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

Pull KVM updates from Paolo Bonzini:
 "x86:

   - Support for userspace to emulate Xen hypercalls

   - Raise the maximum number of user memslots

   - Scalability improvements for the new MMU.

     Instead of the complex "fast page fault" logic that is used in
     mmu.c, tdp_mmu.c uses an rwlock so that page faults are concurrent,
     but the code that can run against page faults is limited. Right now
     only page faults take the lock for reading; in the future this will
     be extended to some cases of page table destruction. I hope to
     switch the default MMU around 5.12-rc3 (some testing was delayed
     due to Chinese New Year).

   - Cleanups for MAXPHYADDR checks

   - Use static calls for vendor-specific callbacks

   - On AMD, use VMLOAD/VMSAVE to save and restore host state

   - Stop using deprecated jump label APIs

   - Workaround for AMD erratum that made nested virtualization
     unreliable

   - Support for LBR emulation in the guest

   - Support for communicating bus lock vmexits to userspace

   - Add support for SEV attestation command

   - Miscellaneous cleanups

  PPC:

   - Support for second data watchpoint on POWER10

   - Remove some complex workarounds for buggy early versions of POWER9

   - Guest entry/exit fixes

  ARM64:

   - Make the nVHE EL2 object relocatable

   - Cleanups for concurrent translation faults hitting the same page

   - Support for the standard TRNG hypervisor call

   - A bunch of small PMU/Debug fixes

   - Simplification of the early init hypercall handling

  Non-KVM changes (with acks):

   - Detection of contended rwlocks (implemented only for qrwlocks,
     because KVM only needs it for x86)

   - Allow __DISABLE_EXPORTS from assembly code

   - Provide a saner follow_pfn replacements for modules"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (192 commits)
  KVM: x86/xen: Explicitly pad struct compat_vcpu_info to 64 bytes
  KVM: selftests: Don't bother mapping GVA for Xen shinfo test
  KVM: selftests: Fix hex vs. decimal snafu in Xen test
  KVM: selftests: Fix size of memslots created by Xen tests
  KVM: selftests: Ignore recently added Xen tests' build output
  KVM: selftests: Add missing header file needed by xAPIC IPI tests
  KVM: selftests: Add operand to vmsave/vmload/vmrun in svm.c
  KVM: SVM: Make symbol 'svm_gp_erratum_intercept' static
  locking/arch: Move qrwlock.h include after qspinlock.h
  KVM: PPC: Book3S HV: Fix host radix SLB optimisation with hash guests
  KVM: PPC: Book3S HV: Ensure radix guest has no SLB entries
  KVM: PPC: Don't always report hash MMU capability for P9 < DD2.2
  KVM: PPC: Book3S HV: Save and restore FSCR in the P9 path
  KVM: PPC: remove unneeded semicolon
  KVM: PPC: Book3S HV: Use POWER9 SLBIA IH=6 variant to clear SLB
  KVM: PPC: Book3S HV: No need to clear radix host SLB before loading HPT guest
  KVM: PPC: Book3S HV: Fix radix guest SLB side channel
  KVM: PPC: Book3S HV: Remove support for running HPT guest on RPT host without mixed mode support
  KVM: PPC: Book3S HV: Introduce new capability for 2nd DAWR
  KVM: PPC: Book3S HV: Add infrastructure to support 2nd DAWR
  ...

12 files changed, 293 insertions, 282 deletions

diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h
index c98f5141e3fc..ed6086d57b22 100644
--- a/arch/powerpc/include/asm/hvcall.h
+++ b/arch/powerpc/include/asm/hvcall.h
@@ -535,9 +535,12 @@ struct h_cpu_char_result {
 	u64 behaviour;
 };
 
-/* Register state for entering a nested guest with H_ENTER_NESTED */
+/*
+ * Register state for entering a nested guest with H_ENTER_NESTED.
+ * New member must be added at the end.
+ */
 struct hv_guest_state {
-	u64 version;		/* version of this structure layout */
+	u64 version;		/* version of this structure layout, must be first */
 	u32 lpid;
 	u32 vcpu_token;
 	/* These registers are hypervisor privileged (at least for writing) */
@@ -566,10 +569,26 @@ struct hv_guest_state {
 	u64 pidr;
 	u64 cfar;
 	u64 ppr;
+	/* Version 1 ends here */
+	u64 dawr1;
+	u64 dawrx1;
+	/* Version 2 ends here */
 };
 
 /* Latest version of hv_guest_state structure */
-#define HV_GUEST_STATE_VERSION	1
+#define HV_GUEST_STATE_VERSION	2
+
+static inline int hv_guest_state_size(unsigned int version)
+{
+	switch (version) {
+	case 1:
+		return offsetofend(struct hv_guest_state, ppr);
+	case 2:
+		return offsetofend(struct hv_guest_state, dawrx1);
+	default:
+		return -1;
+	}
+}
 
 /*
  * From the document "H_GetPerformanceCounterInfo Interface" v1.07
diff --git a/arch/powerpc/include/asm/kvm_book3s_asm.h b/arch/powerpc/include/asm/kvm_book3s_asm.h
index 078f4648ea27..b6d31bff5209 100644
--- a/arch/powerpc/include/asm/kvm_book3s_asm.h
+++ b/arch/powerpc/include/asm/kvm_book3s_asm.h
@@ -74,16 +74,6 @@ struct kvm_split_mode {
 	u8		do_nap;
 	u8		napped[MAX_SMT_THREADS];
 	struct kvmppc_vcore *vc[MAX_SUBCORES];
-	/* Bits for changing lpcr on P9 */
-	unsigned long	lpcr_req;
-	unsigned long	lpidr_req;
-	unsigned long	host_lpcr;
-	u32		do_set;
-	u32		do_restore;
-	union {
-		u32	allphases;
-		u8	phase[4];
-	} lpcr_sync;
 };
 
 /*
@@ -110,7 +100,6 @@ struct kvmppc_host_state {
 	u8 hwthread_state;
 	u8 host_ipi;
 	u8 ptid;		/* thread number within subcore when split */
-	u8 tid;			/* thread number within whole core */
 	u8 fake_suspend;
 	struct kvm_vcpu *kvm_vcpu;
 	struct kvmppc_vcore *kvm_vcore;
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index d67a470e95a3..05fb00d37609 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -28,7 +28,6 @@
 
 #define KVM_MAX_VCPUS		NR_CPUS
 #define KVM_MAX_VCORES		NR_CPUS
-#define KVM_USER_MEM_SLOTS	512
 
