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>

1 files changed, 21 insertions, 2 deletions

diff --git a/cpu-exec.c b/cpu-exec.c
index 06a6b25564..1bd3d72002 100644
--- a/cpu-exec.c
+++ b/cpu-exec.c
@@ -29,6 +29,7 @@
 #include "qemu/rcu.h"
 #include "exec/tb-hash.h"
 #include "exec/log.h"
+#include "qemu/main-loop.h"
 #if defined(TARGET_I386) && !defined(CONFIG_USER_ONLY)
 #include "hw/i386/apic.h"
 #endif
@@ -388,8 +389,10 @@ static inline bool cpu_handle_halt(CPUState *cpu)
         if ((cpu->interrupt_request & CPU_INTERRUPT_POLL)
             && replay_interrupt()) {
             X86CPU *x86_cpu = X86_CPU(cpu);
+            qemu_mutex_lock_iothread();
             apic_poll_irq(x86_cpu->apic_state);
             cpu_reset_interrupt(cpu, CPU_INTERRUPT_POLL);
+            qemu_mutex_unlock_iothread();
         }
 #endif
         if (!cpu_has_work(cpu)) {
@@ -443,7 +446,9 @@ static inline bool cpu_handle_exception(CPUState *cpu, int *ret)
 #else
             if (replay_exception()) {
                 CPUClass *cc = CPU_GET_CLASS(cpu);
+                qemu_mutex_lock_iothread();
                 cc->do_interrupt(cpu);
+                qemu_mutex_unlock_iothread();
                 cpu->exception_index = -1;
             } else if (!replay_has_interrupt()) {
                 /* give a chance to iothread in replay mode */
@@ -469,9 +474,11 @@ static inline bool cpu_handle_interrupt(CPUState *cpu,
                                         TranslationBlock **last_tb)
 {
     CPUClass *cc = CPU_GET_CLASS(cpu);
-    int interrupt_request = cpu->interrupt_request;
 
-    if (unlikely(interrupt_request)) {
+    if (unlikely(atomic_read(&cpu->interrupt_request))) {
+        int interrupt_request;
+        qemu_mutex_lock_iothread();
+        interrupt_request = cpu->interrupt_request;
         if (unlikely(cpu->singlestep_enabled & SSTEP_NOIRQ)) {
             /* Mask out external interrupts for this step. */
             interrupt_request &= ~CPU_INTERRUPT_SSTEP_MASK;
@@ -479,6 +486,7 @@ static inline bool cpu_handle_interrupt(CPUState *cpu,
         if (interrupt_request & CPU_INTERRUPT_DEBUG) {
             cpu->interrupt_request &= ~CPU_INTERRUPT_DEBUG;
             cpu->exception_index = EXCP_DEBUG;
+            qemu_mutex_unlock_iothread();
             return true;
         }
         if (replay_mode == REPLAY_MODE_PLAY && !replay_has_interrupt()) {
@@ -488,6 +496,7 @@ static inline bool cpu_handle_interrupt(CPUState *cpu,
             cpu->interrupt_request &= ~CPU_INTERRUPT_HALT;
             cpu->halted = 1;
             cpu->exception_index = EXCP_HLT;
+            qemu_mutex_unlock_iothread();
             return true;
         }
 #if defined(TARGET_I386)
@@ -498,12 +507,14 @@ static inline bool cpu_handle_interrupt(CPUState *cpu,
             cpu_svm_check_intercept_param(env, SVM_EXIT_INIT, 0, 0);
             do_cpu_init(x86_cpu);
             cpu->exception_index = EXCP_HALTED;
+            qemu_mutex_unlock_iothread();
             return true;
         }
 #else
         else if (interrupt_request & CPU_INTERRUPT_RESET) {
             replay_interrupt();
             cpu_reset(cpu);
+            qemu_mutex_unlock_iothread();
             return true;
         }
 #endif
@@ -526,7 +537,12 @@ static inline bool cpu_handle_interrupt(CPUState *cpu,
                the program flow was changed */
             *last_tb = NULL;
         }
+
+        /* If we exit via cpu_loop_exit/longjmp it is reset in cpu_exec */
+        qemu_mutex_unlock_iothread();
     }
+
+
     if (unlikely(atomic_read(&cpu->exit_request) || replay_has_interrupt())) {
         atomic_set(&cpu->exit_request, 0);
         cpu->exception_index = EXCP_INTERRUPT;
@@ -643,6 +659,9 @@ int cpu_exec(CPUState *cpu)
 #endif /* buggy compiler */
         cpu->can_do_io = 1;
         tb_lock_reset();
+        if (qemu_mutex_iothread_locked()) {
+            qemu_mutex_unlock_iothread();
+        }
     }
 
     /* if an exception is pending, we execute it here */