KVM: PPC: e500: refactor core-specific TLB code

The PID handling is e500v1/v2-specific, and is moved to e500.c.

The MMU sregs code and kvmppc_core_vcpu_translate will be shared with
e500mc, and is moved from e500.c to e500_tlb.c.

Partially based on patches from Liu Yu <yu.liu@freescale.com>.
Signed-off-by: Scott Wood <scottwood@freescale.com>
[agraf: fix bisectability]
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>

arch/powerpc/include/asm/kvm_host.h

@@ -426,6 +426,8 @@ struct kvm_vcpu_arch {
 	ulong fault_esr;
 	ulong queued_dear;
 	ulong queued_esr;
+	u32 tlbcfg[4];
+	u32 mmucfg;
 #endif
 	gpa_t paddr_accessed;
 

arch/powerpc/kvm/e500.c

@@ -22,9 +22,281 @@
 #include <asm/tlbflush.h>
 #include <asm/kvm_ppc.h>
 
+#include "../mm/mmu_decl.h"
 #include "booke.h"
 #include "e500.h"
 
+struct id {
+	unsigned long val;
+	struct id **pentry;
+};
+
+#define NUM_TIDS 256
+
+/*
+ * This table provide mappings from:
+ * (guestAS,guestTID,guestPR) --> ID of physical cpu
+ * guestAS	[0..1]
+ * guestTID	[0..255]
+ * guestPR	[0..1]
+ * ID		[1..255]
+ * Each vcpu keeps one vcpu_id_table.
+ */
+struct vcpu_id_table {
+	struct id id[2][NUM_TIDS][2];
+};
+
+/*
+ * This table provide reversed mappings of vcpu_id_table:
+ * ID --> address of vcpu_id_table item.
+ * Each physical core has one pcpu_id_table.
+ */
+struct pcpu_id_table {
+	struct id *entry[NUM_TIDS];
+};
+
+static DEFINE_PER_CPU(struct pcpu_id_table, pcpu_sids);
+
+/* This variable keeps last used shadow ID on local core.
+ * The valid range of shadow ID is [1..255] */
+static DEFINE_PER_CPU(unsigned long, pcpu_last_used_sid);
+
+/*
+ * Allocate a free shadow id and setup a valid sid mapping in given entry.
+ * A mapping is only valid when vcpu_id_table and pcpu_id_table are match.
+ *
+ * The caller must have preemption disabled, and keep it that way until
+ * it has finished with the returned shadow id (either written into the
+ * TLB or arch.shadow_pid, or discarded).
+ */
+static inline int local_sid_setup_one(struct id *entry)
+{
+	unsigned long sid;
+	int ret = -1;
+
+	sid = ++(__get_cpu_var(pcpu_last_used_sid));
+	if (sid < NUM_TIDS) {
+		__get_cpu_var(pcpu_sids).entry[sid] = entry;
+		entry->val = sid;
+		entry->pentry = &__get_cpu_var(pcpu_sids).entry[sid];
+		ret = sid;
+	}
+
+	/*
+	 * If sid == NUM_TIDS, we've run out of sids.  We return -1, and
+	 * the caller will invalidate everything and start over.
+	 *
+	 * sid > NUM_TIDS indicates a race, which we disable preemption to
+	 * avoid.
+	 */
+	WARN_ON(sid > NUM_TIDS);
+
+	return ret;
+}
+
+/*
+ * Check if given entry contain a valid shadow id mapping.
+ * An ID mapping is considered valid only if
+ * both vcpu and pcpu know this mapping.
+ *
+ * The caller must have preemption disabled, and keep it that way until
+ * it has finished with the returned shadow id (either written into the
+ * TLB or arch.shadow_pid, or discarded).
+ */
+static inline int local_sid_lookup(struct id *entry)
+{
+	if (entry && entry->val != 0 &&
+	    __get_cpu_var(pcpu_sids).entry[entry->val] == entry &&
+	    entry->pentry == &__get_cpu_var(pcpu_sids).entry[entry->val])
+		return entry->val;
+	return -1;
+}
+
+/* Invalidate all id mappings on local core -- call with preempt disabled */
+static inline void local_sid_destroy_all(void)
+{
+	__get_cpu_var(pcpu_last_used_sid) = 0;
+	memset(&__get_cpu_var(pcpu_sids), 0, sizeof(__get_cpu_var(pcpu_sids)));
+}
+
+static void *kvmppc_e500_id_table_alloc(struct kvmppc_vcpu_e500 *vcpu_e500)
+{
+	vcpu_e500->idt = kzalloc(sizeof(struct vcpu_id_table), GFP_KERNEL);
+	return vcpu_e500->idt;
+}
+
+static void kvmppc_e500_id_table_free(struct kvmppc_vcpu_e500 *vcpu_e500)
+{
+	kfree(vcpu_e500->idt);
+	vcpu_e500->idt = NULL;
+}
+
+/* Map guest pid to shadow.
+ * We use PID to keep shadow of current guest non-zero PID,
+ * and use PID1 to keep shadow of guest zero PID.
+ * So that guest tlbe with TID=0 can be accessed at any time */
+static void kvmppc_e500_recalc_shadow_pid(struct kvmppc_vcpu_e500 *vcpu_e500)
+{
+	preempt_disable();
+	vcpu_e500->vcpu.arch.shadow_pid = kvmppc_e500_get_sid(vcpu_e500,
+			get_cur_as(&vcpu_e500->vcpu),
+			get_cur_pid(&vcpu_e500->vcpu),
+			get_cur_pr(&vcpu_e500->vcpu), 1);
+	vcpu_e500->vcpu.arch.shadow_pid1 = kvmppc_e500_get_sid(vcpu_e500,
+			get_cur_as(&vcpu_e500->vcpu), 0,
+			get_cur_pr(&vcpu_e500->vcpu), 1);
+	preempt_enable();
+}
+
+/* Invalidate all mappings on vcpu */
+static void kvmppc_e500_id_table_reset_all(struct kvmppc_vcpu_e500 *vcpu_e500)
+{
+	memset(vcpu_e500->idt, 0, sizeof(struct vcpu_id_table));
+
+	/* Update shadow pid when mappings are changed */
+	kvmppc_e500_recalc_shadow_pid(vcpu_e500);
+}
+
+/* Invalidate one ID mapping on vcpu */
+static inline void kvmppc_e500_id_table_reset_one(
+			       struct kvmppc_vcpu_e500 *vcpu_e500,
+			       int as, int pid, int pr)
+{
+	struct vcpu_id_table *idt = vcpu_e500->idt;
+
+	BUG_ON(as >= 2);
+	BUG_ON(pid >= NUM_TIDS);
+	BUG_ON(pr >= 2);
+
+	idt->id[as][pid][pr].val = 0;
+	idt->id[as][pid][pr].pentry = NULL;
+
+	/* Update shadow pid when mappings are changed */
+	kvmppc_e500_recalc_shadow_pid(vcpu_e500);
+}
+
+/*
+ * Map guest (vcpu,AS,ID,PR) to physical core shadow id.
+ * This function first lookup if a valid mapping exists,
+ * if not, then creates a new one.
+ *
+ * The caller must have preemption disabled, and keep it that way until
+ * it has finished with the returned shadow id (either written into the
+ * TLB or arch.shadow_pid, or discarded).
+ */
+unsigned int kvmppc_e500_get_sid(struct kvmppc_vcpu_e500 *vcpu_e500,
+				 unsigned int as, unsigned int gid,
+				 unsigned int pr, int avoid_recursion)
+{
+	struct vcpu_id_table *idt = vcpu_e500->idt;
+	int sid;
+
+	BUG_ON(as >= 2);
+	BUG_ON(gid >= NUM_TIDS);
+	BUG_ON(pr >= 2);
+
+	sid = local_sid_lookup(&idt->id[as][gid][pr]);
+
+	while (sid <= 0) {
+		/* No mapping yet */
+		sid = local_sid_setup_one(&idt->id[as][gid][pr]);
+		if (sid <= 0) {
+			_tlbil_all();
+			local_sid_destroy_all();
+		}
+
+		/* Update shadow pid when mappings are changed */
+		if (!avoid_recursion)
+			kvmppc_e500_recalc_shadow_pid(vcpu_e500);
+	}
+
+	return sid;
+}
+
+unsigned int kvmppc_e500_get_tlb_stid(struct kvm_vcpu *vcpu,
+				      struct kvm_book3e_206_tlb_entry *gtlbe)
+{
+	return kvmppc_e500_get_sid(to_e500(vcpu), get_tlb_ts(gtlbe),
+				   get_tlb_tid(gtlbe), get_cur_pr(vcpu), 0);
+}
+
+void kvmppc_set_pid(struct kvm_vcpu *vcpu, u32 pid)
+{
+	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+
+	if (vcpu->arch.pid != pid) {
+		vcpu_e500->pid[0] = vcpu->arch.pid = pid;
+		kvmppc_e500_recalc_shadow_pid(vcpu_e500);
+	}
+}
+
+/* gtlbe must not be mapped by more than one host tlbe */
+void kvmppc_e500_tlbil_one(struct kvmppc_vcpu_e500 *vcpu_e500,
+                           struct kvm_book3e_206_tlb_entry *gtlbe)
+{
+	struct vcpu_id_table *idt = vcpu_e500->idt;
+	unsigned int pr, tid, ts, pid;
+	u32 val, eaddr;
+	unsigned long flags;
+
+	ts = get_tlb_ts(gtlbe);
+	tid = get_tlb_tid(gtlbe);
+
+	preempt_disable();
+
+	/* One guest ID may be mapped to two shadow IDs */
+	for (pr = 0; pr < 2; pr++) {
+		/*
+		 * The shadow PID can have a valid mapping on at most one
+		 * host CPU.  In the common case, it will be valid on this
+		 * CPU, in which case we do a local invalidation of the
+		 * specific address.
+		 *
+		 * If the shadow PID is not valid on the current host CPU,
+		 * we invalidate the entire shadow PID.
+		 */
+		pid = local_sid_lookup(&idt->id[ts][tid][pr]);
+		if (pid <= 0) {
+			kvmppc_e500_id_table_reset_one(vcpu_e500, ts, tid, pr);
+			continue;
+		}
+
+		/*
+		 * The guest is invalidating a 4K entry which is in a PID
+		 * that has a valid shadow mapping on this host CPU.  We
+		 * search host TLB to invalidate it's shadow TLB entry,
+		 * similar to __tlbil_va except that we need to look in AS1.
+		 */
+		val = (pid << MAS6_SPID_SHIFT) | MAS6_SAS;
+		eaddr = get_tlb_eaddr(gtlbe);
+
+		local_irq_save(flags);
+
+		mtspr(SPRN_MAS6, val);
+		asm volatile("tlbsx 0, %[eaddr]" : : [eaddr] "r" (eaddr));
+		val = mfspr(SPRN_MAS1);
+		if (val & MAS1_VALID) {
+			mtspr(SPRN_MAS1, val & ~MAS1_VALID);
+			asm volatile("tlbwe");
+		}
+
+		local_irq_restore(flags);
+	}
+
+	preempt_enable();
+}
+
+void kvmppc_e500_tlbil_all(struct kvmppc_vcpu_e500 *vcpu_e500)
+{
+	kvmppc_e500_id_table_reset_all(vcpu_e500);
+}
+
+void kvmppc_mmu_msr_notify(struct kvm_vcpu *vcpu, u32 old_msr)
+{
+	/* Recalc shadow pid since MSR changes */
+	kvmppc_e500_recalc_shadow_pid(to_e500(vcpu));
+}
+
 void kvmppc_core_load_host_debugstate(struct kvm_vcpu *vcpu)
 {
 }
@@ -36,13 +308,13 @@ void kvmppc_core_load_guest_debugstate(struct kvm_vcpu *vcpu)
 void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
 	kvmppc_booke_vcpu_load(vcpu, cpu);
-	kvmppc_e500_tlb_load(vcpu, cpu);
+
+	/* Shadow PID may be expired on local core */
+	kvmppc_e500_recalc_shadow_pid(to_e500(vcpu));
 }
 