 #include <asm/cputhreads.h>
 
@@ -307,6 +306,7 @@ struct kvm_arch {
 	u8 svm_enabled;
 	bool threads_indep;
 	bool nested_enable;
+	bool dawr1_enabled;
 	pgd_t *pgtable;
 	u64 process_table;
 	struct dentry *debugfs_dir;
@@ -584,8 +584,10 @@ struct kvm_vcpu_arch {
 	u32 ctrl;
 	u32 dabrx;
 	ulong dabr;
-	ulong dawr;
-	ulong dawrx;
+	ulong dawr0;
+	ulong dawrx0;
+	ulong dawr1;
+	ulong dawrx1;
 	ulong ciabr;
 	ulong cfar;
 	ulong ppr;
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index 0a056c64c317..df4bda867bab 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -314,6 +314,8 @@ struct kvmppc_ops {
 			      int size);
 	int (*enable_svm)(struct kvm *kvm);
 	int (*svm_off)(struct kvm *kvm);
+	int (*enable_dawr1)(struct kvm *kvm);
+	bool (*hash_v3_possible)(void);
 };
 
 extern struct kvmppc_ops *kvmppc_hv_ops;
diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h
index c3af3f324c5a..9f18fa090f1f 100644
--- a/arch/powerpc/include/uapi/asm/kvm.h
+++ b/arch/powerpc/include/uapi/asm/kvm.h
@@ -644,6 +644,8 @@ struct kvm_ppc_cpu_char {
 #define KVM_REG_PPC_MMCR3	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc1)
 #define KVM_REG_PPC_SIER2	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc2)
 #define KVM_REG_PPC_SIER3	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc3)
+#define KVM_REG_PPC_DAWR1	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc4)
+#define KVM_REG_PPC_DAWRX1	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc5)
 
 /* Transactional Memory checkpointed state:
  * This is all GPRs, all VSX regs and a subset of SPRs
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index b12d7c049bfe..b690c70f061c 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -526,8 +526,10 @@ int main(void)
 	OFFSET(VCPU_CTRL, kvm_vcpu, arch.ctrl);
 	OFFSET(VCPU_DABR, kvm_vcpu, arch.dabr);
 	OFFSET(VCPU_DABRX, kvm_vcpu, arch.dabrx);
-	OFFSET(VCPU_DAWR, kvm_vcpu, arch.dawr);
-	OFFSET(VCPU_DAWRX, kvm_vcpu, arch.dawrx);
+	OFFSET(VCPU_DAWR0, kvm_vcpu, arch.dawr0);
+	OFFSET(VCPU_DAWRX0, kvm_vcpu, arch.dawrx0);
+	OFFSET(VCPU_DAWR1, kvm_vcpu, arch.dawr1);
+	OFFSET(VCPU_DAWRX1, kvm_vcpu, arch.dawrx1);
 	OFFSET(VCPU_CIABR, kvm_vcpu, arch.ciabr);
 	OFFSET(VCPU_HFLAGS, kvm_vcpu, arch.hflags);
 	OFFSET(VCPU_DEC, kvm_vcpu, arch.dec);
@@ -668,7 +670,6 @@ int main(void)
 	HSTATE_FIELD(HSTATE_SAVED_XIRR, saved_xirr);
 	HSTATE_FIELD(HSTATE_HOST_IPI, host_ipi);
 	HSTATE_FIELD(HSTATE_PTID, ptid);
-	HSTATE_FIELD(HSTATE_TID, tid);
 	HSTATE_FIELD(HSTATE_FAKE_SUSPEND, fake_suspend);
 	HSTATE_FIELD(HSTATE_MMCR0, host_mmcr[0]);
 	HSTATE_FIELD(HSTATE_MMCR1, host_mmcr[1]);
@@ -698,8 +699,6 @@ int main(void)
 	OFFSET(KVM_SPLIT_LDBAR, kvm_split_mode, ldbar);
 	OFFSET(KVM_SPLIT_DO_NAP, kvm_split_mode, do_nap);
 	OFFSET(KVM_SPLIT_NAPPED, kvm_split_mode, napped);
-	OFFSET(KVM_SPLIT_DO_SET, kvm_split_mode, do_set);
-	OFFSET(KVM_SPLIT_DO_RESTORE, kvm_split_mode, do_restore);
 #endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */
 
 #ifdef CONFIG_PPC_BOOK3S_64
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 6f612d240392..f09708da216e 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -134,7 +134,7 @@ static inline bool nesting_enabled(struct kvm *kvm)
 }
 
 /* If set, the threads on each CPU core have to be in the same MMU mode */
-static bool no_mixing_hpt_and_radix;
+static bool no_mixing_hpt_and_radix __read_mostly;
 
 static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu);
 
@@ -782,8 +782,24 @@ static int kvmppc_h_set_mode(struct kvm_vcpu *vcpu, unsigned long mflags,
 			return H_UNSUPPORTED_FLAG_START;
 		if (value2 & DABRX_HYP)
 			return H_P4;
-		vcpu->arch.dawr  = value1;
-		vcpu->arch.dawrx = value2;
+		vcpu->arch.dawr0  = value1;
+		vcpu->arch.dawrx0 = value2;
+		return H_SUCCESS;
+	case H_SET_MODE_RESOURCE_SET_DAWR1:
+		if (!kvmppc_power8_compatible(vcpu))
+			return H_P2;
+		if (!ppc_breakpoint_available())
+			return H_P2;
+		if (!cpu_has_feature(CPU_FTR_DAWR1))
+			return H_P2;
+		if (!vcpu->kvm->arch.dawr1_enabled)
+			return H_FUNCTION;
+		if (mflags)
+			return H_UNSUPPORTED_FLAG_START;
+		if (value2 & DABRX_HYP)
+			return H_P4;
+		vcpu->arch.dawr1  = value1;
+		vcpu->arch.dawrx1 = value2;
 		return H_SUCCESS;
 	case H_SET_MODE_RESOURCE_ADDR_TRANS_MODE:
 		/* KVM does not support mflags=2 (AIL=2) */
@@ -1759,10 +1775,16 @@ static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
 		*val = get_reg_val(id, vcpu->arch.vcore->vtb);
 		break;
 	case KVM_REG_PPC_DAWR:
-		*val = get_reg_val(id, vcpu->arch.dawr);
+		*val = get_reg_val(id, vcpu->arch.dawr0);
 		break;
 	case KVM_REG_PPC_DAWRX:
-		*val = get_reg_val(id, vcpu->arch.dawrx);
+		*val = get_reg_val(id, vcpu->arch.dawrx0);
+		break;
+	case KVM_REG_PPC_DAWR1:
+		*val = get_reg_val(id, vcpu->arch.dawr1);
+		break;
+	case KVM_REG_PPC_DAWRX1:
+		*val = get_reg_val(id, vcpu->arch.dawrx1);
 		break;
 	case KVM_REG_PPC_CIABR:
 		*val = get_reg_val(id, vcpu->arch.ciabr);
@@ -1991,10 +2013,16 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
 		vcpu->arch.vcore->vtb = set_reg_val(id, *val);
 		break;
 	case KVM_REG_PPC_DAWR:
-		vcpu->arch.dawr = set_reg_val(id, *val);
+		vcpu->arch.dawr0 = set_reg_val(id, *val);
 		break;
 	case KVM_REG_PPC_DAWRX:
-		vcpu->arch.dawrx = set_reg_val(id, *val) & ~DAWRX_HYP;
+		vcpu->arch.dawrx0 = set_reg_val(id, *val) & ~DAWRX_HYP;
+		break;
+	case KVM_REG_PPC_DAWR1:
+		vcpu->arch.dawr1 = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_DAWRX1:
+		vcpu->arch.dawrx1 = set_reg_val(id, *val) & ~DAWRX_HYP;
 		break;
 	case KVM_REG_PPC_CIABR:
 		vcpu->arch.ciabr = set_reg_val(id, *val);
@@ -2862,11 +2890,6 @@ static bool can_dynamic_split(struct kvmppc_vcore *vc, struct core_info *cip)
 	if (one_vm_per_core && vc->kvm != cip->vc[0]->kvm)
 		return false;
 
