From: Liu Yu <yu.liu@xxxxxxxxxxxxx>
Decrementers are now properly driven by TCR/TSR, and the guest
has full read/write access to these registers.
The decrementer keeps ticking (and setting the TSR bit) regardless of
whether the interrupts are enabled with TCR.
The decrementer stops at zero, rather than going negative.
Signed-off-by: Liu Yu <yu.liu@xxxxxxxxxxxxx>
[scott: added dequeue in kvmppc_booke_irqprio_deliver, and dec stop-at-zero]
Signed-off-by: Scott Wood <scottwood@xxxxxxxxxxxxx>
---
arch/powerpc/include/asm/kvm_host.h | 2 +-
arch/powerpc/include/asm/kvm_ppc.h | 11 +++++
arch/powerpc/kvm/book3s.c | 8 ++++
arch/powerpc/kvm/booke.c | 80 +++++++++++++++++++++++++++--------
arch/powerpc/kvm/booke.h | 4 ++
arch/powerpc/kvm/booke_emulate.c | 11 ++++-
arch/powerpc/kvm/emulate.c | 45 ++++++++-----------
arch/powerpc/kvm/powerpc.c | 20 +--------
8 files changed, 114 insertions(+), 67 deletions(-)
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 3305af4..ea08c79 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -334,7 +334,7 @@ struct kvm_vcpu_arch {
u32 tbl;
u32 tbu;
u32 tcr;
- u32 tsr;
+ ulong tsr; /* we need to perform set/clr_bits() which requires ulong */
u32 ivor[64];
ulong ivpr;
u32 pvr;
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index bdaa6c8..ddaa615 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -66,6 +66,7 @@ extern int kvmppc_emulate_instruction(struct kvm_run *run,
extern int kvmppc_emulate_mmio(struct kvm_run *run, struct kvm_vcpu *vcpu);
extern void kvmppc_emulate_dec(struct kvm_vcpu *vcpu);
extern u32 kvmppc_get_dec(struct kvm_vcpu *vcpu, u64 tb);
+extern void kvmppc_decrementer_func(unsigned long data);
/* Core-specific hooks */
@@ -197,4 +198,14 @@ int kvm_vcpu_ioctl_config_tlb(struct kvm_vcpu *vcpu,
int kvm_vcpu_ioctl_dirty_tlb(struct kvm_vcpu *vcpu,
struct kvm_dirty_tlb *cfg);
+static inline void kvmppc_wakeup_vcpu(struct kvm_vcpu *vcpu)
+{
+ if (waitqueue_active(&vcpu->wq)) {
+ wake_up_interruptible(&vcpu->wq);
+ vcpu->stat.halt_wakeup++;
+ } else if (vcpu->cpu != -1) {
+ smp_send_reschedule(vcpu->cpu);
+ }
+}
+
#endif /* __POWERPC_KVM_PPC_H__ */
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index f68a34d..b057856 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -514,3 +514,11 @@ out:
mutex_unlock(&kvm->slots_lock);
return r;
}
+
+void kvmppc_decrementer_func(unsigned long data)
+{
+ struct kvm_vcpu *vcpu = (struct kvm_vcpu *)data;
+
+ kvmppc_core_queue_dec(vcpu);
+ kvmppc_wakeup_vcpu(vcpu);
+}
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index 0ed62c1..502f9ff 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -205,7 +205,8 @@ void kvmppc_core_dequeue_external(struct kvm_vcpu *vcpu,
static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu,
unsigned int priority)
{
- int allowed = 0;
+ int allowed = 1;
+ int dequeue = 0;
ulong uninitialized_var(msr_mask);
bool update_esr = false, update_dear = false;
ulong crit_raw = vcpu->arch.shared->critical;
@@ -258,10 +259,15 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu,
allowed = vcpu->arch.shared->msr & MSR_ME;
msr_mask = 0;
break;
- case BOOKE_IRQPRIO_EXTERNAL:
case BOOKE_IRQPRIO_DECREMENTER:
+ if (!(vcpu->arch.tcr & TCR_DIE)) {
+ allowed = 0;
+ dequeue = 1;
+ }
+ /* fall through */
+ case BOOKE_IRQPRIO_EXTERNAL:
case BOOKE_IRQPRIO_FIT:
- allowed = vcpu->arch.shared->msr & MSR_EE;
+ allowed = allowed && vcpu->arch.shared->msr & MSR_EE;
allowed = allowed && !crit;
msr_mask = MSR_CE|MSR_ME|MSR_DE;
break;
@@ -269,6 +275,8 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu,
allowed = vcpu->arch.shared->msr & MSR_DE;
msr_mask = MSR_ME;
break;
+ default:
+ allowed = 0;
}
if (allowed) {
@@ -283,6 +291,9 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu,
if (!keep_irq)
clear_bit(priority, &vcpu->arch.pending_exceptions);
+ } else if (dequeue) {
+ /* Should only happen due to races with masking */
+ clear_bit(priority, &vcpu->arch.pending_exceptions);
}
return allowed;
@@ -721,25 +732,16 @@ static int set_sregs_base(struct kvm_vcpu *vcpu,
vcpu->arch.shared->esr = sregs->u.e.esr;
vcpu->arch.shared->dar = sregs->u.e.dear;
vcpu->arch.vrsave = sregs->u.e.vrsave;
- vcpu->arch.tcr = sregs->u.e.tcr;
+ kvmppc_set_tcr(vcpu, sregs->u.e.tcr);
- if (sregs->u.e.update_special & KVM_SREGS_E_UPDATE_DEC)
+ if (sregs->u.e.update_special & KVM_SREGS_E_UPDATE_DEC) {
vcpu->arch.dec = sregs->u.e.dec;
-
- kvmppc_emulate_dec(vcpu);
+ kvmppc_emulate_dec(vcpu);
+ }
if (sregs->u.e.update_special & KVM_SREGS_E_UPDATE_TSR) {
- /*
- * FIXME: existing KVM timer handling is incomplete.
