ARM:

* Correctly clean the BSS to the PoC before allowing EL2 to access it
   on nVHE/hVHE/protected configurations
 
 * Propagate ownership of debug registers in protected mode after
   the rework that landed in 6.14-rc1
 
 * Stop pretending that we can run the protected mode without a GICv3
   being present on the host
 
 * Fix a use-after-free situation that can occur if a vcpu fails to
   initialise the NV shadow S2 MMU contexts
 
 * Always evaluate the need to arm a background timer for fully emulated
   guest timers
 
 * Fix the emulation of EL1 timers in the absence of FEAT_ECV
 
 * Correctly handle the EL2 virtual timer, specially when HCR_EL2.E2H==0
 
 s390:
 
 * move some of the guest page table (gmap) logic into KVM itself,
   inching towards the final goal of completely removing gmap from the
   non-kvm memory management code. As an initial set of cleanups, move
   some code from mm/gmap into kvm and start using __kvm_faultin_pfn()
   to fault-in pages as needed; but especially stop abusing page->index
   and page->lru to aid in the pgdesc conversion.
 
 x86:
 
 * Add missing check in the fix to defer starting the huge page recovery
   vhost_task
 
 * SRSO_USER_KERNEL_NO does not need SYNTHESIZED_F
 -----BEGIN PGP SIGNATURE-----
 
 iQFIBAABCAAyFiEE8TM4V0tmI4mGbHaCv/vSX3jHroMFAmemTnEUHHBib256aW5p
 QHJlZGhhdC5jb20ACgkQv/vSX3jHroP97gf/Rew+yEsRrHVk/j0R2XwFx51raYZy
 eaicv07jYmwsnaALq6BEj4xxDW8dJEJgj05Czm1o9+9x8nvY2+UjT2q4J8fY9xdD
 Yr+5GvEEz4x2GNL3ZYE3iHTNFQckNxOgMilLW3br1E+wjusShKmgGxPYTRyClQ34
 gDBZQWzOG22UNC6PbW9dgTK54b57+NJdIZYuHz4LkMsTvzf6jXo5VumsgbbZqC4e
 VGh5EUEPL7+cNzGY/+WURXI6OojdPzbneH1NP82uT3lo2WaHK9+B3N6H+W71N/T4
 u1P7+g0WmdNj3FITvDpTJ7jNhke2atEjI9rvtHz6gwtf9SIujyuNl55uRA==
 =r0h9
 -----END PGP SIGNATURE-----

Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull kvm fixes from Paolo Bonzini:
 "ARM:

   - Correctly clean the BSS to the PoC before allowing EL2 to access it
     on nVHE/hVHE/protected configurations

   - Propagate ownership of debug registers in protected mode after the
     rework that landed in 6.14-rc1

   - Stop pretending that we can run the protected mode without a GICv3
     being present on the host

   - Fix a use-after-free situation that can occur if a vcpu fails to
     initialise the NV shadow S2 MMU contexts

   - Always evaluate the need to arm a background timer for fully
     emulated guest timers

   - Fix the emulation of EL1 timers in the absence of FEAT_ECV

   - Correctly handle the EL2 virtual timer, specially when HCR_EL2.E2H==0

  s390:

   - move some of the guest page table (gmap) logic into KVM itself,
     inching towards the final goal of completely removing gmap from the
     non-kvm memory management code.

     As an initial set of cleanups, move some code from mm/gmap into kvm
     and start using __kvm_faultin_pfn() to fault-in pages as needed;
     but especially stop abusing page->index and page->lru to aid in the
     pgdesc conversion.

  x86:

   - Add missing check in the fix to defer starting the huge page
     recovery vhost_task

   - SRSO_USER_KERNEL_NO does not need SYNTHESIZED_F"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (31 commits)
  KVM: x86/mmu: Ensure NX huge page recovery thread is alive before waking
  KVM: remove kvm_arch_post_init_vm
  KVM: selftests: Fix spelling mistake "initally" -> "initially"
  kvm: x86: SRSO_USER_KERNEL_NO is not synthesized
  KVM: arm64: timer: Don't adjust the EL2 virtual timer offset
  KVM: arm64: timer: Correctly handle EL1 timer emulation when !FEAT_ECV
  KVM: arm64: timer: Always evaluate the need for a soft timer
  KVM: arm64: Fix nested S2 MMU structures reallocation
  KVM: arm64: Fail protected mode init if no vgic hardware is present
  KVM: arm64: Flush/sync debug state in protected mode
  KVM: s390: selftests: Streamline uc_skey test to issue iske after sske
  KVM: s390: remove the last user of page->index
  KVM: s390: move PGSTE softbits
  KVM: s390: remove useless page->index usage
  KVM: s390: move gmap_shadow_pgt_lookup() into kvm
  KVM: s390: stop using lists to keep track of used dat tables
  KVM: s390: stop using page->index for non-shadow gmaps
  KVM: s390: move some gmap shadowing functions away from mm/gmap.c
  KVM: s390: get rid of gmap_translate()
  KVM: s390: get rid of gmap_fault()
  ...

Documentation/virt/kvm/api.rst

@@ -1419,7 +1419,7 @@ fetch) is injected in the guest.
 S390:
 ^^^^^
 
-Returns -EINVAL if the VM has the KVM_VM_S390_UCONTROL flag set.
+Returns -EINVAL or -EEXIST if the VM has the KVM_VM_S390_UCONTROL flag set.
 Returns -EINVAL if called on a protected VM.
 
 4.36 KVM_SET_TSS_ADDR

arch/arm64/kvm/arch_timer.c

@@ -471,10 +471,8 @@ static void timer_emulate(struct arch_timer_context *ctx)
 
 	trace_kvm_timer_emulate(ctx, should_fire);
 
-	if (should_fire != ctx->irq.level) {
+	if (should_fire != ctx->irq.level)
 		kvm_timer_update_irq(ctx->vcpu, should_fire, ctx);
-		return;
-	}
 
 	kvm_timer_update_status(ctx, should_fire);
 
@@ -761,21 +759,6 @@ static void kvm_timer_vcpu_load_nested_switch(struct kvm_vcpu *vcpu,
 					    timer_irq(map->direct_ptimer),
 					    &arch_timer_irq_ops);
 		WARN_ON_ONCE(ret);
-
-		/*
-		 * The virtual offset behaviour is "interesting", as it
-		 * always applies when HCR_EL2.E2H==0, but only when
-		 * accessed from EL1 when HCR_EL2.E2H==1. So make sure we
-		 * track E2H when putting the HV timer in "direct" mode.
-		 */
-		if (map->direct_vtimer == vcpu_hvtimer(vcpu)) {
-			struct arch_timer_offset *offs = &map->direct_vtimer->offset;
-
-			if (vcpu_el2_e2h_is_set(vcpu))
-				offs->vcpu_offset = NULL;
-			else
-				offs->vcpu_offset = &__vcpu_sys_reg(vcpu, CNTVOFF_EL2);
-		}
 	}
 }
 
@@ -976,31 +959,21 @@ void kvm_timer_sync_nested(struct kvm_vcpu *vcpu)
 	 * which allows trapping of the timer registers even with NV2.
 	 * Still, this is still worse than FEAT_NV on its own. Meh.
 	 */
-	if (!vcpu_el2_e2h_is_set(vcpu)) {
+	if (!cpus_have_final_cap(ARM64_HAS_ECV)) {
-		if (cpus_have_final_cap(ARM64_HAS_ECV))
-			return;
-
-		/*
-		 * A non-VHE guest hypervisor doesn't have any direct access
-		 * to its timers: the EL2 registers trap (and the HW is
-		 * fully emulated), while the EL0 registers access memory
-		 * despite the access being notionally direct. Boo.
-		 *
-		 * We update the hardware timer registers with the
-		 * latest value written by the guest to the VNCR page
-		 * and let the hardware take care of the rest.
-		 */
-		write_sysreg_el0(__vcpu_sys_reg(vcpu, CNTV_CTL_EL0),  SYS_CNTV_CTL);
-		write_sysreg_el0(__vcpu_sys_reg(vcpu, CNTV_CVAL_EL0), SYS_CNTV_CVAL);
-		write_sysreg_el0(__vcpu_sys_reg(vcpu, CNTP_CTL_EL0),  SYS_CNTP_CTL);
-		write_sysreg_el0(__vcpu_sys_reg(vcpu, CNTP_CVAL_EL0), SYS_CNTP_CVAL);
-	} else {
 		/*
 		 * For a VHE guest hypervisor, the EL2 state is directly
-		 * stored in the host EL1 timers, while the emulated EL0
+		 * stored in the host EL1 timers, while the emulated EL1
 		 * state is stored in the VNCR page. The latter could have
 		 * been updated behind our back, and we must reset the
 		 * emulation of the timers.
+		 *
+		 * A non-VHE guest hypervisor doesn't have any direct access
+		 * to its timers: the EL2 registers trap despite being
+		 * notionally direct (we use the EL1 HW, as for VHE), while
+		 * the EL1 registers access memory.
+		 *
+		 * In both cases, process the emulated timers on each guest
+		 * exit. Boo.
 		 */
 		struct timer_map map;
 		get_timer_map(vcpu, &map);

arch/arm64/kvm/arm.c

@@ -2290,6 +2290,19 @@ static int __init init_subsystems(void)
 		break;
 	case -ENODEV:
 	case -ENXIO:
+		/*
+		 * No VGIC? No pKVM for you.
+		 *
+		 * Protected mode assumes that VGICv3 is present, so no point
+		 * in trying to hobble along if vgic initialization fails.
+		 */
+		if (is_protected_kvm_enabled())
+			goto out;
+
+		/*
+		 * Otherwise, userspace could choose to implement a GIC for its
+		 * guest on non-cooperative hardware.
+		 */
 		vgic_present = false;
 		err = 0;
 		break;
@@ -2400,6 +2413,13 @@ static void kvm_hyp_init_symbols(void)
 	kvm_nvhe_sym(id_aa64smfr0_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64SMFR0_EL1);
 	kvm_nvhe_sym(__icache_flags) = __icache_flags;
 	kvm_nvhe_sym(kvm_arm_vmid_bits) = kvm_arm_vmid_bits;
+
+	/*
+	 * Flush entire BSS since part of its data containing init symbols is read
+	 * while the MMU is off.
+	 */
+	kvm_flush_dcache_to_poc(kvm_ksym_ref(__hyp_bss_start),
+				kvm_ksym_ref(__hyp_bss_end) - kvm_ksym_ref(__hyp_bss_start));
 }
 
 static int __init kvm_hyp_init_protection(u32 hyp_va_bits)

arch/arm64/kvm/hyp/nvhe/hyp-main.c

@@ -91,11 +91,34 @@ static void fpsimd_sve_sync(struct kvm_vcpu *vcpu)
 	*host_data_ptr(fp_owner) = FP_STATE_HOST_OWNED;
 }
 
+static void flush_debug_state(struct pkvm_hyp_vcpu *hyp_vcpu)
+{
+	struct kvm_vcpu *host_vcpu = hyp_vcpu->host_vcpu;
+
+	hyp_vcpu->vcpu.arch.debug_owner = host_vcpu->arch.debug_owner;
+
+	if (kvm_guest_owns_debug_regs(&hyp_vcpu->vcpu))
+		hyp_vcpu->vcpu.arch.vcpu_debug_state = host_vcpu->arch.vcpu_debug_state;
+	else if (kvm_host_owns_debug_regs(&hyp_vcpu->vcpu))
+		hyp_vcpu->vcpu.arch.external_debug_state = host_vcpu->arch.external_debug_state;
+}
+
+static void sync_debug_state(struct pkvm_hyp_vcpu *hyp_vcpu)
+{
+	struct kvm_vcpu *host_vcpu = hyp_vcpu->host_vcpu;
+
+	if (kvm_guest_owns_debug_regs(&hyp_vcpu->vcpu))
+		host_vcpu->arch.vcpu_debug_state = hyp_vcpu->vcpu.arch.vcpu_debug_state;
+	else if (kvm_host_owns_debug_regs(&hyp_vcpu->vcpu))
+		host_vcpu->arch.external_debug_state = hyp_vcpu->vcpu.arch.external_debug_state;
+}
+
 static void flush_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu)
 {
 	struct kvm_vcpu *host_vcpu = hyp_vcpu->host_vcpu;
 
 	fpsimd_sve_flush();
+	flush_debug_state(hyp_vcpu);
 
 	hyp_vcpu->vcpu.arch.ctxt	= host_vcpu->arch.ctxt;
 
