35 files changed, 274 insertions, 65 deletions

diff --git a/backends/hostmem.c b/backends/hostmem.c
index 7f5de70609..162c2187d8 100644
--- a/backends/hostmem.c
+++ b/backends/hostmem.c
@@ -224,7 +224,7 @@ static void host_memory_backend_set_prealloc(Object *obj, bool value,
         void *ptr = memory_region_get_ram_ptr(&backend->mr);
         uint64_t sz = memory_region_size(&backend->mr);
 
-        os_mem_prealloc(fd, ptr, sz, &local_err);
+        os_mem_prealloc(fd, ptr, sz, smp_cpus, &local_err);
         if (local_err) {
             error_propagate(errp, local_err);
             return;
@@ -328,7 +328,7 @@ host_memory_backend_memory_complete(UserCreatable *uc, Error **errp)
          */
         if (backend->prealloc) {
             os_mem_prealloc(memory_region_get_fd(&backend->mr), ptr, sz,
-                            &local_err);
+                            smp_cpus, &local_err);
             if (local_err) {
                 goto out;
             }
diff --git a/configure b/configure
index 75c7c3526c..99d8bece70 100755
--- a/configure
+++ b/configure
@@ -1330,6 +1330,12 @@ Advanced options (experts only):
   --with-vss-sdk=SDK-path  enable Windows VSS support in QEMU Guest Agent
   --with-win-sdk=SDK-path  path to Windows Platform SDK (to build VSS .tlb)
   --tls-priority           default TLS protocol/cipher priority string
+  --enable-gprof           QEMU profiling with gprof
+  --enable-profiler        profiler support
+  --enable-xen-pv-domain-build
+                           xen pv domain builder
+  --enable-debug-stack-usage
+                           track the maximum stack usage of stacks created by qemu_alloc_stack
 
 Optional features, enabled with --enable-FEATURE and
 disabled with --disable-FEATURE, default is enabled if available:
@@ -1397,6 +1403,12 @@ disabled with --disable-FEATURE, default is enabled if available:
   tcmalloc        tcmalloc support
   jemalloc        jemalloc support
   replication     replication support
+  vhost-vsock     virtio sockets device support
+  opengl          opengl support
+  virglrenderer   virgl rendering support
+  xfsctl          xfsctl support
+  qom-cast-debug  cast debugging support
+  tools           build qemu-io, qemu-nbd and qemu-image tools
 
 NOTE: The object files are built at the place where configure is launched
 EOF
diff --git a/cpu-exec.c b/cpu-exec.c
index d04dd91ebd..748cb66bca 100644
--- a/cpu-exec.c
+++ b/cpu-exec.c
@@ -33,6 +33,7 @@
 #if defined(TARGET_I386) && !defined(CONFIG_USER_ONLY)
 #include "hw/i386/apic.h"
 #endif
+#include "sysemu/cpus.h"
 #include "sysemu/replay.h"
 
 /* -icount align implementation. */
diff --git a/cpus.c b/cpus.c
index 69e21858b8..b84a392dda 100644
--- a/cpus.c
+++ b/cpus.c
@@ -800,6 +800,27 @@ static void qemu_cpu_kick_rr_cpu(void)
     } while (cpu != atomic_mb_read(&tcg_current_rr_cpu));
 }
 
+static void do_nothing(CPUState *cpu, run_on_cpu_data unused)
+{
+}
+
+void qemu_timer_notify_cb(void *opaque, QEMUClockType type)
+{
+    if (!use_icount || type != QEMU_CLOCK_VIRTUAL) {
+        qemu_notify_event();
+        return;
+    }
+
+    if (!qemu_in_vcpu_thread() && first_cpu) {
+        /* qemu_cpu_kick is not enough to kick a halted CPU out of
+         * qemu_tcg_wait_io_event.  async_run_on_cpu, instead,
+         * causes cpu_thread_is_idle to return false.  This way,
+         * handle_icount_deadline can run.
+         */
+        async_run_on_cpu(first_cpu, do_nothing, RUN_ON_CPU_NULL);
+    }
+}
+
 static void kick_tcg_thread(void *opaque)
 {
     timer_mod(tcg_kick_vcpu_timer, qemu_tcg_next_kick());
@@ -1145,12 +1166,15 @@ static int64_t tcg_get_icount_limit(void)
 
 static void handle_icount_deadline(void)
 {
+    assert(qemu_in_vcpu_thread());
     if (use_icount) {
         int64_t deadline =
             qemu_clock_deadline_ns_all(QEMU_CLOCK_VIRTUAL);
 
         if (deadline == 0) {
+            /* Wake up other AioContexts.  */
             qemu_clock_notify(QEMU_CLOCK_VIRTUAL);
+            qemu_clock_run_timers(QEMU_CLOCK_VIRTUAL);
         }
     }
 }
@@ -1263,6 +1287,11 @@ static void *qemu_tcg_rr_cpu_thread_fn(void *arg)
         /* Account partial waits to QEMU_CLOCK_VIRTUAL.  */
         qemu_account_warp_timer();
 
+        /* Run the timers here.  This is much more efficient than
+         * waking up the I/O thread and waiting for completion.
+         */
+        handle_icount_deadline();
+
         if (!cpu) {
             cpu = first_cpu;
         }
@@ -1304,8 +1333,6 @@ static void *qemu_tcg_rr_cpu_thread_fn(void *arg)
             atomic_mb_set(&cpu->exit_request, 0);
         }
 
