Merge branch 'topic/ppc-kvm' into next

Merge our KVM topic branch, this has been independently included in linux-next
for most of the development cycle.

Documentation/powerpc/index.rst

@@ -26,6 +26,7 @@ powerpc
     isa-versions
     kaslr-booke32
     mpc52xx
+    kvm-nested
     papr_hcalls
     pci_iov_resource_on_powernv
     pmu-ebb

arch/powerpc/Kconfig.debug

@@ -82,6 +82,18 @@ config MSI_BITMAP_SELFTEST
 	bool "Run self-tests of the MSI bitmap code"
 	depends on DEBUG_KERNEL
 
+config GUEST_STATE_BUFFER_TEST
+	def_tristate n
+	prompt "Enable Guest State Buffer unit tests"
+	depends on KUNIT
+	depends on KVM_BOOK3S_HV_POSSIBLE
+	default KUNIT_ALL_TESTS
+	help
+	  The Guest State Buffer is a data format specified in the PAPR.
+	  It is by hcalls to communicate the state of L2 guests between
+	  the L1 and L0 hypervisors. Enable unit tests for the library
+	  used to create and use guest state buffers.
+
 config PPC_IRQ_SOFT_MASK_DEBUG
 	bool "Include extra checks for powerpc irq soft masking"
 	depends on PPC64

arch/powerpc/include/asm/hvcall.h

@@ -100,6 +100,18 @@
 #define H_COP_HW	-74
 #define H_STATE		-75
 #define H_IN_USE	-77
+
+#define H_INVALID_ELEMENT_ID			-79
+#define H_INVALID_ELEMENT_SIZE			-80
+#define H_INVALID_ELEMENT_VALUE			-81
+#define H_INPUT_BUFFER_NOT_DEFINED		-82
+#define H_INPUT_BUFFER_TOO_SMALL		-83
+#define H_OUTPUT_BUFFER_NOT_DEFINED		-84
+#define H_OUTPUT_BUFFER_TOO_SMALL		-85
+#define H_PARTITION_PAGE_TABLE_NOT_DEFINED	-86
+#define H_GUEST_VCPU_STATE_NOT_HV_OWNED		-87
+
+
 #define H_UNSUPPORTED_FLAG_START	-256
 #define H_UNSUPPORTED_FLAG_END		-511
 #define H_MULTI_THREADS_ACTIVE	-9005
@@ -381,6 +393,15 @@
 #define H_ENTER_NESTED		0xF804
 #define H_TLB_INVALIDATE	0xF808
 #define H_COPY_TOFROM_GUEST	0xF80C
+#define H_GUEST_GET_CAPABILITIES 0x460
+#define H_GUEST_SET_CAPABILITIES 0x464
+#define H_GUEST_CREATE		0x470
+#define H_GUEST_CREATE_VCPU	0x474
+#define H_GUEST_GET_STATE	0x478
+#define H_GUEST_SET_STATE	0x47C
+#define H_GUEST_RUN_VCPU	0x480
+#define H_GUEST_COPY_MEMORY	0x484
+#define H_GUEST_DELETE		0x488
 
 /* Flags for H_SVM_PAGE_IN */
 #define H_PAGE_IN_SHARED        0x1
@@ -467,6 +488,15 @@
 #define H_RPTI_PAGE_1G	0x08
 #define H_RPTI_PAGE_ALL (-1UL)
 
+/* Flags for H_GUEST_{S,G}_STATE */
+#define H_GUEST_FLAGS_WIDE     (1UL<<(63-0))
+
+/* Flag values used for H_{S,G}SET_GUEST_CAPABILITIES */
+#define H_GUEST_CAP_COPY_MEM	(1UL<<(63-0))
+#define H_GUEST_CAP_POWER9	(1UL<<(63-1))
+#define H_GUEST_CAP_POWER10	(1UL<<(63-2))
+#define H_GUEST_CAP_BITMAP2	(1UL<<(63-63))
+
 #ifndef __ASSEMBLY__
 #include <linux/types.h>
 

arch/powerpc/include/asm/kvm_book3s_64.h

@@ -624,7 +624,7 @@ static inline void copy_to_checkpoint(struct kvm_vcpu *vcpu)
 
 extern int kvmppc_create_pte(struct kvm *kvm, pgd_t *pgtable, pte_t pte,
 			     unsigned long gpa, unsigned int level,
-			     unsigned long mmu_seq, unsigned int lpid,
+			     unsigned long mmu_seq, u64 lpid,
 			     unsigned long *rmapp, struct rmap_nested **n_rmap);
 extern void kvmhv_insert_nest_rmap(struct kvm *kvm, unsigned long *rmapp,
 				   struct rmap_nested **n_rmap);
@@ -677,6 +677,12 @@ static inline pte_t *find_kvm_host_pte(struct kvm *kvm, unsigned long mmu_seq,
 extern pte_t *find_kvm_nested_guest_pte(struct kvm *kvm, unsigned long lpid,
 					unsigned long ea, unsigned *hshift);
 
+int kvmhv_nestedv2_vcpu_create(struct kvm_vcpu *vcpu, struct kvmhv_nestedv2_io *io);
+void kvmhv_nestedv2_vcpu_free(struct kvm_vcpu *vcpu, struct kvmhv_nestedv2_io *io);
+int kvmhv_nestedv2_flush_vcpu(struct kvm_vcpu *vcpu, u64 time_limit);
+int kvmhv_nestedv2_set_ptbl_entry(unsigned long lpid, u64 dw0, u64 dw1);
+int kvmhv_nestedv2_parse_output(struct kvm_vcpu *vcpu);
+
 #endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */
 
 #endif /* __ASM_KVM_BOOK3S_64_H__ */

arch/powerpc/include/asm/kvm_booke.h

@@ -89,6 +89,16 @@ static inline ulong kvmppc_get_pc(struct kvm_vcpu *vcpu)
 	return vcpu->arch.regs.nip;
 }
 
+static inline void kvmppc_set_fpr(struct kvm_vcpu *vcpu, int i, u64 val)
+{
+	vcpu->arch.fp.fpr[i][TS_FPROFFSET] = val;
+}
+
+static inline u64 kvmppc_get_fpr(struct kvm_vcpu *vcpu, int i)
+{
+	return vcpu->arch.fp.fpr[i][TS_FPROFFSET];
+}
+
 #ifdef CONFIG_BOOKE
 static inline ulong kvmppc_get_fault_dar(struct kvm_vcpu *vcpu)
 {

arch/powerpc/include/asm/kvm_host.h

@@ -25,6 +25,7 @@
 #include <asm/cacheflush.h>
 #include <asm/hvcall.h>
 #include <asm/mce.h>
+#include <asm/guest-state-buffer.h>
 
 #define __KVM_HAVE_ARCH_VCPU_DEBUGFS
 
@@ -276,7 +277,7 @@ struct kvm_resize_hpt;
 #define KVMPPC_SECURE_INIT_ABORT 0x4 /* H_SVM_INIT_ABORT issued */
 
 struct kvm_arch {
-	unsigned int lpid;
+	u64 lpid;
 	unsigned int smt_mode;		/* # vcpus per virtual core */
 	unsigned int emul_smt_mode;	/* emualted SMT mode, on P9 */
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
@@ -509,6 +510,23 @@ union xive_tma_w01 {
 	__be64 w01;
 };
 
