Merge tag 'kvm-s390-pci-5.20' into kernelorgnext

KVM: s390/pci: enable zPCI for interpretive execution

Add the necessary code in s390 base, pci and KVM to enable interpretion
of PCI pasthru.

17 files changed, 1102 insertions, 37 deletions

diff --git a/arch/s390/include/asm/airq.h b/arch/s390/include/asm/airq.h
index 01936fdfaddb..e82e5626e139 100644
--- a/arch/s390/include/asm/airq.h
+++ b/arch/s390/include/asm/airq.h
@@ -12,10 +12,11 @@
 
 #include <linux/bit_spinlock.h>
 #include <linux/dma-mapping.h>
+#include <asm/tpi.h>
 
 struct airq_struct {
 	struct hlist_node list;		/* Handler queueing. */
-	void (*handler)(struct airq_struct *airq, bool floating);
+	void (*handler)(struct airq_struct *airq, struct tpi_info *tpi_info);
 	u8 *lsi_ptr;			/* Local-Summary-Indicator pointer */
 	u8 lsi_mask;			/* Local-Summary-Indicator mask */
 	u8 isc;				/* Interrupt-subclass */
@@ -46,8 +47,10 @@ struct airq_iv {
 #define AIRQ_IV_PTR		4	/* Allocate the ptr array */
 #define AIRQ_IV_DATA		8	/* Allocate the data array */
 #define AIRQ_IV_CACHELINE	16	/* Cacheline alignment for the vector */
+#define AIRQ_IV_GUESTVEC	32	/* Vector is a pinned guest page */
 
-struct airq_iv *airq_iv_create(unsigned long bits, unsigned long flags);
+struct airq_iv *airq_iv_create(unsigned long bits, unsigned long flags,
+			       unsigned long *vec);
 void airq_iv_release(struct airq_iv *iv);
 unsigned long airq_iv_alloc(struct airq_iv *iv, unsigned long num);
 void airq_iv_free(struct airq_iv *iv, unsigned long bit, unsigned long num);
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index a0fbe4820e0a..fca4fcf72a2a 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -19,6 +19,7 @@
 #include <linux/kvm.h>
 #include <linux/seqlock.h>
 #include <linux/module.h>
+#include <linux/pci.h>
 #include <asm/debug.h>
 #include <asm/cpu.h>
 #include <asm/fpu/api.h>
@@ -254,7 +255,10 @@ struct kvm_s390_sie_block {
 #define ECB2_IEP	0x20
 #define ECB2_PFMFI	0x08
 #define ECB2_ESCA	0x04
+#define ECB2_ZPCI_LSI	0x02
 	__u8    ecb2;                   /* 0x0062 */
+#define ECB3_AISI	0x20
+#define ECB3_AISII	0x10
 #define ECB3_DEA 0x08
 #define ECB3_AES 0x04
 #define ECB3_RI  0x01
@@ -759,6 +763,7 @@ struct kvm_vm_stat {
 	u64 inject_pfault_done;
 	u64 inject_service_signal;
 	u64 inject_virtio;
+	u64 aen_forward;
 };
 
 struct kvm_arch_memory_slot {
@@ -940,6 +945,7 @@ struct kvm_arch{
 	int use_cmma;
 	int use_pfmfi;
 	int use_skf;
+	int use_zpci_interp;
 	int user_cpu_state_ctrl;
 	int user_sigp;
 	int user_stsi;
@@ -963,6 +969,8 @@ struct kvm_arch{
 	DECLARE_BITMAP(idle_mask, KVM_MAX_VCPUS);
 	struct kvm_s390_gisa_interrupt gisa_int;
 	struct kvm_s390_pv pv;
+	struct list_head kzdev_list;
+	spinlock_t kzdev_list_lock;
 };
 
 #define KVM_HVA_ERR_BAD		(-1UL)
@@ -1013,4 +1021,19 @@ static inline void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
 static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) {}
 static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) {}
 
+#define __KVM_HAVE_ARCH_VM_FREE
+void kvm_arch_free_vm(struct kvm *kvm);
+
+#ifdef CONFIG_VFIO_PCI_ZDEV_KVM
+int kvm_s390_pci_register_kvm(struct zpci_dev *zdev, struct kvm *kvm);
+void kvm_s390_pci_unregister_kvm(struct zpci_dev *zdev);
+#else
+static inline int kvm_s390_pci_register_kvm(struct zpci_dev *dev,
+					    struct kvm *kvm)
+{
+	return -EPERM;
+}
+static inline void kvm_s390_pci_unregister_kvm(struct zpci_dev *dev) {}
+#endif
+
 #endif
diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h
index fdb9745ee998..85eb0ef9d4c3 100644
--- a/arch/s390/include/asm/pci.h
+++ b/arch/s390/include/asm/pci.h
@@ -9,6 +9,7 @@
 #include <asm-generic/pci.h>
 #include <asm/pci_clp.h>
 #include <asm/pci_debug.h>
+#include <asm/pci_insn.h>
 #include <asm/sclp.h>
 
 #define PCIBIOS_MIN_IO		0x1000
@@ -97,6 +98,7 @@ struct zpci_bar_struct {
 };
 
 struct s390_domain;
+struct kvm_zdev;
 
 #define ZPCI_FUNCTIONS_PER_BUS 256
 struct zpci_bus {
@@ -123,11 +125,14 @@ struct zpci_dev {
 	enum zpci_state state;
 	u32		fid;		/* function ID, used by sclp */
 	u32		fh;		/* function handle, used by insn's */
+	u32		gisa;		/* GISA designation for passthrough */
 	u16		vfn;		/* virtual function number */
 	u16		pchid;		/* physical channel ID */
+	u16		maxstbl;	/* Maximum store block size */
 	u8		pfgid;		/* function group ID */
 	u8		pft;		/* pci function type */
 	u8		port;
+	u8		dtsm;		/* Supported DT mask */
 	u8		rid_available	: 1;
 	u8		has_hp_slot	: 1;
 	u8		has_resources	: 1;
@@ -186,7 +191,10 @@ struct zpci_dev {
 
 	struct dentry	*debugfs_dev;
 
+	/* IOMMU and passthrough */
 	struct s390_domain *s390_domain; /* s390 IOMMU domain data */
+	struct kvm_zdev *kzdev;
+	struct mutex kzdev_lock;
 };
 
 static inline bool zdev_enabled(struct zpci_dev *zdev)
@@ -198,6 +206,9 @@ extern const struct attribute_group *zpci_attr_groups[];
 extern unsigned int s390_pci_force_floating __initdata;
 extern unsigned int s390_pci_no_rid;
 
+extern union zpci_sic_iib *zpci_aipb;
+extern struct airq_iv *zpci_aif_sbv;
+
 /* -----------------------------------------------------------------------------
   Prototypes
 ----------------------------------------------------------------------------- */
diff --git a/arch/s390/include/asm/pci_clp.h b/arch/s390/include/asm/pci_clp.h
index 1f4b666e85ee..d6189ed14f84 100644
--- a/arch/s390/include/asm/pci_clp.h
+++ b/arch/s390/include/asm/pci_clp.h
@@ -153,9 +153,11 @@ struct clp_rsp_query_pci_grp {
 	u8			:  6;
 	u8 frame		:  1;
 	u8 refresh		:  1;	/* TLB refresh mode */
-	u16 reserved2;
+	u16			:  3;
+	u16 maxstbl		: 13;	/* Maximum store block size */
 	u16 mui;
-	u16			: 16;
+	u8 dtsm;			/* Supported DT mask */
+	u8 reserved3;
 	u16 maxfaal;
 	u16			:  4;
 	u16 dnoi		: 12;
@@ -173,7 +175,8 @@ struct clp_req_set_pci {
 	u16 reserved2;
 	u8 oc;				/* operation controls */
 	u8 ndas;			/* number of dma spaces */
-	u64 reserved3;
+	u32 reserved3;
+	u32 gisa;			/* GISA designation */
 } __packed;
 
 /* Set PCI function response */
diff --git a/arch/s390/include/asm/pci_insn.h b/arch/s390/include/asm/pci_insn.h
index 61cf9531f68f..e5f57cfe1d45 100644
--- a/arch/s390/include/asm/pci_insn.h
+++ b/arch/s390/include/asm/pci_insn.h
@@ -98,6 +98,15 @@ struct zpci_fib {
 	u32 gd;
 } __packed __aligned(8);
 
