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>

4 files changed, 56 insertions, 5 deletions

diff --git a/target/arm/helper.c b/target/arm/helper.c
index 47250bcf16..753a69d40d 100644
--- a/target/arm/helper.c
+++ b/target/arm/helper.c
@@ -6769,6 +6769,12 @@ void arm_cpu_do_interrupt(CPUState *cs)
         arm_cpu_do_interrupt_aarch32(cs);
     }
 
+    /* Hooks may change global state so BQL should be held, also the
+     * BQL needs to be held for any modification of
+     * cs->interrupt_request.
+     */
+    g_assert(qemu_mutex_iothread_locked());
+
     arm_call_el_change_hook(cpu);
 
     if (!kvm_enabled()) {
diff --git a/target/arm/op_helper.c b/target/arm/op_helper.c
index fb366fdc35..5f3e3bdae2 100644
--- a/target/arm/op_helper.c
+++ b/target/arm/op_helper.c
@@ -18,6 +18,7 @@
  */
 #include "qemu/osdep.h"
 #include "qemu/log.h"
+#include "qemu/main-loop.h"
 #include "cpu.h"
 #include "exec/helper-proto.h"
 #include "internals.h"
@@ -487,7 +488,9 @@ void HELPER(cpsr_write_eret)(CPUARMState *env, uint32_t val)
      */
     env->regs[15] &= (env->thumb ? ~1 : ~3);
 
+    qemu_mutex_lock_iothread();
     arm_call_el_change_hook(arm_env_get_cpu(env));
+    qemu_mutex_unlock_iothread();
 }
 
 /* Access to user mode registers from privileged modes.  */
@@ -735,28 +738,58 @@ void HELPER(set_cp_reg)(CPUARMState *env, void *rip, uint32_t value)
 {
     const ARMCPRegInfo *ri = rip;
 
-    ri->writefn(env, ri, value);
+    if (ri->type & ARM_CP_IO) {
+        qemu_mutex_lock_iothread();
+        ri->writefn(env, ri, value);
+        qemu_mutex_unlock_iothread();
+    } else {
+        ri->writefn(env, ri, value);
+    }
 }
 
 uint32_t HELPER(get_cp_reg)(CPUARMState *env, void *rip)
 {
     const ARMCPRegInfo *ri = rip;
+    uint32_t res;
 
-    return ri->readfn(env, ri);
+    if (ri->type & ARM_CP_IO) {
+        qemu_mutex_lock_iothread();
+        res = ri->readfn(env, ri);
+        qemu_mutex_unlock_iothread();
+    } else {
+        res = ri->readfn(env, ri);
+    }
+
+    return res;
 }
 
 void HELPER(set_cp_reg64)(CPUARMState *env, void *rip, uint64_t value)
 {
     const ARMCPRegInfo *ri = rip;
 
-    ri->writefn(env, ri, value);
+    if (ri->type & ARM_CP_IO) {
+        qemu_mutex_lock_iothread();
+        ri->writefn(env, ri, value);
+        qemu_mutex_unlock_iothread();
+    } else {
+        ri->writefn(env, ri, value);
+    }
 }
 
 uint64_t HELPER(get_cp_reg64)(CPUARMState *env, void *rip)
 {
     const ARMCPRegInfo *ri = rip;
+    uint64_t res;
+
+    if (ri->type & ARM_CP_IO) {
+        qemu_mutex_lock_iothread();
+        res = ri->readfn(env, ri);
+        qemu_mutex_unlock_iothread();
+    } else {
+        res = ri->readfn(env, ri);
+    }
 
-    return ri->readfn(env, ri);
+    return res;
 }
 
 void HELPER(msr_i_pstate)(CPUARMState *env, uint32_t op, uint32_t imm)
@@ -989,7 +1022,9 @@ void HELPER(exception_return)(CPUARMState *env)
                       cur_el, new_el, env->pc);
     }
 
+    qemu_mutex_lock_iothread();
     arm_call_el_change_hook(arm_env_get_cpu(env));
+    qemu_mutex_unlock_iothread();
 
     return;
 
diff --git a/target/i386/smm_helper.c b/target/i386/smm_helper.c
index 4dd6a2c544..f051a77c4a 100644
--- a/target/i386/smm_helper.c
+++ b/target/i386/smm_helper.c
@@ -18,6 +18,7 @@
  */
 
 #include "qemu/osdep.h"
+#include "qemu/main-loop.h"
 #include "cpu.h"
 #include "exec/helper-proto.h"
 #include "exec/log.h"
@@ -42,11 +43,14 @@ void helper_rsm(CPUX86State *env)
 #define SMM_REVISION_ID 0x00020000
 #endif
 
+/* Called with iothread lock taken */
 void cpu_smm_update(X86CPU *cpu)
 {
     CPUX86State *env = &cpu->env;
     bool smm_enabled = (env->hflags & HF_SMM_MASK);
 
+    g_assert(qemu_mutex_iothread_locked());
+
     if (cpu->smram) {
         memory_region_set_enabled(cpu->smram, smm_enabled);
     }
@@ -333,7 +337,10 @@ void helper_rsm(CPUX86State *env)
     }
     env->hflags2 &= ~HF2_SMM_INSIDE_NMI_MASK;
     env->hflags &= ~HF_SMM_MASK;
+
+    qemu_mutex_lock_iothread();
     cpu_smm_update(cpu);
+    qemu_mutex_unlock_iothread();
 
     qemu_log_mask(CPU_LOG_INT, "SMM: after RSM\n");
     log_cpu_state_mask(CPU_LOG_INT, CPU(cpu), CPU_DUMP_CCOP);
diff --git a/target/s390x/misc_helper.c b/target/s390x/misc_helper.c
index c9604ea9c7..3cb942e8bb 100644
--- a/target/s390x/misc_helper.c
+++ b/target/s390x/misc_helper.c
@@ -25,6 +25,7 @@
 #include "exec/helper-proto.h"
 #include "sysemu/kvm.h"
 #include "qemu/timer.h"
+#include "qemu/main-loop.h"
 #include "exec/address-spaces.h"
 #ifdef CONFIG_KVM
 #include <linux/kvm.h>
@@ -109,11 +110,13 @@ void program_interrupt(CPUS390XState *env, uint32_t code, int ilen)
 /* SCLP service call */
 uint32_t HELPER(servc)(CPUS390XState *env, uint64_t r1, uint64_t r2)
 {
+    qemu_mutex_lock_iothread();
     int r = sclp_service_call(env, r1, r2);
     if (r < 0) {
         program_interrupt(env, -r, 4);
-        return 0;
+        r = 0;
     }
+    qemu_mutex_unlock_iothread();
     return r;
 }