Merge remote-tracking branch 'bonzini/iommu-for-anthony' into staging

# By Paolo Bonzini (10) and others
# Via Paolo Bonzini
* bonzini/iommu-for-anthony:
  exec: remove qemu_safe_ram_ptr
  icount: make it thread-safe
  icount: document (future) locking rules for icount
  icount: prepare the code for future races in calling qemu_clock_warp
  icount: reorganize icount_warp_rt
  icount: use cpu_get_icount() directly
  timer: add timer_mod_anticipate and timer_mod_anticipate_ns
  timer: extract timer_mod_ns_locked and timerlist_rearm
  timer: make qemu_clock_enable sync between disable and timer's cb
  qemu-thread: add QemuEvent
  timer: protect timers_state's clock with seqlock
  seqlock: introduce read-write seqlock
  vga: Mark relevant portio lists regions as coalesced MMIO flushing
  cirrus: Mark vga io region as coalesced MMIO flushing
  portio: Allow to mark portio lists as coalesced MMIO flushing
  compatfd: switch to QemuThread
  memory: fix 128 arithmetic in info mtree

Message-id: 1382024935-28297-1-git-send-email-pbonzini@redhat.com
Signed-off-by: Anthony Liguori <aliguori@amazon.com>

17 files changed, 502 insertions, 143 deletions

diff --git a/cpus.c b/cpus.c
index e566297bd3..398229ecbd 100644
--- a/cpus.c
+++ b/cpus.c
@@ -37,6 +37,7 @@
 #include "sysemu/qtest.h"
 #include "qemu/main-loop.h"
 #include "qemu/bitmap.h"
+#include "qemu/seqlock.h"
 
 #ifndef _WIN32
 #include "qemu/compatfd.h"
@@ -97,21 +98,32 @@ static bool all_cpu_threads_idle(void)
 /***********************************************************/
 /* guest cycle counter */
 
+/* Protected by TimersState seqlock */
+
+/* Compensate for varying guest execution speed.  */
+static int64_t qemu_icount_bias;
+static int64_t vm_clock_warp_start;
 /* Conversion factor from emulated instructions to virtual clock ticks.  */
 static int icount_time_shift;
 /* Arbitrarily pick 1MIPS as the minimum allowable speed.  */
 #define MAX_ICOUNT_SHIFT 10
-/* Compensate for varying guest execution speed.  */
-static int64_t qemu_icount_bias;
+
+/* Only written by TCG thread */
+static int64_t qemu_icount;
+
 static QEMUTimer *icount_rt_timer;
 static QEMUTimer *icount_vm_timer;
 static QEMUTimer *icount_warp_timer;
-static int64_t vm_clock_warp_start;
-static int64_t qemu_icount;
 
 typedef struct TimersState {
+    /* Protected by BQL.  */
     int64_t cpu_ticks_prev;
     int64_t cpu_ticks_offset;
+
+    /* cpu_clock_offset can be read out of BQL, so protect it with
+     * this lock.
+     */
+    QemuSeqLock vm_clock_seqlock;
     int64_t cpu_clock_offset;
     int32_t cpu_ticks_enabled;
     int64_t dummy;
@@ -120,7 +132,7 @@ typedef struct TimersState {
 static TimersState timers_state;
 
 /* Return the virtual CPU time, based on the instruction counter.  */
-int64_t cpu_get_icount(void)
+static int64_t cpu_get_icount_locked(void)
 {
     int64_t icount;
     CPUState *cpu = current_cpu;
@@ -136,7 +148,21 @@ int64_t cpu_get_icount(void)
     return qemu_icount_bias + (icount << icount_time_shift);
 }
 
+int64_t cpu_get_icount(void)
+{
+    int64_t icount;
+    unsigned start;
+
+    do {
+        start = seqlock_read_begin(&timers_state.vm_clock_seqlock);
+        icount = cpu_get_icount_locked();
+    } while (seqlock_read_retry(&timers_state.vm_clock_seqlock, start));
+
+    return icount;
+}
+
 /* return the host CPU cycle counter and handle stop/restart */
+/* Caller must hold the BQL */
 int64_t cpu_get_ticks(void)
 {
     if (use_icount) {
@@ -157,37 +183,63 @@ int64_t cpu_get_ticks(void)
     }
 }
 
-/* return the host CPU monotonic timer and handle stop/restart */
-int64_t cpu_get_clock(void)
+static int64_t cpu_get_clock_locked(void)
 {
     int64_t ti;
+
     if (!timers_state.cpu_ticks_enabled) {
-        return timers_state.cpu_clock_offset;
+        ti = timers_state.cpu_clock_offset;
     } else {
         ti = get_clock();
-        return ti + timers_state.cpu_clock_offset;
+        ti += timers_state.cpu_clock_offset;
     }
+
+    return ti;
 }
 
-/* enable cpu_get_ticks() */
+/* return the host CPU monotonic timer and handle stop/restart */
+int64_t cpu_get_clock(void)
+{
+    int64_t ti;
+    unsigned start;
+
+    do {
+        start = seqlock_read_begin(&timers_state.vm_clock_seqlock);
+        ti = cpu_get_clock_locked();
+    } while (seqlock_read_retry(&timers_state.vm_clock_seqlock, start));
+
+    return ti;
+}
+
+/* enable cpu_get_ticks()
+ * Caller must hold BQL which server as mutex for vm_clock_seqlock.
+ */
 void cpu_enable_ticks(void)
 {
+    /* Here, the really thing protected by seqlock is cpu_clock_offset. */
+    seqlock_write_lock(&timers_state.vm_clock_seqlock);
     if (!timers_state.cpu_ticks_enabled) {
         timers_state.cpu_ticks_offset -= cpu_get_real_ticks();
         timers_state.cpu_clock_offset -= get_clock();
         timers_state.cpu_ticks_enabled = 1;
     }
+    seqlock_write_unlock(&timers_state.vm_clock_seqlock);
 }
 