+/* Set Interruption Controls Operation Controls  */
+#define	SIC_IRQ_MODE_ALL		0
+#define	SIC_IRQ_MODE_SINGLE		1
+#define	SIC_SET_AENI_CONTROLS		2
+#define	SIC_IRQ_MODE_DIRECT		4
+#define	SIC_IRQ_MODE_D_ALL		16
+#define	SIC_IRQ_MODE_D_SINGLE		17
+#define	SIC_IRQ_MODE_SET_CPU		18
+
 /* directed interruption information block */
 struct zpci_diib {
 	u32 : 1;
@@ -119,9 +128,20 @@ struct zpci_cdiib {
 	u64 : 64;
 } __packed __aligned(8);
 
+/* adapter interruption parameters block */
+struct zpci_aipb {
+	u64 faisb;
+	u64 gait;
+	u16 : 13;
+	u16 afi : 3;
+	u32 : 32;
+	u16 faal;
+} __packed __aligned(8);
+
 union zpci_sic_iib {
 	struct zpci_diib diib;
 	struct zpci_cdiib cdiib;
+	struct zpci_aipb aipb;
 };
 
 DECLARE_STATIC_KEY_FALSE(have_mio);
@@ -134,13 +154,6 @@ int __zpci_store(u64 data, u64 req, u64 offset);
 int zpci_store(const volatile void __iomem *addr, u64 data, unsigned long len);
 int __zpci_store_block(const u64 *data, u64 req, u64 offset);
 void zpci_barrier(void);
-int __zpci_set_irq_ctrl(u16 ctl, u8 isc, union zpci_sic_iib *iib);
-
-static inline int zpci_set_irq_ctrl(u16 ctl, u8 isc)
-{
-	union zpci_sic_iib iib = {{0}};
-
-	return __zpci_set_irq_ctrl(ctl, isc, &iib);
-}
+int zpci_set_irq_ctrl(u16 ctl, u8 isc, union zpci_sic_iib *iib);
 
 #endif
diff --git a/arch/s390/include/asm/sclp.h b/arch/s390/include/asm/sclp.h
index 236b34b75ddb..addefe8ccdba 100644
--- a/arch/s390/include/asm/sclp.h
+++ b/arch/s390/include/asm/sclp.h
@@ -88,6 +88,10 @@ struct sclp_info {
 	unsigned char has_sipl : 1;
 	unsigned char has_dirq : 1;
 	unsigned char has_iplcc : 1;
+	unsigned char has_zpci_lsi : 1;
+	unsigned char has_aisii : 1;
+	unsigned char has_aeni : 1;
+	unsigned char has_aisi : 1;
 	unsigned int ibc;
 	unsigned int mtid;
 	unsigned int mtid_cp;
diff --git a/arch/s390/include/asm/tpi.h b/arch/s390/include/asm/tpi.h
index 1ac538b8cbf5..f76e5fdff23a 100644
--- a/arch/s390/include/asm/tpi.h
+++ b/arch/s390/include/asm/tpi.h
@@ -19,6 +19,19 @@ struct tpi_info {
 	u32 :12;
 } __packed __aligned(4);
 
+/* I/O-Interruption Code as stored by TPI for an Adapter I/O */
+struct tpi_adapter_info {
+	u32 aism:8;
+	u32 :22;
+	u32 error:1;
+	u32 forward:1;
+	u32 reserved;
+	u32 adapter_IO:1;
+	u32 directed_irq:1;
+	u32 isc:3;
+	u32 :27;
+} __packed __aligned(4);
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_S390_TPI_H */
diff --git a/arch/s390/kvm/Makefile b/arch/s390/kvm/Makefile
index 26f4a74e5ce4..02217fb4ae10 100644
--- a/arch/s390/kvm/Makefile
+++ b/arch/s390/kvm/Makefile
@@ -10,4 +10,5 @@ ccflags-y := -Ivirt/kvm -Iarch/s390/kvm
 kvm-y += kvm-s390.o intercept.o interrupt.o priv.o sigp.o
 kvm-y += diag.o gaccess.o guestdbg.o vsie.o pv.o
 
+kvm-$(CONFIG_VFIO_PCI_ZDEV_KVM) += pci.o
 obj-$(CONFIG_KVM) += kvm.o
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index af96dc0549a4..d8e1fce78b7c 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -28,9 +28,11 @@
 #include <asm/switch_to.h>
 #include <asm/nmi.h>
 #include <asm/airq.h>
+#include <asm/tpi.h>
 #include "kvm-s390.h"
 #include "gaccess.h"
 #include "trace-s390.h"
+#include "pci.h"
 
 #define PFAULT_INIT 0x0600
 #define PFAULT_DONE 0x0680
@@ -3311,10 +3313,87 @@ out:
 }
 EXPORT_SYMBOL_GPL(kvm_s390_gisc_unregister);
 
-static void gib_alert_irq_handler(struct airq_struct *airq, bool floating)
+static void aen_host_forward(unsigned long si)
 {
+	struct kvm_s390_gisa_interrupt *gi;
+	struct zpci_gaite *gaite;
+	struct kvm *kvm;
+
+	gaite = (struct zpci_gaite *)aift->gait +
+		(si * sizeof(struct zpci_gaite));
+	if (gaite->count == 0)
+		return;
+	if (gaite->aisb != 0)
+		set_bit_inv(gaite->aisbo, (unsigned long *)gaite->aisb);
+
+	kvm = kvm_s390_pci_si_to_kvm(aift, si);
+	if (!kvm)
+		return;
+	gi = &kvm->arch.gisa_int;
+
+	if (!(gi->origin->g1.simm & AIS_MODE_MASK(gaite->gisc)) ||
+	    !(gi->origin->g1.nimm & AIS_MODE_MASK(gaite->gisc))) {
+		gisa_set_ipm_gisc(gi->origin, gaite->gisc);
+		if (hrtimer_active(&gi->timer))
+			hrtimer_cancel(&gi->timer);
+		hrtimer_start(&gi->timer, 0, HRTIMER_MODE_REL);
+		kvm->stat.aen_forward++;
+	}
+}
+
+static void aen_process_gait(u8 isc)
+{
+	bool found = false, first = true;
+	union zpci_sic_iib iib = {{0}};
+	unsigned long si, flags;
+
+	spin_lock_irqsave(&aift->gait_lock, flags);
+
+	if (!aift->gait) {
+		spin_unlock_irqrestore(&aift->gait_lock, flags);
+		return;
+	}
+
+	for (si = 0;;) {
+		/* Scan adapter summary indicator bit vector */
+		si = airq_iv_scan(aift->sbv, si, airq_iv_end(aift->sbv));
+		if (si == -1UL) {
+			if (first || found) {
+				/* Re-enable interrupts. */
+				zpci_set_irq_ctrl(SIC_IRQ_MODE_SINGLE, isc,
+						  &iib);
+				first = found = false;
+			} else {
+				/* Interrupts on and all bits processed */
+				break;
+			}
+			found = false;
+			si = 0;
+			/* Scan again after re-enabling interrupts */
+			continue;
+		}
+		found = true;
+		aen_host_forward(si);
+	}
+
+	spin_unlock_irqrestore(&aift->gait_lock, flags);
+}
+
+static void gib_alert_irq_handler(struct airq_struct *airq,
+				  struct tpi_info *tpi_info)
+{
+	struct tpi_adapter_info *info = (struct tpi_adapter_info *)tpi_info;
+
 	inc_irq_stat(IRQIO_GAL);
-	process_gib_alert_list();
+
+	if ((info->forward || info->error) &&
+	    IS_ENABLED(CONFIG_VFIO_PCI_ZDEV_KVM)) {
+		aen_process_gait(info->isc);
+		if (info->aism != 0)
+			process_gib_alert_list();
+	} else {
+		process_gib_alert_list();
+	}
 }
 
 static struct airq_struct gib_alert_irq = {
@@ -3326,6 +3405,11 @@ void kvm_s390_gib_destroy(void)
 {
 	if (!gib)
 		return;
+	if (kvm_s390_pci_interp_allowed() && aift) {
+		mutex_lock(&aift->aift_lock);
+		kvm_s390_pci_aen_exit();
+		mutex_unlock(&aift->aift_lock);
+	}
 	chsc_sgib(0);
 	unregister_adapter_interrupt(&gib_alert_irq);
 	free_page((unsigned long)gib);
@@ -3363,6 +3447,14 @@ int kvm_s390_gib_init(u8 nisc)
 		goto out_unreg_gal;
 	}
 
+	if (kvm_s390_pci_interp_allowed()) {
+		if (kvm_s390_pci_aen_init(nisc)) {
+			pr_err("Initializing AEN for PCI failed\n");
+			rc = -EIO;
+			goto out_unreg_gal;
+		}
+	}
+
 	KVM_EVENT(3, "gib 0x%pK (nisc=%d) initialized", gib, gib->nisc);
 	goto out;
 