+ /* Nestedv2 H_GUEST_RUN_VCPU configuration */
+struct kvmhv_nestedv2_config {
+	struct kvmppc_gs_buff_info vcpu_run_output_cfg;
+	struct kvmppc_gs_buff_info vcpu_run_input_cfg;
+	u64 vcpu_run_output_size;
+};
+
+ /* Nestedv2 L1<->L0 communication state */
+struct kvmhv_nestedv2_io {
+	struct kvmhv_nestedv2_config cfg;
+	struct kvmppc_gs_buff *vcpu_run_output;
+	struct kvmppc_gs_buff *vcpu_run_input;
+	struct kvmppc_gs_msg *vcpu_message;
+	struct kvmppc_gs_msg *vcore_message;
+	struct kvmppc_gs_bitmap valids;
+};
+
 struct kvm_vcpu_arch {
 	ulong host_stack;
 	u32 host_pid;
@@ -829,6 +847,8 @@ struct kvm_vcpu_arch {
 	u64 nested_hfscr;	/* HFSCR that the L1 requested for the nested guest */
 	u32 nested_vcpu_id;
 	gpa_t nested_io_gpr;
+	/* For nested APIv2 guests*/
+	struct kvmhv_nestedv2_io nestedv2_io;
 #endif
 
 #ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING

arch/powerpc/include/asm/kvm_ppc.h

@@ -615,6 +615,42 @@ static inline bool kvmhv_on_pseries(void)
 {
 	return false;
 }
+
+#endif
+
+#ifndef CONFIG_PPC_BOOK3S
+
+static inline bool kvmhv_is_nestedv2(void)
+{
+	return false;
+}
+
+static inline bool kvmhv_is_nestedv1(void)
+{
+	return false;
+}
+
+static inline int kvmhv_nestedv2_reload_ptregs(struct kvm_vcpu *vcpu,
+					       struct pt_regs *regs)
+{
+	return 0;
+}
+static inline int kvmhv_nestedv2_mark_dirty_ptregs(struct kvm_vcpu *vcpu,
+						   struct pt_regs *regs)
+{
+	return 0;
+}
+
+static inline int kvmhv_nestedv2_mark_dirty(struct kvm_vcpu *vcpu, u16 iden)
+{
+	return 0;
+}
+
+static inline int kvmhv_nestedv2_cached_reload(struct kvm_vcpu *vcpu, u16 iden)
+{
+	return 0;
+}
+
 #endif
 
 #ifdef CONFIG_KVM_XICS
@@ -927,79 +963,85 @@ static inline bool kvmppc_shared_big_endian(struct kvm_vcpu *vcpu)
 #endif
 }
 
-#define SPRNG_WRAPPER_GET(reg, bookehv_spr)				\
+#define KVMPPC_BOOKE_HV_SPRNG_ACCESSOR_GET(reg, bookehv_spr)		\
 static inline ulong kvmppc_get_##reg(struct kvm_vcpu *vcpu)		\
 {									\
 	return mfspr(bookehv_spr);					\
 }									\
 
-#define SPRNG_WRAPPER_SET(reg, bookehv_spr)				\
+#define KVMPPC_BOOKE_HV_SPRNG_ACCESSOR_SET(reg, bookehv_spr)		\
 static inline void kvmppc_set_##reg(struct kvm_vcpu *vcpu, ulong val)	\
 {									\
 	mtspr(bookehv_spr, val);						\
 }									\
 
-#define SHARED_WRAPPER_GET(reg, size)					\
+#define KVMPPC_VCPU_SHARED_REGS_ACCESSOR_GET(reg, size, iden)		\
 static inline u##size kvmppc_get_##reg(struct kvm_vcpu *vcpu)		\
 {									\
+	if (iden)							\
+		WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, iden) < 0);	\
 	if (kvmppc_shared_big_endian(vcpu))				\
-	       return be##size##_to_cpu(vcpu->arch.shared->reg);	\
+		return be##size##_to_cpu((__be##size __force)vcpu->arch.shared->reg);	\
 	else								\
-	       return le##size##_to_cpu(vcpu->arch.shared->reg);	\
+		return le##size##_to_cpu((__le##size __force)vcpu->arch.shared->reg);	\
 }									\
 
-#define SHARED_WRAPPER_SET(reg, size)					\
+#define KVMPPC_VCPU_SHARED_REGS_ACCESSOR_SET(reg, size, iden)		\
 static inline void kvmppc_set_##reg(struct kvm_vcpu *vcpu, u##size val)	\
 {									\
 	if (kvmppc_shared_big_endian(vcpu))				\
-	       vcpu->arch.shared->reg = cpu_to_be##size(val);		\
+		vcpu->arch.shared->reg = (u##size __force)cpu_to_be##size(val);	\
 	else								\
-	       vcpu->arch.shared->reg = cpu_to_le##size(val);		\
+		vcpu->arch.shared->reg = (u##size __force)cpu_to_le##size(val);	\
+									\
+	if (iden)							\
+		kvmhv_nestedv2_mark_dirty(vcpu, iden);			\
 }									\
 
-#define SHARED_WRAPPER(reg, size)					\
-	SHARED_WRAPPER_GET(reg, size)					\
-	SHARED_WRAPPER_SET(reg, size)					\
+#define KVMPPC_VCPU_SHARED_REGS_ACCESSOR(reg, size, iden)		\
+	KVMPPC_VCPU_SHARED_REGS_ACCESSOR_GET(reg, size, iden)		\
+	KVMPPC_VCPU_SHARED_REGS_ACCESSOR_SET(reg, size, iden)		\
 
-#define SPRNG_WRAPPER(reg, bookehv_spr)					\
-	SPRNG_WRAPPER_GET(reg, bookehv_spr)				\
-	SPRNG_WRAPPER_SET(reg, bookehv_spr)				\
+#define KVMPPC_BOOKE_HV_SPRNG_ACCESSOR(reg, bookehv_spr)		\
+	KVMPPC_BOOKE_HV_SPRNG_ACCESSOR_GET(reg, bookehv_spr)		\
+	KVMPPC_BOOKE_HV_SPRNG_ACCESSOR_SET(reg, bookehv_spr)		\
 
 #ifdef CONFIG_KVM_BOOKE_HV
 
-#define SHARED_SPRNG_WRAPPER(reg, size, bookehv_spr)			\
-	SPRNG_WRAPPER(reg, bookehv_spr)					\
+#define KVMPPC_BOOKE_HV_SPRNG_OR_VCPU_SHARED_REGS_ACCESSOR(reg, size, bookehv_spr, iden)	\
+	KVMPPC_BOOKE_HV_SPRNG_ACCESSOR(reg, bookehv_spr)		\
 
 #else
 
-#define SHARED_SPRNG_WRAPPER(reg, size, bookehv_spr)			\
-	SHARED_WRAPPER(reg, size)					\
+#define KVMPPC_BOOKE_HV_SPRNG_OR_VCPU_SHARED_REGS_ACCESSOR(reg, size, bookehv_spr, iden)	\
+	KVMPPC_VCPU_SHARED_REGS_ACCESSOR(reg, size, iden)		\
 
