Merge branch 'topic/ppc-kvm' into next

Merge our KVM topic branch.

arch/powerpc/include/asm/iommu.h

@@ -51,13 +51,11 @@ struct iommu_table_ops {
 	int (*xchg_no_kill)(struct iommu_table *tbl,
 			long index,
 			unsigned long *hpa,
-			enum dma_data_direction *direction,
-			bool realmode);
+			enum dma_data_direction *direction);
 
 	void (*tce_kill)(struct iommu_table *tbl,
 			unsigned long index,
-			unsigned long pages,
-			bool realmode);
+			unsigned long pages);
 
 	__be64 *(*useraddrptr)(struct iommu_table *tbl, long index, bool alloc);
 #endif

arch/powerpc/include/asm/kvm_book3s_asm.h

@@ -14,9 +14,6 @@
 #define XICS_MFRR		0xc
 #define XICS_IPI		2	/* interrupt source # for IPIs */
 
-/* LPIDs we support with this build -- runtime limit may be lower */
-#define KVMPPC_NR_LPIDS			(LPID_RSVD + 1)
-
 /* Maximum number of threads per physical core */
 #define MAX_SMT_THREADS		8
 

arch/powerpc/include/asm/kvm_host.h

@@ -36,7 +36,12 @@
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 #include <asm/kvm_book3s_asm.h>		/* for MAX_SMT_THREADS */
 #define KVM_MAX_VCPU_IDS	(MAX_SMT_THREADS * KVM_MAX_VCORES)
-#define KVM_MAX_NESTED_GUESTS	KVMPPC_NR_LPIDS
+
+/*
+ * Limit the nested partition table to 4096 entries (because that's what
+ * hardware supports). Both guest and host use this value.
+ */
+#define KVM_MAX_NESTED_GUESTS_SHIFT	12
 
 #else
 #define KVM_MAX_VCPU_IDS	KVM_MAX_VCPUS
@@ -327,8 +332,7 @@ struct kvm_arch {
 	struct list_head uvmem_pfns;
 	struct mutex mmu_setup_lock;	/* nests inside vcpu mutexes */
 	u64 l1_ptcr;
-	int max_nested_lpid;
-	struct kvm_nested_guest *nested_guests[KVM_MAX_NESTED_GUESTS];
+	struct idr kvm_nested_guest_idr;
 	/* This array can grow quite large, keep it at the end */
 	struct kvmppc_vcore *vcores[KVM_MAX_VCORES];
 #endif

arch/powerpc/include/asm/kvm_ppc.h

@@ -177,8 +177,6 @@ extern void kvmppc_setup_partition_table(struct kvm *kvm);
 
 extern long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
 				struct kvm_create_spapr_tce_64 *args);
-extern struct kvmppc_spapr_tce_table *kvmppc_find_table(
-		struct kvm *kvm, unsigned long liobn);
 #define kvmppc_ioba_validate(stt, ioba, npages)                         \
 		(iommu_tce_check_ioba((stt)->page_shift, (stt)->offset, \
 				(stt)->size, (ioba), (npages)) ?        \
@@ -685,7 +683,7 @@ extern int kvmppc_xive_set_irq(struct kvm *kvm, int irq_source_id, u32 irq,
 			       int level, bool line_status);
 extern void kvmppc_xive_push_vcpu(struct kvm_vcpu *vcpu);
 extern void kvmppc_xive_pull_vcpu(struct kvm_vcpu *vcpu);
-extern void kvmppc_xive_rearm_escalation(struct kvm_vcpu *vcpu);
+extern bool kvmppc_xive_rearm_escalation(struct kvm_vcpu *vcpu);
 
 static inline int kvmppc_xive_enabled(struct kvm_vcpu *vcpu)
 {
@@ -723,7 +721,7 @@ static inline int kvmppc_xive_set_irq(struct kvm *kvm, int irq_source_id, u32 ir
 				      int level, bool line_status) { return -ENODEV; }
 static inline void kvmppc_xive_push_vcpu(struct kvm_vcpu *vcpu) { }
 static inline void kvmppc_xive_pull_vcpu(struct kvm_vcpu *vcpu) { }
-static inline void kvmppc_xive_rearm_escalation(struct kvm_vcpu *vcpu) { }
+static inline bool kvmppc_xive_rearm_escalation(struct kvm_vcpu *vcpu) { return true; }
 
 static inline int kvmppc_xive_enabled(struct kvm_vcpu *vcpu)
 	{ return 0; }
@@ -789,13 +787,6 @@ long kvmppc_rm_h_page_init(struct kvm_vcpu *vcpu, unsigned long flags,
 			   unsigned long dest, unsigned long src);
 long kvmppc_hpte_hv_fault(struct kvm_vcpu *vcpu, unsigned long addr,
                           unsigned long slb_v, unsigned int status, bool data);
-unsigned long kvmppc_rm_h_xirr(struct kvm_vcpu *vcpu);
-unsigned long kvmppc_rm_h_xirr_x(struct kvm_vcpu *vcpu);
-unsigned long kvmppc_rm_h_ipoll(struct kvm_vcpu *vcpu, unsigned long server);
-int kvmppc_rm_h_ipi(struct kvm_vcpu *vcpu, unsigned long server,
-                    unsigned long mfrr);
-int kvmppc_rm_h_cppr(struct kvm_vcpu *vcpu, unsigned long cppr);
-int kvmppc_rm_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr);
 void kvmppc_guest_entry_inject_int(struct kvm_vcpu *vcpu);
 
 /*
@@ -877,7 +868,6 @@ int kvm_vcpu_ioctl_dirty_tlb(struct kvm_vcpu *vcpu,
 			     struct kvm_dirty_tlb *cfg);
 
 long kvmppc_alloc_lpid(void);
-void kvmppc_claim_lpid(long lpid);
 void kvmppc_free_lpid(long lpid);
 void kvmppc_init_lpid(unsigned long nr_lpids);
 

arch/powerpc/include/asm/mmu_context.h

@@ -34,15 +34,10 @@ extern void mm_iommu_init(struct mm_struct *mm);
 extern void mm_iommu_cleanup(struct mm_struct *mm);
 extern struct mm_iommu_table_group_mem_t *mm_iommu_lookup(struct mm_struct *mm,
 		unsigned long ua, unsigned long size);
-extern struct mm_iommu_table_group_mem_t *mm_iommu_lookup_rm(
-		struct mm_struct *mm, unsigned long ua, unsigned long size);
 extern struct mm_iommu_table_group_mem_t *mm_iommu_get(struct mm_struct *mm,
 		unsigned long ua, unsigned long entries);
 extern long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem,
 		unsigned long ua, unsigned int pageshift, unsigned long *hpa);
-extern long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem,
-		unsigned long ua, unsigned int pageshift, unsigned long *hpa);
-extern void mm_iommu_ua_mark_dirty_rm(struct mm_struct *mm, unsigned long ua);
 extern bool mm_iommu_is_devmem(struct mm_struct *mm, unsigned long hpa,
 		unsigned int pageshift, unsigned long *size);
 extern long mm_iommu_mapped_inc(struct mm_iommu_table_group_mem_t *mem);

arch/powerpc/include/asm/reg.h

@@ -417,7 +417,6 @@
 #define   FSCR_DSCR	__MASK(FSCR_DSCR_LG)
 #define   FSCR_INTR_CAUSE (ASM_CONST(0xFF) << 56)	/* interrupt cause */
 #define SPRN_HFSCR	0xbe	/* HV=1 Facility Status & Control Register */
-#define   HFSCR_PREFIX	__MASK(FSCR_PREFIX_LG)
 #define   HFSCR_MSGP	__MASK(FSCR_MSGP_LG)
 #define   HFSCR_TAR	__MASK(FSCR_TAR_LG)
 #define   HFSCR_EBB	__MASK(FSCR_EBB_LG)
@@ -474,8 +473,6 @@
 #ifndef SPRN_LPID
 #define SPRN_LPID	0x13F	/* Logical Partition Identifier */
 #endif
-#define   LPID_RSVD_POWER7	0x3ff	/* Reserved LPID for partn switching */
-#define   LPID_RSVD		0xfff	/* Reserved LPID for partn switching */
 #define	SPRN_HMER	0x150	/* Hypervisor maintenance exception reg */
 #define   HMER_DEBUG_TRIG	(1ul << (63 - 17)) /* Debug trigger */
 #define	SPRN_HMEER	0x151	/* Hyp maintenance exception enable reg */

arch/powerpc/kernel/iommu.c

@@ -1064,7 +1064,7 @@ extern long iommu_tce_xchg_no_kill(struct mm_struct *mm,
 	long ret;
 	unsigned long size = 0;
 
