1 files changed, 297 insertions, 109 deletions

diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c
index 076090f9e666..13a9661d2b28 100644
--- a/arch/s390/kvm/vsie.c
+++ b/arch/s390/kvm/vsie.c
@@ -12,15 +12,22 @@
 #include <linux/list.h>
 #include <linux/bitmap.h>
 #include <linux/sched/signal.h>
+#include <linux/io.h>
+#include <linux/mman.h>
 
 #include <asm/gmap.h>
 #include <asm/mmu_context.h>
 #include <asm/sclp.h>
 #include <asm/nmi.h>
 #include <asm/dis.h>
+#include <asm/facility.h>
 #include "kvm-s390.h"
 #include "gaccess.h"
 
+enum vsie_page_flags {
+	VSIE_PAGE_IN_USE = 0,
+};
+
 struct vsie_page {
 	struct kvm_s390_sie_block scb_s;	/* 0x0000 */
 	/*
@@ -44,11 +51,40 @@ struct vsie_page {
 	gpa_t gvrd_gpa;				/* 0x0240 */
 	gpa_t riccbd_gpa;			/* 0x0248 */
 	gpa_t sdnx_gpa;				/* 0x0250 */
-	__u8 reserved[0x0700 - 0x0258];		/* 0x0258 */
+	/*
+	 * guest address of the original SCB. Remains set for free vsie
+	 * pages, so we can properly look them up in our addr_to_page
+	 * radix tree.
+	 */
+	gpa_t scb_gpa;				/* 0x0258 */
+	/*
+	 * Flags: must be set/cleared atomically after the vsie page can be
+	 * looked up by other CPUs.
+	 */
+	unsigned long flags;			/* 0x0260 */
+	__u8 reserved[0x0700 - 0x0268];		/* 0x0268 */
 	struct kvm_s390_crypto_cb crycb;	/* 0x0700 */
 	__u8 fac[S390_ARCH_FAC_LIST_SIZE_BYTE];	/* 0x0800 */
 };
 
+/**
+ * gmap_shadow_valid() - check if a shadow guest address space matches the
+ *                       given properties and is still valid
+ * @sg: pointer to the shadow guest address space structure
+ * @asce: ASCE for which the shadow table is requested
+ * @edat_level: edat level to be used for the shadow translation
+ *
+ * Returns 1 if the gmap shadow is still valid and matches the given
+ * properties, the caller can continue using it. Returns 0 otherwise; the
+ * caller has to request a new shadow gmap in this case.
+ */
+int gmap_shadow_valid(struct gmap *sg, unsigned long asce, int edat_level)
+{
+	if (sg->removed)
+		return 0;
+	return sg->orig_asce == asce && sg->edat_level == edat_level;
+}
+
 /* trigger a validity icpt for the given scb */
 static int set_validity_icpt(struct kvm_s390_sie_block *scb,
 			     __u16 reason_code)
@@ -137,11 +173,15 @@ static int prepare_cpuflags(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 }
 /* 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)
+			unsigned long crycb_gpa, struct kvm_s390_apcb1 *apcb_h)
 {
 	struct kvm_s390_apcb0 tmp;
+	unsigned long apcb_gpa;
+
+	apcb_gpa = crycb_gpa + offsetof(struct kvm_s390_crypto_cb, apcb0);
 
-	if (read_guest_real(vcpu, apcb_o, &tmp, sizeof(struct kvm_s390_apcb0)))
+	if (read_guest_real(vcpu, apcb_gpa, &tmp,
+			    sizeof(struct kvm_s390_apcb0)))
 		return -EFAULT;
 
 	apcb_s->apm[0] = apcb_h->apm[0] & tmp.apm[0];
@@ -156,19 +196,24 @@ static int setup_apcb10(struct kvm_vcpu *vcpu, struct kvm_s390_apcb1 *apcb_s,
  * 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
+ * @crycb_gpa: guest physical address to start of original guest crycb
  * @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)
+			unsigned long crycb_gpa, unsigned long *apcb_h)
 {
-	if (read_guest_real(vcpu, apcb_o, apcb_s,
+	unsigned long apcb_gpa;
+
+	apcb_gpa = crycb_gpa + offsetof(struct kvm_s390_crypto_cb, apcb0);
+
+	if (read_guest_real(vcpu, apcb_gpa, apcb_s,
 			    sizeof(struct kvm_s390_apcb0)))
 		return -EFAULT;
 