 void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu)
 {
-	kvmppc_e500_tlb_put(vcpu);
-
 #ifdef CONFIG_SPE
 	if (vcpu->arch.shadow_msr & MSR_SPE)
 		kvmppc_vcpu_disable_spe(vcpu);
@@ -63,6 +335,23 @@ int kvmppc_core_check_processor_compat(void)
 	return r;
 }
 
+static void kvmppc_e500_tlb_setup(struct kvmppc_vcpu_e500 *vcpu_e500)
+{
+	struct kvm_book3e_206_tlb_entry *tlbe;
+
+	/* Insert large initial mapping for guest. */
+	tlbe = get_entry(vcpu_e500, 1, 0);
+	tlbe->mas1 = MAS1_VALID | MAS1_TSIZE(BOOK3E_PAGESZ_256M);
+	tlbe->mas2 = 0;
+	tlbe->mas7_3 = E500_TLB_SUPER_PERM_MASK;
+
+	/* 4K map for serial output. Used by kernel wrapper. */
+	tlbe = get_entry(vcpu_e500, 1, 1);
+	tlbe->mas1 = MAS1_VALID | MAS1_TSIZE(BOOK3E_PAGESZ_4K);
+	tlbe->mas2 = (0xe0004500 & 0xFFFFF000) | MAS2_I | MAS2_G;
+	tlbe->mas7_3 = (0xe0004500 & 0xFFFFF000) | E500_TLB_SUPER_PERM_MASK;
+}
+
 int kvmppc_core_vcpu_setup(struct kvm_vcpu *vcpu)
 {
 	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
@@ -78,32 +367,6 @@ int kvmppc_core_vcpu_setup(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
-/* 'linear_address' is actually an encoding of AS|PID|EADDR . */
-int kvmppc_core_vcpu_translate(struct kvm_vcpu *vcpu,
-                               struct kvm_translation *tr)
-{
-	int index;
-	gva_t eaddr;
-	u8 pid;
-	u8 as;
-
-	eaddr = tr->linear_address;
-	pid = (tr->linear_address >> 32) & 0xff;
-	as = (tr->linear_address >> 40) & 0x1;
-
-	index = kvmppc_e500_tlb_search(vcpu, eaddr, pid, as);
-	if (index < 0) {
-		tr->valid = 0;
-		return 0;
-	}
-
-	tr->physical_address = kvmppc_mmu_xlate(vcpu, index, eaddr);
-	/* XXX what does "writeable" and "usermode" even mean? */
-	tr->valid = 1;
-
-	return 0;
-}
-
 void kvmppc_core_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 {
 	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
@@ -117,19 +380,6 @@ void kvmppc_core_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 	sregs->u.e.impl.fsl.hid0 = vcpu_e500->hid0;
 	sregs->u.e.impl.fsl.mcar = vcpu_e500->mcar;
 