-	/* Some POWER9 chips require all threads to be in the same MMU mode */
-	if (no_mixing_hpt_and_radix &&
-	    kvm_is_radix(vc->kvm) != kvm_is_radix(cip->vc[0]->kvm))
-		return false;
-
 	if (n_threads < cip->max_subcore_threads)
 		n_threads = cip->max_subcore_threads;
 	if (!subcore_config_ok(cip->n_subcores + 1, n_threads))
@@ -2905,6 +2928,9 @@ static void prepare_threads(struct kvmppc_vcore *vc)
 	for_each_runnable_thread(i, vcpu, vc) {
 		if (signal_pending(vcpu->arch.run_task))
 			vcpu->arch.ret = -EINTR;
+		else if (no_mixing_hpt_and_radix &&
+			 kvm_is_radix(vc->kvm) != radix_enabled())
+			vcpu->arch.ret = -EINVAL;
 		else if (vcpu->arch.vpa.update_pending ||
 			 vcpu->arch.slb_shadow.update_pending ||
 			 vcpu->arch.dtl.update_pending)
@@ -3110,7 +3136,6 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
 	int controlled_threads;
 	int trap;
 	bool is_power8;
-	bool hpt_on_radix;
 
 	/*
 	 * Remove from the list any threads that have a signal pending
@@ -3143,11 +3168,8 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
 	 * this is a HPT guest on a radix host machine where the
 	 * CPU threads may not be in different MMU modes.
 	 */
-	hpt_on_radix = no_mixing_hpt_and_radix && radix_enabled() &&
-		!kvm_is_radix(vc->kvm);
-	if (((controlled_threads > 1) &&
-	     ((vc->num_threads > threads_per_subcore) || !on_primary_thread())) ||
-	    (hpt_on_radix && vc->kvm->arch.threads_indep)) {
+	if ((controlled_threads > 1) &&
+	    ((vc->num_threads > threads_per_subcore) || !on_primary_thread())) {
 		for_each_runnable_thread(i, vcpu, vc) {
 			vcpu->arch.ret = -EBUSY;
 			kvmppc_remove_runnable(vc, vcpu);
@@ -3215,7 +3237,7 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
 	is_power8 = cpu_has_feature(CPU_FTR_ARCH_207S)
 		&& !cpu_has_feature(CPU_FTR_ARCH_300);
 
-	if (split > 1 || hpt_on_radix) {
+	if (split > 1) {
 		sip = &split_info;
 		memset(&split_info, 0, sizeof(split_info));
 		for (sub = 0; sub < core_info.n_subcores; ++sub)
@@ -3237,13 +3259,6 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
 			split_info.subcore_size = subcore_size;
 		} else {
 			split_info.subcore_size = 1;
-			if (hpt_on_radix) {
-				/* Use the split_info for LPCR/LPIDR changes */
-				split_info.lpcr_req = vc->lpcr;
-				split_info.lpidr_req = vc->kvm->arch.lpid;
-				split_info.host_lpcr = vc->kvm->arch.host_lpcr;
-				split_info.do_set = 1;
-			}
 		}
 
 		/* order writes to split_info before kvm_split_mode pointer */
@@ -3253,7 +3268,6 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
 	for (thr = 0; thr < controlled_threads; ++thr) {
 		struct paca_struct *paca = paca_ptrs[pcpu + thr];
 
-		paca->kvm_hstate.tid = thr;
 		paca->kvm_hstate.napping = 0;
 		paca->kvm_hstate.kvm_split_mode = sip;
 	}
@@ -3327,10 +3341,8 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
 	 * When doing micro-threading, poke the inactive threads as well.
 	 * This gets them to the nap instruction after kvm_do_nap,
 	 * which reduces the time taken to unsplit later.
-	 * For POWER9 HPT guest on radix host, we need all the secondary
-	 * threads woken up so they can do the LPCR/LPIDR change.
 	 */
-	if (cmd_bit || hpt_on_radix) {
+	if (cmd_bit) {
 		split_info.do_nap = 1;	/* ask secondaries to nap when done */
 		for (thr = 1; thr < threads_per_subcore; ++thr)
 			if (!(active & (1 << thr)))
@@ -3391,19 +3403,8 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
 			cpu_relax();
 			++loops;
 		}
-	} else if (hpt_on_radix) {
-		/* Wait for all threads to have seen final sync */
-		for (thr = 1; thr < controlled_threads; ++thr) {
-			struct paca_struct *paca = paca_ptrs[pcpu + thr];
-
-			while (paca->kvm_hstate.kvm_split_mode) {
-				HMT_low();
-				barrier();
-			}
-			HMT_medium();
-		}
+		split_info.do_nap = 0;
 	}
-	split_info.do_nap = 0;
 
 	kvmppc_set_host_core(pcpu);
 
@@ -3449,10 +3450,17 @@ static int kvmhv_load_hv_regs_and_go(struct kvm_vcpu *vcpu, u64 time_limit,
 	int trap;
 	unsigned long host_hfscr = mfspr(SPRN_HFSCR);
 	unsigned long host_ciabr = mfspr(SPRN_CIABR);
-	unsigned long host_dawr = mfspr(SPRN_DAWR0);
-	unsigned long host_dawrx = mfspr(SPRN_DAWRX0);
+	unsigned long host_dawr0 = mfspr(SPRN_DAWR0);
+	unsigned long host_dawrx0 = mfspr(SPRN_DAWRX0);
 	unsigned long host_psscr = mfspr(SPRN_PSSCR);
 	unsigned long host_pidr = mfspr(SPRN_PID);
+	unsigned long host_dawr1 = 0;
+	unsigned long host_dawrx1 = 0;
+
+	if (cpu_has_feature(CPU_FTR_DAWR1)) {
+		host_dawr1 = mfspr(SPRN_DAWR1);
+		host_dawrx1 = mfspr(SPRN_DAWRX1);
+	}
 
