Merge tag 'kvm-s390-next-20150508' of git://git.kernel.org/pub/scm/linux/kernel/git/kvms390/linux into HEAD

KVM: s390: Fixes and features for 4.2 (kvm/next)

Mostly a bunch of fixes, reworks and optimizations for s390.
There is one new feature (EDAT-2 inside the guest), which boils
down to 2GB pages.

7 files changed, 116 insertions, 77 deletions

diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index d01fc58..444c412 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -80,6 +80,7 @@ struct sca_block {
 #define CPUSTAT_MCDS       0x00000100
 #define CPUSTAT_SM         0x00000080
 #define CPUSTAT_IBS        0x00000040
+#define CPUSTAT_GED2       0x00000010
 #define CPUSTAT_G          0x00000008
 #define CPUSTAT_GED        0x00000004
 #define CPUSTAT_J          0x00000002
@@ -95,7 +96,8 @@ struct kvm_s390_sie_block {
 #define PROG_IN_SIE (1<<0)
 	__u32	prog0c;			/* 0x000c */
 	__u8	reserved10[16];		/* 0x0010 */
-#define PROG_BLOCK_SIE 0x00000001
+#define PROG_BLOCK_SIE	(1<<0)
+#define PROG_REQUEST	(1<<1)
 	atomic_t prog20;		/* 0x0020 */
 	__u8	reserved24[4];		/* 0x0024 */
 	__u64	cputm;			/* 0x0028 */
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index 99b44ac..3238893 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -1005,7 +1005,7 @@ ENTRY(sie64a)
 .Lsie_gmap:
 	lg	%r14,__SF_EMPTY(%r15)		# get control block pointer
 	oi	__SIE_PROG0C+3(%r14),1		# we are going into SIE now
-	tm	__SIE_PROG20+3(%r14),1		# last exit...
+	tm	__SIE_PROG20+3(%r14),3		# last exit...
 	jnz	.Lsie_done
 	LPP	__SF_EMPTY(%r15)		# set guest id
 	sie	0(%r14)
diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
index 9e3779e..7365e8a 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -241,21 +241,6 @@ static int handle_prog(struct kvm_vcpu *vcpu)
 	return kvm_s390_inject_prog_irq(vcpu, &pgm_info);
 }
 
-static int handle_instruction_and_prog(struct kvm_vcpu *vcpu)
-{
-	int rc, rc2;
-
-	vcpu->stat.exit_instr_and_program++;
-	rc = handle_instruction(vcpu);
-	rc2 = handle_prog(vcpu);
-
-	if (rc == -EOPNOTSUPP)
-		vcpu->arch.sie_block->icptcode = 0x04;
-	if (rc)
-		return rc;
-	return rc2;
-}
-
 /**
  * handle_external_interrupt - used for external interruption interceptions
  *
@@ -355,7 +340,6 @@ static const intercept_handler_t intercept_funcs[] = {
 	[0x00 >> 2] = handle_noop,
 	[0x04 >> 2] = handle_instruction,
 	[0x08 >> 2] = handle_prog,
-	[0x0C >> 2] = handle_instruction_and_prog,
 	[0x10 >> 2] = handle_noop,
 	[0x14 >> 2] = handle_external_interrupt,
 	[0x18 >> 2] = handle_noop,
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 9de4726..322ef9c 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -134,6 +134,8 @@ static unsigned long deliverable_irqs(struct kvm_vcpu *vcpu)
 
 	active_mask = pending_local_irqs(vcpu);
 	active_mask |= pending_floating_irqs(vcpu);
+	if (!active_mask)
+		return 0;
 
 	if (psw_extint_disabled(vcpu))
 		active_mask &= ~IRQ_PEND_EXT_MASK;
@@ -941,12 +943,9 @@ int __must_check kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu)
 	if (cpu_timer_irq_pending(vcpu))
 		set_bit(IRQ_PEND_EXT_CPU_TIMER, &li->pending_irqs);
 
-	do {
-		irqs = deliverable_irqs(vcpu);
+	while ((irqs = deliverable_irqs(vcpu)) && !rc) {
 		/* bits are in the order of interrupt priority */
 		irq_type = find_first_bit(&irqs, IRQ_PEND_COUNT);
-		if (irq_type == IRQ_PEND_COUNT)
-			break;
 		if (is_ioirq(irq_type)) {
 			rc = __deliver_io(vcpu, irq_type);
 		} else {
@@ -958,9 +957,7 @@ int __must_check kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu)
 			}
 			rc = func(vcpu);
 		}
-		if (rc)
-			break;
-	} while (!rc);
+	}
 
 	set_intercept_indicators(vcpu);
 
