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

Pull first set of KVM updates from Paolo Bonzini:
 "PPC:
   - minor code cleanups

  x86:
   - PCID emulation and CR3 caching for shadow page tables
   - nested VMX live migration
   - nested VMCS shadowing
   - optimized IPI hypercall
   - some optimizations

  ARM will come next week"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (85 commits)
  kvm: x86: Set highest physical address bits in non-present/reserved SPTEs
  KVM/x86: Use CC_SET()/CC_OUT in arch/x86/kvm/vmx.c
  KVM: X86: Implement PV IPIs in linux guest
  KVM: X86: Add kvm hypervisor init time platform setup callback
  KVM: X86: Implement "send IPI" hypercall
  KVM/x86: Move X86_CR4_OSXSAVE check into kvm_valid_sregs()
  KVM: x86: Skip pae_root shadow allocation if tdp enabled
  KVM/MMU: Combine flushing remote tlb in mmu_set_spte()
  KVM: vmx: skip VMWRITE of HOST_{FS,GS}_BASE when possible
  KVM: vmx: skip VMWRITE of HOST_{FS,GS}_SEL when possible
  KVM: vmx: always initialize HOST_{FS,GS}_BASE to zero during setup
  KVM: vmx: move struct host_state usage to struct loaded_vmcs
  KVM: vmx: compute need to reload FS/GS/LDT on demand
  KVM: nVMX: remove a misleading comment regarding vmcs02 fields
  KVM: vmx: rename __vmx_load_host_state() and vmx_save_host_state()
  KVM: vmx: add dedicated utility to access guest's kernel_gs_base
  KVM: vmx: track host_state.loaded using a loaded_vmcs pointer
  KVM: vmx: refactor segmentation code in vmx_save_host_state()
  kvm: nVMX: Fix fault priority for VMX operations
  kvm: nVMX: Fix fault vector for VMX operation at CPL > 0
  ...

34 files changed, 2185 insertions, 549 deletions

diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index 1f345a0b6ba2..83a9aa3cf689 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -390,4 +390,51 @@ extern int kvmppc_h_logical_ci_store(struct kvm_vcpu *vcpu);
 #define SPLIT_HACK_MASK			0xff000000
 #define SPLIT_HACK_OFFS			0xfb000000
 
+/*
+ * This packs a VCPU ID from the [0..KVM_MAX_VCPU_ID) space down to the
+ * [0..KVM_MAX_VCPUS) space, using knowledge of the guest's core stride
+ * (but not its actual threading mode, which is not available) to avoid
+ * collisions.
+ *
+ * The implementation leaves VCPU IDs from the range [0..KVM_MAX_VCPUS) (block
+ * 0) unchanged: if the guest is filling each VCORE completely then it will be
+ * using consecutive IDs and it will fill the space without any packing.
+ *
+ * For higher VCPU IDs, the packed ID is based on the VCPU ID modulo
+ * KVM_MAX_VCPUS (effectively masking off the top bits) and then an offset is
+ * added to avoid collisions.
+ *
+ * VCPU IDs in the range [KVM_MAX_VCPUS..(KVM_MAX_VCPUS*2)) (block 1) are only
+ * possible if the guest is leaving at least 1/2 of each VCORE empty, so IDs
+ * can be safely packed into the second half of each VCORE by adding an offset
+ * of (stride / 2).
+ *
+ * Similarly, if VCPU IDs in the range [(KVM_MAX_VCPUS*2)..(KVM_MAX_VCPUS*4))
+ * (blocks 2 and 3) are seen, the guest must be leaving at least 3/4 of each
+ * VCORE empty so packed IDs can be offset by (stride / 4) and (stride * 3 / 4).
+ *
+ * Finally, VCPU IDs from blocks 5..7 will only be seen if the guest is using a
+ * stride of 8 and 1 thread per core so the remaining offsets of 1, 5, 3 and 7
+ * must be free to use.
+ *
+ * (The offsets for each block are stored in block_offsets[], indexed by the
+ * block number if the stride is 8. For cases where the guest's stride is less
+ * than 8, we can re-use the block_offsets array by multiplying the block
+ * number by (MAX_SMT_THREADS / stride) to reach the correct entry.)
+ */
+static inline u32 kvmppc_pack_vcpu_id(struct kvm *kvm, u32 id)
+{
+	const int block_offsets[MAX_SMT_THREADS] = {0, 4, 2, 6, 1, 5, 3, 7};
+	int stride = kvm->arch.emul_smt_mode;
+	int block = (id / KVM_MAX_VCPUS) * (MAX_SMT_THREADS / stride);
+	u32 packed_id;
+
+	if (WARN_ONCE(block >= MAX_SMT_THREADS, "VCPU ID too large to pack"))
+		return 0;
+	packed_id = (id % KVM_MAX_VCPUS) + block_offsets[block];
+	if (WARN_ONCE(packed_id >= KVM_MAX_VCPUS, "VCPU ID packing failed"))
+		return 0;
+	return packed_id;
+}
+
 #endif /* __ASM_KVM_BOOK3S_H__ */
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index fa4efa7e88f7..906bcbdfd2a1 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -42,7 +42,14 @@
 #define KVM_USER_MEM_SLOTS	512
 