@@ -123,6 +146,7 @@ static void sync_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu)
 	unsigned int i;
 
 	fpsimd_sve_sync(&hyp_vcpu->vcpu);
+	sync_debug_state(hyp_vcpu);
 
 	host_vcpu->arch.ctxt		= hyp_vcpu->vcpu.arch.ctxt;
 

arch/arm64/kvm/nested.c

@@ -67,26 +67,27 @@ int kvm_vcpu_init_nested(struct kvm_vcpu *vcpu)
 	if (!tmp)
 		return -ENOMEM;
 
+	swap(kvm->arch.nested_mmus, tmp);
+
 	/*
 	 * If we went through a realocation, adjust the MMU back-pointers in
 	 * the previously initialised kvm_pgtable structures.
 	 */
 	if (kvm->arch.nested_mmus != tmp)
 		for (int i = 0; i < kvm->arch.nested_mmus_size; i++)
-			tmp[i].pgt->mmu = &tmp[i];
+			kvm->arch.nested_mmus[i].pgt->mmu = &kvm->arch.nested_mmus[i];
 
 	for (int i = kvm->arch.nested_mmus_size; !ret && i < num_mmus; i++)
-		ret = init_nested_s2_mmu(kvm, &tmp[i]);
+		ret = init_nested_s2_mmu(kvm, &kvm->arch.nested_mmus[i]);
 
 	if (ret) {
 		for (int i = kvm->arch.nested_mmus_size; i < num_mmus; i++)
-			kvm_free_stage2_pgd(&tmp[i]);
+			kvm_free_stage2_pgd(&kvm->arch.nested_mmus[i]);
 
 		return ret;
 	}
 
 	kvm->arch.nested_mmus_size = num_mmus;
-	kvm->arch.nested_mmus = tmp;
 
 	return 0;
 }

arch/arm64/kvm/sys_regs.c

@@ -1452,6 +1452,16 @@ static bool access_arch_timer(struct kvm_vcpu *vcpu,
 	return true;
 }
 
+static bool access_hv_timer(struct kvm_vcpu *vcpu,
+			    struct sys_reg_params *p,
+			    const struct sys_reg_desc *r)
+{
+	if (!vcpu_el2_e2h_is_set(vcpu))
+		return undef_access(vcpu, p, r);
+
+	return access_arch_timer(vcpu, p, r);
+}
+
 static s64 kvm_arm64_ftr_safe_value(u32 id, const struct arm64_ftr_bits *ftrp,
 				    s64 new, s64 cur)
 {
@@ -3103,9 +3113,9 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	EL2_REG(CNTHP_CTL_EL2, access_arch_timer, reset_val, 0),
 	EL2_REG(CNTHP_CVAL_EL2, access_arch_timer, reset_val, 0),
 
-	{ SYS_DESC(SYS_CNTHV_TVAL_EL2), access_arch_timer },
+	{ SYS_DESC(SYS_CNTHV_TVAL_EL2), access_hv_timer },
-	EL2_REG(CNTHV_CTL_EL2, access_arch_timer, reset_val, 0),
+	EL2_REG(CNTHV_CTL_EL2, access_hv_timer, reset_val, 0),
-	EL2_REG(CNTHV_CVAL_EL2, access_arch_timer, reset_val, 0),
+	EL2_REG(CNTHV_CVAL_EL2, access_hv_timer, reset_val, 0),
 
 	{ SYS_DESC(SYS_CNTKCTL_EL12), access_cntkctl_el12 },
 

arch/s390/include/asm/gmap.h

@@ -23,7 +23,6 @@
 /**
  * struct gmap_struct - guest address space
  * @list: list head for the mm->context gmap list
- * @crst_list: list of all crst tables used in the guest address space
  * @mm: pointer to the parent mm_struct
  * @guest_to_host: radix tree with guest to host address translation
  * @host_to_guest: radix tree with pointer to segment table entries
@@ -35,7 +34,6 @@
  * @guest_handle: protected virtual machine handle for the ultravisor
  * @host_to_rmap: radix tree with gmap_rmap lists
  * @children: list of shadow gmap structures
- * @pt_list: list of all page tables used in the shadow guest address space
  * @shadow_lock: spinlock to protect the shadow gmap list
  * @parent: pointer to the parent gmap for shadow guest address spaces
  * @orig_asce: ASCE for which the shadow page table has been created
@@ -45,7 +43,6 @@
  */
 struct gmap {
 	struct list_head list;
-	struct list_head crst_list;
 	struct mm_struct *mm;
 	struct radix_tree_root guest_to_host;
 	struct radix_tree_root host_to_guest;
@@ -61,7 +58,6 @@ struct gmap {
 	/* Additional data for shadow guest address spaces */
 	struct radix_tree_root host_to_rmap;
 	struct list_head children;
-	struct list_head pt_list;
 	spinlock_t shadow_lock;
 	struct gmap *parent;
 	unsigned long orig_asce;
@@ -106,23 +102,21 @@ struct gmap *gmap_create(struct mm_struct *mm, unsigned long limit);
 void gmap_remove(struct gmap *gmap);
 struct gmap *gmap_get(struct gmap *gmap);
 void gmap_put(struct gmap *gmap);
+void gmap_free(struct gmap *gmap);
+struct gmap *gmap_alloc(unsigned long limit);
 
 int gmap_map_segment(struct gmap *gmap, unsigned long from,
 		     unsigned long to, unsigned long len);
 int gmap_unmap_segment(struct gmap *gmap, unsigned long to, unsigned long len);
 unsigned long __gmap_translate(struct gmap *, unsigned long gaddr);
-unsigned long gmap_translate(struct gmap *, unsigned long gaddr);
 int __gmap_link(struct gmap *gmap, unsigned long gaddr, unsigned long vmaddr);
-int gmap_fault(struct gmap *, unsigned long gaddr, unsigned int fault_flags);
 void gmap_discard(struct gmap *, unsigned long from, unsigned long to);
 void __gmap_zap(struct gmap *, unsigned long gaddr);
 void gmap_unlink(struct mm_struct *, unsigned long *table, unsigned long vmaddr);
 
 int gmap_read_table(struct gmap *gmap, unsigned long gaddr, unsigned long *val);
 
-struct gmap *gmap_shadow(struct gmap *parent, unsigned long asce,
+void gmap_unshadow(struct gmap *sg);
-			 int edat_level);
-int gmap_shadow_valid(struct gmap *sg, unsigned long asce, int edat_level);
 int gmap_shadow_r2t(struct gmap *sg, unsigned long saddr, unsigned long r2t,
 		    int fake);
 int gmap_shadow_r3t(struct gmap *sg, unsigned long saddr, unsigned long r3t,
@@ -131,24 +125,22 @@ int gmap_shadow_sgt(struct gmap *sg, unsigned long saddr, unsigned long sgt,
 		    int fake);
 int gmap_shadow_pgt(struct gmap *sg, unsigned long saddr, unsigned long pgt,
 		    int fake);
-int gmap_shadow_pgt_lookup(struct gmap *sg, unsigned long saddr,
-			   unsigned long *pgt, int *dat_protection, int *fake);
 int gmap_shadow_page(struct gmap *sg, unsigned long saddr, pte_t pte);
 
 void gmap_register_pte_notifier(struct gmap_notifier *);
 void gmap_unregister_pte_notifier(struct gmap_notifier *);
 
-int gmap_mprotect_notify(struct gmap *, unsigned long start,
+int gmap_protect_one(struct gmap *gmap, unsigned long gaddr, int prot, unsigned long bits);
-			 unsigned long len, int prot);
 
 void gmap_sync_dirty_log_pmd(struct gmap *gmap, unsigned long dirty_bitmap[4],
 			     unsigned long gaddr, unsigned long vmaddr);
 int s390_disable_cow_sharing(void);
-void s390_unlist_old_asce(struct gmap *gmap);
 int s390_replace_asce(struct gmap *gmap);
 void s390_uv_destroy_pfns(unsigned long count, unsigned long *pfns);
 int __s390_uv_destroy_range(struct mm_struct *mm, unsigned long start,
 			    unsigned long end, bool interruptible);
+int kvm_s390_wiggle_split_folio(struct mm_struct *mm, struct folio *folio, bool split);
+unsigned long *gmap_table_walk(struct gmap *gmap, unsigned long gaddr, int level);
 
 /**
  * s390_uv_destroy_range - Destroy a range of pages in the given mm.

arch/s390/include/asm/kvm_host.h

@@ -30,6 +30,8 @@
 #define KVM_S390_ESCA_CPU_SLOTS 248
 #define KVM_MAX_VCPUS 255
 
+#define KVM_INTERNAL_MEM_SLOTS 1
+
 /*
  * These seem to be used for allocating ->chip in the routing table, which we
  * don't use. 1 is as small as we can get to reduce the needed memory. If we
@@ -931,12 +933,14 @@ struct sie_page2 {
 	u8 reserved928[0x1000 - 0x928];			/* 0x0928 */
 };
 
+struct vsie_page;
+
 struct kvm_s390_vsie {
 	struct mutex mutex;
 	struct radix_tree_root addr_to_page;
 	int page_count;
 	int next;
-	struct page *pages[KVM_MAX_VCPUS];
+	struct vsie_page *pages[KVM_MAX_VCPUS];
 };
 
 struct kvm_s390_gisa_iam {

arch/s390/include/asm/pgtable.h

@@ -420,9 +420,10 @@ void setup_protection_map(void);
 #define PGSTE_HC_BIT	0x0020000000000000UL
 #define PGSTE_GR_BIT	0x0004000000000000UL
 #define PGSTE_GC_BIT	0x0002000000000000UL
-#define PGSTE_UC_BIT	0x0000800000000000UL	/* user dirty (migration) */
+#define PGSTE_ST2_MASK	0x0000ffff00000000UL
-#define PGSTE_IN_BIT	0x0000400000000000UL	/* IPTE notify bit */
+#define PGSTE_UC_BIT	0x0000000000008000UL	/* user dirty (migration) */
-#define PGSTE_VSIE_BIT	0x0000200000000000UL	/* ref'd in a shadow table */
+#define PGSTE_IN_BIT	0x0000000000004000UL	/* IPTE notify bit */
+#define PGSTE_VSIE_BIT	0x0000000000002000UL	/* ref'd in a shadow table */
 
 /* Guest Page State used for virtualization */
 #define _PGSTE_GPS_ZERO			0x0000000080000000UL
@@ -2007,4 +2008,18 @@ extern void s390_reset_cmma(struct mm_struct *mm);
 #define pmd_pgtable(pmd) \
 	((pgtable_t)__va(pmd_val(pmd) & -sizeof(pte_t)*PTRS_PER_PTE))
 