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 72bd5c9b9617..18b0a6f0cd9c 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -47,6 +47,7 @@
 #include <asm/fpu/api.h>
 #include "kvm-s390.h"
 #include "gaccess.h"
+#include "pci.h"
 
 #define CREATE_TRACE_POINTS
 #include "trace.h"
@@ -63,7 +64,8 @@ const struct _kvm_stats_desc kvm_vm_stats_desc[] = {
 	STATS_DESC_COUNTER(VM, inject_float_mchk),
 	STATS_DESC_COUNTER(VM, inject_pfault_done),
 	STATS_DESC_COUNTER(VM, inject_service_signal),
-	STATS_DESC_COUNTER(VM, inject_virtio)
+	STATS_DESC_COUNTER(VM, inject_virtio),
+	STATS_DESC_COUNTER(VM, aen_forward)
 };
 
 const struct kvm_stats_header kvm_vm_stats_header = {
@@ -502,6 +504,14 @@ int kvm_arch_init(void *opaque)
 		goto out;
 	}
 
+	if (kvm_s390_pci_interp_allowed()) {
+		rc = kvm_s390_pci_init();
+		if (rc) {
+			pr_err("Unable to allocate AIFT for PCI\n");
+			goto out;
+		}
+	}
+
 	rc = kvm_s390_gib_init(GAL_ISC);
 	if (rc)
 		goto out;
@@ -516,6 +526,8 @@ out:
 void kvm_arch_exit(void)
 {
 	kvm_s390_gib_destroy();
+	if (kvm_s390_pci_interp_allowed())
+		kvm_s390_pci_exit();
 	debug_unregister(kvm_s390_dbf);
 	debug_unregister(kvm_s390_dbf_uv);
 }
@@ -626,6 +638,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		}
 		break;
 	}
+	case KVM_CAP_S390_ZPCI_OP:
+		r = kvm_s390_pci_interp_allowed();
+		break;
 	default:
 		r = 0;
 	}
@@ -1039,6 +1054,42 @@ static int kvm_s390_vm_set_crypto(struct kvm *kvm, struct kvm_device_attr *attr)
 	return 0;
 }
 
+static void kvm_s390_vcpu_pci_setup(struct kvm_vcpu *vcpu)
+{
+	/* Only set the ECB bits after guest requests zPCI interpretation */
+	if (!vcpu->kvm->arch.use_zpci_interp)
+		return;
+
+	vcpu->arch.sie_block->ecb2 |= ECB2_ZPCI_LSI;
+	vcpu->arch.sie_block->ecb3 |= ECB3_AISII + ECB3_AISI;
+}
+
+void kvm_s390_vcpu_pci_enable_interp(struct kvm *kvm)
+{
+	struct kvm_vcpu *vcpu;
+	unsigned long i;
+
+	lockdep_assert_held(&kvm->lock);
+
+	if (!kvm_s390_pci_interp_allowed())
+		return;
+
+	/*
+	 * If host is configured for PCI and the necessary facilities are
+	 * available, turn on interpretation for the life of this guest
+	 */
+	kvm->arch.use_zpci_interp = 1;
+
+	kvm_s390_vcpu_block_all(kvm);
+
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		kvm_s390_vcpu_pci_setup(vcpu);
+		kvm_s390_sync_request(KVM_REQ_VSIE_RESTART, vcpu);
+	}
+
+	kvm_s390_vcpu_unblock_all(kvm);
+}
+
 static void kvm_s390_sync_request_broadcast(struct kvm *kvm, int req)
 {
 	unsigned long cx;
@@ -2772,6 +2823,19 @@ long kvm_arch_vm_ioctl(struct file *filp,
 			r = -EFAULT;
 		break;
 	}
+	case KVM_S390_ZPCI_OP: {
+		struct kvm_s390_zpci_op args;
+
+		r = -EINVAL;
+		if (!IS_ENABLED(CONFIG_VFIO_PCI_ZDEV_KVM))
+			break;
+		if (copy_from_user(&args, argp, sizeof(args))) {
+			r = -EFAULT;
+			break;
+		}
+		r = kvm_s390_pci_zpci_op(kvm, &args);
+		break;
+	}
 	default:
 		r = -ENOTTY;
 	}
@@ -2933,6 +2997,14 @@ static void sca_dispose(struct kvm *kvm)
 	kvm->arch.sca = NULL;
 }
 
+void kvm_arch_free_vm(struct kvm *kvm)
+{
+	if (IS_ENABLED(CONFIG_VFIO_PCI_ZDEV_KVM))
+		kvm_s390_pci_clear_list(kvm);
+
+	__kvm_arch_free_vm(kvm);
+}
+
 int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 {
 	gfp_t alloc_flags = GFP_KERNEL_ACCOUNT;
@@ -3015,6 +3087,13 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 
 	kvm_s390_crypto_init(kvm);
 
+	if (IS_ENABLED(CONFIG_VFIO_PCI_ZDEV_KVM)) {
+		mutex_lock(&kvm->lock);
+		kvm_s390_pci_init_list(kvm);
+		kvm_s390_vcpu_pci_enable_interp(kvm);
+		mutex_unlock(&kvm->lock);
+	}
+
 	mutex_init(&kvm->arch.float_int.ais_lock);
 	spin_lock_init(&kvm->arch.float_int.lock);
 	for (i = 0; i < FIRQ_LIST_COUNT; i++)
@@ -3513,6 +3592,8 @@ static int kvm_s390_vcpu_setup(struct kvm_vcpu *vcpu)
 
 	kvm_s390_vcpu_crypto_setup(vcpu);
 
+	kvm_s390_vcpu_pci_setup(vcpu);
+
 	mutex_lock(&vcpu->kvm->lock);
 	if (kvm_s390_pv_is_protected(vcpu->kvm)) {
 		rc = kvm_s390_pv_create_cpu(vcpu, &uvrc, &uvrrc);
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index dd01d989816f..cf4f4d1713ea 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -513,6 +513,16 @@ void kvm_s390_reinject_machine_check(struct kvm_vcpu *vcpu,
 void kvm_s390_vcpu_crypto_reset_all(struct kvm *kvm);
 