 #endif
 
-SHARED_WRAPPER(critical, 64)
-SHARED_SPRNG_WRAPPER(sprg0, 64, SPRN_GSPRG0)
-SHARED_SPRNG_WRAPPER(sprg1, 64, SPRN_GSPRG1)
-SHARED_SPRNG_WRAPPER(sprg2, 64, SPRN_GSPRG2)
-SHARED_SPRNG_WRAPPER(sprg3, 64, SPRN_GSPRG3)
-SHARED_SPRNG_WRAPPER(srr0, 64, SPRN_GSRR0)
-SHARED_SPRNG_WRAPPER(srr1, 64, SPRN_GSRR1)
-SHARED_SPRNG_WRAPPER(dar, 64, SPRN_GDEAR)
-SHARED_SPRNG_WRAPPER(esr, 64, SPRN_GESR)
-SHARED_WRAPPER_GET(msr, 64)
+KVMPPC_VCPU_SHARED_REGS_ACCESSOR(critical, 64, 0)
+KVMPPC_BOOKE_HV_SPRNG_OR_VCPU_SHARED_REGS_ACCESSOR(sprg0, 64, SPRN_GSPRG0, KVMPPC_GSID_SPRG0)
+KVMPPC_BOOKE_HV_SPRNG_OR_VCPU_SHARED_REGS_ACCESSOR(sprg1, 64, SPRN_GSPRG1, KVMPPC_GSID_SPRG1)
+KVMPPC_BOOKE_HV_SPRNG_OR_VCPU_SHARED_REGS_ACCESSOR(sprg2, 64, SPRN_GSPRG2, KVMPPC_GSID_SPRG2)
+KVMPPC_BOOKE_HV_SPRNG_OR_VCPU_SHARED_REGS_ACCESSOR(sprg3, 64, SPRN_GSPRG3, KVMPPC_GSID_SPRG3)
+KVMPPC_BOOKE_HV_SPRNG_OR_VCPU_SHARED_REGS_ACCESSOR(srr0, 64, SPRN_GSRR0, KVMPPC_GSID_SRR0)
+KVMPPC_BOOKE_HV_SPRNG_OR_VCPU_SHARED_REGS_ACCESSOR(srr1, 64, SPRN_GSRR1, KVMPPC_GSID_SRR1)
+KVMPPC_BOOKE_HV_SPRNG_OR_VCPU_SHARED_REGS_ACCESSOR(dar, 64, SPRN_GDEAR, KVMPPC_GSID_DAR)
+KVMPPC_BOOKE_HV_SPRNG_OR_VCPU_SHARED_REGS_ACCESSOR(esr, 64, SPRN_GESR, 0)
+KVMPPC_VCPU_SHARED_REGS_ACCESSOR_GET(msr, 64, KVMPPC_GSID_MSR)
 static inline void kvmppc_set_msr_fast(struct kvm_vcpu *vcpu, u64 val)
 {
 	if (kvmppc_shared_big_endian(vcpu))
 	       vcpu->arch.shared->msr = cpu_to_be64(val);
 	else
 	       vcpu->arch.shared->msr = cpu_to_le64(val);
+	kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_MSR);
 }
-SHARED_WRAPPER(dsisr, 32)
-SHARED_WRAPPER(int_pending, 32)
-SHARED_WRAPPER(sprg4, 64)
-SHARED_WRAPPER(sprg5, 64)
-SHARED_WRAPPER(sprg6, 64)
-SHARED_WRAPPER(sprg7, 64)
+KVMPPC_VCPU_SHARED_REGS_ACCESSOR(dsisr, 32, KVMPPC_GSID_DSISR)
+KVMPPC_VCPU_SHARED_REGS_ACCESSOR(int_pending, 32, 0)
+KVMPPC_VCPU_SHARED_REGS_ACCESSOR(sprg4, 64, 0)
+KVMPPC_VCPU_SHARED_REGS_ACCESSOR(sprg5, 64, 0)
+KVMPPC_VCPU_SHARED_REGS_ACCESSOR(sprg6, 64, 0)
+KVMPPC_VCPU_SHARED_REGS_ACCESSOR(sprg7, 64, 0)
 
 static inline u32 kvmppc_get_sr(struct kvm_vcpu *vcpu, int nr)
 {

arch/powerpc/include/asm/plpar_wrappers.h

@@ -6,6 +6,7 @@
 
 #include <linux/string.h>
 #include <linux/irqflags.h>
+#include <linux/delay.h>
 
 #include <asm/hvcall.h>
 #include <asm/paca.h>
@@ -343,6 +344,212 @@ static inline long plpar_get_cpu_characteristics(struct h_cpu_char_result *p)
 	return rc;
 }
 
+static inline long plpar_guest_create(unsigned long flags, unsigned long *guest_id)
+{
+	unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
+	unsigned long token;
+	long rc;
+
+	token = -1UL;
+	do {
+		rc = plpar_hcall(H_GUEST_CREATE, retbuf, flags, token);
+		if (rc == H_SUCCESS)
+			*guest_id = retbuf[0];
+
+		if (rc == H_BUSY) {
+			token = retbuf[0];
+			cond_resched();
+		}
+
+		if (H_IS_LONG_BUSY(rc)) {
+			token = retbuf[0];
+			msleep(get_longbusy_msecs(rc));
+			rc = H_BUSY;
+		}
+
+	} while (rc == H_BUSY);
+
+	return rc;
+}
+
+static inline long plpar_guest_create_vcpu(unsigned long flags,
+					   unsigned long guest_id,
+					   unsigned long vcpu_id)
+{
+	long rc;
+
+	do {
+		rc = plpar_hcall_norets(H_GUEST_CREATE_VCPU, 0, guest_id, vcpu_id);
+
+		if (rc == H_BUSY)
+			cond_resched();
+
+		if (H_IS_LONG_BUSY(rc)) {
+			msleep(get_longbusy_msecs(rc));
+			rc = H_BUSY;
+		}
+
+	} while (rc == H_BUSY);
+
+	return rc;
+}
+
+static inline long plpar_guest_set_state(unsigned long flags,
+					 unsigned long guest_id,
+					 unsigned long vcpu_id,
+					 unsigned long data_buffer,
+					 unsigned long data_size,
+					 unsigned long *failed_index)
+{
+	unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
+	long rc;
+
+	while (true) {
+		rc = plpar_hcall(H_GUEST_SET_STATE, retbuf, flags, guest_id,
+				 vcpu_id, data_buffer, data_size);
+
+		if (rc == H_BUSY) {
+			cpu_relax();
+			continue;
+		}
+
+		if (H_IS_LONG_BUSY(rc)) {
+			mdelay(get_longbusy_msecs(rc));
+			continue;
+		}
+
+		if (rc == H_INVALID_ELEMENT_ID)
+			*failed_index = retbuf[0];
+		else if (rc == H_INVALID_ELEMENT_SIZE)
+			*failed_index = retbuf[0];
+		else if (rc == H_INVALID_ELEMENT_VALUE)
+			*failed_index = retbuf[0];
+
+		break;
+	}
+
+	return rc;
+}
+
+static inline long plpar_guest_get_state(unsigned long flags,
+					 unsigned long guest_id,
+					 unsigned long vcpu_id,
+					 unsigned long data_buffer,
+					 unsigned long data_size,
+					 unsigned long *failed_index)
+{
+	unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
+	long rc;
+
+	while (true) {
+		rc = plpar_hcall(H_GUEST_GET_STATE, retbuf, flags, guest_id,
+				 vcpu_id, data_buffer, data_size);
+
+		if (rc == H_BUSY) {
+			cpu_relax();
+			continue;
+		}
+
+		if (H_IS_LONG_BUSY(rc)) {
+			mdelay(get_longbusy_msecs(rc));
+			continue;
+		}
+
+		if (rc == H_INVALID_ELEMENT_ID)
+			*failed_index = retbuf[0];
+		else if (rc == H_INVALID_ELEMENT_SIZE)
+			*failed_index = retbuf[0];
+		else if (rc == H_INVALID_ELEMENT_VALUE)
+			*failed_index = retbuf[0];
+
+		break;
+	}
+
+	return rc;
+}
+
+static inline long plpar_guest_run_vcpu(unsigned long flags, unsigned long guest_id,
+					unsigned long vcpu_id, int *trap,
+					unsigned long *failed_index)
+{
+	unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
+	long rc;
+
+	rc = plpar_hcall(H_GUEST_RUN_VCPU, retbuf, flags, guest_id, vcpu_id);
+	if (rc == H_SUCCESS)
+		*trap = retbuf[0];
+	else if (rc == H_INVALID_ELEMENT_ID)
+		*failed_index = retbuf[0];
+	else if (rc == H_INVALID_ELEMENT_SIZE)
+		*failed_index = retbuf[0];
+	else if (rc == H_INVALID_ELEMENT_VALUE)
+		*failed_index = retbuf[0];
+
+	return rc;
+}
+
+static inline long plpar_guest_delete(unsigned long flags, u64 guest_id)
+{
+	long rc;
+
+	do {
+		rc = plpar_hcall_norets(H_GUEST_DELETE, flags, guest_id);
+		if (rc == H_BUSY)
+			cond_resched();
+
+		if (H_IS_LONG_BUSY(rc)) {
+			msleep(get_longbusy_msecs(rc));
+			rc = H_BUSY;
+		}
+
+	} while (rc == H_BUSY);
+
+	return rc;
+}
+
+static inline long plpar_guest_set_capabilities(unsigned long flags,
+						unsigned long capabilities)
+{
+	unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
+	long rc;
+
+	do {
+		rc = plpar_hcall(H_GUEST_SET_CAPABILITIES, retbuf, flags, capabilities);
+		if (rc == H_BUSY)
+			cond_resched();
+
+		if (H_IS_LONG_BUSY(rc)) {
+			msleep(get_longbusy_msecs(rc));
+			rc = H_BUSY;
+		}
+	} while (rc == H_BUSY);
+
+	return rc;
+}
+
+static inline long plpar_guest_get_capabilities(unsigned long flags,
+						unsigned long *capabilities)
+{
+	unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
+	long rc;
+
+	do {
+		rc = plpar_hcall(H_GUEST_GET_CAPABILITIES, retbuf, flags);
+		if (rc == H_BUSY)
+			cond_resched();
+
+		if (H_IS_LONG_BUSY(rc)) {
+			msleep(get_longbusy_msecs(rc));
+			rc = H_BUSY;
+		}
+	} while (rc == H_BUSY);
+
+	if (rc == H_SUCCESS)
+		*capabilities = retbuf[0];
+
+	return rc;
+}
+
 /*
  * Wrapper to H_RPT_INVALIDATE hcall that handles return values appropriately
  *
@@ -355,7 +562,7 @@ static inline long plpar_get_cpu_characteristics(struct h_cpu_char_result *p)
  * error recovery of killing the process/guest will be eventually
  * needed.
  */
-static inline long pseries_rpt_invalidate(u32 pid, u64 target, u64 type,
+static inline long pseries_rpt_invalidate(u64 pid, u64 target, u64 type,
 					  u64 page_sizes, u64 start, u64 end)
 {
 	long rc;
@@ -401,12 +608,68 @@ static inline long plpar_pte_read_4(unsigned long flags, unsigned long ptex,
 	return 0;
 }
 
