1 files changed, 170 insertions, 32 deletions

diff --git a/target-ppc/kvm.c b/target-ppc/kvm.c
index 30a870ecb..9974b10cc 100644
--- a/target-ppc/kvm.c
+++ b/target-ppc/kvm.c
@@ -36,6 +36,7 @@
 #include "hw/ppc/spapr.h"
 #include "hw/ppc/spapr_vio.h"
 #include "sysemu/watchdog.h"
+#include "trace.h"
 
 //#define DEBUG_KVM
 
@@ -401,7 +402,7 @@ static inline void kvm_fixup_page_sizes(PowerPCCPU *cpu)
 
 unsigned long kvm_arch_vcpu_id(CPUState *cpu)
 {
-    return cpu->cpu_index;
+    return ppc_get_vcpu_dt_id(POWERPC_CPU(cpu));
 }
 
 int kvm_arch_init_vcpu(CPUState *cs)
@@ -419,7 +420,7 @@ 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) {
@@ -480,8 +481,7 @@ static void kvm_get_one_spr(CPUState *cs, uint64_t id, int spr)
 
     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));
+        trace_kvm_failed_spr_get(spr, strerror(errno));
     } else {
         switch (id & KVM_REG_SIZE_MASK) {
         case KVM_REG_SIZE_U32:
@@ -529,8 +529,7 @@ static void kvm_put_one_spr(CPUState *cs, uint64_t id, int spr)
 
     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));
+        trace_kvm_failed_spr_set(spr, strerror(errno));
     }
 }
 
@@ -818,8 +817,11 @@ 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;
+            if (env->slb[i].esid & SLB_ESID_V) {
+                sregs.u.s.ppc64.slb[i].slbe |= i;
+            }
             sregs.u.s.ppc64.slb[i].slbv = env->slb[i].vsid;
         }
 #endif
@@ -1029,13 +1031,28 @@ int kvm_arch_get_registers(CPUState *cs)
             return ret;
         }
 
-        ppc_store_sdr1(env, sregs.u.s.sdr1);
+        if (!env->external_htab) {
+            ppc_store_sdr1(env, sregs.u.s.sdr1);
+        }
 
         /* 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
 
@@ -1136,7 +1153,7 @@ void kvm_arch_pre_run(CPUState *cs, struct kvm_run *run)
         }
 
         /* 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));
     }
 
@@ -1161,7 +1178,7 @@ static int kvmppc_handle_halt(PowerPCCPU *cpu)
 
     if (!(cs->interrupt_request & CPU_INTERRUPT_HARD) && (msr_ee)) {
         cs->halted = 1;
-        env->exception_index = EXCP_HLT;
+        cs->exception_index = EXCP_HLT;
     }
 
     return 0;
@@ -1215,7 +1232,7 @@ int kvm_arch_handle_exit(CPUState *cs, struct kvm_run *run)
 #endif
     case KVM_EXIT_EPR:
         DPRINTF("handle epr\n");
-        run->epr.epr = ldl_phys(env->mpic_iack);
+        run->epr.epr = ldl_phys(cs->as, env->mpic_iack);
         ret = 0;
         break;
     case KVM_EXIT_WATCHDOG:
@@ -1487,7 +1504,6 @@ int kvmppc_get_hypercall(CPUPPCState *env, uint8_t *buf, int buf_len)
 
 void kvmppc_set_papr(PowerPCCPU *cpu)
 {
-    CPUPPCState *env = &cpu->env;
     CPUState *cs = CPU(cpu);
     struct kvm_enable_cap cap = {};
     int ret;
@@ -1496,7 +1512,7 @@ void kvmppc_set_papr(PowerPCCPU *cpu)
     ret = kvm_vcpu_ioctl(cs, KVM_ENABLE_CAP, &cap);
 
     if (ret) {
-        cpu_abort(env, "This KVM version does not support PAPR\n");
+        cpu_abort(cs, "This KVM version does not support PAPR\n");
     }
 
     /* Update the capability flag so we sync the right information
@@ -1506,7 +1522,6 @@ void kvmppc_set_papr(PowerPCCPU *cpu)
 
 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;
@@ -1516,7 +1531,7 @@ void kvmppc_set_mpic_proxy(PowerPCCPU *cpu, int 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");
+        cpu_abort(cs, "This KVM version does not support EPR\n");
     }
 }
 
@@ -1732,6 +1747,7 @@ static void kvmppc_host_cpu_class_init(ObjectClass *oc, void *data)
     uint32_t icache_size = kvmppc_read_int_cpu_dt("i-cache-size");
 
     /* Now fix up the class with information we can query from the host */
+    pcc->pvr = mfpvr();
 
     if (vmx != -1) {
         /* Only override when we know what the host supports */
@@ -1752,22 +1768,14 @@ static void kvmppc_host_cpu_class_init(ObjectClass *oc, void *data)
     }
 }
 
-int kvmppc_fixup_cpu(PowerPCCPU *cpu)
+bool kvmppc_has_cap_epr(void)
 {
-    CPUState *cs = CPU(cpu);
-    int smt;
-
-    /* Adjust cpu index for SMT */
-    smt = kvmppc_smt_threads();
-    cs->cpu_index = (cs->cpu_index / smp_threads) * smt
-        + (cs->cpu_index % smp_threads);
-
-    return 0;
+    return cap_epr;
 }
 