 /* disable cpu_get_ticks() : the clock is stopped. You must not call
-   cpu_get_ticks() after that.  */
+ * cpu_get_ticks() after that.
+ * Caller must hold BQL which server as mutex for vm_clock_seqlock.
+ */
 void cpu_disable_ticks(void)
 {
+    /* Here, the really thing protected by seqlock is cpu_clock_offset. */
+    seqlock_write_lock(&timers_state.vm_clock_seqlock);
     if (timers_state.cpu_ticks_enabled) {
         timers_state.cpu_ticks_offset = cpu_get_ticks();
-        timers_state.cpu_clock_offset = cpu_get_clock();
+        timers_state.cpu_clock_offset = cpu_get_clock_locked();
         timers_state.cpu_ticks_enabled = 0;
     }
+    seqlock_write_unlock(&timers_state.vm_clock_seqlock);
 }
 
 /* Correlation between real and virtual time is always going to be
@@ -201,13 +253,19 @@ static void icount_adjust(void)
     int64_t cur_time;
     int64_t cur_icount;
     int64_t delta;
+
+    /* Protected by TimersState mutex.  */
     static int64_t last_delta;
+
     /* If the VM is not running, then do nothing.  */
     if (!runstate_is_running()) {
         return;
     }
-    cur_time = cpu_get_clock();
-    cur_icount = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL);
+
+    seqlock_write_lock(&timers_state.vm_clock_seqlock);
+    cur_time = cpu_get_clock_locked();
+    cur_icount = cpu_get_icount_locked();
+
     delta = cur_icount - cur_time;
     /* FIXME: This is a very crude algorithm, somewhat prone to oscillation.  */
     if (delta > 0
@@ -224,6 +282,7 @@ static void icount_adjust(void)
     }
     last_delta = delta;
     qemu_icount_bias = cur_icount - (qemu_icount << icount_time_shift);
+    seqlock_write_unlock(&timers_state.vm_clock_seqlock);
 }
 
 static void icount_adjust_rt(void *opaque)
@@ -248,30 +307,37 @@ static int64_t qemu_icount_round(int64_t count)
 
 static void icount_warp_rt(void *opaque)
 {
-    if (vm_clock_warp_start == -1) {
+    /* The icount_warp_timer is rescheduled soon after vm_clock_warp_start
+     * changes from -1 to another value, so the race here is okay.
+     */
+    if (atomic_read(&vm_clock_warp_start) == -1) {
         return;
     }
 
+    seqlock_write_lock(&timers_state.vm_clock_seqlock);
     if (runstate_is_running()) {
         int64_t clock = qemu_clock_get_ns(QEMU_CLOCK_REALTIME);
-        int64_t warp_delta = clock - vm_clock_warp_start;
-        if (use_icount == 1) {
-            qemu_icount_bias += warp_delta;
-        } else {
+        int64_t warp_delta;
+
+        warp_delta = clock - vm_clock_warp_start;
+        if (use_icount == 2) {
             /*
              * In adaptive mode, do not let QEMU_CLOCK_VIRTUAL run too
              * far ahead of real time.
              */
-            int64_t cur_time = cpu_get_clock();
-            int64_t cur_icount = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL);
+            int64_t cur_time = cpu_get_clock_locked();
+            int64_t cur_icount = cpu_get_icount_locked();
             int64_t delta = cur_time - cur_icount;
-            qemu_icount_bias += MIN(warp_delta, delta);
-        }
-        if (qemu_clock_expired(QEMU_CLOCK_VIRTUAL)) {
-            qemu_clock_notify(QEMU_CLOCK_VIRTUAL);
+            warp_delta = MIN(warp_delta, delta);
         }
+        qemu_icount_bias += warp_delta;
     }
     vm_clock_warp_start = -1;
+    seqlock_write_unlock(&timers_state.vm_clock_seqlock);
+
+    if (qemu_clock_expired(QEMU_CLOCK_VIRTUAL)) {
+        qemu_clock_notify(QEMU_CLOCK_VIRTUAL);
+    }
 }
 
 void qtest_clock_warp(int64_t dest)
@@ -281,7 +347,10 @@ void qtest_clock_warp(int64_t dest)
     while (clock < dest) {
         int64_t deadline = qemu_clock_deadline_ns_all(QEMU_CLOCK_VIRTUAL);
         int64_t warp = MIN(dest - clock, deadline);
+        seqlock_write_lock(&timers_state.vm_clock_seqlock);
         qemu_icount_bias += warp;
+        seqlock_write_unlock(&timers_state.vm_clock_seqlock);
+
         qemu_clock_run_timers(QEMU_CLOCK_VIRTUAL);
         clock = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL);
     }
@@ -290,6 +359,7 @@ void qtest_clock_warp(int64_t dest)
 
 void qemu_clock_warp(QEMUClockType type)
 {
+    int64_t clock;
     int64_t deadline;
 
     /*
@@ -309,8 +379,8 @@ void qemu_clock_warp(QEMUClockType type)
      * the earliest QEMU_CLOCK_VIRTUAL timer.
      */
     icount_warp_rt(NULL);
-    if (!all_cpu_threads_idle() || !qemu_clock_has_timers(QEMU_CLOCK_VIRTUAL)) {
-        timer_del(icount_warp_timer);
+    timer_del(icount_warp_timer);
+    if (!all_cpu_threads_idle()) {
         return;
     }
 
