X-Git-Url: https://git.proxmox.com/?a=blobdiff_plain;f=target-ppc%2Fkvm.c;h=b77ce5e94cbca9e96e791ff10ce67fb633213757;hb=60aad298cb6de52f2716b2e82e1353ea9de95fd6;hp=436ca474ff0b1ba13091db6d7a37d0f3d2e130c1;hpb=34daffa04886444dafd4a6951167225e824003d0;p=qemu.git

diff --git a/target-ppc/kvm.c b/target-ppc/kvm.c
index 436ca474f..b77ce5e94 100644
--- a/target-ppc/kvm.c
+++ b/target-ppc/kvm.c
@@ -30,20 +30,20 @@
 #include "cpu.h"
 #include "sysemu/cpus.h"
 #include "sysemu/device_tree.h"
-#include "hw/sysbus.h"
-#include "hw/spapr.h"
+#include "mmu-hash64.h"
 
 #include "hw/sysbus.h"
-#include "hw/spapr.h"
-#include "hw/spapr_vio.h"
+#include "hw/ppc/spapr.h"
+#include "hw/ppc/spapr_vio.h"
+#include "sysemu/watchdog.h"
 
 //#define DEBUG_KVM
 
 #ifdef DEBUG_KVM
-#define dprintf(fmt, ...) \
+#define DPRINTF(fmt, ...) \
     do { fprintf(stderr, fmt, ## __VA_ARGS__); } while (0)
 #else
-#define dprintf(fmt, ...) \
+#define DPRINTF(fmt, ...) \
     do { } while (0)
 #endif
 
@@ -61,6 +61,11 @@ static int cap_ppc_smt;
 static int cap_ppc_rma;
 static int cap_spapr_tce;
 static int cap_hior;
+static int cap_one_reg;
+static int cap_epr;
+static int cap_ppc_watchdog;
+static int cap_papr;
+static int cap_htab_fd;
 
 /* XXX We have a race condition where we actually have a level triggered
  *     interrupt, but the infrastructure can't expose that yet, so the guest
@@ -80,6 +85,8 @@ static void kvm_kick_cpu(void *opaque)
     qemu_cpu_kick(CPU(cpu));
 }
 
+static int kvm_ppc_register_host_cpu_type(void);
+
 int kvm_arch_init(KVMState *s)
 {
     cap_interrupt_unset = kvm_check_extension(s, KVM_CAP_PPC_UNSET_IRQ);
@@ -89,13 +96,21 @@ int kvm_arch_init(KVMState *s)
     cap_ppc_smt = kvm_check_extension(s, KVM_CAP_PPC_SMT);
     cap_ppc_rma = kvm_check_extension(s, KVM_CAP_PPC_RMA);
     cap_spapr_tce = kvm_check_extension(s, KVM_CAP_SPAPR_TCE);
+    cap_one_reg = kvm_check_extension(s, KVM_CAP_ONE_REG);
     cap_hior = kvm_check_extension(s, KVM_CAP_PPC_HIOR);
+    cap_epr = kvm_check_extension(s, KVM_CAP_PPC_EPR);
+    cap_ppc_watchdog = kvm_check_extension(s, KVM_CAP_PPC_BOOKE_WATCHDOG);
+    /* Note: we don't set cap_papr here, because this capability is
+     * only activated after this by kvmppc_set_papr() */
+    cap_htab_fd = kvm_check_extension(s, KVM_CAP_PPC_HTAB_FD);
 
     if (!cap_interrupt_level) {
         fprintf(stderr, "KVM: Couldn't find level irq capability. Expect the "
                         "VM to stall at times!\n");
     }
 
+    kvm_ppc_register_host_cpu_type();
+
     return 0;
 }
 
@@ -384,6 +399,11 @@ static inline void kvm_fixup_page_sizes(PowerPCCPU *cpu)
 
 #endif /* !defined (TARGET_PPC64) */
 
+unsigned long kvm_arch_vcpu_id(CPUState *cpu)
+{
+    return cpu->cpu_index;
+}
+
 int kvm_arch_init_vcpu(CPUState *cs)
 {
     PowerPCCPU *cpu = POWERPC_CPU(cs);
@@ -399,7 +419,7 @@ int kvm_arch_init_vcpu(CPUState *cs)
         return ret;
     }
 
-    idle_timer = qemu_new_timer_ns(vm_clock, kvm_kick_cpu, cpu);
+    idle_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, kvm_kick_cpu, cpu);
 
     /* Some targets support access to KVM's guest TLB. */
     switch (cenv->mmu_model) {
@@ -444,6 +464,299 @@ static void kvm_sw_tlb_put(PowerPCCPU *cpu)
     g_free(bitmap);
 }
 
