Merge remote-tracking branch 'remotes/kvm/uq/master' into staging

* remotes/kvm/uq/master:
  kvm: Fix eax for cpuid leaf 0x40000000
  kvmclock: Ensure proper env->tsc value for kvmclock_current_nsec calculation
  kvm: Enable -cpu option to hide KVM
  kvm: Ensure negative return value on kvm_init() error handling path
  target-i386: set CC_OP to CC_OP_EFLAGS in cpu_load_eflags
  target-i386: get CPL from SS.DPL
  target-i386: rework CPL checks during task switch, preparing for next patch
  target-i386: fix segment flags for SMM and VM86 mode
  target-i386: Fix vm86 mode regression introduced in fd46060.
  kvm_stat: allow choosing between tracepoints and old stats
  kvmclock: Ensure time in migration never goes backward

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

bsd-user/main.c

@@ -1004,7 +1004,7 @@ int main(int argc, char **argv)
 
 #if defined(TARGET_I386)
     env->cr[0] = CR0_PG_MASK | CR0_WP_MASK | CR0_PE_MASK;
-    env->hflags |= HF_PE_MASK;
+    env->hflags |= HF_PE_MASK | HF_CPL_MASK;
     if (env->features[FEAT_1_EDX] & CPUID_SSE) {
         env->cr[4] |= CR4_OSFXSR_MASK;
         env->hflags |= HF_OSFXSR_MASK;

hw/i386/kvm/clock.c

@@ -14,8 +14,10 @@
  */
 
 #include "qemu-common.h"
+#include "qemu/host-utils.h"
 #include "sysemu/sysemu.h"
 #include "sysemu/kvm.h"
+#include "sysemu/cpus.h"
 #include "hw/sysbus.h"
 #include "hw/kvm/clock.h"
 
@@ -34,6 +36,48 @@ typedef struct KVMClockState {
     bool clock_valid;
 } KVMClockState;
 
+struct pvclock_vcpu_time_info {
+    uint32_t   version;
+    uint32_t   pad0;
+    uint64_t   tsc_timestamp;
+    uint64_t   system_time;
+    uint32_t   tsc_to_system_mul;
+    int8_t     tsc_shift;
+    uint8_t    flags;
+    uint8_t    pad[2];
+} __attribute__((__packed__)); /* 32 bytes */
+
+static uint64_t kvmclock_current_nsec(KVMClockState *s)
+{
+    CPUState *cpu = first_cpu;
+    CPUX86State *env = cpu->env_ptr;
+    hwaddr kvmclock_struct_pa = env->system_time_msr & ~1ULL;
+    uint64_t migration_tsc = env->tsc;
+    struct pvclock_vcpu_time_info time;
+    uint64_t delta;
+    uint64_t nsec_lo;
+    uint64_t nsec_hi;
+    uint64_t nsec;
+
+    if (!(env->system_time_msr & 1ULL)) {
+        /* KVM clock not active */
+        return 0;
+    }
+
+    cpu_physical_memory_read(kvmclock_struct_pa, &time, sizeof(time));
+
+    assert(time.tsc_timestamp <= migration_tsc);
+    delta = migration_tsc - time.tsc_timestamp;
+    if (time.tsc_shift < 0) {
+        delta >>= -time.tsc_shift;
+    } else {
+        delta <<= time.tsc_shift;
+    }
+
+    mulu64(&nsec_lo, &nsec_hi, delta, time.tsc_to_system_mul);
+    nsec = (nsec_lo >> 32) | (nsec_hi << 32);
+    return nsec + time.system_time;
+}
 
 static void kvmclock_vm_state_change(void *opaque, int running,
                                      RunState state)
@@ -45,9 +89,15 @@ static void kvmclock_vm_state_change(void *opaque, int running,
 
     if (running) {
         struct kvm_clock_data data;
+        uint64_t time_at_migration = kvmclock_current_nsec(s);
 
         s->clock_valid = false;
 