+static inline unsigned long gmap_pgste_get_pgt_addr(unsigned long *pgt)
+{
+	unsigned long *pgstes, res;
+
+	pgstes = pgt + _PAGE_ENTRIES;
+
+	res = (pgstes[0] & PGSTE_ST2_MASK) << 16;
+	res |= pgstes[1] & PGSTE_ST2_MASK;
+	res |= (pgstes[2] & PGSTE_ST2_MASK) >> 16;
+	res |= (pgstes[3] & PGSTE_ST2_MASK) >> 32;
+
+	return res;
+}
+
 #endif /* _S390_PAGE_H */

arch/s390/include/asm/uv.h

@@ -628,12 +628,12 @@ static inline int is_prot_virt_host(void)
 }
 
 int uv_pin_shared(unsigned long paddr);
-int gmap_make_secure(struct gmap *gmap, unsigned long gaddr, void *uvcb);
-int gmap_destroy_page(struct gmap *gmap, unsigned long gaddr);
 int uv_destroy_folio(struct folio *folio);
 int uv_destroy_pte(pte_t pte);
 int uv_convert_from_secure_pte(pte_t pte);
-int gmap_convert_to_secure(struct gmap *gmap, unsigned long gaddr);
+int make_folio_secure(struct folio *folio, struct uv_cb_header *uvcb);
+int uv_convert_from_secure(unsigned long paddr);
+int uv_convert_from_secure_folio(struct folio *folio);
 
 void setup_uv(void);
 

arch/s390/kernel/uv.c

@@ -19,19 +19,6 @@
 #include <asm/sections.h>
 #include <asm/uv.h>
 
-#if !IS_ENABLED(CONFIG_KVM)
-unsigned long __gmap_translate(struct gmap *gmap, unsigned long gaddr)
-{
-	return 0;
-}
-
-int gmap_fault(struct gmap *gmap, unsigned long gaddr,
-	       unsigned int fault_flags)
-{
-	return 0;
-}
-#endif
-
 /* the bootdata_preserved fields come from ones in arch/s390/boot/uv.c */
 int __bootdata_preserved(prot_virt_guest);
 EXPORT_SYMBOL(prot_virt_guest);
@@ -159,6 +146,7 @@ int uv_destroy_folio(struct folio *folio)
 	folio_put(folio);
 	return rc;
 }
+EXPORT_SYMBOL(uv_destroy_folio);
 
 /*
  * The present PTE still indirectly holds a folio reference through the mapping.
@@ -175,7 +163,7 @@ int uv_destroy_pte(pte_t pte)
  *
  * @paddr: Absolute host address of page to be exported
  */
-static int uv_convert_from_secure(unsigned long paddr)
+int uv_convert_from_secure(unsigned long paddr)
 {
 	struct uv_cb_cfs uvcb = {
 		.header.cmd = UVC_CMD_CONV_FROM_SEC_STOR,
@@ -187,11 +175,12 @@ static int uv_convert_from_secure(unsigned long paddr)
 		return -EINVAL;
 	return 0;
 }
+EXPORT_SYMBOL_GPL(uv_convert_from_secure);
 
 /*
  * The caller must already hold a reference to the folio.
  */
-static int uv_convert_from_secure_folio(struct folio *folio)
+int uv_convert_from_secure_folio(struct folio *folio)
 {
 	int rc;
 
@@ -206,6 +195,7 @@ static int uv_convert_from_secure_folio(struct folio *folio)
 	folio_put(folio);
 	return rc;
 }
+EXPORT_SYMBOL_GPL(uv_convert_from_secure_folio);
 
 /*
  * The present PTE still indirectly holds a folio reference through the mapping.
@@ -237,13 +227,33 @@ static int expected_folio_refs(struct folio *folio)
 	return res;
 }
 
-static int make_folio_secure(struct folio *folio, struct uv_cb_header *uvcb)
+/**
+ * make_folio_secure() - make a folio secure
+ * @folio: the folio to make secure
+ * @uvcb: the uvcb that describes the UVC to be used
+ *
+ * The folio @folio will be made secure if possible, @uvcb will be passed
+ * as-is to the UVC.
+ *
+ * Return: 0 on success;
+ *         -EBUSY if the folio is in writeback or has too many references;
+ *         -E2BIG if the folio is large;
+ *         -EAGAIN if the UVC needs to be attempted again;
+ *         -ENXIO if the address is not mapped;
+ *         -EINVAL if the UVC failed for other reasons.
+ *
+ * Context: The caller must hold exactly one extra reference on the folio
+ *          (it's the same logic as split_folio())
+ */
+int make_folio_secure(struct folio *folio, struct uv_cb_header *uvcb)
 {
 	int expected, cc = 0;
 
+	if (folio_test_large(folio))
+		return -E2BIG;
 	if (folio_test_writeback(folio))
-		return -EAGAIN;
+		return -EBUSY;
-	expected = expected_folio_refs(folio);
+	expected = expected_folio_refs(folio) + 1;
 	if (!folio_ref_freeze(folio, expected))
 		return -EBUSY;
 	set_bit(PG_arch_1, &folio->flags);
@@ -267,251 +277,7 @@ static int make_folio_secure(struct folio *folio, struct uv_cb_header *uvcb)
 		return -EAGAIN;
 	return uvcb->rc == 0x10a ? -ENXIO : -EINVAL;
 }
-
+EXPORT_SYMBOL_GPL(make_folio_secure);
-/**
- * should_export_before_import - Determine whether an export is needed
- * before an import-like operation
- * @uvcb: the Ultravisor control block of the UVC to be performed
- * @mm: the mm of the process
- *
- * Returns whether an export is needed before every import-like operation.
- * This is needed for shared pages, which don't trigger a secure storage
- * exception when accessed from a different guest.
- *
- * Although considered as one, the Unpin Page UVC is not an actual import,
- * so it is not affected.
- *
- * No export is needed also when there is only one protected VM, because the
- * page cannot belong to the wrong VM in that case (there is no "other VM"
- * it can belong to).
- *
- * Return: true if an export is needed before every import, otherwise false.
- */
-static bool should_export_before_import(struct uv_cb_header *uvcb, struct mm_struct *mm)
-{
-	/*
-	 * The misc feature indicates, among other things, that importing a
-	 * shared page from a different protected VM will automatically also
-	 * transfer its ownership.
-	 */
-	if (uv_has_feature(BIT_UV_FEAT_MISC))
-		return false;
-	if (uvcb->cmd == UVC_CMD_UNPIN_PAGE_SHARED)
-		return false;
-	return atomic_read(&mm->context.protected_count) > 1;
-}
-
-/*
- * Drain LRU caches: the local one on first invocation and the ones of all
- * CPUs on successive invocations. Returns "true" on the first invocation.
- */
-static bool drain_lru(bool *drain_lru_called)
-{
-	/*
-	 * If we have tried a local drain and the folio refcount
-	 * still does not match our expected safe value, try with a
-	 * system wide drain. This is needed if the pagevecs holding
-	 * the page are on a different CPU.
-	 */
-	if (*drain_lru_called) {
-		lru_add_drain_all();
-		/* We give up here, don't retry immediately. */
-		return false;
-	}
-	/*
-	 * We are here if the folio refcount does not match the
-	 * expected safe value. The main culprits are usually
-	 * pagevecs. With lru_add_drain() we drain the pagevecs
-	 * on the local CPU so that hopefully the refcount will
-	 * reach the expected safe value.
-	 */
-	lru_add_drain();
-	*drain_lru_called = true;
-	/* The caller should try again immediately */
-	return true;
-}
-
-/*
- * Requests the Ultravisor to make a page accessible to a guest.
- * If it's brought in the first time, it will be cleared. If
- * it has been exported before, it will be decrypted and integrity
- * checked.
- */
-int gmap_make_secure(struct gmap *gmap, unsigned long gaddr, void *uvcb)
-{
-	struct vm_area_struct *vma;
-	bool drain_lru_called = false;
-	spinlock_t *ptelock;
-	unsigned long uaddr;
-	struct folio *folio;
-	pte_t *ptep;
-	int rc;
-
-again:
-	rc = -EFAULT;
-	mmap_read_lock(gmap->mm);
-
-	uaddr = __gmap_translate(gmap, gaddr);
-	if (IS_ERR_VALUE(uaddr))
-		goto out;
-	vma = vma_lookup(gmap->mm, uaddr);
-	if (!vma)
-		goto out;
-	/*
-	 * Secure pages cannot be huge and userspace should not combine both.
-	 * In case userspace does it anyway this will result in an -EFAULT for
-	 * the unpack. The guest is thus never reaching secure mode. If
-	 * userspace is playing dirty tricky with mapping huge pages later
-	 * on this will result in a segmentation fault.
-	 */
-	if (is_vm_hugetlb_page(vma))
-		goto out;
-
-	rc = -ENXIO;
-	ptep = get_locked_pte(gmap->mm, uaddr, &ptelock);
-	if (!ptep)
-		goto out;
-	if (pte_present(*ptep) && !(pte_val(*ptep) & _PAGE_INVALID) && pte_write(*ptep)) {
-		folio = page_folio(pte_page(*ptep));
-		rc = -EAGAIN;
-		if (folio_test_large(folio)) {
-			rc = -E2BIG;
-		} else if (folio_trylock(folio)) {
-			if (should_export_before_import(uvcb, gmap->mm))
-				uv_convert_from_secure(PFN_PHYS(folio_pfn(folio)));
-			rc = make_folio_secure(folio, uvcb);
-			folio_unlock(folio);
-		}
-
-		/*
-		 * Once we drop the PTL, the folio may get unmapped and
-		 * freed immediately. We need a temporary reference.
-		 */
-		if (rc == -EAGAIN || rc == -E2BIG)
-			folio_get(folio);
-	}
-	pte_unmap_unlock(ptep, ptelock);
-out:
-	mmap_read_unlock(gmap->mm);
-
-	switch (rc) {
-	case -E2BIG:
-		folio_lock(folio);
-		rc = split_folio(folio);
-		folio_unlock(folio);
-		folio_put(folio);
-
-		switch (rc) {
-		case 0:
-			/* Splitting succeeded, try again immediately. */
-			goto again;
-		case -EAGAIN:
-			/* Additional folio references. */
-			if (drain_lru(&drain_lru_called))
-				goto again;
-			return -EAGAIN;
-		case -EBUSY:
-			/* Unexpected race. */
-			return -EAGAIN;
-		}
-		WARN_ON_ONCE(1);
-		return -ENXIO;
-	case -EAGAIN:
-		/*
-		 * If we are here because the UVC returned busy or partial
-		 * completion, this is just a useless check, but it is safe.
-		 */
-		folio_wait_writeback(folio);
-		folio_put(folio);
-		return -EAGAIN;
-	case -EBUSY:
-		/* Additional folio references. */
-		if (drain_lru(&drain_lru_called))
-			goto again;
-		return -EAGAIN;
-	case -ENXIO:
-		if (gmap_fault(gmap, gaddr, FAULT_FLAG_WRITE))
-			return -EFAULT;
-		return -EAGAIN;
-	}
-	return rc;
-}
-EXPORT_SYMBOL_GPL(gmap_make_secure);
-
-int gmap_convert_to_secure(struct gmap *gmap, unsigned long gaddr)
-{
-	struct uv_cb_cts uvcb = {
-		.header.cmd = UVC_CMD_CONV_TO_SEC_STOR,
-		.header.len = sizeof(uvcb),
-		.guest_handle = gmap->guest_handle,
-		.gaddr = gaddr,
-	};
-
-	return gmap_make_secure(gmap, gaddr, &uvcb);
-}
-EXPORT_SYMBOL_GPL(gmap_convert_to_secure);
-
-/**
- * gmap_destroy_page - Destroy a guest page.
- * @gmap: the gmap of the guest
- * @gaddr: the guest address to destroy
- *
- * An attempt will be made to destroy the given guest page. If the attempt
- * fails, an attempt is made to export the page. If both attempts fail, an
- * appropriate error is returned.
- */
-int gmap_destroy_page(struct gmap *gmap, unsigned long gaddr)
-{
-	struct vm_area_struct *vma;
-	struct folio_walk fw;
-	unsigned long uaddr;
-	struct folio *folio;
-	int rc;
-
-	rc = -EFAULT;
-	mmap_read_lock(gmap->mm);
-
-	uaddr = __gmap_translate(gmap, gaddr);
-	if (IS_ERR_VALUE(uaddr))
-		goto out;
-	vma = vma_lookup(gmap->mm, uaddr);
-	if (!vma)
-		goto out;
-	/*
-	 * Huge pages should not be able to become secure
-	 */
-	if (is_vm_hugetlb_page(vma))
-		goto out;
-
-	rc = 0;
-	folio = folio_walk_start(&fw, vma, uaddr, 0);
-	if (!folio)
-		goto out;
-	/*
-	 * See gmap_make_secure(): large folios cannot be secure. Small
-	 * folio implies FW_LEVEL_PTE.
-	 */
-	if (folio_test_large(folio) || !pte_write(fw.pte))
-		goto out_walk_end;
-	rc = uv_destroy_folio(folio);
-	/*
-	 * Fault handlers can race; it is possible that two CPUs will fault
-	 * on the same secure page. One CPU can destroy the page, reboot,
-	 * re-enter secure mode and import it, while the second CPU was
-	 * stuck at the beginning of the handler. At some point the second
-	 * CPU will be able to progress, and it will not be able to destroy
-	 * the page. In that case we do not want to terminate the process,
-	 * we instead try to export the page.
-	 */
-	if (rc)
-		rc = uv_convert_from_secure_folio(folio);
-out_walk_end:
-	folio_walk_end(&fw, vma);
-out:
-	mmap_read_unlock(gmap->mm);
-	return rc;
-}
-EXPORT_SYMBOL_GPL(gmap_destroy_page);
 
