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>
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 541aea0..82b06df 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -347,7 +347,22 @@
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_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 @@
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 @@
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