-        handle_icount_deadline();
-
         qemu_tcg_wait_io_event(cpu ? cpu : QTAILQ_FIRST(&cpus));
         deal_with_unplugged_cpus();
     }
diff --git a/docs/bootindex.txt b/docs/bootindex.txt
index f84fac7200..b9a8ba122f 100644
--- a/docs/bootindex.txt
+++ b/docs/bootindex.txt
@@ -41,3 +41,12 @@ has three bootable devices target1, target3, target5 connected to it,
 the option ROM will have a boot method for each of them, but it is not
 possible to map from boot method back to a specific target.  This is a
 shortcoming of the PC BIOS boot specification.
+
+== Mixing bootindex and boot order parameters ==
+
+Note that it does not make sense to use the bootindex property together
+with the "-boot order=..." (or "-boot once=...") parameter. The guest
+firmware implementations normally either support the one or the other,
+but not both parameters at the same time. Mixing them will result in
+undefined behavior, and thus the guest firmware will likely not boot
+from the expected devices.
diff --git a/exec.c b/exec.c
index aabb035e92..a22f5a0385 100644
--- a/exec.c
+++ b/exec.c
@@ -43,6 +43,7 @@
 #include "exec/ioport.h"
 #include "sysemu/dma.h"
 #include "sysemu/numa.h"
+#include "sysemu/hw_accel.h"
 #include "exec/address-spaces.h"
 #include "sysemu/xen-mapcache.h"
 #include "trace-root.h"
@@ -1467,7 +1468,7 @@ static void *file_ram_alloc(RAMBlock *block,
     }
 
     if (mem_prealloc) {
-        os_mem_prealloc(fd, area, memory, errp);
+        os_mem_prealloc(fd, area, memory, smp_cpus, errp);
         if (errp && *errp) {
             goto error;
         }
@@ -3309,6 +3310,7 @@ int cpu_memory_rw_debug(CPUState *cpu, target_ulong addr,
     hwaddr phys_addr;
     target_ulong page;
 
+    cpu_synchronize_state(cpu);
     while (len > 0) {
         int asidx;
         MemTxAttrs attrs;
diff --git a/hw/core/ptimer.c b/hw/core/ptimer.c
index 59ccb00550..7221c68a98 100644
--- a/hw/core/ptimer.c
+++ b/hw/core/ptimer.c
@@ -13,6 +13,7 @@
 #include "sysemu/replay.h"
 #include "sysemu/qtest.h"
 #include "block/aio.h"
+#include "sysemu/cpus.h"
 
 #define DELTA_ADJUST     1
 #define DELTA_NO_ADJUST -1
diff --git a/hw/i386/kvm/clock.c b/hw/i386/kvm/clock.c
index ef9d560f9c..13eca374cd 100644
--- a/hw/i386/kvm/clock.c
+++ b/hw/i386/kvm/clock.c
@@ -22,6 +22,7 @@
 #include "kvm_i386.h"
 #include "hw/sysbus.h"
 #include "hw/kvm/clock.h"
+#include "qapi/error.h"
 
 #include <linux/kvm.h>
 #include <linux/kvm_para.h>
@@ -208,6 +209,11 @@ static void kvmclock_realize(DeviceState *dev, Error **errp)
 {
     KVMClockState *s = KVM_CLOCK(dev);
 
+    if (!kvm_enabled()) {
+        error_setg(errp, "kvmclock device requires KVM");
+        return;
+    }
+
     kvm_update_clock(s);
 
     qemu_add_vm_change_state_handler(kvmclock_vm_state_change, s);
diff --git a/hw/ppc/pnv.c b/hw/ppc/pnv.c
index 09f0d22def..3fa722af82 100644
--- a/hw/ppc/pnv.c
+++ b/hw/ppc/pnv.c
@@ -21,6 +21,7 @@
 #include "qapi/error.h"
 #include "sysemu/sysemu.h"
 #include "sysemu/numa.h"
+#include "sysemu/cpus.h"
 #include "hw/hw.h"
 #include "target/ppc/cpu.h"
 #include "qemu/log.h"
diff --git a/hw/scsi/mptsas.c b/hw/scsi/mptsas.c
index 2e091c0156..765ab53c34 100644
--- a/hw/scsi/mptsas.c
+++ b/hw/scsi/mptsas.c
@@ -756,7 +756,7 @@ static void mptsas_fetch_request(MPTSASState *s)
 
