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, 20 insertions, 1 deletions

diff --git a/cputlb.c b/cputlb.c
index 6c39927455..1cc9d9da51 100644
--- a/cputlb.c
+++ b/cputlb.c
@@ -18,6 +18,7 @@
  */
 
 #include "qemu/osdep.h"
+#include "qemu/main-loop.h"
 #include "cpu.h"
 #include "exec/exec-all.h"
 #include "exec/memory.h"
@@ -495,6 +496,7 @@ static uint64_t io_readx(CPUArchState *env, CPUIOTLBEntry *iotlbentry,
     hwaddr physaddr = iotlbentry->addr;
     MemoryRegion *mr = iotlb_to_region(cpu, physaddr, iotlbentry->attrs);
     uint64_t val;
+    bool locked = false;
 
     physaddr = (physaddr & TARGET_PAGE_MASK) + addr;
     cpu->mem_io_pc = retaddr;
@@ -503,7 +505,16 @@ static uint64_t io_readx(CPUArchState *env, CPUIOTLBEntry *iotlbentry,
     }
 
     cpu->mem_io_vaddr = addr;
+
+    if (mr->global_locking) {
+        qemu_mutex_lock_iothread();
+        locked = true;
+    }
     memory_region_dispatch_read(mr, physaddr, &val, size, iotlbentry->attrs);
+    if (locked) {
+        qemu_mutex_unlock_iothread();
+    }
+
     return val;
 }
 
@@ -514,15 +525,23 @@ static void io_writex(CPUArchState *env, CPUIOTLBEntry *iotlbentry,
     CPUState *cpu = ENV_GET_CPU(env);
     hwaddr physaddr = iotlbentry->addr;
     MemoryRegion *mr = iotlb_to_region(cpu, physaddr, iotlbentry->attrs);
+    bool locked = false;
 
     physaddr = (physaddr & TARGET_PAGE_MASK) + addr;
     if (mr != &io_mem_rom && mr != &io_mem_notdirty && !cpu->can_do_io) {
         cpu_io_recompile(cpu, retaddr);
     }
-
     cpu->mem_io_vaddr = addr;
     cpu->mem_io_pc = retaddr;
+
+    if (mr->global_locking) {
+        qemu_mutex_lock_iothread();
+        locked = true;
+    }
     memory_region_dispatch_write(mr, physaddr, val, size, iotlbentry->attrs);
+    if (locked) {
+        qemu_mutex_unlock_iothread();
+    }
 }
 
 /* Return true if ADDR is present in the victim tlb, and has been copied