Merge tag 'kvm-s390-next-6.19-1' of https://git.kernel.org/pub/scm/linux/kernel/git/kvms390/linux into HEAD

- SCA rework
- VIRT_XFER_TO_GUEST_WORK support
- Operation exception forwarding support
- Cleanups

Author: bonzini

Documentation/virt/kvm/api.rst

@@ -7855,7 +7855,7 @@ where 0xff represents CPUs 0-7 in cluster 0.
 :Architectures: s390
 :Parameters: none
 
-With this capability enabled, all illegal instructions 0x0000 (2 bytes) will
+With this capability enabled, the illegal instruction 0x0000 (2 bytes) will
 be intercepted and forwarded to user space. User space can use this
 mechanism e.g. to realize 2-byte software breakpoints. The kernel will
 not inject an operating exception for these instructions, user space has
@@ -8727,7 +8727,7 @@ given VM.
 When this capability is enabled, KVM resets the VCPU when setting
 MP_STATE_INIT_RECEIVED through IOCTL.  The original MP_STATE is preserved.
 
-7.43 KVM_CAP_ARM_CACHEABLE_PFNMAP_SUPPORTED
+7.44 KVM_CAP_ARM_CACHEABLE_PFNMAP_SUPPORTED
 -------------------------------------------
 
 :Architectures: arm64
@@ -8750,6 +8750,21 @@ When this capability is enabled, KVM may exit to userspace for SEAs taken to
 EL2 resulting from a guest access. See ``KVM_EXIT_ARM_SEA`` for more
 information.
 
+7.46 KVM_CAP_S390_USER_OPEREXEC
+-------------------------------
+
+:Architectures: s390
+:Parameters: none
+
+When this capability is enabled KVM forwards all operation exceptions
+that it doesn't handle itself to user space. This also includes the
+0x0000 instructions managed by KVM_CAP_S390_USER_INSTR0. This is
+helpful if user space wants to emulate instructions which are not
+(yet) implemented in hardware.
+
+This capability can be enabled dynamically even if VCPUs were already
+created and are running.
+
 8. Other capabilities.
 ======================
 

arch/s390/include/asm/kvm_host.h

@@ -146,6 +146,7 @@ struct kvm_vcpu_stat {
 	u64 instruction_diagnose_500;
 	u64 instruction_diagnose_other;
 	u64 pfault_sync;
+	u64 signal_exits;
 };
 
 #define PGM_OPERATION			0x01
@@ -631,10 +632,8 @@ struct kvm_s390_pv {
 	struct mmu_notifier mmu_notifier;
 };
 
-struct kvm_arch{
-	void *sca;
-	int use_esca;
-	rwlock_t sca_lock;
+struct kvm_arch {
+	struct esca_block *sca;
 	debug_info_t *dbf;
 	struct kvm_s390_float_interrupt float_int;
 	struct kvm_device *flic;
@@ -650,6 +649,7 @@ struct kvm_arch{
 	int user_sigp;
 	int user_stsi;
 	int user_instr0;
+	int user_operexec;
 	struct s390_io_adapter *adapters[MAX_S390_IO_ADAPTERS];
 	wait_queue_head_t ipte_wq;
 	int ipte_lock_count;

arch/s390/include/asm/stacktrace.h

@@ -66,6 +66,7 @@ struct stack_frame {
 			unsigned long sie_flags;
 			unsigned long sie_control_block_phys;
 			unsigned long sie_guest_asce;
+			unsigned long sie_irq;
 		};
 	};
 	unsigned long gprs[10];

arch/s390/kernel/asm-offsets.c

@@ -64,6 +64,7 @@ int main(void)
 	OFFSET(__SF_SIE_FLAGS, stack_frame, sie_flags);
 	OFFSET(__SF_SIE_CONTROL_PHYS, stack_frame, sie_control_block_phys);
 	OFFSET(__SF_SIE_GUEST_ASCE, stack_frame, sie_guest_asce);
+	OFFSET(__SF_SIE_IRQ, stack_frame, sie_irq);
 	DEFINE(STACK_FRAME_OVERHEAD, sizeof(struct stack_frame));
 	BLANK();
 	OFFSET(__SFUSER_BACKCHAIN, stack_frame_user, back_chain);

