Merge remote-tracking branch 'remotes/bonzini/tags/for-upstream' into staging

Usual mix of patches, the most important being Alex and Marcelo's
kvmclock fix.  This was reverted last minute for 2.1, but it is now back
with the problematic case fixed.

Note: I will soon switch to a subkey for signing purposes.  To verify
future signed pull requests from me, please update my key with
"gpg --recv-keys 9B4D86F2".  You should see 3 new subkeys---the
one for signing will be a 2048-bit RSA key, 4E6B09D7.

# gpg: Signature made Fri 26 Sep 2014 15:34:44 BST using RSA key ID 9B4D86F2
# gpg: Good signature from "Paolo Bonzini <pbonzini@redhat.com>"
# gpg:                 aka "Paolo Bonzini <bonzini@gnu.org>"

* remotes/bonzini/tags/for-upstream:
  kvm/valgrind: don't mark memory as initialized
  po: fix conflict with %.mo rule in rules.mak
  kvmvapic: fix migration when VM paused and when not running Windows
  serial: check if backed by a physical serial port at realize time
  serial: reset state at startup
  target-i386: update fp status fix
  hw/dma/i8257: Silence phony error message
  kvmclock: Ensure time in migration never goes backward
  kvmclock: Ensure proper env->tsc value for kvmclock_current_nsec calculation
  Introduce cpu_clean_all_dirty
  pit: fix pit interrupt can't inject into vm after migration

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

17 files changed, 117 insertions, 31 deletions

diff --git a/configure b/configure
index 862f6d27e3..a2c0f2a02a 100755
--- a/configure
+++ b/configure
@@ -3956,12 +3956,11 @@ else
 fi
 
 ########################################
-# check if we have valgrind/valgrind.h and valgrind/memcheck.h
+# check if we have valgrind/valgrind.h
 
 valgrind_h=no
 cat > $TMPC << EOF
 #include <valgrind/valgrind.h>
-#include <valgrind/memcheck.h>
 int main(void) {
   return 0;
 }
diff --git a/cpus.c b/cpus.c
index 2a0e133d39..0c33458bb1 100644
--- a/cpus.c
+++ b/cpus.c
@@ -593,6 +593,15 @@ void cpu_synchronize_all_post_init(void)
     }
 }
 
+void cpu_clean_all_dirty(void)
+{
+    CPUState *cpu;
+
+    CPU_FOREACH(cpu) {
+        cpu_clean_state(cpu);
+    }
+}
+
 static int do_vm_stop(RunState state)
 {
     int ret = 0;
diff --git a/hw/char/serial.c b/hw/char/serial.c
index a668249049..ebcacdc872 100644
--- a/hw/char/serial.c
+++ b/hw/char/serial.c
@@ -815,6 +815,9 @@ static void serial_reset(void *opaque)
     s->thr_ipending = 0;
     s->last_break_enable = 0;
     qemu_irq_lower(s->irq);
+
+    serial_update_msl(s);
+    s->msr &= ~UART_MSR_ANY_DELTA;
 }
 
 void serial_realize_core(SerialState *s, Error **errp)
@@ -833,6 +836,7 @@ void serial_realize_core(SerialState *s, Error **errp)
                           serial_event, s);
     fifo8_create(&s->recv_fifo, UART_FIFO_LENGTH);
     fifo8_create(&s->xmit_fifo, UART_FIFO_LENGTH);
+    serial_reset(s);
 }
 
 void serial_exit_core(SerialState *s)
@@ -944,7 +948,5 @@ SerialState *serial_mm_init(MemoryRegion *address_space,
     memory_region_init_io(&s->io, NULL, &serial_mm_ops[end], s,
                           "serial", 8 << it_shift);
     memory_region_add_subregion(address_space, base, &s->io);
-
-    serial_update_msl(s);
     return s;
 }
diff --git a/hw/dma/i8257.c b/hw/dma/i8257.c
index dd370ed7e5..a414029bea 100644
--- a/hw/dma/i8257.c
+++ b/hw/dma/i8257.c
@@ -24,6 +24,7 @@
 #include "hw/hw.h"
 #include "hw/isa/isa.h"
 #include "qemu/main-loop.h"
+#include "trace.h"
 