 /*
  * To be called with the folio locked or with an extra reference! This will

arch/s390/kvm/Makefile

@@ -8,7 +8,7 @@ include $(srctree)/virt/kvm/Makefile.kvm
 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-y += diag.o gaccess.o guestdbg.o vsie.o pv.o gmap.o gmap-vsie.o
 
 kvm-$(CONFIG_VFIO_PCI_ZDEV_KVM) += pci.o
 obj-$(CONFIG_KVM) += kvm.o

arch/s390/kvm/gaccess.c

@@ -16,6 +16,7 @@
 #include <asm/gmap.h>
 #include <asm/dat-bits.h>
 #include "kvm-s390.h"
+#include "gmap.h"
 #include "gaccess.h"
 
 /*
@@ -1392,6 +1393,44 @@ shadow_pgt:
 	return 0;
 }
 
+/**
+ * shadow_pgt_lookup() - find a shadow page table
+ * @sg: pointer to the shadow guest address space structure
+ * @saddr: the address in the shadow aguest address space
+ * @pgt: parent gmap address of the page table to get shadowed
+ * @dat_protection: if the pgtable is marked as protected by dat
+ * @fake: pgt references contiguous guest memory block, not a pgtable
+ *
+ * Returns 0 if the shadow page table was found and -EAGAIN if the page
+ * table was not found.
+ *
+ * Called with sg->mm->mmap_lock in read.
+ */
+static int shadow_pgt_lookup(struct gmap *sg, unsigned long saddr, unsigned long *pgt,
+			     int *dat_protection, int *fake)
+{
+	unsigned long pt_index;
+	unsigned long *table;
+	struct page *page;
+	int rc;
+
+	spin_lock(&sg->guest_table_lock);
+	table = gmap_table_walk(sg, saddr, 1); /* get segment pointer */
+	if (table && !(*table & _SEGMENT_ENTRY_INVALID)) {
+		/* Shadow page tables are full pages (pte+pgste) */
+		page = pfn_to_page(*table >> PAGE_SHIFT);
+		pt_index = gmap_pgste_get_pgt_addr(page_to_virt(page));
+		*pgt = pt_index & ~GMAP_SHADOW_FAKE_TABLE;
+		*dat_protection = !!(*table & _SEGMENT_ENTRY_PROTECT);
+		*fake = !!(pt_index & GMAP_SHADOW_FAKE_TABLE);
+		rc = 0;
+	} else  {
+		rc = -EAGAIN;
+	}
+	spin_unlock(&sg->guest_table_lock);
+	return rc;
+}
+
 /**
  * kvm_s390_shadow_fault - handle fault on a shadow page table
  * @vcpu: virtual cpu
@@ -1415,6 +1454,9 @@ int kvm_s390_shadow_fault(struct kvm_vcpu *vcpu, struct gmap *sg,
 	int dat_protection, fake;
 	int rc;
 
+	if (KVM_BUG_ON(!gmap_is_shadow(sg), vcpu->kvm))
+		return -EFAULT;
+
 	mmap_read_lock(sg->mm);
 	/*
 	 * We don't want any guest-2 tables to change - so the parent
@@ -1423,7 +1465,7 @@ int kvm_s390_shadow_fault(struct kvm_vcpu *vcpu, struct gmap *sg,
 	 */
 	ipte_lock(vcpu->kvm);
 
-	rc = gmap_shadow_pgt_lookup(sg, saddr, &pgt, &dat_protection, &fake);
+	rc = shadow_pgt_lookup(sg, saddr, &pgt, &dat_protection, &fake);
 	if (rc)
 		rc = kvm_s390_shadow_tables(sg, saddr, &pgt, &dat_protection,
 					    &fake);

arch/s390/kvm/gmap-vsie.c

@@ -0,0 +1,142 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Guest memory management for KVM/s390 nested VMs.
+ *
+ * Copyright IBM Corp. 2008, 2020, 2024
+ *
+ *    Author(s): Claudio Imbrenda <imbrenda@linux.ibm.com>
+ *               Martin Schwidefsky <schwidefsky@de.ibm.com>
+ *               David Hildenbrand <david@redhat.com>
+ *               Janosch Frank <frankja@linux.vnet.ibm.com>
+ */
+
+#include <linux/compiler.h>
+#include <linux/kvm.h>
+#include <linux/kvm_host.h>
+#include <linux/pgtable.h>
+#include <linux/pagemap.h>
+#include <linux/mman.h>
+
+#include <asm/lowcore.h>
+#include <asm/gmap.h>
+#include <asm/uv.h>
+
+#include "kvm-s390.h"
+#include "gmap.h"
+
+/**
+ * gmap_find_shadow - find a specific asce in the list of shadow tables
+ * @parent: pointer to the parent gmap
+ * @asce: ASCE for which the shadow table is created
+ * @edat_level: edat level to be used for the shadow translation
+ *
+ * Returns the pointer to a gmap if a shadow table with the given asce is
+ * already available, ERR_PTR(-EAGAIN) if another one is just being created,
+ * otherwise NULL
+ *
+ * Context: Called with parent->shadow_lock held
+ */
+static struct gmap *gmap_find_shadow(struct gmap *parent, unsigned long asce, int edat_level)
+{
+	struct gmap *sg;
+
+	lockdep_assert_held(&parent->shadow_lock);
+	list_for_each_entry(sg, &parent->children, list) {
+		if (!gmap_shadow_valid(sg, asce, edat_level))
+			continue;
+		if (!sg->initialized)
+			return ERR_PTR(-EAGAIN);
+		refcount_inc(&sg->ref_count);
+		return sg;
+	}
+	return NULL;
+}
+
+/**
+ * gmap_shadow - create/find a shadow guest address space
+ * @parent: pointer to the parent gmap
+ * @asce: ASCE for which the shadow table is created
+ * @edat_level: edat level to be used for the shadow translation
+ *
+ * The pages of the top level page table referred by the asce parameter
+ * will be set to read-only and marked in the PGSTEs of the kvm process.
+ * The shadow table will be removed automatically on any change to the
+ * PTE mapping for the source table.
+ *
+ * Returns a guest address space structure, ERR_PTR(-ENOMEM) if out of memory,
+ * ERR_PTR(-EAGAIN) if the caller has to retry and ERR_PTR(-EFAULT) if the
+ * parent gmap table could not be protected.
+ */
+struct gmap *gmap_shadow(struct gmap *parent, unsigned long asce, int edat_level)
+{
+	struct gmap *sg, *new;
+	unsigned long limit;
+	int rc;
+
+	if (KVM_BUG_ON(parent->mm->context.allow_gmap_hpage_1m, (struct kvm *)parent->private) ||
+	    KVM_BUG_ON(gmap_is_shadow(parent), (struct kvm *)parent->private))
+		return ERR_PTR(-EFAULT);
+	spin_lock(&parent->shadow_lock);
+	sg = gmap_find_shadow(parent, asce, edat_level);
+	spin_unlock(&parent->shadow_lock);
+	if (sg)
+		return sg;
+	/* Create a new shadow gmap */
+	limit = -1UL >> (33 - (((asce & _ASCE_TYPE_MASK) >> 2) * 11));
+	if (asce & _ASCE_REAL_SPACE)
+		limit = -1UL;
+	new = gmap_alloc(limit);
+	if (!new)
+		return ERR_PTR(-ENOMEM);
+	new->mm = parent->mm;
+	new->parent = gmap_get(parent);
+	new->private = parent->private;
+	new->orig_asce = asce;
+	new->edat_level = edat_level;
+	new->initialized = false;
+	spin_lock(&parent->shadow_lock);
+	/* Recheck if another CPU created the same shadow */
+	sg = gmap_find_shadow(parent, asce, edat_level);
+	if (sg) {
+		spin_unlock(&parent->shadow_lock);
+		gmap_free(new);
+		return sg;
+	}
+	if (asce & _ASCE_REAL_SPACE) {
+		/* only allow one real-space gmap shadow */
+		list_for_each_entry(sg, &parent->children, list) {
+			if (sg->orig_asce & _ASCE_REAL_SPACE) {
+				spin_lock(&sg->guest_table_lock);
+				gmap_unshadow(sg);
+				spin_unlock(&sg->guest_table_lock);
+				list_del(&sg->list);
+				gmap_put(sg);
+				break;
+			}
+		}
+	}
+	refcount_set(&new->ref_count, 2);
+	list_add(&new->list, &parent->children);
+	if (asce & _ASCE_REAL_SPACE) {
+		/* nothing to protect, return right away */
+		new->initialized = true;
+		spin_unlock(&parent->shadow_lock);
+		return new;
+	}
+	spin_unlock(&parent->shadow_lock);
+	/* protect after insertion, so it will get properly invalidated */
+	mmap_read_lock(parent->mm);
+	rc = __kvm_s390_mprotect_many(parent, asce & _ASCE_ORIGIN,
+				      ((asce & _ASCE_TABLE_LENGTH) + 1),
+				      PROT_READ, GMAP_NOTIFY_SHADOW);
+	mmap_read_unlock(parent->mm);
+	spin_lock(&parent->shadow_lock);
+	new->initialized = true;
+	if (rc) {
+		list_del(&new->list);
+		gmap_free(new);
+		new = ERR_PTR(rc);
+	}
+	spin_unlock(&parent->shadow_lock);
+	return new;
+}