-	ret = tbl->it_ops->xchg_no_kill(tbl, entry, hpa, direction, false);
+	ret = tbl->it_ops->xchg_no_kill(tbl, entry, hpa, direction);
 	if (!ret && ((*direction == DMA_FROM_DEVICE) ||
 			(*direction == DMA_BIDIRECTIONAL)) &&
 			!mm_iommu_is_devmem(mm, *hpa, tbl->it_page_shift,
@@ -1079,7 +1079,7 @@ void iommu_tce_kill(struct iommu_table *tbl,
 		unsigned long entry, unsigned long pages)
 {
 	if (tbl->it_ops->tce_kill)
-		tbl->it_ops->tce_kill(tbl, entry, pages, false);
+		tbl->it_ops->tce_kill(tbl, entry, pages);
 }
 EXPORT_SYMBOL_GPL(iommu_tce_kill);
 

arch/powerpc/kvm/Makefile

@@ -37,9 +37,6 @@ kvm-e500mc-objs := \
 	e500_emulate.o
 kvm-objs-$(CONFIG_KVM_E500MC) := $(kvm-e500mc-objs)
 
-kvm-book3s_64-builtin-objs-$(CONFIG_SPAPR_TCE_IOMMU) := \
-	book3s_64_vio_hv.o
-
 kvm-pr-y := \
 	fpu.o \
 	emulate.o \
@@ -76,7 +73,7 @@ kvm-hv-$(CONFIG_PPC_TRANSACTIONAL_MEM) += \
 	book3s_hv_tm.o
 
 kvm-book3s_64-builtin-xics-objs-$(CONFIG_KVM_XICS) := \
-	book3s_hv_rm_xics.o book3s_hv_rm_xive.o
+	book3s_hv_rm_xics.o
 
 kvm-book3s_64-builtin-tm-objs-$(CONFIG_PPC_TRANSACTIONAL_MEM) += \
 	book3s_hv_tm_builtin.o

arch/powerpc/kvm/book3s_64_mmu_hv.c

@@ -256,26 +256,34 @@ void kvmppc_map_vrma(struct kvm_vcpu *vcpu, struct kvm_memory_slot *memslot,
 
 int kvmppc_mmu_hv_init(void)
 {
-	unsigned long host_lpid, rsvd_lpid;
+	unsigned long nr_lpids;
 
 	if (!mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE))
 		return -EINVAL;
 
-	host_lpid = 0;
-	if (cpu_has_feature(CPU_FTR_HVMODE))
-		host_lpid = mfspr(SPRN_LPID);
+	if (cpu_has_feature(CPU_FTR_HVMODE)) {
+		if (WARN_ON(mfspr(SPRN_LPID) != 0))
+			return -EINVAL;
+		nr_lpids = 1UL << mmu_lpid_bits;
+	} else {
+		nr_lpids = 1UL << KVM_MAX_NESTED_GUESTS_SHIFT;
+	}
 
-	/* POWER8 and above have 12-bit LPIDs (10-bit in POWER7) */
-	if (cpu_has_feature(CPU_FTR_ARCH_207S))
-		rsvd_lpid = LPID_RSVD;
-	else
-		rsvd_lpid = LPID_RSVD_POWER7;
+	if (!cpu_has_feature(CPU_FTR_ARCH_300)) {
+		/* POWER7 has 10-bit LPIDs, POWER8 has 12-bit LPIDs */
+		if (cpu_has_feature(CPU_FTR_ARCH_207S))
+			WARN_ON(nr_lpids != 1UL << 12);
+		else
+			WARN_ON(nr_lpids != 1UL << 10);
 
-	kvmppc_init_lpid(rsvd_lpid + 1);
+		/*
+		 * Reserve the last implemented LPID use in partition
+		 * switching for POWER7 and POWER8.
+		 */
+		nr_lpids -= 1;
+	}
 
-	kvmppc_claim_lpid(host_lpid);
-	/* rsvd_lpid is reserved for use in partition switching */
-	kvmppc_claim_lpid(rsvd_lpid);
+	kvmppc_init_lpid(nr_lpids);
 
 	return 0;
 }
@@ -879,7 +887,7 @@ static bool kvm_age_rmapp(struct kvm *kvm, struct kvm_memory_slot *memslot,
 	struct revmap_entry *rev = kvm->arch.hpt.rev;
 	unsigned long head, i, j;
 	__be64 *hptep;
-	int ret = 0;
+	bool ret = false;
 	unsigned long *rmapp;
 
 	rmapp = &memslot->arch.rmap[gfn - memslot->base_gfn];
@@ -887,7 +895,7 @@ static bool kvm_age_rmapp(struct kvm *kvm, struct kvm_memory_slot *memslot,
 	lock_rmap(rmapp);
 	if (*rmapp & KVMPPC_RMAP_REFERENCED) {
 		*rmapp &= ~KVMPPC_RMAP_REFERENCED;
-		ret = 1;
+		ret = true;
 	}
 	if (!(*rmapp & KVMPPC_RMAP_PRESENT)) {
 		unlock_rmap(rmapp);
@@ -919,7 +927,7 @@ static bool kvm_age_rmapp(struct kvm *kvm, struct kvm_memory_slot *memslot,
 				rev[i].guest_rpte |= HPTE_R_R;
 				note_hpte_modification(kvm, &rev[i]);
 			}
-			ret = 1;
+			ret = true;
 		}
 		__unlock_hpte(hptep, be64_to_cpu(hptep[0]));
 	} while ((i = j) != head);

arch/powerpc/kvm/book3s_64_vio.c

@@ -32,6 +32,18 @@
 #include <asm/tce.h>
 #include <asm/mmu_context.h>
 
+static struct kvmppc_spapr_tce_table *kvmppc_find_table(struct kvm *kvm,
+	unsigned long liobn)
+{
+	struct kvmppc_spapr_tce_table *stt;
+
+	list_for_each_entry_lockless(stt, &kvm->arch.spapr_tce_tables, list)
+		if (stt->liobn == liobn)
+			return stt;
+
+	return NULL;
+}
+
 static unsigned long kvmppc_tce_pages(unsigned long iommu_pages)
 {
 	return ALIGN(iommu_pages * sizeof(u64), PAGE_SIZE) / PAGE_SIZE;
@@ -753,3 +765,34 @@ long kvmppc_h_stuff_tce(struct kvm_vcpu *vcpu,
 	return ret;
 }
 EXPORT_SYMBOL_GPL(kvmppc_h_stuff_tce);
+
+long kvmppc_h_get_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
+		      unsigned long ioba)
+{
+	struct kvmppc_spapr_tce_table *stt;
+	long ret;
+	unsigned long idx;
+	struct page *page;
+	u64 *tbl;
+
+	stt = kvmppc_find_table(vcpu->kvm, liobn);
+	if (!stt)
+		return H_TOO_HARD;
+
+	ret = kvmppc_ioba_validate(stt, ioba, 1);
+	if (ret != H_SUCCESS)
+		return ret;
+
+	idx = (ioba >> stt->page_shift) - stt->offset;
+	page = stt->pages[idx / TCES_PER_PAGE];
+	if (!page) {
+		vcpu->arch.regs.gpr[4] = 0;
+		return H_SUCCESS;
+	}
+	tbl = (u64 *)page_address(page);
+
+	vcpu->arch.regs.gpr[4] = tbl[idx % TCES_PER_PAGE];
+
+	return H_SUCCESS;
+}
+EXPORT_SYMBOL_GPL(kvmppc_h_get_tce);

arch/powerpc/kvm/book3s_hv.c

@@ -1327,6 +1327,12 @@ static int kvmppc_hcall_impl_hv(unsigned long cmd)
 	case H_CONFER:
 	case H_REGISTER_VPA:
 	case H_SET_MODE:
+#ifdef CONFIG_SPAPR_TCE_IOMMU
+	case H_GET_TCE:
+	case H_PUT_TCE:
+	case H_PUT_TCE_INDIRECT:
+	case H_STUFF_TCE:
+#endif
 	case H_LOGICAL_CI_LOAD:
 	case H_LOGICAL_CI_STORE:
 #ifdef CONFIG_KVM_XICS
@@ -2835,7 +2841,7 @@ static int kvmppc_core_vcpu_create_hv(struct kvm_vcpu *vcpu)
 	 * to trap and then we emulate them.
 	 */
 	vcpu->arch.hfscr = HFSCR_TAR | HFSCR_EBB | HFSCR_PM | HFSCR_BHRB |
-		HFSCR_DSCR | HFSCR_VECVSX | HFSCR_FP | HFSCR_PREFIX;
+		HFSCR_DSCR | HFSCR_VECVSX | HFSCR_FP;
 	if (cpu_has_feature(CPU_FTR_HVMODE)) {
 		vcpu->arch.hfscr &= mfspr(SPRN_HFSCR);
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
@@ -3968,6 +3974,7 @@ static int kvmhv_vcpu_entry_p9_nested(struct kvm_vcpu *vcpu, u64 time_limit, uns
 
 	kvmhv_save_hv_regs(vcpu, &hvregs);
 	hvregs.lpcr = lpcr;
+	hvregs.amor = ~0;
 	vcpu->arch.regs.msr = vcpu->arch.shregs.msr;
 	hvregs.version = HV_GUEST_STATE_VERSION;
 	if (vcpu->arch.nested) {
@@ -4030,6 +4037,8 @@ static int kvmhv_vcpu_entry_p9_nested(struct kvm_vcpu *vcpu, u64 time_limit, uns
 static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
 			 unsigned long lpcr, u64 *tb)
 {
+	struct kvm *kvm = vcpu->kvm;
+	struct kvm_nested_guest *nested = vcpu->arch.nested;
 	u64 next_timer;
 	int trap;
 