 	/*
 	 * P8 and P9 suppress the HDEC exception when LPCR[HDICE] = 0,
@@ -3489,8 +3497,12 @@ static int kvmhv_load_hv_regs_and_go(struct kvm_vcpu *vcpu, u64 time_limit,
 	mtspr(SPRN_SPURR, vcpu->arch.spurr);
 
 	if (dawr_enabled()) {
-		mtspr(SPRN_DAWR0, vcpu->arch.dawr);
-		mtspr(SPRN_DAWRX0, vcpu->arch.dawrx);
+		mtspr(SPRN_DAWR0, vcpu->arch.dawr0);
+		mtspr(SPRN_DAWRX0, vcpu->arch.dawrx0);
+		if (cpu_has_feature(CPU_FTR_DAWR1)) {
+			mtspr(SPRN_DAWR1, vcpu->arch.dawr1);
+			mtspr(SPRN_DAWRX1, vcpu->arch.dawrx1);
+		}
 	}
 	mtspr(SPRN_CIABR, vcpu->arch.ciabr);
 	mtspr(SPRN_IC, vcpu->arch.ic);
@@ -3542,8 +3554,12 @@ static int kvmhv_load_hv_regs_and_go(struct kvm_vcpu *vcpu, u64 time_limit,
 	      (local_paca->kvm_hstate.fake_suspend << PSSCR_FAKE_SUSPEND_LG));
 	mtspr(SPRN_HFSCR, host_hfscr);
 	mtspr(SPRN_CIABR, host_ciabr);
-	mtspr(SPRN_DAWR0, host_dawr);
-	mtspr(SPRN_DAWRX0, host_dawrx);
+	mtspr(SPRN_DAWR0, host_dawr0);
+	mtspr(SPRN_DAWRX0, host_dawrx0);
+	if (cpu_has_feature(CPU_FTR_DAWR1)) {
+		mtspr(SPRN_DAWR1, host_dawr1);
+		mtspr(SPRN_DAWRX1, host_dawrx1);
+	}
 	mtspr(SPRN_PID, host_pidr);
 
 	/*
@@ -3595,6 +3611,7 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
 	unsigned long host_tidr = mfspr(SPRN_TIDR);
 	unsigned long host_iamr = mfspr(SPRN_IAMR);
 	unsigned long host_amr = mfspr(SPRN_AMR);
+	unsigned long host_fscr = mfspr(SPRN_FSCR);
 	s64 dec;
 	u64 tb;
 	int trap, save_pmu;
@@ -3735,6 +3752,9 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
 	if (host_amr != vcpu->arch.amr)
 		mtspr(SPRN_AMR, host_amr);
 
+	if (host_fscr != vcpu->arch.fscr)
+		mtspr(SPRN_FSCR, host_fscr);
+
 	msr_check_and_set(MSR_FP | MSR_VEC | MSR_VSX);
 	store_fp_state(&vcpu->arch.fp);
 #ifdef CONFIG_ALTIVEC
@@ -4173,7 +4193,6 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit,
 
 	kvmppc_clear_host_core(pcpu);
 
-	local_paca->kvm_hstate.tid = 0;
 	local_paca->kvm_hstate.napping = 0;
 	local_paca->kvm_hstate.kvm_split_mode = NULL;
 	kvmppc_start_thread(vcpu, vc);
@@ -4358,15 +4377,11 @@ static int kvmppc_vcpu_run_hv(struct kvm_vcpu *vcpu)
 
 	do {
 		/*
-		 * The early POWER9 chips that can't mix radix and HPT threads
-		 * on the same core also need the workaround for the problem
-		 * where the TLB would prefetch entries in the guest exit path
-		 * for radix guests using the guest PIDR value and LPID 0.
-		 * The workaround is in the old path (kvmppc_run_vcpu())
-		 * but not the new path (kvmhv_run_single_vcpu()).
+		 * The TLB prefetch bug fixup is only in the kvmppc_run_vcpu
+		 * path, which also handles hash and dependent threads mode.
 		 */
 		if (kvm->arch.threads_indep && kvm_is_radix(kvm) &&
-		    !no_mixing_hpt_and_radix)
+		    !cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG))
 			r = kvmhv_run_single_vcpu(vcpu, ~(u64)0,
 						  vcpu->arch.vcore->lpcr);
 		else
@@ -5599,6 +5614,26 @@ out:
 	return ret;
 }
 
+static int kvmhv_enable_dawr1(struct kvm *kvm)
+{
+	if (!cpu_has_feature(CPU_FTR_DAWR1))
+		return -ENODEV;
+
+	/* kvm == NULL means the caller is testing if the capability exists */
+	if (kvm)
+		kvm->arch.dawr1_enabled = true;
+	return 0;
+}
+
+static bool kvmppc_hash_v3_possible(void)
+{
+	if (radix_enabled() && no_mixing_hpt_and_radix)
+		return false;
+
+	return cpu_has_feature(CPU_FTR_ARCH_300) &&
+		cpu_has_feature(CPU_FTR_HVMODE);
+}
+
 static struct kvmppc_ops kvm_ops_hv = {
 	.get_sregs = kvm_arch_vcpu_ioctl_get_sregs_hv,
 	.set_sregs = kvm_arch_vcpu_ioctl_set_sregs_hv,
@@ -5642,6 +5677,8 @@ static struct kvmppc_ops kvm_ops_hv = {
 	.store_to_eaddr = kvmhv_store_to_eaddr,
 	.enable_svm = kvmhv_enable_svm,
 	.svm_off = kvmhv_svm_off,
+	.enable_dawr1 = kvmhv_enable_dawr1,
+	.hash_v3_possible = kvmppc_hash_v3_possible,
 };
 
 static int kvm_init_subcore_bitmap(void)
diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c
index 8053efdf7ea7..f3d3183249fe 100644
--- a/arch/powerpc/kvm/book3s_hv_builtin.c
+++ b/arch/powerpc/kvm/book3s_hv_builtin.c
@@ -277,8 +277,7 @@ void kvmhv_commence_exit(int trap)
 	struct kvmppc_vcore *vc = local_paca->kvm_hstate.kvm_vcore;
 	int ptid = local_paca->kvm_hstate.ptid;
 	struct kvm_split_mode *sip = local_paca->kvm_hstate.kvm_split_mode;
-	int me, ee, i, t;
-	int cpu0;
+	int me, ee, i;
 
 	/* Set our bit in the threads-exiting-guest map in the 0xff00
 	   bits of vcore->entry_exit_map */
@@ -320,22 +319,6 @@ void kvmhv_commence_exit(int trap)
 		if ((ee >> 8) == 0)
 			kvmhv_interrupt_vcore(vc, ee);
 	}
-
-	/*
-	 * On POWER9 when running a HPT guest on a radix host (sip != NULL),
-	 * we have to interrupt inactive CPU threads to get them to
-	 * restore the host LPCR value.
-	 */
-	if (sip->lpcr_req) {
-		if (cmpxchg(&sip->do_restore, 0, 1) == 0) {
-			vc = local_paca->kvm_hstate.kvm_vcore;
-			cpu0 = vc->pcpu + ptid - local_paca->kvm_hstate.tid;
-			for (t = 1; t < threads_per_core; ++t) {
-				if (sip->napped[t])
-					kvmhv_rm_send_ipi(cpu0 + t);
-			}
-		}
-	}
 }
 
 struct kvmppc_host_rm_ops *kvmppc_host_rm_ops_hv;
@@ -667,95 +650,6 @@ void kvmppc_bad_interrupt(struct pt_regs *regs)
 	panic("Bad KVM trap");
 }
 