 #include <asm/cputhreads.h>
-#define KVM_MAX_VCPU_ID                (threads_per_subcore * KVM_MAX_VCORES)
+
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+#include <asm/kvm_book3s_asm.h>		/* for MAX_SMT_THREADS */
+#define KVM_MAX_VCPU_ID		(MAX_SMT_THREADS * KVM_MAX_VCORES)
+
+#else
+#define KVM_MAX_VCPU_ID		KVM_MAX_VCPUS
+#endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */
 
 #define __KVM_HAVE_ARCH_INTC_INITIALIZED
 
@@ -672,7 +679,7 @@ struct kvm_vcpu_arch {
 	gva_t vaddr_accessed;
 	pgd_t *pgdir;
 
-	u8 io_gpr; /* GPR used as IO source/target */
+	u16 io_gpr; /* GPR used as IO source/target */
 	u8 mmio_host_swabbed;
 	u8 mmio_sign_extend;
 	/* conversion between single and double precision */
@@ -688,7 +695,6 @@ struct kvm_vcpu_arch {
 	 */
 	u8 mmio_vsx_copy_nums;
 	u8 mmio_vsx_offset;
-	u8 mmio_vsx_tx_sx_enabled;
 	u8 mmio_vmx_copy_nums;
 	u8 mmio_vmx_offset;
 	u8 mmio_copy_type;
@@ -801,14 +807,14 @@ struct kvm_vcpu_arch {
 #define KVMPPC_VCPU_BUSY_IN_HOST	2
 
 /* Values for vcpu->arch.io_gpr */
-#define KVM_MMIO_REG_MASK	0x001f
-#define KVM_MMIO_REG_EXT_MASK	0xffe0
+#define KVM_MMIO_REG_MASK	0x003f
+#define KVM_MMIO_REG_EXT_MASK	0xffc0
 #define KVM_MMIO_REG_GPR	0x0000
-#define KVM_MMIO_REG_FPR	0x0020
-#define KVM_MMIO_REG_QPR	0x0040
-#define KVM_MMIO_REG_FQPR	0x0060
-#define KVM_MMIO_REG_VSX	0x0080
-#define KVM_MMIO_REG_VMX	0x00c0
+#define KVM_MMIO_REG_FPR	0x0040
+#define KVM_MMIO_REG_QPR	0x0080
+#define KVM_MMIO_REG_FQPR	0x00c0
+#define KVM_MMIO_REG_VSX	0x0100
+#define KVM_MMIO_REG_VMX	0x0180
 
 #define __KVM_HAVE_ARCH_WQP
 #define __KVM_HAVE_CREATE_DEVICE
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index 486b7c83b8c5..e5b314ed054e 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -163,7 +163,7 @@
 #define PSSCR_ESL		0x00200000 /* Enable State Loss */
 #define PSSCR_SD		0x00400000 /* Status Disable */
 #define PSSCR_PLS	0xf000000000000000 /* Power-saving Level Status */
-#define PSSCR_GUEST_VIS	0xf0000000000003ff /* Guest-visible PSSCR fields */
+#define PSSCR_GUEST_VIS	0xf0000000000003ffUL /* Guest-visible PSSCR fields */
 #define PSSCR_FAKE_SUSPEND	0x00000400 /* Fake-suspend bit (P9 DD2.2) */
 #define PSSCR_FAKE_SUSPEND_LG	10	   /* Fake-suspend bit position */
 
diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c
index e8afdd4f4814..9a3f2646ecc7 100644
--- a/arch/powerpc/kvm/book3s_64_vio.c
+++ b/arch/powerpc/kvm/book3s_64_vio.c
@@ -179,7 +179,7 @@ extern long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd,
 		if ((tbltmp->it_page_shift <= stt->page_shift) &&
 				(tbltmp->it_offset << tbltmp->it_page_shift ==
 				 stt->offset << stt->page_shift) &&
-				(tbltmp->it_size << tbltmp->it_page_shift ==
+				(tbltmp->it_size << tbltmp->it_page_shift >=
 				 stt->size << stt->page_shift)) {
 			/*
 			 * Reference the table to avoid races with
@@ -295,7 +295,7 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
 {
 	struct kvmppc_spapr_tce_table *stt = NULL;
 	struct kvmppc_spapr_tce_table *siter;
-	unsigned long npages, size;
+	unsigned long npages, size = args->size;
 	int ret = -ENOMEM;
 	int i;
 
@@ -303,7 +303,6 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
 		(args->offset + args->size > (ULLONG_MAX >> args->page_shift)))
 		return -EINVAL;
 
-	size = _ALIGN_UP(args->size, PAGE_SIZE >> 3);
 	npages = kvmppc_tce_pages(size);
 	ret = kvmppc_account_memlimit(kvmppc_stt_pages(npages), true);
 	if (ret)
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 96f1cc6c97b7..574fc1dcb2bf 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -127,14 +127,14 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu);
  * and SPURR count and should be set according to the number of
  * online threads in the vcore being run.
  */
-#define RWMR_RPA_P8_1THREAD	0x164520C62609AECA
-#define RWMR_RPA_P8_2THREAD	0x7FFF2908450D8DA9
-#define RWMR_RPA_P8_3THREAD	0x164520C62609AECA
-#define RWMR_RPA_P8_4THREAD	0x199A421245058DA9
-#define RWMR_RPA_P8_5THREAD	0x164520C62609AECA
-#define RWMR_RPA_P8_6THREAD	0x164520C62609AECA
-#define RWMR_RPA_P8_7THREAD	0x164520C62609AECA
-#define RWMR_RPA_P8_8THREAD	0x164520C62609AECA
+#define RWMR_RPA_P8_1THREAD	0x164520C62609AECAUL
+#define RWMR_RPA_P8_2THREAD	0x7FFF2908450D8DA9UL
+#define RWMR_RPA_P8_3THREAD	0x164520C62609AECAUL
+#define RWMR_RPA_P8_4THREAD	0x199A421245058DA9UL
+#define RWMR_RPA_P8_5THREAD	0x164520C62609AECAUL
+#define RWMR_RPA_P8_6THREAD	0x164520C62609AECAUL
+#define RWMR_RPA_P8_7THREAD	0x164520C62609AECAUL
+#define RWMR_RPA_P8_8THREAD	0x164520C62609AECAUL
 
 static unsigned long p8_rwmr_values[MAX_SMT_THREADS + 1] = {
 	RWMR_RPA_P8_1THREAD,
@@ -1807,7 +1807,7 @@ static int threads_per_vcore(struct kvm *kvm)
 	return threads_per_subcore;
 }
 
-static struct kvmppc_vcore *kvmppc_vcore_create(struct kvm *kvm, int core)
+static struct kvmppc_vcore *kvmppc_vcore_create(struct kvm *kvm, int id)
 {
 	struct kvmppc_vcore *vcore;
 
@@ -1821,7 +1821,7 @@ static struct kvmppc_vcore *kvmppc_vcore_create(struct kvm *kvm, int core)
 	init_swait_queue_head(&vcore->wq);
 	vcore->preempt_tb = TB_NIL;
 	vcore->lpcr = kvm->arch.lpcr;
-	vcore->first_vcpuid = core * kvm->arch.smt_mode;
+	vcore->first_vcpuid = id;
 	vcore->kvm = kvm;
 	INIT_LIST_HEAD(&vcore->preempt_list);
 