-	bitmap_and(apcb_s, apcb_s, apcb_h, sizeof(struct kvm_s390_apcb0));
+	bitmap_and(apcb_s, apcb_s, apcb_h,
+		   BITS_PER_BYTE * sizeof(struct kvm_s390_apcb0));
 
 	return 0;
 }
@@ -177,20 +222,25 @@ static int setup_apcb00(struct kvm_vcpu *vcpu, unsigned long *apcb_s,
  * 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
+ * @crycb_gpa: guest physical address to start of original guest crycb
  * @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 crycb_gpa,
 			unsigned long *apcb_h)
 {
-	if (read_guest_real(vcpu, apcb_o, apcb_s,
+	unsigned long apcb_gpa;
+
+	apcb_gpa = crycb_gpa + offsetof(struct kvm_s390_crypto_cb, apcb1);
+
+	if (read_guest_real(vcpu, apcb_gpa, apcb_s,
 			    sizeof(struct kvm_s390_apcb1)))
 		return -EFAULT;
 
-	bitmap_and(apcb_s, apcb_s, apcb_h, sizeof(struct kvm_s390_apcb1));
+	bitmap_and(apcb_s, apcb_s, apcb_h,
+		   BITS_PER_BYTE * sizeof(struct kvm_s390_apcb1));
 
 	return 0;
 }
@@ -199,7 +249,7 @@ static int setup_apcb11(struct kvm_vcpu *vcpu, unsigned long *apcb_s,
  * 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_gpa: guest physical address of 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.
@@ -210,50 +260,46 @@ static int setup_apcb11(struct kvm_vcpu *vcpu, unsigned long *apcb_s,
  * 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,
+	       const u32 crycb_gpa,
 	       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))
+		if ((crycb_gpa & PAGE_MASK) != ((crycb_gpa + 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,
+				    crycb_gpa,
 				    (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_gpa,
 					    &crycb_h->apcb1);
 		case CRYCB_FORMAT1:
 			return setup_apcb00(vcpu,
 					    (unsigned long *) &crycb_s->apcb0,
-					    (unsigned long) &crycb->apcb0,
+					    crycb_gpa,
 					    (unsigned long *) &crycb_h->apcb0);
 		}
 		break;
 	case CRYCB_FORMAT0:
-		if ((crycb_o & PAGE_MASK) != ((crycb_o + 32) & PAGE_MASK))
+		if ((crycb_gpa & PAGE_MASK) != ((crycb_gpa + 32) & PAGE_MASK))
 			return -EACCES;
 
 		switch (fmt_h) {
 		case CRYCB_FORMAT2:
 			return setup_apcb10(vcpu, &crycb_s->apcb1,
-					    (unsigned long) &crycb->apcb0,
+					    crycb_gpa,
 					    &crycb_h->apcb1);
 		case CRYCB_FORMAT1:
 		case CRYCB_FORMAT0:
 			return setup_apcb00(vcpu,
 					    (unsigned long *) &crycb_s->apcb0,
-					    (unsigned long) &crycb->apcb0,
+					    crycb_gpa,
 					    (unsigned long *) &crycb_h->apcb0);
 		}
 	}
@@ -323,7 +369,8 @@ static int shadow_crycb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 	/* we may only allow it if enabled for guest 2 */
 	ecb3_flags = scb_o->ecb3 & vcpu->arch.sie_block->ecb3 &
 		     (ECB3_AES | ECB3_DEA);
-	ecd_flags = scb_o->ecd & vcpu->arch.sie_block->ecd & ECD_ECC;
+	ecd_flags = scb_o->ecd & vcpu->arch.sie_block->ecd &
+		     (ECD_ECC | ECD_HMAC);
 	if (!ecb3_flags && !ecd_flags)
 		goto end;
 
@@ -350,7 +397,7 @@ end:
 	case -EACCES:
 		return set_validity_icpt(scb_s, 0x003CU);
 	}
-	scb_s->crycbd = ((__u32)(__u64) &vsie_page->crycb) | CRYCB_FORMAT2;
+	scb_s->crycbd = (u32)virt_to_phys(&vsie_page->crycb) | CRYCB_FORMAT2;
 	return 0;
 }
 
@@ -416,11 +463,6 @@ static void unshadow_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 		memcpy((void *)((u64)scb_o + 0xc0),
 		       (void *)((u64)scb_s + 0xc0), 0xf0 - 0xc0);
 		break;
-	case ICPT_PARTEXEC:
-		/* MVPG only */
-		memcpy((void *)((u64)scb_o + 0xc0),
-		       (void *)((u64)scb_s + 0xc0), 0xd0 - 0xc0);
-		break;
 	}
 
 	if (scb_s->ihcpu != 0xffffU)
@@ -498,7 +540,7 @@ static int shadow_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 	scb_s->mso = new_mso;
 	scb_s->prefix = new_prefix;
 
