Merge tag 'kvm-s390-next-4.20-1' of...

Merge tag 'kvm-s390-next-4.20-1' of git://git.kernel.org/pub/scm/linux/kernel/git/kvms390/linux into HEAD

KVM: s390: Features for 4.20
- Initial version of AP crypto virtualization via vfio-mdev
- Set the host program identifier
- Optimize page table locking

MAINTAINERS

@@ -12668,6 +12668,18 @@ W:	http://www.ibm.com/developerworks/linux/linux390/
 S:	Supported
 F:	drivers/s390/crypto/
 
+S390 VFIO AP DRIVER
+M:	Tony Krowiak <akrowiak@linux.ibm.com>
+M:	Pierre Morel <pmorel@linux.ibm.com>
+M:	Halil Pasic <pasic@linux.ibm.com>
+L:	linux-s390@vger.kernel.org
+W:	http://www.ibm.com/developerworks/linux/linux390/
+S:	Supported
+F:	drivers/s390/crypto/vfio_ap_drv.c
+F:	drivers/s390/crypto/vfio_ap_private.h
+F:	drivers/s390/crypto/vfio_ap_ops.c
+F:	Documentation/s390/vfio-ap.txt
+
 S390 ZFCP DRIVER
 M:	Steffen Maier <maier@linux.ibm.com>
 M:	Benjamin Block <bblock@linux.ibm.com>

arch/s390/Kconfig

@@ -773,6 +773,17 @@ config VFIO_CCW
 	  To compile this driver as a module, choose M here: the
 	  module will be called vfio_ccw.
 
+config VFIO_AP
+	def_tristate n
+	prompt "VFIO support for AP devices"
+	depends on S390_AP_IOMMU && VFIO_MDEV_DEVICE && KVM
+	help
+		This driver grants access to Adjunct Processor (AP) devices
+		via the VFIO mediated device interface.
+
+		To compile this driver as a module, choose M here: the module
+		will be called vfio_ap.
+
 endmenu
 
 menu "Dump support"

arch/s390/include/asm/kvm_host.h

@@ -44,6 +44,7 @@
 #define KVM_REQ_ICPT_OPEREXC	KVM_ARCH_REQ(2)
 #define KVM_REQ_START_MIGRATION KVM_ARCH_REQ(3)
 #define KVM_REQ_STOP_MIGRATION  KVM_ARCH_REQ(4)
+#define KVM_REQ_VSIE_RESTART	KVM_ARCH_REQ(5)
 
 #define SIGP_CTRL_C		0x80
 #define SIGP_CTRL_SCN_MASK	0x3f
@@ -186,6 +187,7 @@ struct kvm_s390_sie_block {
 #define ECA_AIV		0x00200000
 #define ECA_VX		0x00020000
 #define ECA_PROTEXCI	0x00002000
+#define ECA_APIE	0x00000008
 #define ECA_SII		0x00000001
 	__u32	eca;			/* 0x004c */
 #define ICPT_INST	0x04
@@ -237,7 +239,11 @@ struct kvm_s390_sie_block {
 	psw_t	gpsw;			/* 0x0090 */
 	__u64	gg14;			/* 0x00a0 */
 	__u64	gg15;			/* 0x00a8 */
-	__u8	reservedb0[20];		/* 0x00b0 */
+	__u8	reservedb0[8];		/* 0x00b0 */
+#define HPID_KVM	0x4
+#define HPID_VSIE	0x5
+	__u8	hpid;			/* 0x00b8 */
+	__u8	reservedb9[11];		/* 0x00b9 */
 	__u16	extcpuaddr;		/* 0x00c4 */
 	__u16	eic;			/* 0x00c6 */
 	__u32	reservedc8;		/* 0x00c8 */
@@ -255,6 +261,8 @@ struct kvm_s390_sie_block {
 	__u8	reservede4[4];		/* 0x00e4 */
 	__u64	tecmc;			/* 0x00e8 */
 	__u8	reservedf0[12];		/* 0x00f0 */
+#define CRYCB_FORMAT_MASK 0x00000003
+#define CRYCB_FORMAT0 0x00000000
 #define CRYCB_FORMAT1 0x00000001
 #define CRYCB_FORMAT2 0x00000003
 	__u32	crycbd;			/* 0x00fc */
@@ -715,6 +723,7 @@ struct kvm_s390_crypto {
 	__u32 crycbd;
 	__u8 aes_kw;
 	__u8 dea_kw;
+	__u8 apie;
 };
 
 #define APCB0_MASK_SIZE 1
@@ -855,6 +864,8 @@ void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu,
 void kvm_arch_async_page_present(struct kvm_vcpu *vcpu,
 				 struct kvm_async_pf *work);
 
+void kvm_arch_crypto_clear_masks(struct kvm *kvm);
+
 extern int sie64a(struct kvm_s390_sie_block *, u64 *);
 extern char sie_exit;
 

arch/s390/include/uapi/asm/kvm.h

@@ -160,6 +160,8 @@ struct kvm_s390_vm_cpu_subfunc {
 #define KVM_S390_VM_CRYPTO_ENABLE_DEA_KW	1
 #define KVM_S390_VM_CRYPTO_DISABLE_AES_KW	2
 #define KVM_S390_VM_CRYPTO_DISABLE_DEA_KW	3
+#define KVM_S390_VM_CRYPTO_ENABLE_APIE		4
+#define KVM_S390_VM_CRYPTO_DISABLE_APIE		5
 
