Instead of using test_bit() which is an atomic operation and limits
the compiler's choices to do optimization, use logical ANDs with
bitmasks where possible.

The possible candidates have been detected by searching definitions
of bitmasks in the form:

#define MASK  1 << _MASK

On x86 the resulting code is slightly smaller (about 2 bytes for each
case, checked via disassembly in few examples).

I'm quite sure I didn't replace a test_bit() call required to be
atomic, but I'd be grateful for a thorough review especially in the
scheduler.


Juergen Gross (5):
  xen: use masking operation instead of test_bit for RTDS bits
  xen: use masking operation instead of test_bit for CSFLAG bits
  xen: use masking operation instead of test_bit for VGCF bits
  xen: use masking operation instead of test_bit for VPF bits
  xen: use masking operation instead of test_bit for MCSF bits

 xen/arch/x86/domain.c           | 12 ++++++------
 xen/arch/x86/domctl.c           |  2 +-
 xen/arch/x86/hvm/hvm.c          |  4 ++--
 xen/arch/x86/hvm/vpt.c          |  2 +-
 xen/arch/x86/x86_64/compat/mm.c |  4 ++--
 xen/common/domain.c             |  4 ++--
 xen/common/domctl.c             |  8 ++++----
 xen/common/multicall.c          |  2 +-
 xen/common/sched_credit2.c      | 16 ++++++++--------
 xen/common/sched_rt.c           |  4 ++--
 xen/common/schedule.c           | 16 ++++++++--------
 11 files changed, 37 insertions(+), 37 deletions(-)

-- 
2.1.4


_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
http://lists.xen.org/xen-devel

Reply via email to