-/*
- * Functions used to switch LPCR HR and UPRT bits on all threads
- * when entering and exiting HPT guests on a radix host.
- */
-
-#define PHASE_REALMODE		1	/* in real mode */
-#define PHASE_SET_LPCR		2	/* have set LPCR */
-#define PHASE_OUT_OF_GUEST	4	/* have finished executing in guest */
-#define PHASE_RESET_LPCR	8	/* have reset LPCR to host value */
-
-#define ALL(p)		(((p) << 24) | ((p) << 16) | ((p) << 8) | (p))
-
-static void wait_for_sync(struct kvm_split_mode *sip, int phase)
-{
-	int thr = local_paca->kvm_hstate.tid;
-
-	sip->lpcr_sync.phase[thr] |= phase;
-	phase = ALL(phase);
-	while ((sip->lpcr_sync.allphases & phase) != phase) {
-		HMT_low();
-		barrier();
-	}
-	HMT_medium();
-}
-
-void kvmhv_p9_set_lpcr(struct kvm_split_mode *sip)
-{
-	int num_sets;
-	unsigned long rb, set;
-
-	/* wait for every other thread to get to real mode */
-	wait_for_sync(sip, PHASE_REALMODE);
-
-	/* Set LPCR and LPIDR */
-	mtspr(SPRN_LPCR, sip->lpcr_req);
-	mtspr(SPRN_LPID, sip->lpidr_req);
-	isync();
-
-	/*
-	 * P10 will flush all the congruence class with a single tlbiel
-	 */
-	if (cpu_has_feature(CPU_FTR_ARCH_31))
-		num_sets =  1;
-	else
-		num_sets = POWER9_TLB_SETS_RADIX;
-
-	/* Invalidate the TLB on thread 0 */
-	if (local_paca->kvm_hstate.tid == 0) {
-		sip->do_set = 0;
-		asm volatile("ptesync" : : : "memory");
-		for (set = 0; set < num_sets; ++set) {
-			rb = TLBIEL_INVAL_SET_LPID +
-				(set << TLBIEL_INVAL_SET_SHIFT);
-			asm volatile(PPC_TLBIEL(%0, %1, 0, 0, 0) : :
-				     "r" (rb), "r" (0));
-		}
-		asm volatile("ptesync" : : : "memory");
-	}
-
-	/* indicate that we have done so and wait for others */
-	wait_for_sync(sip, PHASE_SET_LPCR);
-	/* order read of sip->lpcr_sync.allphases vs. sip->do_set */
-	smp_rmb();
-}
-
-/*
- * Called when a thread that has been in the guest needs
- * to reload the host LPCR value - but only on POWER9 when
- * running a HPT guest on a radix host.
- */
-void kvmhv_p9_restore_lpcr(struct kvm_split_mode *sip)
-{
-	/* we're out of the guest... */
-	wait_for_sync(sip, PHASE_OUT_OF_GUEST);
-
-	mtspr(SPRN_LPID, 0);
-	mtspr(SPRN_LPCR, sip->host_lpcr);
-	isync();
-
-	if (local_paca->kvm_hstate.tid == 0) {
-		sip->do_restore = 0;
-		smp_wmb();	/* order store of do_restore vs. phase */
-	}
-
-	wait_for_sync(sip, PHASE_RESET_LPCR);
-	smp_mb();
-	local_paca->kvm_hstate.kvm_split_mode = NULL;
-}
-
 static void kvmppc_end_cede(struct kvm_vcpu *vcpu)
 {
 	vcpu->arch.ceded = 0;
diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c
index 33b58549a9aa..0cd0e7aad588 100644
--- a/arch/powerpc/kvm/book3s_hv_nested.c
+++ b/arch/powerpc/kvm/book3s_hv_nested.c
@@ -33,8 +33,8 @@ void kvmhv_save_hv_regs(struct kvm_vcpu *vcpu, struct hv_guest_state *hr)
 	hr->dpdes = vc->dpdes;
 	hr->hfscr = vcpu->arch.hfscr;
 	hr->tb_offset = vc->tb_offset;
-	hr->dawr0 = vcpu->arch.dawr;
-	hr->dawrx0 = vcpu->arch.dawrx;
+	hr->dawr0 = vcpu->arch.dawr0;
+	hr->dawrx0 = vcpu->arch.dawrx0;
 	hr->ciabr = vcpu->arch.ciabr;
 	hr->purr = vcpu->arch.purr;
 	hr->spurr = vcpu->arch.spurr;
@@ -49,6 +49,8 @@ void kvmhv_save_hv_regs(struct kvm_vcpu *vcpu, struct hv_guest_state *hr)
 	hr->pidr = vcpu->arch.pid;
 	hr->cfar = vcpu->arch.cfar;
 	hr->ppr = vcpu->arch.ppr;
+	hr->dawr1 = vcpu->arch.dawr1;
+	hr->dawrx1 = vcpu->arch.dawrx1;
 }
 
 static void byteswap_pt_regs(struct pt_regs *regs)
@@ -91,6 +93,8 @@ static void byteswap_hv_regs(struct hv_guest_state *hr)
 	hr->pidr = swab64(hr->pidr);
 	hr->cfar = swab64(hr->cfar);
 	hr->ppr = swab64(hr->ppr);
+	hr->dawr1 = swab64(hr->dawr1);
+	hr->dawrx1 = swab64(hr->dawrx1);
 }
 
 static void save_hv_return_state(struct kvm_vcpu *vcpu, int trap,
@@ -138,6 +142,7 @@ static void sanitise_hv_regs(struct kvm_vcpu *vcpu, struct hv_guest_state *hr)
 
 	/* Don't let data address watchpoint match in hypervisor state */
 	hr->dawrx0 &= ~DAWRX_HYP;
+	hr->dawrx1 &= ~DAWRX_HYP;
 
 	/* Don't let completed instruction address breakpt match in HV state */
 	if ((hr->ciabr & CIABR_PRIV) == CIABR_PRIV_HYPER)
@@ -151,8 +156,8 @@ static void restore_hv_regs(struct kvm_vcpu *vcpu, struct hv_guest_state *hr)
 	vc->pcr = hr->pcr | PCR_MASK;
 	vc->dpdes = hr->dpdes;
 	vcpu->arch.hfscr = hr->hfscr;
-	vcpu->arch.dawr = hr->dawr0;
-	vcpu->arch.dawrx = hr->dawrx0;
+	vcpu->arch.dawr0 = hr->dawr0;
+	vcpu->arch.dawrx0 = hr->dawrx0;
 	vcpu->arch.ciabr = hr->ciabr;
 	vcpu->arch.purr = hr->purr;
 	vcpu->arch.spurr = hr->spurr;
@@ -167,6 +172,8 @@ static void restore_hv_regs(struct kvm_vcpu *vcpu, struct hv_guest_state *hr)
 	vcpu->arch.pid = hr->pidr;
 	vcpu->arch.cfar = hr->cfar;
 	vcpu->arch.ppr = hr->ppr;
+	vcpu->arch.dawr1 = hr->dawr1;
+	vcpu->arch.dawrx1 = hr->dawrx1;
 }
 
 void kvmhv_restore_hv_return_state(struct kvm_vcpu *vcpu,
@@ -215,12 +222,51 @@ static void kvmhv_nested_mmio_needed(struct kvm_vcpu *vcpu, u64 regs_ptr)
 	}
 }
 
