| From: |
| guoren-AT-kernel.org |
| To: |
| guoren-AT-kernel.org, Anup.Patel-AT-wdc.com |
| Subject: |
| [PATCH v3 0/4] riscv: Add qspinlock/qrwlock |
| Date: |
| Thu, 25 Mar 2021 07:55:33 +0000 |
| Message-ID: |
| <1616658937-82063-1-git-send-email-guoren@kernel.org> |
| Cc: |
| linux-riscv-AT-lists.infradead.org, linux-kernel-AT-vger.kernel.org, linux-csky-AT-vger.kernel.org, linux-arch-AT-vger.kernel.org, tech-unixplatformspec-AT-lists.riscv.org, Guo Ren <guoren-AT-linux.alibaba.com> |
| Archive-link: |
| Article |
From: Guo Ren <guoren@linux.alibaba.com>
Current riscv is still using baby spinlock implementation. It'll cause
fairness and cache line bouncing problems. Many people are involved
and pay the efforts to improve it:
- The first version of patch was made in 2019.1:
https://lore.kernel.org/linux-riscv/20190211043829.30096-...
- The second version was made in 2020.11:
https://lore.kernel.org/linux-riscv/1606225437-22948-2-gi...
- A good discussion at Platform HSC.2021-03-08:
https://drive.google.com/drive/folders/1ooqdnIsYx7XKor5O1...
Hope your comments and Tested-by or Co-developed-by or Reviewed-by ...
Let's kick the qspinlock into riscv right now (Also for the
architectures which doesn't have short atmoic xchg instructions.)
Change V3:
- Fixup short-xchg asm code (slli -> slliw, srli -> srliw)
- Coding convention by Peter Zijlstra's advices
Change V2:
- Coding convention in cmpxchg.h
- Re-implement short xchg
- Remove char & cmpxchg implementations
V1: (by michael)
Guo Ren (3):
riscv: cmpxchg.h: Cleanup unused code
riscv: cmpxchg.h: Merge macros
riscv: cmpxchg.h: Implement xchg for short
Michael Clark (1):
riscv: Convert custom spinlock/rwlock to generic qspinlock/qrwlock
arch/riscv/Kconfig | 2 +
arch/riscv/include/asm/Kbuild | 3 +
arch/riscv/include/asm/cmpxchg.h | 211 ++++++------------------
arch/riscv/include/asm/spinlock.h | 126 +-------------
arch/riscv/include/asm/spinlock_types.h | 15 +-
5 files changed, 58 insertions(+), 299 deletions(-)
--
2.17.1