Merge remote-tracking branch 'remotes/powerpc/topic/ppc-kvm' into kvm-ppc-next

This merges in the POWER9 radix MMU host and guest support, which
was put into a topic branch because it touches both powerpc and
KVM code.

Signed-off-by: Paul Mackerras <paulus@ozlabs.org>

10 files changed, 140 insertions, 27 deletions

diff --git a/arch/powerpc/include/asm/book3s/64/mmu.h b/arch/powerpc/include/asm/book3s/64/mmu.h
index 8afb0e00f7d9..d73e9dfa5237 100644
--- a/arch/powerpc/include/asm/book3s/64/mmu.h
+++ b/arch/powerpc/include/asm/book3s/64/mmu.h
@@ -44,10 +44,20 @@ struct patb_entry {
 };
 extern struct patb_entry *partition_tb;
 
+/* Bits in patb0 field */
 #define PATB_HR		(1UL << 63)
-#define PATB_GR		(1UL << 63)
 #define RPDB_MASK	0x0ffffffffffff00fUL
 #define RPDB_SHIFT	(1UL << 8)
+#define RTS1_SHIFT	61		/* top 2 bits of radix tree size */
+#define RTS1_MASK	(3UL << RTS1_SHIFT)
+#define RTS2_SHIFT	5		/* bottom 3 bits of radix tree size */
+#define RTS2_MASK	(7UL << RTS2_SHIFT)
+#define RPDS_MASK	0x1f		/* root page dir. size field */
+
+/* Bits in patb1 field */
+#define PATB_GR		(1UL << 63)	/* guest uses radix; must match HR */
+#define PRTS_MASK	0x1f		/* process table size field */
+
 /*
  * Limit process table to PAGE_SIZE table. This
  * also limit the max pid we can support.
@@ -138,5 +148,11 @@ static inline void setup_initial_memory_limit(phys_addr_t first_memblock_base,
 extern int (*register_process_table)(unsigned long base, unsigned long page_size,
 				     unsigned long tbl_size);
 
+#ifdef CONFIG_PPC_PSERIES
+extern void radix_init_pseries(void);
+#else
+static inline void radix_init_pseries(void) { };
+#endif
+
 #endif /* __ASSEMBLY__ */
 #endif /* _ASM_POWERPC_BOOK3S_64_MMU_H_ */
diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h
index 9a3eee661297..8fa09fa500f0 100644
--- a/arch/powerpc/include/asm/exception-64s.h
+++ b/arch/powerpc/include/asm/exception-64s.h
@@ -97,6 +97,15 @@
 	ld	reg,PACAKBASE(r13);					\
 	ori	reg,reg,(ABS_ADDR(label))@l;
 
+/*
+ * Branches from unrelocated code (e.g., interrupts) to labels outside
+ * head-y require >64K offsets.
+ */
+#define __LOAD_FAR_HANDLER(reg, label)					\
+	ld	reg,PACAKBASE(r13);					\
+	ori	reg,reg,(ABS_ADDR(label))@l;				\
+	addis	reg,reg,(ABS_ADDR(label))@h;
+
 /* Exception register prefixes */
 #define EXC_HV	H
 #define EXC_STD
@@ -227,13 +236,41 @@ END_FTR_SECTION_NESTED(ftr,ftr,943)
 	mtctr	reg;							\
 	bctr
 
+/*
+ * KVM requires __LOAD_FAR_HANDLER.
+ *
+ * __BRANCH_TO_KVM_EXIT branches are also a special case because they
+ * explicitly use r9 then reload it from PACA before branching. Hence
+ * the double-underscore.
+ */
+#define __BRANCH_TO_KVM_EXIT(area, label)				\
+	mfctr	r9;							\
+	std	r9,HSTATE_SCRATCH1(r13);				\
+	__LOAD_FAR_HANDLER(r9, label);					\
+	mtctr	r9;							\
+	ld	r9,area+EX_R9(r13);					\
+	bctr
+
+#define BRANCH_TO_KVM(reg, label)					\
+	__LOAD_FAR_HANDLER(reg, label);					\
+	mtctr	reg;							\
+	bctr
+
 #else
 #define BRANCH_TO_COMMON(reg, label)					\
 	b	label
 
