lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite for Android: free password hash cracker in your pocket
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20210419173543.GC31045@willie-the-truck>
Date:   Mon, 19 Apr 2021 18:35:43 +0100
From:   Will Deacon <will@...nel.org>
To:     Peter Zijlstra <peterz@...radead.org>
Cc:     Guo Ren <guoren@...nel.org>,
        Christoph Müllner <christophm30@...il.com>,
        Palmer Dabbelt <palmer@...belt.com>,
        Anup Patel <anup@...infault.org>,
        linux-riscv <linux-riscv@...ts.infradead.org>,
        Linux Kernel Mailing List <linux-kernel@...r.kernel.org>,
        Guo Ren <guoren@...ux.alibaba.com>,
        Catalin Marinas <catalin.marinas@....com>,
        Will Deacon <will.deacon@....com>,
        Arnd Bergmann <arnd@...db.de>, jonas@...thpole.se,
        stefan.kristiansson@...nalahti.fi, shorne@...il.com
Subject: Re: [RFC][PATCH] locking: Generic ticket-lock

On Wed, Apr 14, 2021 at 12:16:38PM +0200, Peter Zijlstra wrote:
> How's this then? Compile tested only on openrisc/simple_smp_defconfig.
> 
> diff --git a/include/asm-generic/qspinlock.h b/include/asm-generic/qspinlock.h
> index d74b13825501..a7a1296b0b4d 100644
> --- a/include/asm-generic/qspinlock.h
> +++ b/include/asm-generic/qspinlock.h
> @@ -2,6 +2,36 @@
>  /*
>   * Queued spinlock
>   *
> + * A 'generic' spinlock implementation that is based on MCS locks. An
> + * architecture that's looking for a 'generic' spinlock, please first consider
> + * ticket-lock.h and only come looking here when you've considered all the
> + * constraints below and can show your hardware does actually perform better
> + * with qspinlock.
> + *
> + *
> + * It relies on atomic_*_release()/atomic_*_acquire() to be RCsc (or no weaker
> + * than RCtso if you're power), where regular code only expects atomic_t to be
> + * RCpc.

Maybe capitalise "Power" to make it clear this about the architecture?

> + *
> + * It relies on a far greater (compared to ticket-lock.h) set of atomic
> + * operations to behave well together, please audit them carefully to ensure
> + * they all have forward progress. Many atomic operations may default to
> + * cmpxchg() loops which will not have good forward progress properties on
> + * LL/SC architectures.
> + *
> + * One notable example is atomic_fetch_or_acquire(), which x86 cannot (cheaply)
> + * do. Carefully read the patches that introduced queued_fetch_set_pending_acquire().
> + *
> + * It also heavily relies on mixed size atomic operations, in specific it
> + * requires architectures to have xchg16; something which many LL/SC
> + * architectures need to implement as a 32bit and+or in order to satisfy the
> + * forward progress guarantees mentioned above.
> + *
> + * Further reading on mixed size atomics that might be relevant:
> + *
> + *   http://www.cl.cam.ac.uk/~pes20/popl17/mixed-size.pdf
> + *
> + *
>   * (C) Copyright 2013-2015 Hewlett-Packard Development Company, L.P.
>   * (C) Copyright 2015 Hewlett-Packard Enterprise Development LP
>   *
> diff --git a/include/asm-generic/ticket-lock-types.h b/include/asm-generic/ticket-lock-types.h
> new file mode 100644
> index 000000000000..829759aedda8
> --- /dev/null
> +++ b/include/asm-generic/ticket-lock-types.h
> @@ -0,0 +1,11 @@
> +/* SPDX-License-Identifier: GPL-2.0 */
> +
> +#ifndef __ASM_GENERIC_TICKET_LOCK_TYPES_H
> +#define __ASM_GENERIC_TICKET_LOCK_TYPES_H
> +
> +#include <linux/types.h>
> +typedef atomic_t arch_spinlock_t;
> +
> +#define __ARCH_SPIN_LOCK_UNLOCKED	ATOMIC_INIT(0)
> +
> +#endif /* __ASM_GENERIC_TICKET_LOCK_TYPES_H */
> diff --git a/include/asm-generic/ticket-lock.h b/include/asm-generic/ticket-lock.h
> new file mode 100644
> index 000000000000..3f0d53e21a37
> --- /dev/null
> +++ b/include/asm-generic/ticket-lock.h
> @@ -0,0 +1,86 @@
> +/* SPDX-License-Identifier: GPL-2.0 */
> +
> +/*
> + * 'Generic' ticket-lock implementation.
> + *
> + * It relies on atomic_fetch_add() having well defined forward progress
> + * guarantees under contention. If your architecture cannot provide this, stick
> + * to a test-and-set lock.
> + *
> + * It also relies on atomic_fetch_add() being safe vs smp_store_release() on a
> + * sub-word of the value. This is generally true for anything LL/SC although
> + * you'd be hard pressed to find anything useful in architecture specifications
> + * about this. If your architecture cannot do this you might be better off with
> + * a test-and-set.
> + *
> + * It further assumes atomic_*_release() + atomic_*_acquire() is RCpc and hence
> + * uses atomic_fetch_add() which is SC to create an RCsc lock.
> + *
> + * The implementation uses smp_cond_load_acquire() to spin, so if the
> + * architecture has WFE like instructions to sleep instead of poll for word
> + * modifications be sure to implement that (see ARM64 for example).
> + *
> + */
> +
> +#ifndef __ASM_GENERIC_TICKET_LOCK_H
> +#define __ASM_GENERIC_TICKET_LOCK_H
> +
> +#include <linux/atomic.h>
> +#include <asm/ticket-lock-types.h>
> +
> +static __always_inline void ticket_lock(arch_spinlock_t *lock)
> +{
> +	u32 val = atomic_fetch_add(1<<16, lock); /* SC, gives us RCsc */

I hate to say it, but smp_mb__after_unlock_lock() would make the intention
a lot clearer here :( That is, the implementation as you have it gives
stronger than RCsc semantics for all architectures.

Alternatively, we could write the thing RCpc and throw an smp_mb() into
the unlock path if CONFIG_ARCH_WEAK_RELEASE_ACQUIRE.

> +	u16 ticket = val >> 16;
> +
> +	if (ticket == (u16)val)
> +		return;
> +
> +	atomic_cond_read_acquire(lock, ticket == (u16)VAL);
> +}
> +
> +static __always_inline bool ticket_trylock(arch_spinlock_t *lock)
> +{
> +	u32 old = atomic_read(lock);
> +
> +	if ((old >> 16) != (old & 0xffff))
> +		return false;
> +
> +	return atomic_try_cmpxchg(lock, &old, old + (1<<16)); /* SC, for RCsc */
> +}
> +
> +static __always_inline void ticket_unlock(arch_spinlock_t *lock)
> +{
> +	u16 *ptr = (u16 *)lock + __is_defined(__BIG_ENDIAN);
> +	u32 val = atomic_read(lock);
> +
> +	smp_store_release(ptr, (u16)val + 1);
> +}
> +
> +static __always_inline int ticket_is_locked(arch_spinlock_t *lock)
> +{
> +	u32 val = atomic_read(lock);
> +
> +	return ((val >> 16) != (val & 0xffff));
> +}
> +
> +static __always_inline int ticket_is_contended(arch_spinlock_t *lock)
> +{
> +	u32 val = atomic_read(lock);
> +
> +	return (s16)((val >> 16) - (val & 0xffff)) > 1;

Does this go wonky if the tickets are in the process of wrapping around?

Will

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