- * TSR cannot be read by the guest, and its value in
- * vcpu->arch is always zero. For now, just handle
- * the case where the caller is trying to inject a
- * decrementer interrupt.
- */
-
- if ((sregs->u.e.tsr & TSR_DIS) &&
- (vcpu->arch.tcr & TCR_DIE))
- kvmppc_core_queue_dec(vcpu);
+ kvmppc_clr_tsr_bits(vcpu, ~0);
+ kvmppc_set_tsr_bits(vcpu, sregs->u.e.tsr);
}
return 0;
@@ -895,6 +897,48 @@ void kvmppc_core_destroy_vm(struct kvm *kvm)
{
}
+void kvmppc_set_tcr(struct kvm_vcpu *vcpu, u32 new_tcr)
+{
+ vcpu->arch.tcr = new_tcr;
+ smp_wmb();
+
+ /*
+ * Since TCR changed, we need to check
+ * if blocked interrupts are deliverable.
+ */
+ if ((new_tcr & TCR_DIE) && (vcpu->arch.tsr & TSR_DIS)) {
+ kvmppc_core_queue_dec(vcpu);
+ kvmppc_wakeup_vcpu(vcpu);
+ }
+}
+
+void kvmppc_set_tsr_bits(struct kvm_vcpu *vcpu, u32 tsr_bits)
+{
+ set_bits(tsr_bits, &vcpu->arch.tsr);
+ smp_wmb();
+
+ if ((tsr_bits & TSR_DIS) && (vcpu->arch.tcr & TCR_DIE)) {
+ kvmppc_core_queue_dec(vcpu);
+ kvmppc_wakeup_vcpu(vcpu);
+ }
+}
+
+void kvmppc_clr_tsr_bits(struct kvm_vcpu *vcpu, u32 tsr_bits)
+{
+ if (tsr_bits & TSR_DIS)
+ kvmppc_core_dequeue_dec(vcpu);
+
+ smp_wmb();
+ clear_bits(tsr_bits, &vcpu->arch.tsr);
+}
+
+void kvmppc_decrementer_func(unsigned long data)
+{
+ struct kvm_vcpu *vcpu = (struct kvm_vcpu *)data;
+
+ kvmppc_set_tsr_bits(vcpu, TSR_DIS);
+}
+
int __init kvmppc_booke_init(void)
{
unsigned long ivor[16];
diff --git a/arch/powerpc/kvm/booke.h b/arch/powerpc/kvm/booke.h
index 8e1fe33..2fe2027 100644
--- a/arch/powerpc/kvm/booke.h
+++ b/arch/powerpc/kvm/booke.h
@@ -55,6 +55,10 @@ extern unsigned long kvmppc_booke_handlers;
void kvmppc_set_msr(struct kvm_vcpu *vcpu, u32 new_msr);
void kvmppc_mmu_msr_notify(struct kvm_vcpu *vcpu, u32 old_msr);
+void kvmppc_set_tcr(struct kvm_vcpu *vcpu, u32 new_tcr);
+void kvmppc_set_tsr_bits(struct kvm_vcpu *vcpu, u32 tsr_bits);
+void kvmppc_clr_tsr_bits(struct kvm_vcpu *vcpu, u32 tsr_bits);
+
int kvmppc_booke_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
unsigned int inst, int *advance);
int kvmppc_booke_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt);
diff --git a/arch/powerpc/kvm/booke_emulate.c b/arch/powerpc/kvm/booke_emulate.c
index 162b7ac..dee534e 100644
--- a/arch/powerpc/kvm/booke_emulate.c
+++ b/arch/powerpc/kvm/booke_emulate.c
@@ -13,6 +13,7 @@
* Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
*
* Copyright IBM Corp. 2008
+ * Copyright 2011 Freescale Semiconductor, Inc.