+static int kvmhv_read_guest_state_and_regs(struct kvm_vcpu *vcpu,
+					   struct hv_guest_state *l2_hv,
+					   struct pt_regs *l2_regs,
+					   u64 hv_ptr, u64 regs_ptr)
+{
+	int size;
+
+	if (kvm_vcpu_read_guest(vcpu, hv_ptr, &l2_hv->version,
+				sizeof(l2_hv->version)))
+		return -1;
+
+	if (kvmppc_need_byteswap(vcpu))
+		l2_hv->version = swab64(l2_hv->version);
+
+	size = hv_guest_state_size(l2_hv->version);
+	if (size < 0)
+		return -1;
+
+	return kvm_vcpu_read_guest(vcpu, hv_ptr, l2_hv, size) ||
+		kvm_vcpu_read_guest(vcpu, regs_ptr, l2_regs,
+				    sizeof(struct pt_regs));
+}
+
+static int kvmhv_write_guest_state_and_regs(struct kvm_vcpu *vcpu,
+					    struct hv_guest_state *l2_hv,
+					    struct pt_regs *l2_regs,
+					    u64 hv_ptr, u64 regs_ptr)
+{
+	int size;
+
+	size = hv_guest_state_size(l2_hv->version);
+	if (size < 0)
+		return -1;
+
+	return kvm_vcpu_write_guest(vcpu, hv_ptr, l2_hv, size) ||
+		kvm_vcpu_write_guest(vcpu, regs_ptr, l2_regs,
+				     sizeof(struct pt_regs));
+}
+
 long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu)
 {
 	long int err, r;
 	struct kvm_nested_guest *l2;
 	struct pt_regs l2_regs, saved_l1_regs;
-	struct hv_guest_state l2_hv, saved_l1_hv;
+	struct hv_guest_state l2_hv = {0}, saved_l1_hv;
 	struct kvmppc_vcore *vc = vcpu->arch.vcore;
 	u64 hv_ptr, regs_ptr;
 	u64 hdec_exp;
@@ -235,17 +281,15 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu)
 	hv_ptr = kvmppc_get_gpr(vcpu, 4);
 	regs_ptr = kvmppc_get_gpr(vcpu, 5);
 	vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
-	err = kvm_vcpu_read_guest(vcpu, hv_ptr, &l2_hv,
-				  sizeof(struct hv_guest_state)) ||
-		kvm_vcpu_read_guest(vcpu, regs_ptr, &l2_regs,
-				    sizeof(struct pt_regs));
+	err = kvmhv_read_guest_state_and_regs(vcpu, &l2_hv, &l2_regs,
+					      hv_ptr, regs_ptr);
 	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
 	if (err)
 		return H_PARAMETER;
 
 	if (kvmppc_need_byteswap(vcpu))
 		byteswap_hv_regs(&l2_hv);
-	if (l2_hv.version != HV_GUEST_STATE_VERSION)
+	if (l2_hv.version > HV_GUEST_STATE_VERSION)
 		return H_P2;
 
 	if (kvmppc_need_byteswap(vcpu))
@@ -325,10 +369,8 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu)
 		byteswap_pt_regs(&l2_regs);
 	}
 	vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
-	err = kvm_vcpu_write_guest(vcpu, hv_ptr, &l2_hv,
-				   sizeof(struct hv_guest_state)) ||
-		kvm_vcpu_write_guest(vcpu, regs_ptr, &l2_regs,
-				   sizeof(struct pt_regs));
+	err = kvmhv_write_guest_state_and_regs(vcpu, &l2_hv, &l2_regs,
+					       hv_ptr, regs_ptr);
 	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
 	if (err)
 		return H_AUTHORITY;
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index cd9995ee8441..5e634db4809b 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -52,11 +52,13 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
 #define STACK_SLOT_PID		(SFS-32)
 #define STACK_SLOT_IAMR		(SFS-40)
 #define STACK_SLOT_CIABR	(SFS-48)
-#define STACK_SLOT_DAWR		(SFS-56)
-#define STACK_SLOT_DAWRX	(SFS-64)
+#define STACK_SLOT_DAWR0	(SFS-56)
+#define STACK_SLOT_DAWRX0	(SFS-64)
 #define STACK_SLOT_HFSCR	(SFS-72)
 #define STACK_SLOT_AMR		(SFS-80)
 #define STACK_SLOT_UAMOR	(SFS-88)
+#define STACK_SLOT_DAWR1	(SFS-96)
+#define STACK_SLOT_DAWRX1	(SFS-104)
 /* the following is used by the P9 short path */
 #define STACK_SLOT_NVGPRS	(SFS-152)	/* 18 gprs */
 
@@ -85,19 +87,6 @@ _GLOBAL_TOC(kvmppc_hv_entry_trampoline)
 	RFI_TO_KERNEL
 
 kvmppc_call_hv_entry:
-BEGIN_FTR_SECTION
-	/* On P9, do LPCR setting, if necessary */
-	ld	r3, HSTATE_SPLIT_MODE(r13)
-	cmpdi	r3, 0
-	beq	46f
-	lwz	r4, KVM_SPLIT_DO_SET(r3)
-	cmpwi	r4, 0
-	beq	46f
-	bl	kvmhv_p9_set_lpcr
-	nop
-46:
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
-
 	ld	r4, HSTATE_KVM_VCPU(r13)
 	bl	kvmppc_hv_entry
 
@@ -361,11 +350,11 @@ kvm_secondary_got_guest:
 	LOAD_REG_ADDR(r6, decrementer_max)
 	ld	r6, 0(r6)
 	mtspr	SPRN_HDEC, r6
+BEGIN_FTR_SECTION
 	/* and set per-LPAR registers, if doing dynamic micro-threading */
 	ld	r6, HSTATE_SPLIT_MODE(r13)
 	cmpdi	r6, 0
 	beq	63f
-BEGIN_FTR_SECTION
 	ld	r0, KVM_SPLIT_RPR(r6)
 	mtspr	SPRN_RPR, r0
 	ld	r0, KVM_SPLIT_PMMAR(r6)
@@ -373,16 +362,7 @@ BEGIN_FTR_SECTION
 	ld	r0, KVM_SPLIT_LDBAR(r6)
 	mtspr	SPRN_LDBAR, r0
 	isync
-FTR_SECTION_ELSE
-	/* On P9 we use the split_info for coordinating LPCR changes */
-	lwz	r4, KVM_SPLIT_DO_SET(r6)
-	cmpwi	r4, 0
-	beq	1f
-	mr	r3, r6
-	bl	kvmhv_p9_set_lpcr
-	nop
-1:
-ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300)
+END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
 63:
 	/* Order load of vcpu after load of vcore */
 	lwsync
@@ -452,19 +432,15 @@ kvm_no_guest:
 	mtcr	r5
 	blr
 