@@ -1061,7 +1058,7 @@ static int __inject_extcall(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
 	if (sclp_has_sigpif())
 		return __inject_extcall_sigpif(vcpu, src_id);
 
-	if (!test_and_set_bit(IRQ_PEND_EXT_EXTERNAL, &li->pending_irqs))
+	if (test_and_set_bit(IRQ_PEND_EXT_EXTERNAL, &li->pending_irqs))
 		return -EBUSY;
 	*extcall = irq->u.extcall;
 	atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
@@ -1340,12 +1337,54 @@ static int __inject_io(struct kvm *kvm, struct kvm_s390_interrupt_info *inti)
 	return 0;
 }
 
-static int __inject_vm(struct kvm *kvm, struct kvm_s390_interrupt_info *inti)
+/*
+ * Find a destination VCPU for a floating irq and kick it.
+ */
+static void __floating_irq_kick(struct kvm *kvm, u64 type)
 {
+	struct kvm_s390_float_interrupt *fi = &kvm->arch.float_int;
 	struct kvm_s390_local_interrupt *li;
+	struct kvm_vcpu *dst_vcpu;
+	int sigcpu, online_vcpus, nr_tries = 0;
+
+	online_vcpus = atomic_read(&kvm->online_vcpus);
+	if (!online_vcpus)
+		return;
+
+	/* find idle VCPUs first, then round robin */
+	sigcpu = find_first_bit(fi->idle_mask, online_vcpus);
+	if (sigcpu == online_vcpus) {
+		do {
+			sigcpu = fi->next_rr_cpu;
+			fi->next_rr_cpu = (fi->next_rr_cpu + 1) % online_vcpus;
+			/* avoid endless loops if all vcpus are stopped */
+			if (nr_tries++ >= online_vcpus)
+				return;
+		} while (is_vcpu_stopped(kvm_get_vcpu(kvm, sigcpu)));
+	}
+	dst_vcpu = kvm_get_vcpu(kvm, sigcpu);
+
+	/* make the VCPU drop out of the SIE, or wake it up if sleeping */
+	li = &dst_vcpu->arch.local_int;
+	spin_lock(&li->lock);
+	switch (type) {
+	case KVM_S390_MCHK:
+		atomic_set_mask(CPUSTAT_STOP_INT, li->cpuflags);
+		break;
+	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
+		atomic_set_mask(CPUSTAT_IO_INT, li->cpuflags);
+		break;
+	default:
+		atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
+		break;
+	}
+	spin_unlock(&li->lock);
+	kvm_s390_vcpu_wakeup(dst_vcpu);
+}
+
+static int __inject_vm(struct kvm *kvm, struct kvm_s390_interrupt_info *inti)
+{
 	struct kvm_s390_float_interrupt *fi;
-	struct kvm_vcpu *dst_vcpu = NULL;
-	int sigcpu;
 	u64 type = READ_ONCE(inti->type);
 	int rc;
 
@@ -1373,32 +1412,8 @@ static int __inject_vm(struct kvm *kvm, struct kvm_s390_interrupt_info *inti)
 	if (rc)
 		return rc;
 
-	sigcpu = find_first_bit(fi->idle_mask, KVM_MAX_VCPUS);
-	if (sigcpu == KVM_MAX_VCPUS) {
-		do {
-			sigcpu = fi->next_rr_cpu++;
-			if (sigcpu == KVM_MAX_VCPUS)
-				sigcpu = fi->next_rr_cpu = 0;
-		} while (kvm_get_vcpu(kvm, sigcpu) == NULL);
-	}
-	dst_vcpu = kvm_get_vcpu(kvm, sigcpu);
-	li = &dst_vcpu->arch.local_int;
-	spin_lock(&li->lock);
-	switch (type) {
-	case KVM_S390_MCHK:
-		atomic_set_mask(CPUSTAT_STOP_INT, li->cpuflags);
-		break;
-	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
-		atomic_set_mask(CPUSTAT_IO_INT, li->cpuflags);
-		break;
-	default:
-		atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
-		break;
-	}
-	spin_unlock(&li->lock);
-	kvm_s390_vcpu_wakeup(kvm_get_vcpu(kvm, sigcpu));
+	__floating_irq_kick(kvm, type);
 	return 0;
-
 }
 
 int kvm_s390_inject_vm(struct kvm *kvm,
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 2be391b..d461f8a 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -110,7 +110,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 /* upper facilities limit for kvm */
 unsigned long kvm_s390_fac_list_mask[] = {
 	0xffe6fffbfcfdfc40UL,
-	0x005c800000000000UL,
+	0x005e800000000000UL,
 };
 
