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

Pull kvm updates from Paolo Bonzini:
 "RISCV:

   - Use common KVM implementation of MMU memory caches

   - SBI v0.2 support for Guest

   - Initial KVM selftests support

   - Fix to avoid spurious virtual interrupts after clearing hideleg CSR

   - Update email address for Anup and Atish

  ARM:

   - Simplification of the 'vcpu first run' by integrating it into KVM's
     'pid change' flow

   - Refactoring of the FP and SVE state tracking, also leading to a
     simpler state and less shared data between EL1 and EL2 in the nVHE
     case

   - Tidy up the header file usage for the nvhe hyp object

   - New HYP unsharing mechanism, finally allowing pages to be unmapped
     from the Stage-1 EL2 page-tables

   - Various pKVM cleanups around refcounting and sharing

   - A couple of vgic fixes for bugs that would trigger once the vcpu
     xarray rework is merged, but not sooner

   - Add minimal support for ARMv8.7's PMU extension

   - Rework kvm_pgtable initialisation ahead of the NV work

   - New selftest for IRQ injection

   - Teach selftests about the lack of default IPA space and page sizes

   - Expand sysreg selftest to deal with Pointer Authentication

   - The usual bunch of cleanups and doc update

  s390:

   - fix sigp sense/start/stop/inconsistency

   - cleanups

  x86:

   - Clean up some function prototypes more

   - improved gfn_to_pfn_cache with proper invalidation, used by Xen
     emulation

   - add KVM_IRQ_ROUTING_XEN_EVTCHN and event channel delivery

   - completely remove potential TOC/TOU races in nested SVM consistency
     checks

   - update some PMCs on emulated instructions

   - Intel AMX support (joint work between Thomas and Intel)

   - large MMU cleanups

   - module parameter to disable PMU virtualization

   - cleanup register cache

   - first part of halt handling cleanups

   - Hyper-V enlightened MSR bitmap support for nested hypervisors

  Generic:

   - clean up Makefiles

   - introduce CONFIG_HAVE_KVM_DIRTY_RING

   - optimize memslot lookup using a tree

   - optimize vCPU array usage by converting to xarray"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (268 commits)
  x86/fpu: Fix inline prefix warnings
  selftest: kvm: Add amx selftest
  selftest: kvm: Move struct kvm_x86_state to header
  selftest: kvm: Reorder vcpu_load_state steps for AMX
  kvm: x86: Disable interception for IA32_XFD on demand
  x86/fpu: Provide fpu_sync_guest_vmexit_xfd_state()
  kvm: selftests: Add support for KVM_CAP_XSAVE2
  kvm: x86: Add support for getting/setting expanded xstate buffer
  x86/fpu: Add uabi_size to guest_fpu
  kvm: x86: Add CPUID support for Intel AMX
  kvm: x86: Add XCR0 support for Intel AMX
  kvm: x86: Disable RDMSR interception of IA32_XFD_ERR
  kvm: x86: Emulate IA32_XFD_ERR for guest
  kvm: x86: Intercept #NM for saving IA32_XFD_ERR
  x86/fpu: Prepare xfd_err in struct fpu_guest
  kvm: x86: Add emulation for IA32_XFD
  x86/fpu: Provide fpu_update_guest_xfd() for IA32_XFD emulation
  kvm: x86: Enable dynamic xfeatures at KVM_SET_CPUID2
  x86/fpu: Provide fpu_enable_guest_xfd_features() for KVM
  x86/fpu: Add guest support to xfd_enable_feature()
  ...

10 files changed, 231 insertions, 196 deletions

diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index a604d51acfc8..a22c9266ea05 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -1010,6 +1010,4 @@ static inline void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
 static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) {}
 static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) {}
 
-void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu);
-
 #endif
diff --git a/arch/s390/include/asm/uv.h b/arch/s390/include/asm/uv.h
index 72d3e49c2860..86218382d29c 100644
--- a/arch/s390/include/asm/uv.h
+++ b/arch/s390/include/asm/uv.h
@@ -91,23 +91,23 @@ struct uv_cb_header {
 
 /* Query Ultravisor Information */
 struct uv_cb_qui {
-	struct uv_cb_header header;
-	u64 reserved08;
-	u64 inst_calls_list[4];
-	u64 reserved30[2];
-	u64 uv_base_stor_len;
-	u64 reserved48;
-	u64 conf_base_phys_stor_len;
-	u64 conf_base_virt_stor_len;
-	u64 conf_virt_var_stor_len;
-	u64 cpu_stor_len;
-	u32 reserved70[3];
-	u32 max_num_sec_conf;
-	u64 max_guest_stor_addr;
-	u8  reserved88[158 - 136];
-	u16 max_guest_cpu_id;
-	u64 uv_feature_indications;
-	u8  reserveda0[200 - 168];
+	struct uv_cb_header header;		/* 0x0000 */
+	u64 reserved08;				/* 0x0008 */
+	u64 inst_calls_list[4];			/* 0x0010 */
+	u64 reserved30[2];			/* 0x0030 */
+	u64 uv_base_stor_len;			/* 0x0040 */
+	u64 reserved48;				/* 0x0048 */
+	u64 conf_base_phys_stor_len;		/* 0x0050 */
+	u64 conf_base_virt_stor_len;		/* 0x0058 */
+	u64 conf_virt_var_stor_len;		/* 0x0060 */
+	u64 cpu_stor_len;			/* 0x0068 */
+	u32 reserved70[3];			/* 0x0070 */
+	u32 max_num_sec_conf;			/* 0x007c */
+	u64 max_guest_stor_addr;		/* 0x0080 */
+	u8  reserved88[158 - 136];		/* 0x0088 */
+	u16 max_guest_cpu_id;			/* 0x009e */
+	u64 uv_feature_indications;		/* 0x00a0 */
+	u8  reserveda8[200 - 168];		/* 0x00a8 */
 } __packed __aligned(8);
 