-	/* We have to definetly flush the tlb if this scb never ran */
+	/* We have to definitely flush the tlb if this scb never ran */
 	if (scb_s->ihcpu != 0xffffU)
 		scb_s->ihcpu = scb_o->ihcpu;
 
@@ -507,6 +549,14 @@ static int shadow_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 	/* Host-protection-interruption introduced with ESOP */
 	if (test_kvm_cpu_feat(vcpu->kvm, KVM_S390_VM_CPU_FEAT_ESOP))
 		scb_s->ecb |= scb_o->ecb & ECB_HOSTPROTINT;
+	/*
+	 * CPU Topology
+	 * This facility only uses the utility field of the SCA and none of
+	 * the cpu entries that are problematic with the other interpretation
+	 * facilities so we can pass it through
+	 */
+	if (test_kvm_facility(vcpu->kvm, 11))
+		scb_s->ecb |= scb_o->ecb & ECB_PTF;
 	/* transactional execution */
 	if (test_kvm_facility(vcpu->kvm, 73) && wants_tx) {
 		/* remap the prefix is tx is toggled on */
@@ -514,6 +564,8 @@ static int shadow_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 			prefix_unmapped(vsie_page);
 		scb_s->ecb |= ECB_TE;
 	}
+	/* specification exception interpretation */
+	scb_s->ecb |= scb_o->ecb & ECB_SPECI;
 	/* branch prediction */
 	if (test_kvm_facility(vcpu->kvm, 82))
 		scb_s->fpf |= scb_o->fpf & FPF_BPBC;
@@ -540,14 +592,17 @@ static int shadow_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 	if (test_kvm_cpu_feat(vcpu->kvm, KVM_S390_VM_CPU_FEAT_CEI))
 		scb_s->eca |= scb_o->eca & ECA_CEI;
 	/* Epoch Extension */
-	if (test_kvm_facility(vcpu->kvm, 139))
+	if (test_kvm_facility(vcpu->kvm, 139)) {
 		scb_s->ecd |= scb_o->ecd & ECD_MEF;
+		scb_s->epdx = scb_o->epdx;
+	}
 
 	/* etoken */
 	if (test_kvm_facility(vcpu->kvm, 156))
 		scb_s->ecd |= scb_o->ecd & ECD_ETOKENF;
 
 	scb_s->hpid = HPID_VSIE;
+	scb_s->cpnc = scb_o->cpnc;
 
 	prepare_ibc(vcpu, vsie_page);
 	rc = shadow_crycb(vcpu, vsie_page);
@@ -563,24 +618,18 @@ void kvm_s390_vsie_gmap_notifier(struct gmap *gmap, unsigned long start,
 	struct kvm *kvm = gmap->private;
 	struct vsie_page *cur;
 	unsigned long prefix;
-	struct page *page;
 	int i;
 
 	if (!gmap_is_shadow(gmap))
 		return;
-	if (start >= 1UL << 31)
-		/* We are only interested in prefix pages */
-		return;
-
 	/*
 	 * Only new shadow blocks are added to the list during runtime,
 	 * therefore we can safely reference them all the time.
 	 */
 	for (i = 0; i < kvm->arch.vsie.page_count; i++) {
-		page = READ_ONCE(kvm->arch.vsie.pages[i]);
-		if (!page)
+		cur = READ_ONCE(kvm->arch.vsie.pages[i]);
+		if (!cur)
 			continue;
-		cur = page_to_virt(page);
 		if (READ_ONCE(cur->gmap) != gmap)
 			continue;
 		prefix = cur->scb_s.prefix << GUEST_PREFIX_SHIFT;
@@ -618,10 +667,10 @@ static int map_prefix(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 	/* with mso/msl, the prefix lies at offset *mso* */
 	prefix += scb_s->mso;
 