-53:	HMT_LOW
+53:
+BEGIN_FTR_SECTION
+	HMT_LOW
 	ld	r5, HSTATE_KVM_VCORE(r13)
 	cmpdi	r5, 0
 	bne	60f
 	ld	r3, HSTATE_SPLIT_MODE(r13)
 	cmpdi	r3, 0
 	beq	kvm_no_guest
-	lwz	r0, KVM_SPLIT_DO_SET(r3)
-	cmpwi	r0, 0
-	bne	kvmhv_do_set
-	lwz	r0, KVM_SPLIT_DO_RESTORE(r3)
-	cmpwi	r0, 0
-	bne	kvmhv_do_restore
 	lbz	r0, KVM_SPLIT_DO_NAP(r3)
 	cmpwi	r0, 0
 	beq	kvm_no_guest
@@ -472,24 +448,19 @@ kvm_no_guest:
 	b	kvm_unsplit_nap
 60:	HMT_MEDIUM
 	b	kvm_secondary_got_guest
+FTR_SECTION_ELSE
+	HMT_LOW
+	ld	r5, HSTATE_KVM_VCORE(r13)
+	cmpdi	r5, 0
+	beq	kvm_no_guest
+	HMT_MEDIUM
+	b	kvm_secondary_got_guest
+ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300)
 
 54:	li	r0, KVM_HWTHREAD_IN_KVM
 	stb	r0, HSTATE_HWTHREAD_STATE(r13)
 	b	kvm_no_guest
 
-kvmhv_do_set:
-	/* Set LPCR, LPIDR etc. on P9 */
-	HMT_MEDIUM
-	bl	kvmhv_p9_set_lpcr
-	nop
-	b	kvm_no_guest
-
-kvmhv_do_restore:
-	HMT_MEDIUM
-	bl	kvmhv_p9_restore_lpcr
-	nop
-	b	kvm_no_guest
-
 /*
  * Here the primary thread is trying to return the core to
  * whole-core mode, so we need to nap.
@@ -527,7 +498,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 	/* Set kvm_split_mode.napped[tid] = 1 */
 	ld	r3, HSTATE_SPLIT_MODE(r13)
 	li	r0, 1
-	lbz	r4, HSTATE_TID(r13)
+	lhz	r4, PACAPACAINDEX(r13)
+	clrldi	r4, r4, 61	/* micro-threading => P8 => 8 threads/core */
 	addi	r4, r4, KVM_SPLIT_NAPPED
 	stbx	r0, r3, r4
 	/* Check the do_nap flag again after setting napped[] */
@@ -711,10 +683,16 @@ BEGIN_FTR_SECTION
 	mfspr	r7, SPRN_DAWRX0
 	mfspr	r8, SPRN_IAMR
 	std	r5, STACK_SLOT_CIABR(r1)
-	std	r6, STACK_SLOT_DAWR(r1)
-	std	r7, STACK_SLOT_DAWRX(r1)
+	std	r6, STACK_SLOT_DAWR0(r1)
+	std	r7, STACK_SLOT_DAWRX0(r1)
 	std	r8, STACK_SLOT_IAMR(r1)
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
+BEGIN_FTR_SECTION
+	mfspr	r6, SPRN_DAWR1
+	mfspr	r7, SPRN_DAWRX1
+	std	r6, STACK_SLOT_DAWR1(r1)
+	std	r7, STACK_SLOT_DAWRX1(r1)
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S | CPU_FTR_DAWR1)
 
 	mfspr	r5, SPRN_AMR
 	std	r5, STACK_SLOT_AMR(r1)
@@ -801,10 +779,16 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
 	lbz	r5, 0(r5)
 	cmpdi	r5, 0
 	beq	1f
-	ld	r5, VCPU_DAWR(r4)
-	ld	r6, VCPU_DAWRX(r4)
+	ld	r5, VCPU_DAWR0(r4)
+	ld	r6, VCPU_DAWRX0(r4)
 	mtspr	SPRN_DAWR0, r5
 	mtspr	SPRN_DAWRX0, r6
+BEGIN_FTR_SECTION
+	ld	r5, VCPU_DAWR1(r4)
+	ld	r6, VCPU_DAWRX1(r4)
+	mtspr	SPRN_DAWR1, r5
+	mtspr	SPRN_DAWRX1, r6
+END_FTR_SECTION_IFSET(CPU_FTR_DAWR1)
 1:
 	ld	r7, VCPU_CIABR(r4)
 	ld	r8, VCPU_TAR(r4)
@@ -918,15 +902,19 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300)
 	cmpdi	r3, 512		/* 1 microsecond */
 	blt	hdec_soon
 
-	/* For hash guest, clear out and reload the SLB */
 	ld	r6, VCPU_KVM(r4)
 	lbz	r0, KVM_RADIX(r6)
 	cmpwi	r0, 0
 	bne	9f
+
+	/* For hash guest, clear out and reload the SLB */
+BEGIN_MMU_FTR_SECTION
+	/* Radix host won't have populated the SLB, so no need to clear */
 	li	r6, 0
 	slbmte	r6, r6
-	slbia
+	PPC_SLBIA(6)
 	ptesync
+END_MMU_FTR_SECTION_IFCLR(MMU_FTR_TYPE_RADIX)
 
 	/* Load up guest SLB entries (N.B. slb_max will be 0 for radix) */
 	lwz	r5,VCPU_SLB_MAX(r4)
@@ -1187,6 +1175,20 @@ EXPORT_SYMBOL_GPL(__kvmhv_vcpu_entry_p9)
 	mr	r4, r3
 	b	fast_guest_entry_c
 guest_exit_short_path:
+	/*
+	 * Malicious or buggy radix guests may have inserted SLB entries
+	 * (only 0..3 because radix always runs with UPRT=1), so these must
+	 * be cleared here to avoid side-channels. slbmte is used rather
+	 * than slbia, as it won't clear cached translations.
+	 */
+	li	r0,0
+	slbmte	r0,r0
+	li	r4,1
+	slbmte	r0,r4
+	li	r4,2
+	slbmte	r0,r4
+	li	r4,3
+	slbmte	r0,r4
 
 	li	r0, KVM_GUEST_MODE_NONE
 	stb	r0, HSTATE_IN_GUEST(r13)
@@ -1499,7 +1501,7 @@ guest_exit_cont:		/* r9 = vcpu, r12 = trap, r13 = paca */
 	lbz	r0, KVM_RADIX(r5)
 	li	r5, 0
 	cmpwi	r0, 0
-	bne	3f			/* for radix, save 0 entries */
+	bne	0f			/* for radix, save 0 entries */
 	lwz	r0,VCPU_SLB_NR(r9)	/* number of entries in SLB */
 	mtctr	r0
 	li	r6,0
@@ -1518,13 +1520,13 @@ guest_exit_cont:		/* r9 = vcpu, r12 = trap, r13 = paca */
 	/* Finally clear out the SLB */
 	li	r0,0
 	slbmte	r0,r0
-	slbia
+	PPC_SLBIA(6)
 	ptesync
-3:	stw	r5,VCPU_SLB_MAX(r9)
+	stw	r5,VCPU_SLB_MAX(r9)
 