 /* Initialize Ultravisor */
diff --git a/arch/s390/kvm/Kconfig b/arch/s390/kvm/Kconfig
index 67a8e770e369..2e84d3922f7c 100644
--- a/arch/s390/kvm/Kconfig
+++ b/arch/s390/kvm/Kconfig
@@ -33,6 +33,7 @@ config KVM
 	select HAVE_KVM_NO_POLL
 	select SRCU
 	select KVM_VFIO
+	select INTERVAL_TREE
 	help
 	  Support hosting paravirtualized guest machines using the SIE
 	  virtualization capability on the mainframe. This should work
diff --git a/arch/s390/kvm/Makefile b/arch/s390/kvm/Makefile
index b3aaadc60ead..26f4a74e5ce4 100644
--- a/arch/s390/kvm/Makefile
+++ b/arch/s390/kvm/Makefile
@@ -3,13 +3,11 @@
 #
 # Copyright IBM Corp. 2008
 
-KVM := ../../../virt/kvm
-common-objs = $(KVM)/kvm_main.o $(KVM)/eventfd.o  $(KVM)/async_pf.o \
-	      $(KVM)/irqchip.o $(KVM)/vfio.o $(KVM)/binary_stats.o
+include $(srctree)/virt/kvm/Makefile.kvm
 
 ccflags-y := -Ivirt/kvm -Iarch/s390/kvm
 
-kvm-objs := $(common-objs) kvm-s390.o intercept.o interrupt.o priv.o sigp.o
-kvm-objs += diag.o gaccess.o guestdbg.o vsie.o pv.o
+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
 
 obj-$(CONFIG_KVM) += kvm.o
diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c
index 6af59c59cc1b..4460808c3b9a 100644
--- a/arch/s390/kvm/gaccess.c
+++ b/arch/s390/kvm/gaccess.c
@@ -794,46 +794,100 @@ static int low_address_protection_enabled(struct kvm_vcpu *vcpu,
 	return 1;
 }
 
-static int guest_page_range(struct kvm_vcpu *vcpu, unsigned long ga, u8 ar,
-			    unsigned long *pages, unsigned long nr_pages,
-			    const union asce asce, enum gacc_mode mode)
+/**
+ * guest_range_to_gpas() - Calculate guest physical addresses of page fragments
+ * covering a logical range
+ * @vcpu: virtual cpu
+ * @ga: guest address, start of range
+ * @ar: access register
+ * @gpas: output argument, may be NULL
+ * @len: length of range in bytes
+ * @asce: address-space-control element to use for translation
+ * @mode: access mode
+ *
+ * Translate a logical range to a series of guest absolute addresses,
+ * such that the concatenation of page fragments starting at each gpa make up
+ * the whole range.
+ * The translation is performed as if done by the cpu for the given @asce, @ar,
+ * @mode and state of the @vcpu.
+ * If the translation causes an exception, its program interruption code is
+ * returned and the &struct kvm_s390_pgm_info pgm member of @vcpu is modified
+ * such that a subsequent call to kvm_s390_inject_prog_vcpu() will inject
+ * a correct exception into the guest.
+ * The resulting gpas are stored into @gpas, unless it is NULL.
+ *
+ * Note: All fragments except the first one start at the beginning of a page.
+ *	 When deriving the boundaries of a fragment from a gpa, all but the last
+ *	 fragment end at the end of the page.
+ *
+ * Return:
+ * * 0		- success
+ * * <0		- translation could not be performed, for example if  guest
+ *		  memory could not be accessed
+ * * >0		- an access exception occurred. In this case the returned value
+ *		  is the program interruption code and the contents of pgm may
+ *		  be used to inject an exception into the guest.
+ */
+static int guest_range_to_gpas(struct kvm_vcpu *vcpu, unsigned long ga, u8 ar,
+			       unsigned long *gpas, unsigned long len,
+			       const union asce asce, enum gacc_mode mode)
 {
 	psw_t *psw = &vcpu->arch.sie_block->gpsw;
+	unsigned int offset = offset_in_page(ga);
+	unsigned int fragment_len;
 	int lap_enabled, rc = 0;
 	enum prot_type prot;
+	unsigned long gpa;
 