-	rc = kvm_s390_shadow_fault(vcpu, vsie_page->gmap, prefix);
+	rc = kvm_s390_shadow_fault(vcpu, vsie_page->gmap, prefix, NULL);
 	if (!rc && (scb_s->ecb & ECB_TE))
 		rc = kvm_s390_shadow_fault(vcpu, vsie_page->gmap,
-					   prefix + PAGE_SIZE);
+					   prefix + PAGE_SIZE, NULL);
 	/*
 	 * We don't have to mprotect, we will be called for all unshadows.
 	 * SIE will detect if protection applies and trigger a validity.
@@ -645,16 +694,16 @@ static int pin_guest_page(struct kvm *kvm, gpa_t gpa, hpa_t *hpa)
 	struct page *page;
 
 	page = gfn_to_page(kvm, gpa_to_gfn(gpa));
-	if (is_error_page(page))
+	if (!page)
 		return -EINVAL;
-	*hpa = (hpa_t) page_to_virt(page) + (gpa & ~PAGE_MASK);
+	*hpa = (hpa_t)page_to_phys(page) + (gpa & ~PAGE_MASK);
 	return 0;
 }
 
 /* Unpins a page previously pinned via pin_guest_page, marking it as dirty. */
 static void unpin_guest_page(struct kvm *kvm, gpa_t gpa, hpa_t hpa)
 {
-	kvm_release_pfn_dirty(hpa >> PAGE_SHIFT);
+	kvm_release_page_dirty(pfn_to_page(hpa >> PAGE_SHIFT));
 	/* mark the page always as dirty for migration */
 	mark_page_dirty(kvm, gpa_to_gfn(gpa));
 }
@@ -837,7 +886,7 @@ unpin:
 static void unpin_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page,
 		      gpa_t gpa)
 {
-	hpa_t hpa = (hpa_t) vsie_page->scb_o;
+	hpa_t hpa = virt_to_phys(vsie_page->scb_o);
 
 	if (hpa)
 		unpin_guest_page(vcpu->kvm, gpa, hpa);
@@ -862,7 +911,7 @@ static int pin_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page,
 		WARN_ON_ONCE(rc);
 		return 1;
 	}
-	vsie_page->scb_o = (struct kvm_s390_sie_block *) hpa;
+	vsie_page->scb_o = phys_to_virt(hpa);
 	return 0;
 }
 
@@ -882,7 +931,7 @@ static int inject_fault(struct kvm_vcpu *vcpu, __u16 code, __u64 vaddr,
 			(vaddr & 0xfffffffffffff000UL) |
 			/* 52-53: store / fetch */
 			(((unsigned int) !write_flag) + 1) << 10,
-			/* 62-63: asce id (alway primary == 0) */
+			/* 62-63: asce id (always primary == 0) */
 		.exc_access_id = 0, /* always primary */
 		.op_access_id = 0, /* not MVPG */
 	};
@@ -906,19 +955,19 @@ static int handle_fault(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 {
 	int rc;
 
-	if (current->thread.gmap_int_code == PGM_PROTECTION)
+	if ((current->thread.gmap_int_code & PGM_INT_CODE_MASK) == PGM_PROTECTION)
 		/* we can directly forward all protection exceptions */
 		return inject_fault(vcpu, PGM_PROTECTION,
-				    current->thread.gmap_addr, 1);
+				    current->thread.gmap_teid.addr * PAGE_SIZE, 1);
 
 	rc = kvm_s390_shadow_fault(vcpu, vsie_page->gmap,
-				   current->thread.gmap_addr);
+				   current->thread.gmap_teid.addr * PAGE_SIZE, NULL);
 	if (rc > 0) {
 		rc = inject_fault(vcpu, rc,
-				  current->thread.gmap_addr,
-				  current->thread.gmap_write_flag);
+				  current->thread.gmap_teid.addr * PAGE_SIZE,
+				  kvm_s390_cur_gmap_fault_is_write());
 		if (rc >= 0)
-			vsie_page->fault_addr = current->thread.gmap_addr;
+			vsie_page->fault_addr = current->thread.gmap_teid.addr * PAGE_SIZE;
 	}
 	return rc;
 }
@@ -934,7 +983,7 @@ static void handle_last_fault(struct kvm_vcpu *vcpu,
 {
 	if (vsie_page->fault_addr)
 		kvm_s390_shadow_fault(vcpu, vsie_page->gmap,
-				      vsie_page->fault_addr);
+				      vsie_page->fault_addr, NULL);
 	vsie_page->fault_addr = 0;
 }
 
@@ -969,19 +1018,125 @@ static void retry_vsie_icpt(struct vsie_page *vsie_page)
 static int handle_stfle(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 {
 	struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s;
-	__u32 fac = READ_ONCE(vsie_page->scb_o->fac) & 0x7ffffff8U;
+	__u32 fac = READ_ONCE(vsie_page->scb_o->fac);
 
