tcg: drop global lock during TCG code execution

This finally allows TCG to benefit from the iothread introduction: Drop
the global mutex while running pure TCG CPU code. Reacquire the lock
when entering MMIO or PIO emulation, or when leaving the TCG loop.

We have to revert a few optimization for the current TCG threading
model, namely kicking the TCG thread in qemu_mutex_lock_iothread and not
kicking it in qemu_cpu_kick. We also need to disable RAM block
reordering until we have a more efficient locking mechanism at hand.

Still, a Linux x86 UP guest and my Musicpal ARM model boot fine here.
These numbers demonstrate where we gain something:

20338 jan       20   0  331m  75m 6904 R   99  0.9   0:50.95 qemu-system-arm
20337 jan       20   0  331m  75m 6904 S   20  0.9   0:26.50 qemu-system-arm

The guest CPU was fully loaded, but the iothread could still run mostly
independent on a second core. Without the patch we don't get beyond

32206 jan       20   0  330m  73m 7036 R   82  0.9   1:06.00 qemu-system-arm
32204 jan       20   0  330m  73m 7036 S   21  0.9   0:17.03 qemu-system-arm

We don't benefit significantly, though, when the guest is not fully
loading a host CPU.

Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Message-Id: <1439220437-23957-10-git-send-email-fred.konrad@greensocs.com>
[FK: Rebase, fix qemu_devices_reset deadlock, rm address_space_* mutex]
Signed-off-by: KONRAD Frederic <fred.konrad@greensocs.com>
[EGC: fixed iothread lock for cpu-exec IRQ handling]
Signed-off-by: Emilio G. Cota <cota@braap.org>
[AJB: -smp single-threaded fix, clean commit msg, BQL fixes]
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Reviewed-by: Richard Henderson <rth@twiddle.net>
Reviewed-by: Pranith Kumar <bobby.prani@gmail.com>
[PM: target-arm changes]
Acked-by: Peter Maydell <peter.maydell@linaro.org>

5 files changed, 24 insertions, 3 deletions

diff --git a/hw/core/irq.c b/hw/core/irq.c
index 49ff2e6..b98d1d6 100644
--- a/hw/core/irq.c
+++ b/hw/core/irq.c
@@ -22,6 +22,7 @@
  * THE SOFTWARE.
  */
 #include "qemu/osdep.h"
+#include "qemu/main-loop.h"
 #include "qemu-common.h"
 #include "hw/irq.h"
 #include "qom/object.h"
diff --git a/hw/i386/kvmvapic.c b/hw/i386/kvmvapic.c
index 7135633..82a4955 100644
--- a/hw/i386/kvmvapic.c
+++ b/hw/i386/kvmvapic.c
@@ -457,8 +457,8 @@ static void patch_instruction(VAPICROMState *s, X86CPU *cpu, target_ulong ip)
     resume_all_vcpus();
 
     if (!kvm_enabled()) {
-        /* tb_lock will be reset when cpu_loop_exit_noexc longjmps
-         * back into the cpu_exec loop. */
+        /* Both tb_lock and iothread_mutex will be reset when
+         *  longjmps back into the cpu_exec loop. */
         tb_lock();
         tb_gen_code(cs, current_pc, current_cs_base, current_flags, 1);
         cpu_loop_exit_noexc(cs);
diff --git a/hw/intc/arm_gicv3_cpuif.c b/hw/intc/arm_gicv3_cpuif.c
index c25ee03..f775aba 100644
--- a/hw/intc/arm_gicv3_cpuif.c
+++ b/hw/intc/arm_gicv3_cpuif.c
@@ -14,6 +14,7 @@
 
 #include "qemu/osdep.h"
 #include "qemu/bitops.h"
+#include "qemu/main-loop.h"
 #include "trace.h"
 #include "gicv3_internal.h"
 #include "cpu.h"
@@ -733,6 +734,8 @@ void gicv3_cpuif_update(GICv3CPUState *cs)
     ARMCPU *cpu = ARM_CPU(cs->cpu);
     CPUARMState *env = &cpu->env;
 
+    g_assert(qemu_mutex_iothread_locked());
+
     trace_gicv3_cpuif_update(gicv3_redist_affid(cs), cs->hppi.irq,
                              cs->hppi.grp, cs->hppi.prio);
 
diff --git a/hw/ppc/ppc.c b/hw/ppc/ppc.c
index d171e60..5f93083 100644
--- a/hw/ppc/ppc.c
+++ b/hw/ppc/ppc.c
@@ -62,7 +62,16 @@ void ppc_set_irq(PowerPCCPU *cpu, int n_IRQ, int level)
 {
     CPUState *cs = CPU(cpu);
     CPUPPCState *env = &cpu->env;
-    unsigned int old_pending = env->pending_interrupts;
+    unsigned int old_pending;
+    bool locked = false;
+
+    /* We may already have the BQL if coming from the reset path */
+    if (!qemu_mutex_iothread_locked()) {
+        locked = true;
+        qemu_mutex_lock_iothread();
+    }
+
+    old_pending = env->pending_interrupts;
 
     if (level) {
         env->pending_interrupts |= 1 << n_IRQ;
@@ -80,9 +89,14 @@ void ppc_set_irq(PowerPCCPU *cpu, int n_IRQ, int level)
 #endif
     }
 
+
     LOG_IRQ("%s: %p n_IRQ %d level %d => pending %08" PRIx32
                 "req %08x\n", __func__, env, n_IRQ, level,
                 env->pending_interrupts, CPU(cpu)->interrupt_request);
+
+    if (locked) {
+        qemu_mutex_unlock_iothread();
+    }
 }
 
 /* PowerPC 6xx / 7xx internal IRQ controller */
diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c
index e465d7a..b1e374f 100644
--- a/hw/ppc/spapr.c
+++ b/hw/ppc/spapr.c
@@ -1010,6 +1010,9 @@ static void emulate_spapr_hypercall(PPCVirtualHypervisor *vhyp,
 {
     CPUPPCState *env = &cpu->env;
 
+    /* The TCG path should also be holding the BQL at this point */
+    g_assert(qemu_mutex_iothread_locked());
+
     if (msr_pr) {
         hcall_dprintf("Hypercall made with MSR[PR]=1\n");
         env->gpr[3] = H_PRIVILEGE;