+#define BRANCH_TO_KVM(reg, label)					\
+	b	label
+
+#define __BRANCH_TO_KVM_EXIT(area, label)				\
+	ld	r9,area+EX_R9(r13);					\
+	b	label
+
 #endif
 
-#define __KVM_HANDLER_PROLOG(area, n)					\
+
+#define __KVM_HANDLER(area, h, n)					\
 	BEGIN_FTR_SECTION_NESTED(947)					\
 	ld	r10,area+EX_CFAR(r13);					\
 	std	r10,HSTATE_CFAR(r13);					\
@@ -243,30 +280,28 @@ END_FTR_SECTION_NESTED(ftr,ftr,943)
 	std	r10,HSTATE_PPR(r13);					\
 	END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,948);	\
 	ld	r10,area+EX_R10(r13);					\
-	stw	r9,HSTATE_SCRATCH1(r13);				\
-	ld	r9,area+EX_R9(r13);					\
 	std	r12,HSTATE_SCRATCH0(r13);				\
-
-#define __KVM_HANDLER(area, h, n)					\
-	__KVM_HANDLER_PROLOG(area, n)					\
-	li	r12,n;							\
-	b	kvmppc_interrupt
+	sldi	r12,r9,32;						\
+	ori	r12,r12,(n);						\
+	/* This reloads r9 before branching to kvmppc_interrupt */	\
+	__BRANCH_TO_KVM_EXIT(area, kvmppc_interrupt)
 
 #define __KVM_HANDLER_SKIP(area, h, n)					\
 	cmpwi	r10,KVM_GUEST_MODE_SKIP;				\
-	ld	r10,area+EX_R10(r13);					\
 	beq	89f;							\
-	stw	r9,HSTATE_SCRATCH1(r13);				\
 	BEGIN_FTR_SECTION_NESTED(948)					\
-	ld	r9,area+EX_PPR(r13);					\
-	std	r9,HSTATE_PPR(r13);					\
+	ld	r10,area+EX_PPR(r13);					\
+	std	r10,HSTATE_PPR(r13);					\
 	END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,948);	\
-	ld	r9,area+EX_R9(r13);					\
+	ld	r10,area+EX_R10(r13);					\
 	std	r12,HSTATE_SCRATCH0(r13);				\
-	li	r12,n;							\
-	b	kvmppc_interrupt;					\
+	sldi	r12,r9,32;						\
+	ori	r12,r12,(n);						\
+	/* This reloads r9 before branching to kvmppc_interrupt */	\
+	__BRANCH_TO_KVM_EXIT(area, kvmppc_interrupt);			\
 89:	mtocrf	0x80,r9;						\
 	ld	r9,area+EX_R9(r13);					\
+	ld	r10,area+EX_R10(r13);					\
 	b	kvmppc_skip_##h##interrupt
 
 #ifdef CONFIG_KVM_BOOK3S_64_HANDLER
@@ -393,12 +428,12 @@ END_FTR_SECTION_NESTED(ftr,ftr,943)
 	EXCEPTION_RELON_PROLOG_PSERIES_1(label, EXC_STD)
 
 #define STD_RELON_EXCEPTION_HV(loc, vec, label)		\
-	/* No guest interrupts come through here */	\
 	SET_SCRATCH0(r13);	/* save r13 */		\
-	EXCEPTION_RELON_PROLOG_PSERIES(PACA_EXGEN, label, EXC_HV, NOTEST, vec);
+	EXCEPTION_RELON_PROLOG_PSERIES(PACA_EXGEN, label,	\
+				       EXC_HV, KVMTEST_HV, vec);
 
 #define STD_RELON_EXCEPTION_HV_OOL(vec, label)			\
-	EXCEPTION_PROLOG_1(PACA_EXGEN, NOTEST, vec);		\
+	EXCEPTION_PROLOG_1(PACA_EXGEN, KVMTEST_HV, vec);	\
 	EXCEPTION_RELON_PROLOG_PSERIES_1(label, EXC_HV)
 
 /* This associate vector numbers with bits in paca->irq_happened */
@@ -475,10 +510,10 @@ END_FTR_SECTION_NESTED(ftr,ftr,943)
 