 	lap_enabled = low_address_protection_enabled(vcpu, asce);
-	while (nr_pages) {
+	while (min(PAGE_SIZE - offset, len) > 0) {
+		fragment_len = min(PAGE_SIZE - offset, len);
 		ga = kvm_s390_logical_to_effective(vcpu, ga);
 		if (mode == GACC_STORE && lap_enabled && is_low_address(ga))
 			return trans_exc(vcpu, PGM_PROTECTION, ga, ar, mode,
 					 PROT_TYPE_LA);
-		ga &= PAGE_MASK;
 		if (psw_bits(*psw).dat) {
-			rc = guest_translate(vcpu, ga, pages, asce, mode, &prot);
+			rc = guest_translate(vcpu, ga, &gpa, asce, mode, &prot);
 			if (rc < 0)
 				return rc;
 		} else {
-			*pages = kvm_s390_real_to_abs(vcpu, ga);
-			if (kvm_is_error_gpa(vcpu->kvm, *pages))
+			gpa = kvm_s390_real_to_abs(vcpu, ga);
+			if (kvm_is_error_gpa(vcpu->kvm, gpa))
 				rc = PGM_ADDRESSING;
 		}
 		if (rc)
 			return trans_exc(vcpu, rc, ga, ar, mode, prot);
-		ga += PAGE_SIZE;
-		pages++;
-		nr_pages--;
+		if (gpas)
+			*gpas++ = gpa;
+		offset = 0;
+		ga += fragment_len;
+		len -= fragment_len;
 	}
 	return 0;
 }
 
+static int access_guest_page(struct kvm *kvm, enum gacc_mode mode, gpa_t gpa,
+			     void *data, unsigned int len)
+{
+	const unsigned int offset = offset_in_page(gpa);
+	const gfn_t gfn = gpa_to_gfn(gpa);
+	int rc;
+
+	if (mode == GACC_STORE)
+		rc = kvm_write_guest_page(kvm, gfn, data, offset, len);
+	else
+		rc = kvm_read_guest_page(kvm, gfn, data, offset, len);
+	return rc;
+}
+
 int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, u8 ar, void *data,
 		 unsigned long len, enum gacc_mode mode)
 {
 	psw_t *psw = &vcpu->arch.sie_block->gpsw;
-	unsigned long _len, nr_pages, gpa, idx;
-	unsigned long pages_array[2];
-	unsigned long *pages;
+	unsigned long nr_pages, idx;
+	unsigned long gpa_array[2];
+	unsigned int fragment_len;
+	unsigned long *gpas;
 	int need_ipte_lock;
 	union asce asce;
 	int rc;
@@ -845,49 +899,42 @@ int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, u8 ar, void *data,
 	if (rc)
 		return rc;
 	nr_pages = (((ga & ~PAGE_MASK) + len - 1) >> PAGE_SHIFT) + 1;
-	pages = pages_array;
-	if (nr_pages > ARRAY_SIZE(pages_array))
-		pages = vmalloc(array_size(nr_pages, sizeof(unsigned long)));
-	if (!pages)
+	gpas = gpa_array;
+	if (nr_pages > ARRAY_SIZE(gpa_array))
+		gpas = vmalloc(array_size(nr_pages, sizeof(unsigned long)));
+	if (!gpas)
 		return -ENOMEM;
 	need_ipte_lock = psw_bits(*psw).dat && !asce.r;
 	if (need_ipte_lock)
 		ipte_lock(vcpu);
-	rc = guest_page_range(vcpu, ga, ar, pages, nr_pages, asce, mode);
+	rc = guest_range_to_gpas(vcpu, ga, ar, gpas, len, asce, mode);
 	for (idx = 0; idx < nr_pages && !rc; idx++) {
-		gpa = *(pages + idx) + (ga & ~PAGE_MASK);
-		_len = min(PAGE_SIZE - (gpa & ~PAGE_MASK), len);
-		if (mode == GACC_STORE)
-			rc = kvm_write_guest(vcpu->kvm, gpa, data, _len);
-		else
-			rc = kvm_read_guest(vcpu->kvm, gpa, data, _len);
-		len -= _len;
-		ga += _len;
-		data += _len;
+		fragment_len = min(PAGE_SIZE - offset_in_page(gpas[idx]), len);
+		rc = access_guest_page(vcpu->kvm, mode, gpas[idx], data, fragment_len);
+		len -= fragment_len;
+		data += fragment_len;
 	}
 	if (need_ipte_lock)
 		ipte_unlock(vcpu);
-	if (nr_pages > ARRAY_SIZE(pages_array))
-		vfree(pages);
+	if (nr_pages > ARRAY_SIZE(gpa_array))
+		vfree(gpas);
 	return rc;
 }
 
 int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra,
 		      void *data, unsigned long len, enum gacc_mode mode)
 {
-	unsigned long _len, gpa;
+	unsigned int fragment_len;
+	unsigned long gpa;
 	int rc = 0;
 