 /**
+ * kvm_s390_vcpu_pci_enable_interp
+ *
+ * Set the associated PCI attributes for each vcpu to allow for zPCI Load/Store
+ * interpretation as well as adapter interruption forwarding.
+ *
+ * @kvm: the KVM guest
+ */
+void kvm_s390_vcpu_pci_enable_interp(struct kvm *kvm);
+
+/**
  * diag9c_forwarding_hz
  *
  * Set the maximum number of diag9c forwarding per second
diff --git a/arch/s390/kvm/pci.c b/arch/s390/kvm/pci.c
new file mode 100644
index 000000000000..4946fb7757d6
--- /dev/null
+++ b/arch/s390/kvm/pci.c
@@ -0,0 +1,690 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * s390 kvm PCI passthrough support
+ *
+ * Copyright IBM Corp. 2022
+ *
+ *    Author(s): Matthew Rosato <mjrosato@linux.ibm.com>
+ */
+
+#include <linux/kvm_host.h>
+#include <linux/pci.h>
+#include <asm/pci.h>
+#include <asm/pci_insn.h>
+#include <asm/pci_io.h>
+#include <asm/sclp.h>
+#include "pci.h"
+#include "kvm-s390.h"
+
+struct zpci_aift *aift;
+
+static inline int __set_irq_noiib(u16 ctl, u8 isc)
+{
+	union zpci_sic_iib iib = {{0}};
+
+	return zpci_set_irq_ctrl(ctl, isc, &iib);
+}
+
+void kvm_s390_pci_aen_exit(void)
+{
+	unsigned long flags;
+	struct kvm_zdev **gait_kzdev;
+
+	lockdep_assert_held(&aift->aift_lock);
+
+	/*
+	 * Contents of the aipb remain registered for the life of the host
+	 * kernel, the information preserved in zpci_aipb and zpci_aif_sbv
+	 * in case we insert the KVM module again later.  Clear the AIFT
+	 * information and free anything not registered with underlying
+	 * firmware.
+	 */
+	spin_lock_irqsave(&aift->gait_lock, flags);
+	gait_kzdev = aift->kzdev;
+	aift->gait = NULL;
+	aift->sbv = NULL;
+	aift->kzdev = NULL;
+	spin_unlock_irqrestore(&aift->gait_lock, flags);
+
+	kfree(gait_kzdev);
+}
+
+static int zpci_setup_aipb(u8 nisc)
+{
+	struct page *page;
+	int size, rc;
+
+	zpci_aipb = kzalloc(sizeof(union zpci_sic_iib), GFP_KERNEL);
+	if (!zpci_aipb)
+		return -ENOMEM;
+
+	aift->sbv = airq_iv_create(ZPCI_NR_DEVICES, AIRQ_IV_ALLOC, 0);
+	if (!aift->sbv) {
+		rc = -ENOMEM;
+		goto free_aipb;
+	}
+	zpci_aif_sbv = aift->sbv;
+	size = get_order(PAGE_ALIGN(ZPCI_NR_DEVICES *
+						sizeof(struct zpci_gaite)));
+	page = alloc_pages(GFP_KERNEL | __GFP_ZERO, size);
+	if (!page) {
+		rc = -ENOMEM;
+		goto free_sbv;
+	}
+	aift->gait = (struct zpci_gaite *)page_to_phys(page);
+
+	zpci_aipb->aipb.faisb = virt_to_phys(aift->sbv->vector);
+	zpci_aipb->aipb.gait = virt_to_phys(aift->gait);
+	zpci_aipb->aipb.afi = nisc;
+	zpci_aipb->aipb.faal = ZPCI_NR_DEVICES;
+
+	/* Setup Adapter Event Notification Interpretation */
+	if (zpci_set_irq_ctrl(SIC_SET_AENI_CONTROLS, 0, zpci_aipb)) {
+		rc = -EIO;
+		goto free_gait;
+	}
+
+	return 0;
+
+free_gait:
+	free_pages((unsigned long)aift->gait, size);
+free_sbv:
+	airq_iv_release(aift->sbv);
+	zpci_aif_sbv = NULL;
+free_aipb:
+	kfree(zpci_aipb);
+	zpci_aipb = NULL;
+
+	return rc;
+}
+
+static int zpci_reset_aipb(u8 nisc)
+{
+	/*
+	 * AEN registration can only happen once per system boot.  If
+	 * an aipb already exists then AEN was already registered and
+	 * we can re-use the aipb contents.  This can only happen if
+	 * the KVM module was removed and re-inserted.  However, we must
+	 * ensure that the same forwarding ISC is used as this is assigned
+	 * during KVM module load.
+	 */
+	if (zpci_aipb->aipb.afi != nisc)
+		return -EINVAL;
+
+	aift->sbv = zpci_aif_sbv;
+	aift->gait = (struct zpci_gaite *)zpci_aipb->aipb.gait;
+
+	return 0;
+}
+
+int kvm_s390_pci_aen_init(u8 nisc)
+{
+	int rc = 0;
+
+	/* If already enabled for AEN, bail out now */
+	if (aift->gait || aift->sbv)
+		return -EPERM;
+
+	mutex_lock(&aift->aift_lock);
+	aift->kzdev = kcalloc(ZPCI_NR_DEVICES, sizeof(struct kvm_zdev),
+			      GFP_KERNEL);
+	if (!aift->kzdev) {
+		rc = -ENOMEM;
+		goto unlock;
+	}
+
+	if (!zpci_aipb)
+		rc = zpci_setup_aipb(nisc);
+	else
+		rc = zpci_reset_aipb(nisc);
+	if (rc)
+		goto free_zdev;
+
+	/* Enable floating IRQs */
+	if (__set_irq_noiib(SIC_IRQ_MODE_SINGLE, nisc)) {
+		rc = -EIO;
+		kvm_s390_pci_aen_exit();
+	}
+
+	goto unlock;
+
+free_zdev:
+	kfree(aift->kzdev);
+unlock:
+	mutex_unlock(&aift->aift_lock);
+	return rc;
+}
+
+/* Modify PCI: Register floating adapter interruption forwarding */
+static int kvm_zpci_set_airq(struct zpci_dev *zdev)
+{
+	u64 req = ZPCI_CREATE_REQ(zdev->fh, 0, ZPCI_MOD_FC_REG_INT);
+	struct zpci_fib fib = {};
+	u8 status;
+
+	fib.fmt0.isc = zdev->kzdev->fib.fmt0.isc;
+	fib.fmt0.sum = 1;       /* enable summary notifications */
+	fib.fmt0.noi = airq_iv_end(zdev->aibv);
+	fib.fmt0.aibv = virt_to_phys(zdev->aibv->vector);
+	fib.fmt0.aibvo = 0;
+	fib.fmt0.aisb = virt_to_phys(aift->sbv->vector + (zdev->aisb / 64) * 8);
+	fib.fmt0.aisbo = zdev->aisb & 63;
+	fib.gd = zdev->gisa;
+
+	return zpci_mod_fc(req, &fib, &status) ? -EIO : 0;
+}
+
+/* Modify PCI: Unregister floating adapter interruption forwarding */
+static int kvm_zpci_clear_airq(struct zpci_dev *zdev)
+{
+	u64 req = ZPCI_CREATE_REQ(zdev->fh, 0, ZPCI_MOD_FC_DEREG_INT);
+	struct zpci_fib fib = {};
+	u8 cc, status;
+
+	fib.gd = zdev->gisa;
+
+	cc = zpci_mod_fc(req, &fib, &status);
+	if (cc == 3 || (cc == 1 && status == 24))
+		/* Function already gone or IRQs already deregistered. */
+		cc = 0;
+
+	return cc ? -EIO : 0;
+}
+
+static inline void unaccount_mem(unsigned long nr_pages)
+{
+	struct user_struct *user = get_uid(current_user());
+
+	if (user)
+		atomic_long_sub(nr_pages, &user->locked_vm);
+	if (current->mm)
+		atomic64_sub(nr_pages, &current->mm->pinned_vm);
+}
+
+static inline int account_mem(unsigned long nr_pages)
+{
+	struct user_struct *user = get_uid(current_user());
+	unsigned long page_limit, cur_pages, new_pages;
+
+	page_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
+
+	do {
+		cur_pages = atomic_long_read(&user->locked_vm);
+		new_pages = cur_pages + nr_pages;
+		if (new_pages > page_limit)
+			return -ENOMEM;
+	} while (atomic_long_cmpxchg(&user->locked_vm, cur_pages,
+					new_pages) != cur_pages);
+
+	atomic64_add(nr_pages, &current->mm->pinned_vm);
+
+	return 0;
+}
+
+static int kvm_s390_pci_aif_enable(struct zpci_dev *zdev, struct zpci_fib *fib,
+				   bool assist)
+{
+	struct page *pages[1], *aibv_page, *aisb_page = NULL;
+	unsigned int msi_vecs, idx;
+	struct zpci_gaite *gaite;
+	unsigned long hva, bit;
+	struct kvm *kvm;
+	phys_addr_t gaddr;
+	int rc = 0, gisc, npages, pcount = 0;
+
+	/*
+	 * Interrupt forwarding is only applicable if the device is already
+	 * enabled for interpretation
+	 */