     /* Read the message header from the guest first. */
     addr = s->host_mfa_high_addr | MPTSAS_FIFO_GET(s, request_post);
-    pci_dma_read(pci, addr, req, sizeof(hdr));
+    pci_dma_read(pci, addr, req, sizeof(*hdr));
 
     if (hdr->Function < ARRAY_SIZE(mpi_request_sizes) &&
         mpi_request_sizes[hdr->Function]) {
@@ -766,8 +766,8 @@ static void mptsas_fetch_request(MPTSASState *s)
          */
         size = mpi_request_sizes[hdr->Function];
         assert(size <= MPTSAS_MAX_REQUEST_SIZE);
-        pci_dma_read(pci, addr + sizeof(hdr), &req[sizeof(hdr)],
-                     size - sizeof(hdr));
+        pci_dma_read(pci, addr + sizeof(*hdr), &req[sizeof(*hdr)],
+                     size - sizeof(*hdr));
     }
 
     if (hdr->Function == MPI_FUNCTION_SCSI_IO_REQUEST) {
diff --git a/include/exec/memory.h b/include/exec/memory.h
index 691102317c..e39256ad03 100644
--- a/include/exec/memory.h
+++ b/include/exec/memory.h
@@ -371,7 +371,8 @@ void memory_region_init_io(MemoryRegion *mr,
  *
  * @mr: the #MemoryRegion to be initialized.
  * @owner: the object that tracks the region's reference count
- * @name: the name of the region.
+ * @name: Region name, becomes part of RAMBlock name used in migration stream
+ *        must be unique within any device
  * @size: size of the region.
  * @errp: pointer to Error*, to store an error if it happens.
  */
@@ -390,7 +391,8 @@ void memory_region_init_ram(MemoryRegion *mr,
  *
  * @mr: the #MemoryRegion to be initialized.
  * @owner: the object that tracks the region's reference count
- * @name: the name of the region.
+ * @name: Region name, becomes part of RAMBlock name used in migration stream
+ *        must be unique within any device
  * @size: used size of the region.
  * @max_size: max size of the region.
  * @resized: callback to notify owner about used size change.
@@ -412,7 +414,8 @@ void memory_region_init_resizeable_ram(MemoryRegion *mr,
  *
  * @mr: the #MemoryRegion to be initialized.
  * @owner: the object that tracks the region's reference count
- * @name: the name of the region.
+ * @name: Region name, becomes part of RAMBlock name used in migration stream
+ *        must be unique within any device
  * @size: size of the region.
  * @share: %true if memory must be mmaped with the MAP_SHARED flag
  * @path: the path in which to allocate the RAM.
@@ -434,7 +437,8 @@ void memory_region_init_ram_from_file(MemoryRegion *mr,
  *
  * @mr: the #MemoryRegion to be initialized.
  * @owner: the object that tracks the region's reference count
- * @name: the name of the region.
+ * @name: Region name, becomes part of RAMBlock name used in migration stream
+ *        must be unique within any device
  * @size: size of the region.
  * @ptr: memory to be mapped; must contain at least @size bytes.
  */
@@ -496,7 +500,8 @@ void memory_region_init_alias(MemoryRegion *mr,
  *
  * @mr: the #MemoryRegion to be initialized.
  * @owner: the object that tracks the region's reference count
- * @name: the name of the region.
+ * @name: Region name, becomes part of RAMBlock name used in migration stream
+ *        must be unique within any device
  * @size: size of the region.
  * @errp: pointer to Error*, to store an error if it happens.
  */
@@ -513,7 +518,8 @@ void memory_region_init_rom(MemoryRegion *mr,
  * @mr: the #MemoryRegion to be initialized.
  * @owner: the object that tracks the region's reference count
  * @ops: callbacks for write access handling (must not be NULL).
- * @name: the name of the region.
+ * @name: Region name, becomes part of RAMBlock name used in migration stream
+ *        must be unique within any device
  * @size: size of the region.
  * @errp: pointer to Error*, to store an error if it happens.
  */
diff --git a/include/qemu/osdep.h b/include/qemu/osdep.h
index af37195fef..122ff06ff6 100644
--- a/include/qemu/osdep.h
+++ b/include/qemu/osdep.h
@@ -438,7 +438,8 @@ unsigned long qemu_getauxval(unsigned long type);
 
 void qemu_set_tty_echo(int fd, bool echo);
 
-void os_mem_prealloc(int fd, char *area, size_t sz, Error **errp);
+void os_mem_prealloc(int fd, char *area, size_t sz, int smp_cpus,
+                     Error **errp);
 
 int qemu_read_password(char *buf, int buf_size);
 
diff --git a/include/qemu/timer.h b/include/qemu/timer.h
index 26e628584c..e1742f2f3d 100644
--- a/include/qemu/timer.h
+++ b/include/qemu/timer.h
@@ -4,7 +4,6 @@
 #include "qemu-common.h"
 #include "qemu/notify.h"
 #include "qemu/host-utils.h"
-#include "sysemu/cpus.h"
 
 #define NANOSECONDS_PER_SECOND 1000000000LL
 
@@ -60,7 +59,7 @@ struct QEMUTimerListGroup {
 };
 
 typedef void QEMUTimerCB(void *opaque);
-typedef void QEMUTimerListNotifyCB(void *opaque);
+typedef void QEMUTimerListNotifyCB(void *opaque, QEMUClockType type);
 