 	while (len && !rc) {
 		gpa = kvm_s390_real_to_abs(vcpu, gra);
-		_len = min(PAGE_SIZE - (gpa & ~PAGE_MASK), len);
-		if (mode)
-			rc = write_guest_abs(vcpu, gpa, data, _len);
-		else
-			rc = read_guest_abs(vcpu, gpa, data, _len);
-		len -= _len;
-		gra += _len;
-		data += _len;
+		fragment_len = min(PAGE_SIZE - offset_in_page(gpa), len);
+		rc = access_guest_page(vcpu->kvm, mode, gpa, data, fragment_len);
+		len -= fragment_len;
+		gra += fragment_len;
+		data += fragment_len;
 	}
 	return rc;
 }
@@ -909,8 +956,6 @@ int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra,
 int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva, u8 ar,
 			    unsigned long *gpa, enum gacc_mode mode)
 {
-	psw_t *psw = &vcpu->arch.sie_block->gpsw;
-	enum prot_type prot;
 	union asce asce;
 	int rc;
 
@@ -918,23 +963,7 @@ int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva, u8 ar,
 	rc = get_vcpu_asce(vcpu, &asce, gva, ar, mode);
 	if (rc)
 		return rc;
-	if (is_low_address(gva) && low_address_protection_enabled(vcpu, asce)) {
-		if (mode == GACC_STORE)
-			return trans_exc(vcpu, PGM_PROTECTION, gva, 0,
-					 mode, PROT_TYPE_LA);
-	}
-
-	if (psw_bits(*psw).dat && !asce.r) {	/* Use DAT? */
-		rc = guest_translate(vcpu, gva, gpa, asce, mode, &prot);
-		if (rc > 0)
-			return trans_exc(vcpu, rc, gva, 0, mode, prot);
-	} else {
-		*gpa = kvm_s390_real_to_abs(vcpu, gva);
-		if (kvm_is_error_gpa(vcpu->kvm, *gpa))
-			return trans_exc(vcpu, rc, gva, PGM_ADDRESSING, mode, 0);
-	}
-
-	return rc;
+	return guest_range_to_gpas(vcpu, gva, ar, gpa, 1, asce, mode);
 }
 
 /**
@@ -948,17 +977,14 @@ int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva, u8 ar,
 int check_gva_range(struct kvm_vcpu *vcpu, unsigned long gva, u8 ar,
 		    unsigned long length, enum gacc_mode mode)
 {
-	unsigned long gpa;
-	unsigned long currlen;
+	union asce asce;
 	int rc = 0;
 
+	rc = get_vcpu_asce(vcpu, &asce, gva, ar, mode);
+	if (rc)
+		return rc;
 	ipte_lock(vcpu);
-	while (length > 0 && !rc) {
-		currlen = min(length, PAGE_SIZE - (gva % PAGE_SIZE));
-		rc = guest_translate_address(vcpu, gva, ar, &gpa, mode);
-		gva += currlen;
-		length -= currlen;
-	}
+	rc = guest_range_to_gpas(vcpu, gva, ar, NULL, length, asce, mode);
 	ipte_unlock(vcpu);
 
 	return rc;
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index c3bd993fdd0c..db933c252dbc 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -1335,7 +1335,8 @@ int kvm_s390_handle_wait(struct kvm_vcpu *vcpu)
 	VCPU_EVENT(vcpu, 4, "enabled wait: %llu ns", sltime);
 no_timer:
 	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
-	kvm_vcpu_block(vcpu);
+	kvm_vcpu_halt(vcpu);
+	vcpu->valid_wakeup = false;
 	__unset_cpu_idle(vcpu);
 	vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
 
@@ -2115,6 +2116,13 @@ int kvm_s390_is_stop_irq_pending(struct kvm_vcpu *vcpu)
 	return test_bit(IRQ_PEND_SIGP_STOP, &li->pending_irqs);
 }
 
+int kvm_s390_is_restart_irq_pending(struct kvm_vcpu *vcpu)
+{
+	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
+
+	return test_bit(IRQ_PEND_RESTART, &li->pending_irqs);
+}
+
 void kvm_s390_clear_stop_irq(struct kvm_vcpu *vcpu)
 {
 	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
@@ -2659,7 +2667,7 @@ static int flic_ais_mode_set_all(struct kvm *kvm, struct kvm_device_attr *attr)
 static int flic_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
 {
 	int r = 0;
-	unsigned int i;
+	unsigned long i;
 	struct kvm_vcpu *vcpu;
 
 	switch (attr->group) {
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 14a18ba5ff2c..9c6d45d0d345 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -295,7 +295,7 @@ static int kvm_clock_sync(struct notifier_block *notifier, unsigned long val,
 {
 	struct kvm *kvm;
 	struct kvm_vcpu *vcpu;
-	int i;
+	unsigned long i;
 	unsigned long long *delta = v;
 
 	list_for_each_entry(kvm, &vm_list, vm_list) {
@@ -682,7 +682,7 @@ out:
 
 static void icpt_operexc_on_all_vcpus(struct kvm *kvm)
 {
-	unsigned int i;
+	unsigned long i;
 	struct kvm_vcpu *vcpu;
 
 	kvm_for_each_vcpu(i, vcpu, kvm) {
@@ -936,7 +936,7 @@ static void kvm_s390_vcpu_crypto_setup(struct kvm_vcpu *vcpu);
 void kvm_s390_vcpu_crypto_reset_all(struct kvm *kvm)
 {
 	struct kvm_vcpu *vcpu;
-	int i;
+	unsigned long i;
 
 	kvm_s390_vcpu_block_all(kvm);
 