+	if (zdev->gisa == 0)
+		return -EINVAL;
+
+	kvm = zdev->kzdev->kvm;
+	msi_vecs = min_t(unsigned int, fib->fmt0.noi, zdev->max_msi);
+
+	/* Get the associated forwarding ISC - if invalid, return the error */
+	gisc = kvm_s390_gisc_register(kvm, fib->fmt0.isc);
+	if (gisc < 0)
+		return gisc;
+
+	/* Replace AIBV address */
+	idx = srcu_read_lock(&kvm->srcu);
+	hva = gfn_to_hva(kvm, gpa_to_gfn((gpa_t)fib->fmt0.aibv));
+	npages = pin_user_pages_fast(hva, 1, FOLL_WRITE | FOLL_LONGTERM, pages);
+	srcu_read_unlock(&kvm->srcu, idx);
+	if (npages < 1) {
+		rc = -EIO;
+		goto out;
+	}
+	aibv_page = pages[0];
+	pcount++;
+	gaddr = page_to_phys(aibv_page) + (fib->fmt0.aibv & ~PAGE_MASK);
+	fib->fmt0.aibv = gaddr;
+
+	/* Pin the guest AISB if one was specified */
+	if (fib->fmt0.sum == 1) {
+		idx = srcu_read_lock(&kvm->srcu);
+		hva = gfn_to_hva(kvm, gpa_to_gfn((gpa_t)fib->fmt0.aisb));
+		npages = pin_user_pages_fast(hva, 1, FOLL_WRITE | FOLL_LONGTERM,
+					     pages);
+		srcu_read_unlock(&kvm->srcu, idx);
+		if (npages < 1) {
+			rc = -EIO;
+			goto unpin1;
+		}
+		aisb_page = pages[0];
+		pcount++;
+	}
+
+	/* Account for pinned pages, roll back on failure */
+	if (account_mem(pcount))
+		goto unpin2;
+
+	/* AISB must be allocated before we can fill in GAITE */
+	mutex_lock(&aift->aift_lock);
+	bit = airq_iv_alloc_bit(aift->sbv);
+	if (bit == -1UL)
+		goto unlock;
+	zdev->aisb = bit; /* store the summary bit number */
+	zdev->aibv = airq_iv_create(msi_vecs, AIRQ_IV_DATA |
+				    AIRQ_IV_BITLOCK |
+				    AIRQ_IV_GUESTVEC,
+				    phys_to_virt(fib->fmt0.aibv));
+
+	spin_lock_irq(&aift->gait_lock);
+	gaite = (struct zpci_gaite *)aift->gait + (zdev->aisb *
+						   sizeof(struct zpci_gaite));
+
+	/* If assist not requested, host will get all alerts */
+	if (assist)
+		gaite->gisa = (u32)virt_to_phys(&kvm->arch.sie_page2->gisa);
+	else
+		gaite->gisa = 0;
+
+	gaite->gisc = fib->fmt0.isc;
+	gaite->count++;
+	gaite->aisbo = fib->fmt0.aisbo;
+	gaite->aisb = virt_to_phys(page_address(aisb_page) + (fib->fmt0.aisb &
+							      ~PAGE_MASK));
+	aift->kzdev[zdev->aisb] = zdev->kzdev;
+	spin_unlock_irq(&aift->gait_lock);
+
+	/* Update guest FIB for re-issue */
+	fib->fmt0.aisbo = zdev->aisb & 63;
+	fib->fmt0.aisb = virt_to_phys(aift->sbv->vector + (zdev->aisb / 64) * 8);
+	fib->fmt0.isc = gisc;
+
+	/* Save some guest fib values in the host for later use */
+	zdev->kzdev->fib.fmt0.isc = fib->fmt0.isc;
+	zdev->kzdev->fib.fmt0.aibv = fib->fmt0.aibv;
+	mutex_unlock(&aift->aift_lock);
+
+	/* Issue the clp to setup the irq now */
+	rc = kvm_zpci_set_airq(zdev);
+	return rc;
+
+unlock:
+	mutex_unlock(&aift->aift_lock);
+unpin2:
+	if (fib->fmt0.sum == 1)
+		unpin_user_page(aisb_page);
+unpin1:
+	unpin_user_page(aibv_page);
+out:
+	return rc;
+}
+
+static int kvm_s390_pci_aif_disable(struct zpci_dev *zdev, bool force)
+{
+	struct kvm_zdev *kzdev = zdev->kzdev;
+	struct zpci_gaite *gaite;
+	struct page *vpage = NULL, *spage = NULL;
+	int rc, pcount = 0;
+	u8 isc;
+
+	if (zdev->gisa == 0)
+		return -EINVAL;
+
+	mutex_lock(&aift->aift_lock);
+
+	/*
+	 * If the clear fails due to an error, leave now unless we know this
+	 * device is about to go away (force) -- In that case clear the GAITE
+	 * regardless.
+	 */
+	rc = kvm_zpci_clear_airq(zdev);
+	if (rc && !force)
+		goto out;
+
+	if (zdev->kzdev->fib.fmt0.aibv == 0)
+		goto out;
+	spin_lock_irq(&aift->gait_lock);
+	gaite = (struct zpci_gaite *)aift->gait + (zdev->aisb *
+						   sizeof(struct zpci_gaite));
+	isc = gaite->gisc;
+	gaite->count--;
+	if (gaite->count == 0) {
+		/* Release guest AIBV and AISB */
+		vpage = phys_to_page(kzdev->fib.fmt0.aibv);
+		if (gaite->aisb != 0)
+			spage = phys_to_page(gaite->aisb);
+		/* Clear the GAIT entry */
+		gaite->aisb = 0;
+		gaite->gisc = 0;
+		gaite->aisbo = 0;
+		gaite->gisa = 0;
+		aift->kzdev[zdev->aisb] = 0;
+		/* Clear zdev info */
+		airq_iv_free_bit(aift->sbv, zdev->aisb);
+		airq_iv_release(zdev->aibv);
+		zdev->aisb = 0;
+		zdev->aibv = NULL;
+	}
+	spin_unlock_irq(&aift->gait_lock);
+	kvm_s390_gisc_unregister(kzdev->kvm, isc);
+	kzdev->fib.fmt0.isc = 0;
+	kzdev->fib.fmt0.aibv = 0;
+
+	if (vpage) {
+		unpin_user_page(vpage);
+		pcount++;
+	}
+	if (spage) {
+		unpin_user_page(spage);
+		pcount++;
+	}
+	if (pcount > 0)
+		unaccount_mem(pcount);
+out:
+	mutex_unlock(&aift->aift_lock);
+
+	return rc;
+}
+
+static int kvm_s390_pci_dev_open(struct zpci_dev *zdev)
+{
+	struct kvm_zdev *kzdev;
+
+	kzdev = kzalloc(sizeof(struct kvm_zdev), GFP_KERNEL);
+	if (!kzdev)
+		return -ENOMEM;
+
+	kzdev->zdev = zdev;
+	zdev->kzdev = kzdev;
+
+	return 0;
+}
+
+static void kvm_s390_pci_dev_release(struct zpci_dev *zdev)
+{
+	struct kvm_zdev *kzdev;
+
+	kzdev = zdev->kzdev;
+	WARN_ON(kzdev->zdev != zdev);
+	zdev->kzdev = NULL;
+	kfree(kzdev);
+}
+
+
+/*
+ * Register device with the specified KVM. If interpetation facilities are
+ * available, enable them and let userspace indicate whether or not they will
+ * be used (specify SHM bit to disable).
+ */
+int kvm_s390_pci_register_kvm(struct zpci_dev *zdev, struct kvm *kvm)
+{
+	int rc;
+
+	if (!zdev)
+		return -EINVAL;
+
+	mutex_lock(&zdev->kzdev_lock);
+
+	if (zdev->kzdev || zdev->gisa != 0 || !kvm) {
+		mutex_unlock(&zdev->kzdev_lock);
+		return -EINVAL;
+	}
+
+	kvm_get_kvm(kvm);
+
+	mutex_lock(&kvm->lock);
+
+	rc = kvm_s390_pci_dev_open(zdev);
+	if (rc)
+		goto err;
+
+	/*
+	 * If interpretation facilities aren't available, add the device to
+	 * the kzdev list but don't enable for interpretation.
+	 */
+	if (!kvm_s390_pci_interp_allowed())
+		goto out;
+
+	/*
+	 * If this is the first request to use an interpreted device, make the
+	 * necessary vcpu changes
+	 */
+	if (!kvm->arch.use_zpci_interp)
+		kvm_s390_vcpu_pci_enable_interp(kvm);
+
+	if (zdev_enabled(zdev)) {
+		rc = zpci_disable_device(zdev);
+		if (rc)
+			goto err;
+	}
+
+	/*
+	 * Store information about the identity of the kvm guest allowed to
+	 * access this device via interpretation to be used by host CLP
+	 */
+	zdev->gisa = (u32)virt_to_phys(&kvm->arch.sie_page2->gisa);
+
+	rc = zpci_enable_device(zdev);
+	if (rc)
+		goto clear_gisa;
+
+	/* Re-register the IOMMU that was already created */
+	rc = zpci_register_ioat(zdev, 0, zdev->start_dma, zdev->end_dma,
+				virt_to_phys(zdev->dma_table));
+	if (rc)
+		goto clear_gisa;
+
+out:
+	zdev->kzdev->kvm = kvm;
+
+	spin_lock(&kvm->arch.kzdev_list_lock);
+	list_add_tail(&zdev->kzdev->entry, &kvm->arch.kzdev_list);