@@ -4049,34 +4058,61 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
 		trap = kvmhv_vcpu_entry_p9_nested(vcpu, time_limit, lpcr, tb);
 
 		/* H_CEDE has to be handled now, not later */
-		if (trap == BOOK3S_INTERRUPT_SYSCALL && !vcpu->arch.nested &&
+		if (trap == BOOK3S_INTERRUPT_SYSCALL && !nested &&
 		    kvmppc_get_gpr(vcpu, 3) == H_CEDE) {
 			kvmppc_cede(vcpu);
 			kvmppc_set_gpr(vcpu, 3, 0);
 			trap = 0;
 		}
 
-	} else {
-		struct kvm *kvm = vcpu->kvm;
+	} else if (nested) {
+		__this_cpu_write(cpu_in_guest, kvm);
+		trap = kvmhv_vcpu_entry_p9(vcpu, time_limit, lpcr, tb);
+		__this_cpu_write(cpu_in_guest, NULL);
 
+	} else {
 		kvmppc_xive_push_vcpu(vcpu);
 
 		__this_cpu_write(cpu_in_guest, kvm);
 		trap = kvmhv_vcpu_entry_p9(vcpu, time_limit, lpcr, tb);
 		__this_cpu_write(cpu_in_guest, NULL);
 
-		if (trap == BOOK3S_INTERRUPT_SYSCALL && !vcpu->arch.nested &&
+		if (trap == BOOK3S_INTERRUPT_SYSCALL &&
 		    !(vcpu->arch.shregs.msr & MSR_PR)) {
 			unsigned long req = kvmppc_get_gpr(vcpu, 3);
 
-			/* H_CEDE has to be handled now, not later */
+			/*
+			 * XIVE rearm and XICS hcalls must be handled
+			 * before xive context is pulled (is this
+			 * true?)
+			 */
 			if (req == H_CEDE) {
+				/* H_CEDE has to be handled now */
 				kvmppc_cede(vcpu);
-				kvmppc_xive_rearm_escalation(vcpu); /* may un-cede */
+				if (!kvmppc_xive_rearm_escalation(vcpu)) {
+					/*
+					 * Pending escalation so abort
+					 * the cede.
+					 */
+					vcpu->arch.ceded = 0;
+				}
 				kvmppc_set_gpr(vcpu, 3, 0);
 				trap = 0;
 
-			/* XICS hcalls must be handled before xive is pulled */
+			} else if (req == H_ENTER_NESTED) {
+				/*
+				 * L2 should not run with the L1
+				 * context so rearm and pull it.
+				 */
+				if (!kvmppc_xive_rearm_escalation(vcpu)) {
+					/*
+					 * Pending escalation so abort
+					 * H_ENTER_NESTED.
+					 */
+					kvmppc_set_gpr(vcpu, 3, 0);
+					trap = 0;
+				}
+
 			} else if (hcall_is_xics(req)) {
 				int ret;
 
@@ -4234,13 +4270,13 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc)
 	start_wait = ktime_get();
 
 	vc->vcore_state = VCORE_SLEEPING;
-	trace_kvmppc_vcore_blocked(vc, 0);
+	trace_kvmppc_vcore_blocked(vc->runner, 0);
 	spin_unlock(&vc->lock);
 	schedule();
 	finish_rcuwait(&vc->wait);
 	spin_lock(&vc->lock);
 	vc->vcore_state = VCORE_INACTIVE;
-	trace_kvmppc_vcore_blocked(vc, 1);
+	trace_kvmppc_vcore_blocked(vc->runner, 1);
 	++vc->runner->stat.halt_successful_wait;
 
 	cur = ktime_get();
@@ -4520,9 +4556,14 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit,
 
 	if (!nested) {
 		kvmppc_core_prepare_to_enter(vcpu);
-		if (test_bit(BOOK3S_IRQPRIO_EXTERNAL,
-			     &vcpu->arch.pending_exceptions))
+		if (vcpu->arch.shregs.msr & MSR_EE) {
+			if (xive_interrupt_pending(vcpu))
+				kvmppc_inject_interrupt_hv(vcpu,
+						BOOK3S_INTERRUPT_EXTERNAL, 0);
+		} else if (test_bit(BOOK3S_IRQPRIO_EXTERNAL,
+			     &vcpu->arch.pending_exceptions)) {
 			lpcr |= LPCR_MER;
+		}
 	} else if (vcpu->arch.pending_exceptions ||
 		   vcpu->arch.doorbell_request ||
 		   xive_interrupt_pending(vcpu)) {
@@ -4620,9 +4661,9 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit,
 			if (kvmppc_vcpu_check_block(vcpu))
 				break;
 
-			trace_kvmppc_vcore_blocked(vc, 0);
+			trace_kvmppc_vcore_blocked(vcpu, 0);
 			schedule();
-			trace_kvmppc_vcore_blocked(vc, 1);
+			trace_kvmppc_vcore_blocked(vcpu, 1);
 		}
 		finish_rcuwait(wait);
 	}
@@ -5284,6 +5325,10 @@ static int kvmppc_core_init_vm_hv(struct kvm *kvm)
 		kvm->arch.host_lpcr = lpcr = mfspr(SPRN_LPCR);
 		lpcr &= LPCR_PECE | LPCR_LPES;
 	} else {
+		/*
+		 * The L2 LPES mode will be set by the L0 according to whether
+		 * or not it needs to take external interrupts in HV mode.
+		 */
 		lpcr = 0;
 	}
 	lpcr |= (4UL << LPCR_DPFD_SH) | LPCR_HDICE |

arch/powerpc/kvm/book3s_hv_builtin.c

@@ -489,70 +489,6 @@ static long kvmppc_read_one_intr(bool *again)
 	return kvmppc_check_passthru(xisr, xirr, again);
 }
 
-#ifdef CONFIG_KVM_XICS
-unsigned long kvmppc_rm_h_xirr(struct kvm_vcpu *vcpu)
-{
-	if (!kvmppc_xics_enabled(vcpu))
-		return H_TOO_HARD;
-	if (xics_on_xive())
-		return xive_rm_h_xirr(vcpu);
-	else
-		return xics_rm_h_xirr(vcpu);
-}
-
-unsigned long kvmppc_rm_h_xirr_x(struct kvm_vcpu *vcpu)
-{
-	if (!kvmppc_xics_enabled(vcpu))
-		return H_TOO_HARD;
-	vcpu->arch.regs.gpr[5] = get_tb();
-	if (xics_on_xive())
-		return xive_rm_h_xirr(vcpu);
-	else
-		return xics_rm_h_xirr(vcpu);
-}
-
-unsigned long kvmppc_rm_h_ipoll(struct kvm_vcpu *vcpu, unsigned long server)
-{
-	if (!kvmppc_xics_enabled(vcpu))
-		return H_TOO_HARD;
-	if (xics_on_xive())
-		return xive_rm_h_ipoll(vcpu, server);
-	else
-		return H_TOO_HARD;
-}
-
-int kvmppc_rm_h_ipi(struct kvm_vcpu *vcpu, unsigned long server,
-		    unsigned long mfrr)
-{
-	if (!kvmppc_xics_enabled(vcpu))
-		return H_TOO_HARD;
-	if (xics_on_xive())
-		return xive_rm_h_ipi(vcpu, server, mfrr);
-	else
-		return xics_rm_h_ipi(vcpu, server, mfrr);
-}
-
-int kvmppc_rm_h_cppr(struct kvm_vcpu *vcpu, unsigned long cppr)
-{
-	if (!kvmppc_xics_enabled(vcpu))
-		return H_TOO_HARD;
-	if (xics_on_xive())
-		return xive_rm_h_cppr(vcpu, cppr);
-	else
-		return xics_rm_h_cppr(vcpu, cppr);
-}
-
-int kvmppc_rm_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr)
-{
-	if (!kvmppc_xics_enabled(vcpu))
-		return H_TOO_HARD;
-	if (xics_on_xive())
-		return xive_rm_h_eoi(vcpu, xirr);
-	else
-		return xics_rm_h_eoi(vcpu, xirr);
-}
-#endif /* CONFIG_KVM_XICS */
-
 void kvmppc_bad_interrupt(struct pt_regs *regs)
 {
 	/*