@@ -1021,7 +1021,7 @@ static int kvm_s390_vm_set_crypto(struct kvm *kvm, struct kvm_device_attr *attr)
 
 static void kvm_s390_sync_request_broadcast(struct kvm *kvm, int req)
 {
-	int cx;
+	unsigned long cx;
 	struct kvm_vcpu *vcpu;
 
 	kvm_for_each_vcpu(cx, vcpu, kvm)
@@ -1037,13 +1037,13 @@ static int kvm_s390_vm_start_migration(struct kvm *kvm)
 	struct kvm_memory_slot *ms;
 	struct kvm_memslots *slots;
 	unsigned long ram_pages = 0;
-	int slotnr;
+	int bkt;
 
 	/* migration mode already enabled */
 	if (kvm->arch.migration_mode)
 		return 0;
 	slots = kvm_memslots(kvm);
-	if (!slots || !slots->used_slots)
+	if (!slots || kvm_memslots_empty(slots))
 		return -EINVAL;
 
 	if (!kvm->arch.use_cmma) {
@@ -1051,8 +1051,7 @@ static int kvm_s390_vm_start_migration(struct kvm *kvm)
 		return 0;
 	}
 	/* mark all the pages in active slots as dirty */
-	for (slotnr = 0; slotnr < slots->used_slots; slotnr++) {
-		ms = slots->memslots + slotnr;
+	kvm_for_each_memslot(ms, bkt, slots) {
 		if (!ms->dirty_bitmap)
 			return -EINVAL;
 		/*
@@ -1943,41 +1942,6 @@ out:
 /* for consistency */
 #define KVM_S390_CMMA_SIZE_MAX ((u32)KVM_S390_SKEYS_MAX)
 
-/*
- * Similar to gfn_to_memslot, but returns the index of a memslot also when the
- * address falls in a hole. In that case the index of one of the memslots
- * bordering the hole is returned.
- */
-static int gfn_to_memslot_approx(struct kvm_memslots *slots, gfn_t gfn)
-{
-	int start = 0, end = slots->used_slots;
-	int slot = atomic_read(&slots->last_used_slot);
-	struct kvm_memory_slot *memslots = slots->memslots;
-
-	if (gfn >= memslots[slot].base_gfn &&
-	    gfn < memslots[slot].base_gfn + memslots[slot].npages)
-		return slot;
-
-	while (start < end) {
-		slot = start + (end - start) / 2;
-
-		if (gfn >= memslots[slot].base_gfn)
-			end = slot;
-		else
-			start = slot + 1;
-	}
-
-	if (start >= slots->used_slots)
-		return slots->used_slots - 1;
-
-	if (gfn >= memslots[start].base_gfn &&
-	    gfn < memslots[start].base_gfn + memslots[start].npages) {
-		atomic_set(&slots->last_used_slot, start);
-	}
-
-	return start;
-}
-
 static int kvm_s390_peek_cmma(struct kvm *kvm, struct kvm_s390_cmma_log *args,
 			      u8 *res, unsigned long bufsize)
 {
@@ -2001,26 +1965,31 @@ static int kvm_s390_peek_cmma(struct kvm *kvm, struct kvm_s390_cmma_log *args,
 	return 0;
 }
 
+static struct kvm_memory_slot *gfn_to_memslot_approx(struct kvm_memslots *slots,
+						     gfn_t gfn)
+{
+	return ____gfn_to_memslot(slots, gfn, true);
+}
+
 static unsigned long kvm_s390_next_dirty_cmma(struct kvm_memslots *slots,
 					      unsigned long cur_gfn)
 {
-	int slotidx = gfn_to_memslot_approx(slots, cur_gfn);
-	struct kvm_memory_slot *ms = slots->memslots + slotidx;
+	struct kvm_memory_slot *ms = gfn_to_memslot_approx(slots, cur_gfn);
 	unsigned long ofs = cur_gfn - ms->base_gfn;
+	struct rb_node *mnode = &ms->gfn_node[slots->node_idx];
 
 	if (ms->base_gfn + ms->npages <= cur_gfn) {
-		slotidx--;
+		mnode = rb_next(mnode);
 		/* If we are above the highest slot, wrap around */
-		if (slotidx < 0)
-			slotidx = slots->used_slots - 1;
+		if (!mnode)
+			mnode = rb_first(&slots->gfn_tree);
 