 #define MASKABLE_RELON_EXCEPTION_HV(loc, vec, label)			\
 	_MASKABLE_RELON_EXCEPTION_PSERIES(vec, label,			\
-					  EXC_HV, SOFTEN_NOTEST_HV)
+					  EXC_HV, SOFTEN_TEST_HV)
 
 #define MASKABLE_RELON_EXCEPTION_HV_OOL(vec, label)			\
-	EXCEPTION_PROLOG_1(PACA_EXGEN, SOFTEN_NOTEST_HV, vec);		\
+	EXCEPTION_PROLOG_1(PACA_EXGEN, SOFTEN_TEST_HV, vec);		\
 	EXCEPTION_PROLOG_PSERIES_1(label, EXC_HV)
 
 /*
diff --git a/arch/powerpc/include/asm/head-64.h b/arch/powerpc/include/asm/head-64.h
index fca7033839a9..9bd81619d090 100644
--- a/arch/powerpc/include/asm/head-64.h
+++ b/arch/powerpc/include/asm/head-64.h
@@ -218,7 +218,7 @@ name:
 
 #ifdef CONFIG_KVM_BOOK3S_64_HANDLER
 #define TRAMP_KVM_BEGIN(name)						\
-	TRAMP_REAL_BEGIN(name)
+	TRAMP_VIRT_BEGIN(name)
 #else
 #define TRAMP_KVM_BEGIN(name)
 #endif
diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h
index 77ff1ba99d1f..54d11b3a6bf7 100644
--- a/arch/powerpc/include/asm/hvcall.h
+++ b/arch/powerpc/include/asm/hvcall.h
@@ -276,6 +276,7 @@
 #define H_GET_MPP_X		0x314
 #define H_SET_MODE		0x31C
 #define H_CLEAR_HPT		0x358
+#define H_REGISTER_PROC_TBL	0x37C
 #define H_SIGNAL_SYS_RESET	0x380
 #define MAX_HCALL_OPCODE	H_SIGNAL_SYS_RESET
 
@@ -313,6 +314,16 @@
 #define H_SIGNAL_SYS_RESET_ALL_OTHERS		-2
 /* >= 0 values are CPU number */
 
+/* Flag values used in H_REGISTER_PROC_TBL hcall */
+#define PROC_TABLE_OP_MASK	0x18
+#define PROC_TABLE_DEREG	0x10
+#define PROC_TABLE_NEW		0x18
+#define PROC_TABLE_TYPE_MASK	0x06
+#define PROC_TABLE_HPT_SLB	0x00
+#define PROC_TABLE_HPT_PT	0x02
+#define PROC_TABLE_RADIX	0x04
+#define PROC_TABLE_GTSE		0x01
+
 #ifndef __ASSEMBLY__
 
 /**
diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index 5cf306ae0ac3..2bf35017ffc0 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -170,6 +170,8 @@ extern int kvmppc_book3s_hv_page_fault(struct kvm_run *run,
 			unsigned long status);
 extern long kvmppc_hv_find_lock_hpte(struct kvm *kvm, gva_t eaddr,
 			unsigned long slb_v, unsigned long valid);
+extern int kvmppc_hv_emulate_mmio(struct kvm_run *run, struct kvm_vcpu *vcpu,
+			unsigned long gpa, gva_t ea, int is_store);
 
 extern void kvmppc_mmu_hpte_cache_map(struct kvm_vcpu *vcpu, struct hpte_cache *pte);
 extern struct hpte_cache *kvmppc_mmu_hpte_cache_next(struct kvm_vcpu *vcpu);
@@ -182,6 +184,25 @@ extern void kvmppc_mmu_hpte_sysexit(void);
 extern int kvmppc_mmu_hv_init(void);
 extern int kvmppc_book3s_hcall_implemented(struct kvm *kvm, unsigned long hc);
 