 /* #define DEBUG_DMA */
 
@@ -473,8 +474,7 @@ static void dma_reset(void *opaque)
 
 static int dma_phony_handler (void *opaque, int nchan, int dma_pos, int dma_len)
 {
-    dolog ("unregistered DMA channel used nchan=%d dma_pos=%d dma_len=%d\n",
-           nchan, dma_pos, dma_len);
+    trace_i8257_unregistered_dma(nchan, dma_pos, dma_len);
     return dma_pos;
 }
 
diff --git a/hw/i386/kvm/clock.c b/hw/i386/kvm/clock.c
index 07b9c0e581..1ac60d6cdd 100644
--- a/hw/i386/kvm/clock.c
+++ b/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 +125,9 @@ static void kvmclock_vm_state_change(void *opaque, int running,
         if (s->clock_valid) {
             return;
         }
+
+        cpu_synchronize_all_states();
+        cpu_clean_all_dirty();
         ret = kvm_vm_ioctl(kvm_state, KVM_GET_CLOCK, &data);
         if (ret < 0) {
             fprintf(stderr, "KVM_GET_CLOCK failed: %s\n", strerror(ret));
diff --git a/hw/i386/kvm/i8254.c b/hw/i386/kvm/i8254.c
index 59373aaade..472af811cd 100644
--- a/hw/i386/kvm/i8254.c
+++ b/hw/i386/kvm/i8254.c
@@ -239,6 +239,7 @@ static void kvm_pit_vm_state_change(void *opaque, int running,
 
     if (running) {
         kvm_pit_update_clock_offset(s);
+        kvm_pit_put(PIT_COMMON(s));
         s->vm_stopped = false;
     } else {
         kvm_pit_update_clock_offset(s);
@@ -314,8 +315,6 @@ static void kvm_pit_class_init(ObjectClass *klass, void *data)
     dc->realize = kvm_pit_realizefn;
     k->set_channel_gate = kvm_pit_set_gate;
     k->get_channel_info = kvm_pit_get_channel_info;
-    k->pre_save = kvm_pit_get;
-    k->post_load = kvm_pit_put;
     dc->reset = kvm_pit_reset;
     dc->props = kvm_pit_properties;
 }
diff --git a/hw/i386/kvmvapic.c b/hw/i386/kvmvapic.c
index 2cca7a44f4..2dc362b88f 100644
--- a/hw/i386/kvmvapic.c
+++ b/hw/i386/kvmvapic.c
@@ -732,7 +732,11 @@ static void do_vapic_enable(void *data)
     VAPICROMState *s = data;
     X86CPU *cpu = X86_CPU(first_cpu);
 
-    vapic_enable(s, cpu);
+    static const uint8_t enabled = 1;
+    cpu_physical_memory_write(s->vapic_paddr + offsetof(VAPICState, enabled),
+                              &enabled, sizeof(enabled));
+    apic_enable_vapic(cpu->apic_state, s->vapic_paddr);
+    s->state = VAPIC_ACTIVE;
 }
 
 static void kvmvapic_vm_state_change(void *opaque, int running,
@@ -777,7 +781,10 @@ static int vapic_post_load(void *opaque, int version_id)
         }
     }
 
-    s->vmsentry = qemu_add_vm_change_state_handler(kvmvapic_vm_state_change, s);
+    if (!s->vmsentry) {
+        s->vmsentry =
+            qemu_add_vm_change_state_handler(kvmvapic_vm_state_change, s);
+    }
     return 0;
 }
 
diff --git a/include/sysemu/cpus.h b/include/sysemu/cpus.h
index 4f790810bf..3f162a9e08 100644
--- a/include/sysemu/cpus.h
+++ b/include/sysemu/cpus.h
@@ -10,6 +10,7 @@ void cpu_stop_current(void);
 void cpu_synchronize_all_states(void);
 void cpu_synchronize_all_post_reset(void);
 void cpu_synchronize_all_post_init(void);
+void cpu_clean_all_dirty(void);
 
 void qtest_clock_warp(int64_t dest);
 
diff --git a/include/sysemu/kvm.h b/include/sysemu/kvm.h
index d2000af9c3..77ee240875 100644
--- a/include/sysemu/kvm.h
+++ b/include/sysemu/kvm.h
@@ -350,6 +350,7 @@ int kvm_physical_memory_addr_from_host(KVMState *s, void *ram_addr,
 void kvm_cpu_synchronize_state(CPUState *cpu);
 void kvm_cpu_synchronize_post_reset(CPUState *cpu);
 void kvm_cpu_synchronize_post_init(CPUState *cpu);
+void kvm_cpu_clean_state(CPUState *cpu);
 
 /* generic hooks - to be moved/refactored once there are more users */
 
@@ -374,6 +375,13 @@ static inline void cpu_synchronize_post_init(CPUState *cpu)
     }
 }
 
+static inline void cpu_clean_state(CPUState *cpu)
+{
+    if (kvm_enabled()) {
+        kvm_cpu_clean_state(cpu);
+    }
+}
+
 int kvm_irqchip_add_msi_route(KVMState *s, MSIMessage msg);
 int kvm_irqchip_update_msi_route(KVMState *s, int virq, MSIMessage msg);
 void kvm_irqchip_release_virq(KVMState *s, int virq);
diff --git a/kvm-all.c b/kvm-all.c
index 8b9e66d42d..4afcd0551b 100644
--- a/kvm-all.c
+++ b/kvm-all.c
@@ -44,10 +44,6 @@
 #include <sys/eventfd.h>
 #endif
 