-		ms = slots->memslots + slotidx;
+		ms = container_of(mnode, struct kvm_memory_slot, gfn_node[slots->node_idx]);
 		ofs = 0;
 	}
 	ofs = find_next_bit(kvm_second_dirty_bitmap(ms), ms->npages, ofs);
-	while ((slotidx > 0) && (ofs >= ms->npages)) {
-		slotidx--;
-		ms = slots->memslots + slotidx;
+	while (ofs >= ms->npages && (mnode = rb_next(mnode))) {
+		ms = container_of(mnode, struct kvm_memory_slot, gfn_node[slots->node_idx]);
 		ofs = find_next_bit(kvm_second_dirty_bitmap(ms), ms->npages, 0);
 	}
 	return ms->base_gfn + ofs;
@@ -2033,7 +2002,7 @@ static int kvm_s390_get_cmma(struct kvm *kvm, struct kvm_s390_cmma_log *args,
 	struct kvm_memslots *slots = kvm_memslots(kvm);
 	struct kvm_memory_slot *ms;
 
-	if (unlikely(!slots->used_slots))
+	if (unlikely(kvm_memslots_empty(slots)))
 		return 0;
 
 	cur_gfn = kvm_s390_next_dirty_cmma(slots, args->start_gfn);
@@ -2043,7 +2012,7 @@ static int kvm_s390_get_cmma(struct kvm *kvm, struct kvm_s390_cmma_log *args,
 	if (!ms)
 		return 0;
 	next_gfn = kvm_s390_next_dirty_cmma(slots, cur_gfn + 1);
-	mem_end = slots->memslots[0].base_gfn + slots->memslots[0].npages;
+	mem_end = kvm_s390_get_gfn_end(slots);
 
 	while (args->count < bufsize) {
 		hva = gfn_to_hva(kvm, cur_gfn);
@@ -2206,7 +2175,7 @@ static int kvm_s390_cpus_from_pv(struct kvm *kvm, u16 *rcp, u16 *rrcp)
 	struct kvm_vcpu *vcpu;
 	u16 rc, rrc;
 	int ret = 0;
-	int i;
+	unsigned long i;
 
 	/*
 	 * We ignore failures and try to destroy as many CPUs as possible.
@@ -2230,7 +2199,8 @@ static int kvm_s390_cpus_from_pv(struct kvm *kvm, u16 *rcp, u16 *rrcp)
 
 static int kvm_s390_cpus_to_pv(struct kvm *kvm, u16 *rc, u16 *rrc)
 {
-	int i, r = 0;
+	unsigned long i;
+	int r = 0;
 	u16 dummy;
 
 	struct kvm_vcpu *vcpu;
@@ -2821,27 +2791,11 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 	free_page((unsigned long)(vcpu->arch.sie_block));
 }
 
-static void kvm_free_vcpus(struct kvm *kvm)
-{
-	unsigned int i;
-	struct kvm_vcpu *vcpu;
-
-	kvm_for_each_vcpu(i, vcpu, kvm)
-		kvm_vcpu_destroy(vcpu);
-
-	mutex_lock(&kvm->lock);
-	for (i = 0; i < atomic_read(&kvm->online_vcpus); i++)
-		kvm->vcpus[i] = NULL;
-
-	atomic_set(&kvm->online_vcpus, 0);
-	mutex_unlock(&kvm->lock);
-}
-
 void kvm_arch_destroy_vm(struct kvm *kvm)
 {
 	u16 rc, rrc;
 
-	kvm_free_vcpus(kvm);
+	kvm_destroy_vcpus(kvm);
 	sca_dispose(kvm);
 	kvm_s390_gisa_destroy(kvm);
 	/*
@@ -2945,7 +2899,7 @@ static int sca_switch_to_extended(struct kvm *kvm)
 	struct bsca_block *old_sca = kvm->arch.sca;
 	struct esca_block *new_sca;
 	struct kvm_vcpu *vcpu;
-	unsigned int vcpu_idx;
+	unsigned long vcpu_idx;
 	u32 scaol, scaoh;
 
 	if (kvm->arch.use_esca)
@@ -3427,7 +3381,7 @@ static void kvm_gmap_notifier(struct gmap *gmap, unsigned long start,
 	struct kvm *kvm = gmap->private;
 	struct kvm_vcpu *vcpu;
 	unsigned long prefix;
-	int i;
+	unsigned long i;
 
 	if (gmap_is_shadow(gmap))
 		return;
@@ -3449,7 +3403,7 @@ bool kvm_arch_no_poll(struct kvm_vcpu *vcpu)
 {
 	/* do not poll with more than halt_poll_max_steal percent of steal time */
 	if (S390_lowcore.avg_steal_timer * 100 / (TICK_USEC << 12) >=
-	    halt_poll_max_steal) {
+	    READ_ONCE(halt_poll_max_steal)) {
 		vcpu->stat.halt_no_poll_steal++;
 		return true;
 	}
@@ -3920,7 +3874,7 @@ void kvm_s390_set_tod_clock(struct kvm *kvm,
 {
 	struct kvm_vcpu *vcpu;
 	union tod_clock clk;
-	int i;
+	unsigned long i;
 
 	mutex_lock(&kvm->lock);
 	preempt_disable();
@@ -4552,7 +4506,7 @@ static void __disable_ibs_on_vcpu(struct kvm_vcpu *vcpu)
 
 static void __disable_ibs_on_all_vcpus(struct kvm *kvm)
 {
-	unsigned int i;
+	unsigned long i;
 	struct kvm_vcpu *vcpu;
 
 	kvm_for_each_vcpu(i, vcpu, kvm) {
@@ -4590,7 +4544,7 @@ int kvm_s390_vcpu_start(struct kvm_vcpu *vcpu)
 	}
 
 	for (i = 0; i < online_vcpus; i++) {
-		if (!is_vcpu_stopped(vcpu->kvm->vcpus[i]))
+		if (!is_vcpu_stopped(kvm_get_vcpu(vcpu->kvm, i)))
 			started_vcpus++;
 	}
 
