[PATCH] locking: Generic ticket lock

[Peter Zijlstra]

On Thu, Oct 21, 2021 at 03:05:15PM +0200, Peter Zijlstra wrote:
> 
> There's currently a number of architectures that want/have graduated
> from test-and-set locks and are looking at qspinlock.
> 
> *HOWEVER* qspinlock is very complicated and requires a lot of an
> architecture to actually work correctly. Specifically it requires
> forward progress between a fair number of atomic primitives, including
> an xchg16 operation, which I've seen a fair number of fundamentally
> broken implementations of in the tree (specifically for qspinlock no
> less).
> 
> The benefit of qspinlock over ticket lock is also non-obvious, esp.
> at low contention (the vast majority of cases in the kernel), and it
> takes a fairly large number of CPUs (typically also NUMA) to make
> qspinlock beat ticket locks.
> 
> Esp. things like ARM64's WFE can move the balance a lot in favour of
> simpler locks by reducing the cacheline pressure due to waiters (see
> their smp_cond_load_acquire() implementation for details).
> 
> Unless you've audited qspinlock for your architecture and found it
> sound *and* can show actual benefit, simpler is better.
> 
> Therefore provide ticket locks, which depend on a single atomic
> operation (fetch_add) while still providing fairness.
> 
> Signed-off-by: Peter Zijlstra (Intel) <peterz at infradead.org>
> ---
>  include/asm-generic/qspinlock.h         |   30 +++++++++
>  include/asm-generic/ticket_lock_types.h |   11 +++
>  include/asm-generic/ticket_lock.h       |   97 ++++++++++++++++++++++++++++++++
>  3 files changed, 138 insertions(+)

A few notes...

> + * It relies on smp_store_release() + atomic_*_acquire() to be RCsc (or no
> + * weaker than RCtso if you're Power, also see smp_mb__after_unlock_lock()),

This should hold true to RISC-V in its current form, AFAICT
atomic_fetch_add ends up using AMOADD, and therefore the argument made
in the unlock+lock thread [1], gives that this results in RW,RW
ordering.

[1] https://lore.kernel.org/lkml/5412ab37-2979-5717-4951-6a61366df0f2@nvidia.com/


I've compile tested on openrisc/simple_smp_defconfig using the below.

--- a/arch/openrisc/Kconfig
+++ b/arch/openrisc/Kconfig
@@ -30,7 +30,6 @@ config OPENRISC
 	select HAVE_DEBUG_STACKOVERFLOW
 	select OR1K_PIC
 	select CPU_NO_EFFICIENT_FFS if !OPENRISC_HAVE_INST_FF1
-	select ARCH_USE_QUEUED_SPINLOCKS
 	select ARCH_USE_QUEUED_RWLOCKS
 	select OMPIC if SMP
 	select ARCH_WANT_FRAME_POINTERS
--- a/arch/openrisc/include/asm/Kbuild
+++ b/arch/openrisc/include/asm/Kbuild
@@ -1,9 +1,8 @@
 # SPDX-License-Identifier: GPL-2.0
 generic-y += extable.h
 generic-y += kvm_para.h
-generic-y += mcs_spinlock.h
-generic-y += qspinlock_types.h
-generic-y += qspinlock.h
+generic-y += ticket_lock_types.h
+generic-y += ticket_lock.h
 generic-y += qrwlock_types.h
 generic-y += qrwlock.h
 generic-y += user.h
--- a/arch/openrisc/include/asm/spinlock.h
+++ b/arch/openrisc/include/asm/spinlock.h
@@ -15,7 +15,7 @@
 #ifndef __ASM_OPENRISC_SPINLOCK_H
 #define __ASM_OPENRISC_SPINLOCK_H
 
-#include <asm/qspinlock.h>
+#include <asm/ticket_lock.h>
 
 #include <asm/qrwlock.h>
 
--- a/arch/openrisc/include/asm/spinlock_types.h
+++ b/arch/openrisc/include/asm/spinlock_types.h
@@ -1,7 +1,7 @@
 #ifndef _ASM_OPENRISC_SPINLOCK_TYPES_H
 #define _ASM_OPENRISC_SPINLOCK_TYPES_H
 
-#include <asm/qspinlock_types.h>
+#include <asm/ticket_lock_types.h>
 #include <asm/qrwlock_types.h>
 
 #endif /* _ASM_OPENRISC_SPINLOCK_TYPES_H */