+extern int kvmppc_book3s_radix_page_fault(struct kvm_run *run,
+			struct kvm_vcpu *vcpu,
+			unsigned long ea, unsigned long dsisr);
+extern int kvmppc_mmu_radix_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
+			struct kvmppc_pte *gpte, bool data, bool iswrite);
+extern int kvmppc_init_vm_radix(struct kvm *kvm);
+extern void kvmppc_free_radix(struct kvm *kvm);
+extern int kvmppc_radix_init(void);
+extern void kvmppc_radix_exit(void);
+extern int kvm_unmap_radix(struct kvm *kvm, struct kvm_memory_slot *memslot,
+			unsigned long gfn);
+extern int kvm_age_radix(struct kvm *kvm, struct kvm_memory_slot *memslot,
+			unsigned long gfn);
+extern int kvm_test_age_radix(struct kvm *kvm, struct kvm_memory_slot *memslot,
+			unsigned long gfn);
+extern long kvmppc_hv_get_dirty_log_radix(struct kvm *kvm,
+			struct kvm_memory_slot *memslot, unsigned long *map);
+extern int kvmhv_get_rmmu_info(struct kvm *kvm, struct kvm_ppc_rmmu_info *info);
+
 /* XXX remove this export when load_last_inst() is generic */
 extern int kvmppc_ld(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr, bool data);
 extern void kvmppc_book3s_queue_irqprio(struct kvm_vcpu *vcpu, unsigned int vec);
@@ -211,8 +232,11 @@ extern long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags,
 extern long kvmppc_do_h_remove(struct kvm *kvm, unsigned long flags,
 			unsigned long pte_index, unsigned long avpn,
 			unsigned long *hpret);
-extern long kvmppc_hv_get_dirty_log(struct kvm *kvm,
+extern long kvmppc_hv_get_dirty_log_hpt(struct kvm *kvm,
 			struct kvm_memory_slot *memslot, unsigned long *map);
+extern void kvmppc_harvest_vpa_dirty(struct kvmppc_vpa *vpa,
+			struct kvm_memory_slot *memslot,
+			unsigned long *map);
 extern void kvmppc_update_lpcr(struct kvm *kvm, unsigned long lpcr,
 			unsigned long mask);
 extern void kvmppc_set_fscr(struct kvm_vcpu *vcpu, u64 fscr);
diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h
index 848292176908..0db010cc4e65 100644
--- a/arch/powerpc/include/asm/kvm_book3s_64.h
+++ b/arch/powerpc/include/asm/kvm_book3s_64.h
@@ -36,6 +36,12 @@ static inline void svcpu_put(struct kvmppc_book3s_shadow_vcpu *svcpu)
 #endif
 
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+
+static inline bool kvm_is_radix(struct kvm *kvm)
+{
+	return kvm->arch.radix;
+}
+
 #define KVM_DEFAULT_HPT_ORDER	24	/* 16MB HPT by default */
 #endif
 
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index e59b172666cd..b2dbeac3f450 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -263,7 +263,11 @@ struct kvm_arch {
 	unsigned long hpt_mask;
 	atomic_t hpte_mod_interest;
 	cpumask_t need_tlb_flush;
+	cpumask_t cpu_in_guest;
 	int hpt_cma_alloc;
+	u8 radix;
+	pgd_t *pgtable;
+	u64 process_table;
 	struct dentry *debugfs_dir;
 	struct dentry *htab_dentry;
 #endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */
@@ -603,6 +607,7 @@ struct kvm_vcpu_arch {
 	ulong fault_dar;
 	u32 fault_dsisr;
 	unsigned long intr_msr;
+	ulong fault_gpa;	/* guest real address of page fault (POWER9) */
 #endif
 
 #ifdef CONFIG_BOOKE
@@ -657,6 +662,7 @@ struct kvm_vcpu_arch {
 	int state;
 	int ptid;
 	int thread_cpu;
+	int prev_cpu;
 	bool timer_running;
 	wait_queue_head_t cpu_run;
 
