linux-kernel - Re: [PATCH v2 3/5] locking/qspinlock: Introduce CNA into the slow path of qspinlock

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: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Mon, 1 Apr 2019 11:21:15 +0200
From:   Peter Zijlstra <peterz@...radead.org>
To:     Alex Kogan <alex.kogan@...cle.com>
Cc:     linux@...linux.org.uk, mingo@...hat.com, will.deacon@....com,
        arnd@...db.de, longman@...hat.com, linux-arch@...r.kernel.org,
        linux-arm-kernel@...ts.infradead.org, linux-kernel@...r.kernel.org,
        tglx@...utronix.de, bp@...en8.de, hpa@...or.com, x86@...nel.org,
        steven.sistare@...cle.com, daniel.m.jordan@...cle.com,
        dave.dice@...cle.com, rahul.x.yadav@...cle.com
Subject: Re: [PATCH v2 3/5] locking/qspinlock: Introduce CNA into the slow
 path of qspinlock

On Fri, Mar 29, 2019 at 11:20:04AM -0400, Alex Kogan wrote:
> +static inline void pass_mcs_lock(struct mcs_spinlock *node,
> +				 struct mcs_spinlock *next)
> +{
> +	struct mcs_spinlock *succ = NULL;
> +
> +	succ = find_successor(node);
> +
> +	if (succ) {
> +		arch_mcs_spin_unlock_contended(&succ->locked, node->locked);
> +	} else if (node->locked > 1) {
> +		/*
> +		 * If the secondary queue is not empty, pass the lock
> +		 * to the first node in that queue.
> +		 */
> +		succ = MCS_NODE(node->locked);
> +		succ->tail->next = next;
> +		arch_mcs_spin_unlock_contended(&succ->locked, 1);
> +	} else {
> +		/*
> +		 * Otherwise, pass the lock to the immediate successor
> +		 * in the main queue.
> +		 */
> +		arch_mcs_spin_unlock_contended(&next->locked, 1);
> +	}
> +}

Note that something like:

static inline void
pass_mcs_lock(struct mcs_spinlock *node, struct mcs_spinlock *next)
{
	struct mcs_spinlock *succ = NULL;
	uintptr_t *var = &next->locked;
	uintptr_t val = 1;

	succ = find_successor(node);
	if (succ) {
		var = &succ->locked;
		val = node->locked;
	} else if (node->locked > 1) {
		succ = MCS_NODE(node->locked);
		succ->tail->next = next; /* WRITE_ONCE() !?!? */
		var = &node->locked;
	}

	arch_mcs_spin_unlock_contended(var, val);
}

is shorter and generates much better code if
arch_mcs_spin_unlock_contended() is asm volatile ().