+	/* We can't rely on the migrated clock value, just discard it */
+	if (time_at_migration) {
+	        s->clock = time_at_migration;
+	}
+
         data.clock = s->clock;
         data.flags = 0;
         ret = kvm_vm_ioctl(kvm_state, KVM_SET_CLOCK, &data);
@@ -75,6 +125,8 @@ static void kvmclock_vm_state_change(void *opaque, int running,
         if (s->clock_valid) {
             return;
         }
+
+        cpu_synchronize_all_states();
         ret = kvm_vm_ioctl(kvm_state, KVM_GET_CLOCK, &data);
         if (ret < 0) {
             fprintf(stderr, "KVM_GET_CLOCK failed: %s\n", strerror(ret));

kvm-all.c

@@ -1410,7 +1410,7 @@ int kvm_init(MachineClass *mc)
 
     ret = kvm_ioctl(s, KVM_GET_API_VERSION, 0);
     if (ret < KVM_API_VERSION) {
-        if (ret > 0) {
+        if (ret >= 0) {
             ret = -EINVAL;
         }
         fprintf(stderr, "kvm version too old\n");
@@ -1461,6 +1461,7 @@ int kvm_init(MachineClass *mc)
     if (mc->kvm_type) {
         type = mc->kvm_type(kvm_type);
     } else if (kvm_type) {
+        ret = -EINVAL;
         fprintf(stderr, "Invalid argument kvm-type=%s\n", kvm_type);
         goto err;
     }
@@ -1561,6 +1562,7 @@ int kvm_init(MachineClass *mc)
     return 0;
 
 err:
+    assert(ret < 0);
     if (s->vmfd >= 0) {
         close(s->vmfd);
     }

linux-user/main.c

@@ -4052,7 +4052,7 @@ int main(int argc, char **argv, char **envp)
 
 #if defined(TARGET_I386)
     env->cr[0] = CR0_PG_MASK | CR0_WP_MASK | CR0_PE_MASK;
-    env->hflags |= HF_PE_MASK;
+    env->hflags |= HF_PE_MASK | HF_CPL_MASK;
     if (env->features[FEAT_1_EDX] & CPUID_SSE) {
         env->cr[4] |= CR4_OSFXSR_MASK;
         env->hflags |= HF_OSFXSR_MASK;

scripts/kvm/kvm_stat

@@ -352,8 +352,8 @@ class TracepointProvider(object):
         return ret
 
 class Stats:
-    def __init__(self, provider, fields = None):
-        self.provider = provider
+    def __init__(self, providers, fields = None):
+        self.providers = providers
         self.fields_filter = fields
         self._update()
     def _update(self):
@@ -362,22 +362,25 @@ class Stats:
             if not self.fields_filter:
                 return True
             return re.match(self.fields_filter, key) is not None
-        self.values = dict([(key, None)
-                            for key in provider.fields()
-                            if wanted(key)])
-        self.provider.select(self.values.keys())
+        self.values = dict()
+        for d in providers:
+            provider_fields = [key for key in d.fields() if wanted(key)]
+            for key in provider_fields:
+                self.values[key] = None
+            d.select(provider_fields)
     def set_fields_filter(self, fields_filter):
         self.fields_filter = fields_filter
         self._update()
     def get(self):
-        new = self.provider.read()
-        for key in self.provider.fields():
-            oldval = self.values.get(key, (0, 0))
-            newval = new[key]
-            newdelta = None
-            if oldval is not None:
-                newdelta = newval - oldval[0]
-            self.values[key] = (newval, newdelta)
+        for d in providers:
+            new = d.read()
+            for key in d.fields():
+                oldval = self.values.get(key, (0, 0))
+                newval = new[key]
+                newdelta = None
+                if oldval is not None:
+                    newdelta = newval - oldval[0]
+                self.values[key] = (newval, newdelta)
         return self.values
 
 if not os.access('/sys/kernel/debug', os.F_OK):
@@ -487,6 +490,18 @@ options.add_option('-l', '--log',
                    dest = 'log',
                    help = 'run in logging mode (like vmstat)',
                    )
+options.add_option('-t', '--tracepoints',
+                   action = 'store_true',
+                   default = False,
+                   dest = 'tracepoints',
+                   help = 'retrieve statistics from tracepoints',
+                   )
+options.add_option('-d', '--debugfs',
+                   action = 'store_true',
+                   default = False,
+                   dest = 'debugfs',
+                   help = 'retrieve statistics from debugfs',
+                   )
 options.add_option('-f', '--fields',
                    action = 'store',
                    default = None,
@@ -495,12 +510,19 @@ options.add_option('-f', '--fields',
                    )
 (options, args) = options.parse_args(sys.argv)
 