+static void kvm_get_one_spr(CPUState *cs, uint64_t id, int spr)
+{
+    PowerPCCPU *cpu = POWERPC_CPU(cs);
+    CPUPPCState *env = &cpu->env;
+    union {
+        uint32_t u32;
+        uint64_t u64;
+    } val;
+    struct kvm_one_reg reg = {
+        .id = id,
+        .addr = (uintptr_t) &val,
+    };
+    int ret;
+
+    ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, &reg);
+    if (ret != 0) {
+        fprintf(stderr, "Warning: Unable to retrieve SPR %d from KVM: %s\n",
+                spr, strerror(errno));
+    } else {
+        switch (id & KVM_REG_SIZE_MASK) {
+        case KVM_REG_SIZE_U32:
+            env->spr[spr] = val.u32;
+            break;
+
+        case KVM_REG_SIZE_U64:
+            env->spr[spr] = val.u64;
+            break;
+
+        default:
+            /* Don't handle this size yet */
+            abort();
+        }
+    }
+}
+
+static void kvm_put_one_spr(CPUState *cs, uint64_t id, int spr)
+{
+    PowerPCCPU *cpu = POWERPC_CPU(cs);
+    CPUPPCState *env = &cpu->env;
+    union {
+        uint32_t u32;
+        uint64_t u64;
+    } val;
+    struct kvm_one_reg reg = {
+        .id = id,
+        .addr = (uintptr_t) &val,
+    };
+    int ret;
+
+    switch (id & KVM_REG_SIZE_MASK) {
+    case KVM_REG_SIZE_U32:
+        val.u32 = env->spr[spr];
+        break;
+
+    case KVM_REG_SIZE_U64:
+        val.u64 = env->spr[spr];
+        break;
+
+    default:
+        /* Don't handle this size yet */
+        abort();
+    }
+
+    ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, &reg);
+    if (ret != 0) {
+        fprintf(stderr, "Warning: Unable to set SPR %d to KVM: %s\n",
+                spr, strerror(errno));
+    }
+}
+
+static int kvm_put_fp(CPUState *cs)
+{
+    PowerPCCPU *cpu = POWERPC_CPU(cs);
+    CPUPPCState *env = &cpu->env;
+    struct kvm_one_reg reg;
+    int i;
+    int ret;
+
+    if (env->insns_flags & PPC_FLOAT) {
+        uint64_t fpscr = env->fpscr;
+        bool vsx = !!(env->insns_flags2 & PPC2_VSX);
+
+        reg.id = KVM_REG_PPC_FPSCR;
+        reg.addr = (uintptr_t)&fpscr;
+        ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, &reg);
+        if (ret < 0) {
+            DPRINTF("Unable to set FPSCR to KVM: %s\n", strerror(errno));
+            return ret;
+        }
+
+        for (i = 0; i < 32; i++) {
+            uint64_t vsr[2];
+
+            vsr[0] = float64_val(env->fpr[i]);
+            vsr[1] = env->vsr[i];
+            reg.addr = (uintptr_t) &vsr;
+            reg.id = vsx ? KVM_REG_PPC_VSR(i) : KVM_REG_PPC_FPR(i);
+
+            ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, &reg);
+            if (ret < 0) {
+                DPRINTF("Unable to set %s%d to KVM: %s\n", vsx ? "VSR" : "FPR",
+                        i, strerror(errno));
+                return ret;
+            }
+        }
+    }
+
+    if (env->insns_flags & PPC_ALTIVEC) {
+        reg.id = KVM_REG_PPC_VSCR;
+        reg.addr = (uintptr_t)&env->vscr;
+        ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, &reg);
+        if (ret < 0) {
+            DPRINTF("Unable to set VSCR to KVM: %s\n", strerror(errno));
+            return ret;
+        }
+
+        for (i = 0; i < 32; i++) {
+            reg.id = KVM_REG_PPC_VR(i);
+            reg.addr = (uintptr_t)&env->avr[i];
+            ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, &reg);
+            if (ret < 0) {
+                DPRINTF("Unable to set VR%d to KVM: %s\n", i, strerror(errno));
+                return ret;
+            }
+        }
+    }
+
+    return 0;
+}
+
+static int kvm_get_fp(CPUState *cs)
+{
+    PowerPCCPU *cpu = POWERPC_CPU(cs);
+    CPUPPCState *env = &cpu->env;
+    struct kvm_one_reg reg;
+    int i;
+    int ret;
+
+    if (env->insns_flags & PPC_FLOAT) {
+        uint64_t fpscr;
+        bool vsx = !!(env->insns_flags2 & PPC2_VSX);
+
+        reg.id = KVM_REG_PPC_FPSCR;
+        reg.addr = (uintptr_t)&fpscr;
+        ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, &reg);
+        if (ret < 0) {
+            DPRINTF("Unable to get FPSCR from KVM: %s\n", strerror(errno));
+            return ret;
+        } else {
+            env->fpscr = fpscr;
+        }
+
+        for (i = 0; i < 32; i++) {
+            uint64_t vsr[2];
+
+            reg.addr = (uintptr_t) &vsr;
+            reg.id = vsx ? KVM_REG_PPC_VSR(i) : KVM_REG_PPC_FPR(i);
+
+            ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, &reg);
+            if (ret < 0) {
