Merge tag 'kvm-arm-for-4.6-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm

KVM/ARM Fixes for v4.6-rc4

Addresses:
 - Wrong indentation in the PMU code from the merge window
 - A long-time bug occuring with running ntpd on the host, candidate for stable
 - Properly handle (and warn about) the unsupported configuration of running on
   systems with less than 40 bits of PA space
 - More fixes to the PM and hotplug notifier stuff from the merge window

7 files changed, 95 insertions, 24 deletions

diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index b5384311dec4..dded1b763c16 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -1112,10 +1112,17 @@ static void __init hyp_cpu_pm_init(void)
 {
         cpu_pm_register_notifier(&hyp_init_cpu_pm_nb);
 }
+static void __init hyp_cpu_pm_exit(void)
+{
+        cpu_pm_unregister_notifier(&hyp_init_cpu_pm_nb);
+}
 #else
 static inline void hyp_cpu_pm_init(void)
 {
 }
+static inline void hyp_cpu_pm_exit(void)
+{
+}
 #endif
 
 static void teardown_common_resources(void)
@@ -1141,9 +1148,7 @@ static int init_subsystems(void)
         /*
          * Register CPU Hotplug notifier
          */
-        cpu_notifier_register_begin();
-        err = __register_cpu_notifier(&hyp_init_cpu_nb);
-        cpu_notifier_register_done();
+        err = register_cpu_notifier(&hyp_init_cpu_nb);
         if (err) {
                 kvm_err("Cannot register KVM init CPU notifier (%d)\n", err);
                 return err;
@@ -1193,6 +1198,8 @@ static void teardown_hyp_mode(void)
         free_hyp_pgds();
         for_each_possible_cpu(cpu)
                 free_page(per_cpu(kvm_arm_hyp_stack_page, cpu));
+        unregister_cpu_notifier(&hyp_init_cpu_nb);
+        hyp_cpu_pm_exit();
 }
 
 static int init_vhe_mode(void)
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 4150fd8bae01..3f29887995bc 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -151,8 +151,7 @@
  */
 #define VTCR_EL2_FLAGS          (VTCR_EL2_TG0_64K | VTCR_EL2_SH0_INNER | \
                                  VTCR_EL2_ORGN0_WBWA | VTCR_EL2_IRGN0_WBWA | \
-                                 VTCR_EL2_SL0_LVL1 | VTCR_EL2_T0SZ_40B | \
-                                 VTCR_EL2_RES1)
+                                 VTCR_EL2_SL0_LVL1 | VTCR_EL2_RES1)
 #define VTTBR_X         (38 - VTCR_EL2_T0SZ_40B)
 #else
 /*
@@ -163,8 +162,7 @@
  */
 #define VTCR_EL2_FLAGS          (VTCR_EL2_TG0_4K | VTCR_EL2_SH0_INNER | \
                                  VTCR_EL2_ORGN0_WBWA | VTCR_EL2_IRGN0_WBWA | \
-                                 VTCR_EL2_SL0_LVL1 | VTCR_EL2_T0SZ_40B | \
-                                 VTCR_EL2_RES1)
+                                 VTCR_EL2_SL0_LVL1 | VTCR_EL2_RES1)
 #define VTTBR_X         (37 - VTCR_EL2_T0SZ_40B)
 #endif
 
diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index eb7490d232a0..40a0a24e6c98 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -54,7 +54,7 @@ extern void __vgic_v3_init_lrs(void);
 
 extern u32 __kvm_get_mdcr_el2(void);
 
-extern void __init_stage2_translation(void);
+extern u32 __init_stage2_translation(void);
 
 #endif
 
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index b7e82a795ac9..f5c6bd2541ef 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -369,11 +369,12 @@ int kvm_arm_vcpu_arch_get_attr(struct kvm_vcpu *vcpu,
 int kvm_arm_vcpu_arch_has_attr(struct kvm_vcpu *vcpu,
                                struct kvm_device_attr *attr);
 
-/* #define kvm_call_hyp(f, ...) __kvm_call_hyp(kvm_ksym_ref(f), ##__VA_ARGS__) */
-
 static inline void __cpu_init_stage2(void)
 {
-        kvm_call_hyp(__init_stage2_translation);
+        u32 parange = kvm_call_hyp(__init_stage2_translation);
+
+        WARN_ONCE(parange < 40,
+                  "PARange is %d bits, unsupported configuration!", parange);
 }
 
 #endif /* __ARM64_KVM_HOST_H__ */
diff --git a/arch/arm64/kvm/hyp/s2-setup.c b/arch/arm64/kvm/hyp/s2-setup.c
index 5a9f3bf542b0..bcbe761a5a3d 100644
--- a/arch/arm64/kvm/hyp/s2-setup.c
+++ b/arch/arm64/kvm/hyp/s2-setup.c
@@ -20,9 +20,10 @@
 #include <asm/kvm_asm.h>
 #include <asm/kvm_hyp.h>
 
-void __hyp_text __init_stage2_translation(void)
+u32 __hyp_text __init_stage2_translation(void)
 {
         u64 val = VTCR_EL2_FLAGS;
+        u64 parange;
         u64 tmp;
 