@@ -319,17 +389,11 @@ void qemu_clock_warp(QEMUClockType type)
 	return;
     }
 
-    vm_clock_warp_start = qemu_clock_get_ns(QEMU_CLOCK_REALTIME);
     /* We want to use the earliest deadline from ALL vm_clocks */
+    clock = qemu_clock_get_ns(QEMU_CLOCK_REALTIME);
     deadline = qemu_clock_deadline_ns_all(QEMU_CLOCK_VIRTUAL);
-
-    /* Maintain prior (possibly buggy) behaviour where if no deadline
-     * was set (as there is no QEMU_CLOCK_VIRTUAL timer) or it is more than
-     * INT32_MAX nanoseconds ahead, we still use INT32_MAX
-     * nanoseconds.
-     */
-    if ((deadline < 0) || (deadline > INT32_MAX)) {
-        deadline = INT32_MAX;
+    if (deadline < 0) {
+        return;
     }
 
     if (deadline > 0) {
@@ -350,7 +414,12 @@ void qemu_clock_warp(QEMUClockType type)
          * you will not be sending network packets continuously instead of
          * every 100ms.
          */
-        timer_mod(icount_warp_timer, vm_clock_warp_start + deadline);
+        seqlock_write_lock(&timers_state.vm_clock_seqlock);
+        if (vm_clock_warp_start == -1 || vm_clock_warp_start > clock) {
+            vm_clock_warp_start = clock;
+        }
+        seqlock_write_unlock(&timers_state.vm_clock_seqlock);
+        timer_mod_anticipate(icount_warp_timer, clock + deadline);
     } else if (deadline == 0) {
         qemu_clock_notify(QEMU_CLOCK_VIRTUAL);
     }
@@ -371,6 +440,7 @@ static const VMStateDescription vmstate_timers = {
 
 void configure_icount(const char *option)
 {
+    seqlock_init(&timers_state.vm_clock_seqlock, NULL);
     vmstate_register(NULL, 0, &vmstate_timers, &timers_state);
     if (!option) {
         return;
diff --git a/exec.c b/exec.c
index bea2cffd94..2e31ffcb2c 100644
--- a/exec.c
+++ b/exec.c
@@ -129,7 +129,6 @@ static PhysPageMap next_map;
 
 static void io_mem_init(void);
 static void memory_map_init(void);
-static void *qemu_safe_ram_ptr(ram_addr_t addr);
 
 static MemoryRegion io_mem_watch;
 #endif
@@ -626,22 +625,39 @@ void cpu_abort(CPUArchState *env, const char *fmt, ...)
 }
 
 #if !defined(CONFIG_USER_ONLY)
+static RAMBlock *qemu_get_ram_block(ram_addr_t addr)
+{
+    RAMBlock *block;
+
+    /* The list is protected by the iothread lock here.  */
+    block = ram_list.mru_block;
+    if (block && addr - block->offset < block->length) {
+        goto found;
+    }
+    QTAILQ_FOREACH(block, &ram_list.blocks, next) {
+        if (addr - block->offset < block->length) {
+            goto found;
+        }
+    }
+
+    fprintf(stderr, "Bad ram offset %" PRIx64 "\n", (uint64_t)addr);
+    abort();
+
+found:
+    ram_list.mru_block = block;
+    return block;
+}
+
 static void tlb_reset_dirty_range_all(ram_addr_t start, ram_addr_t end,
                                       uintptr_t length)
 {
-    uintptr_t start1;
+    RAMBlock *block;
+    ram_addr_t start1;
 
-    /* we modify the TLB cache so that the dirty bit will be set again
-       when accessing the range */
-    start1 = (uintptr_t)qemu_safe_ram_ptr(start);
-    /* Check that we don't span multiple blocks - this breaks the
-       address comparisons below.  */
-    if ((uintptr_t)qemu_safe_ram_ptr(end - 1) - start1
-            != (end - 1) - start) {
-        abort();
-    }
+    block = qemu_get_ram_block(start);
+    assert(block == qemu_get_ram_block(end - 1));
+    start1 = (uintptr_t)block->host + (start - block->offset);
     cpu_tlb_reset_dirty_all(start1, length);
-
 }
 
 /* Note: start and end must be within the same ram block.  */
@@ -1269,29 +1285,6 @@ void qemu_ram_remap(ram_addr_t addr, ram_addr_t length)
 }
 #endif /* !_WIN32 */
 
-static RAMBlock *qemu_get_ram_block(ram_addr_t addr)
-{
-    RAMBlock *block;
-
-    /* The list is protected by the iothread lock here.  */
-    block = ram_list.mru_block;
-    if (block && addr - block->offset < block->length) {
-        goto found;
-    }
-    QTAILQ_FOREACH(block, &ram_list.blocks, next) {
-        if (addr - block->offset < block->length) {
-            goto found;
-        }
-    }
-
-    fprintf(stderr, "Bad ram offset %" PRIx64 "\n", (uint64_t)addr);
-    abort();
-
-found:
-    ram_list.mru_block = block;
-    return block;
-}
-
 /* Return a host pointer to ram allocated with qemu_ram_alloc.
    With the exception of the softmmu code in this file, this should
    only be used for local memory (e.g. video ram) that the device owns,
@@ -1319,40 +1312,6 @@ void *qemu_get_ram_ptr(ram_addr_t addr)
     return block->host + (addr - block->offset);
 }
 