 /* kvm attributes for migration mode */
 #define KVM_S390_VM_MIGRATION_STOP	0

arch/s390/kvm/kvm-s390.c

@@ -40,6 +40,7 @@
 #include <asm/sclp.h>
 #include <asm/cpacf.h>
 #include <asm/timex.h>
+#include <asm/ap.h>
 #include "kvm-s390.h"
 #include "gaccess.h"
 
@@ -844,20 +845,22 @@ void kvm_s390_vcpu_crypto_reset_all(struct kvm *kvm)
 
 	kvm_s390_vcpu_block_all(kvm);
 
-	kvm_for_each_vcpu(i, vcpu, kvm)
+	kvm_for_each_vcpu(i, vcpu, kvm) {
 		kvm_s390_vcpu_crypto_setup(vcpu);
+		/* recreate the shadow crycb by leaving the VSIE handler */
+		kvm_s390_sync_request(KVM_REQ_VSIE_RESTART, vcpu);
+	}
 
 	kvm_s390_vcpu_unblock_all(kvm);
 }
 
 static int kvm_s390_vm_set_crypto(struct kvm *kvm, struct kvm_device_attr *attr)
 {
-	if (!test_kvm_facility(kvm, 76))
-		return -EINVAL;
-
 	mutex_lock(&kvm->lock);
 	switch (attr->attr) {
 	case KVM_S390_VM_CRYPTO_ENABLE_AES_KW:
+		if (!test_kvm_facility(kvm, 76))
+			return -EINVAL;
 		get_random_bytes(
 			kvm->arch.crypto.crycb->aes_wrapping_key_mask,
 			sizeof(kvm->arch.crypto.crycb->aes_wrapping_key_mask));
@@ -865,6 +868,8 @@ static int kvm_s390_vm_set_crypto(struct kvm *kvm, struct kvm_device_attr *attr)
 		VM_EVENT(kvm, 3, "%s", "ENABLE: AES keywrapping support");
 		break;
 	case KVM_S390_VM_CRYPTO_ENABLE_DEA_KW:
+		if (!test_kvm_facility(kvm, 76))
+			return -EINVAL;
 		get_random_bytes(
 			kvm->arch.crypto.crycb->dea_wrapping_key_mask,
 			sizeof(kvm->arch.crypto.crycb->dea_wrapping_key_mask));
@@ -872,17 +877,35 @@ static int kvm_s390_vm_set_crypto(struct kvm *kvm, struct kvm_device_attr *attr)
 		VM_EVENT(kvm, 3, "%s", "ENABLE: DEA keywrapping support");
 		break;
 	case KVM_S390_VM_CRYPTO_DISABLE_AES_KW:
+		if (!test_kvm_facility(kvm, 76))
+			return -EINVAL;
 		kvm->arch.crypto.aes_kw = 0;
 		memset(kvm->arch.crypto.crycb->aes_wrapping_key_mask, 0,
 			sizeof(kvm->arch.crypto.crycb->aes_wrapping_key_mask));
 		VM_EVENT(kvm, 3, "%s", "DISABLE: AES keywrapping support");
 		break;
 	case KVM_S390_VM_CRYPTO_DISABLE_DEA_KW:
+		if (!test_kvm_facility(kvm, 76))
+			return -EINVAL;
 		kvm->arch.crypto.dea_kw = 0;
 		memset(kvm->arch.crypto.crycb->dea_wrapping_key_mask, 0,
 			sizeof(kvm->arch.crypto.crycb->dea_wrapping_key_mask));
 		VM_EVENT(kvm, 3, "%s", "DISABLE: DEA keywrapping support");
 		break;
+	case KVM_S390_VM_CRYPTO_ENABLE_APIE:
+		if (!ap_instructions_available()) {
+			mutex_unlock(&kvm->lock);
+			return -EOPNOTSUPP;
+		}
+		kvm->arch.crypto.apie = 1;
+		break;
+	case KVM_S390_VM_CRYPTO_DISABLE_APIE:
+		if (!ap_instructions_available()) {
+			mutex_unlock(&kvm->lock);
+			return -EOPNOTSUPP;
+		}
+		kvm->arch.crypto.apie = 0;
+		break;
 	default:
 		mutex_unlock(&kvm->lock);
 		return -ENXIO;
@@ -1491,6 +1514,10 @@ static int kvm_s390_vm_has_attr(struct kvm *kvm, struct kvm_device_attr *attr)
 		case KVM_S390_VM_CRYPTO_DISABLE_DEA_KW:
 			ret = 0;
 			break;
+		case KVM_S390_VM_CRYPTO_ENABLE_APIE:
+		case KVM_S390_VM_CRYPTO_DISABLE_APIE:
+			ret = ap_instructions_available() ? 0 : -ENXIO;
+			break;
 		default:
 			ret = -ENXIO;
 			break;
@@ -1992,55 +2019,60 @@ long kvm_arch_vm_ioctl(struct file *filp,
 	return r;
 }
 
-static int kvm_s390_query_ap_config(u8 *config)
-{
-	u32 fcn_code = 0x04000000UL;
-	u32 cc = 0;
-
-	memset(config, 0, 128);
-	asm volatile(
-		"lgr 0,%1\n"
-		"lgr 2,%2\n"
-		".long 0xb2af0000\n"		/* PQAP(QCI) */
-		"0: ipm %0\n"
-		"srl %0,28\n"
-		"1:\n"
-		EX_TABLE(0b, 1b)
-		: "+r" (cc)
-		: "r" (fcn_code), "r" (config)
-		: "cc", "0", "2", "memory"
-	);
-
-	return cc;
-}
-
 static int kvm_s390_apxa_installed(void)
 {
-	u8 config[128];
-	int cc;
-
-	if (test_facility(12)) {
-		cc = kvm_s390_query_ap_config(config);
+	struct ap_config_info info;
 