+	/*
+	 * Alternate-STFLE-Interpretive-Execution facilities are not supported
+	 * -> format-0 flcb
+	 */
 	if (fac && test_kvm_facility(vcpu->kvm, 7)) {
 		retry_vsie_icpt(vsie_page);
+		/*
+		 * The facility list origin (FLO) is in bits 1 - 28 of the FLD
+		 * so we need to mask here before reading.
+		 */
+		fac = fac & 0x7ffffff8U;
+		/*
+		 * format-0 -> size of nested guest's facility list == guest's size
+		 * guest's size == host's size, since STFLE is interpretatively executed
+		 * using a format-0 for the guest, too.
+		 */
 		if (read_guest_real(vcpu, fac, &vsie_page->fac,
-				    sizeof(vsie_page->fac)))
+				    stfle_size() * sizeof(u64)))
 			return set_validity_icpt(scb_s, 0x1090U);
-		scb_s->fac = (__u32)(__u64) &vsie_page->fac;
+		scb_s->fac = (u32)virt_to_phys(&vsie_page->fac);
 	}
 	return 0;
 }
 
 /*
+ * Get a register for a nested guest.
+ * @vcpu the vcpu of the guest
+ * @vsie_page the vsie_page for the nested guest
+ * @reg the register number, the upper 4 bits are ignored.
+ * returns: the value of the register.
+ */
+static u64 vsie_get_register(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page, u8 reg)
+{
+	/* no need to validate the parameter and/or perform error handling */
+	reg &= 0xf;
+	switch (reg) {
+	case 15:
+		return vsie_page->scb_s.gg15;
+	case 14:
+		return vsie_page->scb_s.gg14;
+	default:
+		return vcpu->run->s.regs.gprs[reg];
+	}
+}
+
+static int vsie_handle_mvpg(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
+{
+	struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s;
+	unsigned long pei_dest, pei_src, src, dest, mask, prefix;
+	u64 *pei_block = &vsie_page->scb_o->mcic;
+	int edat, rc_dest, rc_src;
+	union ctlreg0 cr0;
+
+	cr0.val = vcpu->arch.sie_block->gcr[0];
+	edat = cr0.edat && test_kvm_facility(vcpu->kvm, 8);
+	mask = _kvm_s390_logical_to_effective(&scb_s->gpsw, PAGE_MASK);
+	prefix = scb_s->prefix << GUEST_PREFIX_SHIFT;
+
+	dest = vsie_get_register(vcpu, vsie_page, scb_s->ipb >> 20) & mask;
+	dest = _kvm_s390_real_to_abs(prefix, dest) + scb_s->mso;
+	src = vsie_get_register(vcpu, vsie_page, scb_s->ipb >> 16) & mask;
+	src = _kvm_s390_real_to_abs(prefix, src) + scb_s->mso;
+
+	rc_dest = kvm_s390_shadow_fault(vcpu, vsie_page->gmap, dest, &pei_dest);
+	rc_src = kvm_s390_shadow_fault(vcpu, vsie_page->gmap, src, &pei_src);
+	/*
+	 * Either everything went well, or something non-critical went wrong
+	 * e.g. because of a race. In either case, simply retry.
+	 */
+	if (rc_dest == -EAGAIN || rc_src == -EAGAIN || (!rc_dest && !rc_src)) {
+		retry_vsie_icpt(vsie_page);
+		return -EAGAIN;
+	}
+	/* Something more serious went wrong, propagate the error */
+	if (rc_dest < 0)
+		return rc_dest;
+	if (rc_src < 0)
+		return rc_src;
+
+	/* The only possible suppressing exception: just deliver it */
+	if (rc_dest == PGM_TRANSLATION_SPEC || rc_src == PGM_TRANSLATION_SPEC) {
+		clear_vsie_icpt(vsie_page);
+		rc_dest = kvm_s390_inject_program_int(vcpu, PGM_TRANSLATION_SPEC);
+		WARN_ON_ONCE(rc_dest);
+		return 1;
+	}
+
+	/*
+	 * Forward the PEI intercept to the guest if it was a page fault, or
+	 * also for segment and region table faults if EDAT applies.
+	 */
+	if (edat) {
+		rc_dest = rc_dest == PGM_ASCE_TYPE ? rc_dest : 0;
+		rc_src = rc_src == PGM_ASCE_TYPE ? rc_src : 0;
+	} else {
+		rc_dest = rc_dest != PGM_PAGE_TRANSLATION ? rc_dest : 0;
+		rc_src = rc_src != PGM_PAGE_TRANSLATION ? rc_src : 0;
+	}
+	if (!rc_dest && !rc_src) {
+		pei_block[0] = pei_dest;
+		pei_block[1] = pei_src;
+		return 1;
+	}
+
+	retry_vsie_icpt(vsie_page);
+
+	/*
+	 * The host has edat, and the guest does not, or it was an ASCE type
+	 * exception. The host needs to inject the appropriate DAT interrupts
+	 * into the guest.
+	 */
+	if (rc_dest)
+		return inject_fault(vcpu, rc_dest, dest, 1);
+	return inject_fault(vcpu, rc_src, src, 0);
+}
+
+/*
  * Run the vsie on a shadow scb and a shadow gmap, without any further
  * sanity checks, handling SIE faults.
  *
@@ -1000,12 +1155,7 @@ static int do_vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 
 	handle_last_fault(vcpu, vsie_page);
 