arch/s390/kvm/gmap.c

@@ -0,0 +1,212 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Guest memory management for KVM/s390
+ *
+ * Copyright IBM Corp. 2008, 2020, 2024
+ *
+ *    Author(s): Claudio Imbrenda <imbrenda@linux.ibm.com>
+ *               Martin Schwidefsky <schwidefsky@de.ibm.com>
+ *               David Hildenbrand <david@redhat.com>
+ *               Janosch Frank <frankja@linux.vnet.ibm.com>
+ */
+
+#include <linux/compiler.h>
+#include <linux/kvm.h>
+#include <linux/kvm_host.h>
+#include <linux/pgtable.h>
+#include <linux/pagemap.h>
+
+#include <asm/lowcore.h>
+#include <asm/gmap.h>
+#include <asm/uv.h>
+
+#include "gmap.h"
+
+/**
+ * should_export_before_import - Determine whether an export is needed
+ * before an import-like operation
+ * @uvcb: the Ultravisor control block of the UVC to be performed
+ * @mm: the mm of the process
+ *
+ * Returns whether an export is needed before every import-like operation.
+ * This is needed for shared pages, which don't trigger a secure storage
+ * exception when accessed from a different guest.
+ *
+ * Although considered as one, the Unpin Page UVC is not an actual import,
+ * so it is not affected.
+ *
+ * No export is needed also when there is only one protected VM, because the
+ * page cannot belong to the wrong VM in that case (there is no "other VM"
+ * it can belong to).
+ *
+ * Return: true if an export is needed before every import, otherwise false.
+ */
+static bool should_export_before_import(struct uv_cb_header *uvcb, struct mm_struct *mm)
+{
+	/*
+	 * The misc feature indicates, among other things, that importing a
+	 * shared page from a different protected VM will automatically also
+	 * transfer its ownership.
+	 */
+	if (uv_has_feature(BIT_UV_FEAT_MISC))
+		return false;
+	if (uvcb->cmd == UVC_CMD_UNPIN_PAGE_SHARED)
+		return false;
+	return atomic_read(&mm->context.protected_count) > 1;
+}
+
+static int __gmap_make_secure(struct gmap *gmap, struct page *page, void *uvcb)
+{
+	struct folio *folio = page_folio(page);
+	int rc;
+
+	/*
+	 * Secure pages cannot be huge and userspace should not combine both.
+	 * In case userspace does it anyway this will result in an -EFAULT for
+	 * the unpack. The guest is thus never reaching secure mode.
+	 * If userspace plays dirty tricks and decides to map huge pages at a
+	 * later point in time, it will receive a segmentation fault or
+	 * KVM_RUN will return -EFAULT.
+	 */
+	if (folio_test_hugetlb(folio))
+		return -EFAULT;
+	if (folio_test_large(folio)) {
+		mmap_read_unlock(gmap->mm);
+		rc = kvm_s390_wiggle_split_folio(gmap->mm, folio, true);
+		mmap_read_lock(gmap->mm);
+		if (rc)
+			return rc;
+		folio = page_folio(page);
+	}
+
+	if (!folio_trylock(folio))
+		return -EAGAIN;
+	if (should_export_before_import(uvcb, gmap->mm))
+		uv_convert_from_secure(folio_to_phys(folio));
+	rc = make_folio_secure(folio, uvcb);
+	folio_unlock(folio);
+
+	/*
+	 * In theory a race is possible and the folio might have become
+	 * large again before the folio_trylock() above. In that case, no
+	 * action is performed and -EAGAIN is returned; the callers will
+	 * have to try again later.
+	 * In most cases this implies running the VM again, getting the same
+	 * exception again, and make another attempt in this function.
+	 * This is expected to happen extremely rarely.
+	 */
+	if (rc == -E2BIG)
+		return -EAGAIN;
+	/* The folio has too many references, try to shake some off */
+	if (rc == -EBUSY) {
+		mmap_read_unlock(gmap->mm);
+		kvm_s390_wiggle_split_folio(gmap->mm, folio, false);
+		mmap_read_lock(gmap->mm);
+		return -EAGAIN;
+	}
+
+	return rc;
+}
+
+/**
+ * gmap_make_secure() - make one guest page secure
+ * @gmap: the guest gmap
+ * @gaddr: the guest address that needs to be made secure
+ * @uvcb: the UVCB specifying which operation needs to be performed
+ *
+ * Context: needs to be called with kvm->srcu held.
+ * Return: 0 on success, < 0 in case of error (see __gmap_make_secure()).
+ */
+int gmap_make_secure(struct gmap *gmap, unsigned long gaddr, void *uvcb)
+{
+	struct kvm *kvm = gmap->private;
+	struct page *page;
+	int rc = 0;
+
+	lockdep_assert_held(&kvm->srcu);
+
+	page = gfn_to_page(kvm, gpa_to_gfn(gaddr));
+	mmap_read_lock(gmap->mm);
+	if (page)
+		rc = __gmap_make_secure(gmap, page, uvcb);
+	kvm_release_page_clean(page);
+	mmap_read_unlock(gmap->mm);
+
+	return rc;
+}
+
+int gmap_convert_to_secure(struct gmap *gmap, unsigned long gaddr)
+{
+	struct uv_cb_cts uvcb = {
+		.header.cmd = UVC_CMD_CONV_TO_SEC_STOR,
+		.header.len = sizeof(uvcb),
+		.guest_handle = gmap->guest_handle,
+		.gaddr = gaddr,
+	};
+
+	return gmap_make_secure(gmap, gaddr, &uvcb);
+}
+
+/**
+ * __gmap_destroy_page() - Destroy a guest page.
+ * @gmap: the gmap of the guest
+ * @page: the page to destroy
+ *
+ * An attempt will be made to destroy the given guest page. If the attempt
+ * fails, an attempt is made to export the page. If both attempts fail, an
+ * appropriate error is returned.
+ *
+ * Context: must be called holding the mm lock for gmap->mm
+ */
+static int __gmap_destroy_page(struct gmap *gmap, struct page *page)
+{
+	struct folio *folio = page_folio(page);
+	int rc;
+
+	/*
+	 * See gmap_make_secure(): large folios cannot be secure. Small
+	 * folio implies FW_LEVEL_PTE.
+	 */
+	if (folio_test_large(folio))
+		return -EFAULT;
+
+	rc = uv_destroy_folio(folio);
+	/*
+	 * Fault handlers can race; it is possible that two CPUs will fault
+	 * on the same secure page. One CPU can destroy the page, reboot,
+	 * re-enter secure mode and import it, while the second CPU was
+	 * stuck at the beginning of the handler. At some point the second
+	 * CPU will be able to progress, and it will not be able to destroy
+	 * the page. In that case we do not want to terminate the process,
+	 * we instead try to export the page.
+	 */
+	if (rc)
+		rc = uv_convert_from_secure_folio(folio);
+
+	return rc;
+}
+
+/**
+ * gmap_destroy_page() - Destroy a guest page.
+ * @gmap: the gmap of the guest
+ * @gaddr: the guest address to destroy
+ *
+ * An attempt will be made to destroy the given guest page. If the attempt
+ * fails, an attempt is made to export the page. If both attempts fail, an
+ * appropriate error is returned.
+ *
+ * Context: may sleep.
+ */
+int gmap_destroy_page(struct gmap *gmap, unsigned long gaddr)
+{
+	struct page *page;
+	int rc = 0;
+
+	mmap_read_lock(gmap->mm);
+	page = gfn_to_page(gmap->private, gpa_to_gfn(gaddr));
+	if (page)
+		rc = __gmap_destroy_page(gmap, page);
+	kvm_release_page_clean(page);
+	mmap_read_unlock(gmap->mm);
+	return rc;
+}

arch/s390/kvm/gmap.h

@@ -0,0 +1,39 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ *  KVM guest address space mapping code
+ *
+ *    Copyright IBM Corp. 2007, 2016, 2025
+ *    Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
+ *               Claudio Imbrenda <imbrenda@linux.ibm.com>
+ */
+
+#ifndef ARCH_KVM_S390_GMAP_H
+#define ARCH_KVM_S390_GMAP_H
+
+#define GMAP_SHADOW_FAKE_TABLE 1ULL
+
+int gmap_make_secure(struct gmap *gmap, unsigned long gaddr, void *uvcb);
+int gmap_convert_to_secure(struct gmap *gmap, unsigned long gaddr);
+int gmap_destroy_page(struct gmap *gmap, unsigned long gaddr);
+struct gmap *gmap_shadow(struct gmap *parent, unsigned long asce, int edat_level);
+
+/**
+ * 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.
+ *
+ */
+static inline 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;
+}
+
+#endif

arch/s390/kvm/intercept.c

@@ -21,6 +21,7 @@
 #include "gaccess.h"
 #include "trace.h"
 #include "trace-s390.h"
+#include "gmap.h"
 
 u8 kvm_s390_get_ilen(struct kvm_vcpu *vcpu)
 {
@@ -367,7 +368,7 @@ static int handle_mvpg_pei(struct kvm_vcpu *vcpu)
 					      reg2, &srcaddr, GACC_FETCH, 0);
 	if (rc)
 		return kvm_s390_inject_prog_cond(vcpu, rc);
-	rc = gmap_fault(vcpu->arch.gmap, srcaddr, 0);
+	rc = kvm_s390_handle_dat_fault(vcpu, srcaddr, 0);
 	if (rc != 0)
 		return rc;
 
@@ -376,7 +377,7 @@ static int handle_mvpg_pei(struct kvm_vcpu *vcpu)
 					      reg1, &dstaddr, GACC_STORE, 0);
 	if (rc)
 		return kvm_s390_inject_prog_cond(vcpu, rc);
-	rc = gmap_fault(vcpu->arch.gmap, dstaddr, FAULT_FLAG_WRITE);
+	rc = kvm_s390_handle_dat_fault(vcpu, dstaddr, FOLL_WRITE);
 	if (rc != 0)
 		return rc;
 
@@ -549,7 +550,7 @@ static int handle_pv_uvc(struct kvm_vcpu *vcpu)
 	 * If the unpin did not succeed, the guest will exit again for the UVC
 	 * and we will retry the unpin.
 	 */
-	if (rc == -EINVAL)
+	if (rc == -EINVAL || rc == -ENXIO)
 		return 0;
 	/*
 	 * If we got -EAGAIN here, we simply return it. It will eventually

arch/s390/kvm/interrupt.c

@@ -2893,7 +2893,8 @@ int kvm_set_routing_entry(struct kvm *kvm,
 			  struct kvm_kernel_irq_routing_entry *e,
 			  const struct kvm_irq_routing_entry *ue)
 {
-	u64 uaddr;
+	u64 uaddr_s, uaddr_i;
+	int idx;
 
 	switch (ue->type) {
 	/* we store the userspace addresses instead of the guest addresses */
@@ -2901,14 +2902,16 @@ int kvm_set_routing_entry(struct kvm *kvm,
 		if (kvm_is_ucontrol(kvm))
 			return -EINVAL;
 		e->set = set_adapter_int;
-		uaddr =  gmap_translate(kvm->arch.gmap, ue->u.adapter.summary_addr);
+
-		if (uaddr == -EFAULT)
+		idx = srcu_read_lock(&kvm->srcu);
+		uaddr_s = gpa_to_hva(kvm, ue->u.adapter.summary_addr);
+		uaddr_i = gpa_to_hva(kvm, ue->u.adapter.ind_addr);
+		srcu_read_unlock(&kvm->srcu, idx);
+
+		if (kvm_is_error_hva(uaddr_s) || kvm_is_error_hva(uaddr_i))
 			return -EFAULT;
-		e->adapter.summary_addr = uaddr;
+		e->adapter.summary_addr = uaddr_s;
-		uaddr =  gmap_translate(kvm->arch.gmap, ue->u.adapter.ind_addr);
+		e->adapter.ind_addr = uaddr_i;
-		if (uaddr == -EFAULT)
-			return -EFAULT;
-		e->adapter.ind_addr = uaddr;
 		e->adapter.summary_offset = ue->u.adapter.summary_offset;
 		e->adapter.ind_offset = ue->u.adapter.ind_offset;
 		e->adapter.adapter_id = ue->u.adapter.adapter_id;

arch/s390/kvm/kvm-s390.c

@@ -50,6 +50,7 @@
 #include "kvm-s390.h"
 #include "gaccess.h"
 #include "pci.h"
+#include "gmap.h"
 