-		if (cc)
-			pr_err("PQAP(QCI) failed with cc=%d", cc);
-		else
-			return config[0] & 0x40;
+	if (ap_instructions_available()) {
+		if (ap_qci(&info) == 0)
+			return info.apxa;
 	}
 
 	return 0;
 }
 
+/*
+ * The format of the crypto control block (CRYCB) is specified in the 3 low
+ * order bits of the CRYCB designation (CRYCBD) field as follows:
+ * Format 0: Neither the message security assist extension 3 (MSAX3) nor the
+ *	     AP extended addressing (APXA) facility are installed.
+ * Format 1: The APXA facility is not installed but the MSAX3 facility is.
+ * Format 2: Both the APXA and MSAX3 facilities are installed
+ */
 static void kvm_s390_set_crycb_format(struct kvm *kvm)
 {
 	kvm->arch.crypto.crycbd = (__u32)(unsigned long) kvm->arch.crypto.crycb;
 
+	/* Clear the CRYCB format bits - i.e., set format 0 by default */
+	kvm->arch.crypto.crycbd &= ~(CRYCB_FORMAT_MASK);
+
+	/* Check whether MSAX3 is installed */
+	if (!test_kvm_facility(kvm, 76))
+		return;
+
 	if (kvm_s390_apxa_installed())
 		kvm->arch.crypto.crycbd |= CRYCB_FORMAT2;
 	else
 		kvm->arch.crypto.crycbd |= CRYCB_FORMAT1;
 }
 
+void kvm_arch_crypto_clear_masks(struct kvm *kvm)
+{
+	mutex_lock(&kvm->lock);
+	kvm_s390_vcpu_block_all(kvm);
+
+	memset(&kvm->arch.crypto.crycb->apcb0, 0,
+	       sizeof(kvm->arch.crypto.crycb->apcb0));
+	memset(&kvm->arch.crypto.crycb->apcb1, 0,
+	       sizeof(kvm->arch.crypto.crycb->apcb1));
+
+	/* recreate the shadow crycb for each vcpu */
+	kvm_s390_sync_request_broadcast(kvm, KVM_REQ_VSIE_RESTART);
+	kvm_s390_vcpu_unblock_all(kvm);
+	mutex_unlock(&kvm->lock);
+}
+EXPORT_SYMBOL_GPL(kvm_arch_crypto_clear_masks);
+
 static u64 kvm_s390_get_initial_cpuid(void)
 {
 	struct cpuid cpuid;
@@ -2052,12 +2084,12 @@ static u64 kvm_s390_get_initial_cpuid(void)
 
 static void kvm_s390_crypto_init(struct kvm *kvm)
 {
-	if (!test_kvm_facility(kvm, 76))
-		return;
-
 	kvm->arch.crypto.crycb = &kvm->arch.sie_page2->crycb;
 	kvm_s390_set_crycb_format(kvm);
 
+	if (!test_kvm_facility(kvm, 76))
+		return;
+
 	/* Enable AES/DEA protected key functions by default */
 	kvm->arch.crypto.aes_kw = 1;
 	kvm->arch.crypto.dea_kw = 1;
@@ -2583,17 +2615,25 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
 
 static void kvm_s390_vcpu_crypto_setup(struct kvm_vcpu *vcpu)
 {
-	if (!test_kvm_facility(vcpu->kvm, 76))
+	/*
+	 * If the AP instructions are not being interpreted and the MSAX3
+	 * facility is not configured for the guest, there is nothing to set up.
+	 */
+	if (!vcpu->kvm->arch.crypto.apie && !test_kvm_facility(vcpu->kvm, 76))
 		return;
 
+	vcpu->arch.sie_block->crycbd = vcpu->kvm->arch.crypto.crycbd;
 	vcpu->arch.sie_block->ecb3 &= ~(ECB3_AES | ECB3_DEA);
+	vcpu->arch.sie_block->eca &= ~ECA_APIE;
+
+	if (vcpu->kvm->arch.crypto.apie)
+		vcpu->arch.sie_block->eca |= ECA_APIE;
 
+	/* Set up protected key support */
 	if (vcpu->kvm->arch.crypto.aes_kw)
 		vcpu->arch.sie_block->ecb3 |= ECB3_AES;
 	if (vcpu->kvm->arch.crypto.dea_kw)
 		vcpu->arch.sie_block->ecb3 |= ECB3_DEA;
-
-	vcpu->arch.sie_block->crycbd = vcpu->kvm->arch.crypto.crycbd;
 }
 
 void kvm_s390_vcpu_unsetup_cmma(struct kvm_vcpu *vcpu)
@@ -2685,6 +2725,8 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 	hrtimer_init(&vcpu->arch.ckc_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	vcpu->arch.ckc_timer.function = kvm_s390_idle_wakeup;
 
+	vcpu->arch.sie_block->hpid = HPID_KVM;
+
 	kvm_s390_vcpu_crypto_setup(vcpu);
 
 	return rc;
@@ -2768,18 +2810,25 @@ static void kvm_s390_vcpu_request(struct kvm_vcpu *vcpu)
 	exit_sie(vcpu);
 }
 