arch/s390/kernel/entry.S

@@ -189,6 +189,7 @@ SYM_FUNC_START(__sie64a)
 	mvc	__SF_SIE_FLAGS(8,%r15),__TI_flags(%r14) # copy thread flags
 	lmg	%r0,%r13,0(%r4)			# load guest gprs 0-13
 	mvi	__TI_sie(%r14),1
+	stosm	__SF_SIE_IRQ(%r15),0x03		# enable interrupts
 	lctlg	%c1,%c1,__SF_SIE_GUEST_ASCE(%r15) # load primary asce
 	lg	%r14,__SF_SIE_CONTROL(%r15)	# get control block pointer
 	oi	__SIE_PROG0C+3(%r14),1		# we are going into SIE now
@@ -212,6 +213,7 @@ SYM_FUNC_START(__sie64a)
 	lg	%r14,__LC_CURRENT(%r14)
 	mvi	__TI_sie(%r14),0
 SYM_INNER_LABEL(sie_exit, SYM_L_GLOBAL)
+	stnsm	__SF_SIE_IRQ(%r15),0xfc		# disable interrupts
 	lg	%r14,__SF_SIE_SAVEAREA(%r15)	# load guest register save area
 	stmg	%r0,%r13,0(%r14)		# save guest gprs 0-13
 	xgr	%r0,%r0				# clear guest registers to

arch/s390/kvm/Kconfig

@@ -29,6 +29,7 @@ config KVM
 	select HAVE_KVM_NO_POLL
 	select KVM_VFIO
 	select MMU_NOTIFIER
+	select VIRT_XFER_TO_GUEST_WORK
 	help
 	  Support hosting paravirtualized guest machines using the SIE
 	  virtualization capability on the mainframe. This should work

arch/s390/kvm/gaccess.c

@@ -109,14 +109,9 @@ struct aste {
 
 int ipte_lock_held(struct kvm *kvm)
 {
-	if (sclp.has_siif) {
-		int rc;
+	if (sclp.has_siif)
+		return kvm->arch.sca->ipte_control.kh != 0;
 
-		read_lock(&kvm->arch.sca_lock);
-		rc = kvm_s390_get_ipte_control(kvm)->kh != 0;
-		read_unlock(&kvm->arch.sca_lock);
-		return rc;
-	}
 	return kvm->arch.ipte_lock_count != 0;
 }
 
@@ -129,19 +124,16 @@ static void ipte_lock_simple(struct kvm *kvm)
 	if (kvm->arch.ipte_lock_count > 1)
 		goto out;
 retry:
-	read_lock(&kvm->arch.sca_lock);
-	ic = kvm_s390_get_ipte_control(kvm);
+	ic = &kvm->arch.sca->ipte_control;
 	old = READ_ONCE(*ic);
 	do {
 		if (old.k) {
-			read_unlock(&kvm->arch.sca_lock);
 			cond_resched();
 			goto retry;
 		}
 		new = old;
 		new.k = 1;
 	} while (!try_cmpxchg(&ic->val, &old.val, new.val));
-	read_unlock(&kvm->arch.sca_lock);
 out:
 	mutex_unlock(&kvm->arch.ipte_mutex);
 }
@@ -154,14 +146,12 @@ static void ipte_unlock_simple(struct kvm *kvm)
 	kvm->arch.ipte_lock_count--;
 	if (kvm->arch.ipte_lock_count)
 		goto out;
-	read_lock(&kvm->arch.sca_lock);
-	ic = kvm_s390_get_ipte_control(kvm);
+	ic = &kvm->arch.sca->ipte_control;
 	old = READ_ONCE(*ic);
 	do {
 		new = old;
 		new.k = 0;
 	} while (!try_cmpxchg(&ic->val, &old.val, new.val));
-	read_unlock(&kvm->arch.sca_lock);
 	wake_up(&kvm->arch.ipte_wq);
 out:
 	mutex_unlock(&kvm->arch.ipte_mutex);
@@ -172,36 +162,31 @@ static void ipte_lock_siif(struct kvm *kvm)
 	union ipte_control old, new, *ic;
 