 #define CREATE_TRACE_POINTS
 #include "trace.h"
@@ -3428,8 +3429,20 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	VM_EVENT(kvm, 3, "vm created with type %lu", type);
 
 	if (type & KVM_VM_S390_UCONTROL) {
+		struct kvm_userspace_memory_region2 fake_memslot = {
+			.slot = KVM_S390_UCONTROL_MEMSLOT,
+			.guest_phys_addr = 0,
+			.userspace_addr = 0,
+			.memory_size = ALIGN_DOWN(TASK_SIZE, _SEGMENT_SIZE),
+			.flags = 0,
+		};
+
 		kvm->arch.gmap = NULL;
 		kvm->arch.mem_limit = KVM_S390_NO_MEM_LIMIT;
+		/* one flat fake memslot covering the whole address-space */
+		mutex_lock(&kvm->slots_lock);
+		KVM_BUG_ON(kvm_set_internal_memslot(kvm, &fake_memslot), kvm);
+		mutex_unlock(&kvm->slots_lock);
 	} else {
 		if (sclp.hamax == U64_MAX)
 			kvm->arch.mem_limit = TASK_SIZE_MAX;
@@ -4498,6 +4511,75 @@ static bool ibs_enabled(struct kvm_vcpu *vcpu)
 	return kvm_s390_test_cpuflags(vcpu, CPUSTAT_IBS);
 }
 
+static int __kvm_s390_fixup_fault_sync(struct gmap *gmap, gpa_t gaddr, unsigned int flags)
+{
+	struct kvm *kvm = gmap->private;
+	gfn_t gfn = gpa_to_gfn(gaddr);
+	bool unlocked;
+	hva_t vmaddr;
+	gpa_t tmp;
+	int rc;
+
+	if (kvm_is_ucontrol(kvm)) {
+		tmp = __gmap_translate(gmap, gaddr);
+		gfn = gpa_to_gfn(tmp);
+	}
+
+	vmaddr = gfn_to_hva(kvm, gfn);
+	rc = fixup_user_fault(gmap->mm, vmaddr, FAULT_FLAG_WRITE, &unlocked);
+	if (!rc)
+		rc = __gmap_link(gmap, gaddr, vmaddr);
+	return rc;
+}
+
+/**
+ * __kvm_s390_mprotect_many() - Apply specified protection to guest pages
+ * @gmap: the gmap of the guest
+ * @gpa: the starting guest address
+ * @npages: how many pages to protect
+ * @prot: indicates access rights: PROT_NONE, PROT_READ or PROT_WRITE
+ * @bits: pgste notification bits to set
+ *
+ * Returns: 0 in case of success, < 0 in case of error - see gmap_protect_one()
+ *
+ * Context: kvm->srcu and gmap->mm need to be held in read mode
+ */
+int __kvm_s390_mprotect_many(struct gmap *gmap, gpa_t gpa, u8 npages, unsigned int prot,
+			     unsigned long bits)
+{
+	unsigned int fault_flag = (prot & PROT_WRITE) ? FAULT_FLAG_WRITE : 0;
+	gpa_t end = gpa + npages * PAGE_SIZE;
+	int rc;
+
+	for (; gpa < end; gpa = ALIGN(gpa + 1, rc)) {
+		rc = gmap_protect_one(gmap, gpa, prot, bits);
+		if (rc == -EAGAIN) {
+			__kvm_s390_fixup_fault_sync(gmap, gpa, fault_flag);
+			rc = gmap_protect_one(gmap, gpa, prot, bits);
+		}
+		if (rc < 0)
+			return rc;
+	}
+
+	return 0;
+}
+
+static int kvm_s390_mprotect_notify_prefix(struct kvm_vcpu *vcpu)
+{
+	gpa_t gaddr = kvm_s390_get_prefix(vcpu);
+	int idx, rc;
+
+	idx = srcu_read_lock(&vcpu->kvm->srcu);
+	mmap_read_lock(vcpu->arch.gmap->mm);
+
+	rc = __kvm_s390_mprotect_many(vcpu->arch.gmap, gaddr, 2, PROT_WRITE, GMAP_NOTIFY_MPROT);
+
+	mmap_read_unlock(vcpu->arch.gmap->mm);
+	srcu_read_unlock(&vcpu->kvm->srcu, idx);
+
+	return rc;
+}
+
 static int kvm_s390_handle_requests(struct kvm_vcpu *vcpu)
 {
 retry:
@@ -4513,9 +4595,8 @@ retry:
 	 */
 	if (kvm_check_request(KVM_REQ_REFRESH_GUEST_PREFIX, vcpu)) {
 		int rc;
-		rc = gmap_mprotect_notify(vcpu->arch.gmap,
+
-					  kvm_s390_get_prefix(vcpu),
+		rc = kvm_s390_mprotect_notify_prefix(vcpu);
-					  PAGE_SIZE * 2, PROT_WRITE);
 		if (rc) {
 			kvm_make_request(KVM_REQ_REFRESH_GUEST_PREFIX, vcpu);
 			return rc;
@@ -4766,11 +4847,111 @@ static int vcpu_post_run_addressing_exception(struct kvm_vcpu *vcpu)
 	return kvm_s390_inject_prog_irq(vcpu, &pgm_info);
 }
 
+static void kvm_s390_assert_primary_as(struct kvm_vcpu *vcpu)
+{
+	KVM_BUG(current->thread.gmap_teid.as != PSW_BITS_AS_PRIMARY, vcpu->kvm,
+		"Unexpected program interrupt 0x%x, TEID 0x%016lx",
+		current->thread.gmap_int_code, current->thread.gmap_teid.val);
+}
+
+/*
+ * __kvm_s390_handle_dat_fault() - handle a dat fault for the gmap of a vcpu
+ * @vcpu: the vCPU whose gmap is to be fixed up
+ * @gfn: the guest frame number used for memslots (including fake memslots)
+ * @gaddr: the gmap address, does not have to match @gfn for ucontrol gmaps
+ * @flags: FOLL_* flags
+ *
+ * Return: 0 on success, < 0 in case of error.
+ * Context: The mm lock must not be held before calling. May sleep.
+ */
+int __kvm_s390_handle_dat_fault(struct kvm_vcpu *vcpu, gfn_t gfn, gpa_t gaddr, unsigned int flags)
+{
+	struct kvm_memory_slot *slot;
+	unsigned int fault_flags;
+	bool writable, unlocked;
+	unsigned long vmaddr;
+	struct page *page;
+	kvm_pfn_t pfn;
+	int rc;
+
+	slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
+	if (!slot || slot->flags & KVM_MEMSLOT_INVALID)
+		return vcpu_post_run_addressing_exception(vcpu);
+
+	fault_flags = flags & FOLL_WRITE ? FAULT_FLAG_WRITE : 0;
+	if (vcpu->arch.gmap->pfault_enabled)
+		flags |= FOLL_NOWAIT;
+	vmaddr = __gfn_to_hva_memslot(slot, gfn);
+
+try_again:
+	pfn = __kvm_faultin_pfn(slot, gfn, flags, &writable, &page);
+
+	/* Access outside memory, inject addressing exception */
+	if (is_noslot_pfn(pfn))
+		return vcpu_post_run_addressing_exception(vcpu);
+	/* Signal pending: try again */
+	if (pfn == KVM_PFN_ERR_SIGPENDING)
+		return -EAGAIN;
+
+	/* Needs I/O, try to setup async pfault (only possible with FOLL_NOWAIT) */
+	if (pfn == KVM_PFN_ERR_NEEDS_IO) {
+		trace_kvm_s390_major_guest_pfault(vcpu);
+		if (kvm_arch_setup_async_pf(vcpu))
+			return 0;
+		vcpu->stat.pfault_sync++;
+		/* Could not setup async pfault, try again synchronously */
+		flags &= ~FOLL_NOWAIT;
+		goto try_again;
+	}
+	/* Any other error */
+	if (is_error_pfn(pfn))
+		return -EFAULT;
+
+	/* Success */
+	mmap_read_lock(vcpu->arch.gmap->mm);
+	/* Mark the userspace PTEs as young and/or dirty, to avoid page fault loops */
+	rc = fixup_user_fault(vcpu->arch.gmap->mm, vmaddr, fault_flags, &unlocked);
+	if (!rc)
+		rc = __gmap_link(vcpu->arch.gmap, gaddr, vmaddr);
+	scoped_guard(spinlock, &vcpu->kvm->mmu_lock) {
+		kvm_release_faultin_page(vcpu->kvm, page, false, writable);
+	}
+	mmap_read_unlock(vcpu->arch.gmap->mm);
+	return rc;
+}
+
+static int vcpu_dat_fault_handler(struct kvm_vcpu *vcpu, unsigned long gaddr, unsigned int flags)
+{
+	unsigned long gaddr_tmp;
+	gfn_t gfn;
+
+	gfn = gpa_to_gfn(gaddr);
+	if (kvm_is_ucontrol(vcpu->kvm)) {
+		/*
+		 * This translates the per-vCPU guest address into a
+		 * fake guest address, which can then be used with the
+		 * fake memslots that are identity mapping userspace.
+		 * This allows ucontrol VMs to use the normal fault
+		 * resolution path, like normal VMs.
+		 */
+		mmap_read_lock(vcpu->arch.gmap->mm);
+		gaddr_tmp = __gmap_translate(vcpu->arch.gmap, gaddr);
+		mmap_read_unlock(vcpu->arch.gmap->mm);
+		if (gaddr_tmp == -EFAULT) {
+			vcpu->run->exit_reason = KVM_EXIT_S390_UCONTROL;
+			vcpu->run->s390_ucontrol.trans_exc_code = gaddr;
+			vcpu->run->s390_ucontrol.pgm_code = PGM_SEGMENT_TRANSLATION;
+			return -EREMOTE;
+		}
+		gfn = gpa_to_gfn(gaddr_tmp);
+	}
+	return __kvm_s390_handle_dat_fault(vcpu, gfn, gaddr, flags);
+}
+
 static int vcpu_post_run_handle_fault(struct kvm_vcpu *vcpu)
 {
 	unsigned int flags = 0;
 	unsigned long gaddr;
-	int rc = 0;
 