arch/powerpc/kvm/book3s_hv_nested.c

@@ -261,8 +261,7 @@ static void load_l2_hv_regs(struct kvm_vcpu *vcpu,
 	/*
 	 * Don't let L1 change LPCR bits for the L2 except these:
 	 */
-	mask = LPCR_DPFD | LPCR_ILE | LPCR_TC | LPCR_AIL | LPCR_LD |
-		LPCR_LPES | LPCR_MER;
+	mask = LPCR_DPFD | LPCR_ILE | LPCR_TC | LPCR_AIL | LPCR_LD | LPCR_MER;
 
 	/*
 	 * Additional filtering is required depending on hardware
@@ -439,10 +438,11 @@ long kvmhv_nested_init(void)
 	if (!radix_enabled())
 		return -ENODEV;
 
-	/* find log base 2 of KVMPPC_NR_LPIDS, rounding up */
-	ptb_order = __ilog2(KVMPPC_NR_LPIDS - 1) + 1;
-	if (ptb_order < 8)
-		ptb_order = 8;
+	/* 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 */
+	if (ptb_order < 12)
+		ptb_order = 12;
 	pseries_partition_tb = kmalloc(sizeof(struct patb_entry) << ptb_order,
 				       GFP_KERNEL);
 	if (!pseries_partition_tb) {
@@ -450,7 +450,7 @@ long kvmhv_nested_init(void)
 		return -ENOMEM;
 	}
 
-	ptcr = __pa(pseries_partition_tb) | (ptb_order - 8);
+	ptcr = __pa(pseries_partition_tb) | (ptb_order - 12);
 	rc = plpar_hcall_norets(H_SET_PARTITION_TABLE, ptcr);
 	if (rc != H_SUCCESS) {
 		pr_err("kvm-hv: Parent hypervisor does not support nesting (rc=%ld)\n",
@@ -521,11 +521,6 @@ static void kvmhv_set_nested_ptbl(struct kvm_nested_guest *gp)
 	kvmhv_set_ptbl_entry(gp->shadow_lpid, dw0, gp->process_table);
 }
 
-void kvmhv_vm_nested_init(struct kvm *kvm)
-{
-	kvm->arch.max_nested_lpid = -1;
-}
-
 /*
  * Handle the H_SET_PARTITION_TABLE hcall.
  * r4 = guest real address of partition table + log_2(size) - 12
@@ -539,16 +534,14 @@ long kvmhv_set_partition_table(struct kvm_vcpu *vcpu)
 	long ret = H_SUCCESS;
 
 	srcu_idx = srcu_read_lock(&kvm->srcu);
-	/*
-	 * Limit the partition table to 4096 entries (because that's what
-	 * hardware supports), and check the base address.
-	 */
-	if ((ptcr & PRTS_MASK) > 12 - 8 ||
+	/* Check partition size and base address. */
+	if ((ptcr & PRTS_MASK) + 12 - 4 > KVM_MAX_NESTED_GUESTS_SHIFT ||
 	    !kvm_is_visible_gfn(vcpu->kvm, (ptcr & PRTB_MASK) >> PAGE_SHIFT))
 		ret = H_PARAMETER;
 	srcu_read_unlock(&kvm->srcu, srcu_idx);
 	if (ret == H_SUCCESS)
 		kvm->arch.l1_ptcr = ptcr;
+
 	return ret;
 }
 
@@ -644,7 +637,7 @@ static void kvmhv_update_ptbl_cache(struct kvm_nested_guest *gp)
 
 	ret = -EFAULT;
 	ptbl_addr = (kvm->arch.l1_ptcr & PRTB_MASK) + (gp->l1_lpid << 4);
-	if (gp->l1_lpid < (1ul << ((kvm->arch.l1_ptcr & PRTS_MASK) + 8))) {
+	if (gp->l1_lpid < (1ul << ((kvm->arch.l1_ptcr & PRTS_MASK) + 12 - 4))) {
 		int srcu_idx = srcu_read_lock(&kvm->srcu);
 		ret = kvm_read_guest(kvm, ptbl_addr,
 				     &ptbl_entry, sizeof(ptbl_entry));
@@ -660,6 +653,35 @@ static void kvmhv_update_ptbl_cache(struct kvm_nested_guest *gp)
 	kvmhv_set_nested_ptbl(gp);
 }
 
+void kvmhv_vm_nested_init(struct kvm *kvm)
+{
+	idr_init(&kvm->arch.kvm_nested_guest_idr);
+}
+
+static struct kvm_nested_guest *__find_nested(struct kvm *kvm, int lpid)
+{
+	return idr_find(&kvm->arch.kvm_nested_guest_idr, lpid);
+}
+
+static bool __prealloc_nested(struct kvm *kvm, int lpid)
+{
+	if (idr_alloc(&kvm->arch.kvm_nested_guest_idr,
+				NULL, lpid, lpid + 1, GFP_KERNEL) != lpid)
+		return false;
+	return true;
+}
+
+static void __add_nested(struct kvm *kvm, int lpid, struct kvm_nested_guest *gp)
+{
+	if (idr_replace(&kvm->arch.kvm_nested_guest_idr, gp, lpid))
+		WARN_ON(1);
+}
+
+static void __remove_nested(struct kvm *kvm, int lpid)
+{
+	idr_remove(&kvm->arch.kvm_nested_guest_idr, lpid);
+}
+
 static struct kvm_nested_guest *kvmhv_alloc_nested(struct kvm *kvm, unsigned int lpid)
 {
 	struct kvm_nested_guest *gp;
@@ -720,13 +742,8 @@ static void kvmhv_remove_nested(struct kvm_nested_guest *gp)
 	long ref;
 
 	spin_lock(&kvm->mmu_lock);
-	if (gp == kvm->arch.nested_guests[lpid]) {
-		kvm->arch.nested_guests[lpid] = NULL;
-		if (lpid == kvm->arch.max_nested_lpid) {
-			while (--lpid >= 0 && !kvm->arch.nested_guests[lpid])
-				;
-			kvm->arch.max_nested_lpid = lpid;
-		}
+	if (gp == __find_nested(kvm, lpid)) {
+		__remove_nested(kvm, lpid);
 		--gp->refcnt;
 	}
 	ref = gp->refcnt;
@@ -743,24 +760,22 @@ static void kvmhv_remove_nested(struct kvm_nested_guest *gp)
  */
 void kvmhv_release_all_nested(struct kvm *kvm)
 {
-	int i;
+	int lpid;
 	struct kvm_nested_guest *gp;
 	struct kvm_nested_guest *freelist = NULL;
 	struct kvm_memory_slot *memslot;
 	int srcu_idx, bkt;
 
 	spin_lock(&kvm->mmu_lock);
-	for (i = 0; i <= kvm->arch.max_nested_lpid; i++) {
-		gp = kvm->arch.nested_guests[i];
-		if (!gp)
-			continue;
-		kvm->arch.nested_guests[i] = NULL;
+	idr_for_each_entry(&kvm->arch.kvm_nested_guest_idr, gp, lpid) {
+		__remove_nested(kvm, lpid);
 		if (--gp->refcnt == 0) {
 			gp->next = freelist;
 			freelist = gp;
 		}
 	}
-	kvm->arch.max_nested_lpid = -1;
+	idr_destroy(&kvm->arch.kvm_nested_guest_idr);
+	/* idr is empty and may be reused at this point */
 	spin_unlock(&kvm->mmu_lock);
 	while ((gp = freelist) != NULL) {
 		freelist = gp->next;
@@ -792,12 +807,11 @@ struct kvm_nested_guest *kvmhv_get_nested(struct kvm *kvm, int l1_lpid,
 {
 	struct kvm_nested_guest *gp, *newgp;
 