-static inline long pseries_rpt_invalidate(u32 pid, u64 target, u64 type,
+static inline long pseries_rpt_invalidate(u64 pid, u64 target, u64 type,
 					  u64 page_sizes, u64 start, u64 end)
 {
 	return 0;
 }
 
+static inline long plpar_guest_create_vcpu(unsigned long flags,
+					   unsigned long guest_id,
+					   unsigned long vcpu_id)
+{
+	return 0;
+}
+
+static inline long plpar_guest_get_state(unsigned long flags,
+					 unsigned long guest_id,
+					 unsigned long vcpu_id,
+					 unsigned long data_buffer,
+					 unsigned long data_size,
+					 unsigned long *failed_index)
+{
+	return 0;
+}
+
+static inline long plpar_guest_set_state(unsigned long flags,
+					 unsigned long guest_id,
+					 unsigned long vcpu_id,
+					 unsigned long data_buffer,
+					 unsigned long data_size,
+					 unsigned long *failed_index)
+{
+	return 0;
+}
+
+static inline long plpar_guest_run_vcpu(unsigned long flags, unsigned long guest_id,
+					unsigned long vcpu_id, int *trap,
+					unsigned long *failed_index)
+{
+	return 0;
+}
+
+static inline long plpar_guest_create(unsigned long flags, unsigned long *guest_id)
+{
+	return 0;
+}
+
+static inline long plpar_guest_delete(unsigned long flags, u64 guest_id)
+{
+	return 0;
+}
+
+static inline long plpar_guest_get_capabilities(unsigned long flags,
+						unsigned long *capabilities)
+{
+	return 0;
+}
+
+static inline long plpar_guest_set_capabilities(unsigned long flags,
+						unsigned long capabilities)
+{
+	return 0;
+}
+
 #endif /* CONFIG_PPC_PSERIES */
 
 #endif /* _ASM_POWERPC_PLPAR_WRAPPERS_H */

arch/powerpc/kvm/Makefile

@@ -87,8 +87,12 @@ kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HANDLER) += \
 	book3s_hv_ras.o \
 	book3s_hv_builtin.o \
 	book3s_hv_p9_perf.o \
+	book3s_hv_nestedv2.o \
+	guest-state-buffer.o \
 	$(kvm-book3s_64-builtin-tm-objs-y) \
 	$(kvm-book3s_64-builtin-xics-objs-y)
+
+obj-$(CONFIG_GUEST_STATE_BUFFER_TEST) += test-guest-state-buffer.o
 endif
 