 	gaddr = current->thread.gmap_teid.addr * PAGE_SIZE;
 	if (kvm_s390_cur_gmap_fault_is_write())
@@ -4781,9 +4962,7 @@ static int vcpu_post_run_handle_fault(struct kvm_vcpu *vcpu)
 		vcpu->stat.exit_null++;
 		break;
 	case PGM_NON_SECURE_STORAGE_ACCESS:
-		KVM_BUG(current->thread.gmap_teid.as != PSW_BITS_AS_PRIMARY, vcpu->kvm,
+		kvm_s390_assert_primary_as(vcpu);
-			"Unexpected program interrupt 0x%x, TEID 0x%016lx",
-			current->thread.gmap_int_code, current->thread.gmap_teid.val);
 		/*
 		 * This is normal operation; a page belonging to a protected
 		 * guest has not been imported yet. Try to import the page into
@@ -4794,9 +4973,7 @@ static int vcpu_post_run_handle_fault(struct kvm_vcpu *vcpu)
 		break;
 	case PGM_SECURE_STORAGE_ACCESS:
 	case PGM_SECURE_STORAGE_VIOLATION:
-		KVM_BUG(current->thread.gmap_teid.as != PSW_BITS_AS_PRIMARY, vcpu->kvm,
+		kvm_s390_assert_primary_as(vcpu);
-			"Unexpected program interrupt 0x%x, TEID 0x%016lx",
-			current->thread.gmap_int_code, current->thread.gmap_teid.val);
 		/*
 		 * This can happen after a reboot with asynchronous teardown;
 		 * the new guest (normal or protected) will run on top of the
@@ -4825,40 +5002,15 @@ static int vcpu_post_run_handle_fault(struct kvm_vcpu *vcpu)
 	case PGM_REGION_FIRST_TRANS:
 	case PGM_REGION_SECOND_TRANS:
 	case PGM_REGION_THIRD_TRANS:
-		KVM_BUG(current->thread.gmap_teid.as != PSW_BITS_AS_PRIMARY, vcpu->kvm,
+		kvm_s390_assert_primary_as(vcpu);
-			"Unexpected program interrupt 0x%x, TEID 0x%016lx",
+		return vcpu_dat_fault_handler(vcpu, gaddr, flags);
-			current->thread.gmap_int_code, current->thread.gmap_teid.val);
-		if (vcpu->arch.gmap->pfault_enabled) {
-			rc = gmap_fault(vcpu->arch.gmap, gaddr, flags | FAULT_FLAG_RETRY_NOWAIT);
-			if (rc == -EFAULT)
-				return vcpu_post_run_addressing_exception(vcpu);
-			if (rc == -EAGAIN) {
-				trace_kvm_s390_major_guest_pfault(vcpu);
-				if (kvm_arch_setup_async_pf(vcpu))
-					return 0;
-				vcpu->stat.pfault_sync++;
-			} else {
-				return rc;
-			}
-		}
-		rc = gmap_fault(vcpu->arch.gmap, gaddr, flags);
-		if (rc == -EFAULT) {
-			if (kvm_is_ucontrol(vcpu->kvm)) {
-				vcpu->run->exit_reason = KVM_EXIT_S390_UCONTROL;
-				vcpu->run->s390_ucontrol.trans_exc_code = gaddr;
-				vcpu->run->s390_ucontrol.pgm_code = 0x10;
-				return -EREMOTE;
-			}
-			return vcpu_post_run_addressing_exception(vcpu);
-		}
-		break;
 	default:
 		KVM_BUG(1, vcpu->kvm, "Unexpected program interrupt 0x%x, TEID 0x%016lx",
 			current->thread.gmap_int_code, current->thread.gmap_teid.val);
 		send_sig(SIGSEGV, current, 0);
 		break;
 	}
-	return rc;
+	return 0;
 }
 
 static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason)
@@ -5737,7 +5889,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 	}
 #endif
 	case KVM_S390_VCPU_FAULT: {
-		r = gmap_fault(vcpu->arch.gmap, arg, 0);
+		idx = srcu_read_lock(&vcpu->kvm->srcu);
+		r = vcpu_dat_fault_handler(vcpu, arg, 0);
+		srcu_read_unlock(&vcpu->kvm->srcu, idx);
 		break;
 	}
 	case KVM_ENABLE_CAP:
@@ -5853,7 +6007,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 {
 	gpa_t size;
 
-	if (kvm_is_ucontrol(kvm))
+	if (kvm_is_ucontrol(kvm) && new->id < KVM_USER_MEM_SLOTS)
 		return -EINVAL;
 
 	/* When we are protected, we should not change the memory slots */
@@ -5905,6 +6059,9 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 {
 	int rc = 0;
 
+	if (kvm_is_ucontrol(kvm))
+		return;
+
 	switch (change) {
 	case KVM_MR_DELETE:
 		rc = gmap_unmap_segment(kvm->arch.gmap, old->base_gfn * PAGE_SIZE,

arch/s390/kvm/kvm-s390.h

@@ -20,6 +20,8 @@
 #include <asm/processor.h>
 #include <asm/sclp.h>
 
+#define KVM_S390_UCONTROL_MEMSLOT (KVM_USER_MEM_SLOTS + 0)
+
 static inline void kvm_s390_fpu_store(struct kvm_run *run)
 {
 	fpu_stfpc(&run->s.regs.fpc);
@@ -279,6 +281,15 @@ static inline u32 kvm_s390_get_gisa_desc(struct kvm *kvm)
 	return gd;
 }
 
+static inline hva_t gpa_to_hva(struct kvm *kvm, gpa_t gpa)
+{
+	hva_t hva = gfn_to_hva(kvm, gpa_to_gfn(gpa));
+
+	if (!kvm_is_error_hva(hva))
+		hva |= offset_in_page(gpa);
+	return hva;
+}
+
 /* implemented in pv.c */
 int kvm_s390_pv_destroy_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc);
 int kvm_s390_pv_create_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc);
@@ -408,6 +419,14 @@ void kvm_s390_vcpu_unsetup_cmma(struct kvm_vcpu *vcpu);
 void kvm_s390_set_cpu_timer(struct kvm_vcpu *vcpu, __u64 cputm);
 __u64 kvm_s390_get_cpu_timer(struct kvm_vcpu *vcpu);
 int kvm_s390_cpus_from_pv(struct kvm *kvm, u16 *rc, u16 *rrc);
+int __kvm_s390_handle_dat_fault(struct kvm_vcpu *vcpu, gfn_t gfn, gpa_t gaddr, unsigned int flags);
+int __kvm_s390_mprotect_many(struct gmap *gmap, gpa_t gpa, u8 npages, unsigned int prot,
+			     unsigned long bits);
+
+static inline int kvm_s390_handle_dat_fault(struct kvm_vcpu *vcpu, gpa_t gaddr, unsigned int flags)
+{
+	return __kvm_s390_handle_dat_fault(vcpu, gpa_to_gfn(gaddr), gaddr, flags);
+}
 
 /* implemented in diag.c */
 int kvm_s390_handle_diag(struct kvm_vcpu *vcpu);

arch/s390/kvm/pv.c

@@ -17,6 +17,7 @@
 #include <linux/sched/mm.h>
 #include <linux/mmu_notifier.h>
 #include "kvm-s390.h"
+#include "gmap.h"
 
 bool kvm_s390_pv_is_protected(struct kvm *kvm)
 {
@@ -638,10 +639,28 @@ static int unpack_one(struct kvm *kvm, unsigned long addr, u64 tweak,
 		.tweak[1] = offset,
 	};
 	int ret = gmap_make_secure(kvm->arch.gmap, addr, &uvcb);
+	unsigned long vmaddr;
+	bool unlocked;
 
 	*rc = uvcb.header.rc;
 	*rrc = uvcb.header.rrc;
 
+	if (ret == -ENXIO) {
+		mmap_read_lock(kvm->mm);
+		vmaddr = gfn_to_hva(kvm, gpa_to_gfn(addr));
+		if (kvm_is_error_hva(vmaddr)) {
+			ret = -EFAULT;
+		} else {
+			ret = fixup_user_fault(kvm->mm, vmaddr, FAULT_FLAG_WRITE, &unlocked);
+			if (!ret)
+				ret = __gmap_link(kvm->arch.gmap, addr, vmaddr);
+		}
+		mmap_read_unlock(kvm->mm);
+		if (!ret)
+			return -EAGAIN;
+		return ret;
+	}
+
 	if (ret && ret != -EAGAIN)
 		KVM_UV_EVENT(kvm, 3, "PROTVIRT VM UNPACK: failed addr %llx with rc %x rrc %x",
 			     uvcb.gaddr, *rc, *rrc);
@@ -660,6 +679,8 @@ int kvm_s390_pv_unpack(struct kvm *kvm, unsigned long addr, unsigned long size,
 	KVM_UV_EVENT(kvm, 3, "PROTVIRT VM UNPACK: start addr %lx size %lx",
 		     addr, size);
 
+	guard(srcu)(&kvm->srcu);
+
 	while (offset < size) {
 		ret = unpack_one(kvm, addr, tweak, offset, rc, rrc);
 		if (ret == -EAGAIN) {

arch/s390/kvm/vsie.c

@@ -13,6 +13,7 @@
 #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>
@@ -22,6 +23,11 @@
 #include <asm/facility.h>
 #include "kvm-s390.h"
 #include "gaccess.h"
+#include "gmap.h"
+
+enum vsie_page_flags {
+	VSIE_PAGE_IN_USE = 0,
+};
 
 struct vsie_page {
 	struct kvm_s390_sie_block scb_s;	/* 0x0000 */
@@ -46,7 +52,18 @@ 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 */
 };
@@ -584,7 +601,6 @@ 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))
@@ -594,10 +610,9 @@ void kvm_s390_vsie_gmap_notifier(struct gmap *gmap, unsigned long start,
 	 * 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]);
+		cur = READ_ONCE(kvm->arch.vsie.pages[i]);
-		if (!page)
+		if (!cur)
 			continue;
-		cur = page_to_virt(page);
 		if (READ_ONCE(cur->gmap) != gmap)
 			continue;
 		prefix = cur->scb_s.prefix << GUEST_PREFIX_SHIFT;
@@ -1345,6 +1360,20 @@ static int vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 	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.
  *
@@ -1355,16 +1384,21 @@ 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 (vsie_page) {
-		if (page_ref_inc_return(page) == 2)
+		if (try_get_vsie_page(vsie_page)) {
-			return page_to_virt(page);
+			if (vsie_page->scb_gpa == addr)
-		page_ref_dec(page);
+				return vsie_page;
+			/*
+			 * We raced with someone reusing + putting this vsie
+			 * page before we grabbed it.
+			 */
+			put_vsie_page(vsie_page);
+		}
 	}
 
 	/*
@@ -1375,36 +1409,40 @@ 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_ACCOUNT | __GFP_ZERO | GFP_DMA);
+		vsie_page = (void *)__get_free_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO | GFP_DMA);
-		if (!page) {
+		if (!vsie_page) {
 			mutex_unlock(&kvm->arch.vsie.mutex);
 			return ERR_PTR(-ENOMEM);
 		}
-		page_ref_inc(page);
+		__set_bit(VSIE_PAGE_IN_USE, &vsie_page->flags);
-		kvm->arch.vsie.pages[kvm->arch.vsie.page_count] = page;
+		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];
+			vsie_page = kvm->arch.vsie.pages[kvm->arch.vsie.next];
-			if (page_ref_inc_return(page) == 2)
+			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;
+	/* Mark it as invalid until it resides in the tree. */
-	/* double use of the same address */
+	vsie_page->scb_gpa = ULONG_MAX;
-	if (radix_tree_insert(&kvm->arch.vsie.addr_to_page, addr >> 9, page)) {
+
-		page_ref_dec(page);
+	/* 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;
@@ -1412,14 +1450,6 @@ 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;
@@ -1470,7 +1500,7 @@ 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;
 }
@@ -1486,18 +1516,18 @@ void kvm_s390_vsie_init(struct kvm *kvm)
 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);
+		if (vsie_page->scb_gpa != ULONG_MAX)
-		__free_page(page);
+			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);

arch/s390/mm/pgalloc.c

@@ -176,8 +176,6 @@ unsigned long *page_table_alloc(struct mm_struct *mm)
 	}
 	table = ptdesc_to_virt(ptdesc);
 	__arch_set_page_dat(table, 1);
-	/* pt_list is used by gmap only */
-	INIT_LIST_HEAD(&ptdesc->pt_list);
 	memset64((u64 *)table, _PAGE_INVALID, PTRS_PER_PTE);
 	memset64((u64 *)table + PTRS_PER_PTE, 0, PTRS_PER_PTE);
 	return table;

arch/x86/kvm/cpuid.c

@@ -1180,7 +1180,7 @@ void kvm_set_cpu_caps(void)
 		SYNTHESIZED_F(SBPB),
 		SYNTHESIZED_F(IBPB_BRTYPE),
 		SYNTHESIZED_F(SRSO_NO),
-		SYNTHESIZED_F(SRSO_USER_KERNEL_NO),
+		F(SRSO_USER_KERNEL_NO),
 	);
 
 	kvm_cpu_cap_init(CPUID_8000_0022_EAX,

arch/x86/kvm/mmu/mmu.c

@@ -7120,6 +7120,19 @@ static void mmu_destroy_caches(void)
 	kmem_cache_destroy(mmu_page_header_cache);
 }
 