-	if (l1_lpid >= KVM_MAX_NESTED_GUESTS ||
-	    l1_lpid >= (1ul << ((kvm->arch.l1_ptcr & PRTS_MASK) + 12 - 4)))
+	if (l1_lpid >= (1ul << ((kvm->arch.l1_ptcr & PRTS_MASK) + 12 - 4)))
 		return NULL;
 
 	spin_lock(&kvm->mmu_lock);
-	gp = kvm->arch.nested_guests[l1_lpid];
+	gp = __find_nested(kvm, l1_lpid);
 	if (gp)
 		++gp->refcnt;
 	spin_unlock(&kvm->mmu_lock);
@@ -808,17 +822,19 @@ struct kvm_nested_guest *kvmhv_get_nested(struct kvm *kvm, int l1_lpid,
 	newgp = kvmhv_alloc_nested(kvm, l1_lpid);
 	if (!newgp)
 		return NULL;
+
+	if (!__prealloc_nested(kvm, l1_lpid)) {
+		kvmhv_release_nested(newgp);
+		return NULL;
+	}
+
 	spin_lock(&kvm->mmu_lock);
-	if (kvm->arch.nested_guests[l1_lpid]) {
-		/* someone else beat us to it */
-		gp = kvm->arch.nested_guests[l1_lpid];
-	} else {
-		kvm->arch.nested_guests[l1_lpid] = newgp;
+	gp = __find_nested(kvm, l1_lpid);
+	if (!gp) {
+		__add_nested(kvm, l1_lpid, newgp);
 		++newgp->refcnt;
 		gp = newgp;
 		newgp = NULL;
-		if (l1_lpid > kvm->arch.max_nested_lpid)
-			kvm->arch.max_nested_lpid = l1_lpid;
 	}
 	++gp->refcnt;
 	spin_unlock(&kvm->mmu_lock);
@@ -841,20 +857,13 @@ void kvmhv_put_nested(struct kvm_nested_guest *gp)
 		kvmhv_release_nested(gp);
 }
 
-static struct kvm_nested_guest *kvmhv_find_nested(struct kvm *kvm, int lpid)
-{
-	if (lpid > kvm->arch.max_nested_lpid)
-		return NULL;
-	return kvm->arch.nested_guests[lpid];
-}
-
 pte_t *find_kvm_nested_guest_pte(struct kvm *kvm, unsigned long lpid,
 				 unsigned long ea, unsigned *hshift)
 {
 	struct kvm_nested_guest *gp;
 	pte_t *pte;
 
-	gp = kvmhv_find_nested(kvm, lpid);
+	gp = __find_nested(kvm, lpid);
 	if (!gp)
 		return NULL;
 
@@ -960,7 +969,7 @@ static void kvmhv_remove_nest_rmap(struct kvm *kvm, u64 n_rmap,
 
 	gpa = n_rmap & RMAP_NESTED_GPA_MASK;
 	lpid = (n_rmap & RMAP_NESTED_LPID_MASK) >> RMAP_NESTED_LPID_SHIFT;
-	gp = kvmhv_find_nested(kvm, lpid);
+	gp = __find_nested(kvm, lpid);
 	if (!gp)
 		return;
 
@@ -1152,16 +1161,13 @@ static void kvmhv_emulate_tlbie_all_lpid(struct kvm_vcpu *vcpu, int ric)
 {
 	struct kvm *kvm = vcpu->kvm;
 	struct kvm_nested_guest *gp;
-	int i;
+	int lpid;
 
 	spin_lock(&kvm->mmu_lock);
-	for (i = 0; i <= kvm->arch.max_nested_lpid; i++) {
-		gp = kvm->arch.nested_guests[i];
-		if (gp) {
-			spin_unlock(&kvm->mmu_lock);
-			kvmhv_emulate_tlbie_lpid(vcpu, gp, ric);
-			spin_lock(&kvm->mmu_lock);
-		}
+	idr_for_each_entry(&kvm->arch.kvm_nested_guest_idr, gp, lpid) {
+		spin_unlock(&kvm->mmu_lock);
+		kvmhv_emulate_tlbie_lpid(vcpu, gp, ric);
+		spin_lock(&kvm->mmu_lock);
 	}
 	spin_unlock(&kvm->mmu_lock);
 }
@@ -1313,7 +1319,7 @@ long do_h_rpt_invalidate_pat(struct kvm_vcpu *vcpu, unsigned long lpid,
 	 * H_ENTER_NESTED call. Since we can't differentiate this case from
 	 * the invalid case, we ignore such flush requests and return success.
 	 */
-	if (!kvmhv_find_nested(vcpu->kvm, lpid))
+	if (!__find_nested(vcpu->kvm, lpid))
 		return H_SUCCESS;
 
 	/*
@@ -1657,15 +1663,12 @@ long int kvmhv_nested_page_fault(struct kvm_vcpu *vcpu)
 
 int kvmhv_nested_next_lpid(struct kvm *kvm, int lpid)
 {
-	int ret = -1;
+	int ret = lpid + 1;
 
 	spin_lock(&kvm->mmu_lock);
-	while (++lpid <= kvm->arch.max_nested_lpid) {
-		if (kvm->arch.nested_guests[lpid]) {
-			ret = lpid;
-			break;
-		}
-	}
+	if (!idr_get_next(&kvm->arch.kvm_nested_guest_idr, &ret))
+		ret = -1;
 	spin_unlock(&kvm->mmu_lock);
+
 	return ret;
 }

arch/powerpc/kvm/book3s_hv_p9_entry.c

@@ -539,8 +539,10 @@ static void switch_mmu_to_guest_radix(struct kvm *kvm, struct kvm_vcpu *vcpu, u6
 {
 	struct kvm_nested_guest *nested = vcpu->arch.nested;
 	u32 lpid;
+	u32 pid;
 
 	lpid = nested ? nested->shadow_lpid : kvm->arch.lpid;
+	pid = vcpu->arch.pid;
 
 	/*
 	 * Prior memory accesses to host PID Q3 must be completed before we
@@ -551,7 +553,7 @@ static void switch_mmu_to_guest_radix(struct kvm *kvm, struct kvm_vcpu *vcpu, u6
 	isync();
 	mtspr(SPRN_LPID, lpid);
 	mtspr(SPRN_LPCR, lpcr);
-	mtspr(SPRN_PID, vcpu->arch.pid);
+	mtspr(SPRN_PID, pid);
 	/*
 	 * isync not required here because we are HRFID'ing to guest before
 	 * any guest context access, which is context synchronising.
@@ -561,9 +563,11 @@ static void switch_mmu_to_guest_radix(struct kvm *kvm, struct kvm_vcpu *vcpu, u6
 static void switch_mmu_to_guest_hpt(struct kvm *kvm, struct kvm_vcpu *vcpu, u64 lpcr)
 {
 	u32 lpid;
+	u32 pid;
 	int i;
 
 	lpid = kvm->arch.lpid;
+	pid = vcpu->arch.pid;
 
 	/*
 	 * See switch_mmu_to_guest_radix. ptesync should not be required here
@@ -574,7 +578,7 @@ static void switch_mmu_to_guest_hpt(struct kvm *kvm, struct kvm_vcpu *vcpu, u64
 	isync();
 	mtspr(SPRN_LPID, lpid);
 	mtspr(SPRN_LPCR, lpcr);
-	mtspr(SPRN_PID, vcpu->arch.pid);
+	mtspr(SPRN_PID, pid);
 
 	for (i = 0; i < vcpu->arch.slb_max; i++)
 		mtslb(vcpu->arch.slb[i].orige, vcpu->arch.slb[i].origv);
@@ -585,6 +589,9 @@ static void switch_mmu_to_guest_hpt(struct kvm *kvm, struct kvm_vcpu *vcpu, u64
 
 static void switch_mmu_to_host(struct kvm *kvm, u32 pid)
 {
+	u32 lpid = kvm->arch.host_lpid;
+	u64 lpcr = kvm->arch.host_lpcr;
+
 	/*
 	 * The guest has exited, so guest MMU context is no longer being
 	 * non-speculatively accessed, but a hwsync is needed before the
@@ -594,8 +601,8 @@ static void switch_mmu_to_host(struct kvm *kvm, u32 pid)
 	asm volatile("hwsync" ::: "memory");
 	isync();
 	mtspr(SPRN_PID, pid);
-	mtspr(SPRN_LPID, kvm->arch.host_lpid);
-	mtspr(SPRN_LPCR, kvm->arch.host_lpcr);
+	mtspr(SPRN_LPID, lpid);
+	mtspr(SPRN_LPCR, lpcr);
 	/*
 	 * isync is not required after the switch, because mtmsrd with L=0
 	 * is performed after this switch, which is context synchronising.