-	sregs->u.e.mas0 = vcpu->arch.shared->mas0;
-	sregs->u.e.mas1 = vcpu->arch.shared->mas1;
-	sregs->u.e.mas2 = vcpu->arch.shared->mas2;
-	sregs->u.e.mas7_3 = vcpu->arch.shared->mas7_3;
-	sregs->u.e.mas4 = vcpu->arch.shared->mas4;
-	sregs->u.e.mas6 = vcpu->arch.shared->mas6;
-
-	sregs->u.e.mmucfg = mfspr(SPRN_MMUCFG);
-	sregs->u.e.tlbcfg[0] = vcpu_e500->tlb0cfg;
-	sregs->u.e.tlbcfg[1] = vcpu_e500->tlb1cfg;
-	sregs->u.e.tlbcfg[2] = 0;
-	sregs->u.e.tlbcfg[3] = 0;
-
 	sregs->u.e.ivor_high[0] = vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_UNAVAIL];
 	sregs->u.e.ivor_high[1] = vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_FP_DATA];
 	sregs->u.e.ivor_high[2] = vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_FP_ROUND];
@@ -137,11 +387,13 @@ void kvmppc_core_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 		vcpu->arch.ivor[BOOKE_IRQPRIO_PERFORMANCE_MONITOR];
 
 	kvmppc_get_sregs_ivor(vcpu, sregs);
+	kvmppc_get_sregs_e500_tlb(vcpu, sregs);
 }
 
 int kvmppc_core_set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 {
 	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+	int ret;
 
 	if (sregs->u.e.impl_id == KVM_SREGS_E_IMPL_FSL) {
 		vcpu_e500->svr = sregs->u.e.impl.fsl.svr;
@@ -149,14 +401,9 @@ int kvmppc_core_set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 		vcpu_e500->mcar = sregs->u.e.impl.fsl.mcar;
 	}
 
-	if (sregs->u.e.features & KVM_SREGS_E_ARCH206_MMU) {
-		vcpu->arch.shared->mas0 = sregs->u.e.mas0;
-		vcpu->arch.shared->mas1 = sregs->u.e.mas1;
-		vcpu->arch.shared->mas2 = sregs->u.e.mas2;
-		vcpu->arch.shared->mas7_3 = sregs->u.e.mas7_3;
-		vcpu->arch.shared->mas4 = sregs->u.e.mas4;
-		vcpu->arch.shared->mas6 = sregs->u.e.mas6;
-	}
+	ret = kvmppc_set_sregs_e500_tlb(vcpu, sregs);
+	if (ret < 0)
+		return ret;
 
 	if (!(sregs->u.e.features & KVM_SREGS_E_IVOR))
 		return 0;
@@ -195,9 +442,12 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
 	if (err)
 		goto free_vcpu;
 
+	if (kvmppc_e500_id_table_alloc(vcpu_e500) == NULL)
+		goto uninit_vcpu;
+
 	err = kvmppc_e500_tlb_init(vcpu_e500);
 	if (err)
-		goto uninit_vcpu;
+		goto uninit_id;
 
 	vcpu->arch.shared = (void*)__get_free_page(GFP_KERNEL|__GFP_ZERO);
 	if (!vcpu->arch.shared)
@@ -207,6 +457,8 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
 
 uninit_tlb:
 	kvmppc_e500_tlb_uninit(vcpu_e500);
+uninit_id:
+	kvmppc_e500_id_table_free(vcpu_e500);
 uninit_vcpu:
 	kvm_vcpu_uninit(vcpu);
 free_vcpu:
@@ -220,8 +472,9 @@ void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
 	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
 
 	free_page((unsigned long)vcpu->arch.shared);
-	kvm_vcpu_uninit(vcpu);
 	kvmppc_e500_tlb_uninit(vcpu_e500);
+	kvmppc_e500_id_table_free(vcpu_e500);
+	kvm_vcpu_uninit(vcpu);
 	kmem_cache_free(kvm_vcpu_cache, vcpu_e500);
 }
 

arch/powerpc/kvm/e500.h

@@ -35,7 +35,9 @@ struct tlbe_priv {
 	struct tlbe_ref ref; /* TLB0 only -- TLB1 uses tlb_refs */
 };
 
+#ifdef CONFIG_KVM_E500
 struct vcpu_id_table;
+#endif
 
 struct kvmppc_e500_tlb_params {
 	int entries, ways, sets;
@@ -70,23 +72,22 @@ struct kvmppc_vcpu_e500 {
 	struct tlbe_ref *tlb_refs[E500_TLB_NUM];
 	unsigned int host_tlb1_nv;
 
-	u32 host_pid[E500_PID_NUM];
-	u32 pid[E500_PID_NUM];
 	u32 svr;
-
-	/* vcpu id table */
-	struct vcpu_id_table *idt;
-
 	u32 l1csr0;
 	u32 l1csr1;
 	u32 hid0;
 	u32 hid1;
-	u32 tlb0cfg;
-	u32 tlb1cfg;
 	u64 mcar;
 
 	struct page **shared_tlb_pages;
 	int num_shared_tlb_pages;
+
+#ifdef CONFIG_KVM_E500
+	u32 pid[E500_PID_NUM];
+
+	/* vcpu id table */
+	struct vcpu_id_table *idt;
+#endif
 };
 
 static inline struct kvmppc_vcpu_e500 *to_e500(struct kvm_vcpu *vcpu)
@@ -113,23 +114,25 @@ static inline struct kvmppc_vcpu_e500 *to_e500(struct kvm_vcpu *vcpu)
 	  (MAS3_U0 | MAS3_U1 | MAS3_U2 | MAS3_U3 \
 	   | E500_TLB_USER_PERM_MASK | E500_TLB_SUPER_PERM_MASK)
 