-#ifdef CONFIG_VALGRIND_H
-#include <valgrind/memcheck.h>
-#endif
-
 /* KVM uses PAGE_SIZE in its definition of COALESCED_MMIO_MAX */
 #define PAGE_SIZE TARGET_PAGE_SIZE
 
@@ -1708,6 +1704,11 @@ void kvm_cpu_synchronize_post_init(CPUState *cpu)
     run_on_cpu(cpu, do_kvm_cpu_synchronize_post_init, cpu);
 }
 
+void kvm_cpu_clean_state(CPUState *cpu)
+{
+    cpu->kvm_vcpu_dirty = false;
+}
+
 int kvm_cpu_exec(CPUState *cpu)
 {
     struct kvm_run *run = cpu->kvm_run;
@@ -1954,9 +1955,6 @@ int kvm_has_intx_set_mask(void)
 
 void kvm_setup_guest_memory(void *start, size_t size)
 {
-#ifdef CONFIG_VALGRIND_H
-    VALGRIND_MAKE_MEM_DEFINED(start, size);
-#endif
     if (!kvm_has_sync_mmu()) {
         int ret = qemu_madvise(start, size, QEMU_MADV_DONTFORK);
 
diff --git a/po/Makefile b/po/Makefile
index 1ab241a5b7..b271f79ba2 100644
--- a/po/Makefile
+++ b/po/Makefile
@@ -9,6 +9,9 @@ all:
 
 .PHONY:	all build clean install update
 
+%.mo: %.po
+	$(call quiet-command, msgfmt -o $@ $<, "  GEN   $@")
+
 -include ../config-host.mak
 include $(SRC_PATH)/rules.mak
 
@@ -38,9 +41,6 @@ install: $(OBJS)
 	    $(INSTALL) -m644 $$obj $(DESTDIR)$(prefix)/share/locale/$$base/LC_MESSAGES/qemu.mo; \
 	done
 
-%.mo: %.po
-	$(call quiet-command, msgfmt -o $@ $<, "  GEN   $@")
-
 $(PO_PATH)/messages.po: $(SRC_PATH)/ui/gtk.c
 	$(call quiet-command, ( cd $(SRC_PATH) && \
           xgettext -o - --from-code=UTF-8 --foreign-user \
diff --git a/target-i386/cpu.c b/target-i386/cpu.c
index 2406c727a5..e7bf9de80f 100644
--- a/target-i386/cpu.c
+++ b/target-i386/cpu.c
@@ -2580,7 +2580,7 @@ static void x86_cpu_reset(CPUState *s)
     for (i = 0; i < 8; i++) {
         env->fptags[i] = 1;
     }
-    env->fpuc = 0x37f;
+    cpu_set_fpuc(env, 0x37f);
 
     env->mxcsr = 0x1f80;
     env->xstate_bv = XSTATE_FP | XSTATE_SSE;
diff --git a/target-i386/cpu.h b/target-i386/cpu.h
index 71b505f56c..2968749578 100644
--- a/target-i386/cpu.h
+++ b/target-i386/cpu.h
@@ -1251,6 +1251,7 @@ void QEMU_NORETURN raise_interrupt(CPUX86State *nenv, int intno, int is_int,
 /* cc_helper.c */
 extern const uint8_t parity_table[256];
 uint32_t cpu_cc_compute_all(CPUX86State *env1, int op);
+void update_fp_status(CPUX86State *env);
 
 static inline uint32_t cpu_compute_eflags(CPUX86State *env)
 {
@@ -1286,6 +1287,7 @@ static inline void cpu_load_efer(CPUX86State *env, uint64_t val)
 
 /* fpu_helper.c */
 void cpu_set_mxcsr(CPUX86State *env, uint32_t val);
+void cpu_set_fpuc(CPUX86State *env, uint16_t val);
 
 /* svm_helper.c */
 void cpu_svm_check_intercept_param(CPUX86State *env1, uint32_t type,
diff --git a/target-i386/fpu_helper.c b/target-i386/fpu_helper.c
index 1b2900d5d2..1d4eee3974 100644
--- a/target-i386/fpu_helper.c
+++ b/target-i386/fpu_helper.c
@@ -537,7 +537,7 @@ uint32_t helper_fnstcw(CPUX86State *env)
     return env->fpuc;
 }
 
-static void update_fp_status(CPUX86State *env)
+void update_fp_status(CPUX86State *env)
 {
     int rnd_type;
 