@@ -4645,16 +4599,23 @@ int kvm_s390_vcpu_stop(struct kvm_vcpu *vcpu)
 		}
 	}
 
-	/* SIGP STOP and SIGP STOP AND STORE STATUS has been fully processed */
+	/*
+	 * Set the VCPU to STOPPED and THEN clear the interrupt flag,
+	 * now that the SIGP STOP and SIGP STOP AND STORE STATUS orders
+	 * have been fully processed. This will ensure that the VCPU
+	 * is kept BUSY if another VCPU is inquiring with SIGP SENSE.
+	 */
+	kvm_s390_set_cpuflags(vcpu, CPUSTAT_STOPPED);
 	kvm_s390_clear_stop_irq(vcpu);
 
-	kvm_s390_set_cpuflags(vcpu, CPUSTAT_STOPPED);
 	__disable_ibs_on_vcpu(vcpu);
 
 	for (i = 0; i < online_vcpus; i++) {
-		if (!is_vcpu_stopped(vcpu->kvm->vcpus[i])) {
+		struct kvm_vcpu *tmp = kvm_get_vcpu(vcpu->kvm, i);
+
+		if (!is_vcpu_stopped(tmp)) {
 			started_vcpus++;
-			started_vcpu = vcpu->kvm->vcpus[i];
+			started_vcpu = tmp;
 		}
 	}
 
@@ -5020,32 +4981,38 @@ vm_fault_t kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf)
 
 /* Section: memory related */
 int kvm_arch_prepare_memory_region(struct kvm *kvm,
-				   struct kvm_memory_slot *memslot,
-				   const struct kvm_userspace_memory_region *mem,
+				   const struct kvm_memory_slot *old,
+				   struct kvm_memory_slot *new,
 				   enum kvm_mr_change change)
 {
+	gpa_t size;
+
+	/* When we are protected, we should not change the memory slots */
+	if (kvm_s390_pv_get_handle(kvm))
+		return -EINVAL;
+
+	if (change == KVM_MR_DELETE || change == KVM_MR_FLAGS_ONLY)
+		return 0;
+
 	/* A few sanity checks. We can have memory slots which have to be
 	   located/ended at a segment boundary (1MB). The memory in userland is
 	   ok to be fragmented into various different vmas. It is okay to mmap()
 	   and munmap() stuff in this slot after doing this call at any time */
 
-	if (mem->userspace_addr & 0xffffful)
+	if (new->userspace_addr & 0xffffful)
 		return -EINVAL;
 
-	if (mem->memory_size & 0xffffful)
+	size = new->npages * PAGE_SIZE;
+	if (size & 0xffffful)
 		return -EINVAL;
 
-	if (mem->guest_phys_addr + mem->memory_size > kvm->arch.mem_limit)
+	if ((new->base_gfn * PAGE_SIZE) + size > kvm->arch.mem_limit)
 		return -EINVAL;
 
-	/* When we are protected, we should not change the memory slots */
-	if (kvm_s390_pv_get_handle(kvm))
-		return -EINVAL;
 	return 0;
 }
 
 void kvm_arch_commit_memory_region(struct kvm *kvm,
-				const struct kvm_userspace_memory_region *mem,
 				struct kvm_memory_slot *old,
 				const struct kvm_memory_slot *new,
 				enum kvm_mr_change change)
@@ -5064,8 +5031,9 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 			break;
 		fallthrough;
 	case KVM_MR_CREATE:
-		rc = gmap_map_segment(kvm->arch.gmap, mem->userspace_addr,
-				      mem->guest_phys_addr, mem->memory_size);
+		rc = gmap_map_segment(kvm->arch.gmap, new->userspace_addr,
+				      new->base_gfn * PAGE_SIZE,
+				      new->npages * PAGE_SIZE);
 		break;
 	case KVM_MR_FLAGS_ONLY:
 		break;
@@ -5084,11 +5052,6 @@ static inline unsigned long nonhyp_mask(int i)
 	return 0x0000ffffffffffffUL >> (nonhyp_fai << 4);
 }
 
-void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu)
-{
-	vcpu->valid_wakeup = false;
-}
-
 static int __init kvm_s390_init(void)
 {
 	int i;
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index c07a050d757d..098831e815e6 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -217,6 +217,20 @@ static inline void kvm_s390_set_user_cpu_state_ctrl(struct kvm *kvm)
 	kvm->arch.user_cpu_state_ctrl = 1;
 }
 