+bool kvm_s390_vcpu_sie_inhibited(struct kvm_vcpu *vcpu)
+{
+	return atomic_read(&vcpu->arch.sie_block->prog20) &
+	       (PROG_BLOCK_SIE | PROG_REQUEST);
+}
+
 static void kvm_s390_vcpu_request_handled(struct kvm_vcpu *vcpu)
 {
 	atomic_andnot(PROG_REQUEST, &vcpu->arch.sie_block->prog20);
 }
 
 /*
- * Kick a guest cpu out of SIE and wait until SIE is not running.
+ * Kick a guest cpu out of (v)SIE and wait until (v)SIE is not running.
  * If the CPU is not running (e.g. waiting as idle) the function will
  * return immediately. */
 void exit_sie(struct kvm_vcpu *vcpu)
 {
 	kvm_s390_set_cpuflags(vcpu, CPUSTAT_STOP_INT);
+	kvm_s390_vsie_kick(vcpu);
 	while (vcpu->arch.sie_block->prog0c & PROG_IN_SIE)
 		cpu_relax();
 }
@@ -3196,6 +3245,8 @@ static int kvm_s390_handle_requests(struct kvm_vcpu *vcpu)
 
 	/* nothing to do, just clear the request */
 	kvm_clear_request(KVM_REQ_UNHALT, vcpu);
+	/* we left the vsie handler, nothing to do, just clear the request */
+	kvm_clear_request(KVM_REQ_VSIE_RESTART, vcpu);
 
 	return 0;
 }

arch/s390/kvm/kvm-s390.h

@@ -290,6 +290,7 @@ void kvm_s390_vcpu_start(struct kvm_vcpu *vcpu);
 void kvm_s390_vcpu_stop(struct kvm_vcpu *vcpu);
 void kvm_s390_vcpu_block(struct kvm_vcpu *vcpu);
 void kvm_s390_vcpu_unblock(struct kvm_vcpu *vcpu);
+bool kvm_s390_vcpu_sie_inhibited(struct kvm_vcpu *vcpu);
 void exit_sie(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);

arch/s390/kvm/vsie.c

@@ -135,14 +135,148 @@ static int prepare_cpuflags(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 	atomic_set(&scb_s->cpuflags, newflags);
 	return 0;
 }
+/* Copy to APCB FORMAT1 from APCB FORMAT0 */
+static int setup_apcb10(struct kvm_vcpu *vcpu, struct kvm_s390_apcb1 *apcb_s,
+			unsigned long apcb_o, struct kvm_s390_apcb1 *apcb_h)
+{
+	struct kvm_s390_apcb0 tmp;
 
