KVM: PPC: booke: Add watchdog emulation

This patch adds the watchdog emulation in KVM. The watchdog
emulation is enabled by KVM_ENABLE_CAP(KVM_CAP_PPC_BOOKE_WATCHDOG) ioctl.
The kernel timer are used for watchdog emulation and emulates
h/w watchdog state machine. On watchdog timer expiry, it exit to QEMU
if TCR.WRC is non ZERO. QEMU can reset/shutdown etc depending upon how
it is configured.

Signed-off-by: Liu Yu <yu.liu@freescale.com>
Signed-off-by: Scott Wood <scottwood@freescale.com>
[bharat.bhushan@freescale.com: reworked patch]
Signed-off-by: Bharat Bhushan <bharat.bhushan@freescale.com>
[agraf: adjust to new request framework]
Signed-off-by: Alexander Graf <agraf@suse.de>

9 files changed, 199 insertions, 2 deletions

diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 4a5ec8f573c7..51b0ccd56769 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -471,6 +471,8 @@ struct kvm_vcpu_arch {
         ulong fault_esr;
         ulong queued_dear;
         ulong queued_esr;
+        spinlock_t wdt_lock;
+        struct timer_list wdt_timer;
         u32 tlbcfg[4];
         u32 mmucfg;
         u32 epr;
@@ -486,6 +488,7 @@ struct kvm_vcpu_arch {
         u8 osi_needed;
         u8 osi_enabled;
         u8 papr_enabled;
+        u8 watchdog_enabled;
         u8 sane;
         u8 cpu_type;
         u8 hcall_needed;
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index 3dfc437fb9d9..c06a64b53362 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -68,6 +68,8 @@ 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);
 extern int kvmppc_sanity_check(struct kvm_vcpu *vcpu);
+extern int kvmppc_subarch_vcpu_init(struct kvm_vcpu *vcpu);
+extern void kvmppc_subarch_vcpu_uninit(struct kvm_vcpu *vcpu);
 
 /* Core-specific hooks */
 
diff --git a/arch/powerpc/include/asm/reg_booke.h b/arch/powerpc/include/asm/reg_booke.h
index 2d916c4982c5..e07e6af5e1ff 100644
--- a/arch/powerpc/include/asm/reg_booke.h
+++ b/arch/powerpc/include/asm/reg_booke.h
@@ -539,6 +539,13 @@
 #define TCR_FIE         0x00800000      /* FIT Interrupt Enable */
 #define TCR_ARE         0x00400000      /* Auto Reload Enable */
 
+#ifdef CONFIG_E500
+#define TCR_GET_WP(tcr)  ((((tcr) & 0xC0000000) >> 30) | \
+                              (((tcr) & 0x1E0000) >> 15))
+#else
+#define TCR_GET_WP(tcr)  (((tcr) & 0xC0000000) >> 30)
+#endif
+
 /* Bit definitions for the TSR. */
 #define TSR_ENW         0x80000000      /* Enable Next Watchdog */
 #define TSR_WIS         0x40000000      /* WDT Interrupt Status */
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 3f2a8360c857..e94666566fa9 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -411,6 +411,15 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
         return 0;
 }
 
+int kvmppc_subarch_vcpu_init(struct kvm_vcpu *vcpu)
+{
+        return 0;
+}
+
+void kvmppc_subarch_vcpu_uninit(struct kvm_vcpu *vcpu)
+{
+}
+
 int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 {
         int i;
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index c36493087dbf..09e8bf33a8c9 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -209,6 +209,16 @@ void kvmppc_core_dequeue_external(struct kvm_vcpu *vcpu,
         clear_bit(BOOKE_IRQPRIO_EXTERNAL_LEVEL, &vcpu->arch.pending_exceptions);
 }
 
