Re: [Qemu-devel] [RFC PATCH V7 00/19] Multithread TCG.

[Paolo Bonzini]

On 11/08/2015 15:59, Frederic Konrad wrote:
>> - tb_lock usage in tb_find_fast is complicated and introduces the need
>> for other complicated code such as the tb_invalidate callback.  Instead,
>> the tb locking should reuse the cpu-exec.c code for user-mode emulation,
>> with additional locking in the spots identified by Fred.
> 
> The reason for this is that locking around tb_find_fast just kills the
> performance.

Let's make it correct first. :)

>> - the whole signal-based qemu_cpu_kick can just go away.  Just setting
>> tcg_exit_req and exit_request will kick the TCG thread.  The hairy Win32
>> SuspendThread/ResumeThread goes away too.  I suggest doing it now,
>> because proving it unnecessary is easier than proving it correct.
> 
> Just setting tcg_exit_req and exit_request and signal the cpu->halt_cond
> I guess?

Yes.

>> - the big QEMU lock is not taken anywhere for MMIO accesses that require
>> it (i.e. basically all of them)
> Isn't that handled by prepare_mmio_access?

That's not used on the TCG path (which calls
memory_region_dispatch_read/write directly).

Paolo