+                DPRINTF("Unable to get %s%d from KVM: %s\n",
+                        vsx ? "VSR" : "FPR", i, strerror(errno));
+                return ret;
+            } else {
+                env->fpr[i] = vsr[0];
+                if (vsx) {
+                    env->vsr[i] = vsr[1];
+                }
+            }
+        }
+    }
+
+    if (env->insns_flags & PPC_ALTIVEC) {
+        reg.id = KVM_REG_PPC_VSCR;
+        reg.addr = (uintptr_t)&env->vscr;
+        ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, &reg);
+        if (ret < 0) {
+            DPRINTF("Unable to get VSCR from KVM: %s\n", strerror(errno));
+            return ret;
+        }
+
+        for (i = 0; i < 32; i++) {
+            reg.id = KVM_REG_PPC_VR(i);
+            reg.addr = (uintptr_t)&env->avr[i];
+            ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, &reg);
+            if (ret < 0) {
+                DPRINTF("Unable to get VR%d from KVM: %s\n",
+                        i, strerror(errno));
+                return ret;
+            }
+        }
+    }
+
+    return 0;
+}
+
+#if defined(TARGET_PPC64)
+static int kvm_get_vpa(CPUState *cs)
+{
+    PowerPCCPU *cpu = POWERPC_CPU(cs);
+    CPUPPCState *env = &cpu->env;
+    struct kvm_one_reg reg;
+    int ret;
+
+    reg.id = KVM_REG_PPC_VPA_ADDR;
+    reg.addr = (uintptr_t)&env->vpa_addr;
+    ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, &reg);
+    if (ret < 0) {
+        DPRINTF("Unable to get VPA address from KVM: %s\n", strerror(errno));
+        return ret;
+    }
+
+    assert((uintptr_t)&env->slb_shadow_size
+           == ((uintptr_t)&env->slb_shadow_addr + 8));
+    reg.id = KVM_REG_PPC_VPA_SLB;
+    reg.addr = (uintptr_t)&env->slb_shadow_addr;
+    ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, &reg);
+    if (ret < 0) {
+        DPRINTF("Unable to get SLB shadow state from KVM: %s\n",
+                strerror(errno));
+        return ret;
+    }
+
+    assert((uintptr_t)&env->dtl_size == ((uintptr_t)&env->dtl_addr + 8));
+    reg.id = KVM_REG_PPC_VPA_DTL;
+    reg.addr = (uintptr_t)&env->dtl_addr;
+    ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, &reg);
+    if (ret < 0) {
+        DPRINTF("Unable to get dispatch trace log state from KVM: %s\n",
+                strerror(errno));
+        return ret;
+    }
+
+    return 0;
+}
+
+static int kvm_put_vpa(CPUState *cs)
+{
+    PowerPCCPU *cpu = POWERPC_CPU(cs);
+    CPUPPCState *env = &cpu->env;
+    struct kvm_one_reg reg;
+    int ret;
+
+    /* SLB shadow or DTL can't be registered unless a master VPA is
+     * registered.  That means when restoring state, if a VPA *is*
+     * registered, we need to set that up first.  If not, we need to
+     * deregister the others before deregistering the master VPA */
+    assert(env->vpa_addr || !(env->slb_shadow_addr || env->dtl_addr));
+
+    if (env->vpa_addr) {
+        reg.id = KVM_REG_PPC_VPA_ADDR;
+        reg.addr = (uintptr_t)&env->vpa_addr;
+        ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, &reg);
+        if (ret < 0) {
+            DPRINTF("Unable to set VPA address to KVM: %s\n", strerror(errno));
+            return ret;
+        }
+    }
+
+    assert((uintptr_t)&env->slb_shadow_size
+           == ((uintptr_t)&env->slb_shadow_addr + 8));
+    reg.id = KVM_REG_PPC_VPA_SLB;
+    reg.addr = (uintptr_t)&env->slb_shadow_addr;
+    ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, &reg);
+    if (ret < 0) {
+        DPRINTF("Unable to set SLB shadow state to KVM: %s\n", strerror(errno));
+        return ret;
+    }
+
+    assert((uintptr_t)&env->dtl_size == ((uintptr_t)&env->dtl_addr + 8));
+    reg.id = KVM_REG_PPC_VPA_DTL;
+    reg.addr = (uintptr_t)&env->dtl_addr;
+    ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, &reg);
+    if (ret < 0) {
+        DPRINTF("Unable to set dispatch trace log state to KVM: %s\n",
+                strerror(errno));
+        return ret;
+    }
+
+    if (!env->vpa_addr) {
+        reg.id = KVM_REG_PPC_VPA_ADDR;
+        reg.addr = (uintptr_t)&env->vpa_addr;
+        ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, &reg);
+        if (ret < 0) {
+            DPRINTF("Unable to set VPA address to KVM: %s\n", strerror(errno));
+            return ret;
+        }
+    }
+
+    return 0;
+}
+#endif /* TARGET_PPC64 */
+
 int kvm_arch_put_registers(CPUState *cs, int level)
 {
     PowerPCCPU *cpu = POWERPC_CPU(cs);
@@ -459,7 +772,7 @@ int kvm_arch_put_registers(CPUState *cs, int level)
 