 retry:
-	read_lock(&kvm->arch.sca_lock);
-	ic = kvm_s390_get_ipte_control(kvm);
+	ic = &kvm->arch.sca->ipte_control;
 	old = READ_ONCE(*ic);
 	do {
 		if (old.kg) {
-			read_unlock(&kvm->arch.sca_lock);
 			cond_resched();
 			goto retry;
 		}
 		new = old;
 		new.k = 1;
 		new.kh++;
 	} while (!try_cmpxchg(&ic->val, &old.val, new.val));
-	read_unlock(&kvm->arch.sca_lock);
 }
 
 static void ipte_unlock_siif(struct kvm *kvm)
 {
 	union ipte_control old, new, *ic;
 
-	read_lock(&kvm->arch.sca_lock);
-	ic = kvm_s390_get_ipte_control(kvm);
+	ic = &kvm->arch.sca->ipte_control;
 	old = READ_ONCE(*ic);
 	do {
 		new = old;
 		new.kh--;
 		if (!new.kh)
 			new.k = 0;
 	} while (!try_cmpxchg(&ic->val, &old.val, new.val));
-	read_unlock(&kvm->arch.sca_lock);
 	if (!new.kh)
 		wake_up(&kvm->arch.ipte_wq);
 }

arch/s390/kvm/intercept.c

@@ -471,6 +471,9 @@ static int handle_operexc(struct kvm_vcpu *vcpu)
 	if (vcpu->arch.sie_block->ipa == 0xb256)
 		return handle_sthyi(vcpu);
 
+	if (vcpu->kvm->arch.user_operexec)
+		return -EOPNOTSUPP;
+
 	if (vcpu->arch.sie_block->ipa == 0 && vcpu->kvm->arch.user_instr0)
 		return -EOPNOTSUPP;
 	rc = read_guest_lc(vcpu, __LC_PGM_NEW_PSW, &newpsw, sizeof(psw_t));

arch/s390/kvm/interrupt.c

@@ -45,70 +45,34 @@ static struct kvm_s390_gib *gib;
 /* handle external calls via sigp interpretation facility */
 static int sca_ext_call_pending(struct kvm_vcpu *vcpu, int *src_id)
 {
-	int c, scn;
+	struct esca_block *sca = vcpu->kvm->arch.sca;
+	union esca_sigp_ctrl sigp_ctrl = sca->cpu[vcpu->vcpu_id].sigp_ctrl;
 
 	if (!kvm_s390_test_cpuflags(vcpu, CPUSTAT_ECALL_PEND))
 		return 0;
 
 	BUG_ON(!kvm_s390_use_sca_entries());
-	read_lock(&vcpu->kvm->arch.sca_lock);
-	if (vcpu->kvm->arch.use_esca) {
-		struct esca_block *sca = vcpu->kvm->arch.sca;
-		union esca_sigp_ctrl sigp_ctrl =
-			sca->cpu[vcpu->vcpu_id].sigp_ctrl;
-
-		c = sigp_ctrl.c;
-		scn = sigp_ctrl.scn;
-	} else {
-		struct bsca_block *sca = vcpu->kvm->arch.sca;
-		union bsca_sigp_ctrl sigp_ctrl =
-			sca->cpu[vcpu->vcpu_id].sigp_ctrl;
-
-		c = sigp_ctrl.c;
-		scn = sigp_ctrl.scn;
-	}
-	read_unlock(&vcpu->kvm->arch.sca_lock);
 
 	if (src_id)
-		*src_id = scn;
+		*src_id = sigp_ctrl.scn;
 
-	return c;
+	return sigp_ctrl.c;
 }
 
 static int sca_inject_ext_call(struct kvm_vcpu *vcpu, int src_id)
 {
+	struct esca_block *sca = vcpu->kvm->arch.sca;
+	union esca_sigp_ctrl *sigp_ctrl = &sca->cpu[vcpu->vcpu_id].sigp_ctrl;
+	union esca_sigp_ctrl old_val, new_val = {.scn = src_id, .c = 1};
 	int expect, rc;
 