-	if (need_resched())
-		schedule();
-	if (test_cpu_flag(CIF_MCCK_PENDING))
-		s390_handle_mcck();
-
-	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
+	kvm_vcpu_srcu_read_unlock(vcpu);
 
 	/* save current guest state of bp isolation override */
 	guest_bp_isolation = test_thread_flag(TIF_ISOLATE_BP_GUEST);
@@ -1031,9 +1181,10 @@ static int do_vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 	 * also kick the vSIE.
 	 */
 	vcpu->arch.sie_block->prog0c |= PROG_IN_SIE;
+	current->thread.gmap_int_code = 0;
 	barrier();
 	if (!kvm_s390_vcpu_sie_inhibited(vcpu))
-		rc = sie64a(scb_s, vcpu->run->s.regs.gprs);
+		rc = sie64a(scb_s, vcpu->run->s.regs.gprs, vsie_page->gmap->asce);
 	barrier();
 	vcpu->arch.sie_block->prog0c &= ~PROG_IN_SIE;
 
@@ -1045,7 +1196,7 @@ static int do_vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 	if (!guest_bp_isolation)
 		clear_thread_flag(TIF_ISOLATE_BP_GUEST);
 
-	vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
+	kvm_vcpu_srcu_read_lock(vcpu);
 
 	if (rc == -EINTR) {
 		VCPU_EVENT(vcpu, 3, "%s", "machine check");
@@ -1055,7 +1206,7 @@ static int do_vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 
 	if (rc > 0)
 		rc = 0; /* we could still have an icpt */
-	else if (rc == -EFAULT)
+	else if (current->thread.gmap_int_code)
 		return handle_fault(vcpu, vsie_page);
 
 	switch (scb_s->icptcode) {
@@ -1072,6 +1223,10 @@ static int do_vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 		if ((scb_s->ipa & 0xf000) != 0xf000)
 			scb_s->ipa += 0x1000;
 		break;
+	case ICPT_PARTEXEC:
+		if (scb_s->ipa == 0xb254)
+			rc = vsie_handle_mvpg(vcpu, vsie_page);
+		break;
 	}
 	return rc;
 }
@@ -1102,15 +1257,17 @@ static int acquire_gmap_shadow(struct kvm_vcpu *vcpu,
 	 * we're holding has been unshadowed. If the gmap is still valid,
 	 * we can safely reuse it.
 	 */
-	if (vsie_page->gmap && gmap_shadow_valid(vsie_page->gmap, asce, edat))
+	if (vsie_page->gmap && gmap_shadow_valid(vsie_page->gmap, asce, edat)) {
+		vcpu->kvm->stat.gmap_shadow_reuse++;
 		return 0;
+	}
 
 	/* release the old shadow - if any, and mark the prefix as unmapped */
 	release_gmap_shadow(vsie_page);
 	gmap = gmap_shadow(vcpu->arch.gmap, asce, edat);
 	if (IS_ERR(gmap))
 		return PTR_ERR(gmap);
-	gmap->private = vcpu->kvm;
+	vcpu->kvm->stat.gmap_shadow_create++;
 	WRITE_ONCE(vsie_page->gmap, gmap);
 	return 0;
 }
@@ -1172,19 +1329,32 @@ static int vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 		if (!rc)
 			rc = map_prefix(vcpu, vsie_page);
 		if (!rc) {
-			gmap_enable(vsie_page->gmap);
 			update_intervention_requests(vsie_page);
 			rc = do_vsie_run(vcpu, vsie_page);
-			gmap_enable(vcpu->arch.gmap);
 		}
 		atomic_andnot(PROG_BLOCK_SIE, &scb_s->prog20);
 