@@ -2037,12 +2037,26 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm,
 	mutex_lock(&kvm->lock);
 	vcore = NULL;
 	err = -EINVAL;
-	core = id / kvm->arch.smt_mode;
+	if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+		if (id >= (KVM_MAX_VCPUS * kvm->arch.emul_smt_mode)) {
+			pr_devel("KVM: VCPU ID too high\n");
+			core = KVM_MAX_VCORES;
+		} else {
+			BUG_ON(kvm->arch.smt_mode != 1);
+			core = kvmppc_pack_vcpu_id(kvm, id);
+		}
+	} else {
+		core = id / kvm->arch.smt_mode;
+	}
 	if (core < KVM_MAX_VCORES) {
 		vcore = kvm->arch.vcores[core];
-		if (!vcore) {
+		if (vcore && cpu_has_feature(CPU_FTR_ARCH_300)) {
+			pr_devel("KVM: collision on id %u", id);
+			vcore = NULL;
+		} else if (!vcore) {
 			err = -ENOMEM;
-			vcore = kvmppc_vcore_create(kvm, core);
+			vcore = kvmppc_vcore_create(kvm,
+					id & ~(kvm->arch.smt_mode - 1));
 			kvm->arch.vcores[core] = vcore;
 			kvm->arch.online_vcores++;
 		}
@@ -4550,6 +4564,8 @@ static int kvmppc_book3s_init_hv(void)
 			pr_err("KVM-HV: Cannot determine method for accessing XICS\n");
 			return -ENODEV;
 		}
+		/* presence of intc confirmed - node can be dropped again */
+		of_node_put(np);
 	}
 #endif
 
diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c
index f9818d7d3381..126f02b3ffb8 100644
--- a/arch/powerpc/kvm/book3s_xive.c
+++ b/arch/powerpc/kvm/book3s_xive.c
@@ -317,6 +317,11 @@ static int xive_select_target(struct kvm *kvm, u32 *server, u8 prio)
 	return -EBUSY;
 }
 
+static u32 xive_vp(struct kvmppc_xive *xive, u32 server)
+{
+	return xive->vp_base + kvmppc_pack_vcpu_id(xive->kvm, server);
+}
+
 static u8 xive_lock_and_mask(struct kvmppc_xive *xive,
 			     struct kvmppc_xive_src_block *sb,
 			     struct kvmppc_xive_irq_state *state)
@@ -362,7 +367,7 @@ static u8 xive_lock_and_mask(struct kvmppc_xive *xive,
 	 */
 	if (xd->flags & OPAL_XIVE_IRQ_MASK_VIA_FW) {
 		xive_native_configure_irq(hw_num,
-					  xive->vp_base + state->act_server,
+					  xive_vp(xive, state->act_server),
 					  MASKED, state->number);
 		/* set old_p so we can track if an H_EOI was done */
 		state->old_p = true;
@@ -418,7 +423,7 @@ static void xive_finish_unmask(struct kvmppc_xive *xive,
 	 */
 	if (xd->flags & OPAL_XIVE_IRQ_MASK_VIA_FW) {
 		xive_native_configure_irq(hw_num,
-					  xive->vp_base + state->act_server,
+					  xive_vp(xive, state->act_server),
 					  state->act_priority, state->number);
 		/* If an EOI is needed, do it here */
 		if (!state->old_p)
@@ -495,7 +500,7 @@ static int xive_target_interrupt(struct kvm *kvm,
 	kvmppc_xive_select_irq(state, &hw_num, NULL);
 
 	return xive_native_configure_irq(hw_num,
-					 xive->vp_base + server,
+					 xive_vp(xive, server),
 					 prio, state->number);
 }
 
@@ -883,7 +888,7 @@ int kvmppc_xive_set_mapped(struct kvm *kvm, unsigned long guest_irq,
 	 * which is fine for a never started interrupt.
 	 */
 	xive_native_configure_irq(hw_irq,
-				  xive->vp_base + state->act_server,
+				  xive_vp(xive, state->act_server),
 				  state->act_priority, state->number);
 
 	/*
@@ -959,7 +964,7 @@ int kvmppc_xive_clr_mapped(struct kvm *kvm, unsigned long guest_irq,
 
 	/* Reconfigure the IPI */
 	xive_native_configure_irq(state->ipi_number,
-				  xive->vp_base + state->act_server,
+				  xive_vp(xive, state->act_server),
 				  state->act_priority, state->number);
 
