Re: [PATCH 2/3] x86, fpu: don't abuse ->has_fpu in __kernel_fpu_{begin,end}()

[Rik van Riel <riel@redhat.com>]

-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1

On 01/15/2015 02:20 PM, Oleg Nesterov wrote:
> Now that we have in_kernel_fpu we can remove
> __thread_clear_has_fpu() in __kernel_fpu_begin(). And this allows
> to replace the asymmetrical and nontrivial use_eager_fpu +
> tsk_used_math check in kernel_fpu_end() with the same
> __thread_has_fpu() check.
> 
> The logic becomes really simple; if _begin() does save() then
> _end() needs restore(), this is controlled by __thread_has_fpu().
> Otherwise they do clts/stts unless use_eager_fpu().
> 
> Not only this makes begin/end symmetrical and imo more
> understandable, potentially this allows to change irq_fpu_usable()
> to avoid all other checks except "in_kernel_fpu".
> 
> Also, with this patch __kernel_fpu_end() does
> restore_fpu_checking() and WARNs if it fails instead of
> math_state_restore(). I think this looks better because we no
> longer need __thread_fpu_begin(), and it would be better to report
> the failure in this case.
> 
> Signed-off-by: Oleg Nesterov <oleg@redhat.com> --- 
> arch/x86/kernel/i387.c |   19 ++++++------------- 1 files changed,
> 6 insertions(+), 13 deletions(-)
> 
> diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c index
> a815723..12088a3 100644 --- a/arch/x86/kernel/i387.c +++
> b/arch/x86/kernel/i387.c @@ -81,9 +81,7 @@ void
> __kernel_fpu_begin(void) this_cpu_write(in_kernel_fpu, true);
> 
> if (__thread_has_fpu(me)) { -		__thread_clear_has_fpu(me);

I will put that line back in the patch series that defers the
loading of FPU state until the switch to user space, but I
guess we can go either way for now...

> __save_init_fpu(me); -		/* We do 'stts()' in __kernel_fpu_end() */ 
> } else if (!use_eager_fpu()) { this_cpu_write(fpu_owner_task,
> NULL); clts(); @@ -93,17 +91,12 @@
> EXPORT_SYMBOL(__kernel_fpu_begin);
> 
> void __kernel_fpu_end(void) { -	if (use_eager_fpu()) { -		/* -		 *
> For eager fpu, most the time, tsk_used_math() is true. -		 *
> Restore the user math as we are done with the kernel usage. -		 *
> At few instances during thread exit, signal handling etc, -		 *
> tsk_used_math() is false. Those few places will take proper -		 *
> actions, so we don't need to restore the math here. -		 */ -		if
> (likely(tsk_used_math(current))) -			math_state_restore(); -	} else
> { +	struct task_struct *me = current; + +	if (__thread_has_fpu(me))
> { +		if (WARN_ON(restore_fpu_checking(me))) +			drop_init_fpu(me); 
> +	} else if (!use_eager_fpu()) { stts(); }
> 
> 


- -- 
All rights reversed
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1

iQEcBAEBAgAGBQJUuHb9AAoJEM553pKExN6DOqAIALCVqEtQ9yZEA6G9a4n4wf2r
2FHhz+H1KXUcFSVQp/KeqPq2ZJ4/1rO/omai49m1isXnjmOOLGF4Ur4E0gg6WM5W
cBgN4HYNaFIr0JMWbMfFo7hnwL7BiQLoMwqxJDxi7HQcGoIkFFDIRtezZz75acey
dKhOUz4p6C8EMgOEc1ssa5Vgo011hIfuB6aCS6NRNDJAlYornhzf0bt7HILw4tFj
1IGR+yBpb7AmlWm6EvY4NluQ3M0KjtWErpBMSMCubVMBSa62e7Twv2K9eDLx+dbz
eScoNZiy0aTgMGlN4hfXoSIwbxUkOaBl+6yAMOLn0OEV00OxxRKOAuZdQS0NUsE=
=M7Fz
-----END PGP SIGNATURE-----