[PATCH v4 0/5] sparc64: Optimize fls and __fls

From: Vijay Kumar
Date: Wed Oct 11 2017 - 14:51:33 EST


SPARC provides lzcnt instruction (with VIS3) which can be used to
optimize fls, __fls and fls64 functions. For the systems that supports
lzcnt instruction, we now do boot time patching to use sparc
optimized fls, __fls and fls64 functions.

v3->v4:
- Fixed a typo.
v2->v3:
- Using ENTRY(), ENDPROC() for assembler functions.
- Removed BITS_PER_LONG from __fls.
- Using generic fls64().
- Replaced lzcnt instruction with .word directive.
v1->v2:
- Fixed delay slot issue.

Vijay Kumar (5):
sparc64: Define SPARC default fls function
sparc64: Define SPARC default __fls function
sparc64: SPARC optimized fls function
sparc64: SPARC optimized __fls function
sparc64: Use sparc optimized fls and __fls for T4 and above

arch/sparc/include/asm/bitops_64.h | 5 ++-
arch/sparc/kernel/head_64.S | 2 +
arch/sparc/lib/Makefile | 3 ++
arch/sparc/lib/NG4fls.S | 30 ++++++++++++++++
arch/sparc/lib/NG4patch.S | 9 +++++
arch/sparc/lib/fls.S | 67 ++++++++++++++++++++++++++++++++++++
arch/sparc/lib/fls64.S | 61 ++++++++++++++++++++++++++++++++
7 files changed, 175 insertions(+), 2 deletions(-)
create mode 100644 arch/sparc/lib/NG4fls.S
create mode 100644 arch/sparc/lib/fls.S
create mode 100644 arch/sparc/lib/fls64.S