+static void kvmppc_core_queue_watchdog(struct kvm_vcpu *vcpu)
+{
+        kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_WATCHDOG);
+}
+
+static void kvmppc_core_dequeue_watchdog(struct kvm_vcpu *vcpu)
+{
+        clear_bit(BOOKE_IRQPRIO_WATCHDOG, &vcpu->arch.pending_exceptions);
+}
+
 static void set_guest_srr(struct kvm_vcpu *vcpu, unsigned long srr0, u32 srr1)
 {
 #ifdef CONFIG_KVM_BOOKE_HV
@@ -328,6 +338,7 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu,
                 msr_mask = MSR_CE | MSR_ME | MSR_DE;
                 int_class = INT_CLASS_NONCRIT;
                 break;
+        case BOOKE_IRQPRIO_WATCHDOG:
         case BOOKE_IRQPRIO_CRITICAL:
         case BOOKE_IRQPRIO_DBELL_CRIT:
                 allowed = vcpu->arch.shared->msr & MSR_CE;
@@ -407,12 +418,121 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu,
         return allowed;
 }
 
+/*
+ * Return the number of jiffies until the next timeout.  If the timeout is
+ * longer than the NEXT_TIMER_MAX_DELTA, then return NEXT_TIMER_MAX_DELTA
+ * because the larger value can break the timer APIs.
+ */
+static unsigned long watchdog_next_timeout(struct kvm_vcpu *vcpu)
+{
+        u64 tb, wdt_tb, wdt_ticks = 0;
+        u64 nr_jiffies = 0;
+        u32 period = TCR_GET_WP(vcpu->arch.tcr);
+
+        wdt_tb = 1ULL << (63 - period);
+        tb = get_tb();
+        /*
+         * The watchdog timeout will hapeen when TB bit corresponding
+         * to watchdog will toggle from 0 to 1.
+         */
+        if (tb & wdt_tb)
+                wdt_ticks = wdt_tb;
+
+        wdt_ticks += wdt_tb - (tb & (wdt_tb - 1));
+
+        /* Convert timebase ticks to jiffies */
+        nr_jiffies = wdt_ticks;
+
+        if (do_div(nr_jiffies, tb_ticks_per_jiffy))
+                nr_jiffies++;
+
+        return min_t(unsigned long long, nr_jiffies, NEXT_TIMER_MAX_DELTA);
+}
+
+static void arm_next_watchdog(struct kvm_vcpu *vcpu)
+{
+        unsigned long nr_jiffies;
+        unsigned long flags;
+
+        /*
+         * If TSR_ENW and TSR_WIS are not set then no need to exit to
+         * userspace, so clear the KVM_REQ_WATCHDOG request.
+         */
+        if ((vcpu->arch.tsr & (TSR_ENW | TSR_WIS)) != (TSR_ENW | TSR_WIS))
+                clear_bit(KVM_REQ_WATCHDOG, &vcpu->requests);
+
+        spin_lock_irqsave(&vcpu->arch.wdt_lock, flags);
+        nr_jiffies = watchdog_next_timeout(vcpu);
+        /*
+         * If the number of jiffies of watchdog timer >= NEXT_TIMER_MAX_DELTA
+         * then do not run the watchdog timer as this can break timer APIs.
+         */
+        if (nr_jiffies < NEXT_TIMER_MAX_DELTA)
+                mod_timer(&vcpu->arch.wdt_timer, jiffies + nr_jiffies);
+        else
+                del_timer(&vcpu->arch.wdt_timer);
+        spin_unlock_irqrestore(&vcpu->arch.wdt_lock, flags);
+}
+
+void kvmppc_watchdog_func(unsigned long data)
+{
+        struct kvm_vcpu *vcpu = (struct kvm_vcpu *)data;
+        u32 tsr, new_tsr;
+        int final;
+
+        do {
+                new_tsr = tsr = vcpu->arch.tsr;
+                final = 0;
+
+                /* Time out event */
+                if (tsr & TSR_ENW) {
+                        if (tsr & TSR_WIS)
+                                final = 1;
+                        else
+                                new_tsr = tsr | TSR_WIS;
+                } else {
+                        new_tsr = tsr | TSR_ENW;
+                }
+        } while (cmpxchg(&vcpu->arch.tsr, tsr, new_tsr) != tsr);
+
+        if (new_tsr & TSR_WIS) {
+                smp_wmb();
+                kvm_make_request(KVM_REQ_PENDING_TIMER, vcpu);
+                kvm_vcpu_kick(vcpu);
+        }
+
+        /*
+         * If this is final watchdog expiry and some action is required
+         * then exit to userspace.
+         */
+        if (final && (vcpu->arch.tcr & TCR_WRC_MASK) &&
+            vcpu->arch.watchdog_enabled) {
+                smp_wmb();
+                kvm_make_request(KVM_REQ_WATCHDOG, vcpu);
+                kvm_vcpu_kick(vcpu);
+        }
+
+        /*
+         * Stop running the watchdog timer after final expiration to
+         * prevent the host from being flooded with timers if the
+         * guest sets a short period.
+         * Timers will resume when TSR/TCR is updated next time.
+         */
+        if (!final)
+                arm_next_watchdog(vcpu);
+}
+
 static void update_timer_ints(struct kvm_vcpu *vcpu)
 {
         if ((vcpu->arch.tcr & TCR_DIE) && (vcpu->arch.tsr & TSR_DIS))
                 kvmppc_core_queue_dec(vcpu);
         else
                 kvmppc_core_dequeue_dec(vcpu);
+
+        if ((vcpu->arch.tcr & TCR_WIE) && (vcpu->arch.tsr & TSR_WIS))
+                kvmppc_core_queue_watchdog(vcpu);
+        else
+                kvmppc_core_dequeue_watchdog(vcpu);
 }
 