*
* Authors: Hollis Blanchard <hollisb@xxxxxxxxxx>
*/
@@ -115,10 +116,10 @@ int kvmppc_booke_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
case SPRN_DBSR:
vcpu->arch.dbsr &= ~spr_val; break;
case SPRN_TSR:
- vcpu->arch.tsr &= ~spr_val; break;
+ kvmppc_clr_tsr_bits(vcpu, spr_val);
+ break;
case SPRN_TCR:
- vcpu->arch.tcr = spr_val;
- kvmppc_emulate_dec(vcpu);
+ kvmppc_set_tcr(vcpu, spr_val);
break;
/* Note: SPRG4-7 are user-readable. These values are
@@ -209,6 +210,10 @@ int kvmppc_booke_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
kvmppc_set_gpr(vcpu, rt, vcpu->arch.dbcr1); break;
case SPRN_DBSR:
kvmppc_set_gpr(vcpu, rt, vcpu->arch.dbsr); break;
+ case SPRN_TSR:
+ kvmppc_set_gpr(vcpu, rt, vcpu->arch.tsr); break;
+ case SPRN_TCR:
+ kvmppc_set_gpr(vcpu, rt, vcpu->arch.tcr); break;
case SPRN_IVOR0:
kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_CRITICAL]);
diff --git a/arch/powerpc/kvm/emulate.c b/arch/powerpc/kvm/emulate.c
index dc8259d..af210b7 100644
--- a/arch/powerpc/kvm/emulate.c
+++ b/arch/powerpc/kvm/emulate.c
@@ -13,6 +13,7 @@
* Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
*
* Copyright IBM Corp. 2007
+ * Copyright 2011 Freescale Semiconductor, Inc.
*
* Authors: Hollis Blanchard <hollisb@xxxxxxxxxx>
*/
@@ -69,18 +70,6 @@
#define OP_STH 44
#define OP_STHU 45
-#ifdef CONFIG_PPC_BOOK3S
-static int kvmppc_dec_enabled(struct kvm_vcpu *vcpu)
-{
- return 1;
-}
-#else
-static int kvmppc_dec_enabled(struct kvm_vcpu *vcpu)
-{
- return vcpu->arch.tcr & TCR_DIE;
-}
-#endif
-
void kvmppc_emulate_dec(struct kvm_vcpu *vcpu)
{
unsigned long dec_nsec;
@@ -97,26 +86,30 @@ void kvmppc_emulate_dec(struct kvm_vcpu *vcpu)
return;
}
#endif
- if (kvmppc_dec_enabled(vcpu)) {
- /* The decrementer ticks at the same rate as the timebase, so
- * that's how we convert the guest DEC value to the number of
- * host ticks. */
-
- hrtimer_try_to_cancel(&vcpu->arch.dec_timer);
- dec_nsec = vcpu->arch.dec;
- dec_nsec *= 1000;
- dec_nsec /= tb_ticks_per_usec;
- hrtimer_start(&vcpu->arch.dec_timer, ktime_set(0, dec_nsec),
- HRTIMER_MODE_REL);
- vcpu->arch.dec_jiffies = get_tb();
- } else {
- hrtimer_try_to_cancel(&vcpu->arch.dec_timer);
- }
+ /*
+ * The decrementer ticks at the same rate as the timebase, so
+ * that's how we convert the guest DEC value to the number of
+ * host ticks.
+ */
+
+ hrtimer_try_to_cancel(&vcpu->arch.dec_timer);
+ dec_nsec = vcpu->arch.dec;
+ dec_nsec *= 1000;
+ dec_nsec /= tb_ticks_per_usec;
+ hrtimer_start(&vcpu->arch.dec_timer, ktime_set(0, dec_nsec),
+ HRTIMER_MODE_REL);
+ vcpu->arch.dec_jiffies = get_tb();
}
u32 kvmppc_get_dec(struct kvm_vcpu *vcpu, u64 tb)
{
u64 jd = tb - vcpu->arch.dec_jiffies;
+
+#ifdef CONFIG_BOOKE
+ if (vcpu->arch.dec < jd)
+ return 0;
+#endif
+
return vcpu->arch.dec - jd;
}
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 0ee0b80..05f8dc4 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -286,18 +286,6 @@ int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
return kvmppc_core_pending_dec(vcpu);
}
-static void kvmppc_decrementer_func(unsigned long data)
-{
- struct kvm_vcpu *vcpu = (struct kvm_vcpu *)data;
-
- kvmppc_core_queue_dec(vcpu);
-
- if (waitqueue_active(&vcpu->wq)) {
- wake_up_interruptible(&vcpu->wq);
- vcpu->stat.halt_wakeup++;
- }
-}
-
/*
* low level hrtimer wake routine. Because this runs in hardirq context
* we schedule a tasklet to do the real work.
@@ -551,13 +539,7 @@ int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, struct kvm_interrupt *irq)
else
kvmppc_core_queue_external(vcpu, irq);
- if (waitqueue_active(&vcpu->wq)) {
- wake_up_interruptible(&vcpu->wq);
- vcpu->stat.halt_wakeup++;
- } else if (vcpu->cpu != -1) {
- smp_send_reschedule(vcpu->cpu);
- }
-
+ kvmppc_wakeup_vcpu(vcpu);
return 0;
}
--
1.7.6
--
To unsubscribe from this list: send the line "unsubscribe kvm-ppc" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