 	BUG_ON(!kvm_s390_use_sca_entries());
-	read_lock(&vcpu->kvm->arch.sca_lock);
-	if (vcpu->kvm->arch.use_esca) {
-		struct esca_block *sca = vcpu->kvm->arch.sca;
-		union esca_sigp_ctrl *sigp_ctrl =
-			&(sca->cpu[vcpu->vcpu_id].sigp_ctrl);
-		union esca_sigp_ctrl new_val = {0}, old_val;
-
-		old_val = READ_ONCE(*sigp_ctrl);
-		new_val.scn = src_id;
-		new_val.c = 1;
-		old_val.c = 0;
-
-		expect = old_val.value;
-		rc = cmpxchg(&sigp_ctrl->value, old_val.value, new_val.value);
-	} else {
-		struct bsca_block *sca = vcpu->kvm->arch.sca;
-		union bsca_sigp_ctrl *sigp_ctrl =
-			&(sca->cpu[vcpu->vcpu_id].sigp_ctrl);
-		union bsca_sigp_ctrl new_val = {0}, old_val;
 
-		old_val = READ_ONCE(*sigp_ctrl);
-		new_val.scn = src_id;
-		new_val.c = 1;
-		old_val.c = 0;
+	old_val = READ_ONCE(*sigp_ctrl);
+	old_val.c = 0;
 
-		expect = old_val.value;
-		rc = cmpxchg(&sigp_ctrl->value, old_val.value, new_val.value);
-	}
-	read_unlock(&vcpu->kvm->arch.sca_lock);
+	expect = old_val.value;
+	rc = cmpxchg(&sigp_ctrl->value, old_val.value, new_val.value);
 
 	if (rc != expect) {
 		/* another external call is pending */
@@ -120,24 +84,14 @@ static int sca_inject_ext_call(struct kvm_vcpu *vcpu, int src_id)
 
 static void sca_clear_ext_call(struct kvm_vcpu *vcpu)
 {
+	struct esca_block *sca = vcpu->kvm->arch.sca;
+	union esca_sigp_ctrl *sigp_ctrl = &sca->cpu[vcpu->vcpu_id].sigp_ctrl;
+
 	if (!kvm_s390_use_sca_entries())
 		return;
 	kvm_s390_clear_cpuflags(vcpu, CPUSTAT_ECALL_PEND);
-	read_lock(&vcpu->kvm->arch.sca_lock);
-	if (vcpu->kvm->arch.use_esca) {
-		struct esca_block *sca = vcpu->kvm->arch.sca;
-		union esca_sigp_ctrl *sigp_ctrl =
-			&(sca->cpu[vcpu->vcpu_id].sigp_ctrl);
-
-		WRITE_ONCE(sigp_ctrl->value, 0);
-	} else {
-		struct bsca_block *sca = vcpu->kvm->arch.sca;
-		union bsca_sigp_ctrl *sigp_ctrl =
-			&(sca->cpu[vcpu->vcpu_id].sigp_ctrl);
 
-		WRITE_ONCE(sigp_ctrl->value, 0);
-	}
-	read_unlock(&vcpu->kvm->arch.sca_lock);
+	WRITE_ONCE(sigp_ctrl->value, 0);
 }
 
 int psw_extint_disabled(struct kvm_vcpu *vcpu)
@@ -1224,7 +1178,7 @@ int kvm_s390_ext_call_pending(struct kvm_vcpu *vcpu)
 {
 	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
 
-	if (!sclp.has_sigpif)
+	if (!kvm_s390_use_sca_entries())
 		return test_bit(IRQ_PEND_EXT_EXTERNAL, &li->pending_irqs);
 
 	return sca_ext_call_pending(vcpu, NULL);
@@ -1549,7 +1503,7 @@ static int __inject_extcall(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
 	if (kvm_get_vcpu_by_id(vcpu->kvm, src_id) == NULL)
 		return -EINVAL;
 
-	if (sclp.has_sigpif && !kvm_s390_pv_cpu_get_handle(vcpu))
+	if (kvm_s390_use_sca_entries() && !kvm_s390_pv_cpu_get_handle(vcpu))
 		return sca_inject_ext_call(vcpu, src_id);
 
 	if (test_and_set_bit(IRQ_PEND_EXT_EXTERNAL, &li->pending_irqs))