 struct QEMUTimer {
     int64_t expire_time;        /* in nanoseconds */
@@ -534,6 +533,12 @@ static inline QEMUTimer *timer_new_tl(QEMUTimerList *timer_list,
  * Create a new timer and associate it with the default
  * timer list for the clock type @type.
  *
+ * The default timer list has one special feature: in icount mode,
+ * %QEMU_CLOCK_VIRTUAL timers are run in the vCPU thread.  This is
+ * not true of other timer lists, which are typically associated
+ * with an AioContext---each of them runs its timer callbacks in its own
+ * AioContext thread.
+ *
  * Returns: a pointer to the timer
  */
 static inline QEMUTimer *timer_new(QEMUClockType type, int scale,
@@ -551,6 +556,12 @@ static inline QEMUTimer *timer_new(QEMUClockType type, int scale,
  * Create a new timer with nanosecond scale on the default timer list
  * associated with the clock.
  *
+ * The default timer list has one special feature: in icount mode,
+ * %QEMU_CLOCK_VIRTUAL timers are run in the vCPU thread.  This is
+ * not true of other timer lists, which are typically associated
+ * with an AioContext---each of them runs its timer callbacks in its own
+ * AioContext thread.
+ *
  * Returns: a pointer to the newly created timer
  */
 static inline QEMUTimer *timer_new_ns(QEMUClockType type, QEMUTimerCB *cb,
@@ -565,6 +576,12 @@ static inline QEMUTimer *timer_new_ns(QEMUClockType type, QEMUTimerCB *cb,
  * @cb: the callback to call when the timer expires
  * @opaque: the opaque pointer to pass to the callback
  *
+ * The default timer list has one special feature: in icount mode,
+ * %QEMU_CLOCK_VIRTUAL timers are run in the vCPU thread.  This is
+ * not true of other timer lists, which are typically associated
+ * with an AioContext---each of them runs its timer callbacks in its own
+ * AioContext thread.
+ *
  * Create a new timer with microsecond scale on the default timer list
  * associated with the clock.
  *
@@ -582,6 +599,12 @@ static inline QEMUTimer *timer_new_us(QEMUClockType type, QEMUTimerCB *cb,
  * @cb: the callback to call when the timer expires
  * @opaque: the opaque pointer to pass to the callback
  *
+ * The default timer list has one special feature: in icount mode,
+ * %QEMU_CLOCK_VIRTUAL timers are run in the vCPU thread.  This is
+ * not true of other timer lists, which are typically associated
+ * with an AioContext---each of them runs its timer callbacks in its own
+ * AioContext thread.
+ *
  * Create a new timer with millisecond scale on the default timer list
  * associated with the clock.
  *
@@ -777,7 +800,7 @@ static inline int64_t qemu_soonest_timeout(int64_t timeout1, int64_t timeout2)
  *
  * Initialise the clock & timer infrastructure
  */
-void init_clocks(void);
+void init_clocks(QEMUTimerListNotifyCB *notify_cb);
 
 int64_t cpu_get_ticks(void);
 /* Caller must hold BQL */
diff --git a/include/sysemu/cpus.h b/include/sysemu/cpus.h
index a73b5d4bce..a8053f1715 100644
--- a/include/sysemu/cpus.h
+++ b/include/sysemu/cpus.h
@@ -1,6 +1,8 @@
 #ifndef QEMU_CPUS_H
 #define QEMU_CPUS_H
 
+#include "qemu/timer.h"
+
 /* cpus.c */
 bool qemu_in_vcpu_thread(void);
 void qemu_init_cpu_loop(void);
@@ -20,6 +22,7 @@ void dump_drift_info(FILE *f, fprintf_function cpu_fprintf);
 
 /* Unblock cpu */
 void qemu_cpu_kick_self(void);
+void qemu_timer_notify_cb(void *opaque, QEMUClockType type);
 
 void cpu_synchronize_all_states(void);
 void cpu_synchronize_all_post_reset(void);
diff --git a/kvm-all.c b/kvm-all.c
index 9040bd50a4..90b8573656 100644
--- a/kvm-all.c
+++ b/kvm-all.c
@@ -29,6 +29,7 @@
 #include "hw/s390x/adapter.h"
 #include "exec/gdbstub.h"
 #include "sysemu/kvm_int.h"
+#include "sysemu/cpus.h"
 #include "qemu/bswap.h"
 #include "exec/memory.h"
 #include "exec/ram_addr.h"
diff --git a/memory.c b/memory.c
index 284894b135..64b0a605ef 100644
--- a/memory.c
+++ b/memory.c
@@ -2494,6 +2494,7 @@ static void mtree_print_mr(fprintf_function mon_printf, void *f,
     MemoryRegionListHead submr_print_queue;
     const MemoryRegion *submr;
     unsigned int i;
+    hwaddr cur_start, cur_end;
 
     if (!mr) {
         return;
@@ -2503,6 +2504,18 @@ static void mtree_print_mr(fprintf_function mon_printf, void *f,
         mon_printf(f, MTREE_INDENT);
     }
 