 	/*
@@ -1084,7 +1089,7 @@ int kvmppc_xive_connect_vcpu(struct kvm_device *dev,
 		pr_devel("Duplicate !\n");
 		return -EEXIST;
 	}
-	if (cpu >= KVM_MAX_VCPUS) {
+	if (cpu >= (KVM_MAX_VCPUS * vcpu->kvm->arch.emul_smt_mode)) {
 		pr_devel("Out of bounds !\n");
 		return -EINVAL;
 	}
@@ -1098,7 +1103,7 @@ int kvmppc_xive_connect_vcpu(struct kvm_device *dev,
 	xc->xive = xive;
 	xc->vcpu = vcpu;
 	xc->server_num = cpu;
-	xc->vp_id = xive->vp_base + cpu;
+	xc->vp_id = xive_vp(xive, cpu);
 	xc->mfrr = 0xff;
 	xc->valid = true;
 
diff --git a/arch/powerpc/kvm/emulate_loadstore.c b/arch/powerpc/kvm/emulate_loadstore.c
index afde788be141..75dce1ef3bc8 100644
--- a/arch/powerpc/kvm/emulate_loadstore.c
+++ b/arch/powerpc/kvm/emulate_loadstore.c
@@ -106,7 +106,6 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu)
 	 * if mmio_vsx_tx_sx_enabled == 1, copy data between
 	 * VSR[32..63] and memory
 	 */
-	vcpu->arch.mmio_vsx_tx_sx_enabled = get_tx_or_sx(inst);
 	vcpu->arch.mmio_vsx_copy_nums = 0;
 	vcpu->arch.mmio_vsx_offset = 0;
 	vcpu->arch.mmio_copy_type = KVMPPC_VSX_COPY_NONE;
@@ -242,8 +241,8 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu)
 			}
 
 			emulated = kvmppc_handle_vsx_load(run, vcpu,
-					KVM_MMIO_REG_VSX | (op.reg & 0x1f),
-					io_size_each, 1, op.type & SIGNEXT);
+					KVM_MMIO_REG_VSX|op.reg, io_size_each,
+					1, op.type & SIGNEXT);
 			break;
 		}
 #endif
@@ -363,7 +362,7 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu)
 			}
 
 			emulated = kvmppc_handle_vsx_store(run, vcpu,
-					op.reg & 0x1f, io_size_each, 1);
+					op.reg, io_size_each, 1);
 			break;
 		}
 #endif
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 3ccc386b380d..eba5756d5b41 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -879,10 +879,10 @@ static inline void kvmppc_set_vsr_dword(struct kvm_vcpu *vcpu,
 	if (offset == -1)
 		return;
 
-	if (vcpu->arch.mmio_vsx_tx_sx_enabled) {
-		val.vval = VCPU_VSX_VR(vcpu, index);
+	if (index >= 32) {
+		val.vval = VCPU_VSX_VR(vcpu, index - 32);
 		val.vsxval[offset] = gpr;
-		VCPU_VSX_VR(vcpu, index) = val.vval;
+		VCPU_VSX_VR(vcpu, index - 32) = val.vval;
 	} else {
 		VCPU_VSX_FPR(vcpu, index, offset) = gpr;
 	}
@@ -894,11 +894,11 @@ static inline void kvmppc_set_vsr_dword_dump(struct kvm_vcpu *vcpu,
 	union kvmppc_one_reg val;
 	int index = vcpu->arch.io_gpr & KVM_MMIO_REG_MASK;
 
-	if (vcpu->arch.mmio_vsx_tx_sx_enabled) {
-		val.vval = VCPU_VSX_VR(vcpu, index);
+	if (index >= 32) {
+		val.vval = VCPU_VSX_VR(vcpu, index - 32);
 		val.vsxval[0] = gpr;
 		val.vsxval[1] = gpr;
-		VCPU_VSX_VR(vcpu, index) = val.vval;
+		VCPU_VSX_VR(vcpu, index - 32) = val.vval;
 	} else {
 		VCPU_VSX_FPR(vcpu, index, 0) = gpr;
 		VCPU_VSX_FPR(vcpu, index, 1) = gpr;
@@ -911,12 +911,12 @@ static inline void kvmppc_set_vsr_word_dump(struct kvm_vcpu *vcpu,
 	union kvmppc_one_reg val;
 	int index = vcpu->arch.io_gpr & KVM_MMIO_REG_MASK;
 