-extern void kvmppc_e500_tlb_put(struct kvm_vcpu *);
-extern void kvmppc_e500_tlb_load(struct kvm_vcpu *, int);
-extern void kvmppc_e500_tlb_setup(struct kvmppc_vcpu_e500 *);
-extern void kvmppc_e500_recalc_shadow_pid(struct kvmppc_vcpu_e500 *);
 int kvmppc_e500_emul_mt_mmucsr0(struct kvmppc_vcpu_e500 *vcpu_e500,
 				ulong value);
 int kvmppc_e500_emul_tlbwe(struct kvm_vcpu *vcpu);
 int kvmppc_e500_emul_tlbre(struct kvm_vcpu *vcpu);
 int kvmppc_e500_emul_tlbivax(struct kvm_vcpu *vcpu, int ra, int rb);
 int kvmppc_e500_emul_tlbsx(struct kvm_vcpu *vcpu, int rb);
-int kvmppc_e500_tlb_search(struct kvm_vcpu *, gva_t, unsigned int, int);
 int kvmppc_e500_tlb_init(struct kvmppc_vcpu_e500 *vcpu_e500);
 void kvmppc_e500_tlb_uninit(struct kvmppc_vcpu_e500 *vcpu_e500);
 
 void kvmppc_get_sregs_e500_tlb(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs);
 int kvmppc_set_sregs_e500_tlb(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs);
 
+
+#ifdef CONFIG_KVM_E500
+unsigned int kvmppc_e500_get_sid(struct kvmppc_vcpu_e500 *vcpu_e500,
+				 unsigned int as, unsigned int gid,
+				 unsigned int pr, int avoid_recursion);
+#endif
+
 /* TLB helper functions */
 static inline unsigned int
 get_tlb_size(const struct kvm_book3e_206_tlb_entry *tlbe)
@@ -183,6 +186,12 @@ get_tlb_iprot(const struct kvm_book3e_206_tlb_entry *tlbe)
 	return (tlbe->mas1 >> 30) & 0x1;
 }
 
+static inline unsigned int
+get_tlb_tsize(const struct kvm_book3e_206_tlb_entry *tlbe)
+{
+	return (tlbe->mas1 & MAS1_TSIZE_MASK) >> MAS1_TSIZE_SHIFT;
+}
+
 static inline unsigned int get_cur_pid(struct kvm_vcpu *vcpu)
 {
 	return vcpu->arch.pid & 0xff;
@@ -248,4 +257,31 @@ static inline int tlbe_is_host_safe(const struct kvm_vcpu *vcpu,
 	return 1;
 }
 
+static inline struct kvm_book3e_206_tlb_entry *get_entry(
+	struct kvmppc_vcpu_e500 *vcpu_e500, int tlbsel, int entry)
+{
+	int offset = vcpu_e500->gtlb_offset[tlbsel];
+	return &vcpu_e500->gtlb_arch[offset + entry];
+}
+
+void kvmppc_e500_tlbil_one(struct kvmppc_vcpu_e500 *vcpu_e500,
+			   struct kvm_book3e_206_tlb_entry *gtlbe);
+void kvmppc_e500_tlbil_all(struct kvmppc_vcpu_e500 *vcpu_e500);
+
+#ifdef CONFIG_KVM_E500
+unsigned int kvmppc_e500_get_tlb_stid(struct kvm_vcpu *vcpu,
+				      struct kvm_book3e_206_tlb_entry *gtlbe);
+
+static inline unsigned int get_tlbmiss_tid(struct kvm_vcpu *vcpu)
+{
+	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+	unsigned int tidseld = (vcpu->arch.shared->mas4 >> 16) & 0xf;
+
+	return vcpu_e500->pid[tidseld];
+}
+
+/* Force TS=1 for all guest mappings. */
+#define get_tlb_sts(gtlbe)              (MAS1_TS)
+#endif /* CONFIG_KVM_E500 */
+
 #endif /* KVM_E500_H */

arch/powerpc/kvm/e500_emulate.c

@@ -174,9 +174,9 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
 		kvmppc_set_gpr(vcpu, rt, val);
 		break;
 	case SPRN_TLB0CFG:
-		kvmppc_set_gpr(vcpu, rt, vcpu_e500->tlb0cfg); break;
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.tlbcfg[0]); break;
 	case SPRN_TLB1CFG:
-		kvmppc_set_gpr(vcpu, rt, vcpu_e500->tlb1cfg); break;
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.tlbcfg[1]); break;
 	case SPRN_L1CSR0:
 		kvmppc_set_gpr(vcpu, rt, vcpu_e500->l1csr0); break;
 	case SPRN_L1CSR1:
@@ -192,7 +192,7 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
 		kvmppc_set_gpr(vcpu, rt, 0); break;
 
 	case SPRN_MMUCFG:
-		kvmppc_set_gpr(vcpu, rt, mfspr(SPRN_MMUCFG)); break;
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.mmucfg); break;
 
 	/* extra exceptions */
 	case SPRN_IVOR32:

arch/powerpc/kvm/e500_tlb.c

@@ -27,208 +27,14 @@
 #include <linux/hugetlb.h>
 #include <asm/kvm_ppc.h>
 
-#include "../mm/mmu_decl.h"
 #include "e500.h"
 #include "trace.h"
 #include "timing.h"
 
 #define to_htlb1_esel(esel) (host_tlb_params[1].entries - (esel) - 1)
 
-struct id {
-	unsigned long val;
-	struct id **pentry;
-};
-
-#define NUM_TIDS 256
-
-/*
- * This table provide mappings from:
- * (guestAS,guestTID,guestPR) --> ID of physical cpu
- * guestAS	[0..1]
- * guestTID	[0..255]
- * guestPR	[0..1]
- * ID		[1..255]
- * Each vcpu keeps one vcpu_id_table.
- */
-struct vcpu_id_table {
-	struct id id[2][NUM_TIDS][2];
-};
-
-/*
- * This table provide reversed mappings of vcpu_id_table:
- * ID --> address of vcpu_id_table item.
- * Each physical core has one pcpu_id_table.
- */
-struct pcpu_id_table {
-	struct id *entry[NUM_TIDS];
-};
-
-static DEFINE_PER_CPU(struct pcpu_id_table, pcpu_sids);
-
-/* This variable keeps last used shadow ID on local core.
- * The valid range of shadow ID is [1..255] */
-static DEFINE_PER_CPU(unsigned long, pcpu_last_used_sid);
-
 static struct kvmppc_e500_tlb_params host_tlb_params[E500_TLB_NUM];
 