+    cur_start = base + mr->addr;
+    cur_end = cur_start + MR_SIZE(mr->size);
+
+    /*
+     * Try to detect overflow of memory region. This should never
+     * happen normally. When it happens, we dump something to warn the
+     * user who is observing this.
+     */
+    if (cur_start < base || cur_end < cur_start) {
+        mon_printf(f, "[DETECTED OVERFLOW!] ");
+    }
+
     if (mr->alias) {
         MemoryRegionList *ml;
         bool found = false;
@@ -2522,8 +2535,7 @@ static void mtree_print_mr(fprintf_function mon_printf, void *f,
         mon_printf(f, TARGET_FMT_plx "-" TARGET_FMT_plx
                    " (prio %d, %s): alias %s @%s " TARGET_FMT_plx
                    "-" TARGET_FMT_plx "%s\n",
-                   base + mr->addr,
-                   base + mr->addr + MR_SIZE(mr->size),
+                   cur_start, cur_end,
                    mr->priority,
                    memory_region_type((MemoryRegion *)mr),
                    memory_region_name(mr),
@@ -2534,8 +2546,7 @@ static void mtree_print_mr(fprintf_function mon_printf, void *f,
     } else {
         mon_printf(f,
                    TARGET_FMT_plx "-" TARGET_FMT_plx " (prio %d, %s): %s%s\n",
-                   base + mr->addr,
-                   base + mr->addr + MR_SIZE(mr->size),
+                   cur_start, cur_end,
                    mr->priority,
                    memory_region_type((MemoryRegion *)mr),
                    memory_region_name(mr),
@@ -2562,7 +2573,7 @@ static void mtree_print_mr(fprintf_function mon_printf, void *f,
     }
 
     QTAILQ_FOREACH(ml, &submr_print_queue, queue) {
-        mtree_print_mr(mon_printf, f, ml->mr, level + 1, base + mr->addr,
+        mtree_print_mr(mon_printf, f, ml->mr, level + 1, cur_start,
                        alias_print_queue);
     }
 
diff --git a/monitor.c b/monitor.c
index f11893e1c3..be282ecb80 100644
--- a/monitor.c
+++ b/monitor.c
@@ -77,6 +77,7 @@
 #include "qapi-event.h"
 #include "qmp-introspect.h"
 #include "sysemu/qtest.h"
+#include "sysemu/cpus.h"
 #include "qemu/cutils.h"
 #include "qapi/qmp/dispatch.h"
 
diff --git a/nbd/client.c b/nbd/client.c
index 5c9dee37fa..3dc2564cd0 100644
--- a/nbd/client.c
+++ b/nbd/client.c
@@ -94,7 +94,7 @@ static ssize_t drop_sync(QIOChannel *ioc, size_t size)
     char small[1024];
     char *buffer;
 
-    buffer = sizeof(small) < size ? small : g_malloc(MIN(65536, size));
+    buffer = sizeof(small) >= size ? small : g_malloc(MIN(65536, size));
     while (size > 0) {
         ssize_t count = read_sync(ioc, buffer, MIN(65536, size));
 
diff --git a/qemu-options.hx b/qemu-options.hx
index 8dd8ee34a6..99af8edf5f 100644
--- a/qemu-options.hx
+++ b/qemu-options.hx
@@ -252,7 +252,10 @@ drive letters depend on the target architecture. The x86 PC uses: a, b
 (floppy 1 and 2), c (first hard disk), d (first CD-ROM), n-p (Etherboot
 from network adapter 1-4), hard disk boot is the default. To apply a
 particular boot order only on the first startup, specify it via
-@option{once}.
+@option{once}. Note that the @option{order} or @option{once} parameter
+should not be used together with the @option{bootindex} property of
+devices, since the firmware implementations normally do not support both
+at the same time.
 
 Interactive boot menus/prompts can be enabled via @option{menu=on} as far
 as firmware/BIOS supports them. The default is non-interactive boot.
diff --git a/replay/replay.c b/replay/replay.c
index 1835b9902e..78e2a7e570 100644
--- a/replay/replay.c
+++ b/replay/replay.c
@@ -16,6 +16,7 @@
 #include "replay-internal.h"
 #include "qemu/timer.h"
 #include "qemu/main-loop.h"
+#include "sysemu/cpus.h"
 #include "sysemu/sysemu.h"
 #include "qemu/error-report.h"
 
diff --git a/scripts/dump-guest-memory.py b/scripts/dump-guest-memory.py
index 9956fc036c..f7c6635f15 100644
--- a/scripts/dump-guest-memory.py
+++ b/scripts/dump-guest-memory.py
@@ -314,8 +314,18 @@ def get_arch_phdr(endianness, elfclass):
 def int128_get64(val):
     """Returns low 64bit part of Int128 struct."""
 
-    assert val["hi"] == 0
-    return val["lo"]
+    try:
+        assert val["hi"] == 0
+        return val["lo"]
+    except gdb.error:
+        u64t = gdb.lookup_type('uint64_t').array(2)
+        u64 = val.cast(u64t)
+        if sys.byteorder == 'little':
+            assert u64[1] == 0
+            return u64[0]
+        else:
+            assert u64[0] == 0
+            return u64[1]
 
 
 def qlist_foreach(head, field_str):
diff --git a/stubs/cpu-get-icount.c b/stubs/cpu-get-icount.c
index 2e8b63b225..0b7239d721 100644
--- a/stubs/cpu-get-icount.c
+++ b/stubs/cpu-get-icount.c
@@ -2,6 +2,7 @@
 #include "qemu-common.h"
 #include "qemu/timer.h"
 #include "sysemu/cpus.h"
+#include "qemu/main-loop.h"
 
 int use_icount;
 
@@ -9,3 +10,8 @@ int64_t cpu_get_icount(void)
 {
     abort();
 }
+
+void qemu_timer_notify_cb(void *opaque, QEMUClockType type)
+{
+    qemu_notify_event();
+}
diff --git a/target/alpha/translate.c b/target/alpha/translate.c
index 055286a7b8..df5d695344 100644
--- a/target/alpha/translate.c
+++ b/target/alpha/translate.c
@@ -19,6 +19,7 @@
 