arch/powerpc/kvm/book3s_hv_rm_xics.c

@@ -479,6 +479,11 @@ 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();
+	return xics_rm_h_xirr(vcpu);
+}
 
 unsigned long xics_rm_h_xirr(struct kvm_vcpu *vcpu)
 {
@@ -883,7 +888,7 @@ long kvmppc_deliver_irq_passthru(struct kvm_vcpu *vcpu,
 
 /*  --- Non-real mode XICS-related built-in routines ---  */
 
-/**
+/*
  * Host Operations poked by RM KVM
  */
 static void rm_host_ipi_action(int action, void *data)

arch/powerpc/kvm/book3s_hv_rm_xive.c

-// SPDX-License-Identifier: GPL-2.0
-#include <linux/kernel.h>
-#include <linux/kvm_host.h>
-#include <linux/err.h>
-#include <linux/kernel_stat.h>
-#include <linux/pgtable.h>
-
-#include <asm/kvm_book3s.h>
-#include <asm/kvm_ppc.h>
-#include <asm/hvcall.h>
-#include <asm/xics.h>
-#include <asm/debug.h>
-#include <asm/synch.h>
-#include <asm/cputhreads.h>
-#include <asm/ppc-opcode.h>
-#include <asm/pnv-pci.h>
-#include <asm/opal.h>
-#include <asm/smp.h>
-#include <asm/xive.h>
-#include <asm/xive-regs.h>
-
-#include "book3s_xive.h"
-
-/* XXX */
-#include <asm/udbg.h>
-//#define DBG(fmt...) udbg_printf(fmt)
-#define DBG(fmt...) do { } while(0)
-
-static inline void __iomem *get_tima_phys(void)
-{
-	return local_paca->kvm_hstate.xive_tima_phys;
-}
-
-#undef XIVE_RUNTIME_CHECKS
-#define X_PFX xive_rm_
-#define X_STATIC
-#define X_STAT_PFX stat_rm_
-#define __x_tima		get_tima_phys()
-#define __x_eoi_page(xd)	((void __iomem *)((xd)->eoi_page))
-#define __x_trig_page(xd)	((void __iomem *)((xd)->trig_page))
-#define __x_writeb	__raw_rm_writeb
-#define __x_readw	__raw_rm_readw
-#define __x_readq	__raw_rm_readq
-#define __x_writeq	__raw_rm_writeq
-
-#include "book3s_xive_template.c"

arch/powerpc/kvm/book3s_hv_rmhandlers.S

@@ -50,6 +50,14 @@
 #define STACK_SLOT_UAMOR	(SFS-88)
 #define STACK_SLOT_FSCR		(SFS-96)
 
+/*
+ * Use the last LPID (all implemented LPID bits = 1) for partition switching.
+ * This is reserved in the LPID allocator. POWER7 only implements 0x3ff, but
+ * we write 0xfff into the LPID SPR anyway, which seems to work and just
+ * ignores the top bits.
+ */
+#define   LPID_RSVD		0xfff
+
 /*
  * Call kvmppc_hv_entry in real mode.
  * Must be called with interrupts hard-disabled.
@@ -1784,13 +1792,8 @@ hcall_real_table:
 	.long	DOTSYM(kvmppc_h_clear_mod) - hcall_real_table
 	.long	DOTSYM(kvmppc_h_clear_ref) - hcall_real_table
 	.long	DOTSYM(kvmppc_h_protect) - hcall_real_table
-#ifdef CONFIG_SPAPR_TCE_IOMMU
-	.long	DOTSYM(kvmppc_h_get_tce) - hcall_real_table
-	.long	DOTSYM(kvmppc_rm_h_put_tce) - hcall_real_table
-#else
 	.long	0		/* 0x1c */
 	.long	0		/* 0x20 */
-#endif
 	.long	0		/* 0x24 - H_SET_SPRG0 */
 	.long	DOTSYM(kvmppc_h_set_dabr) - hcall_real_table
 	.long	DOTSYM(kvmppc_rm_h_page_init) - hcall_real_table
@@ -1808,11 +1811,11 @@ hcall_real_table:
 	.long	0		/* 0x5c */
 	.long	0		/* 0x60 */
 #ifdef CONFIG_KVM_XICS
-	.long	DOTSYM(kvmppc_rm_h_eoi) - hcall_real_table
-	.long	DOTSYM(kvmppc_rm_h_cppr) - hcall_real_table
-	.long	DOTSYM(kvmppc_rm_h_ipi) - hcall_real_table
-	.long	DOTSYM(kvmppc_rm_h_ipoll) - hcall_real_table
-	.long	DOTSYM(kvmppc_rm_h_xirr) - hcall_real_table
+	.long	DOTSYM(xics_rm_h_eoi) - hcall_real_table
+	.long	DOTSYM(xics_rm_h_cppr) - hcall_real_table
+	.long	DOTSYM(xics_rm_h_ipi) - hcall_real_table
+	.long	0		/* 0x70 - H_IPOLL */
+	.long	DOTSYM(xics_rm_h_xirr) - hcall_real_table
 #else
 	.long	0		/* 0x64 - H_EOI */
 	.long	0		/* 0x68 - H_CPPR */
@@ -1868,13 +1871,8 @@ hcall_real_table:
 	.long	0		/* 0x12c */
 	.long	0		/* 0x130 */
 	.long	DOTSYM(kvmppc_h_set_xdabr) - hcall_real_table
-#ifdef CONFIG_SPAPR_TCE_IOMMU
-	.long	DOTSYM(kvmppc_rm_h_stuff_tce) - hcall_real_table
-	.long	DOTSYM(kvmppc_rm_h_put_tce_indirect) - hcall_real_table
-#else
 	.long	0		/* 0x138 */
 	.long	0		/* 0x13c */
-#endif
 	.long	0		/* 0x140 */
 	.long	0		/* 0x144 */
 	.long	0		/* 0x148 */
@@ -1987,7 +1985,7 @@ hcall_real_table:
 	.long	0		/* 0x2f4 */
 	.long	0		/* 0x2f8 */
 #ifdef CONFIG_KVM_XICS
-	.long	DOTSYM(kvmppc_rm_h_xirr_x) - hcall_real_table
+	.long	DOTSYM(xics_rm_h_xirr_x) - hcall_real_table
 #else
 	.long	0		/* 0x2fc - H_XIRR_X*/
 #endif

arch/powerpc/kvm/book3s_hv_uvmem.c

@@ -361,13 +361,15 @@ static bool kvmppc_gfn_is_uvmem_pfn(unsigned long gfn, struct kvm *kvm,
 static bool kvmppc_next_nontransitioned_gfn(const struct kvm_memory_slot *memslot,
 		struct kvm *kvm, unsigned long *gfn)
 {
-	struct kvmppc_uvmem_slot *p;
+	struct kvmppc_uvmem_slot *p = NULL, *iter;
 	bool ret = false;
 	unsigned long i;
 
-	list_for_each_entry(p, &kvm->arch.uvmem_pfns, list)
-		if (*gfn >= p->base_pfn && *gfn < p->base_pfn + p->nr_pfns)
+	list_for_each_entry(iter, &kvm->arch.uvmem_pfns, list)
+		if (*gfn >= iter->base_pfn && *gfn < iter->base_pfn + iter->nr_pfns) {
+			p = iter;
 			break;
+		}
 	if (!p)
 		return ret;
 	/*

arch/powerpc/kvm/book3s_pr_papr.c

@@ -433,9 +433,12 @@ int kvmppc_hcall_impl_pr(unsigned long cmd)
 	case H_REMOVE:
 	case H_PROTECT:
 	case H_BULK_REMOVE:
+#ifdef CONFIG_SPAPR_TCE_IOMMU
+	case H_GET_TCE:
 	case H_PUT_TCE:
 	case H_PUT_TCE_INDIRECT:
 	case H_STUFF_TCE:
+#endif
 	case H_CEDE:
 	case H_LOGICAL_CI_LOAD:
 	case H_LOGICAL_CI_STORE:
@@ -464,7 +467,10 @@ static unsigned int default_hcall_list[] = {
 	H_REMOVE,
 	H_PROTECT,
 	H_BULK_REMOVE,
+#ifdef CONFIG_SPAPR_TCE_IOMMU
+	H_GET_TCE,
 	H_PUT_TCE,
+#endif
 	H_CEDE,
 	H_SET_MODE,
 #ifdef CONFIG_KVM_XICS

arch/powerpc/kvm/book3s_xive.h

@@ -285,13 +285,6 @@ static inline u32 __xive_read_eq(__be32 *qpage, u32 msk, u32 *idx, u32 *toggle)
 	return cur & 0x7fffffff;
 }
 