+/* get the end gfn of the last (highest gfn) memslot */
+static inline unsigned long kvm_s390_get_gfn_end(struct kvm_memslots *slots)
+{
+	struct rb_node *node;
+	struct kvm_memory_slot *ms;
+
+	if (WARN_ON(kvm_memslots_empty(slots)))
+		return 0;
+
+	node = rb_last(&slots->gfn_tree);
+	ms = container_of(node, struct kvm_memory_slot, gfn_node[slots->node_idx]);
+	return ms->base_gfn + ms->npages;
+}
+
 /* 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);
@@ -357,7 +371,7 @@ int kvm_s390_handle_diag(struct kvm_vcpu *vcpu);
 
 static inline void kvm_s390_vcpu_block_all(struct kvm *kvm)
 {
-	int i;
+	unsigned long i;
 	struct kvm_vcpu *vcpu;
 
 	WARN_ON(!mutex_is_locked(&kvm->lock));
@@ -367,7 +381,7 @@ static inline void kvm_s390_vcpu_block_all(struct kvm *kvm)
 
 static inline void kvm_s390_vcpu_unblock_all(struct kvm *kvm)
 {
-	int i;
+	unsigned long i;
 	struct kvm_vcpu *vcpu;
 
 	kvm_for_each_vcpu(i, vcpu, kvm)
@@ -427,6 +441,7 @@ void kvm_s390_destroy_adapters(struct kvm *kvm);
 int kvm_s390_ext_call_pending(struct kvm_vcpu *vcpu);
 extern struct kvm_device_ops kvm_flic_ops;
 int kvm_s390_is_stop_irq_pending(struct kvm_vcpu *vcpu);
+int kvm_s390_is_restart_irq_pending(struct kvm_vcpu *vcpu);
 void kvm_s390_clear_stop_irq(struct kvm_vcpu *vcpu);
 int kvm_s390_set_irq_state(struct kvm_vcpu *vcpu,
 			   void __user *buf, int len);
diff --git a/arch/s390/kvm/pv.c b/arch/s390/kvm/pv.c
index 00d272d134c2..7f7c0d6af2ce 100644
--- a/arch/s390/kvm/pv.c
+++ b/arch/s390/kvm/pv.c
@@ -116,7 +116,6 @@ static int kvm_s390_pv_alloc_vm(struct kvm *kvm)
 	unsigned long base = uv_info.guest_base_stor_len;
 	unsigned long virt = uv_info.guest_virt_var_stor_len;
 	unsigned long npages = 0, vlen = 0;
-	struct kvm_memory_slot *memslot;
 
 	kvm->arch.pv.stor_var = NULL;
 	kvm->arch.pv.stor_base = __get_free_pages(GFP_KERNEL_ACCOUNT, get_order(base));
@@ -130,8 +129,7 @@ static int kvm_s390_pv_alloc_vm(struct kvm *kvm)
 	 * Slots are sorted by GFN
 	 */
 	mutex_lock(&kvm->slots_lock);
-	memslot = kvm_memslots(kvm)->memslots;
-	npages = memslot->base_gfn + memslot->npages;
+	npages = kvm_s390_get_gfn_end(kvm_memslots(kvm));
 	mutex_unlock(&kvm->slots_lock);
 
 	kvm->arch.pv.guest_len = npages * PAGE_SIZE;
diff --git a/arch/s390/kvm/sigp.c b/arch/s390/kvm/sigp.c
index cf4de80bd541..8aaee2892ec3 100644
--- a/arch/s390/kvm/sigp.c
+++ b/arch/s390/kvm/sigp.c
@@ -276,6 +276,34 @@ static int handle_sigp_dst(struct kvm_vcpu *vcpu, u8 order_code,
 	if (!dst_vcpu)
 		return SIGP_CC_NOT_OPERATIONAL;
 
+	/*
+	 * SIGP RESTART, SIGP STOP, and SIGP STOP AND STORE STATUS orders
+	 * are processed asynchronously. Until the affected VCPU finishes
+	 * its work and calls back into KVM to clear the (RESTART or STOP)
+	 * interrupt, we need to return any new non-reset orders "busy".
+	 *
+	 * This is important because a single VCPU could issue:
+	 *  1) SIGP STOP $DESTINATION
+	 *  2) SIGP SENSE $DESTINATION
+	 *
+	 * If the SIGP SENSE would not be rejected as "busy", it could
+	 * return an incorrect answer as to whether the VCPU is STOPPED
+	 * or OPERATING.
+	 */
+	if (order_code != SIGP_INITIAL_CPU_RESET &&
+	    order_code != SIGP_CPU_RESET) {
+		/*
+		 * Lockless check. Both SIGP STOP and SIGP (RE)START
+		 * properly synchronize everything while processing
+		 * their orders, while the guest cannot observe a
+		 * difference when issuing other orders from two
+		 * different VCPUs.
+		 */
+		if (kvm_s390_is_stop_irq_pending(dst_vcpu) ||
+		    kvm_s390_is_restart_irq_pending(dst_vcpu))
+			return SIGP_CC_BUSY;
+	}
+
 	switch (order_code) {
 	case SIGP_SENSE:
 		vcpu->stat.instruction_sigp_sense++;