 kvm-book3s_64-objs-$(CONFIG_KVM_XICS) += \

arch/powerpc/kvm/book3s.c

@@ -565,7 +565,7 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 	regs->msr = kvmppc_get_msr(vcpu);
 	regs->srr0 = kvmppc_get_srr0(vcpu);
 	regs->srr1 = kvmppc_get_srr1(vcpu);
-	regs->pid = vcpu->arch.pid;
+	regs->pid = kvmppc_get_pid(vcpu);
 	regs->sprg0 = kvmppc_get_sprg0(vcpu);
 	regs->sprg1 = kvmppc_get_sprg1(vcpu);
 	regs->sprg2 = kvmppc_get_sprg2(vcpu);
@@ -636,17 +636,17 @@ int kvmppc_get_one_reg(struct kvm_vcpu *vcpu, u64 id,
 			break;
 		case KVM_REG_PPC_FPR0 ... KVM_REG_PPC_FPR31:
 			i = id - KVM_REG_PPC_FPR0;
-			*val = get_reg_val(id, VCPU_FPR(vcpu, i));
+			*val = get_reg_val(id, kvmppc_get_fpr(vcpu, i));
 			break;
 		case KVM_REG_PPC_FPSCR:
-			*val = get_reg_val(id, vcpu->arch.fp.fpscr);
+			*val = get_reg_val(id, kvmppc_get_fpscr(vcpu));
 			break;
 #ifdef CONFIG_VSX
 		case KVM_REG_PPC_VSR0 ... KVM_REG_PPC_VSR31:
 			if (cpu_has_feature(CPU_FTR_VSX)) {
 				i = id - KVM_REG_PPC_VSR0;
-				val->vsxval[0] = vcpu->arch.fp.fpr[i][0];
-				val->vsxval[1] = vcpu->arch.fp.fpr[i][1];
+				val->vsxval[0] = kvmppc_get_vsx_fpr(vcpu, i, 0);
+				val->vsxval[1] = kvmppc_get_vsx_fpr(vcpu, i, 1);
 			} else {
 				r = -ENXIO;
 			}
@@ -683,19 +683,19 @@ int kvmppc_get_one_reg(struct kvm_vcpu *vcpu, u64 id,
 			*val = get_reg_val(id, vcpu->arch.fscr);
 			break;
 		case KVM_REG_PPC_TAR:
-			*val = get_reg_val(id, vcpu->arch.tar);
+			*val = get_reg_val(id, kvmppc_get_tar(vcpu));
 			break;
 		case KVM_REG_PPC_EBBHR:
-			*val = get_reg_val(id, vcpu->arch.ebbhr);
+			*val = get_reg_val(id, kvmppc_get_ebbhr(vcpu));
 			break;
 		case KVM_REG_PPC_EBBRR:
-			*val = get_reg_val(id, vcpu->arch.ebbrr);
+			*val = get_reg_val(id, kvmppc_get_ebbrr(vcpu));
 			break;
 		case KVM_REG_PPC_BESCR:
-			*val = get_reg_val(id, vcpu->arch.bescr);
+			*val = get_reg_val(id, kvmppc_get_bescr(vcpu));
 			break;
 		case KVM_REG_PPC_IC:
-			*val = get_reg_val(id, vcpu->arch.ic);
+			*val = get_reg_val(id, kvmppc_get_ic(vcpu));
 			break;
 		default:
 			r = -EINVAL;
@@ -724,7 +724,7 @@ int kvmppc_set_one_reg(struct kvm_vcpu *vcpu, u64 id,
 			break;
 		case KVM_REG_PPC_FPR0 ... KVM_REG_PPC_FPR31:
 			i = id - KVM_REG_PPC_FPR0;
-			VCPU_FPR(vcpu, i) = set_reg_val(id, *val);
+			kvmppc_set_fpr(vcpu, i, set_reg_val(id, *val));
 			break;
 		case KVM_REG_PPC_FPSCR:
 			vcpu->arch.fp.fpscr = set_reg_val(id, *val);
@@ -733,8 +733,8 @@ int kvmppc_set_one_reg(struct kvm_vcpu *vcpu, u64 id,
 		case KVM_REG_PPC_VSR0 ... KVM_REG_PPC_VSR31:
 			if (cpu_has_feature(CPU_FTR_VSX)) {
 				i = id - KVM_REG_PPC_VSR0;
-				vcpu->arch.fp.fpr[i][0] = val->vsxval[0];
-				vcpu->arch.fp.fpr[i][1] = val->vsxval[1];
+				kvmppc_set_vsx_fpr(vcpu, i, 0, val->vsxval[0]);
+				kvmppc_set_vsx_fpr(vcpu, i, 1, val->vsxval[1]);
 			} else {
 				r = -ENXIO;
 			}
@@ -765,22 +765,22 @@ int kvmppc_set_one_reg(struct kvm_vcpu *vcpu, u64 id,
 			break;
 #endif /* CONFIG_KVM_XIVE */
 		case KVM_REG_PPC_FSCR:
-			vcpu->arch.fscr = set_reg_val(id, *val);
+			kvmppc_set_fpscr(vcpu, set_reg_val(id, *val));
 			break;
 		case KVM_REG_PPC_TAR:
-			vcpu->arch.tar = set_reg_val(id, *val);
+			kvmppc_set_tar(vcpu, set_reg_val(id, *val));
 			break;
 		case KVM_REG_PPC_EBBHR:
-			vcpu->arch.ebbhr = set_reg_val(id, *val);
+			kvmppc_set_ebbhr(vcpu, set_reg_val(id, *val));
 			break;
 		case KVM_REG_PPC_EBBRR:
-			vcpu->arch.ebbrr = set_reg_val(id, *val);
+			kvmppc_set_ebbrr(vcpu, set_reg_val(id, *val));
 			break;
 		case KVM_REG_PPC_BESCR:
-			vcpu->arch.bescr = set_reg_val(id, *val);
+			kvmppc_set_bescr(vcpu, set_reg_val(id, *val));
 			break;
 		case KVM_REG_PPC_IC:
-			vcpu->arch.ic = set_reg_val(id, *val);
+			kvmppc_set_ic(vcpu, set_reg_val(id, *val));
 			break;
 		default:
 			r = -EINVAL;

arch/powerpc/kvm/book3s_64_mmu_hv.c

@@ -28,6 +28,7 @@
 #include <asm/pte-walk.h>
 
 #include "book3s.h"
+#include "book3s_hv.h"
 #include "trace_hv.h"
 
 //#define DEBUG_RESIZE_HPT	1
@@ -120,7 +121,7 @@ void kvmppc_set_hpt(struct kvm *kvm, struct kvm_hpt_info *info)
 	kvm->arch.hpt = *info;
 	kvm->arch.sdr1 = __pa(info->virt) | (info->order - 18);
 
-	pr_debug("KVM guest htab at %lx (order %ld), LPID %x\n",
+	pr_debug("KVM guest htab at %lx (order %ld), LPID %llx\n",
 		 info->virt, (long)info->order, kvm->arch.lpid);
 }
 
@@ -347,7 +348,7 @@ static int kvmppc_mmu_book3s_64_hv_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 	unsigned long v, orig_v, gr;
 	__be64 *hptep;
 	long int index;
-	int virtmode = vcpu->arch.shregs.msr & (data ? MSR_DR : MSR_IR);
+	int virtmode = __kvmppc_get_msr_hv(vcpu) & (data ? MSR_DR : MSR_IR);
 
 	if (kvm_is_radix(vcpu->kvm))
 		return kvmppc_mmu_radix_xlate(vcpu, eaddr, gpte, data, iswrite);
@@ -385,7 +386,7 @@ static int kvmppc_mmu_book3s_64_hv_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 
 	/* Get PP bits and key for permission check */
 	pp = gr & (HPTE_R_PP0 | HPTE_R_PP);
-	key = (vcpu->arch.shregs.msr & MSR_PR) ? SLB_VSID_KP : SLB_VSID_KS;
+	key = (__kvmppc_get_msr_hv(vcpu) & MSR_PR) ? SLB_VSID_KP : SLB_VSID_KS;
 	key &= slb_v;
 
 	/* Calculate permissions */

arch/powerpc/kvm/book3s_64_mmu_radix.c

@@ -15,6 +15,7 @@
 
 #include <asm/kvm_ppc.h>
 #include <asm/kvm_book3s.h>
+#include "book3s_hv.h"
 #include <asm/page.h>
 #include <asm/mmu.h>
 #include <asm/pgalloc.h>
@@ -96,7 +97,7 @@ static long kvmhv_copy_tofrom_guest_radix(struct kvm_vcpu *vcpu, gva_t eaddr,
 					  void *to, void *from, unsigned long n)
 {
 	int lpid = vcpu->kvm->arch.lpid;
-	int pid = vcpu->arch.pid;
+	int pid = kvmppc_get_pid(vcpu);
 