 		if (rc == -EAGAIN)
 			rc = 0;
-		if (rc || scb_s->icptcode || signal_pending(current) ||
+
+		/*
+		 * Exit the loop if the guest needs to process the intercept
+		 */
+		if (rc || scb_s->icptcode)
+			break;
+
+		/*
+		 * Exit the loop if the host needs to process an intercept,
+		 * but rewind the PSW to re-enter SIE once that's completed
+		 * instead of passing a "no action" intercept to the guest.
+		 */
+		if (signal_pending(current) ||
 		    kvm_s390_vcpu_has_irq(vcpu, 0) ||
-		    kvm_s390_vcpu_sie_inhibited(vcpu))
+		    kvm_s390_vcpu_sie_inhibited(vcpu)) {
+			kvm_s390_rewind_psw(vcpu, 4);
 			break;
+		}
+		cond_resched();
 	}
 
 	if (rc == -EFAULT) {
@@ -1202,10 +1372,25 @@ static int vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 		scb_s->iprcc = PGM_ADDRESSING;
 		scb_s->pgmilc = 4;
 		scb_s->gpsw.addr = __rewind_psw(scb_s->gpsw, 4);
+		rc = 1;
 	}
 	return rc;
 }
 
+/* Try getting a given vsie page, returning "true" on success. */
+static inline bool try_get_vsie_page(struct vsie_page *vsie_page)
+{
+	if (test_bit(VSIE_PAGE_IN_USE, &vsie_page->flags))
+		return false;
+	return !test_and_set_bit(VSIE_PAGE_IN_USE, &vsie_page->flags);
+}
+
+/* Put a vsie page acquired through get_vsie_page / try_get_vsie_page. */
+static void put_vsie_page(struct vsie_page *vsie_page)
+{
+	clear_bit(VSIE_PAGE_IN_USE, &vsie_page->flags);
+}
+
 /*
  * Get or create a vsie page for a scb address.
  *
@@ -1216,16 +1401,21 @@ static int vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 static struct vsie_page *get_vsie_page(struct kvm *kvm, unsigned long addr)
 {
 	struct vsie_page *vsie_page;
-	struct page *page;
 	int nr_vcpus;
 
 	rcu_read_lock();
-	page = radix_tree_lookup(&kvm->arch.vsie.addr_to_page, addr >> 9);
+	vsie_page = radix_tree_lookup(&kvm->arch.vsie.addr_to_page, addr >> 9);
 	rcu_read_unlock();
-	if (page) {
-		if (page_ref_inc_return(page) == 2)
-			return page_to_virt(page);
-		page_ref_dec(page);
+	if (vsie_page) {
+		if (try_get_vsie_page(vsie_page)) {
+			if (vsie_page->scb_gpa == addr)
+				return vsie_page;
+			/*
+			 * We raced with someone reusing + putting this vsie
+			 * page before we grabbed it.
+			 */
+			put_vsie_page(vsie_page);
+		}
 	}
 
 	/*
@@ -1236,36 +1426,40 @@ static struct vsie_page *get_vsie_page(struct kvm *kvm, unsigned long addr)
 
 	mutex_lock(&kvm->arch.vsie.mutex);
 	if (kvm->arch.vsie.page_count < nr_vcpus) {
-		page = alloc_page(GFP_KERNEL | __GFP_ZERO | GFP_DMA);
-		if (!page) {
+		vsie_page = (void *)__get_free_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO | GFP_DMA);
+		if (!vsie_page) {
 			mutex_unlock(&kvm->arch.vsie.mutex);
 			return ERR_PTR(-ENOMEM);
 		}
-		page_ref_inc(page);
-		kvm->arch.vsie.pages[kvm->arch.vsie.page_count] = page;
+		__set_bit(VSIE_PAGE_IN_USE, &vsie_page->flags);
+		kvm->arch.vsie.pages[kvm->arch.vsie.page_count] = vsie_page;
 		kvm->arch.vsie.page_count++;
 	} else {
 		/* reuse an existing entry that belongs to nobody */
 		while (true) {
-			page = kvm->arch.vsie.pages[kvm->arch.vsie.next];
-			if (page_ref_inc_return(page) == 2)
+			vsie_page = kvm->arch.vsie.pages[kvm->arch.vsie.next];
+			if (try_get_vsie_page(vsie_page))
 				break;
-			page_ref_dec(page);
 			kvm->arch.vsie.next++;
 			kvm->arch.vsie.next %= nr_vcpus;
 		}
-		radix_tree_delete(&kvm->arch.vsie.addr_to_page, page->index >> 9);
+		if (vsie_page->scb_gpa != ULONG_MAX)
+			radix_tree_delete(&kvm->arch.vsie.addr_to_page,
+					  vsie_page->scb_gpa >> 9);
 	}
-	page->index = addr;
-	/* double use of the same address */
-	if (radix_tree_insert(&kvm->arch.vsie.addr_to_page, addr >> 9, page)) {
-		page_ref_dec(page);
+	/* Mark it as invalid until it resides in the tree. */
+	vsie_page->scb_gpa = ULONG_MAX;
+
+	/* Double use of the same address or allocation failure. */
+	if (radix_tree_insert(&kvm->arch.vsie.addr_to_page, addr >> 9,
+			      vsie_page)) {
+		put_vsie_page(vsie_page);
 		mutex_unlock(&kvm->arch.vsie.mutex);
 		return NULL;
 	}
+	vsie_page->scb_gpa = addr;
 	mutex_unlock(&kvm->arch.vsie.mutex);
 