@@ -575,8 +575,7 @@ static void update_fp_status(CPUX86State *env)
 
 void helper_fldcw(CPUX86State *env, uint32_t val)
 {
-    env->fpuc = val;
-    update_fp_status(env);
+    cpu_set_fpuc(env, val);
 }
 
 void helper_fclex(CPUX86State *env)
@@ -595,7 +594,7 @@ void helper_fninit(CPUX86State *env)
 {
     env->fpus = 0;
     env->fpstt = 0;
-    env->fpuc = 0x37f;
+    cpu_set_fpuc(env, 0x37f);
     env->fptags[0] = 1;
     env->fptags[1] = 1;
     env->fptags[2] = 1;
@@ -1013,11 +1012,11 @@ void helper_fldenv(CPUX86State *env, target_ulong ptr, int data32)
     int i, fpus, fptag;
 
     if (data32) {
-        env->fpuc = cpu_lduw_data(env, ptr);
+        cpu_set_fpuc(env, cpu_lduw_data(env, ptr));
         fpus = cpu_lduw_data(env, ptr + 4);
         fptag = cpu_lduw_data(env, ptr + 8);
     } else {
-        env->fpuc = cpu_lduw_data(env, ptr);
+        cpu_set_fpuc(env, cpu_lduw_data(env, ptr));
         fpus = cpu_lduw_data(env, ptr + 2);
         fptag = cpu_lduw_data(env, ptr + 4);
     }
@@ -1046,7 +1045,7 @@ void helper_fsave(CPUX86State *env, target_ulong ptr, int data32)
     /* fninit */
     env->fpus = 0;
     env->fpstt = 0;
-    env->fpuc = 0x37f;
+    cpu_set_fpuc(env, 0x37f);
     env->fptags[0] = 1;
     env->fptags[1] = 1;
     env->fptags[2] = 1;
@@ -1157,7 +1156,7 @@ void helper_fxrstor(CPUX86State *env, target_ulong ptr, int data64)
         raise_exception(env, EXCP0D_GPF);
     }
 
-    env->fpuc = cpu_lduw_data(env, ptr);
+    cpu_set_fpuc(env, cpu_lduw_data(env, ptr));
     fpus = cpu_lduw_data(env, ptr + 2);
     fptag = cpu_lduw_data(env, ptr + 4);
     env->fpstt = (fpus >> 11) & 7;
@@ -1257,6 +1256,12 @@ void cpu_set_mxcsr(CPUX86State *env, uint32_t mxcsr)
     set_flush_to_zero((mxcsr & SSE_FZ) ? 1 : 0, &env->fp_status);
 }
 
+void cpu_set_fpuc(CPUX86State *env, uint16_t val)
+{
+    env->fpuc = val;
+    update_fp_status(env);
+}
+
 void helper_ldmxcsr(CPUX86State *env, uint32_t val)
 {
     cpu_set_mxcsr(env, val);
diff --git a/target-i386/gdbstub.c b/target-i386/gdbstub.c
index 19fe9adc3f..ff99cfb007 100644
--- a/target-i386/gdbstub.c
+++ b/target-i386/gdbstub.c
@@ -203,7 +203,7 @@ int x86_cpu_gdb_write_register(CPUState *cs, uint8_t *mem_buf, int n)
             return x86_cpu_gdb_load_seg(cpu, R_GS, mem_buf);
 
         case IDX_FP_REGS + 8:
-            env->fpuc = ldl_p(mem_buf);
+            cpu_set_fpuc(env, ldl_p(mem_buf));
             return 4;
         case IDX_FP_REGS + 9:
             tmp = ldl_p(mem_buf);
diff --git a/target-i386/machine.c b/target-i386/machine.c
index fb890654b1..0dd49f0005 100644
--- a/target-i386/machine.c
+++ b/target-i386/machine.c
@@ -315,13 +315,13 @@ static int cpu_post_load(void *opaque, int version_id)
     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;
     env->fptag_vmstate ^= 0xff;
     for(i = 0; i < 8; i++) {
         env->fptags[i] = (env->fptag_vmstate >> i) & 1;
     }
+    update_fp_status(env);
 
     cpu_breakpoint_remove_all(cs, BP_CPU);
     cpu_watchpoint_remove_all(cs, BP_CPU);
diff --git a/trace-events b/trace-events
index 9153f983f4..011d1059f8 100644
--- a/trace-events
+++ b/trace-events
@@ -1369,3 +1369,6 @@ mhp_pc_dimm_assigned_address(uint64_t addr) "0x%"PRIx64
 # target-s390x/kvm.c
 kvm_enable_cmma(int rc) "CMMA: enabling with result code %d"
 kvm_clear_cmma(int rc) "CMMA: clearing with result code %d"
+
+# hw/dma/i8257.c
+i8257_unregistered_dma(int nchan, int dma_pos, int dma_len) "unregistered DMA channel used nchan=%d dma_pos=%d dma_len=%d"