-	if (vcpu->arch.mmio_vsx_tx_sx_enabled) {
+	if (index >= 32) {
 		val.vsx32val[0] = gpr;
 		val.vsx32val[1] = gpr;
 		val.vsx32val[2] = gpr;
 		val.vsx32val[3] = gpr;
-		VCPU_VSX_VR(vcpu, index) = val.vval;
+		VCPU_VSX_VR(vcpu, index - 32) = val.vval;
 	} else {
 		val.vsx32val[0] = gpr;
 		val.vsx32val[1] = gpr;
@@ -936,10 +936,10 @@ static inline void kvmppc_set_vsr_word(struct kvm_vcpu *vcpu,
 	if (offset == -1)
 		return;
 
-	if (vcpu->arch.mmio_vsx_tx_sx_enabled) {
-		val.vval = VCPU_VSX_VR(vcpu, index);
+	if (index >= 32) {
+		val.vval = VCPU_VSX_VR(vcpu, index - 32);
 		val.vsx32val[offset] = gpr32;
-		VCPU_VSX_VR(vcpu, index) = val.vval;
+		VCPU_VSX_VR(vcpu, index - 32) = val.vval;
 	} else {
 		dword_offset = offset / 2;
 		word_offset = offset % 2;
@@ -1360,10 +1360,10 @@ static inline int kvmppc_get_vsr_data(struct kvm_vcpu *vcpu, int rs, u64 *val)
 			break;
 		}
 
-		if (!vcpu->arch.mmio_vsx_tx_sx_enabled) {
+		if (rs < 32) {
 			*val = VCPU_VSX_FPR(vcpu, rs, vsx_offset);
 		} else {
-			reg.vval = VCPU_VSX_VR(vcpu, rs);
+			reg.vval = VCPU_VSX_VR(vcpu, rs - 32);
 			*val = reg.vsxval[vsx_offset];
 		}
 		break;
@@ -1377,13 +1377,13 @@ static inline int kvmppc_get_vsr_data(struct kvm_vcpu *vcpu, int rs, u64 *val)
 			break;
 		}
 
-		if (!vcpu->arch.mmio_vsx_tx_sx_enabled) {
+		if (rs < 32) {
 			dword_offset = vsx_offset / 2;
 			word_offset = vsx_offset % 2;
 			reg.vsxval[0] = VCPU_VSX_FPR(vcpu, rs, dword_offset);
 			*val = reg.vsx32val[word_offset];
 		} else {
-			reg.vval = VCPU_VSX_VR(vcpu, rs);
+			reg.vval = VCPU_VSX_VR(vcpu, rs - 32);
 			*val = reg.vsx32val[vsx_offset];
 		}
 		break;
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index a2188e309bd6..29c940bf8506 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -269,6 +269,7 @@ struct kvm_s390_sie_block {
 	__u8	reserved1c0[8];		/* 0x01c0 */
 #define ECD_HOSTREGMGMT	0x20000000
 #define ECD_MEF		0x08000000
+#define ECD_ETOKENF	0x02000000
 	__u32	ecd;			/* 0x01c8 */
 	__u8	reserved1cc[18];	/* 0x01cc */
 	__u64	pp;			/* 0x01de */
@@ -655,6 +656,7 @@ struct kvm_vcpu_arch {
 	seqcount_t cputm_seqcount;
 	__u64 cputm_start;
 	bool gs_enabled;
+	bool skey_enabled;
 };
 
 struct kvm_vm_stat {
@@ -793,12 +795,6 @@ struct kvm_s390_vsie {
 	struct page *pages[KVM_MAX_VCPUS];
 };
 