     regs.ctr = env->ctr;
     regs.lr  = env->lr;
-    regs.xer = env->xer;
+    regs.xer = cpu_read_xer(env);
     regs.msr = env->msr;
     regs.pc = env->nip;
 
@@ -480,10 +793,17 @@ int kvm_arch_put_registers(CPUState *cs, int level)
     for (i = 0;i < 32; i++)
         regs.gpr[i] = env->gpr[i];
 
+    regs.cr = 0;
+    for (i = 0; i < 8; i++) {
+        regs.cr |= (env->crf[i] & 15) << (4 * (7 - i));
+    }
+
     ret = kvm_vcpu_ioctl(cs, KVM_SET_REGS, &regs);
     if (ret < 0)
         return ret;
 
+    kvm_put_fp(cs);
+
     if (env->tlb_dirty) {
         kvm_sw_tlb_put(cpu);
         env->tlb_dirty = false;
@@ -498,7 +818,7 @@ int kvm_arch_put_registers(CPUState *cs, int level)
 
         /* Sync SLB */
 #ifdef TARGET_PPC64
-        for (i = 0; i < 64; i++) {
+        for (i = 0; i < ARRAY_SIZE(env->slb); i++) {
             sregs.u.s.ppc64.slb[i].slbe = env->slb[i].esid;
             sregs.u.s.ppc64.slb[i].slbv = env->slb[i].vsid;
         }
@@ -525,16 +845,31 @@ int kvm_arch_put_registers(CPUState *cs, int level)
     }
 
     if (cap_hior && (level >= KVM_PUT_RESET_STATE)) {
-        uint64_t hior = env->spr[SPR_HIOR];
-        struct kvm_one_reg reg = {
-            .id = KVM_REG_PPC_HIOR,
-            .addr = (uintptr_t) &hior,
-        };
+        kvm_put_one_spr(cs, KVM_REG_PPC_HIOR, SPR_HIOR);
+    }
 
-        ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, &reg);
-        if (ret) {
-            return ret;
+    if (cap_one_reg) {
+        int i;
+
+        /* We deliberately ignore errors here, for kernels which have
+         * the ONE_REG calls, but don't support the specific
+         * registers, there's a reasonable chance things will still
+         * work, at least until we try to migrate. */
+        for (i = 0; i < 1024; i++) {
+            uint64_t id = env->spr_cb[i].one_reg_id;
+
+            if (id != 0) {
+                kvm_put_one_spr(cs, id, i);
+            }
+        }
+
+#ifdef TARGET_PPC64
+        if (cap_papr) {
+            if (kvm_put_vpa(cs) < 0) {
+                DPRINTF("Warning: Unable to set VPA information to KVM\n");
+            }
         }
+#endif /* TARGET_PPC64 */
     }
 
     return ret;
@@ -561,7 +896,7 @@ int kvm_arch_get_registers(CPUState *cs)
 
     env->ctr = regs.ctr;
     env->lr = regs.lr;
-    env->xer = regs.xer;
+    cpu_write_xer(env, regs.xer);
     env->msr = regs.msr;
     env->nip = regs.pc;
 
@@ -582,6 +917,8 @@ int kvm_arch_get_registers(CPUState *cs)
     for (i = 0;i < 32; i++)
         env->gpr[i] = regs.gpr[i];
 
+    kvm_get_fp(cs);
+
     if (cap_booke_sregs) {
         ret = kvm_vcpu_ioctl(cs, KVM_GET_SREGS, &sregs);
         if (ret < 0) {
@@ -696,9 +1033,22 @@ int kvm_arch_get_registers(CPUState *cs)
 
         /* Sync SLB */
 #ifdef TARGET_PPC64
-        for (i = 0; i < 64; i++) {
-            ppc_store_slb(env, sregs.u.s.ppc64.slb[i].slbe,
-                               sregs.u.s.ppc64.slb[i].slbv);
+        /*
+         * The packed SLB array we get from KVM_GET_SREGS only contains
+         * information about valid entries. So we flush our internal
+         * copy to get rid of stale ones, then put all valid SLB entries
+         * back in.
+         */
+        memset(env->slb, 0, sizeof(env->slb));
+        for (i = 0; i < ARRAY_SIZE(env->slb); i++) {
+            target_ulong rb = sregs.u.s.ppc64.slb[i].slbe;
+            target_ulong rs = sregs.u.s.ppc64.slb[i].slbv;
+            /*
+             * Only restore valid entries
+             */
+            if (rb & SLB_ESID_V) {
+                ppc_store_slb(env, rb, rs);
+            }
         }
 #endif
 