-static struct kvm_book3e_206_tlb_entry *get_entry(
-	struct kvmppc_vcpu_e500 *vcpu_e500, int tlbsel, int entry)
-{
-	int offset = vcpu_e500->gtlb_offset[tlbsel];
-	return &vcpu_e500->gtlb_arch[offset + entry];
-}
-
-/*
- * Allocate a free shadow id and setup a valid sid mapping in given entry.
- * A mapping is only valid when vcpu_id_table and pcpu_id_table are match.
- *
- * The caller must have preemption disabled, and keep it that way until
- * it has finished with the returned shadow id (either written into the
- * TLB or arch.shadow_pid, or discarded).
- */
-static inline int local_sid_setup_one(struct id *entry)
-{
-	unsigned long sid;
-	int ret = -1;
-
-	sid = ++(__get_cpu_var(pcpu_last_used_sid));
-	if (sid < NUM_TIDS) {
-		__get_cpu_var(pcpu_sids).entry[sid] = entry;
-		entry->val = sid;
-		entry->pentry = &__get_cpu_var(pcpu_sids).entry[sid];
-		ret = sid;
-	}
-
-	/*
-	 * If sid == NUM_TIDS, we've run out of sids.  We return -1, and
-	 * the caller will invalidate everything and start over.
-	 *
-	 * sid > NUM_TIDS indicates a race, which we disable preemption to
-	 * avoid.
-	 */
-	WARN_ON(sid > NUM_TIDS);
-
-	return ret;
-}
-
-/*
- * Check if given entry contain a valid shadow id mapping.
- * An ID mapping is considered valid only if
- * both vcpu and pcpu know this mapping.
- *
- * The caller must have preemption disabled, and keep it that way until
- * it has finished with the returned shadow id (either written into the
- * TLB or arch.shadow_pid, or discarded).
- */
-static inline int local_sid_lookup(struct id *entry)
-{
-	if (entry && entry->val != 0 &&
-	    __get_cpu_var(pcpu_sids).entry[entry->val] == entry &&
-	    entry->pentry == &__get_cpu_var(pcpu_sids).entry[entry->val])
-		return entry->val;
-	return -1;
-}
-
-/* Invalidate all id mappings on local core -- call with preempt disabled */
-static inline void local_sid_destroy_all(void)
-{
-	__get_cpu_var(pcpu_last_used_sid) = 0;
-	memset(&__get_cpu_var(pcpu_sids), 0, sizeof(__get_cpu_var(pcpu_sids)));
-}
-
-static void *kvmppc_e500_id_table_alloc(struct kvmppc_vcpu_e500 *vcpu_e500)
-{
-	vcpu_e500->idt = kzalloc(sizeof(struct vcpu_id_table), GFP_KERNEL);
-	return vcpu_e500->idt;
-}
-
-static void kvmppc_e500_id_table_free(struct kvmppc_vcpu_e500 *vcpu_e500)
-{
-	kfree(vcpu_e500->idt);
-}
-
-/* Invalidate all mappings on vcpu */
-static void kvmppc_e500_id_table_reset_all(struct kvmppc_vcpu_e500 *vcpu_e500)
-{
-	memset(vcpu_e500->idt, 0, sizeof(struct vcpu_id_table));
-
-	/* Update shadow pid when mappings are changed */
-	kvmppc_e500_recalc_shadow_pid(vcpu_e500);
-}
-
-/* Invalidate one ID mapping on vcpu */
-static inline void kvmppc_e500_id_table_reset_one(
-			       struct kvmppc_vcpu_e500 *vcpu_e500,
-			       int as, int pid, int pr)
-{
-	struct vcpu_id_table *idt = vcpu_e500->idt;
-
-	BUG_ON(as >= 2);
-	BUG_ON(pid >= NUM_TIDS);
-	BUG_ON(pr >= 2);
-
-	idt->id[as][pid][pr].val = 0;
-	idt->id[as][pid][pr].pentry = NULL;
-
-	/* Update shadow pid when mappings are changed */
-	kvmppc_e500_recalc_shadow_pid(vcpu_e500);
-}
-
-/*
- * Map guest (vcpu,AS,ID,PR) to physical core shadow id.
- * This function first lookup if a valid mapping exists,
- * if not, then creates a new one.
- *
- * The caller must have preemption disabled, and keep it that way until
- * it has finished with the returned shadow id (either written into the
- * TLB or arch.shadow_pid, or discarded).
- */
-static unsigned int kvmppc_e500_get_sid(struct kvmppc_vcpu_e500 *vcpu_e500,
-					unsigned int as, unsigned int gid,
-					unsigned int pr, int avoid_recursion)
-{
-	struct vcpu_id_table *idt = vcpu_e500->idt;
-	int sid;
-
-	BUG_ON(as >= 2);
-	BUG_ON(gid >= NUM_TIDS);
-	BUG_ON(pr >= 2);
-
-	sid = local_sid_lookup(&idt->id[as][gid][pr]);
-
-	while (sid <= 0) {
-		/* No mapping yet */
-		sid = local_sid_setup_one(&idt->id[as][gid][pr]);
-		if (sid <= 0) {
-			_tlbil_all();
-			local_sid_destroy_all();
-		}
-
-		/* Update shadow pid when mappings are changed */
-		if (!avoid_recursion)
-			kvmppc_e500_recalc_shadow_pid(vcpu_e500);
-	}
-
-	return sid;
-}
-
-/* Map guest pid to shadow.
- * We use PID to keep shadow of current guest non-zero PID,
- * and use PID1 to keep shadow of guest zero PID.
- * So that guest tlbe with TID=0 can be accessed at any time */
-void kvmppc_e500_recalc_shadow_pid(struct kvmppc_vcpu_e500 *vcpu_e500)
-{
-	preempt_disable();
-	vcpu_e500->vcpu.arch.shadow_pid = kvmppc_e500_get_sid(vcpu_e500,
-			get_cur_as(&vcpu_e500->vcpu),
-			get_cur_pid(&vcpu_e500->vcpu),
-			get_cur_pr(&vcpu_e500->vcpu), 1);
-	vcpu_e500->vcpu.arch.shadow_pid1 = kvmppc_e500_get_sid(vcpu_e500,
-			get_cur_as(&vcpu_e500->vcpu), 0,
-			get_cur_pr(&vcpu_e500->vcpu), 1);
-	preempt_enable();
-}
-
 static inline unsigned int gtlb0_get_next_victim(
 		struct kvmppc_vcpu_e500 *vcpu_e500)
 {
@@ -336,6 +142,7 @@ static inline void write_host_tlbe(struct kvmppc_vcpu_e500 *vcpu_e500,
 	}
 }
 
+#ifdef CONFIG_KVM_E500
 void kvmppc_map_magic(struct kvm_vcpu *vcpu)
 {
 	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
@@ -360,75 +167,21 @@ void kvmppc_map_magic(struct kvm_vcpu *vcpu)
 	__write_host_tlbe(&magic, MAS0_TLBSEL(1) | MAS0_ESEL(tlbcam_index));
 	preempt_enable();
 }
-
-void kvmppc_e500_tlb_load(struct kvm_vcpu *vcpu, int cpu)
-{
-	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
-
-	/* Shadow PID may be expired on local core */
-	kvmppc_e500_recalc_shadow_pid(vcpu_e500);
-}
-
-void kvmppc_e500_tlb_put(struct kvm_vcpu *vcpu)
-{
-}
+#endif
 