+	spin_unlock(&kvm->arch.kzdev_list_lock);
+
+	mutex_unlock(&kvm->lock);
+	mutex_unlock(&zdev->kzdev_lock);
+	return 0;
+
+clear_gisa:
+	zdev->gisa = 0;
+err:
+	if (zdev->kzdev)
+		kvm_s390_pci_dev_release(zdev);
+	mutex_unlock(&kvm->lock);
+	mutex_unlock(&zdev->kzdev_lock);
+	kvm_put_kvm(kvm);
+	return rc;
+}
+EXPORT_SYMBOL_GPL(kvm_s390_pci_register_kvm);
+
+void kvm_s390_pci_unregister_kvm(struct zpci_dev *zdev)
+{
+	struct kvm *kvm;
+
+	if (!zdev)
+		return;
+
+	mutex_lock(&zdev->kzdev_lock);
+
+	if (WARN_ON(!zdev->kzdev)) {
+		mutex_unlock(&zdev->kzdev_lock);
+		return;
+	}
+
+	kvm = zdev->kzdev->kvm;
+	mutex_lock(&kvm->lock);
+
+	/*
+	 * A 0 gisa means interpretation was never enabled, just remove the
+	 * device from the list.
+	 */
+	if (zdev->gisa == 0)
+		goto out;
+
+	/* Forwarding must be turned off before interpretation */
+	if (zdev->kzdev->fib.fmt0.aibv != 0)
+		kvm_s390_pci_aif_disable(zdev, true);
+
+	/* Remove the host CLP guest designation */
+	zdev->gisa = 0;
+
+	if (zdev_enabled(zdev)) {
+		if (zpci_disable_device(zdev))
+			goto out;
+	}
+
+	if (zpci_enable_device(zdev))
+		goto out;
+
+	/* Re-register the IOMMU that was already created */
+	zpci_register_ioat(zdev, 0, zdev->start_dma, zdev->end_dma,
+			   virt_to_phys(zdev->dma_table));
+
+out:
+	spin_lock(&kvm->arch.kzdev_list_lock);
+	list_del(&zdev->kzdev->entry);
+	spin_unlock(&kvm->arch.kzdev_list_lock);
+	kvm_s390_pci_dev_release(zdev);
+
+	mutex_unlock(&kvm->lock);
+	mutex_unlock(&zdev->kzdev_lock);
+
+	kvm_put_kvm(kvm);
+}
+EXPORT_SYMBOL_GPL(kvm_s390_pci_unregister_kvm);
+
+void kvm_s390_pci_init_list(struct kvm *kvm)
+{
+	spin_lock_init(&kvm->arch.kzdev_list_lock);
+	INIT_LIST_HEAD(&kvm->arch.kzdev_list);
+}
+
+void kvm_s390_pci_clear_list(struct kvm *kvm)
+{
+	/*
+	 * This list should already be empty, either via vfio device closures
+	 * or kvm fd cleanup.
+	 */
+	spin_lock(&kvm->arch.kzdev_list_lock);
+	WARN_ON_ONCE(!list_empty(&kvm->arch.kzdev_list));
+	spin_unlock(&kvm->arch.kzdev_list_lock);
+}
+
+static struct zpci_dev *get_zdev_from_kvm_by_fh(struct kvm *kvm, u32 fh)
+{
+	struct zpci_dev *zdev = NULL;
+	struct kvm_zdev *kzdev;
+
+	spin_lock(&kvm->arch.kzdev_list_lock);
+	list_for_each_entry(kzdev, &kvm->arch.kzdev_list, entry) {
+		if (kzdev->zdev->fh == fh) {
+			zdev = kzdev->zdev;
+			break;
+		}
+	}
+	spin_unlock(&kvm->arch.kzdev_list_lock);
+
+	return zdev;
+}
+
+static int kvm_s390_pci_zpci_reg_aen(struct zpci_dev *zdev,
+				     struct kvm_s390_zpci_op *args)
+{
+	struct zpci_fib fib = {};
+	bool hostflag;
+
+	fib.fmt0.aibv = args->u.reg_aen.ibv;
+	fib.fmt0.isc = args->u.reg_aen.isc;
+	fib.fmt0.noi = args->u.reg_aen.noi;
+	if (args->u.reg_aen.sb != 0) {
+		fib.fmt0.aisb = args->u.reg_aen.sb;
+		fib.fmt0.aisbo = args->u.reg_aen.sbo;
+		fib.fmt0.sum = 1;
+	} else {
+		fib.fmt0.aisb = 0;
+		fib.fmt0.aisbo = 0;
+		fib.fmt0.sum = 0;
+	}
+
+	hostflag = !(args->u.reg_aen.flags & KVM_S390_ZPCIOP_REGAEN_HOST);
+	return kvm_s390_pci_aif_enable(zdev, &fib, hostflag);
+}
+
+int kvm_s390_pci_zpci_op(struct kvm *kvm, struct kvm_s390_zpci_op *args)
+{
+	struct kvm_zdev *kzdev;
+	struct zpci_dev *zdev;
+	int r;
+
+	zdev = get_zdev_from_kvm_by_fh(kvm, args->fh);
+	if (!zdev)
+		return -ENODEV;
+
+	mutex_lock(&zdev->kzdev_lock);
+	mutex_lock(&kvm->lock);
+
+	kzdev = zdev->kzdev;
+	if (!kzdev) {
+		r = -ENODEV;
+		goto out;
+	}
+	if (kzdev->kvm != kvm) {
+		r = -EPERM;
+		goto out;
+	}
+
+	switch (args->op) {
+	case KVM_S390_ZPCIOP_REG_AEN:
+		/* Fail on unknown flags */
+		if (args->u.reg_aen.flags & ~KVM_S390_ZPCIOP_REGAEN_HOST) {
+			r = -EINVAL;
+			break;
+		}
+		r = kvm_s390_pci_zpci_reg_aen(zdev, args);
+		break;
+	case KVM_S390_ZPCIOP_DEREG_AEN:
+		r = kvm_s390_pci_aif_disable(zdev, false);
+		break;
+	default:
+		r = -EINVAL;
+	}
+
+out:
+	mutex_unlock(&kvm->lock);
+	mutex_unlock(&zdev->kzdev_lock);
+	return r;
+}
+
+int kvm_s390_pci_init(void)
+{
+	aift = kzalloc(sizeof(struct zpci_aift), GFP_KERNEL);
+	if (!aift)
+		return -ENOMEM;
+
+	spin_lock_init(&aift->gait_lock);
+	mutex_init(&aift->aift_lock);
+
+	return 0;
+}
+
+void kvm_s390_pci_exit(void)
+{
+	mutex_destroy(&aift->aift_lock);
+
+	kfree(aift);
+}
diff --git a/arch/s390/kvm/pci.h b/arch/s390/kvm/pci.h
new file mode 100644
index 000000000000..0351382e990f
--- /dev/null
+++ b/arch/s390/kvm/pci.h
@@ -0,0 +1,88 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * s390 kvm PCI passthrough support
+ *
+ * Copyright IBM Corp. 2022
+ *
+ *    Author(s): Matthew Rosato <mjrosato@linux.ibm.com>
+ */
+
+#ifndef __KVM_S390_PCI_H
+#define __KVM_S390_PCI_H
+
+#include <linux/kvm_host.h>
+#include <linux/pci.h>
+#include <linux/mutex.h>
+#include <linux/kvm.h>
+#include <linux/kvm_host.h>
+#include <asm/airq.h>
+#include <asm/cpu.h>
+
+struct kvm_zdev {
+	struct zpci_dev *zdev;
+	struct kvm *kvm;
+	struct zpci_fib fib;
+	struct list_head entry;
+};
+
+struct zpci_gaite {
+	u32 gisa;
+	u8 gisc;
+	u8 count;
+	u8 reserved;
+	u8 aisbo;
+	u64 aisb;
+};
+
+struct zpci_aift {
+	struct zpci_gaite *gait;
+	struct airq_iv *sbv;
+	struct kvm_zdev **kzdev;
+	spinlock_t gait_lock; /* Protects the gait, used during AEN forward */
+	struct mutex aift_lock; /* Protects the other structures in aift */
+};
+
+extern struct zpci_aift *aift;
+
+static inline struct kvm *kvm_s390_pci_si_to_kvm(struct zpci_aift *aift,
+						 unsigned long si)
+{
+	if (!IS_ENABLED(CONFIG_VFIO_PCI_ZDEV_KVM) || aift->kzdev == 0 ||
+	    aift->kzdev[si] == 0)
+		return 0;
+	return aift->kzdev[si]->kvm;
+};
+
+int kvm_s390_pci_aen_init(u8 nisc);
+void kvm_s390_pci_aen_exit(void);
+
+void kvm_s390_pci_init_list(struct kvm *kvm);
+void kvm_s390_pci_clear_list(struct kvm *kvm);
+
+int kvm_s390_pci_zpci_op(struct kvm *kvm, struct kvm_s390_zpci_op *args);
+
+int kvm_s390_pci_init(void);
+void kvm_s390_pci_exit(void);
+
+static inline bool kvm_s390_pci_interp_allowed(void)
+{
+	struct cpuid cpu_id;
+
+	get_cpu_id(&cpu_id);
+	switch (cpu_id.machine) {
+	case 0x2817:
+	case 0x2818:
+	case 0x2827:
+	case 0x2828:
+	case 0x2964:
+	case 0x2965:
+		/* No SHM on certain machines */
+		return false;
+	default:
+		return (IS_ENABLED(CONFIG_VFIO_PCI_ZDEV_KVM) &&
+			sclp.has_zpci_lsi && sclp.has_aeni && sclp.has_aisi &&
+			sclp.has_aisii);
+	}
+}
+
+#endif /* __KVM_S390_PCI_H */
diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c
index bc980fd313d5..73cdc5539384 100644
--- a/arch/s390/pci/pci.c
+++ b/arch/s390/pci/pci.c
@@ -61,6 +61,12 @@ DEFINE_STATIC_KEY_FALSE(have_mio);
 