 	/* load host SLB entries */
 BEGIN_MMU_FTR_SECTION
-	b	0f
+	b	guest_bypass
 END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_RADIX)
 	ld	r8,PACA_SLBSHADOWPTR(r13)
 
@@ -1538,7 +1540,21 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_RADIX)
 	slbmte	r6,r5
 1:	addi	r8,r8,16
 	.endr
-0:
+	b	guest_bypass
+
+0:	/*
+	 * Sanitise radix guest SLB, see guest_exit_short_path comment.
+	 * We clear vcpu->arch.slb_max to match earlier behaviour.
+	 */
+	li	r0,0
+	stw	r0,VCPU_SLB_MAX(r9)
+	slbmte	r0,r0
+	li	r4,1
+	slbmte	r0,r4
+	li	r4,2
+	slbmte	r0,r4
+	li	r4,3
+	slbmte	r0,r4
 
 guest_bypass:
 	stw	r12, STACK_SLOT_TRAP(r1)
@@ -1759,8 +1775,8 @@ END_FTR_SECTION(CPU_FTR_TM | CPU_FTR_P9_TM_HV_ASSIST, 0)
 	/* Restore host values of some registers */
 BEGIN_FTR_SECTION
 	ld	r5, STACK_SLOT_CIABR(r1)
-	ld	r6, STACK_SLOT_DAWR(r1)
-	ld	r7, STACK_SLOT_DAWRX(r1)
+	ld	r6, STACK_SLOT_DAWR0(r1)
+	ld	r7, STACK_SLOT_DAWRX0(r1)
 	mtspr	SPRN_CIABR, r5
 	/*
 	 * If the DAWR doesn't work, it's ok to write these here as
@@ -1770,6 +1786,12 @@ BEGIN_FTR_SECTION
 	mtspr	SPRN_DAWRX0, r7
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 BEGIN_FTR_SECTION
+	ld	r6, STACK_SLOT_DAWR1(r1)
+	ld	r7, STACK_SLOT_DAWRX1(r1)
+	mtspr	SPRN_DAWR1, r6
+	mtspr	SPRN_DAWRX1, r7
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S | CPU_FTR_DAWR1)
+BEGIN_FTR_SECTION
 	ld	r5, STACK_SLOT_TID(r1)
 	ld	r6, STACK_SLOT_PSSCR(r1)
 	ld	r7, STACK_SLOT_PID(r1)
@@ -1938,24 +1960,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 19:	lis	r8,0x7fff		/* MAX_INT@h */
 	mtspr	SPRN_HDEC,r8
 
-16:
-BEGIN_FTR_SECTION
-	/* On POWER9 with HPT-on-radix we need to wait for all other threads */
-	ld	r3, HSTATE_SPLIT_MODE(r13)
-	cmpdi	r3, 0
-	beq	47f
-	lwz	r8, KVM_SPLIT_DO_RESTORE(r3)
-	cmpwi	r8, 0
-	beq	47f
-	bl	kvmhv_p9_restore_lpcr
-	nop
-	b	48f
-47:
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
-	ld	r8,KVM_HOST_LPCR(r4)
+16:	ld	r8,KVM_HOST_LPCR(r4)
 	mtspr	SPRN_LPCR,r8
 	isync
-48:
+
 #ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
 	/* Finish timing, if we have a vcpu */
 	ld	r4, HSTATE_KVM_VCPU(r13)
@@ -2574,8 +2582,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 	rlwimi	r5, r4, 5, DAWRX_DR | DAWRX_DW
 	rlwimi	r5, r4, 2, DAWRX_WT
 	clrrdi	r4, r4, 3
-	std	r4, VCPU_DAWR(r3)
-	std	r5, VCPU_DAWRX(r3)
+	std	r4, VCPU_DAWR0(r3)
+	std	r5, VCPU_DAWRX0(r3)
 	/*
 	 * If came in through the real mode hcall handler then it is necessary
 	 * to write the registers since the return path won't. Otherwise it is
@@ -2779,8 +2787,10 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_ARCH_300)
 	beq	kvm_end_cede
 	cmpwi	r0, NAPPING_NOVCPU
 	beq	kvm_novcpu_wakeup
+BEGIN_FTR_SECTION
 	cmpwi	r0, NAPPING_UNSPLIT
 	beq	kvm_unsplit_wakeup
+END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
 	twi	31,0,0 /* Nap state must not be zero */
 
 33:	mr	r4, r3
@@ -3343,13 +3353,18 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
 	mtspr	SPRN_IAMR, r0
 	mtspr	SPRN_CIABR, r0
 	mtspr	SPRN_DAWRX0, r0
+BEGIN_FTR_SECTION
+	mtspr	SPRN_DAWRX1, r0
+END_FTR_SECTION_IFSET(CPU_FTR_DAWR1)
+
+	/* Clear hash and radix guest SLB, see guest_exit_short_path comment. */
+	slbmte	r0, r0
+	PPC_SLBIA(6)
 
 BEGIN_MMU_FTR_SECTION
 	b	4f
 END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_RADIX)
 
-	slbmte	r0, r0
-	slbia
 	ptesync
 	ld	r8, PACA_SLBSHADOWPTR(r13)
 	.rept	SLB_NUM_BOLTED
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index 288a9820ec01..f38ae3e54b37 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -698,7 +698,7 @@ int kvmppc_core_prepare_to_enter(struct kvm_vcpu *vcpu)
 
 		kvmppc_set_exit_type(vcpu, EMULATED_MTMSRWE_EXITS);
 		r = 1;
-	};
+	}
 
 	return r;
 }
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index cf52d26f49cd..6c083a9b3545 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -611,8 +611,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		r = !!(hv_enabled && radix_enabled());
 		break;
 	case KVM_CAP_PPC_MMU_HASH_V3:
-		r = !!(hv_enabled && cpu_has_feature(CPU_FTR_ARCH_300) &&
-		       cpu_has_feature(CPU_FTR_HVMODE));
+		r = !!(hv_enabled && kvmppc_hv_ops->hash_v3_possible &&
+		       kvmppc_hv_ops->hash_v3_possible());
 		break;
 	case KVM_CAP_PPC_NESTED_HV:
 		r = !!(hv_enabled && kvmppc_hv_ops->enable_nested &&
@@ -678,6 +678,10 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		r = hv_enabled && kvmppc_hv_ops->enable_svm &&
 			!kvmppc_hv_ops->enable_svm(NULL);
 		break;
+	case KVM_CAP_PPC_DAWR1:
+		r = !!(hv_enabled && kvmppc_hv_ops->enable_dawr1 &&
+		       !kvmppc_hv_ops->enable_dawr1(NULL));
+		break;
 #endif
 	default:
 		r = 0;
@@ -2187,6 +2191,12 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
 			break;
 		r = kvm->arch.kvm_ops->enable_svm(kvm);
 		break;
+	case KVM_CAP_PPC_DAWR1:
+		r = -EINVAL;
+		if (!is_kvmppc_hv_enabled(kvm) || !kvm->arch.kvm_ops->enable_dawr1)
+			break;
+		r = kvm->arch.kvm_ops->enable_dawr1(kvm);
+		break;
 #endif
 	default:
 		r = -EINVAL;