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

* Record-replay lockstep execution, log dumper and fixes (Alex, Pavel)
* SCSI fix to pass maximum transfer size (Daniel Barboza)
* chardev fixes and improved iothread support (Daniel Berrangé, Peter)
* checkpatch tweak (Eric)
* make help tweak (Marc-André)
* make more PCI NICs available with -net or -nic (myself)
* change default q35 NIC to e1000e (myself)
* SCSI support for NDOB bit (myself)
* membarrier system call support (myself)
* SuperIO refactoring (Philippe)
* miscellaneous cleanups and fixes (Thomas)

# gpg: Signature made Mon 12 Mar 2018 16:10:52 GMT
# gpg:                using RSA key BFFBD25F78C7AE83
# gpg: Good signature from "Paolo Bonzini <bonzini@gnu.org>"
# gpg:                 aka "Paolo Bonzini <pbonzini@redhat.com>"
# Primary key fingerprint: 46F5 9FBD 57D6 12E7 BFD4  E2F7 7E15 100C CD36 69B1
#      Subkey fingerprint: F133 3857 4B66 2389 866C  7682 BFFB D25F 78C7 AE83

* remotes/bonzini/tags/for-upstream: (69 commits)
  tcg: fix cpu_io_recompile
  replay: update documentation
  replay: save vmstate of the asynchronous events
  replay: don't process async events when warping the clock
  scripts/replay-dump.py: replay log dumper
  replay: avoid recursive call of checkpoints
  replay: check return values of fwrite
  replay: push replay_mutex_lock up the call tree
  replay: don't destroy mutex at exit
  replay: make locking visible outside replay code
  replay/replay-internal.c: track holding of replay_lock
  replay/replay.c: bump REPLAY_VERSION again
  replay: save prior value of the host clock
  replay: added replay log format description
  replay: fix save/load vm for non-empty queue
  replay: fixed replay_enable_events
  replay: fix processing async events
  cpu-exec: fix exception_index handling
  hw/i386/pc: Factor out the superio code
  hw/alpha/dp264: Use the TYPE_SMC37C669_SUPERIO
  ...

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

# Conflicts:
#	default-configs/i386-softmmu.mak
#	default-configs/x86_64-softmmu.mak

5 files changed, 85 insertions, 8 deletions

diff --git a/util/Makefile.objs b/util/Makefile.objs
index ae90b99..728c354 100644
--- a/util/Makefile.objs
+++ b/util/Makefile.objs
@@ -33,6 +33,7 @@ util-obj-y += throttle.o
 util-obj-y += getauxval.o
 util-obj-y += readline.o
 util-obj-y += rcu.o
+util-obj-$(CONFIG_MEMBARRIER) += sys_membarrier.o
 util-obj-y += qemu-coroutine.o qemu-coroutine-lock.o qemu-coroutine-io.o
 util-obj-y += qemu-coroutine-sleep.o
 util-obj-y += coroutine-$(CONFIG_COROUTINE_BACKEND).o
diff --git a/util/main-loop.c b/util/main-loop.c
index 7558eb5..992f9b0 100644
--- a/util/main-loop.c
+++ b/util/main-loop.c
@@ -29,6 +29,7 @@
 #include "qemu/sockets.h"	// struct in_addr needed for libslirp.h
 #include "sysemu/qtest.h"
 #include "sysemu/cpus.h"
+#include "sysemu/replay.h"
 #include "slirp/libslirp.h"
 #include "qemu/main-loop.h"
 #include "block/aio.h"
@@ -245,18 +246,19 @@ static int os_host_main_loop_wait(int64_t timeout)
         timeout = SCALE_MS;
     }
 
+
     if (timeout) {
         spin_counter = 0;
-        qemu_mutex_unlock_iothread();
     } else {
         spin_counter++;
     }
+    qemu_mutex_unlock_iothread();
+    replay_mutex_unlock();
 
     ret = qemu_poll_ns((GPollFD *)gpollfds->data, gpollfds->len, timeout);
 
-    if (timeout) {
-        qemu_mutex_lock_iothread();
-    }
+    replay_mutex_lock();
+    qemu_mutex_lock_iothread();
 
     glib_pollfds_poll();
 
@@ -463,8 +465,13 @@ static int os_host_main_loop_wait(int64_t timeout)
     poll_timeout_ns = qemu_soonest_timeout(poll_timeout_ns, timeout);
 
     qemu_mutex_unlock_iothread();
+
+    replay_mutex_unlock();
+
     g_poll_ret = qemu_poll_ns(poll_fds, n_poll_fds + w->num, poll_timeout_ns);
 