 static struct kmem_cache *zdev_fmb_cache;
 
+/* AEN structures that must be preserved over KVM module re-insertion */
+union zpci_sic_iib *zpci_aipb;
+EXPORT_SYMBOL_GPL(zpci_aipb);
+struct airq_iv *zpci_aif_sbv;
+EXPORT_SYMBOL_GPL(zpci_aif_sbv);
+
 struct zpci_dev *get_zdev_by_fid(u32 fid)
 {
 	struct zpci_dev *tmp, *zdev = NULL;
@@ -120,11 +126,13 @@ int zpci_register_ioat(struct zpci_dev *zdev, u8 dmaas,
 	fib.pba = base;
 	fib.pal = limit;
 	fib.iota = iota | ZPCI_IOTA_RTTO_FLAG;
+	fib.gd = zdev->gisa;
 	cc = zpci_mod_fc(req, &fib, &status);
 	if (cc)
 		zpci_dbg(3, "reg ioat fid:%x, cc:%d, status:%d\n", zdev->fid, cc, status);
 	return cc;
 }
+EXPORT_SYMBOL_GPL(zpci_register_ioat);
 
 /* Modify PCI: Unregister I/O address translation parameters */
 int zpci_unregister_ioat(struct zpci_dev *zdev, u8 dmaas)
@@ -133,6 +141,8 @@ int zpci_unregister_ioat(struct zpci_dev *zdev, u8 dmaas)
 	struct zpci_fib fib = {0};
 	u8 cc, status;
 
+	fib.gd = zdev->gisa;
+
 	cc = zpci_mod_fc(req, &fib, &status);
 	if (cc)
 		zpci_dbg(3, "unreg ioat fid:%x, cc:%d, status:%d\n", zdev->fid, cc, status);
@@ -160,6 +170,7 @@ int zpci_fmb_enable_device(struct zpci_dev *zdev)
 	atomic64_set(&zdev->unmapped_pages, 0);
 
 	fib.fmb_addr = virt_to_phys(zdev->fmb);
+	fib.gd = zdev->gisa;
 	cc = zpci_mod_fc(req, &fib, &status);
 	if (cc) {
 		kmem_cache_free(zdev_fmb_cache, zdev->fmb);
@@ -178,6 +189,8 @@ int zpci_fmb_disable_device(struct zpci_dev *zdev)
 	if (!zdev->fmb)
 		return -EINVAL;
 
+	fib.gd = zdev->gisa;
+
 	/* Function measurement is disabled if fmb address is zero */
 	cc = zpci_mod_fc(req, &fib, &status);
 	if (cc == 3) /* Function already gone. */
@@ -700,6 +713,7 @@ int zpci_enable_device(struct zpci_dev *zdev)
 		zpci_update_fh(zdev, fh);
 	return rc;
 }
+EXPORT_SYMBOL_GPL(zpci_enable_device);
 
 int zpci_disable_device(struct zpci_dev *zdev)
 {
@@ -723,6 +737,7 @@ int zpci_disable_device(struct zpci_dev *zdev)
 	}
 	return rc;
 }
+EXPORT_SYMBOL_GPL(zpci_disable_device);
 
 /**
  * zpci_hot_reset_device - perform a reset of the given zPCI function
@@ -816,6 +831,7 @@ struct zpci_dev *zpci_create_device(u32 fid, u32 fh, enum zpci_state state)
 
 	kref_init(&zdev->kref);
 	mutex_init(&zdev->lock);
+	mutex_init(&zdev->kzdev_lock);
 
 	rc = zpci_init_iommu(zdev);
 	if (rc)
diff --git a/arch/s390/pci/pci_clp.c b/arch/s390/pci/pci_clp.c
index 375e0a5120bc..ee367798e388 100644
--- a/arch/s390/pci/pci_clp.c
+++ b/arch/s390/pci/pci_clp.c
@@ -106,6 +106,8 @@ static void clp_store_query_pci_fngrp(struct zpci_dev *zdev,
 	zdev->max_msi = response->noi;
 	zdev->fmb_update = response->mui;
 	zdev->version = response->version;
+	zdev->maxstbl = response->maxstbl;
+	zdev->dtsm = response->dtsm;
 
 	switch (response->version) {
 	case 1:
@@ -229,12 +231,16 @@ static int clp_set_pci_fn(struct zpci_dev *zdev, u32 *fh, u8 nr_dma_as, u8 comma
 {
 	struct clp_req_rsp_set_pci *rrb;
 	int rc, retries = 100;
+	u32 gisa = 0;
 
 	*fh = 0;
 	rrb = clp_alloc_block(GFP_KERNEL);
 	if (!rrb)
 		return -ENOMEM;
 
+	if (command != CLP_SET_DISABLE_PCI_FN)
+		gisa = zdev->gisa;
+
 	do {
 		memset(rrb, 0, sizeof(*rrb));
 		rrb->request.hdr.len = sizeof(rrb->request);
@@ -243,6 +249,7 @@ static int clp_set_pci_fn(struct zpci_dev *zdev, u32 *fh, u8 nr_dma_as, u8 comma
 		rrb->request.fh = zdev->fh;
 		rrb->request.oc = command;
 		rrb->request.ndas = nr_dma_as;
+		rrb->request.gisa = gisa;
 
 		rc = clp_req(rrb, CLP_LPS_PCI);
 		if (rrb->response.hdr.rsp == CLP_RC_SETPCIFN_BUSY) {
diff --git a/arch/s390/pci/pci_insn.c b/arch/s390/pci/pci_insn.c
index 1a822b7799f8..56480be48244 100644
--- a/arch/s390/pci/pci_insn.c
+++ b/arch/s390/pci/pci_insn.c
@@ -92,6 +92,7 @@ u8 zpci_mod_fc(u64 req, struct zpci_fib *fib, u8 *status)
 
 	return cc;
 }
+EXPORT_SYMBOL_GPL(zpci_mod_fc);
 
 /* Refresh PCI Translations */
 static inline u8 __rpcit(u64 fn, u64 addr, u64 range, u8 *status)
@@ -138,7 +139,7 @@ int zpci_refresh_trans(u64 fn, u64 addr, u64 range)
 }
 
 /* Set Interruption Controls */
-int __zpci_set_irq_ctrl(u16 ctl, u8 isc, union zpci_sic_iib *iib)
+int zpci_set_irq_ctrl(u16 ctl, u8 isc, union zpci_sic_iib *iib)
 {
 	if (!test_facility(72))
 		return -EIO;
@@ -149,6 +150,7 @@ int __zpci_set_irq_ctrl(u16 ctl, u8 isc, union zpci_sic_iib *iib)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(zpci_set_irq_ctrl);
 
 /* PCI Load */
 static inline int ____pcilg(u64 *data, u64 req, u64 offset, u8 *status)
diff --git a/arch/s390/pci/pci_irq.c b/arch/s390/pci/pci_irq.c
index 500cd2dbdf53..a2b42a63a53b 100644
--- a/arch/s390/pci/pci_irq.c
+++ b/arch/s390/pci/pci_irq.c
@@ -11,16 +11,10 @@
 
 #include <asm/isc.h>
 #include <asm/airq.h>
+#include <asm/tpi.h>
 
 static enum {FLOATING, DIRECTED} irq_delivery;
 
-#define	SIC_IRQ_MODE_ALL		0
-#define	SIC_IRQ_MODE_SINGLE		1
-#define	SIC_IRQ_MODE_DIRECT		4
-#define	SIC_IRQ_MODE_D_ALL		16
-#define	SIC_IRQ_MODE_D_SINGLE		17
-#define	SIC_IRQ_MODE_SET_CPU		18
-
 /*
  * summary bit vector
  * FLOATING - summary bit per function
@@ -49,6 +43,7 @@ static int zpci_set_airq(struct zpci_dev *zdev)
 	fib.fmt0.aibvo = 0;	/* each zdev has its own interrupt vector */
 	fib.fmt0.aisb = virt_to_phys(zpci_sbv->vector) + (zdev->aisb / 64) * 8;
 	fib.fmt0.aisbo = zdev->aisb & 63;
+	fib.gd = zdev->gisa;
 
 	return zpci_mod_fc(req, &fib, &status) ? -EIO : 0;
 }
@@ -60,6 +55,8 @@ static int zpci_clear_airq(struct zpci_dev *zdev)
 	struct zpci_fib fib = {0};
 	u8 cc, status;
 