 static void inval_gtlbe_on_host(struct kvmppc_vcpu_e500 *vcpu_e500,
 				int tlbsel, int esel)
 {
 	struct kvm_book3e_206_tlb_entry *gtlbe =
 		get_entry(vcpu_e500, tlbsel, esel);
-	struct vcpu_id_table *idt = vcpu_e500->idt;
-	unsigned int pr, tid, ts, pid;
-	u32 val, eaddr;
-	unsigned long flags;
-
-	ts = get_tlb_ts(gtlbe);
-	tid = get_tlb_tid(gtlbe);
-
-	preempt_disable();
-
-	/* One guest ID may be mapped to two shadow IDs */
-	for (pr = 0; pr < 2; pr++) {
-		/*
-		 * The shadow PID can have a valid mapping on at most one
-		 * host CPU.  In the common case, it will be valid on this
-		 * CPU, in which case (for TLB0) we do a local invalidation
-		 * of the specific address.
-		 *
-		 * If the shadow PID is not valid on the current host CPU, or
-		 * if we're invalidating a TLB1 entry, we invalidate the
-		 * entire shadow PID.
-		 */
-		if (tlbsel == 1 ||
-		    (pid = local_sid_lookup(&idt->id[ts][tid][pr])) <= 0) {
-			kvmppc_e500_id_table_reset_one(vcpu_e500, ts, tid, pr);
-			continue;
-		}
-
-		/*
-		 * The guest is invalidating a TLB0 entry which is in a PID
-		 * that has a valid shadow mapping on this host CPU.  We
-		 * search host TLB0 to invalidate it's shadow TLB entry,
-		 * similar to __tlbil_va except that we need to look in AS1.
-		 */
-		val = (pid << MAS6_SPID_SHIFT) | MAS6_SAS;
-		eaddr = get_tlb_eaddr(gtlbe);
-
-		local_irq_save(flags);
-
-		mtspr(SPRN_MAS6, val);
-		asm volatile("tlbsx 0, %[eaddr]" : : [eaddr] "r" (eaddr));
-		val = mfspr(SPRN_MAS1);
-		if (val & MAS1_VALID) {
-			mtspr(SPRN_MAS1, val & ~MAS1_VALID);
-			asm volatile("tlbwe");
-		}
 
-		local_irq_restore(flags);
+	if (tlbsel == 1) {
+		kvmppc_e500_tlbil_all(vcpu_e500);
+		return;
 	}
 
-	preempt_enable();
+	/* Guest tlbe is backed by at most one host tlbe per shadow pid. */
+	kvmppc_e500_tlbil_one(vcpu_e500, gtlbe);
 }
 
 static int tlb0_set_base(gva_t addr, int sets, int ways)
@@ -546,7 +299,7 @@ static void clear_tlb_refs(struct kvmppc_vcpu_e500 *vcpu_e500)
 	int stlbsel = 1;
 	int i;
 
-	kvmppc_e500_id_table_reset_all(vcpu_e500);
+	kvmppc_e500_tlbil_all(vcpu_e500);
 
 	for (i = 0; i < host_tlb_params[stlbsel].entries; i++) {
 		struct tlbe_ref *ref =
@@ -561,19 +314,18 @@ static inline void kvmppc_e500_deliver_tlb_miss(struct kvm_vcpu *vcpu,
 		unsigned int eaddr, int as)
 {
 	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
-	unsigned int victim, pidsel, tsized;
+	unsigned int victim, tsized;
 	int tlbsel;
 
 	/* since we only have two TLBs, only lower bit is used. */
 	tlbsel = (vcpu->arch.shared->mas4 >> 28) & 0x1;
 	victim = (tlbsel == 0) ? gtlb0_get_next_victim(vcpu_e500) : 0;
-	pidsel = (vcpu->arch.shared->mas4 >> 16) & 0xf;
 	tsized = (vcpu->arch.shared->mas4 >> 7) & 0x1f;
 
 	vcpu->arch.shared->mas0 = MAS0_TLBSEL(tlbsel) | MAS0_ESEL(victim)
 		| MAS0_NV(vcpu_e500->gtlb_nv[tlbsel]);
 	vcpu->arch.shared->mas1 = MAS1_VALID | (as ? MAS1_TS : 0)
-		| MAS1_TID(vcpu_e500->pid[pidsel])
+		| MAS1_TID(get_tlbmiss_tid(vcpu))
 		| MAS1_TSIZE(tsized);
 	vcpu->arch.shared->mas2 = (eaddr & MAS2_EPN)
 		| (vcpu->arch.shared->mas4 & MAS2_ATTRIB_MASK);
@@ -585,23 +337,22 @@ static inline void kvmppc_e500_deliver_tlb_miss(struct kvm_vcpu *vcpu,
 
 /* TID must be supplied by the caller */
 static inline void kvmppc_e500_setup_stlbe(
-	struct kvmppc_vcpu_e500 *vcpu_e500,
+	struct kvm_vcpu *vcpu,
 	struct kvm_book3e_206_tlb_entry *gtlbe,
 	int tsize, struct tlbe_ref *ref, u64 gvaddr,
 	struct kvm_book3e_206_tlb_entry *stlbe)
 {
 	pfn_t pfn = ref->pfn;
+	u32 pr = vcpu->arch.shared->msr & MSR_PR;
 
 	BUG_ON(!(ref->flags & E500_TLB_VALID));
 
-	/* Force TS=1 IPROT=0 for all guest mappings. */
-	stlbe->mas1 = MAS1_TSIZE(tsize) | MAS1_TS | MAS1_VALID;
-	stlbe->mas2 = (gvaddr & MAS2_EPN)
-		| e500_shadow_mas2_attrib(gtlbe->mas2,
-				vcpu_e500->vcpu.arch.shared->msr & MSR_PR);
-	stlbe->mas7_3 = ((u64)pfn << PAGE_SHIFT)
-		| e500_shadow_mas3_attrib(gtlbe->mas7_3,
-				vcpu_e500->vcpu.arch.shared->msr & MSR_PR);
+	/* Force IPROT=0 for all guest mappings. */
+	stlbe->mas1 = MAS1_TSIZE(tsize) | get_tlb_sts(gtlbe) | MAS1_VALID;
+	stlbe->mas2 = (gvaddr & MAS2_EPN) |
+		      e500_shadow_mas2_attrib(gtlbe->mas2, pr);
+	stlbe->mas7_3 = ((u64)pfn << PAGE_SHIFT) |
+			e500_shadow_mas3_attrib(gtlbe->mas7_3, pr);
 }
 
 static inline void kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
@@ -735,7 +486,8 @@ static inline void kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
 	kvmppc_e500_ref_release(ref);
 	kvmppc_e500_ref_setup(ref, gtlbe, pfn);
 
-	kvmppc_e500_setup_stlbe(vcpu_e500, gtlbe, tsize, ref, gvaddr, stlbe);
+	kvmppc_e500_setup_stlbe(&vcpu_e500->vcpu, gtlbe, tsize,
+				ref, gvaddr, stlbe);
 }
 
 /* XXX only map the one-one case, for now use TLB0 */
@@ -775,14 +527,6 @@ static int kvmppc_e500_tlb1_map(struct kvmppc_vcpu_e500 *vcpu_e500,
 	return victim;
 }
 
-void kvmppc_mmu_msr_notify(struct kvm_vcpu *vcpu, u32 old_msr)
-{
-	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
-
-	/* Recalc shadow pid since MSR changes */
-	kvmppc_e500_recalc_shadow_pid(vcpu_e500);
-}
-
 static inline int kvmppc_e500_gtlbe_invalidate(
 				struct kvmppc_vcpu_e500 *vcpu_e500,
 				int tlbsel, int esel)
@@ -810,7 +554,7 @@ int kvmppc_e500_emul_mt_mmucsr0(struct kvmppc_vcpu_e500 *vcpu_e500, ulong value)
 			kvmppc_e500_gtlbe_invalidate(vcpu_e500, 1, esel);
 
 	/* Invalidate all vcpu id mappings */
-	kvmppc_e500_id_table_reset_all(vcpu_e500);
+	kvmppc_e500_tlbil_all(vcpu_e500);
 
 	return EMULATE_DONE;
 }
@@ -843,7 +587,7 @@ int kvmppc_e500_emul_tlbivax(struct kvm_vcpu *vcpu, int ra, int rb)
 	}
 
 	/* Invalidate all vcpu id mappings */
-	kvmppc_e500_id_table_reset_all(vcpu_e500);
+	kvmppc_e500_tlbil_all(vcpu_e500);
 
 	return EMULATE_DONE;
 }
@@ -928,9 +672,7 @@ static void write_stlbe(struct kvmppc_vcpu_e500 *vcpu_e500,
 	int stid;
 
 	preempt_disable();
-	stid = kvmppc_e500_get_sid(vcpu_e500, get_tlb_ts(gtlbe),
-				   get_tlb_tid(gtlbe),
-				   get_cur_pr(&vcpu_e500->vcpu), 0);
+	stid = kvmppc_e500_get_tlb_stid(&vcpu_e500->vcpu, gtlbe);
 
 	stlbe->mas1 |= MAS1_TID(stid);
 	write_host_tlbe(vcpu_e500, stlbsel, sesel, stlbe);
@@ -940,8 +682,8 @@ static void write_stlbe(struct kvmppc_vcpu_e500 *vcpu_e500,
 int kvmppc_e500_emul_tlbwe(struct kvm_vcpu *vcpu)
 {
 	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
-	struct kvm_book3e_206_tlb_entry *gtlbe;
-	int tlbsel, esel;
+	struct kvm_book3e_206_tlb_entry *gtlbe, stlbe;
+	int tlbsel, esel, stlbsel, sesel;
 
 	tlbsel = get_tlb_tlbsel(vcpu);
 	esel = get_tlb_esel(vcpu, tlbsel);
@@ -960,8 +702,6 @@ int kvmppc_e500_emul_tlbwe(struct kvm_vcpu *vcpu)
 
 	/* Invalidate shadow mappings for the about-to-be-clobbered TLBE. */
 	if (tlbe_is_host_safe(vcpu, gtlbe)) {
-		struct kvm_book3e_206_tlb_entry stlbe;
-		int stlbsel, sesel;
 		u64 eaddr;
 		u64 raddr;
 
@@ -988,7 +728,7 @@ int kvmppc_e500_emul_tlbwe(struct kvm_vcpu *vcpu)
 			 * are mapped on the fly. */
 			stlbsel = 1;
 			sesel = kvmppc_e500_tlb1_map(vcpu_e500, eaddr,
-					raddr >> PAGE_SHIFT, gtlbe, &stlbe);
+				    raddr >> PAGE_SHIFT, gtlbe, &stlbe);
 			break;
 
 		default:
@@ -1002,6 +742,48 @@ int kvmppc_e500_emul_tlbwe(struct kvm_vcpu *vcpu)
 	return EMULATE_DONE;
 }
 
+static int kvmppc_e500_tlb_search(struct kvm_vcpu *vcpu,
+				  gva_t eaddr, unsigned int pid, int as)
+{
+	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+	int esel, tlbsel;
+
+	for (tlbsel = 0; tlbsel < 2; tlbsel++) {
+		esel = kvmppc_e500_tlb_index(vcpu_e500, eaddr, tlbsel, pid, as);
+		if (esel >= 0)
+			return index_of(tlbsel, esel);
+	}
+
+	return -1;
+}
+
+/* 'linear_address' is actually an encoding of AS|PID|EADDR . */
+int kvmppc_core_vcpu_translate(struct kvm_vcpu *vcpu,
+                               struct kvm_translation *tr)
+{
+	int index;
+	gva_t eaddr;
+	u8 pid;
+	u8 as;
+
+	eaddr = tr->linear_address;
+	pid = (tr->linear_address >> 32) & 0xff;
+	as = (tr->linear_address >> 40) & 0x1;
+
+	index = kvmppc_e500_tlb_search(vcpu, eaddr, pid, as);
+	if (index < 0) {
+		tr->valid = 0;
+		return 0;
+	}
+
+	tr->physical_address = kvmppc_mmu_xlate(vcpu, index, eaddr);
+	/* XXX what does "writeable" and "usermode" even mean? */
+	tr->valid = 1;
+
+	return 0;
+}
+
+
 int kvmppc_mmu_itlb_index(struct kvm_vcpu *vcpu, gva_t eaddr)
 {
 	unsigned int as = !!(vcpu->arch.shared->msr & MSR_IS);
@@ -1065,7 +847,7 @@ void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 eaddr, gpa_t gpaddr,
 		sesel = 0; /* unused */
 		priv = &vcpu_e500->gtlb_priv[tlbsel][esel];
 
-		kvmppc_e500_setup_stlbe(vcpu_e500, gtlbe, BOOK3E_PAGESZ_4K,
+		kvmppc_e500_setup_stlbe(vcpu, gtlbe, BOOK3E_PAGESZ_4K,
 					&priv->ref, eaddr, &stlbe);
 		break;
 
@@ -1086,48 +868,6 @@ void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 eaddr, gpa_t gpaddr,
 	write_stlbe(vcpu_e500, gtlbe, &stlbe, stlbsel, sesel);
 }
 
-int kvmppc_e500_tlb_search(struct kvm_vcpu *vcpu,
-				gva_t eaddr, unsigned int pid, int as)
-{
-	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
-	int esel, tlbsel;
-
-	for (tlbsel = 0; tlbsel < 2; tlbsel++) {
-		esel = kvmppc_e500_tlb_index(vcpu_e500, eaddr, tlbsel, pid, as);
-		if (esel >= 0)
-			return index_of(tlbsel, esel);
-	}
-
-	return -1;
-}
-
-void kvmppc_set_pid(struct kvm_vcpu *vcpu, u32 pid)
-{
-	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
-
-	if (vcpu->arch.pid != pid) {
-		vcpu_e500->pid[0] = vcpu->arch.pid = pid;
-		kvmppc_e500_recalc_shadow_pid(vcpu_e500);
-	}
-}
-
-void kvmppc_e500_tlb_setup(struct kvmppc_vcpu_e500 *vcpu_e500)
-{
-	struct kvm_book3e_206_tlb_entry *tlbe;
-
-	/* Insert large initial mapping for guest. */
-	tlbe = get_entry(vcpu_e500, 1, 0);
-	tlbe->mas1 = MAS1_VALID | MAS1_TSIZE(BOOK3E_PAGESZ_256M);
-	tlbe->mas2 = 0;
-	tlbe->mas7_3 = E500_TLB_SUPER_PERM_MASK;
-
-	/* 4K map for serial output. Used by kernel wrapper. */
-	tlbe = get_entry(vcpu_e500, 1, 1);
-	tlbe->mas1 = MAS1_VALID | MAS1_TSIZE(BOOK3E_PAGESZ_4K);
-	tlbe->mas2 = (0xe0004500 & 0xFFFFF000) | MAS2_I | MAS2_G;
-	tlbe->mas7_3 = (0xe0004500 & 0xFFFFF000) | E500_TLB_SUPER_PERM_MASK;
-}
-
 static void free_gtlb(struct kvmppc_vcpu_e500 *vcpu_e500)
 {
 	int i;
@@ -1154,6 +894,36 @@ static void free_gtlb(struct kvmppc_vcpu_e500 *vcpu_e500)
 	vcpu_e500->gtlb_arch = NULL;
 }
 