 	/* This would cause a data segment intr so don't allow the access */
 	if (eaddr & (0x3FFUL << 52))
@@ -270,7 +271,7 @@ int kvmppc_mmu_radix_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 	/* Work out effective PID */
 	switch (eaddr >> 62) {
 	case 0:
-		pid = vcpu->arch.pid;
+		pid = kvmppc_get_pid(vcpu);
 		break;
 	case 3:
 		pid = 0;
@@ -294,9 +295,9 @@ int kvmppc_mmu_radix_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 	} else {
 		if (!(pte & _PAGE_PRIVILEGED)) {
 			/* Check AMR/IAMR to see if strict mode is in force */
-			if (vcpu->arch.amr & (1ul << 62))
+			if (kvmppc_get_amr_hv(vcpu) & (1ul << 62))
 				gpte->may_read = 0;
-			if (vcpu->arch.amr & (1ul << 63))
+			if (kvmppc_get_amr_hv(vcpu) & (1ul << 63))
 				gpte->may_write = 0;
 			if (vcpu->arch.iamr & (1ul << 62))
 				gpte->may_execute = 0;
@@ -307,7 +308,7 @@ int kvmppc_mmu_radix_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 }
 
 void kvmppc_radix_tlbie_page(struct kvm *kvm, unsigned long addr,
-			     unsigned int pshift, unsigned int lpid)
+			     unsigned int pshift, u64 lpid)
 {
 	unsigned long psize = PAGE_SIZE;
 	int psi;
@@ -344,7 +345,7 @@ void kvmppc_radix_tlbie_page(struct kvm *kvm, unsigned long addr,
 		pr_err("KVM: TLB page invalidation hcall failed, rc=%ld\n", rc);
 }
 
-static void kvmppc_radix_flush_pwc(struct kvm *kvm, unsigned int lpid)
+static void kvmppc_radix_flush_pwc(struct kvm *kvm, u64 lpid)
 {
 	long rc;
 
@@ -417,7 +418,7 @@ static void kvmppc_pmd_free(pmd_t *pmdp)
 void kvmppc_unmap_pte(struct kvm *kvm, pte_t *pte, unsigned long gpa,
 		      unsigned int shift,
 		      const struct kvm_memory_slot *memslot,
-		      unsigned int lpid)
+		      u64 lpid)
 
 {
 	unsigned long old;
@@ -468,7 +469,7 @@ void kvmppc_unmap_pte(struct kvm *kvm, pte_t *pte, unsigned long gpa,
  * (or 4kB) mappings (of sub-pages of the same 2MB page).
  */
 static void kvmppc_unmap_free_pte(struct kvm *kvm, pte_t *pte, bool full,
-				  unsigned int lpid)
+				  u64 lpid)
 {
 	if (full) {
 		memset(pte, 0, sizeof(long) << RADIX_PTE_INDEX_SIZE);
@@ -489,7 +490,7 @@ static void kvmppc_unmap_free_pte(struct kvm *kvm, pte_t *pte, bool full,
 }
 
 static void kvmppc_unmap_free_pmd(struct kvm *kvm, pmd_t *pmd, bool full,
-				  unsigned int lpid)
+				  u64 lpid)
 {
 	unsigned long im;
 	pmd_t *p = pmd;
@@ -518,7 +519,7 @@ static void kvmppc_unmap_free_pmd(struct kvm *kvm, pmd_t *pmd, bool full,
 }
 
 static void kvmppc_unmap_free_pud(struct kvm *kvm, pud_t *pud,
-				  unsigned int lpid)
+				  u64 lpid)
 {
 	unsigned long iu;
 	pud_t *p = pud;
@@ -539,7 +540,7 @@ static void kvmppc_unmap_free_pud(struct kvm *kvm, pud_t *pud,
 	pud_free(kvm->mm, pud);
 }
 
-void kvmppc_free_pgtable_radix(struct kvm *kvm, pgd_t *pgd, unsigned int lpid)
+void kvmppc_free_pgtable_radix(struct kvm *kvm, pgd_t *pgd, u64 lpid)
 {
 	unsigned long ig;
 
@@ -566,7 +567,7 @@ void kvmppc_free_radix(struct kvm *kvm)
 }
 
 static void kvmppc_unmap_free_pmd_entry_table(struct kvm *kvm, pmd_t *pmd,
-					unsigned long gpa, unsigned int lpid)
+					unsigned long gpa, u64 lpid)
 {
 	pte_t *pte = pte_offset_kernel(pmd, 0);
 
@@ -582,7 +583,7 @@ static void kvmppc_unmap_free_pmd_entry_table(struct kvm *kvm, pmd_t *pmd,
 }
 
 static void kvmppc_unmap_free_pud_entry_table(struct kvm *kvm, pud_t *pud,
-					unsigned long gpa, unsigned int lpid)
+					unsigned long gpa, u64 lpid)
 {
 	pmd_t *pmd = pmd_offset(pud, 0);
 
@@ -608,7 +609,7 @@ static void kvmppc_unmap_free_pud_entry_table(struct kvm *kvm, pud_t *pud,
 
 int kvmppc_create_pte(struct kvm *kvm, pgd_t *pgtable, pte_t pte,
 		      unsigned long gpa, unsigned int level,
-		      unsigned long mmu_seq, unsigned int lpid,
+		      unsigned long mmu_seq, u64 lpid,
 		      unsigned long *rmapp, struct rmap_nested **n_rmap)
 {
 	pgd_t *pgd;
@@ -785,7 +786,7 @@ int kvmppc_create_pte(struct kvm *kvm, pgd_t *pgtable, pte_t pte,
 }
 
 bool kvmppc_hv_handle_set_rc(struct kvm *kvm, bool nested, bool writing,
-			     unsigned long gpa, unsigned int lpid)
+			     unsigned long gpa, u64 lpid)
 {
 	unsigned long pgflags;
 	unsigned int shift;

arch/powerpc/kvm/book3s_64_vio.c

@@ -786,12 +786,12 @@ long kvmppc_h_get_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 	idx = (ioba >> stt->page_shift) - stt->offset;
 	page = stt->pages[idx / TCES_PER_PAGE];
 	if (!page) {
-		vcpu->arch.regs.gpr[4] = 0;
+		kvmppc_set_gpr(vcpu, 4, 0);
 		return H_SUCCESS;
 	}
 	tbl = (u64 *)page_address(page);
 
-	vcpu->arch.regs.gpr[4] = tbl[idx % TCES_PER_PAGE];
+	kvmppc_set_gpr(vcpu, 4, tbl[idx % TCES_PER_PAGE]);
 