-/* Return a host pointer to ram allocated with qemu_ram_alloc.  Same as
- * qemu_get_ram_ptr but do not touch ram_list.mru_block.
- *
- * ??? Is this still necessary?
- */
-static void *qemu_safe_ram_ptr(ram_addr_t addr)
-{
-    RAMBlock *block;
-
-    /* The list is protected by the iothread lock here.  */
-    QTAILQ_FOREACH(block, &ram_list.blocks, next) {
-        if (addr - block->offset < block->length) {
-            if (xen_enabled()) {
-                /* We need to check if the requested address is in the RAM
-                 * because we don't want to map the entire memory in QEMU.
-                 * In that case just map until the end of the page.
-                 */
-                if (block->offset == 0) {
-                    return xen_map_cache(addr, 0, 0);
-                } else if (block->host == NULL) {
-                    block->host =
-                        xen_map_cache(block->offset, block->length, 1);
-                }
-            }
-            return block->host + (addr - block->offset);
-        }
-    }
-
-    fprintf(stderr, "Bad ram offset %" PRIx64 "\n", (uint64_t)addr);
-    abort();
-
-    return NULL;
-}
-
 /* Return a host pointer to guest's ram. Similar to qemu_get_ram_ptr
  * but takes a size argument */
 static void *qemu_ram_ptr_length(ram_addr_t addr, hwaddr *size)
diff --git a/hw/display/cirrus_vga.c b/hw/display/cirrus_vga.c
index dbd1f4a47b..e4c345fa82 100644
--- a/hw/display/cirrus_vga.c
+++ b/hw/display/cirrus_vga.c
@@ -2447,7 +2447,6 @@ static uint64_t cirrus_vga_ioport_read(void *opaque, hwaddr addr,
     VGACommonState *s = &c->vga;
     int val, index;
 
-    qemu_flush_coalesced_mmio_buffer();
     addr += 0x3b0;
 
     if (vga_ioport_invalid(s, addr)) {
@@ -2544,7 +2543,6 @@ static void cirrus_vga_ioport_write(void *opaque, hwaddr addr, uint64_t val,
     VGACommonState *s = &c->vga;
     int index;
 
-    qemu_flush_coalesced_mmio_buffer();
     addr += 0x3b0;
 
     /* check port range access depending on color/monochrome mode */
@@ -2843,6 +2841,7 @@ static void cirrus_init_common(CirrusVGAState *s, Object *owner,
     /* Register ioport 0x3b0 - 0x3df */
     memory_region_init_io(&s->cirrus_vga_io, owner, &cirrus_vga_io_ops, s,
                           "cirrus-io", 0x30);
+    memory_region_set_flush_coalesced(&s->cirrus_vga_io);
     memory_region_add_subregion(system_io, 0x3b0, &s->cirrus_vga_io);
 
     memory_region_init(&s->low_mem_container, owner,
diff --git a/hw/display/qxl.c b/hw/display/qxl.c
index c2cea1ce88..de835d6af8 100644
--- a/hw/display/qxl.c
+++ b/hw/display/qxl.c
@@ -2073,6 +2073,7 @@ static int qxl_init_primary(PCIDevice *dev)
              pci_address_space(dev), pci_address_space_io(dev), false);
     portio_list_init(qxl_vga_port_list, OBJECT(dev), qxl_vga_portio_list,
                      vga, "vga");
+    portio_list_set_flush_coalesced(qxl_vga_port_list);
     portio_list_add(qxl_vga_port_list, pci_address_space_io(dev), 0x3b0);
 
     vga->con = graphic_console_init(DEVICE(dev), &qxl_ops, qxl);
diff --git a/hw/display/vga.c b/hw/display/vga.c
index 7b91d9c54e..b5e22849ab 100644
--- a/hw/display/vga.c
+++ b/hw/display/vga.c
@@ -359,8 +359,6 @@ uint32_t vga_ioport_read(void *opaque, uint32_t addr)
     VGACommonState *s = opaque;
     int val, index;
 
-    qemu_flush_coalesced_mmio_buffer();
-
     if (vga_ioport_invalid(s, addr)) {
         val = 0xff;
     } else {
@@ -453,8 +451,6 @@ void vga_ioport_write(void *opaque, uint32_t addr, uint32_t val)
     VGACommonState *s = opaque;
     int index;
 
-    qemu_flush_coalesced_mmio_buffer();
-
     /* check port range access depending on color/monochrome mode */
     if (vga_ioport_invalid(s, addr)) {
         return;
@@ -2373,6 +2369,7 @@ void vga_init(VGACommonState *s, Object *obj, MemoryRegion *address_space,
     memory_region_set_coalescing(vga_io_memory);
     if (init_vga_ports) {
         portio_list_init(vga_port_list, obj, vga_ports, s, "vga");
+        portio_list_set_flush_coalesced(vga_port_list);
         portio_list_add(vga_port_list, address_space_io, 0x3b0);
     }
     if (vbe_ports) {
diff --git a/include/exec/ioport.h b/include/exec/ioport.h
index b3848be684..3bd6722627 100644
--- a/include/exec/ioport.h
+++ b/include/exec/ioport.h
@@ -64,11 +64,13 @@ typedef struct PortioList {
     struct MemoryRegion **regions;
     void *opaque;
     const char *name;
+    bool flush_coalesced_mmio;
 } PortioList;
 