 static void kvmppc_core_check_exceptions(struct kvm_vcpu *vcpu)
@@ -466,6 +586,11 @@ int kvmppc_core_check_requests(struct kvm_vcpu *vcpu)
                 kvmppc_core_flush_tlb(vcpu);
 #endif
 
+        if (kvm_check_request(KVM_REQ_WATCHDOG, vcpu)) {
+                vcpu->run->exit_reason = KVM_EXIT_WATCHDOG;
+                r = 0;
+        }
+
         return r;
 }
 
@@ -995,6 +1120,21 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
         return r;
 }
 
+int kvmppc_subarch_vcpu_init(struct kvm_vcpu *vcpu)
+{
+        /* setup watchdog timer once */
+        spin_lock_init(&vcpu->arch.wdt_lock);
+        setup_timer(&vcpu->arch.wdt_timer, kvmppc_watchdog_func,
+                    (unsigned long)vcpu);
+
+        return 0;
+}
+
+void kvmppc_subarch_vcpu_uninit(struct kvm_vcpu *vcpu)
+{
+        del_timer_sync(&vcpu->arch.wdt_timer);
+}
+
 int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 {
         int i;
@@ -1090,7 +1230,13 @@ static int set_sregs_base(struct kvm_vcpu *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);
         }
 
@@ -1251,6 +1397,7 @@ void kvmppc_core_commit_memory_region(struct kvm *kvm,
 void kvmppc_set_tcr(struct kvm_vcpu *vcpu, u32 new_tcr)
 {
         vcpu->arch.tcr = new_tcr;
+        arm_next_watchdog(vcpu);
         update_timer_ints(vcpu);
 }
 
@@ -1265,6 +1412,14 @@ void kvmppc_set_tsr_bits(struct kvm_vcpu *vcpu, u32 tsr_bits)
 void kvmppc_clr_tsr_bits(struct kvm_vcpu *vcpu, u32 tsr_bits)
 {
         clear_bits(tsr_bits, &vcpu->arch.tsr);
+
+        /*
+         * We may have stopped the watchdog due to
+         * being stuck on final expiration.
+         */
+        if (tsr_bits & (TSR_ENW | TSR_WIS))
+                arm_next_watchdog(vcpu);
+
         update_timer_ints(vcpu);
 }
 