+static void kvm_wake_nx_recovery_thread(struct kvm *kvm)
+{
+	/*
+	 * The NX recovery thread is spawned on-demand at the first KVM_RUN and
+	 * may not be valid even though the VM is globally visible.  Do nothing,
+	 * as such a VM can't have any possible NX huge pages.
+	 */
+	struct vhost_task *nx_thread = READ_ONCE(kvm->arch.nx_huge_page_recovery_thread);
+
+	if (nx_thread)
+		vhost_task_wake(nx_thread);
+}
+
 static int get_nx_huge_pages(char *buffer, const struct kernel_param *kp)
 {
 	if (nx_hugepage_mitigation_hard_disabled)
@@ -7180,7 +7193,7 @@ static int set_nx_huge_pages(const char *val, const struct kernel_param *kp)
 			kvm_mmu_zap_all_fast(kvm);
 			mutex_unlock(&kvm->slots_lock);
 
-			vhost_task_wake(kvm->arch.nx_huge_page_recovery_thread);
+			kvm_wake_nx_recovery_thread(kvm);
 		}
 		mutex_unlock(&kvm_lock);
 	}
@@ -7315,7 +7328,7 @@ static int set_nx_huge_pages_recovery_param(const char *val, const struct kernel
 		mutex_lock(&kvm_lock);
 
 		list_for_each_entry(kvm, &vm_list, vm_list)
-			vhost_task_wake(kvm->arch.nx_huge_page_recovery_thread);
+			kvm_wake_nx_recovery_thread(kvm);
 
 		mutex_unlock(&kvm_lock);
 	}
@@ -7451,14 +7464,20 @@ static void kvm_mmu_start_lpage_recovery(struct once *once)
 {
 	struct kvm_arch *ka = container_of(once, struct kvm_arch, nx_once);
 	struct kvm *kvm = container_of(ka, struct kvm, arch);
+	struct vhost_task *nx_thread;
 
 	kvm->arch.nx_huge_page_last = get_jiffies_64();
-	kvm->arch.nx_huge_page_recovery_thread = vhost_task_create(
+	nx_thread = vhost_task_create(kvm_nx_huge_page_recovery_worker,
-		kvm_nx_huge_page_recovery_worker, kvm_nx_huge_page_recovery_worker_kill,
+				      kvm_nx_huge_page_recovery_worker_kill,
-		kvm, "kvm-nx-lpage-recovery");
+				      kvm, "kvm-nx-lpage-recovery");
 
-	if (kvm->arch.nx_huge_page_recovery_thread)
+	if (!nx_thread)
-		vhost_task_start(kvm->arch.nx_huge_page_recovery_thread);
+		return;
+
+	vhost_task_start(nx_thread);
+
+	/* Make the task visible only once it is fully started. */
+	WRITE_ONCE(kvm->arch.nx_huge_page_recovery_thread, nx_thread);
 }
 
 int kvm_mmu_post_init_vm(struct kvm *kvm)

arch/x86/kvm/x86.c

@@ -12741,6 +12741,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 			     "does not run without ignore_msrs=1, please report it to kvm@vger.kernel.org.\n");
 	}
 
+	once_init(&kvm->arch.nx_once);
 	return 0;
 
 out_uninit_mmu:
@@ -12750,12 +12751,6 @@ out:
 	return ret;
 }
 
-int kvm_arch_post_init_vm(struct kvm *kvm)
-{
-	once_init(&kvm->arch.nx_once);
-	return 0;
-}
-
 static void kvm_unload_vcpu_mmu(struct kvm_vcpu *vcpu)
 {
 	vcpu_load(vcpu);

include/linux/kvm_host.h

@@ -1615,7 +1615,6 @@ int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu);
 bool kvm_arch_dy_runnable(struct kvm_vcpu *vcpu);
 bool kvm_arch_dy_has_pending_interrupt(struct kvm_vcpu *vcpu);
 bool kvm_arch_vcpu_preempted_in_kernel(struct kvm_vcpu *vcpu);
-int kvm_arch_post_init_vm(struct kvm *kvm);
 void kvm_arch_pre_destroy_vm(struct kvm *kvm);
 void kvm_arch_create_vm_debugfs(struct kvm *kvm);
 

tools/testing/selftests/kvm/s390/cmma_test.c

@@ -444,7 +444,7 @@ static void assert_no_pages_cmma_dirty(struct kvm_vm *vm)
 			 );
 }
 
-static void test_get_inital_dirty(void)
+static void test_get_initial_dirty(void)
 {
 	struct kvm_vm *vm = create_vm_two_memslots();
 	struct kvm_vcpu *vcpu;
@@ -651,7 +651,7 @@ struct testdef {
 } testlist[] = {
 	{ "migration mode and dirty tracking", test_migration_mode },
 	{ "GET_CMMA_BITS: basic calls", test_get_cmma_basic },
-	{ "GET_CMMA_BITS: all pages are dirty initally", test_get_inital_dirty },
+	{ "GET_CMMA_BITS: all pages are dirty initially", test_get_initial_dirty },
 	{ "GET_CMMA_BITS: holes are skipped", test_get_skip_holes },
 };
 

tools/testing/selftests/kvm/s390/ucontrol_test.c

@@ -88,10 +88,6 @@ asm("test_skey_asm:\n"
 	"	ahi	%r0,1\n"
 	"	st	%r1,0(%r5,%r6)\n"
 
-	"	iske	%r1,%r6\n"
-	"	ahi	%r0,1\n"
-	"	diag	0,0,0x44\n"
-
 	"	sske	%r1,%r6\n"
 	"	xgr	%r1,%r1\n"
 	"	iske	%r1,%r6\n"
@@ -459,10 +455,14 @@ TEST_F(uc_kvm, uc_no_user_region)
 	};
 
 	ASSERT_EQ(-1, ioctl(self->vm_fd, KVM_SET_USER_MEMORY_REGION, &region));
-	ASSERT_EQ(EINVAL, errno);
+	ASSERT_TRUE(errno == EEXIST || errno == EINVAL)
+		TH_LOG("errno %s (%i) not expected for ioctl KVM_SET_USER_MEMORY_REGION",
+		       strerror(errno), errno);
 
 	ASSERT_EQ(-1, ioctl(self->vm_fd, KVM_SET_USER_MEMORY_REGION2, &region2));
-	ASSERT_EQ(EINVAL, errno);
+	ASSERT_TRUE(errno == EEXIST || errno == EINVAL)
+		TH_LOG("errno %s (%i) not expected for ioctl KVM_SET_USER_MEMORY_REGION2",
+		       strerror(errno), errno);
 }
 
 TEST_F(uc_kvm, uc_map_unmap)
@@ -596,7 +596,9 @@ TEST_F(uc_kvm, uc_skey)
 	ASSERT_EQ(true, uc_handle_exit(self));
 	ASSERT_EQ(1, sync_regs->gprs[0]);
 
-	/* ISKE */
+	/* SSKE + ISKE */
+	sync_regs->gprs[1] = skeyvalue;
+	run->kvm_dirty_regs |= KVM_SYNC_GPRS;
 	ASSERT_EQ(0, uc_run_once(self));
 
 	/*
@@ -608,21 +610,11 @@ TEST_F(uc_kvm, uc_skey)
 	TEST_ASSERT_EQ(0, sie_block->ictl & (ICTL_ISKE | ICTL_SSKE | ICTL_RRBE));
 	TEST_ASSERT_EQ(KVM_EXIT_S390_SIEIC, self->run->exit_reason);
 	TEST_ASSERT_EQ(ICPT_INST, sie_block->icptcode);
-	TEST_REQUIRE(sie_block->ipa != 0xb229);
+	TEST_REQUIRE(sie_block->ipa != 0xb22b);
 
-	/* ISKE contd. */
+	/* SSKE + ISKE contd. */
 	ASSERT_EQ(false, uc_handle_exit(self));
 	ASSERT_EQ(2, sync_regs->gprs[0]);
-	/* assert initial skey (ACC = 0, R & C = 1) */
-	ASSERT_EQ(0x06, sync_regs->gprs[1]);
-	uc_assert_diag44(self);
-
-	/* SSKE + ISKE */
-	sync_regs->gprs[1] = skeyvalue;
-	run->kvm_dirty_regs |= KVM_SYNC_GPRS;
-	ASSERT_EQ(0, uc_run_once(self));
-	ASSERT_EQ(false, uc_handle_exit(self));
-	ASSERT_EQ(3, sync_regs->gprs[0]);
 	ASSERT_EQ(skeyvalue, sync_regs->gprs[1]);
 	uc_assert_diag44(self);
 
@@ -631,7 +623,7 @@ TEST_F(uc_kvm, uc_skey)
 	run->kvm_dirty_regs |= KVM_SYNC_GPRS;
 	ASSERT_EQ(0, uc_run_once(self));
 	ASSERT_EQ(false, uc_handle_exit(self));
-	ASSERT_EQ(4, sync_regs->gprs[0]);
+	ASSERT_EQ(3, sync_regs->gprs[0]);
 	/* assert R reset but rest of skey unchanged */
 	ASSERT_EQ(skeyvalue & 0xfa, sync_regs->gprs[1]);
 	ASSERT_EQ(0, sync_regs->gprs[1] & 0x04);

virt/kvm/kvm_main.c

@@ -1070,15 +1070,6 @@ out_err:
 	return ret;
 }
 
-/*
- * Called after the VM is otherwise initialized, but just before adding it to
- * the vm_list.
- */
-int __weak kvm_arch_post_init_vm(struct kvm *kvm)
-{
-	return 0;
-}
-
 /*
  * Called just after removing the VM from the vm_list, but before doing any
  * other destruction.
@@ -1199,10 +1190,6 @@ static struct kvm *kvm_create_vm(unsigned long type, const char *fdname)
 	if (r)
 		goto out_err_no_debugfs;
 
-	r = kvm_arch_post_init_vm(kvm);
-	if (r)
-		goto out_err;
-
 	mutex_lock(&kvm_lock);
 	list_add(&kvm->vm_list, &vm_list);
 	mutex_unlock(&kvm_lock);
@@ -1212,8 +1199,6 @@ static struct kvm *kvm_create_vm(unsigned long type, const char *fdname)
 
 	return kvm;
 
-out_err:
-	kvm_destroy_vm_debugfs(kvm);
 out_err_no_debugfs:
 	kvm_coalesced_mmio_free(kvm);
 out_no_coalesced_mmio:
@@ -1971,7 +1956,15 @@ static int kvm_set_memory_region(struct kvm *kvm,
 		return -EINVAL;
 	if (mem->guest_phys_addr + mem->memory_size < mem->guest_phys_addr)
 		return -EINVAL;
-	if ((mem->memory_size >> PAGE_SHIFT) > KVM_MEM_MAX_NR_PAGES)
+
+	/*
+	 * The size of userspace-defined memory regions is restricted in order
+	 * to play nice with dirty bitmap operations, which are indexed with an
+	 * "unsigned int".  KVM's internal memory regions don't support dirty
+	 * logging, and so are exempt.
+	 */
+	if (id < KVM_USER_MEM_SLOTS &&
+	    (mem->memory_size >> PAGE_SHIFT) > KVM_MEM_MAX_NR_PAGES)
 		return -EINVAL;
 
 	slots = __kvm_memslots(kvm, as_id);