 unsigned long kvm_s390_fac_list_mask_size(void)
@@ -454,10 +454,10 @@ static int kvm_s390_set_tod_low(struct kvm *kvm, struct kvm_device_attr *attr)
 
 	mutex_lock(&kvm->lock);
 	kvm->arch.epoch = gtod - host_tod;
-	kvm_for_each_vcpu(vcpu_idx, cur_vcpu, kvm) {
+	kvm_s390_vcpu_block_all(kvm);
+	kvm_for_each_vcpu(vcpu_idx, cur_vcpu, kvm)
 		cur_vcpu->arch.sie_block->epoch = kvm->arch.epoch;
-		exit_sie(cur_vcpu);
-	}
+	kvm_s390_vcpu_unblock_all(kvm);
 	mutex_unlock(&kvm->lock);
 	return 0;
 }
@@ -1311,8 +1311,13 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 
 	atomic_set(&vcpu->arch.sie_block->cpuflags, CPUSTAT_ZARCH |
 						    CPUSTAT_SM |
-						    CPUSTAT_STOPPED |
-						    CPUSTAT_GED);
+						    CPUSTAT_STOPPED);
+
+	if (test_kvm_facility(vcpu->kvm, 78))
+		atomic_set_mask(CPUSTAT_GED2, &vcpu->arch.sie_block->cpuflags);
+	else if (test_kvm_facility(vcpu->kvm, 8))
+		atomic_set_mask(CPUSTAT_GED, &vcpu->arch.sie_block->cpuflags);
+
 	kvm_s390_vcpu_setup_model(vcpu);
 
 	vcpu->arch.sie_block->ecb   = 6;
@@ -1409,16 +1414,26 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
 	return kvm_s390_vcpu_has_irq(vcpu, 0);
 }
 
-void s390_vcpu_block(struct kvm_vcpu *vcpu)
+void kvm_s390_vcpu_block(struct kvm_vcpu *vcpu)
 {
 	atomic_set_mask(PROG_BLOCK_SIE, &vcpu->arch.sie_block->prog20);
 }
 
-void s390_vcpu_unblock(struct kvm_vcpu *vcpu)
+void kvm_s390_vcpu_unblock(struct kvm_vcpu *vcpu)
 {
 	atomic_clear_mask(PROG_BLOCK_SIE, &vcpu->arch.sie_block->prog20);
 }
 
+static void kvm_s390_vcpu_request(struct kvm_vcpu *vcpu)
+{
+	atomic_set_mask(PROG_REQUEST, &vcpu->arch.sie_block->prog20);
+}
+
+static void kvm_s390_vcpu_request_handled(struct kvm_vcpu *vcpu)
+{
+	atomic_clear_mask(PROG_REQUEST, &vcpu->arch.sie_block->prog20);
+}
+
 /*
  * Kick a guest cpu out of SIE and wait until SIE is not running.
  * If the CPU is not running (e.g. waiting as idle) the function will
@@ -1430,10 +1445,11 @@ void exit_sie(struct kvm_vcpu *vcpu)
 		cpu_relax();
 }
 
-/* Kick a guest cpu out of SIE and prevent SIE-reentry */
-void exit_sie_sync(struct kvm_vcpu *vcpu)
+/* Kick a guest cpu out of SIE to process a request synchronously */
+void kvm_s390_sync_request(int req, struct kvm_vcpu *vcpu)
 {
-	s390_vcpu_block(vcpu);
+	kvm_make_request(req, vcpu);
+	kvm_s390_vcpu_request(vcpu);
 	exit_sie(vcpu);
 }
 
@@ -1447,8 +1463,7 @@ static void kvm_gmap_notifier(struct gmap *gmap, unsigned long address)
 		/* match against both prefix pages */
 		if (kvm_s390_get_prefix(vcpu) == (address & ~0x1000UL)) {
 			VCPU_EVENT(vcpu, 2, "gmap notifier for %lx", address);
-			kvm_make_request(KVM_REQ_MMU_RELOAD, vcpu);
-			exit_sie_sync(vcpu);
+			kvm_s390_sync_request(KVM_REQ_MMU_RELOAD, vcpu);
 		}
 	}
 }
@@ -1720,8 +1735,10 @@ static bool ibs_enabled(struct kvm_vcpu *vcpu)
 