 void portio_list_init(PortioList *piolist, Object *owner,
                       const struct MemoryRegionPortio *callbacks,
                       void *opaque, const char *name);
+void portio_list_set_flush_coalesced(PortioList *piolist);
 void portio_list_destroy(PortioList *piolist);
 void portio_list_add(PortioList *piolist,
                      struct MemoryRegion *address_space,
diff --git a/include/qemu/seqlock.h b/include/qemu/seqlock.h
new file mode 100644
index 0000000000..3ff118a1a1
--- /dev/null
+++ b/include/qemu/seqlock.h
@@ -0,0 +1,72 @@
+/*
+ * Seqlock implementation for QEMU
+ *
+ * Copyright Red Hat, Inc. 2013
+ *
+ * Author:
+ *  Paolo Bonzini <pbonzini@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ *
+ */
+#ifndef QEMU_SEQLOCK_H
+#define QEMU_SEQLOCK_H 1
+
+#include <qemu/atomic.h>
+#include <qemu/thread.h>
+
+typedef struct QemuSeqLock QemuSeqLock;
+
+struct QemuSeqLock {
+    QemuMutex *mutex;
+    unsigned sequence;
+};
+
+static inline void seqlock_init(QemuSeqLock *sl, QemuMutex *mutex)
+{
+    sl->mutex = mutex;
+    sl->sequence = 0;
+}
+
+/* Lock out other writers and update the count.  */
+static inline void seqlock_write_lock(QemuSeqLock *sl)
+{
+    if (sl->mutex) {
+        qemu_mutex_lock(sl->mutex);
+    }
+    ++sl->sequence;
+
+    /* Write sequence before updating other fields.  */
+    smp_wmb();
+}
+
+static inline void seqlock_write_unlock(QemuSeqLock *sl)
+{
+    /* Write other fields before finalizing sequence.  */
+    smp_wmb();
+
+    ++sl->sequence;
+    if (sl->mutex) {
+        qemu_mutex_unlock(sl->mutex);
+    }
+}
+
+static inline unsigned seqlock_read_begin(QemuSeqLock *sl)
+{
+    /* Always fail if a write is in progress.  */
+    unsigned ret = sl->sequence & ~1;
+
+    /* Read sequence before reading other fields.  */
+    smp_rmb();
+    return ret;
+}
+
+static int seqlock_read_retry(const QemuSeqLock *sl, unsigned start)
+{
+    /* Read other fields before reading final sequence.  */
+    smp_rmb();
+    return unlikely(sl->sequence != start);
+}
+
+#endif
diff --git a/include/qemu/thread-posix.h b/include/qemu/thread-posix.h
index 361566abc4..eb5c7a1da1 100644
--- a/include/qemu/thread-posix.h
+++ b/include/qemu/thread-posix.h
@@ -21,6 +21,14 @@ struct QemuSemaphore {
 #endif
 };
 
+struct QemuEvent {
+#ifndef __linux__
+    pthread_mutex_t lock;
+    pthread_cond_t cond;
+#endif
+    unsigned value;
+};
+
 struct QemuThread {
     pthread_t thread;
 };
diff --git a/include/qemu/thread-win32.h b/include/qemu/thread-win32.h
index 13adb958f0..3d58081bed 100644
--- a/include/qemu/thread-win32.h
+++ b/include/qemu/thread-win32.h
@@ -17,6 +17,10 @@ struct QemuSemaphore {
     HANDLE sema;
 };
 
+struct QemuEvent {
+    HANDLE event;
+};
+
 typedef struct QemuThreadData QemuThreadData;
 struct QemuThread {
     QemuThreadData *data;
diff --git a/include/qemu/thread.h b/include/qemu/thread.h
index c02404b9fb..3e32c6531c 100644
--- a/include/qemu/thread.h
+++ b/include/qemu/thread.h
@@ -7,6 +7,7 @@
 typedef struct QemuMutex QemuMutex;
 typedef struct QemuCond QemuCond;
 typedef struct QemuSemaphore QemuSemaphore;
+typedef struct QemuEvent QemuEvent;
 typedef struct QemuThread QemuThread;
 
 #ifdef _WIN32
@@ -45,6 +46,12 @@ void qemu_sem_wait(QemuSemaphore *sem);
 int qemu_sem_timedwait(QemuSemaphore *sem, int ms);
 void qemu_sem_destroy(QemuSemaphore *sem);
 
+void qemu_event_init(QemuEvent *ev, bool init);
+void qemu_event_set(QemuEvent *ev);
+void qemu_event_reset(QemuEvent *ev);
+void qemu_event_wait(QemuEvent *ev);
+void qemu_event_destroy(QemuEvent *ev);
+
 void qemu_thread_create(QemuThread *thread,
                         void *(*start_routine)(void *),
                         void *arg, int mode);
diff --git a/include/qemu/timer.h b/include/qemu/timer.h
index b58903bef5..5afcffc3f9 100644
--- a/include/qemu/timer.h
+++ b/include/qemu/timer.h
@@ -189,6 +189,12 @@ void qemu_clock_notify(QEMUClockType type);
  * @enabled: true to enable, false to disable
  *
  * Enable or disable a clock
+ * Disabling the clock will wait for related timerlists to stop
+ * executing qemu_run_timers.  Thus, this functions should not
+ * be used from the callback of a timer that is based on @clock.
+ * Doing so would cause a deadlock.
+ *
+ * Caller should hold BQL.
  */
 void qemu_clock_enable(QEMUClockType type, bool enabled);
 
@@ -539,6 +545,19 @@ void timer_del(QEMUTimer *ts);
 void timer_mod_ns(QEMUTimer *ts, int64_t expire_time);
 
 /**
+ * timer_mod_anticipate_ns:
+ * @ts: the timer
+ * @expire_time: the expiry time in nanoseconds
+ *
+ * Modify a timer to expire at @expire_time or the current time,
+ * whichever comes earlier.
+ *
+ * This function is thread-safe but the timer and its timer list must not be
+ * freed while this function is running.
+ */
+void timer_mod_anticipate_ns(QEMUTimer *ts, int64_t expire_time);
+
+/**
  * timer_mod:
  * @ts: the timer
  * @expire_time: the expire time in the units associated with the timer
@@ -552,6 +571,19 @@ void timer_mod_ns(QEMUTimer *ts, int64_t expire_time);
 void timer_mod(QEMUTimer *ts, int64_t expire_timer);
 