-try:
-    provider = TracepointProvider()
-except:
-    provider = DebugfsProvider()
+providers = []
+if options.tracepoints:
+    providers.append(TracepointProvider())
+if options.debugfs:
+    providers.append(DebugfsProvider())
+
+if len(providers) == 0:
+    try:
+        providers = [TracepointProvider()]
+    except:
+        providers = [DebugfsProvider()]
 
-stats = Stats(provider, fields = options.fields)
+stats = Stats(providers, fields = options.fields)
 
 if options.log:
     log(stats)

target-i386/cpu-qom.h

@@ -87,6 +87,7 @@ typedef struct X86CPU {
     bool hyperv_time;
     bool check_cpuid;
     bool enforce_cpuid;
+    bool expose_kvm;
 
     /* if true the CPUID code directly forward host cache leaves to the guest */
     bool cache_info_passthrough;

target-i386/cpu.c

@@ -2792,6 +2792,7 @@ static Property x86_cpu_properties[] = {
     DEFINE_PROP_BOOL("hv-time", X86CPU, hyperv_time, false),
     DEFINE_PROP_BOOL("check", X86CPU, check_cpuid, false),
     DEFINE_PROP_BOOL("enforce", X86CPU, enforce_cpuid, false),
+    DEFINE_PROP_BOOL("kvm", X86CPU, expose_kvm, true),
     DEFINE_PROP_END_OF_LIST()
 };
 

target-i386/cpu.h

@@ -986,7 +986,6 @@ static inline void cpu_x86_load_seg_cache(CPUX86State *env,
     /* update the hidden flags */
     {
         if (seg_reg == R_CS) {
-            int cpl = selector & 3;
 #ifdef TARGET_X86_64
             if ((env->hflags & HF_LMA_MASK) && (flags & DESC_L_MASK)) {
                 /* long mode */
@@ -996,15 +995,14 @@ static inline void cpu_x86_load_seg_cache(CPUX86State *env,
 #endif
             {
                 /* legacy / compatibility case */
-                if (!(env->cr[0] & CR0_PE_MASK))
-                    cpl = 0;
-                else if (env->eflags & VM_MASK)
-                    cpl = 3;
                 new_hflags = (env->segs[R_CS].flags & DESC_B_MASK)
                     >> (DESC_B_SHIFT - HF_CS32_SHIFT);
                 env->hflags = (env->hflags & ~(HF_CS32_MASK | HF_CS64_MASK)) |
                     new_hflags;
             }
+        }
+        if (seg_reg == R_SS) {
+            int cpl = (flags >> DESC_DPL_SHIFT) & 3;
 #if HF_CPL_MASK != 3
 #error HF_CPL_MASK is hardcoded
 #endif
@@ -1234,11 +1232,14 @@ static inline uint32_t cpu_compute_eflags(CPUX86State *env)
     return env->eflags | cpu_cc_compute_all(env, CC_OP) | (env->df & DF_MASK);
 }
 
-/* NOTE: CC_OP must be modified manually to CC_OP_EFLAGS */
+/* NOTE: the translator must set DisasContext.cc_op to CC_OP_EFLAGS
+ * after generating a call to a helper that uses this.
+ */
 static inline void cpu_load_eflags(CPUX86State *env, int eflags,
                                    int update_mask)
 {
     CC_SRC = eflags & (CC_O | CC_S | CC_Z | CC_A | CC_P | CC_C);
+    CC_OP = CC_OP_EFLAGS;
     env->df = 1 - (2 * ((eflags >> 10) & 1));
     env->eflags = (env->eflags & ~update_mask) |
         (eflags & update_mask) | 0x2;

target-i386/gdbstub.c

@@ -127,9 +127,11 @@ static int x86_cpu_gdb_load_seg(X86CPU *cpu, int sreg, uint8_t *mem_buf)
         target_ulong base;
 
         if (!(env->cr[0] & CR0_PE_MASK) || (env->eflags & VM_MASK)) {
+            int dpl = (env->eflags & VM_MASK) ? 3 : 0;
             base = selector << 4;
             limit = 0xffff;
-            flags = 0;
+            flags = DESC_P_MASK | DESC_S_MASK | DESC_W_MASK |
+                    DESC_A_MASK | (dpl << DESC_DPL_SHIFT);
         } else {
             if (!cpu_x86_get_descr_debug(env, selector, &base, &limit,
                                          &flags)) {

target-i386/kvm.c

@@ -528,23 +528,25 @@ int kvm_arch_init_vcpu(CPUState *cs)
         has_msr_hv_hypercall = true;
     }
 