-	vsie_page = page_to_virt(page);
 	memset(&vsie_page->scb_s, 0, sizeof(struct kvm_s390_sie_block));
 	release_gmap_shadow(vsie_page);
 	vsie_page->fault_addr = 0;
@@ -1273,14 +1467,6 @@ static struct vsie_page *get_vsie_page(struct kvm *kvm, unsigned long addr)
 	return vsie_page;
 }
 
-/* put a vsie page acquired via get_vsie_page */
-static void put_vsie_page(struct kvm *kvm, struct vsie_page *vsie_page)
-{
-	struct page *page = pfn_to_page(__pa(vsie_page) >> PAGE_SHIFT);
-
-	page_ref_dec(page);
-}
-
 int kvm_s390_handle_vsie(struct kvm_vcpu *vcpu)
 {
 	struct vsie_page *vsie_page;
@@ -1301,8 +1487,10 @@ int kvm_s390_handle_vsie(struct kvm_vcpu *vcpu)
 		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
 
 	if (signal_pending(current) || kvm_s390_vcpu_has_irq(vcpu, 0) ||
-	    kvm_s390_vcpu_sie_inhibited(vcpu))
+	    kvm_s390_vcpu_sie_inhibited(vcpu)) {
+		kvm_s390_rewind_psw(vcpu, 4);
 		return 0;
+	}
 
 	vsie_page = get_vsie_page(vcpu->kvm, scb_addr);
 	if (IS_ERR(vsie_page))
@@ -1329,7 +1517,7 @@ out_unshadow:
 out_unpin_scb:
 	unpin_scb(vcpu, vsie_page, scb_addr);
 out_put:
-	put_vsie_page(vcpu->kvm, vsie_page);
+	put_vsie_page(vsie_page);
 
 	return rc < 0 ? rc : 0;
 }
@@ -1338,25 +1526,25 @@ out_put:
 void kvm_s390_vsie_init(struct kvm *kvm)
 {
 	mutex_init(&kvm->arch.vsie.mutex);
-	INIT_RADIX_TREE(&kvm->arch.vsie.addr_to_page, GFP_KERNEL);
+	INIT_RADIX_TREE(&kvm->arch.vsie.addr_to_page, GFP_KERNEL_ACCOUNT);
 }
 
 /* Destroy the vsie data structures. To be called when a vm is destroyed. */
 void kvm_s390_vsie_destroy(struct kvm *kvm)
 {
 	struct vsie_page *vsie_page;
-	struct page *page;
 	int i;
 
 	mutex_lock(&kvm->arch.vsie.mutex);
 	for (i = 0; i < kvm->arch.vsie.page_count; i++) {
-		page = kvm->arch.vsie.pages[i];
+		vsie_page = kvm->arch.vsie.pages[i];
 		kvm->arch.vsie.pages[i] = NULL;
-		vsie_page = page_to_virt(page);
 		release_gmap_shadow(vsie_page);
 		/* free the radix tree entry */
-		radix_tree_delete(&kvm->arch.vsie.addr_to_page, page->index >> 9);
-		__free_page(page);
+		if (vsie_page->scb_gpa != ULONG_MAX)
+			radix_tree_delete(&kvm->arch.vsie.addr_to_page,
+					  vsie_page->scb_gpa >> 9);
+		free_page((unsigned long)vsie_page);
 	}
 	kvm->arch.vsie.page_count = 0;
 	mutex_unlock(&kvm->arch.vsie.mutex);