-extern unsigned long xive_rm_h_xirr(struct kvm_vcpu *vcpu);
-extern unsigned long xive_rm_h_ipoll(struct kvm_vcpu *vcpu, unsigned long server);
-extern int xive_rm_h_ipi(struct kvm_vcpu *vcpu, unsigned long server,
-			 unsigned long mfrr);
-extern int xive_rm_h_cppr(struct kvm_vcpu *vcpu, unsigned long cppr);
-extern int xive_rm_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr);
-
 /*
  * Common Xive routines for XICS-over-XIVE and XIVE native
  */

arch/powerpc/kvm/e500mc.c

@@ -399,7 +399,6 @@ static int __init kvmppc_e500mc_init(void)
 	 * allocator.
 	 */
 	kvmppc_init_lpid(KVMPPC_NR_LPIDS/threads_per_core);
-	kvmppc_claim_lpid(0); /* host */
 
 	r = kvm_init(NULL, sizeof(struct kvmppc_vcpu_e500), 0, THIS_MODULE);
 	if (r)

arch/powerpc/kvm/powerpc.c

@@ -2497,41 +2497,37 @@ long kvm_arch_vm_ioctl(struct file *filp,
 	return r;
 }
 
-static unsigned long lpid_inuse[BITS_TO_LONGS(KVMPPC_NR_LPIDS)];
+static DEFINE_IDA(lpid_inuse);
 static unsigned long nr_lpids;
 
 long kvmppc_alloc_lpid(void)
 {
-	long lpid;
+	int lpid;
 
-	do {
-		lpid = find_first_zero_bit(lpid_inuse, KVMPPC_NR_LPIDS);
-		if (lpid >= nr_lpids) {
+	/* The host LPID must always be 0 (allocation starts at 1) */
+	lpid = ida_alloc_range(&lpid_inuse, 1, nr_lpids - 1, GFP_KERNEL);
+	if (lpid < 0) {
+		if (lpid == -ENOMEM)
+			pr_err("%s: Out of memory\n", __func__);
+		else
 			pr_err("%s: No LPIDs free\n", __func__);
-			return -ENOMEM;
-		}
-	} while (test_and_set_bit(lpid, lpid_inuse));
+		return -ENOMEM;
+	}
 
 	return lpid;
 }
 EXPORT_SYMBOL_GPL(kvmppc_alloc_lpid);
 
-void kvmppc_claim_lpid(long lpid)
-{
-	set_bit(lpid, lpid_inuse);
-}
-EXPORT_SYMBOL_GPL(kvmppc_claim_lpid);
-
 void kvmppc_free_lpid(long lpid)
 {
-	clear_bit(lpid, lpid_inuse);
+	ida_free(&lpid_inuse, lpid);
 }
 EXPORT_SYMBOL_GPL(kvmppc_free_lpid);
 
+/* nr_lpids_param includes the host LPID */
 void kvmppc_init_lpid(unsigned long nr_lpids_param)
 {
-	nr_lpids = min_t(unsigned long, KVMPPC_NR_LPIDS, nr_lpids_param);
-	memset(lpid_inuse, 0, sizeof(lpid_inuse));
+	nr_lpids = nr_lpids_param;
 }
 EXPORT_SYMBOL_GPL(kvmppc_init_lpid);
 

arch/powerpc/kvm/trace_hv.h

@@ -409,9 +409,9 @@ TRACE_EVENT(kvmppc_run_core,
 );
 
 TRACE_EVENT(kvmppc_vcore_blocked,
-	TP_PROTO(struct kvmppc_vcore *vc, int where),
+	TP_PROTO(struct kvm_vcpu *vcpu, int where),
 
-	TP_ARGS(vc, where),
+	TP_ARGS(vcpu, where),
 
 	TP_STRUCT__entry(
 		__field(int,	n_runnable)
@@ -421,8 +421,8 @@ TRACE_EVENT(kvmppc_vcore_blocked,
 	),
 
 	TP_fast_assign(
-		__entry->runner_vcpu = vc->runner->vcpu_id;
-		__entry->n_runnable  = vc->n_runnable;
+		__entry->runner_vcpu = vcpu->vcpu_id;
+		__entry->n_runnable  = vcpu->arch.vcore->n_runnable;
 		__entry->where       = where;
 		__entry->tgid	     = current->tgid;
 	),

arch/powerpc/mm/book3s64/iommu_api.c

@@ -305,24 +305,6 @@ struct mm_iommu_table_group_mem_t *mm_iommu_lookup(struct mm_struct *mm,
 }
 EXPORT_SYMBOL_GPL(mm_iommu_lookup);
 
-struct mm_iommu_table_group_mem_t *mm_iommu_lookup_rm(struct mm_struct *mm,
-		unsigned long ua, unsigned long size)
-{
-	struct mm_iommu_table_group_mem_t *mem, *ret = NULL;
-
-	list_for_each_entry_lockless(mem, &mm->context.iommu_group_mem_list,
-			next) {
-		if ((mem->ua <= ua) &&
-				(ua + size <= mem->ua +
-				 (mem->entries << PAGE_SHIFT))) {
-			ret = mem;
-			break;
-		}
-	}
-
-	return ret;
-}
-
 struct mm_iommu_table_group_mem_t *mm_iommu_get(struct mm_struct *mm,
 		unsigned long ua, unsigned long entries)
 {
@@ -369,56 +351,6 @@ long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem,
 }
 EXPORT_SYMBOL_GPL(mm_iommu_ua_to_hpa);
 
-long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem,
-		unsigned long ua, unsigned int pageshift, unsigned long *hpa)
-{
-	const long entry = (ua - mem->ua) >> PAGE_SHIFT;
-	unsigned long *pa;
-
-	if (entry >= mem->entries)
-		return -EFAULT;
-
-	if (pageshift > mem->pageshift)
-		return -EFAULT;
-
-	if (!mem->hpas) {
-		*hpa = mem->dev_hpa + (ua - mem->ua);
-		return 0;
-	}
-
-	pa = (void *) vmalloc_to_phys(&mem->hpas[entry]);
-	if (!pa)
-		return -EFAULT;
-
-	*hpa = (*pa & MM_IOMMU_TABLE_GROUP_PAGE_MASK) | (ua & ~PAGE_MASK);
-
-	return 0;
-}
-
-extern void mm_iommu_ua_mark_dirty_rm(struct mm_struct *mm, unsigned long ua)
-{
-	struct mm_iommu_table_group_mem_t *mem;
-	long entry;
-	void *va;
-	unsigned long *pa;
-
-	mem = mm_iommu_lookup_rm(mm, ua, PAGE_SIZE);
-	if (!mem)
-		return;
-
-	if (mem->dev_hpa != MM_IOMMU_TABLE_INVALID_HPA)
-		return;
-
-	entry = (ua - mem->ua) >> PAGE_SHIFT;
-	va = &mem->hpas[entry];
-
-	pa = (void *) vmalloc_to_phys(va);
-	if (!pa)
-		return;
-
-	*pa |= MM_IOMMU_TABLE_GROUP_PAGE_DIRTY;
-}
-
 bool mm_iommu_is_devmem(struct mm_struct *mm, unsigned long hpa,
 		unsigned int pageshift, unsigned long *size)
 {

arch/powerpc/mm/init_64.c

@@ -372,6 +372,9 @@ void register_page_bootmem_memmap(unsigned long section_nr,
 
 #ifdef CONFIG_PPC_BOOK3S_64
 unsigned int mmu_lpid_bits;
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+EXPORT_SYMBOL_GPL(mmu_lpid_bits);
+#endif
 unsigned int mmu_pid_bits;
 
 static bool disable_radix = !IS_ENABLED(CONFIG_PPC_RADIX_MMU_DEFAULT);

arch/powerpc/platforms/powernv/pci-ioda-tce.c

@@ -145,8 +145,7 @@ int pnv_tce_build(struct iommu_table *tbl, long index, long npages,
 
 #ifdef CONFIG_IOMMU_API
 int pnv_tce_xchg(struct iommu_table *tbl, long index,
-		unsigned long *hpa, enum dma_data_direction *direction,
-		bool alloc)
+		unsigned long *hpa, enum dma_data_direction *direction)
 {
 	u64 proto_tce = iommu_direction_to_tce_perm(*direction);
 	unsigned long newtce = *hpa | proto_tce, oldtce;
@@ -164,7 +163,7 @@ int pnv_tce_xchg(struct iommu_table *tbl, long index,
 	}
 
 	if (!ptce) {
-		ptce = pnv_tce(tbl, false, idx, alloc);
+		ptce = pnv_tce(tbl, false, idx, true);
 		if (!ptce)
 			return -ENOMEM;
 	}

arch/powerpc/platforms/powernv/pci-ioda.c

@@ -1268,22 +1268,20 @@ static bool pnv_pci_ioda_iommu_bypass_supported(struct pci_dev *pdev,
 	return false;
 }
 