 /**
+ * timer_mod_anticipate:
+ * @ts: the timer
+ * @expire_time: the expiry time in nanoseconds
+ *
+ * Modify a timer to expire at @expire_time or the current time, whichever
+ * comes earlier, taking into account the scale associated with the timer.
+ *
+ * This function is thread-safe but the timer and its timer list must not be
+ * freed while this function is running.
+ */
+void timer_mod_anticipate(QEMUTimer *ts, int64_t expire_time);
+
+/**
  * timer_pending:
  * @ts: the timer
  *
@@ -653,7 +685,9 @@ static inline int64_t qemu_soonest_timeout(int64_t timeout1, int64_t timeout2)
 void init_clocks(void);
 
 int64_t cpu_get_ticks(void);
+/* Caller must hold BQL */
 void cpu_enable_ticks(void);
+/* Caller must hold BQL */
 void cpu_disable_ticks(void);
 
 static inline int64_t get_ticks_per_sec(void)
diff --git a/ioport.c b/ioport.c
index 707cce88ab..3d91e79edc 100644
--- a/ioport.c
+++ b/ioport.c
@@ -139,6 +139,12 @@ void portio_list_init(PortioList *piolist,
     piolist->opaque = opaque;
     piolist->owner = owner;
     piolist->name = name;
+    piolist->flush_coalesced_mmio = false;
+}
+
+void portio_list_set_flush_coalesced(PortioList *piolist)
+{
+    piolist->flush_coalesced_mmio = true;
 }
 
 void portio_list_destroy(PortioList *piolist)
@@ -231,6 +237,9 @@ static void portio_list_add_1(PortioList *piolist,
      */
     memory_region_init_io(&mrpio->mr, piolist->owner, &portio_ops, mrpio,
                           piolist->name, off_high - off_low);
+    if (piolist->flush_coalesced_mmio) {
+        memory_region_set_flush_coalesced(&mrpio->mr);
+    }
     memory_region_add_subregion(piolist->address_space,
                                 start + off_low, &mrpio->mr);
     piolist->regions[piolist->nr] = &mrpio->mr;
diff --git a/memory.c b/memory.c
index 5a10fd0bde..7f1f2661a5 100644
--- a/memory.c
+++ b/memory.c
@@ -1809,7 +1809,9 @@ static void mtree_print_mr(fprintf_function mon_printf, void *f,
                    mr->alias->name,
                    mr->alias_offset,
                    mr->alias_offset
-                   + (hwaddr)int128_get64(mr->size) - 1);
+                   + (int128_nz(mr->size) ?
+                      (hwaddr)int128_get64(int128_sub(mr->size,
+                                                      int128_one())) : 0));
     } else {
         mon_printf(f,
                    TARGET_FMT_plx "-" TARGET_FMT_plx " (prio %d, %c%c): %s\n",
diff --git a/qemu-timer.c b/qemu-timer.c
index 6b62e88669..e15ce477cc 100644
--- a/qemu-timer.c
+++ b/qemu-timer.c
@@ -45,6 +45,7 @@
 /* timers */
 
 typedef struct QEMUClock {
+    /* We rely on BQL to protect the timerlists */
     QLIST_HEAD(, QEMUTimerList) timerlists;
 
     NotifierList reset_notifiers;
@@ -71,6 +72,9 @@ struct QEMUTimerList {
     QLIST_ENTRY(QEMUTimerList) list;
     QEMUTimerListNotifyCB *notify_cb;
     void *notify_opaque;
+
+    /* lightweight method to mark the end of timerlist's running */
+    QemuEvent timers_done_ev;
 };
 
 /**
@@ -99,6 +103,7 @@ QEMUTimerList *timerlist_new(QEMUClockType type,
     QEMUClock *clock = qemu_clock_ptr(type);
 
     timer_list = g_malloc0(sizeof(QEMUTimerList));
+    qemu_event_init(&timer_list->timers_done_ev, false);
     timer_list->clock = clock;
     timer_list->notify_cb = cb;
     timer_list->notify_opaque = opaque;
@@ -143,13 +148,25 @@ void qemu_clock_notify(QEMUClockType type)
     }
 }
 
+/* Disabling the clock will wait for related timerlists to stop
+ * executing qemu_run_timers.  Thus, this functions should not
+ * be used from the callback of a timer that is based on @clock.
+ * Doing so would cause a deadlock.
+ *
+ * Caller should hold BQL.
+ */
 void qemu_clock_enable(QEMUClockType type, bool enabled)
 {
     QEMUClock *clock = qemu_clock_ptr(type);
+    QEMUTimerList *tl;
     bool old = clock->enabled;
     clock->enabled = enabled;
     if (enabled && !old) {
         qemu_clock_notify(type);
+    } else if (!enabled && old) {
+        QLIST_FOREACH(tl, &clock->timerlists, list) {
+            qemu_event_wait(&tl->timers_done_ev);
+        }
     }
 }
 
@@ -338,6 +355,34 @@ static void timer_del_locked(QEMUTimerList *timer_list, QEMUTimer *ts)
     }
 }
 