         /*
@@ -30,7 +31,39 @@ void __hyp_text __init_stage2_translation(void)
          * bits in VTCR_EL2. Amusingly, the PARange is 4 bits, while
          * PS is only 3. Fortunately, bit 19 is RES0 in VTCR_EL2...
          */
-        val |= (read_sysreg(id_aa64mmfr0_el1) & 7) << 16;
+        parange = read_sysreg(id_aa64mmfr0_el1) & 7;
+        val |= parange << 16;
+
+        /* Compute the actual PARange... */
+        switch (parange) {
+        case 0:
+                parange = 32;
+                break;
+        case 1:
+                parange = 36;
+                break;
+        case 2:
+                parange = 40;
+                break;
+        case 3:
+                parange = 42;
+                break;
+        case 4:
+                parange = 44;
+                break;
+        case 5:
+        default:
+                parange = 48;
+                break;
+        }
+
+        /*
+         * ... and clamp it to 40 bits, unless we have some braindead
+         * HW that implements less than that. In all cases, we'll
+         * return that value for the rest of the kernel to decide what
+         * to do.
+         */
+        val |= 64 - (parange > 40 ? 40 : parange);
 
         /*
          * Read the VMIDBits bits from ID_AA64MMFR1_EL1 and set the VS
@@ -42,4 +75,6 @@ void __hyp_text __init_stage2_translation(void)
                         VTCR_EL2_VS_8BIT;
 
         write_sysreg(val, vtcr_el2);
+
+        return parange;
 }
diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c
index a9ad4fe3f68f..9aaa35dd9144 100644
--- a/virt/kvm/arm/arch_timer.c
+++ b/virt/kvm/arm/arch_timer.c
@@ -91,6 +91,8 @@ static void kvm_timer_inject_irq_work(struct work_struct *work)
         vcpu = container_of(work, struct kvm_vcpu, arch.timer_cpu.expired);
         vcpu->arch.timer_cpu.armed = false;
 
+        WARN_ON(!kvm_timer_should_fire(vcpu));
+
         /*
          * If the vcpu is blocked we want to wake it up so that it will see
          * the timer has expired when entering the guest.
@@ -98,10 +100,46 @@ static void kvm_timer_inject_irq_work(struct work_struct *work)
         kvm_vcpu_kick(vcpu);
 }
 
+static u64 kvm_timer_compute_delta(struct kvm_vcpu *vcpu)
+{
+        cycle_t cval, now;
+
+        cval = vcpu->arch.timer_cpu.cntv_cval;
+        now = kvm_phys_timer_read() - vcpu->kvm->arch.timer.cntvoff;
+
+        if (now < cval) {
+                u64 ns;
+
+                ns = cyclecounter_cyc2ns(timecounter->cc,
+                                         cval - now,
+                                         timecounter->mask,
+                                         &timecounter->frac);
+                return ns;
+        }
+
+        return 0;
+}
+
 static enum hrtimer_restart kvm_timer_expire(struct hrtimer *hrt)
 {
         struct arch_timer_cpu *timer;
+        struct kvm_vcpu *vcpu;
+        u64 ns;
+
         timer = container_of(hrt, struct arch_timer_cpu, timer);
+        vcpu = container_of(timer, struct kvm_vcpu, arch.timer_cpu);
+
+        /*
+         * Check that the timer has really expired from the guest's
+         * PoV (NTP on the host may have forced it to expire
+         * early). If we should have slept longer, restart it.
+         */
+        ns = kvm_timer_compute_delta(vcpu);
+        if (unlikely(ns)) {
+                hrtimer_forward_now(hrt, ns_to_ktime(ns));
+                return HRTIMER_RESTART;
+        }
+
         queue_work(wqueue, &timer->expired);
         return HRTIMER_NORESTART;
 }
@@ -176,8 +214,6 @@ static int kvm_timer_update_state(struct kvm_vcpu *vcpu)
 void kvm_timer_schedule(struct kvm_vcpu *vcpu)
 {
         struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
-        u64 ns;
-        cycle_t cval, now;
 
         BUG_ON(timer_is_armed(timer));
 
@@ -197,14 +233,7 @@ void kvm_timer_schedule(struct kvm_vcpu *vcpu)
                 return;
 
         /*  The timer has not yet expired, schedule a background timer */
-        cval = timer->cntv_cval;
-        now = kvm_phys_timer_read() - vcpu->kvm->arch.timer.cntvoff;
-
-        ns = cyclecounter_cyc2ns(timecounter->cc,
-                                 cval - now,
-                                 timecounter->mask,
-                                 &timecounter->frac);
-        timer_arm(timer, ns);
+        timer_arm(timer, kvm_timer_compute_delta(vcpu));
 }
 
 void kvm_timer_unschedule(struct kvm_vcpu *vcpu)
diff --git a/virt/kvm/arm/pmu.c b/virt/kvm/arm/pmu.c
index b5754c6c5508..575c7aa30d7e 100644
--- a/virt/kvm/arm/pmu.c
+++ b/virt/kvm/arm/pmu.c
@@ -193,11 +193,12 @@ static u64 kvm_pmu_overflow_status(struct kvm_vcpu *vcpu)
 {
         u64 reg = 0;
 
-        if ((vcpu_sys_reg(vcpu, PMCR_EL0) & ARMV8_PMU_PMCR_E))
+        if ((vcpu_sys_reg(vcpu, PMCR_EL0) & ARMV8_PMU_PMCR_E)) {
                 reg = vcpu_sys_reg(vcpu, PMOVSSET_EL0);
                 reg &= vcpu_sys_reg(vcpu, PMCNTENSET_EL0);
                 reg &= vcpu_sys_reg(vcpu, PMINTENSET_EL1);
                 reg &= kvm_pmu_valid_counter_mask(vcpu);
+        }
 
         return reg;
 }