@@ -716,6 +1066,34 @@ int kvm_arch_get_registers(CPUState *cs)
         }
     }
 
+    if (cap_hior) {
+        kvm_get_one_spr(cs, KVM_REG_PPC_HIOR, SPR_HIOR);
+    }
+
+    if (cap_one_reg) {
+        int i;
+
+        /* We deliberately ignore errors here, for kernels which have
+         * the ONE_REG calls, but don't support the specific
+         * registers, there's a reasonable chance things will still
+         * work, at least until we try to migrate. */
+        for (i = 0; i < 1024; i++) {
+            uint64_t id = env->spr_cb[i].one_reg_id;
+
+            if (id != 0) {
+                kvm_get_one_spr(cs, id, i);
+            }
+        }
+
+#ifdef TARGET_PPC64
+        if (cap_papr) {
+            if (kvm_get_vpa(cs) < 0) {
+                DPRINTF("Warning: Unable to get VPA information from KVM\n");
+            }
+        }
+#endif
+    }
+
     return 0;
 }
 
@@ -755,7 +1133,7 @@ void kvm_arch_pre_run(CPUState *cs, struct kvm_run *run)
      * interrupt, reset, etc) in PPC-specific env->irq_input_state. */
     if (!cap_interrupt_level &&
         run->ready_for_interrupt_injection &&
-        (env->interrupt_request & CPU_INTERRUPT_HARD) &&
+        (cs->interrupt_request & CPU_INTERRUPT_HARD) &&
         (env->irq_input_state & (1<<PPC_INPUT_INT)))
     {
         /* For now KVM disregards the 'irq' argument. However, in the
@@ -764,13 +1142,14 @@ void kvm_arch_pre_run(CPUState *cs, struct kvm_run *run)
          */
         irq = KVM_INTERRUPT_SET;
 
-        dprintf("injected interrupt %d\n", irq);
+        DPRINTF("injected interrupt %d\n", irq);
         r = kvm_vcpu_ioctl(cs, KVM_INTERRUPT, &irq);
-        if (r < 0)
-            printf("cpu %d fail inject %x\n", env->cpu_index, irq);
+        if (r < 0) {
+            printf("cpu %d fail inject %x\n", cs->cpu_index, irq);
+        }
 
         /* Always wake up soon in case the interrupt was level based */
-        qemu_mod_timer(idle_timer, qemu_get_clock_ns(vm_clock) +
+        timer_mod(idle_timer, qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) +
                        (get_ticks_per_sec() / 50));
     }
 
@@ -785,14 +1164,16 @@ void kvm_arch_post_run(CPUState *cpu, struct kvm_run *run)
 
 int kvm_arch_process_async_events(CPUState *cs)
 {
-    PowerPCCPU *cpu = POWERPC_CPU(cs);
-    return cpu->env.halted;
+    return cs->halted;
 }
 
-static int kvmppc_handle_halt(CPUPPCState *env)
+static int kvmppc_handle_halt(PowerPCCPU *cpu)
 {
-    if (!(env->interrupt_request & CPU_INTERRUPT_HARD) && (msr_ee)) {
-        env->halted = 1;
+    CPUState *cs = CPU(cpu);
+    CPUPPCState *env = &cpu->env;
+
+    if (!(cs->interrupt_request & CPU_INTERRUPT_HARD) && (msr_ee)) {
+        cs->halted = 1;
         env->exception_index = EXCP_HLT;
     }
 
@@ -825,26 +1206,37 @@ int kvm_arch_handle_exit(CPUState *cs, struct kvm_run *run)
     switch (run->exit_reason) {
     case KVM_EXIT_DCR:
         if (run->dcr.is_write) {
-            dprintf("handle dcr write\n");
+            DPRINTF("handle dcr write\n");
             ret = kvmppc_handle_dcr_write(env, run->dcr.dcrn, run->dcr.data);
         } else {
-            dprintf("handle dcr read\n");
+            DPRINTF("handle dcr read\n");
             ret = kvmppc_handle_dcr_read(env, run->dcr.dcrn, &run->dcr.data);
         }
         break;
     case KVM_EXIT_HLT:
-        dprintf("handle halt\n");
-        ret = kvmppc_handle_halt(env);
+        DPRINTF("handle halt\n");
+        ret = kvmppc_handle_halt(cpu);
         break;
-#ifdef CONFIG_PSERIES
+#if defined(TARGET_PPC64)
     case KVM_EXIT_PAPR_HCALL:
-        dprintf("handle PAPR hypercall\n");
+        DPRINTF("handle PAPR hypercall\n");
         run->papr_hcall.ret = spapr_hypercall(cpu,
                                               run->papr_hcall.nr,
                                               run->papr_hcall.args);
         ret = 0;
         break;
 #endif
+    case KVM_EXIT_EPR:
+        DPRINTF("handle epr\n");
+        run->epr.epr = ldl_phys(env->mpic_iack);
+        ret = 0;
+        break;
+    case KVM_EXIT_WATCHDOG:
+        DPRINTF("handle watchdog expiry\n");
+        watchdog_perform_action();
+        ret = 0;
+        break;
+
     default:
         fprintf(stderr, "KVM: unknown exit reason %d\n", run->exit_reason);
         ret = -1;
@@ -854,6 +1246,71 @@ int kvm_arch_handle_exit(CPUState *cs, struct kvm_run *run)
     return ret;
 }
 