 static int kvm_s390_handle_requests(struct kvm_vcpu *vcpu)
 {
+	if (!vcpu->requests)
+		return 0;
 retry:
-	s390_vcpu_unblock(vcpu);
+	kvm_s390_vcpu_request_handled(vcpu);
 	/*
 	 * We use MMU_RELOAD just to re-arm the ipte notifier for the
 	 * guest prefix page. gmap_ipte_notify will wait on the ptl lock.
@@ -2208,8 +2225,7 @@ int kvm_s390_vcpu_store_adtl_status(struct kvm_vcpu *vcpu, unsigned long addr)
 static void __disable_ibs_on_vcpu(struct kvm_vcpu *vcpu)
 {
 	kvm_check_request(KVM_REQ_ENABLE_IBS, vcpu);
-	kvm_make_request(KVM_REQ_DISABLE_IBS, vcpu);
-	exit_sie_sync(vcpu);
+	kvm_s390_sync_request(KVM_REQ_DISABLE_IBS, vcpu);
 }
 
 static void __disable_ibs_on_all_vcpus(struct kvm *kvm)
@@ -2225,8 +2241,7 @@ static void __disable_ibs_on_all_vcpus(struct kvm *kvm)
 static void __enable_ibs_on_vcpu(struct kvm_vcpu *vcpu)
 {
 	kvm_check_request(KVM_REQ_DISABLE_IBS, vcpu);
-	kvm_make_request(KVM_REQ_ENABLE_IBS, vcpu);
-	exit_sie_sync(vcpu);
+	kvm_s390_sync_request(KVM_REQ_ENABLE_IBS, vcpu);
 }
 
 void kvm_s390_vcpu_start(struct kvm_vcpu *vcpu)
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index ca108b9..c570478 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -211,10 +211,10 @@ int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr);
 int kvm_s390_vcpu_store_adtl_status(struct kvm_vcpu *vcpu, unsigned long addr);
 void kvm_s390_vcpu_start(struct kvm_vcpu *vcpu);
 void kvm_s390_vcpu_stop(struct kvm_vcpu *vcpu);
-void s390_vcpu_block(struct kvm_vcpu *vcpu);
-void s390_vcpu_unblock(struct kvm_vcpu *vcpu);
+void kvm_s390_vcpu_block(struct kvm_vcpu *vcpu);
+void kvm_s390_vcpu_unblock(struct kvm_vcpu *vcpu);
 void exit_sie(struct kvm_vcpu *vcpu);
-void exit_sie_sync(struct kvm_vcpu *vcpu);
+void kvm_s390_sync_request(int req, struct kvm_vcpu *vcpu);
 int kvm_s390_vcpu_setup_cmma(struct kvm_vcpu *vcpu);
 void kvm_s390_vcpu_unsetup_cmma(struct kvm_vcpu *vcpu);
 /* is cmma enabled */
@@ -228,6 +228,25 @@ int kvm_s390_handle_diag(struct kvm_vcpu *vcpu);
 int kvm_s390_inject_prog_irq(struct kvm_vcpu *vcpu,
 			     struct kvm_s390_pgm_info *pgm_info);
 
+static inline void kvm_s390_vcpu_block_all(struct kvm *kvm)
+{
+	int i;
+	struct kvm_vcpu *vcpu;
+
+	WARN_ON(!mutex_is_locked(&kvm->lock));
+	kvm_for_each_vcpu(i, vcpu, kvm)
+		kvm_s390_vcpu_block(vcpu);
+}
+
+static inline void kvm_s390_vcpu_unblock_all(struct kvm *kvm)
+{
+	int i;
+	struct kvm_vcpu *vcpu;
+
+	kvm_for_each_vcpu(i, vcpu, kvm)
+		kvm_s390_vcpu_unblock(vcpu);
+}
+
 /**
  * kvm_s390_inject_prog_cond - conditionally inject a program check
  * @vcpu: virtual cpu
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index d22d8ee..ad42422 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -698,10 +698,14 @@ static int handle_pfmf(struct kvm_vcpu *vcpu)
 	case 0x00001000:
 		end = (start + (1UL << 20)) & ~((1UL << 20) - 1);
 		break;
-	/* We dont support EDAT2
 	case 0x00002000:
+		/* only support 2G frame size if EDAT2 is available and we are
+		   not in 24-bit addressing mode */
+		if (!test_kvm_facility(vcpu->kvm, 78) ||
+		    psw_bits(vcpu->arch.sie_block->gpsw).eaba == PSW_AMODE_24BIT)
+			return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
 		end = (start + (1UL << 31)) & ~((1UL << 31) - 1);
-		break;*/
+		break;
 	default:
 		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
 	}