lkml.org 
[lkml]   [2014]   [Aug]   [29]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
Date
From
Subject[PATCH 3/4] x86, fpu: irq_fpu_usable: always return true if use_eager_fpu()
According to the comment and the changelog in 5187b28f "x86: Allow FPU
to be used at interrupt time even with eagerfpu", the __thread_has_fpu()
check was added to avoid the nested kernel_fpu_begin(). Now that we have
in_kernel_fpu we can remove this check and always return true.

__thread_has_fpu() can be false even if use_eager_fpu(), but this case
doesn't differ from !use_eager_fpu() case except we should not worry
about X86_CR0_TS, __kernel_fpu_begin/end will not touch this bit. And I
still think that "use_eager_fpu && (!__thread_has_fpu || !used_math)"
special cases should die, but this is off-topic right now.

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
---
arch/x86/kernel/i387.c | 5 ++---
1 files changed, 2 insertions(+), 3 deletions(-)

diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c
index 19dd36d..9fb2899 100644
--- a/arch/x86/kernel/i387.c
+++ b/arch/x86/kernel/i387.c
@@ -30,8 +30,7 @@ static DEFINE_PER_CPU(bool, in_kernel_fpu);
* be set (so that the clts/stts pair does nothing that is
* visible in the interrupted kernel thread).
*
- * Except for the eagerfpu case when we return 1 unless we've already
- * been eager and saved the state in kernel_fpu_begin().
+ * Except for the eagerfpu case when we return 1.
*/
static inline bool interrupted_kernel_fpu_idle(void)
{
@@ -39,7 +38,7 @@ static inline bool interrupted_kernel_fpu_idle(void)
return false;

if (use_eager_fpu())
- return __thread_has_fpu(current);
+ return true;

return !__thread_has_fpu(current) &&
(read_cr0() & X86_CR0_TS);
--
1.5.5.1



\
 
 \ /
  Last update: 2014-08-29 20:41    [W:0.130 / U:0.572 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site