diff --git a/arch/powerpc/kvm/booke_emulate.c b/arch/powerpc/kvm/booke_emulate.c
index 12834bb608ab..5a66ade7fd17 100644
--- a/arch/powerpc/kvm/booke_emulate.c
+++ b/arch/powerpc/kvm/booke_emulate.c
@@ -145,6 +145,14 @@ int kvmppc_booke_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, ulong spr_val)
                 kvmppc_clr_tsr_bits(vcpu, spr_val);
                 break;
         case SPRN_TCR:
+                /*
+                 * WRC is a 2-bit field that is supposed to preserve its
+                 * value once written to non-zero.
+                 */
+                if (vcpu->arch.tcr & TCR_WRC_MASK) {
+                        spr_val &= ~TCR_WRC_MASK;
+                        spr_val |= vcpu->arch.tcr & TCR_WRC_MASK;
+                }
                 kvmppc_set_tcr(vcpu, spr_val);
                 break;
 
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 54b12af577d0..0ffd7d17adc7 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -300,6 +300,7 @@ int kvm_dev_ioctl_check_extension(long ext)
         switch (ext) {
 #ifdef CONFIG_BOOKE
         case KVM_CAP_PPC_BOOKE_SREGS:
+        case KVM_CAP_PPC_BOOKE_WATCHDOG:
 #else
         case KVM_CAP_PPC_SEGSTATE:
         case KVM_CAP_PPC_HIOR:
@@ -476,6 +477,8 @@ enum hrtimer_restart kvmppc_decrementer_wakeup(struct hrtimer *timer)
 
 int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 {
+        int ret;
+
         hrtimer_init(&vcpu->arch.dec_timer, CLOCK_REALTIME, HRTIMER_MODE_ABS);
         tasklet_init(&vcpu->arch.tasklet, kvmppc_decrementer_func, (ulong)vcpu);
         vcpu->arch.dec_timer.function = kvmppc_decrementer_wakeup;
@@ -484,13 +487,14 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 #ifdef CONFIG_KVM_EXIT_TIMING
         mutex_init(&vcpu->arch.exit_timing_lock);
 #endif
-
-        return 0;
+        ret = kvmppc_subarch_vcpu_init(vcpu);
+        return ret;
 }
 
 void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
 {
         kvmppc_mmu_destroy(vcpu);
+        kvmppc_subarch_vcpu_uninit(vcpu);
 }
 
 void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
@@ -735,6 +739,12 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
                 r = 0;
                 vcpu->arch.papr_enabled = true;
                 break;
+#ifdef CONFIG_BOOKE
+        case KVM_CAP_PPC_BOOKE_WATCHDOG:
+                r = 0;
+                vcpu->arch.watchdog_enabled = true;
+                break;
+#endif
 #if defined(CONFIG_KVM_E500V2) || defined(CONFIG_KVM_E500MC)
         case KVM_CAP_SW_TLB: {
                 struct kvm_config_tlb cfg;
diff --git a/include/linux/kvm.h b/include/linux/kvm.h
index 4cb3761bebae..1649d4b57e1f 100644
--- a/include/linux/kvm.h
+++ b/include/linux/kvm.h
@@ -167,6 +167,7 @@ struct kvm_pit_config {
 #define KVM_EXIT_OSI              18
 #define KVM_EXIT_PAPR_HCALL       19
 #define KVM_EXIT_S390_UCONTROL    20
+#define KVM_EXIT_WATCHDOG         21
 
 /* For KVM_EXIT_INTERNAL_ERROR */
 #define KVM_INTERNAL_ERROR_EMULATION 1
@@ -628,6 +629,7 @@ struct kvm_ppc_smmu_info {
 #define KVM_CAP_READONLY_MEM 81
 #endif
 #define KVM_CAP_IRQFD_RESAMPLE 82
+#define KVM_CAP_PPC_BOOKE_WATCHDOG 83
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 2850656e2e96..0ca3663206f8 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -118,6 +118,7 @@ static inline bool is_error_page(struct page *page)
 #define KVM_REQ_IMMEDIATE_EXIT    15
 #define KVM_REQ_PMU               16
 #define KVM_REQ_PMI               17
+#define KVM_REQ_WATCHDOG          18
 
 #define KVM_USERSPACE_IRQ_SOURCE_ID             0
 #define KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID        1