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

* KVM error improvement from Laurent
* CONFIG_PARALLEL fix from Mirek
* Atomic/optimized dirty bitmap access from myself and Stefan
* BUILD_DIR convenience/bugfix from Peter C
* Memory leak fix from Shannon
* SMM improvements (though still TCG only) from myself and Gerd, acked by mst

# gpg: Signature made Fri Jun  5 18:45:20 2015 BST using RSA key ID 78C7AE83
# gpg: Good signature from "Paolo Bonzini <bonzini@gnu.org>"
# gpg:                 aka "Paolo Bonzini <pbonzini@redhat.com>"
# gpg: WARNING: This key is not certified with sufficiently trusted signatures!
# gpg:          It is not certain that the signature belongs to the owner.
# 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: (62 commits)
  update Linux headers from kvm/next
  atomics: add explicit compiler fence in __atomic memory barriers
  ich9: implement SMI_LOCK
  q35: implement TSEG
  q35: add test for SMRAM.D_LCK
  q35: implement SMRAM.D_LCK
  q35: add config space wmask for SMRAM and ESMRAMC
  q35: fix ESMRAMC default
  q35: implement high SMRAM
  hw/i386: remove smram_update
  target-i386: use memory API to implement SMRAM
  hw/i386: add a separate region that tracks the SMRAME bit
  target-i386: create a separate AddressSpace for each CPU
  vl: run "late" notifiers immediately
  qom: add object_property_add_const_link
  vl: allow full-blown QemuOpts syntax for -global
  pflash_cfi01: add secure property
  pflash_cfi01: change to new-style MMIO accessors
  pflash_cfi01: change big-endian property to BIT type
  target-i386: wake up processors that receive an SMI
  ...

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

1 files changed, 58 insertions, 26 deletions

diff --git a/cpus.c b/cpus.c
index de6469fa8d..f38b858f9b 100644
--- a/cpus.c
+++ b/cpus.c
@@ -105,6 +105,7 @@ static bool all_cpu_threads_idle(void)
 
 /* Protected by TimersState seqlock */
 
+static bool icount_sleep = true;
 static int64_t vm_clock_warp_start = -1;
 /* Conversion factor from emulated instructions to virtual clock ticks.  */
 static int icount_time_shift;
@@ -393,15 +394,18 @@ void qemu_clock_warp(QEMUClockType type)
         return;
     }
 
-    /*
-     * If the CPUs have been sleeping, advance QEMU_CLOCK_VIRTUAL timer now.
-     * This ensures that the deadline for the timer is computed correctly below.
-     * This also makes sure that the insn counter is synchronized before the
-     * CPU starts running, in case the CPU is woken by an event other than
-     * the earliest QEMU_CLOCK_VIRTUAL timer.
-     */
-    icount_warp_rt(NULL);
-    timer_del(icount_warp_timer);
+    if (icount_sleep) {
+        /*
+         * If the CPUs have been sleeping, advance QEMU_CLOCK_VIRTUAL timer now.
+         * This ensures that the deadline for the timer is computed correctly
+         * below.
+         * This also makes sure that the insn counter is synchronized before
+         * the CPU starts running, in case the CPU is woken by an event other
+         * than the earliest QEMU_CLOCK_VIRTUAL timer.
+         */
+        icount_warp_rt(NULL);
+        timer_del(icount_warp_timer);
+    }
     if (!all_cpu_threads_idle()) {
         return;
     }
@@ -415,6 +419,11 @@ void qemu_clock_warp(QEMUClockType type)
     clock = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL_RT);
     deadline = qemu_clock_deadline_ns_all(QEMU_CLOCK_VIRTUAL);
     if (deadline < 0) {
+        static bool notified;
+        if (!icount_sleep && !notified) {
+            error_report("WARNING: icount sleep disabled and no active timers");
+            notified = true;
+        }
         return;
     }
 
@@ -425,23 +434,35 @@ void qemu_clock_warp(QEMUClockType type)
          * interrupt to wake it up, but the interrupt never comes because
          * the vCPU isn't running any insns and thus doesn't advance the
          * QEMU_CLOCK_VIRTUAL.
-         *
-         * An extreme solution for this problem would be to never let VCPUs
-         * sleep in icount mode if there is a pending QEMU_CLOCK_VIRTUAL
-         * timer; rather time could just advance to the next QEMU_CLOCK_VIRTUAL
-         * event.  Instead, we do stop VCPUs and only advance QEMU_CLOCK_VIRTUAL
-         * after some "real" time, (related to the time left until the next
-         * event) has passed. The QEMU_CLOCK_VIRTUAL_RT clock will do this.
-         * This avoids that the warps are visible externally; for example,
-         * you will not be sending network packets continuously instead of
-         * every 100ms.
          */
-        seqlock_write_lock(&timers_state.vm_clock_seqlock);
-        if (vm_clock_warp_start == -1 || vm_clock_warp_start > clock) {
-            vm_clock_warp_start = clock;
+        if (!icount_sleep) {
+            /*
+             * We never let VCPUs sleep in no sleep icount mode.
+             * If there is a pending QEMU_CLOCK_VIRTUAL timer we just advance
+             * to the next QEMU_CLOCK_VIRTUAL event and notify it.
+             * It is useful when we want a deterministic execution time,
+             * isolated from host latencies.
+             */
+            seqlock_write_lock(&timers_state.vm_clock_seqlock);
+            timers_state.qemu_icount_bias += deadline;
+            seqlock_write_unlock(&timers_state.vm_clock_seqlock);
+            qemu_clock_notify(QEMU_CLOCK_VIRTUAL);
+        } else {
+            /*
+             * We do stop VCPUs and only advance QEMU_CLOCK_VIRTUAL after some
+             * "real" time, (related to the time left until the next event) has
+             * passed. The QEMU_CLOCK_VIRTUAL_RT clock will do this.
+             * This avoids that the warps are visible externally; for example,
+             * you will not be sending network packets continuously instead of
+             * every 100ms.
+             */
+            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);
         }
-        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);
     }
@@ -504,9 +525,18 @@ void configure_icount(QemuOpts *opts, Error **errp)
         }
         return;
     }
+
+    icount_sleep = qemu_opt_get_bool(opts, "sleep", true);
+    if (icount_sleep) {
+        icount_warp_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL_RT,
+                                         icount_warp_rt, NULL);
+    }
+
     icount_align_option = qemu_opt_get_bool(opts, "align", false);
-    icount_warp_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL_RT,
-                                     icount_warp_rt, NULL);
+
+    if (icount_align_option && !icount_sleep) {
+        error_setg(errp, "align=on and sleep=no are incompatible");
+    }
     if (strcmp(option, "auto") != 0) {
         errno = 0;
         icount_time_shift = strtol(option, &rem_str, 0);
@@ -517,6 +547,8 @@ void configure_icount(QemuOpts *opts, Error **errp)
         return;
     } else if (icount_align_option) {
         error_setg(errp, "shift=auto and align=on are incompatible");
+    } else if (!icount_sleep) {
+        error_setg(errp, "shift=auto and sleep=no are incompatible");
     }
 
     use_icount = 2;