 #include "qemu/osdep.h"
 #include "cpu.h"
+#include "sysemu/cpus.h"
 #include "disas/disas.h"
 #include "qemu/host-utils.h"
 #include "exec/exec-all.h"
diff --git a/target/i386/kvm.c b/target/i386/kvm.c
index 472399fb2c..55865dbee0 100644
--- a/target/i386/kvm.c
+++ b/target/i386/kvm.c
@@ -1824,6 +1824,12 @@ static int kvm_put_msrs(X86CPU *cpu, int level)
         return ret;
     }
 
+    if (ret < cpu->kvm_msr_buf->nmsrs) {
+        struct kvm_msr_entry *e = &cpu->kvm_msr_buf->entries[ret];
+        error_report("error: failed to set MSR 0x%" PRIx32 " to 0x%" PRIx64,
+                     (uint32_t)e->index, (uint64_t)e->data);
+    }
+
     assert(ret == cpu->kvm_msr_buf->nmsrs);
     return 0;
 }
@@ -2189,6 +2195,12 @@ static int kvm_get_msrs(X86CPU *cpu)
         return ret;
     }
 
+    if (ret < cpu->kvm_msr_buf->nmsrs) {
+        struct kvm_msr_entry *e = &cpu->kvm_msr_buf->entries[ret];
+        error_report("error: failed to get MSR 0x%" PRIx32,
+                     (uint32_t)e->index);
+    }
+
     assert(ret == cpu->kvm_msr_buf->nmsrs);
     /*
      * MTRR masks: Each mask consists of 5 parts
diff --git a/target/nios2/op_helper.c b/target/nios2/op_helper.c
index 538853cda7..efb1c489c9 100644
--- a/target/nios2/op_helper.c
+++ b/target/nios2/op_helper.c
@@ -21,6 +21,7 @@
 #include "cpu.h"
 #include "exec/helper-proto.h"
 #include "exec/cpu_ldst.h"
+#include "qemu/main-loop.h"
 
 #if !defined(CONFIG_USER_ONLY)
 void helper_mmu_read_debug(CPUNios2State *env, uint32_t rn)
@@ -35,7 +36,9 @@ void helper_mmu_write(CPUNios2State *env, uint32_t rn, uint32_t v)
 
 void helper_check_interrupts(CPUNios2State *env)
 {
+    qemu_mutex_lock_iothread();
     nios2_check_interrupts(env);
+    qemu_mutex_unlock_iothread();
 }
 #endif /* !CONFIG_USER_ONLY */
 
diff --git a/tests/test-aio-multithread.c b/tests/test-aio-multithread.c
index 8b0b40ec78..549d784915 100644
--- a/tests/test-aio-multithread.c
+++ b/tests/test-aio-multithread.c
@@ -438,7 +438,7 @@ static void test_multi_mutex_10(void)
 
 int main(int argc, char **argv)
 {
-    init_clocks();
+    init_clocks(NULL);
 
     g_test_init(&argc, &argv, NULL);
     g_test_add_func("/aio/multi/lifecycle", test_lifecycle);
diff --git a/tests/test-aio.c b/tests/test-aio.c
index 2754f154ce..54e20d6ab1 100644
--- a/tests/test-aio.c
+++ b/tests/test-aio.c
@@ -835,7 +835,7 @@ int main(int argc, char **argv)
     Error *local_error = NULL;
     GSource *src;
 
-    init_clocks();
+    init_clocks(NULL);
 
     ctx = aio_context_new(&local_error);
     if (!ctx) {
diff --git a/translate-all.c b/translate-all.c
index 34480aebba..b3ee876526 100644
--- a/translate-all.c
+++ b/translate-all.c
@@ -57,6 +57,7 @@
 #include "qemu/timer.h"
 #include "qemu/main-loop.h"
 #include "exec/log.h"
+#include "sysemu/cpus.h"
 
 /* #define DEBUG_TB_INVALIDATE */
 /* #define DEBUG_TB_FLUSH */
diff --git a/util/async.c b/util/async.c
index 7d469eb857..663e297e1f 100644
--- a/util/async.c
+++ b/util/async.c
@@ -351,7 +351,7 @@ void aio_notify_accept(AioContext *ctx)
     }
 }
 
-static void aio_timerlist_notify(void *opaque)
+static void aio_timerlist_notify(void *opaque, QEMUClockType type)
 {
     aio_notify(opaque);
 }
diff --git a/util/main-loop.c b/util/main-loop.c
index ca7bb072f9..4534c89308 100644
--- a/util/main-loop.c
+++ b/util/main-loop.c
@@ -28,6 +28,7 @@
 #include "qemu/timer.h"
 #include "qemu/sockets.h"	// struct in_addr needed for libslirp.h
 #include "sysemu/qtest.h"
+#include "sysemu/cpus.h"
 #include "slirp/libslirp.h"
 #include "qemu/main-loop.h"
 #include "block/aio.h"
@@ -143,7 +144,7 @@ int qemu_init_main_loop(Error **errp)
     GSource *src;
     Error *local_error = NULL;
 