 	return H_SUCCESS;
 }

arch/powerpc/kvm/book3s_hv.h

@@ -3,6 +3,8 @@
 /*
  * Privileged (non-hypervisor) host registers to save.
  */
+#include "asm/guest-state-buffer.h"
+
 struct p9_host_os_sprs {
 	unsigned long iamr;
 	unsigned long amr;
@@ -50,3 +52,77 @@ void accumulate_time(struct kvm_vcpu *vcpu, struct kvmhv_tb_accumulator *next);
 #define start_timing(vcpu, next) do {} while (0)
 #define end_timing(vcpu) do {} while (0)
 #endif
+
+static inline void __kvmppc_set_msr_hv(struct kvm_vcpu *vcpu, u64 val)
+{
+	vcpu->arch.shregs.msr = val;
+	kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_MSR);
+}
+
+static inline u64 __kvmppc_get_msr_hv(struct kvm_vcpu *vcpu)
+{
+	WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, KVMPPC_GSID_MSR) < 0);
+	return vcpu->arch.shregs.msr;
+}
+
+#define KVMPPC_BOOK3S_HV_VCPU_ACCESSOR_SET(reg, size, iden)		\
+static inline void kvmppc_set_##reg ##_hv(struct kvm_vcpu *vcpu, u##size val)	\
+{									\
+	vcpu->arch.reg = val;						\
+	kvmhv_nestedv2_mark_dirty(vcpu, iden);				\
+}
+
+#define KVMPPC_BOOK3S_HV_VCPU_ACCESSOR_GET(reg, size, iden)		\
+static inline u##size kvmppc_get_##reg ##_hv(struct kvm_vcpu *vcpu)	\
+{									\
+	kvmhv_nestedv2_cached_reload(vcpu, iden);			\
+	return vcpu->arch.reg;						\
+}
+
+#define KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(reg, size, iden)			\
+	KVMPPC_BOOK3S_HV_VCPU_ACCESSOR_SET(reg, size, iden)		\
+	KVMPPC_BOOK3S_HV_VCPU_ACCESSOR_GET(reg, size, iden)		\
+
+#define KVMPPC_BOOK3S_HV_VCPU_ARRAY_ACCESSOR_SET(reg, size, iden)	\
+static inline void kvmppc_set_##reg ##_hv(struct kvm_vcpu *vcpu, int i, u##size val)	\
+{									\
+	vcpu->arch.reg[i] = val;					\
+	kvmhv_nestedv2_mark_dirty(vcpu, iden(i));			\
+}
+
+#define KVMPPC_BOOK3S_HV_VCPU_ARRAY_ACCESSOR_GET(reg, size, iden)	\
+static inline u##size kvmppc_get_##reg ##_hv(struct kvm_vcpu *vcpu, int i)	\
+{									\
+	WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, iden(i)) < 0);	\
+	return vcpu->arch.reg[i];					\
+}
+
+#define KVMPPC_BOOK3S_HV_VCPU_ARRAY_ACCESSOR(reg, size, iden)		\
+	KVMPPC_BOOK3S_HV_VCPU_ARRAY_ACCESSOR_SET(reg, size, iden)	\
+	KVMPPC_BOOK3S_HV_VCPU_ARRAY_ACCESSOR_GET(reg, size, iden)	\
+
+KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(mmcra, 64, KVMPPC_GSID_MMCRA)
+KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(hfscr, 64, KVMPPC_GSID_HFSCR)
+KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(fscr, 64, KVMPPC_GSID_FSCR)
+KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(dscr, 64, KVMPPC_GSID_DSCR)
+KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(purr, 64, KVMPPC_GSID_PURR)
+KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(spurr, 64, KVMPPC_GSID_SPURR)
+KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(amr, 64, KVMPPC_GSID_AMR)
+KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(uamor, 64, KVMPPC_GSID_UAMOR)
+KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(siar, 64, KVMPPC_GSID_SIAR)
+KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(sdar, 64, KVMPPC_GSID_SDAR)
+KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(iamr, 64, KVMPPC_GSID_IAMR)
+KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(dawr0, 64, KVMPPC_GSID_DAWR0)
+KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(dawr1, 64, KVMPPC_GSID_DAWR1)
+KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(dawrx0, 64, KVMPPC_GSID_DAWRX0)
+KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(dawrx1, 64, KVMPPC_GSID_DAWRX1)
+KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(ciabr, 64, KVMPPC_GSID_CIABR)
+KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(wort, 64, KVMPPC_GSID_WORT)
+KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(ppr, 64, KVMPPC_GSID_PPR)
+KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(ctrl, 64, KVMPPC_GSID_CTRL);
+
+KVMPPC_BOOK3S_HV_VCPU_ARRAY_ACCESSOR(mmcr, 64, KVMPPC_GSID_MMCR)
+KVMPPC_BOOK3S_HV_VCPU_ARRAY_ACCESSOR(sier, 64, KVMPPC_GSID_SIER)
+KVMPPC_BOOK3S_HV_VCPU_ARRAY_ACCESSOR(pmc, 32, KVMPPC_GSID_PMC)
+
+KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(pspb, 32, KVMPPC_GSID_PSPB)

arch/powerpc/kvm/book3s_hv_builtin.c

@@ -32,6 +32,7 @@
 
 #include "book3s_xics.h"
 #include "book3s_xive.h"
+#include "book3s_hv.h"
 
 /*
  * Hash page table alignment on newer cpus(CPU_FTR_ARCH_206)
@@ -182,9 +183,13 @@ EXPORT_SYMBOL_GPL(kvmppc_hwrng_present);
 
 long kvmppc_rm_h_random(struct kvm_vcpu *vcpu)
 {
+	unsigned long rand;
+
 	if (ppc_md.get_random_seed &&
-	    ppc_md.get_random_seed(&vcpu->arch.regs.gpr[4]))
+	    ppc_md.get_random_seed(&rand)) {
+		kvmppc_set_gpr(vcpu, 4, rand);
 		return H_SUCCESS;
+	}
 
 	return H_HARDWARE;
 }
@@ -510,7 +515,7 @@ void kvmppc_set_msr_hv(struct kvm_vcpu *vcpu, u64 msr)
 	 */
 	if ((msr & MSR_TS_MASK) == MSR_TS_MASK)
 		msr &= ~MSR_TS_MASK;
-	vcpu->arch.shregs.msr = msr;
+	__kvmppc_set_msr_hv(vcpu, msr);
 	kvmppc_end_cede(vcpu);
 }
 EXPORT_SYMBOL_GPL(kvmppc_set_msr_hv);
@@ -548,7 +553,7 @@ static void inject_interrupt(struct kvm_vcpu *vcpu, int vec, u64 srr1_flags)
 	kvmppc_set_srr0(vcpu, pc);
 	kvmppc_set_srr1(vcpu, (msr & SRR1_MSR_BITS) | srr1_flags);
 	kvmppc_set_pc(vcpu, new_pc);
-	vcpu->arch.shregs.msr = new_msr;
+	__kvmppc_set_msr_hv(vcpu, new_msr);
 }
 
 void kvmppc_inject_interrupt_hv(struct kvm_vcpu *vcpu, int vec, u64 srr1_flags)

arch/powerpc/kvm/book3s_hv_nested.c

@@ -428,10 +428,12 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu)
 	return vcpu->arch.trap;
 }
 
+unsigned long nested_capabilities;
+
 long kvmhv_nested_init(void)
 {
 	long int ptb_order;
-	unsigned long ptcr;
+	unsigned long ptcr, host_capabilities;
 	long rc;
 
 	if (!kvmhv_on_pseries())
@@ -439,6 +441,29 @@ long kvmhv_nested_init(void)
 	if (!radix_enabled())
 		return -ENODEV;
 
+	rc = plpar_guest_get_capabilities(0, &host_capabilities);
+	if (rc == H_SUCCESS) {
+		unsigned long capabilities = 0;
+
+		if (cpu_has_feature(CPU_FTR_ARCH_31))
+			capabilities |= H_GUEST_CAP_POWER10;
+		if (cpu_has_feature(CPU_FTR_ARCH_300))
+			capabilities |= H_GUEST_CAP_POWER9;
+
+		nested_capabilities = capabilities & host_capabilities;
+		rc = plpar_guest_set_capabilities(0, nested_capabilities);
+		if (rc != H_SUCCESS) {
+			pr_err("kvm-hv: Could not configure parent hypervisor capabilities (rc=%ld)",
+			       rc);
+			return -ENODEV;
+		}
+
+		static_branch_enable(&__kvmhv_is_nestedv2);
+		return 0;
+	}
+
+	pr_info("kvm-hv: nestedv2 get capabilities hcall failed, falling back to nestedv1 (rc=%ld)\n",
+		rc);
 	/* Partition table entry is 1<<4 bytes in size, hence the 4. */
 	ptb_order = KVM_MAX_NESTED_GUESTS_SHIFT + 4;
 	/* Minimum partition table size is 1<<12 bytes */
@@ -478,7 +503,7 @@ void kvmhv_nested_exit(void)
 	}
 }
 
-static void kvmhv_flush_lpid(unsigned int lpid)
+static void kvmhv_flush_lpid(u64 lpid)
 {
 	long rc;
 
@@ -500,17 +525,22 @@ static void kvmhv_flush_lpid(unsigned int lpid)
 		pr_err("KVM: TLB LPID invalidation hcall failed, rc=%ld\n", rc);
 }
 