+static bool timer_mod_ns_locked(QEMUTimerList *timer_list,
+                                QEMUTimer *ts, int64_t expire_time)
+{
+    QEMUTimer **pt, *t;
+
+    /* add the timer in the sorted list */
+    pt = &timer_list->active_timers;
+    for (;;) {
+        t = *pt;
+        if (!timer_expired_ns(t, expire_time)) {
+            break;
+        }
+        pt = &t->next;
+    }
+    ts->expire_time = MAX(expire_time, 0);
+    ts->next = *pt;
+    *pt = ts;
+
+    return pt == &timer_list->active_timers;
+}
+
+static void timerlist_rearm(QEMUTimerList *timer_list)
+{
+    /* Interrupt execution to force deadline recalculation.  */
+    qemu_clock_warp(timer_list->clock->type);
+    timerlist_notify(timer_list);
+}
+
 /* stop a timer, but do not dealloc it */
 void timer_del(QEMUTimer *ts)
 {
@@ -353,30 +398,39 @@ void timer_del(QEMUTimer *ts)
 void timer_mod_ns(QEMUTimer *ts, int64_t expire_time)
 {
     QEMUTimerList *timer_list = ts->timer_list;
-    QEMUTimer **pt, *t;
+    bool rearm;
 
     qemu_mutex_lock(&timer_list->active_timers_lock);
     timer_del_locked(timer_list, ts);
+    rearm = timer_mod_ns_locked(timer_list, ts, expire_time);
+    qemu_mutex_unlock(&timer_list->active_timers_lock);
 
-    /* add the timer in the sorted list */
-    pt = &timer_list->active_timers;
-    for(;;) {
-        t = *pt;
-        if (!timer_expired_ns(t, expire_time)) {
-            break;
+    if (rearm) {
+        timerlist_rearm(timer_list);
+    }
+}
+
+/* modify the current timer so that it will be fired when current_time
+   >= expire_time or the current deadline, whichever comes earlier.
+   The corresponding callback will be called. */
+void timer_mod_anticipate_ns(QEMUTimer *ts, int64_t expire_time)
+{
+    QEMUTimerList *timer_list = ts->timer_list;
+    bool rearm;
+
+    qemu_mutex_lock(&timer_list->active_timers_lock);
+    if (ts->expire_time == -1 || ts->expire_time > expire_time) {
+        if (ts->expire_time != -1) {
+            timer_del_locked(timer_list, ts);
         }
-        pt = &t->next;
+        rearm = timer_mod_ns_locked(timer_list, ts, expire_time);
+    } else {
+        rearm = false;
     }
-    ts->expire_time = MAX(expire_time, 0);
-    ts->next = *pt;
-    *pt = ts;
     qemu_mutex_unlock(&timer_list->active_timers_lock);
 
-    /* Rearm if necessary  */
-    if (pt == &timer_list->active_timers) {
-        /* Interrupt execution to force deadline recalculation.  */
-        qemu_clock_warp(timer_list->clock->type);
-        timerlist_notify(timer_list);
+    if (rearm) {
+        timerlist_rearm(timer_list);
     }
 }
 
@@ -385,6 +439,11 @@ void timer_mod(QEMUTimer *ts, int64_t expire_time)
     timer_mod_ns(ts, expire_time * ts->scale);
 }
 
+void timer_mod_anticipate(QEMUTimer *ts, int64_t expire_time)
+{
+    timer_mod_anticipate_ns(ts, expire_time * ts->scale);
+}
+
 bool timer_pending(QEMUTimer *ts)
 {
     return ts->expire_time >= 0;
@@ -403,8 +462,9 @@ bool timerlist_run_timers(QEMUTimerList *timer_list)
     QEMUTimerCB *cb;
     void *opaque;
 
+    qemu_event_reset(&timer_list->timers_done_ev);
     if (!timer_list->clock->enabled) {
-        return progress;
+        goto out;
     }
 
     current_time = qemu_clock_get_ns(timer_list->clock->type);
@@ -428,6 +488,9 @@ bool timerlist_run_timers(QEMUTimerList *timer_list)
         cb(opaque);
         progress = true;
     }
+
+out:
+    qemu_event_set(&timer_list->timers_done_ev);
     return progress;
 }
 
diff --git a/util/compatfd.c b/util/compatfd.c
index 9cf3f2834d..430a41c855 100644
--- a/util/compatfd.c
+++ b/util/compatfd.c
@@ -15,9 +15,9 @@
 
 #include "qemu-common.h"
 #include "qemu/compatfd.h"
+#include "qemu/thread.h"
 
 #include <sys/syscall.h>
-#include <pthread.h>
 
 struct sigfd_compat_info
 {
@@ -28,10 +28,6 @@ struct sigfd_compat_info
 static void *sigwait_compat(void *opaque)
 {
     struct sigfd_compat_info *info = opaque;
-    sigset_t all;
-
-    sigfillset(&all);
-    pthread_sigmask(SIG_BLOCK, &all, NULL);
 
     while (1) {
         int sig;
@@ -71,9 +67,8 @@ static void *sigwait_compat(void *opaque)
 
 static int qemu_signalfd_compat(const sigset_t *mask)
 {
-    pthread_attr_t attr;
-    pthread_t tid;
     struct sigfd_compat_info *info;
+    QemuThread thread;
     int fds[2];
 
     info = malloc(sizeof(*info));
@@ -93,12 +88,7 @@ static int qemu_signalfd_compat(const sigset_t *mask)
     memcpy(&info->mask, mask, sizeof(*mask));
     info->fd = fds[1];
 