-bool kvmppc_has_cap_epr(void)
+bool kvmppc_has_cap_htab_fd(void)
 {
-    return cap_epr;
+    return cap_htab_fd;
 }
 
 static int kvm_ppc_register_host_cpu_type(void)
@@ -1782,6 +1790,9 @@ static int kvm_ppc_register_host_cpu_type(void)
 
     pvr_pcc = ppc_cpu_class_by_pvr(host_pvr);
     if (pvr_pcc == NULL) {
+        pvr_pcc = ppc_cpu_class_by_pvr_mask(host_pvr);
+    }
+    if (pvr_pcc == NULL) {
         return -1;
     }
     type_info.parent = object_class_get_name(OBJECT_CLASS(pvr_pcc));
@@ -1789,6 +1800,20 @@ static int kvm_ppc_register_host_cpu_type(void)
     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)
 {
@@ -1807,7 +1832,7 @@ int kvmppc_get_htab_fd(bool write)
 
 int kvmppc_save_htab(QEMUFile *f, int fd, size_t bufsize, int64_t max_ns)
 {
-    int64_t starttime = qemu_get_clock_ns(rt_clock);
+    int64_t starttime = qemu_clock_get_ns(QEMU_CLOCK_REALTIME);
     uint8_t buf[bufsize];
     ssize_t rc;
 
@@ -1823,7 +1848,7 @@ int kvmppc_save_htab(QEMUFile *f, int fd, size_t bufsize, int64_t max_ns)
         }
     } while ((rc != 0)
              && ((max_ns < 0)
-                 || ((qemu_get_clock_ns(rt_clock) - starttime) < max_ns)));
+                 || ((qemu_clock_get_ns(QEMU_CLOCK_REALTIME) - starttime) < max_ns)));
 
     return (rc == 0) ? 1 : 0;
 }
@@ -1875,3 +1900,116 @@ int kvm_arch_on_sigbus(int code, void *addr)
 void kvm_arch_init_irq_routing(KVMState *s)
 {
 }
+
+int kvm_arch_insert_sw_breakpoint(CPUState *cpu, struct kvm_sw_breakpoint *bp)
+{
+    return -EINVAL;
+}
+
+int kvm_arch_remove_sw_breakpoint(CPUState *cpu, struct kvm_sw_breakpoint *bp)
+{
+    return -EINVAL;
+}
+
+int kvm_arch_insert_hw_breakpoint(target_ulong addr, target_ulong len, int type)
+{
+    return -EINVAL;
+}
+
+int kvm_arch_remove_hw_breakpoint(target_ulong addr, target_ulong len, int type)
+{
+    return -EINVAL;
+}
+
+void kvm_arch_remove_all_hw_breakpoints(void)
+{
+}
+
+void kvm_arch_update_guest_debug(CPUState *cpu, struct kvm_guest_debug *dbg)
+{
+}
+
+struct kvm_get_htab_buf {
+    struct kvm_get_htab_header header;
+    /*
+     * We require one extra byte for read
+     */
+    target_ulong hpte[(HPTES_PER_GROUP * 2) + 1];
+};
+
+uint64_t kvmppc_hash64_read_pteg(PowerPCCPU *cpu, target_ulong pte_index)
+{
+    int htab_fd;
+    struct kvm_get_htab_fd ghf;
+    struct kvm_get_htab_buf  *hpte_buf;
+
+    ghf.flags = 0;
+    ghf.start_index = pte_index;
+    htab_fd = kvm_vm_ioctl(kvm_state, KVM_PPC_GET_HTAB_FD, &ghf);
+    if (htab_fd < 0) {
+        goto error_out;
+    }
+
+    hpte_buf = g_malloc0(sizeof(*hpte_buf));
+    /*
+     * Read the hpte group
+     */
+    if (read(htab_fd, hpte_buf, sizeof(*hpte_buf)) < 0) {
+        goto out_close;
+    }
+
+    close(htab_fd);
+    return (uint64_t)(uintptr_t) hpte_buf->hpte;
+
+out_close:
+    g_free(hpte_buf);
+    close(htab_fd);
+error_out:
+    return 0;
+}
+
+void kvmppc_hash64_free_pteg(uint64_t token)
+{
+    struct kvm_get_htab_buf *htab_buf;
+
+    htab_buf = container_of((void *)(uintptr_t) token, struct kvm_get_htab_buf,
+                            hpte);
+    g_free(htab_buf);
+    return;
+}
+
+void kvmppc_hash64_write_pte(CPUPPCState *env, target_ulong pte_index,
+                             target_ulong pte0, target_ulong pte1)
+{
+    int htab_fd;
+    struct kvm_get_htab_fd ghf;
+    struct kvm_get_htab_buf hpte_buf;
+
+    ghf.flags = 0;
+    ghf.start_index = 0;     /* Ignored */
+    htab_fd = kvm_vm_ioctl(kvm_state, KVM_PPC_GET_HTAB_FD, &ghf);
+    if (htab_fd < 0) {
+        goto error_out;
+    }
+
+    hpte_buf.header.n_valid = 1;
+    hpte_buf.header.n_invalid = 0;
+    hpte_buf.header.index = pte_index;
+    hpte_buf.hpte[0] = pte0;
+    hpte_buf.hpte[1] = pte1;
+    /*
+     * Write the hpte entry.
+     * CAUTION: write() has the warn_unused_result attribute. Hence we
+     * need to check the return value, even though we do nothing.
+     */
+    if (write(htab_fd, &hpte_buf, sizeof(hpte_buf)) < 0) {
+        goto out_close;
+    }
+
+out_close:
+    close(htab_fd);
+    return;
+
+error_out:
+    return;
+}