-/*
+	if (read_guest_real(vcpu, apcb_o, &tmp, sizeof(struct kvm_s390_apcb0)))
+		return -EFAULT;
+
+	apcb_s->apm[0] = apcb_h->apm[0] & tmp.apm[0];
+	apcb_s->aqm[0] = apcb_h->aqm[0] & tmp.aqm[0] & 0xffff000000000000UL;
+	apcb_s->adm[0] = apcb_h->adm[0] & tmp.adm[0] & 0xffff000000000000UL;
+
+	return 0;
+
+}
+
+/**
+ * setup_apcb00 - Copy to APCB FORMAT0 from APCB FORMAT0
+ * @vcpu: pointer to the virtual CPU
+ * @apcb_s: pointer to start of apcb in the shadow crycb
+ * @apcb_o: pointer to start of original apcb in the guest2
+ * @apcb_h: pointer to start of apcb in the guest1
+ *
+ * Returns 0 and -EFAULT on error reading guest apcb
+ */
+static int setup_apcb00(struct kvm_vcpu *vcpu, unsigned long *apcb_s,
+			unsigned long apcb_o, unsigned long *apcb_h)
+{
+	if (read_guest_real(vcpu, apcb_o, apcb_s,
+			    sizeof(struct kvm_s390_apcb0)))
+		return -EFAULT;
+
+	bitmap_and(apcb_s, apcb_s, apcb_h, sizeof(struct kvm_s390_apcb0));
+
+	return 0;
+}
+
+/**
+ * setup_apcb11 - Copy the FORMAT1 APCB from the guest to the shadow CRYCB
+ * @vcpu: pointer to the virtual CPU
+ * @apcb_s: pointer to start of apcb in the shadow crycb
+ * @apcb_o: pointer to start of original guest apcb
+ * @apcb_h: pointer to start of apcb in the host
+ *
+ * Returns 0 and -EFAULT on error reading guest apcb
+ */
+static int setup_apcb11(struct kvm_vcpu *vcpu, unsigned long *apcb_s,
+			unsigned long apcb_o,
+			unsigned long *apcb_h)
+{
+	if (read_guest_real(vcpu, apcb_o, apcb_s,
+			    sizeof(struct kvm_s390_apcb1)))
+		return -EFAULT;
+
+	bitmap_and(apcb_s, apcb_s, apcb_h, sizeof(struct kvm_s390_apcb1));
+
+	return 0;
+}
+
+/**
+ * setup_apcb - Create a shadow copy of the apcb.
+ * @vcpu: pointer to the virtual CPU
+ * @crycb_s: pointer to shadow crycb
+ * @crycb_o: pointer to original guest crycb
+ * @crycb_h: pointer to the host crycb
+ * @fmt_o: format of the original guest crycb.
+ * @fmt_h: format of the host crycb.
+ *
+ * Checks the compatibility between the guest and host crycb and calls the
+ * appropriate copy function.
+ *
+ * Return 0 or an error number if the guest and host crycb are incompatible.
+ */
+static int setup_apcb(struct kvm_vcpu *vcpu, struct kvm_s390_crypto_cb *crycb_s,
+	       const u32 crycb_o,
+	       struct kvm_s390_crypto_cb *crycb_h,
+	       int fmt_o, int fmt_h)
+{
+	struct kvm_s390_crypto_cb *crycb;
+
+	crycb = (struct kvm_s390_crypto_cb *) (unsigned long)crycb_o;
+
+	switch (fmt_o) {
+	case CRYCB_FORMAT2:
+		if ((crycb_o & PAGE_MASK) != ((crycb_o + 256) & PAGE_MASK))
+			return -EACCES;
+		if (fmt_h != CRYCB_FORMAT2)
+			return -EINVAL;
+		return setup_apcb11(vcpu, (unsigned long *)&crycb_s->apcb1,
+				    (unsigned long) &crycb->apcb1,
+				    (unsigned long *)&crycb_h->apcb1);
+	case CRYCB_FORMAT1:
+		switch (fmt_h) {
+		case CRYCB_FORMAT2:
+			return setup_apcb10(vcpu, &crycb_s->apcb1,
+					    (unsigned long) &crycb->apcb0,
+					    &crycb_h->apcb1);
+		case CRYCB_FORMAT1:
+			return setup_apcb00(vcpu,
+					    (unsigned long *) &crycb_s->apcb0,
+					    (unsigned long) &crycb->apcb0,
+					    (unsigned long *) &crycb_h->apcb0);
+		}
+		break;
+	case CRYCB_FORMAT0:
+		if ((crycb_o & PAGE_MASK) != ((crycb_o + 32) & PAGE_MASK))
+			return -EACCES;
+
+		switch (fmt_h) {
+		case CRYCB_FORMAT2:
+			return setup_apcb10(vcpu, &crycb_s->apcb1,
+					    (unsigned long) &crycb->apcb0,
+					    &crycb_h->apcb1);
+		case CRYCB_FORMAT1:
+		case CRYCB_FORMAT0:
+			return setup_apcb00(vcpu,
+					    (unsigned long *) &crycb_s->apcb0,
+					    (unsigned long) &crycb->apcb0,
+					    (unsigned long *) &crycb_h->apcb0);
+		}
+	}
+	return -EINVAL;
+}
+
+/**
+ * shadow_crycb - Create a shadow copy of the crycb block
+ * @vcpu: a pointer to the virtual CPU
+ * @vsie_page: a pointer to internal date used for the vSIE
+ *
  * Create a shadow copy of the crycb block and setup key wrapping, if
  * requested for guest 3 and enabled for guest 2.
  *
- * We only accept format-1 (no AP in g2), but convert it into format-2
+ * We accept format-1 or format-2, but we convert format-1 into format-2
+ * in the shadow CRYCB.
+ * Using format-2 enables the firmware to choose the right format when
+ * scheduling the SIE.
  * There is nothing to do for format-0.
  *
+ * This function centralize the issuing of set_validity_icpt() for all
+ * the subfunctions working on the crycb.
+ *
  * Returns: - 0 if shadowed or nothing to do
  *          - > 0 if control has to be given to guest 2
  */
@@ -154,23 +288,40 @@ static int shadow_crycb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 	const u32 crycb_addr = crycbd_o & 0x7ffffff8U;
 	unsigned long *b1, *b2;
 	u8 ecb3_flags;
+	int apie_h;
+	int key_msk = test_kvm_facility(vcpu->kvm, 76);
+	int fmt_o = crycbd_o & CRYCB_FORMAT_MASK;
+	int fmt_h = vcpu->arch.sie_block->crycbd & CRYCB_FORMAT_MASK;
+	int ret = 0;
 
 	scb_s->crycbd = 0;
-	if (!(crycbd_o & vcpu->arch.sie_block->crycbd & CRYCB_FORMAT1))
-		return 0;
-	/* format-1 is supported with message-security-assist extension 3 */
-	if (!test_kvm_facility(vcpu->kvm, 76))
+
+	apie_h = vcpu->arch.sie_block->eca & ECA_APIE;
+	if (!apie_h && !key_msk)
 		return 0;
+
+	if (!crycb_addr)
+		return set_validity_icpt(scb_s, 0x0039U);
+
+	if (fmt_o == CRYCB_FORMAT1)
+		if ((crycb_addr & PAGE_MASK) !=
+		    ((crycb_addr + 128) & PAGE_MASK))
+			return set_validity_icpt(scb_s, 0x003CU);
+
+	if (apie_h && (scb_o->eca & ECA_APIE)) {
+		ret = setup_apcb(vcpu, &vsie_page->crycb, crycb_addr,
+				 vcpu->kvm->arch.crypto.crycb,
+				 fmt_o, fmt_h);
+		if (ret)
+			goto end;
+		scb_s->eca |= scb_o->eca & ECA_APIE;
+	}
+
 	/* we may only allow it if enabled for guest 2 */
 	ecb3_flags = scb_o->ecb3 & vcpu->arch.sie_block->ecb3 &
 		     (ECB3_AES | ECB3_DEA);
 	if (!ecb3_flags)
-		return 0;
-
-	if ((crycb_addr & PAGE_MASK) != ((crycb_addr + 128) & PAGE_MASK))
-		return set_validity_icpt(scb_s, 0x003CU);
-	else if (!crycb_addr)
-		return set_validity_icpt(scb_s, 0x0039U);
+		goto end;
 
