Merge 'git://github.com/agraf/linux-2.6.git kvm-ppc-next' into queue

Documentation/virtual/kvm/api.txt

@@ -1788,6 +1788,10 @@ registers, find a list below:
   PPC   | KVM_REG_PPC_VPA_DTL   | 128
   PPC   | KVM_REG_PPC_EPCR	| 32
   PPC   | KVM_REG_PPC_EPR	| 32
+  PPC   | KVM_REG_PPC_TCR	| 32
+  PPC   | KVM_REG_PPC_TSR	| 32
+  PPC   | KVM_REG_PPC_OR_TSR	| 32
+  PPC   | KVM_REG_PPC_CLEAR_TSR	| 32
 
 ARM registers are mapped using the lower 32 bits.  The upper 16 of that
 is the register group type, or coprocessor number:

arch/powerpc/include/asm/kvm_host.h

@@ -504,6 +504,7 @@ struct kvm_vcpu_arch {
 	u32 tlbcfg[4];
 	u32 mmucfg;
 	u32 epr;
+	u32 crit_save;
 	struct kvmppc_booke_debug_reg dbg_reg;
 #endif
 	gpa_t paddr_accessed;

arch/powerpc/include/asm/kvm_ppc.h

@@ -104,8 +104,7 @@ extern void kvmppc_core_queue_dec(struct kvm_vcpu *vcpu);
 extern void kvmppc_core_dequeue_dec(struct kvm_vcpu *vcpu);
 extern void kvmppc_core_queue_external(struct kvm_vcpu *vcpu,
                                        struct kvm_interrupt *irq);
-extern void kvmppc_core_dequeue_external(struct kvm_vcpu *vcpu,
-                                         struct kvm_interrupt *irq);
+extern void kvmppc_core_dequeue_external(struct kvm_vcpu *vcpu);
 extern void kvmppc_core_flush_tlb(struct kvm_vcpu *vcpu);
 
 extern int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,

arch/powerpc/include/uapi/asm/kvm.h

@@ -417,4 +417,9 @@ struct kvm_get_htab_header {
 #define KVM_REG_PPC_EPCR	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x85)
 #define KVM_REG_PPC_EPR		(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x86)
 
+/* Timer Status Register OR/CLEAR interface */
+#define KVM_REG_PPC_OR_TSR	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x87)
+#define KVM_REG_PPC_CLEAR_TSR	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x88)
+#define KVM_REG_PPC_TCR		(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x89)
+#define KVM_REG_PPC_TSR		(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x8a)
 #endif /* __LINUX_KVM_POWERPC_H */

arch/powerpc/kernel/asm-offsets.c

@@ -596,6 +596,7 @@ int main(void)
 	DEFINE(VCPU_LAST_INST, offsetof(struct kvm_vcpu, arch.last_inst));
 	DEFINE(VCPU_FAULT_DEAR, offsetof(struct kvm_vcpu, arch.fault_dear));
 	DEFINE(VCPU_FAULT_ESR, offsetof(struct kvm_vcpu, arch.fault_esr));
+	DEFINE(VCPU_CRIT_SAVE, offsetof(struct kvm_vcpu, arch.crit_save));
 #endif /* CONFIG_PPC_BOOK3S */
 #endif /* CONFIG_KVM */
 

arch/powerpc/kvm/book3s.c

@@ -160,8 +160,7 @@ void kvmppc_core_queue_external(struct kvm_vcpu *vcpu,
 	kvmppc_book3s_queue_irqprio(vcpu, vec);
 }
 
-void kvmppc_core_dequeue_external(struct kvm_vcpu *vcpu,
-                                  struct kvm_interrupt *irq)
+void kvmppc_core_dequeue_external(struct kvm_vcpu *vcpu)
 {
 	kvmppc_book3s_dequeue_irqprio(vcpu, BOOK3S_INTERRUPT_EXTERNAL);
 	kvmppc_book3s_dequeue_irqprio(vcpu, BOOK3S_INTERRUPT_EXTERNAL_LEVEL);

arch/powerpc/kvm/booke.c

@@ -222,8 +222,7 @@ void kvmppc_core_queue_external(struct kvm_vcpu *vcpu,
 	kvmppc_booke_queue_irqprio(vcpu, prio);
 }
 
-void kvmppc_core_dequeue_external(struct kvm_vcpu *vcpu,
-                                  struct kvm_interrupt *irq)
+void kvmppc_core_dequeue_external(struct kvm_vcpu *vcpu)
 {
 	clear_bit(BOOKE_IRQPRIO_EXTERNAL, &vcpu->arch.pending_exceptions);
 	clear_bit(BOOKE_IRQPRIO_EXTERNAL_LEVEL, &vcpu->arch.pending_exceptions);
@@ -1148,6 +1147,18 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	return r;
 }
 
+static void kvmppc_set_tsr(struct kvm_vcpu *vcpu, u32 new_tsr)
+{
+	u32 old_tsr = vcpu->arch.tsr;
+
+	vcpu->arch.tsr = new_tsr;
+
+	if ((old_tsr ^ vcpu->arch.tsr) & (TSR_ENW | TSR_WIS))
+		arm_next_watchdog(vcpu);
+
+	update_timer_ints(vcpu);
+}
+
 /* Initial guest state: 16MB mapping 0 -> 0, PC = 0, MSR = 0, R1 = 16MB */
 int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 {
@@ -1287,16 +1298,8 @@ static int set_sregs_base(struct kvm_vcpu *vcpu,
 		kvmppc_emulate_dec(vcpu);
 	}
 
-	if (sregs->u.e.update_special & KVM_SREGS_E_UPDATE_TSR) {
-		u32 old_tsr = vcpu->arch.tsr;
-
-		vcpu->arch.tsr = sregs->u.e.tsr;
-
-		if ((old_tsr ^ vcpu->arch.tsr) & (TSR_ENW | TSR_WIS))
-			arm_next_watchdog(vcpu);
-
-		update_timer_ints(vcpu);
-	}
+	if (sregs->u.e.update_special & KVM_SREGS_E_UPDATE_TSR)
+		kvmppc_set_tsr(vcpu, sregs->u.e.tsr);
 
 	return 0;
 }
@@ -1438,6 +1441,12 @@ int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
 		r = put_user(vcpu->arch.epcr, (u32 __user *)(long)reg->addr);
 		break;
 #endif
+	case KVM_REG_PPC_TCR:
+		r = put_user(vcpu->arch.tcr, (u32 __user *)(long)reg->addr);
+		break;
+	case KVM_REG_PPC_TSR:
+		r = put_user(vcpu->arch.tsr, (u32 __user *)(long)reg->addr);
+		break;
 	default:
 		break;
 	}
@@ -1481,6 +1490,30 @@ int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
 		break;
 	}
 #endif
+	case KVM_REG_PPC_OR_TSR: {
+		u32 tsr_bits;
+		r = get_user(tsr_bits, (u32 __user *)(long)reg->addr);
+		kvmppc_set_tsr_bits(vcpu, tsr_bits);
+		break;
+	}
+	case KVM_REG_PPC_CLEAR_TSR: {
+		u32 tsr_bits;
+		r = get_user(tsr_bits, (u32 __user *)(long)reg->addr);
+		kvmppc_clr_tsr_bits(vcpu, tsr_bits);
+		break;
+	}
+	case KVM_REG_PPC_TSR: {
+		u32 tsr;
+		r = get_user(tsr, (u32 __user *)(long)reg->addr);
+		kvmppc_set_tsr(vcpu, tsr);
+		break;
+	}
+	case KVM_REG_PPC_TCR: {
+		u32 tcr;
+		r = get_user(tcr, (u32 __user *)(long)reg->addr);
+		kvmppc_set_tcr(vcpu, tcr);
+		break;
+	}
 	default:
 		break;
 	}

arch/powerpc/kvm/booke_interrupts.S

@@ -54,8 +54,7 @@
                        (1<<BOOKE_INTERRUPT_DTLB_MISS) | \
                        (1<<BOOKE_INTERRUPT_ALIGNMENT))
 
-.macro KVM_HANDLER ivor_nr scratch srr0
-_GLOBAL(kvmppc_handler_\ivor_nr)
+.macro __KVM_HANDLER ivor_nr scratch srr0
 	/* Get pointer to vcpu and record exit number. */
 	mtspr	\scratch , r4
 	mfspr   r4, SPRN_SPRG_THREAD
@@ -76,6 +75,43 @@ _GLOBAL(kvmppc_handler_\ivor_nr)
 	bctr
 .endm
 
+.macro KVM_HANDLER ivor_nr scratch srr0
+_GLOBAL(kvmppc_handler_\ivor_nr)
+	__KVM_HANDLER \ivor_nr \scratch \srr0
+.endm
+
+.macro KVM_DBG_HANDLER ivor_nr scratch srr0
+_GLOBAL(kvmppc_handler_\ivor_nr)
+	mtspr   \scratch, r4
+	mfspr	r4, SPRN_SPRG_THREAD
+	lwz	r4, THREAD_KVM_VCPU(r4)
+	stw	r3, VCPU_CRIT_SAVE(r4)
+	mfcr	r3
+	mfspr	r4, SPRN_CSRR1
+	andi.	r4, r4, MSR_PR
+	bne	1f
+	/* debug interrupt happened in enter/exit path */
+	mfspr   r4, SPRN_CSRR1
+	rlwinm  r4, r4, 0, ~MSR_DE
+	mtspr   SPRN_CSRR1, r4
+	lis	r4, 0xffff
+	ori	r4, r4, 0xffff
+	mtspr	SPRN_DBSR, r4
+	mfspr	r4, SPRN_SPRG_THREAD
+	lwz	r4, THREAD_KVM_VCPU(r4)
+	mtcr	r3
+	lwz     r3, VCPU_CRIT_SAVE(r4)
+	mfspr   r4, \scratch
+	rfci
+1:	/* debug interrupt happened in guest */
+	mtcr	r3
+	mfspr	r4, SPRN_SPRG_THREAD
+	lwz	r4, THREAD_KVM_VCPU(r4)
+	lwz     r3, VCPU_CRIT_SAVE(r4)
+	mfspr   r4, \scratch
+	__KVM_HANDLER \ivor_nr \scratch \srr0
+.endm
+
 .macro KVM_HANDLER_ADDR ivor_nr
 	.long	kvmppc_handler_\ivor_nr
 .endm
@@ -100,7 +136,7 @@ KVM_HANDLER BOOKE_INTERRUPT_FIT SPRN_SPRG_RSCRATCH0 SPRN_SRR0
 KVM_HANDLER BOOKE_INTERRUPT_WATCHDOG SPRN_SPRG_RSCRATCH_CRIT SPRN_CSRR0
 KVM_HANDLER BOOKE_INTERRUPT_DTLB_MISS SPRN_SPRG_RSCRATCH0 SPRN_SRR0
 KVM_HANDLER BOOKE_INTERRUPT_ITLB_MISS SPRN_SPRG_RSCRATCH0 SPRN_SRR0
-KVM_HANDLER BOOKE_INTERRUPT_DEBUG SPRN_SPRG_RSCRATCH_CRIT SPRN_CSRR0
+KVM_DBG_HANDLER BOOKE_INTERRUPT_DEBUG SPRN_SPRG_RSCRATCH_CRIT SPRN_CSRR0
 KVM_HANDLER BOOKE_INTERRUPT_SPE_UNAVAIL SPRN_SPRG_RSCRATCH0 SPRN_SRR0
 KVM_HANDLER BOOKE_INTERRUPT_SPE_FP_DATA SPRN_SPRG_RSCRATCH0 SPRN_SRR0
 KVM_HANDLER BOOKE_INTERRUPT_SPE_FP_ROUND SPRN_SPRG_RSCRATCH0 SPRN_SRR0

arch/powerpc/kvm/e500.h

@@ -26,17 +26,20 @@
 #define E500_PID_NUM   3
 #define E500_TLB_NUM   2
 
-#define E500_TLB_VALID 1
-#define E500_TLB_BITMAP 2
+/* entry is mapped somewhere in host TLB */
+#define E500_TLB_VALID		(1 << 0)
+/* TLB1 entry is mapped by host TLB1, tracked by bitmaps */
+#define E500_TLB_BITMAP		(1 << 1)
+/* TLB1 entry is mapped by host TLB0 */
 #define E500_TLB_TLB0		(1 << 2)
 
 struct tlbe_ref {
-	pfn_t pfn;
+	pfn_t pfn;		/* valid only for TLB0, except briefly */
 	unsigned int flags;	/* E500_TLB_* */
 };
 
 struct tlbe_priv {
-	struct tlbe_ref ref; /* TLB0 only -- TLB1 uses tlb_refs */
+	struct tlbe_ref ref;
 };
 
 #ifdef CONFIG_KVM_E500V2
@@ -63,17 +66,6 @@ struct kvmppc_vcpu_e500 {
 
 	unsigned int gtlb_nv[E500_TLB_NUM];
 
-	/*
-	 * information associated with each host TLB entry --
-	 * TLB1 only for now.  If/when guest TLB1 entries can be
-	 * mapped with host TLB0, this will be used for that too.
-	 *
-	 * We don't want to use this for guest TLB0 because then we'd
-	 * have the overhead of doing the translation again even if
-	 * the entry is still in the guest TLB (e.g. we swapped out
-	 * and back, and our host TLB entries got evicted).
-	 */
-	struct tlbe_ref *tlb_refs[E500_TLB_NUM];
 	unsigned int host_tlb1_nv;
 
 	u32 svr;

arch/powerpc/kvm/e500_mmu_host.c

@@ -193,8 +193,11 @@ void inval_gtlbe_on_host(struct kvmppc_vcpu_e500 *vcpu_e500, int tlbsel,
 	struct tlbe_ref *ref = &vcpu_e500->gtlb_priv[tlbsel][esel].ref;
 
 	/* Don't bother with unmapped entries */
-	if (!(ref->flags & E500_TLB_VALID))
-		return;
+	if (!(ref->flags & E500_TLB_VALID)) {
+		WARN(ref->flags & (E500_TLB_BITMAP | E500_TLB_TLB0),
+		     "%s: flags %x\n", __func__, ref->flags);
+		WARN_ON(tlbsel == 1 && vcpu_e500->g2h_tlb1_map[esel]);
+	}
 
 	if (tlbsel == 1 && ref->flags & E500_TLB_BITMAP) {
 		u64 tmp = vcpu_e500->g2h_tlb1_map[esel];
@@ -248,7 +251,7 @@ static inline void kvmppc_e500_ref_setup(struct tlbe_ref *ref,
 					 pfn_t pfn)
 {
 	ref->pfn = pfn;
-	ref->flags = E500_TLB_VALID;
+	ref->flags |= E500_TLB_VALID;
 
 	if (tlbe_is_writable(gtlbe))
 		kvm_set_pfn_dirty(pfn);
@@ -257,6 +260,7 @@ static inline void kvmppc_e500_ref_setup(struct tlbe_ref *ref,
 static inline void kvmppc_e500_ref_release(struct tlbe_ref *ref)
 {
 	if (ref->flags & E500_TLB_VALID) {
+		/* FIXME: don't log bogus pfn for TLB1 */
 		trace_kvm_booke206_ref_release(ref->pfn, ref->flags);
 		ref->flags = 0;
 	}
@@ -274,36 +278,23 @@ static void clear_tlb1_bitmap(struct kvmppc_vcpu_e500 *vcpu_e500)
 
 static void clear_tlb_privs(struct kvmppc_vcpu_e500 *vcpu_e500)
 {
-	int tlbsel = 0;
+	int tlbsel;
 	int i;
 
+	for (tlbsel = 0; tlbsel <= 1; tlbsel++) {
 		for (i = 0; i < vcpu_e500->gtlb_params[tlbsel].entries; i++) {
 			struct tlbe_ref *ref =
 				&vcpu_e500->gtlb_priv[tlbsel][i].ref;
 			kvmppc_e500_ref_release(ref);
 		}
-}
-
-static void clear_tlb_refs(struct kvmppc_vcpu_e500 *vcpu_e500)
-{
-	int stlbsel = 1;
-	int i;
-
-	kvmppc_e500_tlbil_all(vcpu_e500);
-
-	for (i = 0; i < host_tlb_params[stlbsel].entries; i++) {
-		struct tlbe_ref *ref =
-			&vcpu_e500->tlb_refs[stlbsel][i];
-		kvmppc_e500_ref_release(ref);
 	}
-
-	clear_tlb_privs(vcpu_e500);
 }
 
 void kvmppc_core_flush_tlb(struct kvm_vcpu *vcpu)
 {
 	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
-	clear_tlb_refs(vcpu_e500);
+	kvmppc_e500_tlbil_all(vcpu_e500);
+	clear_tlb_privs(vcpu_e500);
 	clear_tlb1_bitmap(vcpu_e500);
 }
 
@@ -458,8 +449,6 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
 		gvaddr &= ~((tsize_pages << PAGE_SHIFT) - 1);
 	}
 
-	/* Drop old ref and setup new one. */
-	kvmppc_e500_ref_release(ref);
 	kvmppc_e500_ref_setup(ref, gtlbe, pfn);
 
 	kvmppc_e500_setup_stlbe(&vcpu_e500->vcpu, gtlbe, tsize,
@@ -507,14 +496,15 @@ static int kvmppc_e500_tlb1_map_tlb1(struct kvmppc_vcpu_e500 *vcpu_e500,
 	if (unlikely(vcpu_e500->host_tlb1_nv >= tlb1_max_shadow_size()))
 		vcpu_e500->host_tlb1_nv = 0;
 
-	vcpu_e500->tlb_refs[1][sesel] = *ref;
-	vcpu_e500->g2h_tlb1_map[esel] |= (u64)1 << sesel;
-	vcpu_e500->gtlb_priv[1][esel].ref.flags |= E500_TLB_BITMAP;
 	if (vcpu_e500->h2g_tlb1_rmap[sesel]) {
-		unsigned int idx = vcpu_e500->h2g_tlb1_rmap[sesel];
+		unsigned int idx = vcpu_e500->h2g_tlb1_rmap[sesel] - 1;
 		vcpu_e500->g2h_tlb1_map[idx] &= ~(1ULL << sesel);
 	}
-	vcpu_e500->h2g_tlb1_rmap[sesel] = esel;
+
+	vcpu_e500->gtlb_priv[1][esel].ref.flags |= E500_TLB_BITMAP;
+	vcpu_e500->g2h_tlb1_map[esel] |= (u64)1 << sesel;
+	vcpu_e500->h2g_tlb1_rmap[sesel] = esel + 1;
+	WARN_ON(!(ref->flags & E500_TLB_VALID));
 
 	return sesel;
 }
@@ -526,13 +516,12 @@ static int kvmppc_e500_tlb1_map(struct kvmppc_vcpu_e500 *vcpu_e500,
 		u64 gvaddr, gfn_t gfn, struct kvm_book3e_206_tlb_entry *gtlbe,
 		struct kvm_book3e_206_tlb_entry *stlbe, int esel)
 {
-	struct tlbe_ref ref;
+	struct tlbe_ref *ref = &vcpu_e500->gtlb_priv[1][esel].ref;
 	int sesel;
 	int r;
 
-	ref.flags = 0;
 	r = kvmppc_e500_shadow_map(vcpu_e500, gvaddr, gfn, gtlbe, 1, stlbe,
-				   &ref);
+				   ref);
 	if (r)
 		return r;
 
@@ -544,7 +533,7 @@ static int kvmppc_e500_tlb1_map(struct kvmppc_vcpu_e500 *vcpu_e500,
 	}
 
 	/* Otherwise map into TLB1 */
-	sesel = kvmppc_e500_tlb1_map_tlb1(vcpu_e500, &ref, esel);
+	sesel = kvmppc_e500_tlb1_map_tlb1(vcpu_e500, ref, esel);
 	write_stlbe(vcpu_e500, gtlbe, stlbe, 1, sesel);
 
 	return 0;
@@ -565,7 +554,7 @@ void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 eaddr, gpa_t gpaddr,
 	case 0:
 		priv = &vcpu_e500->gtlb_priv[tlbsel][esel];
 
-		/* Triggers after clear_tlb_refs or on initial mapping */
+		/* Triggers after clear_tlb_privs or on initial mapping */
 		if (!(priv->ref.flags & E500_TLB_VALID)) {
 			kvmppc_e500_tlb0_map(vcpu_e500, esel, &stlbe);
 		} else {
@@ -665,35 +654,16 @@ int e500_mmu_host_init(struct kvmppc_vcpu_e500 *vcpu_e500)
 		host_tlb_params[0].entries / host_tlb_params[0].ways;
 	host_tlb_params[1].sets = 1;
 
-	vcpu_e500->tlb_refs[0] =
-		kzalloc(sizeof(struct tlbe_ref) * host_tlb_params[0].entries,
-			GFP_KERNEL);
-	if (!vcpu_e500->tlb_refs[0])
-		goto err;
-
-	vcpu_e500->tlb_refs[1] =
-		kzalloc(sizeof(struct tlbe_ref) * host_tlb_params[1].entries,
-			GFP_KERNEL);
-	if (!vcpu_e500->tlb_refs[1])
-		goto err;
-
 	vcpu_e500->h2g_tlb1_rmap = kzalloc(sizeof(unsigned int) *
 					   host_tlb_params[1].entries,
 					   GFP_KERNEL);
 	if (!vcpu_e500->h2g_tlb1_rmap)
-		goto err;
+		return -EINVAL;
 
 	return 0;
-
-err:
-	kfree(vcpu_e500->tlb_refs[0]);
-	kfree(vcpu_e500->tlb_refs[1]);
-	return -EINVAL;
 }
 
 void e500_mmu_host_uninit(struct kvmppc_vcpu_e500 *vcpu_e500)
 {
 	kfree(vcpu_e500->h2g_tlb1_rmap);
-	kfree(vcpu_e500->tlb_refs[0]);
-	kfree(vcpu_e500->tlb_refs[1]);
 }

arch/powerpc/kvm/powerpc.c

@@ -739,7 +739,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, struct kvm_interrupt *irq)
 {
 	if (irq->irq == KVM_INTERRUPT_UNSET) {
-		kvmppc_core_dequeue_external(vcpu, irq);
+		kvmppc_core_dequeue_external(vcpu);
 		return 0;
 	}