+int kvmppc_or_tsr_bits(PowerPCCPU *cpu, uint32_t tsr_bits)
+{
+    CPUState *cs = CPU(cpu);
+    uint32_t bits = tsr_bits;
+    struct kvm_one_reg reg = {
+        .id = KVM_REG_PPC_OR_TSR,
+        .addr = (uintptr_t) &bits,
+    };
+
+    return kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, &reg);
+}
+
+int kvmppc_clear_tsr_bits(PowerPCCPU *cpu, uint32_t tsr_bits)
+{
+
+    CPUState *cs = CPU(cpu);
+    uint32_t bits = tsr_bits;
+    struct kvm_one_reg reg = {
+        .id = KVM_REG_PPC_CLEAR_TSR,
+        .addr = (uintptr_t) &bits,
+    };
+
+    return kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, &reg);
+}
+
+int kvmppc_set_tcr(PowerPCCPU *cpu)
+{
+    CPUState *cs = CPU(cpu);
+    CPUPPCState *env = &cpu->env;
+    uint32_t tcr = env->spr[SPR_BOOKE_TCR];
+
+    struct kvm_one_reg reg = {
+        .id = KVM_REG_PPC_TCR,
+        .addr = (uintptr_t) &tcr,
+    };
+
+    return kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, &reg);
+}
+
+int kvmppc_booke_watchdog_enable(PowerPCCPU *cpu)
+{
+    CPUState *cs = CPU(cpu);
+    struct kvm_enable_cap encap = {};
+    int ret;
+
+    if (!kvm_enabled()) {
+        return -1;
+    }
+
+    if (!cap_ppc_watchdog) {
+        printf("warning: KVM does not support watchdog");
+        return -1;
+    }
+
+    encap.cap = KVM_CAP_PPC_BOOKE_WATCHDOG;
+    ret = kvm_vcpu_ioctl(cs, KVM_ENABLE_CAP, &encap);
+    if (ret < 0) {
+        fprintf(stderr, "%s: couldn't enable KVM_CAP_PPC_BOOKE_WATCHDOG: %s\n",
+                __func__, strerror(-ret));
+        return ret;
+    }
+
+    return ret;
+}
+
 static int read_cpuinfo(const char *field, char *value, int len)
 {
     FILE *f;
@@ -989,18 +1446,38 @@ uint32_t kvmppc_get_dfp(void)
     return kvmppc_read_int_cpu_dt("ibm,dfp");
 }
 
+static int kvmppc_get_pvinfo(CPUPPCState *env, struct kvm_ppc_pvinfo *pvinfo)
+ {
+     PowerPCCPU *cpu = ppc_env_get_cpu(env);
+     CPUState *cs = CPU(cpu);
+
+    if (kvm_check_extension(cs->kvm_state, KVM_CAP_PPC_GET_PVINFO) &&
+        !kvm_vm_ioctl(cs->kvm_state, KVM_PPC_GET_PVINFO, pvinfo)) {
+        return 0;
+    }
+
+    return 1;
+}
+
+int kvmppc_get_hasidle(CPUPPCState *env)
+{
+    struct kvm_ppc_pvinfo pvinfo;
+
+    if (!kvmppc_get_pvinfo(env, &pvinfo) &&
+        (pvinfo.flags & KVM_PPC_PVINFO_FLAGS_EV_IDLE)) {
+        return 1;
+    }
+
+    return 0;
+}
+
 int kvmppc_get_hypercall(CPUPPCState *env, uint8_t *buf, int buf_len)
 {
-    PowerPCCPU *cpu = ppc_env_get_cpu(env);
-    CPUState *cs = CPU(cpu);
     uint32_t *hc = (uint32_t*)buf;
-
     struct kvm_ppc_pvinfo pvinfo;
 
-    if (kvm_check_extension(cs->kvm_state, KVM_CAP_PPC_GET_PVINFO) &&
-        !kvm_vm_ioctl(cs->kvm_state, KVM_PPC_GET_PVINFO, &pvinfo)) {
+    if (!kvmppc_get_pvinfo(env, &pvinfo)) {
         memcpy(buf, pvinfo.hcall, buf_len);
-
         return 0;
     }
 
@@ -1034,6 +1511,26 @@ void kvmppc_set_papr(PowerPCCPU *cpu)
     if (ret) {
         cpu_abort(env, "This KVM version does not support PAPR\n");
     }
+
+    /* Update the capability flag so we sync the right information
+     * with kvm */
+    cap_papr = 1;
+}
+
+void kvmppc_set_mpic_proxy(PowerPCCPU *cpu, int mpic_proxy)
+{
+    CPUPPCState *env = &cpu->env;
+    CPUState *cs = CPU(cpu);
+    struct kvm_enable_cap cap = {};
+    int ret;
+
+    cap.cap = KVM_CAP_PPC_EPR;
+    cap.args[0] = mpic_proxy;
+    ret = kvm_vcpu_ioctl(cs, KVM_ENABLE_CAP, &cap);
+
+    if (ret && mpic_proxy) {
+        cpu_abort(env, "This KVM version does not support EPR\n");
+    }
 }
 
 int kvmppc_smt_threads(void)
@@ -1078,7 +1575,7 @@ off_t kvmppc_alloc_rma(const char *name, MemoryRegion *sysmem)
     };
 
     rma_region = g_new(MemoryRegion, 1);
-    memory_region_init_ram_ptr(rma_region, name, size, rma);
+    memory_region_init_ram_ptr(rma_region, NULL, name, size, rma);
     vmstate_register_ram_global(rma_region);
     memory_region_add_subregion(sysmem, 0, rma_region);
 