+	fib.gd = zdev->gisa;
+
 	cc = zpci_mod_fc(req, &fib, &status);
 	if (cc == 3 || (cc == 1 && status == 24))
 		/* Function already gone or IRQs already deregistered. */
@@ -78,6 +75,7 @@ static int zpci_set_directed_irq(struct zpci_dev *zdev)
 	fib.fmt = 1;
 	fib.fmt1.noi = zdev->msi_nr_irqs;
 	fib.fmt1.dibvo = zdev->msi_first_bit;
+	fib.gd = zdev->gisa;
 
 	return zpci_mod_fc(req, &fib, &status) ? -EIO : 0;
 }
@@ -90,6 +88,7 @@ static int zpci_clear_directed_irq(struct zpci_dev *zdev)
 	u8 cc, status;
 
 	fib.fmt = 1;
+	fib.gd = zdev->gisa;
 	cc = zpci_mod_fc(req, &fib, &status);
 	if (cc == 3 || (cc == 1 && status == 24))
 		/* Function already gone or IRQs already deregistered. */
@@ -153,6 +152,7 @@ static struct irq_chip zpci_irq_chip = {
 static void zpci_handle_cpu_local_irq(bool rescan)
 {
 	struct airq_iv *dibv = zpci_ibv[smp_processor_id()];
+	union zpci_sic_iib iib = {{0}};
 	unsigned long bit;
 	int irqs_on = 0;
 
@@ -164,7 +164,7 @@ static void zpci_handle_cpu_local_irq(bool rescan)
 				/* End of second scan with interrupts on. */
 				break;
 			/* First scan complete, reenable interrupts. */
-			if (zpci_set_irq_ctrl(SIC_IRQ_MODE_D_SINGLE, PCI_ISC))
+			if (zpci_set_irq_ctrl(SIC_IRQ_MODE_D_SINGLE, PCI_ISC, &iib))
 				break;
 			bit = 0;
 			continue;
@@ -192,6 +192,7 @@ static void zpci_handle_remote_irq(void *data)
 static void zpci_handle_fallback_irq(void)
 {
 	struct cpu_irq_data *cpu_data;
+	union zpci_sic_iib iib = {{0}};
 	unsigned long cpu;
 	int irqs_on = 0;
 
@@ -202,7 +203,7 @@ static void zpci_handle_fallback_irq(void)
 				/* End of second scan with interrupts on. */
 				break;
 			/* First scan complete, reenable interrupts. */
-			if (zpci_set_irq_ctrl(SIC_IRQ_MODE_SINGLE, PCI_ISC))
+			if (zpci_set_irq_ctrl(SIC_IRQ_MODE_SINGLE, PCI_ISC, &iib))
 				break;
 			cpu = 0;
 			continue;
@@ -216,8 +217,11 @@ static void zpci_handle_fallback_irq(void)
 	}
 }
 
-static void zpci_directed_irq_handler(struct airq_struct *airq, bool floating)
+static void zpci_directed_irq_handler(struct airq_struct *airq,
+				      struct tpi_info *tpi_info)
 {
+	bool floating = !tpi_info->directed_irq;
+
 	if (floating) {
 		inc_irq_stat(IRQIO_PCF);
 		zpci_handle_fallback_irq();
@@ -227,8 +231,10 @@ static void zpci_directed_irq_handler(struct airq_struct *airq, bool floating)
 	}
 }
 
-static void zpci_floating_irq_handler(struct airq_struct *airq, bool floating)
+static void zpci_floating_irq_handler(struct airq_struct *airq,
+				      struct tpi_info *tpi_info)
 {
+	union zpci_sic_iib iib = {{0}};
 	unsigned long si, ai;
 	struct airq_iv *aibv;
 	int irqs_on = 0;
@@ -242,7 +248,7 @@ static void zpci_floating_irq_handler(struct airq_struct *airq, bool floating)
 				/* End of second scan with interrupts on. */
 				break;
 			/* First scan complete, reenable interrupts. */
-			if (zpci_set_irq_ctrl(SIC_IRQ_MODE_SINGLE, PCI_ISC))
+			if (zpci_set_irq_ctrl(SIC_IRQ_MODE_SINGLE, PCI_ISC, &iib))
 				break;
 			si = 0;
 			continue;
@@ -291,7 +297,7 @@ int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
 		zdev->aisb = bit;
 
 		/* Create adapter interrupt vector */
-		zdev->aibv = airq_iv_create(msi_vecs, AIRQ_IV_DATA | AIRQ_IV_BITLOCK);
+		zdev->aibv = airq_iv_create(msi_vecs, AIRQ_IV_DATA | AIRQ_IV_BITLOCK, NULL);
 		if (!zdev->aibv)
 			return -ENOMEM;
 
@@ -402,11 +408,12 @@ static struct airq_struct zpci_airq = {
 static void __init cpu_enable_directed_irq(void *unused)
 {
 	union zpci_sic_iib iib = {{0}};
+	union zpci_sic_iib ziib = {{0}};
 
 	iib.cdiib.dibv_addr = (u64) zpci_ibv[smp_processor_id()]->vector;
 
-	__zpci_set_irq_ctrl(SIC_IRQ_MODE_SET_CPU, 0, &iib);
-	zpci_set_irq_ctrl(SIC_IRQ_MODE_D_SINGLE, PCI_ISC);
+	zpci_set_irq_ctrl(SIC_IRQ_MODE_SET_CPU, 0, &iib);
+	zpci_set_irq_ctrl(SIC_IRQ_MODE_D_SINGLE, PCI_ISC, &ziib);
 }
 
 static int __init zpci_directed_irq_init(void)
@@ -414,14 +421,14 @@ static int __init zpci_directed_irq_init(void)
 	union zpci_sic_iib iib = {{0}};
 	unsigned int cpu;
 
-	zpci_sbv = airq_iv_create(num_possible_cpus(), 0);
+	zpci_sbv = airq_iv_create(num_possible_cpus(), 0, NULL);
 	if (!zpci_sbv)
 		return -ENOMEM;
 
 	iib.diib.isc = PCI_ISC;
 	iib.diib.nr_cpus = num_possible_cpus();
 	iib.diib.disb_addr = virt_to_phys(zpci_sbv->vector);
-	__zpci_set_irq_ctrl(SIC_IRQ_MODE_DIRECT, 0, &iib);
+	zpci_set_irq_ctrl(SIC_IRQ_MODE_DIRECT, 0, &iib);
 
 	zpci_ibv = kcalloc(num_possible_cpus(), sizeof(*zpci_ibv),
 			   GFP_KERNEL);
@@ -436,7 +443,7 @@ static int __init zpci_directed_irq_init(void)
 		zpci_ibv[cpu] = airq_iv_create(cache_line_size() * BITS_PER_BYTE,
 					       AIRQ_IV_DATA |
 					       AIRQ_IV_CACHELINE |
-					       (!cpu ? AIRQ_IV_ALLOC : 0));
+					       (!cpu ? AIRQ_IV_ALLOC : 0), NULL);
 		if (!zpci_ibv[cpu])
 			return -ENOMEM;
 	}
@@ -453,7 +460,7 @@ static int __init zpci_floating_irq_init(void)
 	if (!zpci_ibv)
 		return -ENOMEM;
 
-	zpci_sbv = airq_iv_create(ZPCI_NR_DEVICES, AIRQ_IV_ALLOC);
+	zpci_sbv = airq_iv_create(ZPCI_NR_DEVICES, AIRQ_IV_ALLOC, NULL);
 	if (!zpci_sbv)
 		goto out_free;
 
@@ -466,6 +473,7 @@ out_free:
 
 int __init zpci_irq_init(void)
 {
+	union zpci_sic_iib iib = {{0}};
 	int rc;
 
 	irq_delivery = sclp.has_dirq ? DIRECTED : FLOATING;
@@ -497,7 +505,7 @@ int __init zpci_irq_init(void)
 	 * Enable floating IRQs (with suppression after one IRQ). When using
 	 * directed IRQs this enables the fallback path.
 	 */
-	zpci_set_irq_ctrl(SIC_IRQ_MODE_SINGLE, PCI_ISC);
+	zpci_set_irq_ctrl(SIC_IRQ_MODE_SINGLE, PCI_ISC, &iib);
 
 	return 0;
 out_airq: