KVM: PPC: Book3S HV: Implement timebase offset for guests

This allows guests to have a different timebase origin from the host.
This is needed for migration, where a guest can migrate from one host
to another and the two hosts might have a different timebase origin.
However, the timebase seen by the guest must not go backwards, and
should go forwards only by a small amount corresponding to the time
taken for the migration.

Therefore this provides a new per-vcpu value accessed via the one_reg
interface using the new KVM_REG_PPC_TB_OFFSET identifier.  This value
defaults to 0 and is not modified by KVM.  On entering the guest, this
value is added onto the timebase, and on exiting the guest, it is
subtracted from the timebase.

This is only supported for recent POWER hardware which has the TBU40
(timebase upper 40 bits) register.  Writing to the TBU40 register only
alters the upper 40 bits of the timebase, leaving the lower 24 bits
unchanged.  This provides a way to modify the timebase for guest
migration without disturbing the synchronization of the timebase
registers across CPU cores.  The kernel rounds up the value given
to a multiple of 2^24.

Timebase values stored in KVM structures (struct kvm_vcpu, struct
kvmppc_vcore, etc.) are stored as host timebase values.  The timebase
values in the dispatch trace log need to be guest timebase values,
however, since that is read directly by the guest.  This moves the
setting of vcpu->arch.dec_expires on guest exit to a point after we
have restored the host timebase so that vcpu->arch.dec_expires is a
host timebase value.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>

Documentation/virtual/kvm/api.txt

@@ -1810,6 +1810,7 @@ registers, find a list below:
   PPC   | KVM_REG_PPC_TLB3PS	| 32
   PPC   | KVM_REG_PPC_EPTCFG	| 32
   PPC   | KVM_REG_PPC_ICP_STATE | 64
+  PPC   | KVM_REG_PPC_TB_OFFSET	| 64
   PPC   | KVM_REG_PPC_SPMC1	| 32
   PPC   | KVM_REG_PPC_SPMC2	| 32
   PPC   | KVM_REG_PPC_IAMR	| 64

arch/powerpc/include/asm/kvm_host.h

@@ -289,6 +289,7 @@ struct kvmppc_vcore {
 	u64 stolen_tb;
 	u64 preempt_tb;
 	struct kvm_vcpu *runner;
+	u64 tb_offset;		/* guest timebase - host timebase */
 };
 
 #define VCORE_ENTRY_COUNT(vc)	((vc)->entry_exit_count & 0xff)

arch/powerpc/include/asm/reg.h

@@ -243,6 +243,7 @@
 #define SPRN_TBRU	0x10D	/* Time Base Read Upper Register (user, R/O) */
 #define SPRN_TBWL	0x11C	/* Time Base Lower Register (super, R/W) */
 #define SPRN_TBWU	0x11D	/* Time Base Upper Register (super, R/W) */
+#define SPRN_TBU40	0x11E	/* Timebase upper 40 bits (hyper, R/W) */
 #define SPRN_SPURR	0x134	/* Scaled PURR */
 #define SPRN_HSPRG0	0x130	/* Hypervisor Scratch 0 */
 #define SPRN_HSPRG1	0x131	/* Hypervisor Scratch 1 */

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

@@ -504,6 +504,9 @@ struct kvm_get_htab_header {
 #define KVM_REG_PPC_TLB3PS	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x9a)
 #define KVM_REG_PPC_EPTCFG	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x9b)
 
+/* Timebase offset */
+#define KVM_REG_PPC_TB_OFFSET	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x9c)
+
 /* POWER8 registers */
 #define KVM_REG_PPC_SPMC1	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x9d)
 #define KVM_REG_PPC_SPMC2	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x9e)

arch/powerpc/kernel/asm-offsets.c

@@ -523,6 +523,7 @@ int main(void)
 	DEFINE(VCORE_NAP_COUNT, offsetof(struct kvmppc_vcore, nap_count));
 	DEFINE(VCORE_IN_GUEST, offsetof(struct kvmppc_vcore, in_guest));
 	DEFINE(VCORE_NAPPING_THREADS, offsetof(struct kvmppc_vcore, napping_threads));
+	DEFINE(VCORE_TB_OFFSET, offsetof(struct kvmppc_vcore, tb_offset));
 	DEFINE(VCPU_SVCPU, offsetof(struct kvmppc_vcpu_book3s, shadow_vcpu) -
 			   offsetof(struct kvmppc_vcpu_book3s, vcpu));
 	DEFINE(VCPU_SLB_E, offsetof(struct kvmppc_slb, orige));

arch/powerpc/kvm/book3s_hv.c

@@ -489,7 +489,7 @@ static void kvmppc_create_dtl_entry(struct kvm_vcpu *vcpu,
 	memset(dt, 0, sizeof(struct dtl_entry));
 	dt->dispatch_reason = 7;
 	dt->processor_id = vc->pcpu + vcpu->arch.ptid;
-	dt->timebase = now;
+	dt->timebase = now + vc->tb_offset;
 	dt->enqueue_to_dispatch_time = stolen;
 	dt->srr0 = kvmppc_get_pc(vcpu);
 	dt->srr1 = vcpu->arch.shregs.msr;
@@ -793,6 +793,9 @@ int kvmppc_get_one_reg(struct kvm_vcpu *vcpu, u64 id, union kvmppc_one_reg *val)
 		val->vpaval.length = vcpu->arch.dtl.len;
 		spin_unlock(&vcpu->arch.vpa_update_lock);
 		break;
+	case KVM_REG_PPC_TB_OFFSET:
+		*val = get_reg_val(id, vcpu->arch.vcore->tb_offset);
+		break;
 	default:
 		r = -EINVAL;
 		break;
@@ -892,6 +895,11 @@ int kvmppc_set_one_reg(struct kvm_vcpu *vcpu, u64 id, union kvmppc_one_reg *val)
 		len -= len % sizeof(struct dtl_entry);
 		r = set_vpa(vcpu, &vcpu->arch.dtl, addr, len);
 		break;
+	case KVM_REG_PPC_TB_OFFSET:
+		/* round up to multiple of 2^24 */
+		vcpu->arch.vcore->tb_offset =
+			ALIGN(set_reg_val(id, *val), 1UL << 24);
+		break;
 	default:
 		r = -EINVAL;
 		break;

arch/powerpc/kvm/book3s_hv_rmhandlers.S

@@ -347,7 +347,22 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
 	bdnz	28b
 	ptesync
 
-22:	li	r0,1
+	/* Add timebase offset onto timebase */
+22:	ld	r8,VCORE_TB_OFFSET(r5)
+	cmpdi	r8,0
+	beq	37f
+	mftb	r6		/* current host timebase */
+	add	r8,r8,r6
+	mtspr	SPRN_TBU40,r8	/* update upper 40 bits */
+	mftb	r7		/* check if lower 24 bits overflowed */
+	clrldi	r6,r6,40
+	clrldi	r7,r7,40
+	cmpld	r7,r6
+	bge	37f
+	addis	r8,r8,0x100	/* if so, increment upper 40 bits */
+	mtspr	SPRN_TBU40,r8
+
+37:	li	r0,1
 	stb	r0,VCORE_IN_GUEST(r5)	/* signal secondaries to continue */
 	b	10f
 
@@ -782,13 +797,6 @@ ext_stash_for_host:
 ext_interrupt_to_host:
 
 guest_exit_cont:		/* r9 = vcpu, r12 = trap, r13 = paca */
-	/* Save DEC */
-	mfspr	r5,SPRN_DEC
-	mftb	r6
-	extsw	r5,r5
-	add	r5,r5,r6
-	std	r5,VCPU_DEC_EXPIRES(r9)
-
 	/* Save more register state  */
 	mfdar	r6
 	mfdsisr	r7
@@ -958,7 +966,24 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
 	mtspr	SPRN_SDR1,r6		/* switch to partition page table */
 	mtspr	SPRN_LPID,r7
 	isync
-	li	r0,0
+
+	/* Subtract timebase offset from timebase */
+	ld	r8,VCORE_TB_OFFSET(r5)
+	cmpdi	r8,0
+	beq	17f
+	mftb	r6			/* current host timebase */
+	subf	r8,r8,r6
+	mtspr	SPRN_TBU40,r8		/* update upper 40 bits */
+	mftb	r7			/* check if lower 24 bits overflowed */
+	clrldi	r6,r6,40
+	clrldi	r7,r7,40
+	cmpld	r7,r6
+	bge	17f
+	addis	r8,r8,0x100		/* if so, increment upper 40 bits */
+	mtspr	SPRN_TBU40,r8
+
+	/* Signal secondary CPUs to continue */
+17:	li	r0,0
 	stb	r0,VCORE_IN_GUEST(r5)
 	lis	r8,0x7fff		/* MAX_INT@h */
 	mtspr	SPRN_HDEC,r8
@@ -1056,6 +1081,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
 1:	addi	r8,r8,16
 	.endr
 
+	/* Save DEC */
+	mfspr	r5,SPRN_DEC
+	mftb	r6
+	extsw	r5,r5
+	add	r5,r5,r6
+	std	r5,VCPU_DEC_EXPIRES(r9)
+
 	/* Save and reset AMR and UAMOR before turning on the MMU */
 BEGIN_FTR_SECTION
 	mfspr	r5,SPRN_AMR