-    init_clocks();
+    init_clocks(qemu_timer_notify_cb);
 
     ret = qemu_signal_init();
     if (ret) {
diff --git a/util/oslib-posix.c b/util/oslib-posix.c
index cd686aae3d..956f66ab4a 100644
--- a/util/oslib-posix.c
+++ b/util/oslib-posix.c
@@ -55,6 +55,21 @@
 #include "qemu/error-report.h"
 #endif
 
+#define MAX_MEM_PREALLOC_THREAD_COUNT (MIN(sysconf(_SC_NPROCESSORS_ONLN), 16))
+
+struct MemsetThread {
+    char *addr;
+    uint64_t numpages;
+    uint64_t hpagesize;
+    QemuThread pgthread;
+    sigjmp_buf env;
+};
+typedef struct MemsetThread MemsetThread;
+
+static MemsetThread *memset_thread;
+static int memset_num_threads;
+static bool memset_thread_failed;
+
 int qemu_get_thread_id(void)
 {
 #if defined(__linux__)
@@ -316,18 +331,83 @@ char *qemu_get_exec_dir(void)
     return g_strdup(exec_dir);
 }
 
-static sigjmp_buf sigjump;
-
 static void sigbus_handler(int signal)
 {
-    siglongjmp(sigjump, 1);
+    int i;
+    if (memset_thread) {
+        for (i = 0; i < memset_num_threads; i++) {
+            if (qemu_thread_is_self(&memset_thread[i].pgthread)) {
+                siglongjmp(memset_thread[i].env, 1);
+            }
+        }
+    }
+}
+
+static void *do_touch_pages(void *arg)
+{
+    MemsetThread *memset_args = (MemsetThread *)arg;
+    char *addr = memset_args->addr;
+    uint64_t numpages = memset_args->numpages;
+    uint64_t hpagesize = memset_args->hpagesize;
+    sigset_t set, oldset;
+    int i = 0;
+
+    /* unblock SIGBUS */
+    sigemptyset(&set);
+    sigaddset(&set, SIGBUS);
+    pthread_sigmask(SIG_UNBLOCK, &set, &oldset);
+
+    if (sigsetjmp(memset_args->env, 1)) {
+        memset_thread_failed = true;
+    } else {
+        for (i = 0; i < numpages; i++) {
+            memset(addr, 0, 1);
+            addr += hpagesize;
+        }
+    }
+    pthread_sigmask(SIG_SETMASK, &oldset, NULL);
+    return NULL;
+}
+
+static bool touch_all_pages(char *area, size_t hpagesize, size_t numpages,
+                            int smp_cpus)
+{
+    uint64_t numpages_per_thread, size_per_thread;
+    char *addr = area;
+    int i = 0;
+
+    memset_thread_failed = false;
+    memset_num_threads = MIN(smp_cpus, MAX_MEM_PREALLOC_THREAD_COUNT);
+    memset_thread = g_new0(MemsetThread, memset_num_threads);
+    numpages_per_thread = (numpages / memset_num_threads);
+    size_per_thread = (hpagesize * numpages_per_thread);
+    for (i = 0; i < memset_num_threads; i++) {
+        memset_thread[i].addr = addr;
+        memset_thread[i].numpages = (i == (memset_num_threads - 1)) ?
+                                    numpages : numpages_per_thread;
+        memset_thread[i].hpagesize = hpagesize;
+        qemu_thread_create(&memset_thread[i].pgthread, "touch_pages",
+                           do_touch_pages, &memset_thread[i],
+                           QEMU_THREAD_JOINABLE);
+        addr += size_per_thread;
+        numpages -= numpages_per_thread;
+    }
+    for (i = 0; i < memset_num_threads; i++) {
+        qemu_thread_join(&memset_thread[i].pgthread);
+    }
+    g_free(memset_thread);
+    memset_thread = NULL;
+
+    return memset_thread_failed;
 }
 
-void os_mem_prealloc(int fd, char *area, size_t memory, Error **errp)
+void os_mem_prealloc(int fd, char *area, size_t memory, int smp_cpus,
+                     Error **errp)
 {
     int ret;
     struct sigaction act, oldact;
-    sigset_t set, oldset;
+    size_t hpagesize = qemu_fd_getpagesize(fd);
+    size_t numpages = DIV_ROUND_UP(memory, hpagesize);
 
     memset(&act, 0, sizeof(act));
     act.sa_handler = &sigbus_handler;
@@ -340,23 +420,10 @@ void os_mem_prealloc(int fd, char *area, size_t memory, Error **errp)
         return;
     }
 
-    /* unblock SIGBUS */
-    sigemptyset(&set);
-    sigaddset(&set, SIGBUS);
-    pthread_sigmask(SIG_UNBLOCK, &set, &oldset);
-
-    if (sigsetjmp(sigjump, 1)) {
+    /* touch pages simultaneously */
+    if (touch_all_pages(area, hpagesize, numpages, smp_cpus)) {
         error_setg(errp, "os_mem_prealloc: Insufficient free host memory "
             "pages available to allocate guest RAM\n");
-    } else {
-        int i;
-        size_t hpagesize = qemu_fd_getpagesize(fd);
-        size_t numpages = DIV_ROUND_UP(memory, hpagesize);
-
-        /* MAP_POPULATE silently ignores failures */
-        for (i = 0; i < numpages; i++) {
-            memset(area + (hpagesize * i), 0, 1);
-        }
     }
 
     ret = sigaction(SIGBUS, &oldact, NULL);
@@ -365,7 +432,6 @@ void os_mem_prealloc(int fd, char *area, size_t memory, Error **errp)
         perror("os_mem_prealloc: failed to reinstall signal handler");
         exit(1);
     }
-    pthread_sigmask(SIG_SETMASK, &oldset, NULL);
 }
 
 
diff --git a/util/oslib-win32.c b/util/oslib-win32.c
index 0b1890fd33..80e4668935 100644
--- a/util/oslib-win32.c
+++ b/util/oslib-win32.c
@@ -541,7 +541,8 @@ int getpagesize(void)
     return system_info.dwPageSize;
 }
 