@@ -1087,11 +1584,35 @@ off_t kvmppc_alloc_rma(const char *name, MemoryRegion *sysmem)
 
 uint64_t kvmppc_rma_size(uint64_t current_size, unsigned int hash_shift)
 {
+    struct kvm_ppc_smmu_info info;
+    long rampagesize, best_page_shift;
+    int i;
+
     if (cap_ppc_rma >= 2) {
         return current_size;
     }
+
+    /* Find the largest hardware supported page size that's less than
+     * or equal to the (logical) backing page size of guest RAM */
+    kvm_get_smmu_info(POWERPC_CPU(first_cpu), &info);
+    rampagesize = getrampagesize();
+    best_page_shift = 0;
+
+    for (i = 0; i < KVM_PPC_PAGE_SIZES_MAX_SZ; i++) {
+        struct kvm_ppc_one_seg_page_size *sps = &info.sps[i];
+
+        if (!sps->page_shift) {
+            continue;
+        }
+
+        if ((sps->page_shift > best_page_shift)
+            && ((1UL << sps->page_shift) <= rampagesize)) {
+            best_page_shift = sps->page_shift;
+        }
+    }
+
     return MIN(current_size,
-               getrampagesize() << (hash_shift - 7));
+               1ULL << (best_page_shift + hash_shift - 7));
 }
 #endif
 
@@ -1120,7 +1641,7 @@ void *kvmppc_create_spapr_tce(uint32_t liobn, uint32_t window_size, int *pfd)
         return NULL;
     }
 
-    len = (window_size / SPAPR_TCE_PAGE_SIZE) * sizeof(sPAPRTCE);
+    len = (window_size / SPAPR_TCE_PAGE_SIZE) * sizeof(uint64_t);
     /* FIXME: round this up to page size */
 
     table = mmap(NULL, len, PROT_READ|PROT_WRITE, MAP_SHARED, fd, 0);
@@ -1143,7 +1664,7 @@ int kvmppc_remove_spapr_tce(void *table, int fd, uint32_t window_size)
         return -1;
     }
 
-    len = (window_size / SPAPR_TCE_PAGE_SIZE)*sizeof(sPAPRTCE);
+    len = (window_size / SPAPR_TCE_PAGE_SIZE)*sizeof(uint64_t);
     if ((munmap(table, len) < 0) ||
         (close(fd) < 0)) {
         fprintf(stderr, "KVM: Unexpected error removing TCE table: %s",
@@ -1210,46 +1731,158 @@ static void alter_insns(uint64_t *word, uint64_t flags, bool on)
     }
 }
 
-const ppc_def_t *kvmppc_host_cpu_def(void)
+static void kvmppc_host_cpu_initfn(Object *obj)
 {
-    uint32_t host_pvr = mfpvr();
-    const ppc_def_t *base_spec;
-    ppc_def_t *spec;
+    assert(kvm_enabled());
+}
+
+static void kvmppc_host_cpu_class_init(ObjectClass *oc, void *data)
+{
+    PowerPCCPUClass *pcc = POWERPC_CPU_CLASS(oc);
     uint32_t vmx = kvmppc_get_vmx();
     uint32_t dfp = kvmppc_get_dfp();
+    uint32_t dcache_size = kvmppc_read_int_cpu_dt("d-cache-size");
+    uint32_t icache_size = kvmppc_read_int_cpu_dt("i-cache-size");
 
-    base_spec = ppc_find_by_pvr(host_pvr);
-
-    spec = g_malloc0(sizeof(*spec));
-    memcpy(spec, base_spec, sizeof(*spec));
-
-    /* Now fix up the spec with information we can query from the host */
+    /* Now fix up the class with information we can query from the host */
 
     if (vmx != -1) {
         /* Only override when we know what the host supports */
-        alter_insns(&spec->insns_flags, PPC_ALTIVEC, vmx > 0);
-        alter_insns(&spec->insns_flags2, PPC2_VSX, vmx > 1);
+        alter_insns(&pcc->insns_flags, PPC_ALTIVEC, vmx > 0);
+        alter_insns(&pcc->insns_flags2, PPC2_VSX, vmx > 1);
     }
     if (dfp != -1) {
         /* Only override when we know what the host supports */
-        alter_insns(&spec->insns_flags2, PPC2_DFP, dfp);
+        alter_insns(&pcc->insns_flags2, PPC2_DFP, dfp);
     }
 