+    replay_mutex_lock();
+
     qemu_mutex_lock_iothread();
     if (g_poll_ret > 0) {
         for (i = 0; i < w->num; i++) {
diff --git a/util/qemu-timer.c b/util/qemu-timer.c
index 82d5650..2ed1bf2 100644
--- a/util/qemu-timer.c
+++ b/util/qemu-timer.c
@@ -622,6 +622,18 @@ int64_t qemu_clock_get_ns(QEMUClockType type)
     }
 }
 
+uint64_t qemu_clock_get_last(QEMUClockType type)
+{
+    QEMUClock *clock = qemu_clock_ptr(type);
+    return clock->last;
+}
+
+void qemu_clock_set_last(QEMUClockType type, uint64_t last)
+{
+    QEMUClock *clock = qemu_clock_ptr(type);
+    clock->last = last;
+}
+
 void qemu_clock_register_reset_notifier(QEMUClockType type,
                                         Notifier *notifier)
 {
diff --git a/util/rcu.c b/util/rcu.c
index f4d09c8..5676c22 100644
--- a/util/rcu.c
+++ b/util/rcu.c
@@ -92,10 +92,11 @@ static void wait_for_readers(void)
             atomic_set(&index->waiting, true);
         }
 
-        /* Here, order the stores to index->waiting before the
-         * loads of index->ctr.
+        /* Here, order the stores to index->waiting before the loads of
+         * index->ctr.  Pairs with smp_mb_placeholder() in rcu_read_unlock(),
+         * ensuring that the loads of index->ctr are sequentially consistent.
          */
-        smp_mb();
+        smp_mb_global();
 
         QLIST_FOREACH_SAFE(index, &registry, node, tmp) {
             if (!rcu_gp_ongoing(&index->ctr)) {
@@ -142,8 +143,13 @@ static void wait_for_readers(void)
 void synchronize_rcu(void)
 {
     qemu_mutex_lock(&rcu_sync_lock);
-    qemu_mutex_lock(&rcu_registry_lock);
 
+    /* Write RCU-protected pointers before reading p_rcu_reader->ctr.
+     * Pairs with smp_mb_placeholder() in rcu_read_lock().
+     */
+    smp_mb_global();
+
+    qemu_mutex_lock(&rcu_registry_lock);
     if (!QLIST_EMPTY(&registry)) {
         /* In either case, the atomic_mb_set below blocks stores that free
          * old RCU-protected pointers.
@@ -370,6 +376,7 @@ static void rcu_init_child(void)
 
 static void __attribute__((__constructor__)) rcu_init(void)
 {
+    smp_mb_global_init();
 #ifdef CONFIG_POSIX
     pthread_atfork(rcu_init_lock, rcu_init_unlock, rcu_init_child);
 #endif
diff --git a/util/sys_membarrier.c b/util/sys_membarrier.c
new file mode 100644
index 0000000..8dcb53e
--- /dev/null
+++ b/util/sys_membarrier.c
@@ -0,0 +1,50 @@
+/*
+ * Process-global memory barriers
+ *
+ * Copyright (c) 2018 Red Hat, Inc.
+ *
+ * Author: Paolo Bonzini <pbonzini@redhat.com>
+ */
+
+#include <qemu/osdep.h>
+#include <qemu/sys_membarrier.h>
+#include <qemu/error-report.h>
+
+#ifdef CONFIG_LINUX
+#include <linux/membarrier.h>
+#include <sys/syscall.h>
+
+static int
+membarrier(int cmd, int flags)
+{
+    return syscall(__NR_membarrier, cmd, flags);
+}
+#endif
+
+void smp_mb_global(void)
+{
+#if defined CONFIG_WIN32
+    FlushProcessWriteBuffers();
+#elif defined CONFIG_LINUX
+    membarrier(MEMBARRIER_CMD_SHARED, 0);
+#else
+#error --enable-membarrier is not supported on this operating system.
+#endif
+}
+
+void smp_mb_global_init(void)
+{
+#ifdef CONFIG_LINUX
+    int ret = membarrier(MEMBARRIER_CMD_QUERY, 0);
+    if (ret < 0) {
+        error_report("This QEMU binary requires the membarrier system call.");
+        error_report("Please upgrade your system to a newer version of Linux");
+        exit(1);
+    }
+    if (!(ret & MEMBARRIER_CMD_SHARED)) {
+        error_report("This QEMU binary requires MEMBARRIER_CMD_SHARED support.");
+        error_report("Please upgrade your system to a newer version of Linux");
+        exit(1);
+    }
+#endif
+}