-    pthread_attr_init(&attr);
-    pthread_attr_setdetachstate(&attr, PTHREAD_CREATE_DETACHED);
-
-    pthread_create(&tid, &attr, sigwait_compat, info);
-
-    pthread_attr_destroy(&attr);
+    qemu_thread_create(&thread, sigwait_compat, info, QEMU_THREAD_DETACHED);
 
     return fds[0];
 }
diff --git a/util/qemu-thread-posix.c b/util/qemu-thread-posix.c
index 4de133e7b2..37dd298631 100644
--- a/util/qemu-thread-posix.c
+++ b/util/qemu-thread-posix.c
@@ -20,7 +20,12 @@
 #include <limits.h>
 #include <unistd.h>
 #include <sys/time.h>
+#ifdef __linux__
+#include <sys/syscall.h>
+#include <linux/futex.h>
+#endif
 #include "qemu/thread.h"
+#include "qemu/atomic.h"
 
 static void error_exit(int err, const char *msg)
 {
@@ -272,6 +277,117 @@ void qemu_sem_wait(QemuSemaphore *sem)
 #endif
 }
 
+#ifdef __linux__
+#define futex(...)              syscall(__NR_futex, __VA_ARGS__)
+
+static inline void futex_wake(QemuEvent *ev, int n)
+{
+    futex(ev, FUTEX_WAKE, n, NULL, NULL, 0);
+}
+
+static inline void futex_wait(QemuEvent *ev, unsigned val)
+{
+    futex(ev, FUTEX_WAIT, (int) val, NULL, NULL, 0);
+}
+#else
+static inline void futex_wake(QemuEvent *ev, int n)
+{
+    if (n == 1) {
+        pthread_cond_signal(&ev->cond);
+    } else {
+        pthread_cond_broadcast(&ev->cond);
+    }
+}
+
+static inline void futex_wait(QemuEvent *ev, unsigned val)
+{
+    pthread_mutex_lock(&ev->lock);
+    if (ev->value == val) {
+        pthread_cond_wait(&ev->cond, &ev->lock);
+    }
+    pthread_mutex_unlock(&ev->lock);
+}
+#endif
+
+/* Valid transitions:
+ * - free->set, when setting the event
+ * - busy->set, when setting the event, followed by futex_wake
+ * - set->free, when resetting the event
+ * - free->busy, when waiting
+ *
+ * set->busy does not happen (it can be observed from the outside but
+ * it really is set->free->busy).
+ *
+ * busy->free provably cannot happen; to enforce it, the set->free transition
+ * is done with an OR, which becomes a no-op if the event has concurrently
+ * transitioned to free or busy.
+ */
+
+#define EV_SET         0
+#define EV_FREE        1
+#define EV_BUSY       -1
+
+void qemu_event_init(QemuEvent *ev, bool init)
+{
+#ifndef __linux__
+    pthread_mutex_init(&ev->lock, NULL);
+    pthread_cond_init(&ev->cond, NULL);
+#endif
+
+    ev->value = (init ? EV_SET : EV_FREE);
+}
+
+void qemu_event_destroy(QemuEvent *ev)
+{
+#ifndef __linux__
+    pthread_mutex_destroy(&ev->lock);
+    pthread_cond_destroy(&ev->cond);
+#endif
+}
+
+void qemu_event_set(QemuEvent *ev)
+{
+    if (atomic_mb_read(&ev->value) != EV_SET) {
+        if (atomic_xchg(&ev->value, EV_SET) == EV_BUSY) {
+            /* There were waiters, wake them up.  */
+            futex_wake(ev, INT_MAX);
+        }
+    }
+}
+
+void qemu_event_reset(QemuEvent *ev)
+{
+    if (atomic_mb_read(&ev->value) == EV_SET) {
+        /*
+         * If there was a concurrent reset (or even reset+wait),
+         * do nothing.  Otherwise change EV_SET->EV_FREE.
+         */
+        atomic_or(&ev->value, EV_FREE);
+    }
+}
+
+void qemu_event_wait(QemuEvent *ev)
+{
+    unsigned value;
+
+    value = atomic_mb_read(&ev->value);
+    if (value != EV_SET) {
+        if (value == EV_FREE) {
+            /*
+             * Leave the event reset and tell qemu_event_set that there
+             * are waiters.  No need to retry, because there cannot be
+             * a concurent busy->free transition.  After the CAS, the
+             * event will be either set or busy.
+             */
+            if (atomic_cmpxchg(&ev->value, EV_FREE, EV_BUSY) == EV_SET) {
+                return;
+            }
+        }
+        futex_wait(ev, EV_BUSY);
+    }
+}
+
+
 void qemu_thread_create(QemuThread *thread,
                        void *(*start_routine)(void*),
                        void *arg, int mode)
diff --git a/util/qemu-thread-win32.c b/util/qemu-thread-win32.c
index 517878dcc1..27a5217769 100644
--- a/util/qemu-thread-win32.c
+++ b/util/qemu-thread-win32.c
@@ -227,6 +227,32 @@ void qemu_sem_wait(QemuSemaphore *sem)
     }
 }
 
+void qemu_event_init(QemuEvent *ev, bool init)
+{
+    /* Manual reset.  */
+    ev->event = CreateEvent(NULL, TRUE, init, NULL);
+}
+
+void qemu_event_destroy(QemuEvent *ev)
+{
+    CloseHandle(ev->event);
+}
+
+void qemu_event_set(QemuEvent *ev)
+{
+    SetEvent(ev->event);
+}
+
+void qemu_event_reset(QemuEvent *ev)
+{
+    ResetEvent(ev->event);
+}
+
+void qemu_event_wait(QemuEvent *ev)
+{
+    WaitForSingleObject(ev->event, INFINITE);
+}
+
 struct QemuThreadData {
     /* Passed to win32_start_routine.  */
     void             *(*start_routine)(void *);