-    return spec;
+    if (dcache_size != -1) {
+        pcc->l1_dcache_size = dcache_size;
+    }
+
+    if (icache_size != -1) {
+        pcc->l1_icache_size = icache_size;
+    }
 }
 
-int kvmppc_fixup_cpu(CPUPPCState *env)
+int kvmppc_fixup_cpu(PowerPCCPU *cpu)
 {
+    CPUState *cs = CPU(cpu);
     int smt;
 
     /* Adjust cpu index for SMT */
     smt = kvmppc_smt_threads();
-    env->cpu_index = (env->cpu_index / smp_threads) * smt
-        + (env->cpu_index % smp_threads);
+    cs->cpu_index = (cs->cpu_index / smp_threads) * smt
+        + (cs->cpu_index % smp_threads);
+
+    return 0;
+}
+
+bool kvmppc_has_cap_epr(void)
+{
+    return cap_epr;
+}
 
+static int kvm_ppc_register_host_cpu_type(void)
+{
+    TypeInfo type_info = {
+        .name = TYPE_HOST_POWERPC_CPU,
+        .instance_init = kvmppc_host_cpu_initfn,
+        .class_init = kvmppc_host_cpu_class_init,
+    };
+    uint32_t host_pvr = mfpvr();
+    PowerPCCPUClass *pvr_pcc;
+
+    pvr_pcc = ppc_cpu_class_by_pvr(host_pvr);
+    if (pvr_pcc == NULL) {
+        return -1;
+    }
+    type_info.parent = object_class_get_name(OBJECT_CLASS(pvr_pcc));
+    type_register(&type_info);
     return 0;
 }
 
+int kvmppc_define_rtas_kernel_token(uint32_t token, const char *function)
+{
+    struct kvm_rtas_token_args args = {
+        .token = token,
+    };
+
+    if (!kvm_check_extension(kvm_state, KVM_CAP_PPC_RTAS)) {
+        return -ENOENT;
+    }
+
+    strncpy(args.name, function, sizeof(args.name));
+
+    return kvm_vm_ioctl(kvm_state, KVM_PPC_RTAS_DEFINE_TOKEN, &args);
+}
+
+int kvmppc_get_htab_fd(bool write)
+{
+    struct kvm_get_htab_fd s = {
+        .flags = write ? KVM_GET_HTAB_WRITE : 0,
+        .start_index = 0,
+    };
+
+    if (!cap_htab_fd) {
+        fprintf(stderr, "KVM version doesn't support saving the hash table\n");
+        return -1;
+    }
+
+    return kvm_vm_ioctl(kvm_state, KVM_PPC_GET_HTAB_FD, &s);
+}
+
+int kvmppc_save_htab(QEMUFile *f, int fd, size_t bufsize, int64_t max_ns)
+{
+    int64_t starttime = qemu_clock_get_ns(QEMU_CLOCK_REALTIME);
+    uint8_t buf[bufsize];
+    ssize_t rc;
+
+    do {
+        rc = read(fd, buf, bufsize);
+        if (rc < 0) {
+            fprintf(stderr, "Error reading data from KVM HTAB fd: %s\n",
+                    strerror(errno));
+            return rc;
+        } else if (rc) {
+            /* Kernel already retuns data in BE format for the file */
+            qemu_put_buffer(f, buf, rc);
+        }
+    } while ((rc != 0)
+             && ((max_ns < 0)
+                 || ((qemu_clock_get_ns(QEMU_CLOCK_REALTIME) - starttime) < max_ns)));
+
+    return (rc == 0) ? 1 : 0;
+}
+
+int kvmppc_load_htab_chunk(QEMUFile *f, int fd, uint32_t index,
+                           uint16_t n_valid, uint16_t n_invalid)
+{
+    struct kvm_get_htab_header *buf;
+    size_t chunksize = sizeof(*buf) + n_valid*HASH_PTE_SIZE_64;
+    ssize_t rc;
+
+    buf = alloca(chunksize);
+    /* This is KVM on ppc, so this is all big-endian */
+    buf->index = index;
+    buf->n_valid = n_valid;
+    buf->n_invalid = n_invalid;
+
+    qemu_get_buffer(f, (void *)(buf + 1), HASH_PTE_SIZE_64*n_valid);
+
+    rc = write(fd, buf, chunksize);
+    if (rc < 0) {
+        fprintf(stderr, "Error writing KVM hash table: %s\n",
+                strerror(errno));
+        return rc;
+    }
+    if (rc != chunksize) {
+        /* We should never get a short write on a single chunk */
+        fprintf(stderr, "Short write, restoring KVM hash table\n");
+        return -1;
+    }
+    return 0;
+}
 
 bool kvm_arch_stop_on_emulation_error(CPUState *cpu)
 {
@@ -1265,3 +1898,7 @@ int kvm_arch_on_sigbus(int code, void *addr)
 {
     return 1;
 }
+
+void kvm_arch_init_irq_routing(KVMState *s)
+{
+}