-    memcpy(signature, "KVMKVMKVM\0\0\0", 12);
-    c = &cpuid_data.entries[cpuid_i++];
-    c->function = KVM_CPUID_SIGNATURE | kvm_base;
-    c->eax = 0;
-    c->ebx = signature[0];
-    c->ecx = signature[1];
-    c->edx = signature[2];
+    if (cpu->expose_kvm) {
+        memcpy(signature, "KVMKVMKVM\0\0\0", 12);
+        c = &cpuid_data.entries[cpuid_i++];
+        c->function = KVM_CPUID_SIGNATURE | kvm_base;
+        c->eax = KVM_CPUID_FEATURES | kvm_base;
+        c->ebx = signature[0];
+        c->ecx = signature[1];
+        c->edx = signature[2];
 
-    c = &cpuid_data.entries[cpuid_i++];
-    c->function = KVM_CPUID_FEATURES | kvm_base;
-    c->eax = env->features[FEAT_KVM];
+        c = &cpuid_data.entries[cpuid_i++];
+        c->function = KVM_CPUID_FEATURES | kvm_base;
+        c->eax = env->features[FEAT_KVM];
 
-    has_msr_async_pf_en = c->eax & (1 << KVM_FEATURE_ASYNC_PF);
+        has_msr_async_pf_en = c->eax & (1 << KVM_FEATURE_ASYNC_PF);
 
-    has_msr_pv_eoi_en = c->eax & (1 << KVM_FEATURE_PV_EOI);
+        has_msr_pv_eoi_en = c->eax & (1 << KVM_FEATURE_PV_EOI);
 
-    has_msr_kvm_steal_time = c->eax & (1 << KVM_FEATURE_STEAL_TIME);
+        has_msr_kvm_steal_time = c->eax & (1 << KVM_FEATURE_STEAL_TIME);
+    }
 
     cpu_x86_cpuid(env, 0, 0, &limit, &unused, &unused, &unused);
 
@@ -1430,7 +1432,7 @@ static int kvm_get_sregs(X86CPU *cpu)
        HF_OSFXSR_MASK | HF_LMA_MASK | HF_CS32_MASK | \
        HF_SS32_MASK | HF_CS64_MASK | HF_ADDSEG_MASK)
 
-    hflags = (env->segs[R_CS].flags >> DESC_DPL_SHIFT) & HF_CPL_MASK;
+    hflags = (env->segs[R_SS].flags >> DESC_DPL_SHIFT) & HF_CPL_MASK;
     hflags |= (env->cr[0] & CR0_PE_MASK) << (HF_PE_SHIFT - CR0_PE_SHIFT);
     hflags |= (env->cr[0] << (HF_MP_SHIFT - CR0_MP_SHIFT)) &
                 (HF_MP_MASK | HF_EM_MASK | HF_TS_MASK);

target-i386/machine.c

@@ -312,6 +312,14 @@ static int cpu_post_load(void *opaque, int version_id)
         env->segs[R_SS].flags &= ~(env->segs[R_SS].flags & DESC_DPL_MASK);
     }
 
+    /* Older versions of QEMU incorrectly used CS.DPL as the CPL when
+     * running under KVM.  This is wrong for conforming code segments.
+     * Luckily, in our implementation the CPL field of hflags is redundant
+     * and we can get the right value from the SS descriptor privilege level.
+     */
+    env->hflags &= ~HF_CPL_MASK;
+    env->hflags |= (env->segs[R_SS].flags >> DESC_DPL_SHIFT) & HF_CPL_MASK;
+
     /* XXX: restore FPU round state */
     env->fpstt = (env->fpus_vmstate >> 11) & 7;
     env->fpus = env->fpus_vmstate & ~0x3800;