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index 2da67bf1f2ec..48c760f89590 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -291,6 +291,8 @@ struct kvmppc_ops {
 				       struct irq_bypass_producer *);
 	void (*irq_bypass_del_producer)(struct irq_bypass_consumer *,
 					struct irq_bypass_producer *);
+	int (*configure_mmu)(struct kvm *kvm, struct kvm_ppc_mmuv3_cfg *cfg);
+	int (*get_rmmu_info)(struct kvm *kvm, struct kvm_ppc_rmmu_info *info);
 };
 
 extern struct kvmppc_ops *kvmppc_hv_ops;
diff --git a/arch/powerpc/include/asm/prom.h b/arch/powerpc/include/asm/prom.h
index 5e57705b4759..8af2546ea593 100644
--- a/arch/powerpc/include/asm/prom.h
+++ b/arch/powerpc/include/asm/prom.h
@@ -121,6 +121,8 @@ struct of_drconf_cell {
 #define OV1_PPC_2_06		0x02	/* set if we support PowerPC 2.06 */
 #define OV1_PPC_2_07		0x01	/* set if we support PowerPC 2.07 */
 
+#define OV1_PPC_3_00		0x80	/* set if we support PowerPC 3.00 */
+
 /* Option vector 2: Open Firmware options supported */
 #define OV2_REAL_MODE		0x20	/* set if we want OF in real mode */
 
@@ -151,10 +153,17 @@ struct of_drconf_cell {
 #define OV5_XCMO		0x0440	/* Page Coalescing */
 #define OV5_TYPE1_AFFINITY	0x0580	/* Type 1 NUMA affinity */
 #define OV5_PRRN		0x0540	/* Platform Resource Reassignment */
-#define OV5_PFO_HW_RNG		0x0E80	/* PFO Random Number Generator */
-#define OV5_PFO_HW_842		0x0E40	/* PFO Compression Accelerator */
-#define OV5_PFO_HW_ENCR		0x0E20	/* PFO Encryption Accelerator */
-#define OV5_SUB_PROCESSORS	0x0F01	/* 1,2,or 4 Sub-Processors supported */
+#define OV5_PFO_HW_RNG		0x1180	/* PFO Random Number Generator */
+#define OV5_PFO_HW_842		0x1140	/* PFO Compression Accelerator */
+#define OV5_PFO_HW_ENCR		0x1120	/* PFO Encryption Accelerator */
+#define OV5_SUB_PROCESSORS	0x1501	/* 1,2,or 4 Sub-Processors supported */
+#define OV5_XIVE_EXPLOIT	0x1701	/* XIVE exploitation supported */
+#define OV5_MMU_RADIX_300	0x1880	/* ISA v3.00 radix MMU supported */
+#define OV5_MMU_HASH_300	0x1840	/* ISA v3.00 hash MMU supported */
+#define OV5_MMU_SEGM_RADIX	0x1820	/* radix mode (no segmentation) */
+#define OV5_MMU_PROC_TBL	0x1810	/* hcall selects SLB or proc table */
+#define OV5_MMU_SLB		0x1800	/* always use SLB */
+#define OV5_MMU_GTSE		0x1808	/* Guest translation shootdown */
 
 /* Option Vector 6: IBM PAPR hints */
 #define OV6_LINUX		0x02	/* Linux is our OS */
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index 0d4531aa2052..aa44a83ad3ec 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -274,10 +274,14 @@
 #define SPRN_DSISR	0x012	/* Data Storage Interrupt Status Register */
 #define   DSISR_NOHPTE		0x40000000	/* no translation found */
 #define   DSISR_PROTFAULT	0x08000000	/* protection fault */
+#define   DSISR_BADACCESS	0x04000000	/* bad access to CI or G */
 #define   DSISR_ISSTORE		0x02000000	/* access was a store */
 #define   DSISR_DABRMATCH	0x00400000	/* hit data breakpoint */
 #define   DSISR_NOSEGMENT	0x00200000	/* SLB miss */
 #define   DSISR_KEYFAULT	0x00200000	/* Key fault */
+#define   DSISR_UNSUPP_MMU	0x00080000	/* Unsupported MMU config */
+#define   DSISR_SET_RC		0x00040000	/* Failed setting of R/C bits */
+#define   DSISR_PGDIRFAULT      0x00020000      /* Fault on page directory */
 #define SPRN_TBRL	0x10C	/* Time Base Read Lower Register (user, R/O) */
 #define SPRN_TBRU	0x10D	/* Time Base Read Upper Register (user, R/O) */
 #define SPRN_CIR	0x11B	/* Chip Information Register (hyper, R/0) */