-struct kvm_s390_migration_state {
-	unsigned long bitmap_size;	/* in bits (number of guest pages) */
-	atomic64_t dirty_pages;		/* number of dirty pages */
-	unsigned long *pgste_bitmap;
-};
-
 struct kvm_arch{
 	void *sca;
 	int use_esca;
@@ -828,7 +824,8 @@ struct kvm_arch{
 	struct kvm_s390_vsie vsie;
 	u8 epdx;
 	u64 epoch;
-	struct kvm_s390_migration_state *migration_state;
+	int migration_mode;
+	atomic64_t cmma_dirty_pages;
 	/* subset of available cpu features enabled by user space */
 	DECLARE_BITMAP(cpu_feat, KVM_S390_VM_CPU_FEAT_NR_BITS);
 	struct kvm_s390_gisa *gisa;
diff --git a/arch/s390/include/uapi/asm/kvm.h b/arch/s390/include/uapi/asm/kvm.h
index 4cdaa55fabfe..9a50f02b9894 100644
--- a/arch/s390/include/uapi/asm/kvm.h
+++ b/arch/s390/include/uapi/asm/kvm.h
@@ -4,7 +4,7 @@
 /*
  * KVM s390 specific structures and definitions
  *
- * Copyright IBM Corp. 2008
+ * Copyright IBM Corp. 2008, 2018
  *
  *    Author(s): Carsten Otte <cotte@de.ibm.com>
  *               Christian Borntraeger <borntraeger@de.ibm.com>
@@ -225,6 +225,7 @@ struct kvm_guest_debug_arch {
 #define KVM_SYNC_FPRS   (1UL << 8)
 #define KVM_SYNC_GSCB   (1UL << 9)
 #define KVM_SYNC_BPBC   (1UL << 10)
+#define KVM_SYNC_ETOKEN (1UL << 11)
 /* length and alignment of the sdnx as a power of two */
 #define SDNXC 8
 #define SDNXL (1UL << SDNXC)
@@ -258,6 +259,8 @@ struct kvm_sync_regs {
 		struct {
 			__u64 reserved1[2];
 			__u64 gscb[4];
+			__u64 etoken;
+			__u64 etoken_extension;
 		};
 	};
 };
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index f9d90337e64a..91ad4a9425c0 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -906,54 +906,37 @@ static void kvm_s390_sync_request_broadcast(struct kvm *kvm, int req)
  */
 static int kvm_s390_vm_start_migration(struct kvm *kvm)
 {
-	struct kvm_s390_migration_state *mgs;
 	struct kvm_memory_slot *ms;
-	/* should be the only one */
 	struct kvm_memslots *slots;
-	unsigned long ram_pages;
+	unsigned long ram_pages = 0;
 	int slotnr;
 
 	/* migration mode already enabled */
-	if (kvm->arch.migration_state)
+	if (kvm->arch.migration_mode)
 		return 0;
-
 	slots = kvm_memslots(kvm);
 	if (!slots || !slots->used_slots)
 		return -EINVAL;
 
-	mgs = kzalloc(sizeof(*mgs), GFP_KERNEL);
-	if (!mgs)
-		return -ENOMEM;
-	kvm->arch.migration_state = mgs;
-
-	if (kvm->arch.use_cmma) {
+	if (!kvm->arch.use_cmma) {
+		kvm->arch.migration_mode = 1;
+		return 0;
+	}
+	/* mark all the pages in active slots as dirty */
+	for (slotnr = 0; slotnr < slots->used_slots; slotnr++) {
+		ms = slots->memslots + slotnr;
 		/*
-		 * Get the first slot. They are reverse sorted by base_gfn, so
-		 * the first slot is also the one at the end of the address
-		 * space. We have verified above that at least one slot is
-		 * present.
+		 * The second half of the bitmap is only used on x86,
+		 * and would be wasted otherwise, so we put it to good
+		 * use here to keep track of the state of the storage
+		 * attributes.
 		 */
-		ms = slots->memslots;
-		/* round up so we only use full longs */
-		ram_pages = roundup(ms->base_gfn + ms->npages, BITS_PER_LONG);
-		/* allocate enough bytes to store all the bits */
-		mgs->pgste_bitmap = vmalloc(ram_pages / 8);
-		if (!mgs->pgste_bitmap) {
-			kfree(mgs);
-			kvm->arch.migration_state = NULL;
-			return -ENOMEM;
-		}
-
-		mgs->bitmap_size = ram_pages;
-		atomic64_set(&mgs->dirty_pages, ram_pages);
-		/* mark all the pages in active slots as dirty */
-		for (slotnr = 0; slotnr < slots->used_slots; slotnr++) {
-			ms = slots->memslots + slotnr;
-			bitmap_set(mgs->pgste_bitmap, ms->base_gfn, ms->npages);
-		}
-
-		kvm_s390_sync_request_broadcast(kvm, KVM_REQ_START_MIGRATION);
+		memset(kvm_second_dirty_bitmap(ms), 0xff, kvm_dirty_bitmap_bytes(ms));
+		ram_pages += ms->npages;
 	}
+	atomic64_set(&kvm->arch.cmma_dirty_pages, ram_pages);
+	kvm->arch.migration_mode = 1;
+	kvm_s390_sync_request_broadcast(kvm, KVM_REQ_START_MIGRATION);
 	return 0;
 }
 