 	/* copy only the wrapping keys */
 	if (read_guest_real(vcpu, crycb_addr + 72,
@@ -178,8 +329,6 @@ static int shadow_crycb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 		return set_validity_icpt(scb_s, 0x0035U);
 
 	scb_s->ecb3 |= ecb3_flags;
-	scb_s->crycbd = ((__u32)(__u64) &vsie_page->crycb) | CRYCB_FORMAT1 |
-			CRYCB_FORMAT2;
 
 	/* xor both blocks in one run */
 	b1 = (unsigned long *) vsie_page->crycb.dea_wrapping_key_mask;
@@ -187,6 +336,16 @@ static int shadow_crycb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 			    vcpu->kvm->arch.crypto.crycb->dea_wrapping_key_mask;
 	/* as 56%8 == 0, bitmap_xor won't overwrite any data */
 	bitmap_xor(b1, b1, b2, BITS_PER_BYTE * 56);
+end:
+	switch (ret) {
+	case -EINVAL:
+		return set_validity_icpt(scb_s, 0x0020U);
+	case -EFAULT:
+		return set_validity_icpt(scb_s, 0x0035U);
+	case -EACCES:
+		return set_validity_icpt(scb_s, 0x003CU);
+	}
+	scb_s->crycbd = ((__u32)(__u64) &vsie_page->crycb) | CRYCB_FORMAT2;
 	return 0;
 }
 
@@ -383,6 +542,8 @@ static int shadow_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 	if (test_kvm_facility(vcpu->kvm, 156))
 		scb_s->ecd |= scb_o->ecd & ECD_ETOKENF;
 
+	scb_s->hpid = HPID_VSIE;
+
 	prepare_ibc(vcpu, vsie_page);
 	rc = shadow_crycb(vcpu, vsie_page);
 out:
@@ -830,7 +991,7 @@ static int do_vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 	struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s;
 	struct kvm_s390_sie_block *scb_o = vsie_page->scb_o;
 	int guest_bp_isolation;
-	int rc;
+	int rc = 0;
 
 	handle_last_fault(vcpu, vsie_page);
 
@@ -858,7 +1019,18 @@ static int do_vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 	guest_enter_irqoff();
 	local_irq_enable();
 
-	rc = sie64a(scb_s, vcpu->run->s.regs.gprs);
+	/*
+	 * Simulate a SIE entry of the VCPU (see sie64a), so VCPU blocking
+	 * and VCPU requests also hinder the vSIE from running and lead
+	 * to an immediate exit. kvm_s390_vsie_kick() has to be used to
+	 * also kick the vSIE.
+	 */
+	vcpu->arch.sie_block->prog0c |= PROG_IN_SIE;
+	barrier();
+	if (!kvm_s390_vcpu_sie_inhibited(vcpu))
+		rc = sie64a(scb_s, vcpu->run->s.regs.gprs);
+	barrier();
+	vcpu->arch.sie_block->prog0c &= ~PROG_IN_SIE;
 
 	local_irq_disable();
 	guest_exit_irqoff();
@@ -1005,7 +1177,8 @@ static int vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 		if (rc == -EAGAIN)
 			rc = 0;
 		if (rc || scb_s->icptcode || signal_pending(current) ||
-		    kvm_s390_vcpu_has_irq(vcpu, 0))
+		    kvm_s390_vcpu_has_irq(vcpu, 0) ||
+		    kvm_s390_vcpu_sie_inhibited(vcpu))
 			break;
 	}
 
@@ -1122,7 +1295,8 @@ int kvm_s390_handle_vsie(struct kvm_vcpu *vcpu)
 	if (unlikely(scb_addr & 0x1ffUL))
 		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
 
-	if (signal_pending(current) || kvm_s390_vcpu_has_irq(vcpu, 0))
+	if (signal_pending(current) || kvm_s390_vcpu_has_irq(vcpu, 0) ||
+	    kvm_s390_vcpu_sie_inhibited(vcpu))
 		return 0;
 
 	vsie_page = get_vsie_page(vcpu->kvm, scb_addr);

arch/s390/mm/gmap.c

@@ -907,10 +907,16 @@ static inline pmd_t *gmap_pmd_op_walk(struct gmap *gmap, unsigned long gaddr)
 	pmd_t *pmdp;
 
 	BUG_ON(gmap_is_shadow(gmap));
-	spin_lock(&gmap->guest_table_lock);
 	pmdp = (pmd_t *) gmap_table_walk(gmap, gaddr, 1);
+	if (!pmdp)
+		return NULL;
 
-	if (!pmdp || pmd_none(*pmdp)) {
+	/* without huge pages, there is no need to take the table lock */
+	if (!gmap->mm->context.allow_gmap_hpage_1m)
+		return pmd_none(*pmdp) ? NULL : pmdp;
+
+	spin_lock(&gmap->guest_table_lock);
+	if (pmd_none(*pmdp)) {
 		spin_unlock(&gmap->guest_table_lock);
 		return NULL;
 	}

arch/s390/tools/gen_facilities.c

@@ -106,6 +106,8 @@ static struct facility_def facility_defs[] = {
 
 		.name = "FACILITIES_KVM_CPUMODEL",
 		.bits = (int[]){
+			12, /* AP Query Configuration Information */
+			15, /* AP Facilities Test */
 			156, /* etoken facility */
 			-1  /* END */
 		}

drivers/iommu/Kconfig

@@ -372,6 +372,14 @@ config S390_CCW_IOMMU
 	  Enables bits of IOMMU API required by VFIO. The iommu_ops
 	  is not implemented as it is not necessary for VFIO.
 