-void os_mem_prealloc(int fd, char *area, size_t memory, Error **errp)
+void os_mem_prealloc(int fd, char *area, size_t memory, int smp_cpus,
+                     Error **errp)
 {
     int i;
     size_t pagesize = getpagesize();
diff --git a/util/path.c b/util/path.c
index 5479f76c6d..7f9fc272fb 100644
--- a/util/path.c
+++ b/util/path.c
@@ -6,7 +6,6 @@
 #include "qemu/osdep.h"
 #include <sys/param.h>
 #include <dirent.h>
-#include "qemu-common.h"
 #include "qemu/cutils.h"
 #include "qemu/path.h"
 
diff --git a/util/qemu-timer.c b/util/qemu-timer.c
index 6cf70b96f6..82d56507a2 100644
--- a/util/qemu-timer.c
+++ b/util/qemu-timer.c
@@ -27,6 +27,7 @@
 #include "qemu/timer.h"
 #include "sysemu/replay.h"
 #include "sysemu/sysemu.h"
+#include "sysemu/cpus.h"
 
 #ifdef CONFIG_POSIX
 #include <pthread.h>
@@ -121,7 +122,7 @@ void timerlist_free(QEMUTimerList *timer_list)
     g_free(timer_list);
 }
 
-static void qemu_clock_init(QEMUClockType type)
+static void qemu_clock_init(QEMUClockType type, QEMUTimerListNotifyCB *notify_cb)
 {
     QEMUClock *clock = qemu_clock_ptr(type);
 
@@ -133,7 +134,7 @@ static void qemu_clock_init(QEMUClockType type)
     clock->last = INT64_MIN;
     QLIST_INIT(&clock->timerlists);
     notifier_list_init(&clock->reset_notifiers);
-    main_loop_tlg.tl[type] = timerlist_new(type, NULL, NULL);
+    main_loop_tlg.tl[type] = timerlist_new(type, notify_cb, NULL);
 }
 
 bool qemu_clock_use_for_deadline(QEMUClockType type)
@@ -199,7 +200,7 @@ bool timerlist_expired(QEMUTimerList *timer_list)
     expire_time = timer_list->active_timers->expire_time;
     qemu_mutex_unlock(&timer_list->active_timers_lock);
 
-    return expire_time < qemu_clock_get_ns(timer_list->clock->type);
+    return expire_time <= qemu_clock_get_ns(timer_list->clock->type);
 }
 
 bool qemu_clock_expired(QEMUClockType type)
@@ -277,7 +278,7 @@ QEMUTimerList *qemu_clock_get_main_loop_timerlist(QEMUClockType type)
 void timerlist_notify(QEMUTimerList *timer_list)
 {
     if (timer_list->notify_cb) {
-        timer_list->notify_cb(timer_list->notify_opaque);
+        timer_list->notify_cb(timer_list->notify_opaque, timer_list->clock->type);
     } else {
         qemu_notify_event();
     }
@@ -634,11 +635,11 @@ void qemu_clock_unregister_reset_notifier(QEMUClockType type,
     notifier_remove(notifier);
 }
 
-void init_clocks(void)
+void init_clocks(QEMUTimerListNotifyCB *notify_cb)
 {
     QEMUClockType type;
     for (type = 0; type < QEMU_CLOCK_MAX; type++) {
-        qemu_clock_init(type);
+        qemu_clock_init(type, notify_cb);
     }
 
 #ifdef CONFIG_PRCTL_PR_SET_TIMERSLACK
@@ -657,7 +658,9 @@ bool qemu_clock_run_all_timers(void)
     QEMUClockType type;
 
     for (type = 0; type < QEMU_CLOCK_MAX; type++) {
-        progress |= qemu_clock_run_timers(type);
+        if (qemu_clock_use_for_deadline(type)) {
+            progress |= qemu_clock_run_timers(type);
+        }
     }
 
     return progress;
diff --git a/vl.c b/vl.c
index 1a95500ac7..0b4ed5241c 100644
--- a/vl.c
+++ b/vl.c
@@ -1888,17 +1888,14 @@ static bool main_loop_should_exit(void)
 
 static void main_loop(void)
 {
-    bool nonblocking;
-    int last_io = 0;
 #ifdef CONFIG_PROFILER
     int64_t ti;
 #endif
     do {
-        nonblocking = tcg_enabled() && last_io > 0;
 #ifdef CONFIG_PROFILER
         ti = profile_getclock();
 #endif
-        last_io = main_loop_wait(nonblocking);
+        main_loop_wait(false);
 #ifdef CONFIG_PROFILER
         dev_time += profile_getclock() - ti;
 #endif