@@ -963,21 +946,12 @@ static int kvm_s390_vm_start_migration(struct kvm *kvm)
  */
 static int kvm_s390_vm_stop_migration(struct kvm *kvm)
 {
-	struct kvm_s390_migration_state *mgs;
-
 	/* migration mode already disabled */
-	if (!kvm->arch.migration_state)
+	if (!kvm->arch.migration_mode)
 		return 0;
-	mgs = kvm->arch.migration_state;
-	kvm->arch.migration_state = NULL;
-
-	if (kvm->arch.use_cmma) {
+	kvm->arch.migration_mode = 0;
+	if (kvm->arch.use_cmma)
 		kvm_s390_sync_request_broadcast(kvm, KVM_REQ_STOP_MIGRATION);
-		/* We have to wait for the essa emulation to finish */
-		synchronize_srcu(&kvm->srcu);
-		vfree(mgs->pgste_bitmap);
-	}
-	kfree(mgs);
 	return 0;
 }
 
@@ -1005,7 +979,7 @@ static int kvm_s390_vm_set_migration(struct kvm *kvm,
 static int kvm_s390_vm_get_migration(struct kvm *kvm,
 				     struct kvm_device_attr *attr)
 {
-	u64 mig = (kvm->arch.migration_state != NULL);
+	u64 mig = kvm->arch.migration_mode;
 
 	if (attr->attr != KVM_S390_VM_MIGRATION_STATUS)
 		return -ENXIO;
@@ -1653,6 +1627,134 @@ out:
 #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->lru_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 (gfn >= memslots[start].base_gfn &&
+	    gfn < memslots[start].base_gfn + memslots[start].npages) {
+		atomic_set(&slots->lru_slot, start);
+	}
+
+	return start;
+}
+
+static int kvm_s390_peek_cmma(struct kvm *kvm, struct kvm_s390_cmma_log *args,
+			      u8 *res, unsigned long bufsize)
+{
+	unsigned long pgstev, hva, cur_gfn = args->start_gfn;
+
+	args->count = 0;
+	while (args->count < bufsize) {
+		hva = gfn_to_hva(kvm, cur_gfn);
+		/*
+		 * We return an error if the first value was invalid, but we
+		 * return successfully if at least one value was copied.
+		 */
+		if (kvm_is_error_hva(hva))
+			return args->count ? 0 : -EFAULT;
+		if (get_pgste(kvm->mm, hva, &pgstev) < 0)
+			pgstev = 0;
+		res[args->count++] = (pgstev >> 24) & 0x43;
+		cur_gfn++;
+	}
+
+	return 0;
+}
+
+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;
+	unsigned long ofs = cur_gfn - ms->base_gfn;
+
+	if (ms->base_gfn + ms->npages <= cur_gfn) {
+		slotidx--;
+		/* If we are above the highest slot, wrap around */
+		if (slotidx < 0)
+			slotidx = slots->used_slots - 1;
+
+		ms = slots->memslots + slotidx;
+		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;
+		ofs = find_next_bit(kvm_second_dirty_bitmap(ms), ms->npages, 0);
+	}
+	return ms->base_gfn + ofs;
+}
+
+static int kvm_s390_get_cmma(struct kvm *kvm, struct kvm_s390_cmma_log *args,
+			     u8 *res, unsigned long bufsize)
+{
+	unsigned long mem_end, cur_gfn, next_gfn, hva, pgstev;
+	struct kvm_memslots *slots = kvm_memslots(kvm);
+	struct kvm_memory_slot *ms;
+
+	cur_gfn = kvm_s390_next_dirty_cmma(slots, args->start_gfn);
+	ms = gfn_to_memslot(kvm, cur_gfn);
+	args->count = 0;
+	args->start_gfn = cur_gfn;
+	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;
+
+	while (args->count < bufsize) {
+		hva = gfn_to_hva(kvm, cur_gfn);
+		if (kvm_is_error_hva(hva))
+			return 0;
+		/* Decrement only if we actually flipped the bit to 0 */
+		if (test_and_clear_bit(cur_gfn - ms->base_gfn, kvm_second_dirty_bitmap(ms)))
+			atomic64_dec(&kvm->arch.cmma_dirty_pages);
+		if (get_pgste(kvm->mm, hva, &pgstev) < 0)
+			pgstev = 0;
+		/* Save the value */
+		res[args->c