+void kvmppc_get_sregs_e500_tlb(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
+{
+	sregs->u.e.mas0 = vcpu->arch.shared->mas0;
+	sregs->u.e.mas1 = vcpu->arch.shared->mas1;
+	sregs->u.e.mas2 = vcpu->arch.shared->mas2;
+	sregs->u.e.mas7_3 = vcpu->arch.shared->mas7_3;
+	sregs->u.e.mas4 = vcpu->arch.shared->mas4;
+	sregs->u.e.mas6 = vcpu->arch.shared->mas6;
+
+	sregs->u.e.mmucfg = vcpu->arch.mmucfg;
+	sregs->u.e.tlbcfg[0] = vcpu->arch.tlbcfg[0];
+	sregs->u.e.tlbcfg[1] = vcpu->arch.tlbcfg[1];
+	sregs->u.e.tlbcfg[2] = 0;
+	sregs->u.e.tlbcfg[3] = 0;
+}
+
+int kvmppc_set_sregs_e500_tlb(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
+{
+	if (sregs->u.e.features & KVM_SREGS_E_ARCH206_MMU) {
+		vcpu->arch.shared->mas0 = sregs->u.e.mas0;
+		vcpu->arch.shared->mas1 = sregs->u.e.mas1;
+		vcpu->arch.shared->mas2 = sregs->u.e.mas2;
+		vcpu->arch.shared->mas7_3 = sregs->u.e.mas7_3;
+		vcpu->arch.shared->mas4 = sregs->u.e.mas4;
+		vcpu->arch.shared->mas6 = sregs->u.e.mas6;
+	}
+
+	return 0;
+}
+
 int kvm_vcpu_ioctl_config_tlb(struct kvm_vcpu *vcpu,
 			      struct kvm_config_tlb *cfg)
 {
@@ -1237,14 +1007,16 @@ int kvm_vcpu_ioctl_config_tlb(struct kvm_vcpu *vcpu,
 	vcpu_e500->gtlb_offset[0] = 0;
 	vcpu_e500->gtlb_offset[1] = params.tlb_sizes[0];
 
-	vcpu_e500->tlb0cfg &= ~(TLBnCFG_N_ENTRY | TLBnCFG_ASSOC);
+	vcpu->arch.mmucfg = mfspr(SPRN_MMUCFG) & ~MMUCFG_LPIDSIZE;
+
+	vcpu->arch.tlbcfg[0] &= ~(TLBnCFG_N_ENTRY | TLBnCFG_ASSOC);
 	if (params.tlb_sizes[0] <= 2048)
-		vcpu_e500->tlb0cfg |= params.tlb_sizes[0];
-	vcpu_e500->tlb0cfg |= params.tlb_ways[0] << TLBnCFG_ASSOC_SHIFT;
+		vcpu->arch.tlbcfg[0] |= params.tlb_sizes[0];
+	vcpu->arch.tlbcfg[0] |= params.tlb_ways[0] << TLBnCFG_ASSOC_SHIFT;
 
-	vcpu_e500->tlb1cfg &= ~(TLBnCFG_N_ENTRY | TLBnCFG_ASSOC);
-	vcpu_e500->tlb1cfg |= params.tlb_sizes[1];
-	vcpu_e500->tlb1cfg |= params.tlb_ways[1] << TLBnCFG_ASSOC_SHIFT;
+	vcpu->arch.tlbcfg[1] &= ~(TLBnCFG_N_ENTRY | TLBnCFG_ASSOC);
+	vcpu->arch.tlbcfg[1] |= params.tlb_sizes[1];
+	vcpu->arch.tlbcfg[1] |= params.tlb_ways[1] << TLBnCFG_ASSOC_SHIFT;
 
 	vcpu_e500->shared_tlb_pages = pages;
 	vcpu_e500->num_shared_tlb_pages = num_pages;
@@ -1280,6 +1052,7 @@ int kvm_vcpu_ioctl_dirty_tlb(struct kvm_vcpu *vcpu,
 
 int kvmppc_e500_tlb_init(struct kvmppc_vcpu_e500 *vcpu_e500)
 {
+	struct kvm_vcpu *vcpu = &vcpu_e500->vcpu;
 	int entry_size = sizeof(struct kvm_book3e_206_tlb_entry);
 	int entries = KVM_E500_TLB0_SIZE + KVM_E500_TLB1_SIZE;
 
@@ -1356,20 +1129,17 @@ int kvmppc_e500_tlb_init(struct kvmppc_vcpu_e500 *vcpu_e500)
 	if (!vcpu_e500->gtlb_priv[1])
 		goto err;
 
-	if (kvmppc_e500_id_table_alloc(vcpu_e500) == NULL)
-		goto err;
-
 	/* Init TLB configuration register */
-	vcpu_e500->tlb0cfg = mfspr(SPRN_TLB0CFG) &
+	vcpu->arch.tlbcfg[0] = mfspr(SPRN_TLB0CFG) &
 			     ~(TLBnCFG_N_ENTRY | TLBnCFG_ASSOC);
-	vcpu_e500->tlb0cfg |= vcpu_e500->gtlb_params[0].entries;
-	vcpu_e500->tlb0cfg |=
+	vcpu->arch.tlbcfg[0] |= vcpu_e500->gtlb_params[0].entries;
+	vcpu->arch.tlbcfg[0] |=
 		vcpu_e500->gtlb_params[0].ways << TLBnCFG_ASSOC_SHIFT;
 
-	vcpu_e500->tlb1cfg = mfspr(SPRN_TLB1CFG) &
+	vcpu->arch.tlbcfg[1] = mfspr(SPRN_TLB1CFG) &
 			     ~(TLBnCFG_N_ENTRY | TLBnCFG_ASSOC);
-	vcpu_e500->tlb0cfg |= vcpu_e500->gtlb_params[1].entries;
-	vcpu_e500->tlb0cfg |=
+	vcpu->arch.tlbcfg[0] |= vcpu_e500->gtlb_params[1].entries;
+	vcpu->arch.tlbcfg[0] |=
 		vcpu_e500->gtlb_params[1].ways << TLBnCFG_ASSOC_SHIFT;
 
 	return 0;
@@ -1384,8 +1154,6 @@ int kvmppc_e500_tlb_init(struct kvmppc_vcpu_e500 *vcpu_e500)
 void kvmppc_e500_tlb_uninit(struct kvmppc_vcpu_e500 *vcpu_e500)
 {
 	free_gtlb(vcpu_e500);
-	kvmppc_e500_id_table_free(vcpu_e500);
-
 	kfree(vcpu_e500->tlb_refs[0]);
 	kfree(vcpu_e500->tlb_refs[1]);
 }