+config S390_AP_IOMMU
+	bool "S390 AP IOMMU Support"
+	depends on S390 && ZCRYPT
+	select IOMMU_API
+	help
+	  Enables bits of IOMMU API required by VFIO. The iommu_ops
+	  is not implemented as it is not necessary for VFIO.
+
 config MTK_IOMMU
 	bool "MTK IOMMU Support"
 	depends on ARM || ARM64

drivers/s390/crypto/Makefile

@@ -15,3 +15,7 @@ obj-$(CONFIG_ZCRYPT) += zcrypt_pcixcc.o zcrypt_cex2a.o zcrypt_cex4.o
 # pkey kernel module
 pkey-objs := pkey_api.o
 obj-$(CONFIG_PKEY) += pkey.o
+
+# adjunct processor matrix
+vfio_ap-objs := vfio_ap_drv.o vfio_ap_ops.o
+obj-$(CONFIG_VFIO_AP) += vfio_ap.o

drivers/s390/crypto/vfio_ap_drv.c

+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * VFIO based AP device driver
+ *
+ * Copyright IBM Corp. 2018
+ *
+ * Author(s): Tony Krowiak <akrowiak@linux.ibm.com>
+ */
+
+#include <linux/module.h>
+#include <linux/mod_devicetable.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include "vfio_ap_private.h"
+
+#define VFIO_AP_ROOT_NAME "vfio_ap"
+#define VFIO_AP_DEV_TYPE_NAME "ap_matrix"
+#define VFIO_AP_DEV_NAME "matrix"
+
+MODULE_AUTHOR("IBM Corporation");
+MODULE_DESCRIPTION("VFIO AP device driver, Copyright IBM Corp. 2018");
+MODULE_LICENSE("GPL v2");
+
+static struct ap_driver vfio_ap_drv;
+
+static struct device_type vfio_ap_dev_type = {
+	.name = VFIO_AP_DEV_TYPE_NAME,
+};
+
+struct ap_matrix_dev *matrix_dev;
+
+/* Only type 10 adapters (CEX4 and later) are supported
+ * by the AP matrix device driver
+ */
+static struct ap_device_id ap_queue_ids[] = {
+	{ .dev_type = AP_DEVICE_TYPE_CEX4,
+	  .match_flags = AP_DEVICE_ID_MATCH_QUEUE_TYPE },
+	{ .dev_type = AP_DEVICE_TYPE_CEX5,
+	  .match_flags = AP_DEVICE_ID_MATCH_QUEUE_TYPE },
+	{ .dev_type = AP_DEVICE_TYPE_CEX6,
+	  .match_flags = AP_DEVICE_ID_MATCH_QUEUE_TYPE },
+	{ /* end of sibling */ },
+};
+
+MODULE_DEVICE_TABLE(vfio_ap, ap_queue_ids);
+
+static int vfio_ap_queue_dev_probe(struct ap_device *apdev)
+{
+	return 0;
+}
+
+static void vfio_ap_queue_dev_remove(struct ap_device *apdev)
+{
+	/* Nothing to do yet */
+}
+
+static void vfio_ap_matrix_dev_release(struct device *dev)
+{
+	struct ap_matrix_dev *matrix_dev = dev_get_drvdata(dev);
+
+	kfree(matrix_dev);
+}
+
+static int vfio_ap_matrix_dev_create(void)
+{
+	int ret;
+	struct device *root_device;
+
+	root_device = root_device_register(VFIO_AP_ROOT_NAME);
+	if (IS_ERR(root_device))
+		return PTR_ERR(root_device);
+
+	matrix_dev = kzalloc(sizeof(*matrix_dev), GFP_KERNEL);
+	if (!matrix_dev) {
+		ret = -ENOMEM;
+		goto matrix_alloc_err;
+	}
+
+	/* Fill in config info via PQAP(QCI), if available */
+	if (test_facility(12)) {
+		ret = ap_qci(&matrix_dev->info);
+		if (ret)
+			goto matrix_alloc_err;
+	}
+
+	mutex_init(&matrix_dev->lock);
+	INIT_LIST_HEAD(&matrix_dev->mdev_list);
+
+	matrix_dev->device.type = &vfio_ap_dev_type;
+	dev_set_name(&matrix_dev->device, "%s", VFIO_AP_DEV_NAME);
+	matrix_dev->device.parent = root_device;
+	matrix_dev->device.release = vfio_ap_matrix_dev_release;
+	matrix_dev->device.driver = &vfio_ap_drv.driver;
+
+	ret = device_register(&matrix_dev->device);
+	if (ret)
+		goto matrix_reg_err;
+
+	return 0;
+
+matrix_reg_err:
+	put_device(&matrix_dev->device);
+matrix_alloc_err:
+	root_device_unregister(root_device);
+
+	return ret;
+}
+
+static void vfio_ap_matrix_dev_destroy(void)
+{
+	device_unregister(&matrix_dev->device);
+	root_device_unregister(matrix_dev->device.parent);
+}
+
+int __init vfio_ap_init(void)
+{
+	int ret;
+
+	/* If there are no AP instructions, there is nothing to pass through. */
+	if (!ap_instructions_available())
+		return -ENODEV;
+
+	ret = vfio_ap_matrix_dev_create();
+	if (ret)
+		return ret;
+
+	memset(&vfio_ap_drv, 0, sizeof(vfio_ap_drv));
+	vfio_ap_drv.probe = vfio_ap_queue_dev_probe;
+	vfio_ap_drv.remove = vfio_ap_queue_dev_remove;
+	vfio_ap_drv.ids = ap_queue_ids;
+
+	ret = ap_driver_register(&vfio_ap_drv, THIS_MODULE, VFIO_AP_DRV_NAME);
+	if (ret) {
+		vfio_ap_matrix_dev_destroy();
+		return ret;
+	}
+
+	ret = vfio_ap_mdev_register();
+	if (ret) {
+		ap_driver_unregister(&vfio_ap_drv);
+		vfio_ap_matrix_dev_destroy();
+
+		return ret;
+	}
+
+	return 0;
+}
+
+void __exit vfio_ap_exit(void)
+{
+	vfio_ap_mdev_unregister();
+	ap_driver_unregister(&vfio_ap_drv);
+	vfio_ap_matrix_dev_destroy();
+}
+
+module_init(vfio_ap_init);
+module_exit(vfio_ap_exit);