-void kvmhv_set_ptbl_entry(unsigned int lpid, u64 dw0, u64 dw1)
+void kvmhv_set_ptbl_entry(u64 lpid, u64 dw0, u64 dw1)
 {
 	if (!kvmhv_on_pseries()) {
 		mmu_partition_table_set_entry(lpid, dw0, dw1, true);
 		return;
 	}
 
-	pseries_partition_tb[lpid].patb0 = cpu_to_be64(dw0);
-	pseries_partition_tb[lpid].patb1 = cpu_to_be64(dw1);
-	/* L0 will do the necessary barriers */
-	kvmhv_flush_lpid(lpid);
+	if (kvmhv_is_nestedv1()) {
+		pseries_partition_tb[lpid].patb0 = cpu_to_be64(dw0);
+		pseries_partition_tb[lpid].patb1 = cpu_to_be64(dw1);
+		/* L0 will do the necessary barriers */
+		kvmhv_flush_lpid(lpid);
+	}
+
+	if (kvmhv_is_nestedv2())
+		kvmhv_nestedv2_set_ptbl_entry(lpid, dw0, dw1);
 }
 
 static void kvmhv_set_nested_ptbl(struct kvm_nested_guest *gp)

arch/powerpc/kvm/book3s_hv_p9_entry.c

@@ -305,7 +305,7 @@ static void switch_mmu_to_guest_radix(struct kvm *kvm, struct kvm_vcpu *vcpu, u6
 	u32 pid;
 
 	lpid = nested ? nested->shadow_lpid : kvm->arch.lpid;
-	pid = vcpu->arch.pid;
+	pid = kvmppc_get_pid(vcpu);
 
 	/*
 	 * Prior memory accesses to host PID Q3 must be completed before we
@@ -330,7 +330,7 @@ static void switch_mmu_to_guest_hpt(struct kvm *kvm, struct kvm_vcpu *vcpu, u64
 	int i;
 
 	lpid = kvm->arch.lpid;
-	pid = vcpu->arch.pid;
+	pid = kvmppc_get_pid(vcpu);
 
 	/*
 	 * See switch_mmu_to_guest_radix. ptesync should not be required here

arch/powerpc/kvm/book3s_hv_ras.c

@@ -174,14 +174,14 @@ long kvmppc_p9_realmode_hmi_handler(struct kvm_vcpu *vcpu)
 		ppc_md.hmi_exception_early(NULL);
 
 out:
-	if (vc->tb_offset) {
+	if (kvmppc_get_tb_offset(vcpu)) {
 		u64 new_tb = mftb() + vc->tb_offset;
 		mtspr(SPRN_TBU40, new_tb);
 		if ((mftb() & 0xffffff) < (new_tb & 0xffffff)) {
 			new_tb += 0x1000000;
 			mtspr(SPRN_TBU40, new_tb);
 		}
-		vc->tb_offset_applied = vc->tb_offset;
+		vc->tb_offset_applied = kvmppc_get_tb_offset(vcpu);
 	}
 
 	return ret;

arch/powerpc/kvm/book3s_hv_rm_mmu.c

@@ -776,8 +776,8 @@ long kvmppc_h_read(struct kvm_vcpu *vcpu, unsigned long flags,
 			r = rev[i].guest_rpte | (r & (HPTE_R_R | HPTE_R_C));
 			r &= ~HPTE_GR_RESERVED;
 		}
-		vcpu->arch.regs.gpr[4 + i * 2] = v;
-		vcpu->arch.regs.gpr[5 + i * 2] = r;
+		kvmppc_set_gpr(vcpu, 4 + i * 2, v);
+		kvmppc_set_gpr(vcpu, 5 + i * 2, r);
 	}
 	return H_SUCCESS;
 }
@@ -824,7 +824,7 @@ long kvmppc_h_clear_ref(struct kvm_vcpu *vcpu, unsigned long flags,
 			}
 		}
 	}
-	vcpu->arch.regs.gpr[4] = gr;
+	kvmppc_set_gpr(vcpu, 4, gr);
 	ret = H_SUCCESS;
  out:
 	unlock_hpte(hpte, v & ~HPTE_V_HVLOCK);
@@ -872,7 +872,7 @@ long kvmppc_h_clear_mod(struct kvm_vcpu *vcpu, unsigned long flags,
 			kvmppc_set_dirty_from_hpte(kvm, v, gr);
 		}
 	}
-	vcpu->arch.regs.gpr[4] = gr;
+	kvmppc_set_gpr(vcpu, 4, gr);
 	ret = H_SUCCESS;
  out:
 	unlock_hpte(hpte, v & ~HPTE_V_HVLOCK);

arch/powerpc/kvm/book3s_hv_rm_xics.c

@@ -481,7 +481,7 @@ static void icp_rm_down_cppr(struct kvmppc_xics *xics, struct kvmppc_icp *icp,
 
 unsigned long xics_rm_h_xirr_x(struct kvm_vcpu *vcpu)
 {
-	vcpu->arch.regs.gpr[5] = get_tb();
+	kvmppc_set_gpr(vcpu, 5, get_tb());
 	return xics_rm_h_xirr(vcpu);
 }
 
@@ -518,7 +518,7 @@ unsigned long xics_rm_h_xirr(struct kvm_vcpu *vcpu)
 	} while (!icp_rm_try_update(icp, old_state, new_state));
 
 	/* Return the result in GPR4 */
-	vcpu->arch.regs.gpr[4] = xirr;
+	kvmppc_set_gpr(vcpu, 4, xirr);
 
 	return check_too_hard(xics, icp);
 }

arch/powerpc/kvm/book3s_hv_uvmem.c

@@ -858,7 +858,7 @@ unsigned long kvmppc_h_svm_init_done(struct kvm *kvm)
 	}
 
 	kvm->arch.secure_guest |= KVMPPC_SECURE_INIT_DONE;
-	pr_info("LPID %d went secure\n", kvm->arch.lpid);
+	pr_info("LPID %lld went secure\n", kvm->arch.lpid);
 
 out:
 	srcu_read_unlock(&kvm->srcu, srcu_idx);

arch/powerpc/kvm/emulate_loadstore.c

@@ -92,7 +92,8 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu)
 	vcpu->arch.mmio_host_swabbed = 0;
 
 	emulated = EMULATE_FAIL;
-	vcpu->arch.regs.msr = vcpu->arch.shared->msr;
+	vcpu->arch.regs.msr = kvmppc_get_msr(vcpu);
+	kvmhv_nestedv2_reload_ptregs(vcpu, &vcpu->arch.regs);
 	if (analyse_instr(&op, &vcpu->arch.regs, inst) == 0) {
 		int type = op.type & INSTR_TYPE_MASK;
 		int size = GETSIZE(op.type);
@@ -250,7 +251,7 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu)
 				vcpu->arch.mmio_sp64_extend = 1;
 
 			emulated = kvmppc_handle_store(vcpu,
-					VCPU_FPR(vcpu, op.reg), size, 1);
+					kvmppc_get_fpr(vcpu, op.reg), size, 1);
 
 			if ((op.type & UPDATE) && (emulated != EMULATE_FAIL))
 				kvmppc_set_gpr(vcpu, op.update_reg, op.ea);
@@ -357,6 +358,7 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu)
 	}
 
 	trace_kvm_ppc_instr(ppc_inst_val(inst), kvmppc_get_pc(vcpu), emulated);
+	kvmhv_nestedv2_mark_dirty_ptregs(vcpu, &vcpu->arch.regs);
 
 	/* Advance past emulated instruction. */
 	if (emulated != EMULATE_FAIL)