-static inline __be64 __iomem *pnv_ioda_get_inval_reg(struct pnv_phb *phb,
-						     bool real_mode)
+static inline __be64 __iomem *pnv_ioda_get_inval_reg(struct pnv_phb *phb)
 {
-	return real_mode ? (__be64 __iomem *)(phb->regs_phys + 0x210) :
-		(phb->regs + 0x210);
+	return phb->regs + 0x210;
 }
 
 static void pnv_pci_p7ioc_tce_invalidate(struct iommu_table *tbl,
-		unsigned long index, unsigned long npages, bool rm)
+		unsigned long index, unsigned long npages)
 {
 	struct iommu_table_group_link *tgl = list_first_entry_or_null(
 			&tbl->it_group_list, struct iommu_table_group_link,
 			next);
 	struct pnv_ioda_pe *pe = container_of(tgl->table_group,
 			struct pnv_ioda_pe, table_group);
-	__be64 __iomem *invalidate = pnv_ioda_get_inval_reg(pe->phb, rm);
+	__be64 __iomem *invalidate = pnv_ioda_get_inval_reg(pe->phb);
 	unsigned long start, end, inc;
 
 	start = __pa(((__be64 *)tbl->it_base) + index - tbl->it_offset);
@@ -1298,11 +1296,7 @@ static void pnv_pci_p7ioc_tce_invalidate(struct iommu_table *tbl,
 
         mb(); /* Ensure above stores are visible */
         while (start <= end) {
-		if (rm)
-			__raw_rm_writeq_be(start, invalidate);
-		else
-			__raw_writeq_be(start, invalidate);
-
+		__raw_writeq_be(start, invalidate);
                 start += inc;
         }
 
@@ -1321,7 +1315,7 @@ static int pnv_ioda1_tce_build(struct iommu_table *tbl, long index,
 			attrs);
 
 	if (!ret)
-		pnv_pci_p7ioc_tce_invalidate(tbl, index, npages, false);
+		pnv_pci_p7ioc_tce_invalidate(tbl, index, npages);
 
 	return ret;
 }
@@ -1329,10 +1323,9 @@ static int pnv_ioda1_tce_build(struct iommu_table *tbl, long index,
 #ifdef CONFIG_IOMMU_API
 /* Common for IODA1 and IODA2 */
 static int pnv_ioda_tce_xchg_no_kill(struct iommu_table *tbl, long index,
-		unsigned long *hpa, enum dma_data_direction *direction,
-		bool realmode)
+		unsigned long *hpa, enum dma_data_direction *direction)
 {
-	return pnv_tce_xchg(tbl, index, hpa, direction, !realmode);
+	return pnv_tce_xchg(tbl, index, hpa, direction);
 }
 #endif
 
@@ -1341,7 +1334,7 @@ static void pnv_ioda1_tce_free(struct iommu_table *tbl, long index,
 {
 	pnv_tce_free(tbl, index, npages);
 
-	pnv_pci_p7ioc_tce_invalidate(tbl, index, npages, false);
+	pnv_pci_p7ioc_tce_invalidate(tbl, index, npages);
 }
 
 static struct iommu_table_ops pnv_ioda1_iommu_ops = {
@@ -1362,18 +1355,18 @@ static struct iommu_table_ops pnv_ioda1_iommu_ops = {
 static inline void pnv_pci_phb3_tce_invalidate_pe(struct pnv_ioda_pe *pe)
 {
 	/* 01xb - invalidate TCEs that match the specified PE# */
-	__be64 __iomem *invalidate = pnv_ioda_get_inval_reg(pe->phb, false);
+	__be64 __iomem *invalidate = pnv_ioda_get_inval_reg(pe->phb);
 	unsigned long val = PHB3_TCE_KILL_INVAL_PE | (pe->pe_number & 0xFF);
 
 	mb(); /* Ensure above stores are visible */
 	__raw_writeq_be(val, invalidate);
 }
 
-static void pnv_pci_phb3_tce_invalidate(struct pnv_ioda_pe *pe, bool rm,
+static void pnv_pci_phb3_tce_invalidate(struct pnv_ioda_pe *pe,
 					unsigned shift, unsigned long index,
 					unsigned long npages)
 {
-	__be64 __iomem *invalidate = pnv_ioda_get_inval_reg(pe->phb, rm);
+	__be64 __iomem *invalidate = pnv_ioda_get_inval_reg(pe->phb);
 	unsigned long start, end, inc;
 
 	/* We'll invalidate DMA address in PE scope */
@@ -1388,10 +1381,7 @@ static void pnv_pci_phb3_tce_invalidate(struct pnv_ioda_pe *pe, bool rm,
 	mb();
 
 	while (start <= end) {
-		if (rm)
-			__raw_rm_writeq_be(start, invalidate);
-		else
-			__raw_writeq_be(start, invalidate);
+		__raw_writeq_be(start, invalidate);
 		start += inc;
 	}
 }
@@ -1408,7 +1398,7 @@ static inline void pnv_pci_ioda2_tce_invalidate_pe(struct pnv_ioda_pe *pe)
 }
 
 static void pnv_pci_ioda2_tce_invalidate(struct iommu_table *tbl,
-		unsigned long index, unsigned long npages, bool rm)
+		unsigned long index, unsigned long npages)
 {
 	struct iommu_table_group_link *tgl;
 
@@ -1419,7 +1409,7 @@ static void pnv_pci_ioda2_tce_invalidate(struct iommu_table *tbl,
 		unsigned int shift = tbl->it_page_shift;
 
 		if (phb->model == PNV_PHB_MODEL_PHB3 && phb->regs)
-			pnv_pci_phb3_tce_invalidate(pe, rm, shift,
+			pnv_pci_phb3_tce_invalidate(pe, shift,
 						    index, npages);
 		else
 			opal_pci_tce_kill(phb->opal_id,
@@ -1438,7 +1428,7 @@ static int pnv_ioda2_tce_build(struct iommu_table *tbl, long index,
 			attrs);
 
 	if (!ret)
-		pnv_pci_ioda2_tce_invalidate(tbl, index, npages, false);
+		pnv_pci_ioda2_tce_invalidate(tbl, index, npages);
 
 	return ret;
 }
@@ -1448,7 +1438,7 @@ static void pnv_ioda2_tce_free(struct iommu_table *tbl, long index,
 {
 	pnv_tce_free(tbl, index, npages);
 
-	pnv_pci_ioda2_tce_invalidate(tbl, index, npages, false);
+	pnv_pci_ioda2_tce_invalidate(tbl, index, npages);
 }
 
 static struct iommu_table_ops pnv_ioda2_iommu_ops = {
@@ -2739,7 +2729,7 @@ static void pnv_pci_ioda1_release_pe_dma(struct pnv_ioda_pe *pe)
 	if (rc != OPAL_SUCCESS)
 		return;
 
-	pnv_pci_p7ioc_tce_invalidate(tbl, tbl->it_offset, tbl->it_size, false);
+	pnv_pci_p7ioc_tce_invalidate(tbl, tbl->it_offset, tbl->it_size);
 	if (pe->table_group.group) {
 		iommu_group_put(pe->table_group.group);
 		WARN_ON(pe->table_group.group);

arch/powerpc/platforms/powernv/pci.h

@@ -311,8 +311,7 @@ extern int pnv_tce_build(struct iommu_table *tbl, long index, long npages,
 		unsigned long attrs);
 extern void pnv_tce_free(struct iommu_table *tbl, long index, long npages);
 extern int pnv_tce_xchg(struct iommu_table *tbl, long index,
-		unsigned long *hpa, enum dma_data_direction *direction,
-		bool alloc);
+		unsigned long *hpa, enum dma_data_direction *direction);
 extern __be64 *pnv_tce_useraddrptr(struct iommu_table *tbl, long index,
 		bool alloc);
 extern unsigned long pnv_tce_get(struct iommu_table *tbl, long index);

arch/powerpc/platforms/pseries/iommu.c

@@ -666,8 +666,7 @@ static void pci_dma_bus_setup_pSeries(struct pci_bus *bus)
 
 #ifdef CONFIG_IOMMU_API
 static int tce_exchange_pseries(struct iommu_table *tbl, long index, unsigned
-				long *tce, enum dma_data_direction *direction,
-				bool realmode)
+				long *tce, enum dma_data_direction *direction)
 {
 	long rc;
 	unsigned long ioba = (unsigned long) index << tbl->it_page_shift;