drivers/s390/crypto/vfio_ap_private.h

+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Private data and functions for adjunct processor VFIO matrix driver.
+ *
+ * Author(s): Tony Krowiak <akrowiak@linux.ibm.com>
+ *	      Halil Pasic <pasic@linux.ibm.com>
+ *
+ * Copyright IBM Corp. 2018
+ */
+
+#ifndef _VFIO_AP_PRIVATE_H_
+#define _VFIO_AP_PRIVATE_H_
+
+#include <linux/types.h>
+#include <linux/device.h>
+#include <linux/mdev.h>
+#include <linux/delay.h>
+#include <linux/mutex.h>
+
+#include "ap_bus.h"
+
+#define VFIO_AP_MODULE_NAME "vfio_ap"
+#define VFIO_AP_DRV_NAME "vfio_ap"
+
+/**
+ * ap_matrix_dev - the AP matrix device structure
+ * @device:	generic device structure associated with the AP matrix device
+ * @available_instances: number of mediated matrix devices that can be created
+ * @info:	the struct containing the output from the PQAP(QCI) instruction
+ * mdev_list:	the list of mediated matrix devices created
+ * lock:	mutex for locking the AP matrix device. This lock will be
+ *		taken every time we fiddle with state managed by the vfio_ap
+ *		driver, be it using @mdev_list or writing the state of a
+ *		single ap_matrix_mdev device. It's quite coarse but we don't
+ *		expect much contention.
+ */
+struct ap_matrix_dev {
+	struct device device;
+	atomic_t available_instances;
+	struct ap_config_info info;
+	struct list_head mdev_list;
+	struct mutex lock;
+};
+
+extern struct ap_matrix_dev *matrix_dev;
+
+/**
+ * The AP matrix is comprised of three bit masks identifying the adapters,
+ * queues (domains) and control domains that belong to an AP matrix. The bits i
+ * each mask, from least significant to most significant bit, correspond to IDs
+ * 0 to 255. When a bit is set, the corresponding ID belongs to the matrix.
+ *
+ * @apm_max: max adapter number in @apm
+ * @apm identifies the AP adapters in the matrix
+ * @aqm_max: max domain number in @aqm
+ * @aqm identifies the AP queues (domains) in the matrix
+ * @adm_max: max domain number in @adm
+ * @adm identifies the AP control domains in the matrix
+ */
+struct ap_matrix {
+	unsigned long apm_max;
+	DECLARE_BITMAP(apm, 256);
+	unsigned long aqm_max;
+	DECLARE_BITMAP(aqm, 256);
+	unsigned long adm_max;
+	DECLARE_BITMAP(adm, 256);
+};
+
+/**
+ * struct ap_matrix_mdev - the mediated matrix device structure
+ * @list:	allows the ap_matrix_mdev struct to be added to a list
+ * @matrix:	the adapters, usage domains and control domains assigned to the
+ *		mediated matrix device.
+ * @group_notifier: notifier block used for specifying callback function for
+ *		    handling the VFIO_GROUP_NOTIFY_SET_KVM event
+ * @kvm:	the struct holding guest's state
+ */
+struct ap_matrix_mdev {
+	struct list_head node;
+	struct ap_matrix matrix;
+	struct notifier_block group_notifier;
+	struct kvm *kvm;
+};
+
+extern int vfio_ap_mdev_register(void);
+extern void vfio_ap_mdev_unregister(void);
+
+#endif /* _VFIO_AP_PRIVATE_H_ */

include/uapi/linux/vfio.h

@@ -200,6 +200,7 @@ struct vfio_device_info {
 #define VFIO_DEVICE_FLAGS_PLATFORM (1 << 2)	/* vfio-platform device */
 #define VFIO_DEVICE_FLAGS_AMBA  (1 << 3)	/* vfio-amba device */
 #define VFIO_DEVICE_FLAGS_CCW	(1 << 4)	/* vfio-ccw device */
+#define VFIO_DEVICE_FLAGS_AP	(1 << 5)	/* vfio-ap device */
 	__u32	num_regions;	/* Max region index + 1 */
 	__u32	num_irqs;	/* Max IRQ index + 1 */
 };
@@ -215,6 +216,7 @@ struct vfio_device_info {
 #define VFIO_DEVICE_API_PLATFORM_STRING		"vfio-platform"
 #define VFIO_DEVICE_API_AMBA_STRING		"vfio-amba"
 #define VFIO_DEVICE_API_CCW_STRING		"vfio-ccw"
+#define VFIO_DEVICE_API_AP_STRING		"vfio-ap"
 
 /**
  * VFIO_DEVICE_GET_REGION_INFO - _IOWR(VFIO_TYPE, VFIO_BASE + 8,