvm))
-		return -EINVAL;
 	return 0;
 }
 
 void kvm_arch_commit_memory_region(struct kvm *kvm,
-				const struct kvm_userspace_memory_region *mem,
 				struct kvm_memory_slot *old,
 				const struct kvm_memory_slot *new,
 				enum kvm_mr_change change)
@@ -5064,8 +5033,9 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 			break;
 		fallthrough;
 	case KVM_MR_CREATE:
-		rc = gmap_map_segment(kvm->arch.gmap, mem->userspace_addr,
-				      mem->guest_phys_addr, mem->memory_size);
+		rc = gmap_map_segment(kvm->arch.gmap, new->userspace_addr,
+				      new->base_gfn * PAGE_SIZE,
+				      new->npages * PAGE_SIZE);
 		break;
 	case KVM_MR_FLAGS_ONLY:
 		break;
@@ -5084,11 +5054,6 @@ static inline unsigned long nonhyp_mask(int i)
 	return 0x0000ffffffffffffUL >> (nonhyp_fai << 4);
 }
 
-void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu)
-{
-	vcpu->valid_wakeup = false;
-}
-
 static int __init kvm_s390_init(void)
 {
 	int i;