linux-kernel - Re: [PATCH 3/4] paravirt: add virt_spin

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]

Message-ID: <20170905135506.55drjahteljbatak@hirez.programming.kicks-ass.net>
Date:   Tue, 5 Sep 2017 15:55:06 +0200
From:   Peter Zijlstra <peterz@...radead.org>
To:     Juergen Gross <jgross@...e.com>
Cc:     linux-kernel@...r.kernel.org, xen-devel@...ts.xenproject.org,
        x86@...nel.org, virtualization@...ts.linux-foundation.org,
        jeremy@...p.org, chrisw@...s-sol.org, akataria@...are.com,
        rusty@...tcorp.com.au, boris.ostrovsky@...cle.com, hpa@...or.com,
        tglx@...utronix.de, mingo@...hat.com, longman@...hat.com
Subject: Re: [PATCH 3/4] paravirt: add virt_spin_lock pvops function

On Tue, Sep 05, 2017 at 03:24:43PM +0200, Juergen Gross wrote:
> diff --git a/arch/x86/include/asm/qspinlock.h b/arch/x86/include/asm/qspinlock.h
> index 48a706f641f2..fbd98896385c 100644
> --- a/arch/x86/include/asm/qspinlock.h
> +++ b/arch/x86/include/asm/qspinlock.h
> @@ -17,6 +17,25 @@ static inline void native_queued_spin_unlock(struct qspinlock *lock)
>  	smp_store_release((u8 *)lock, 0);
>  }
>  


Should this not have:

#ifdef CONFIG_PARAVIRT

?

> +static inline bool native_virt_spin_lock(struct qspinlock *lock)
> +{
> +	if (!static_cpu_has(X86_FEATURE_HYPERVISOR))
> +		return false;
> +
> +	/*
> +	 * On hypervisors without PARAVIRT_SPINLOCKS support we fall
> +	 * back to a Test-and-Set spinlock, because fair locks have
> +	 * horrible lock 'holder' preemption issues.
> +	 */
> +
> +	do {
> +		while (atomic_read(&lock->val) != 0)
> +			cpu_relax();
> +	} while (atomic_cmpxchg(&lock->val, 0, _Q_LOCKED_VAL) != 0);
> +
> +	return true;
> +}

#endif

> +
>  #ifdef CONFIG_PARAVIRT_SPINLOCKS
>  extern void native_queued_spin_lock_slowpath(struct qspinlock *lock, u32 val);
>  extern void __pv_init_lock_hash(void);


>  #ifdef CONFIG_PARAVIRT
>  #define virt_spin_lock virt_spin_lock
> +#ifdef CONFIG_PARAVIRT_SPINLOCKS
>  static inline bool virt_spin_lock(struct qspinlock *lock)
>  {
> +	return pv_virt_spin_lock(lock);
> +}
> +#else
> +static inline bool virt_spin_lock(struct qspinlock *lock)
> +{
> +	return native_virt_spin_lock(lock);
>  }
> +#endif /* CONFIG_PARAVIRT_SPINLOCKS */
>  #endif /* CONFIG_PARAVIRT */

Because I think the above only ever uses native_virt_spin_lock() when
PARAVIRT.

> @@ -1381,6 +1382,7 @@ void __init native_smp_prepare_boot_cpu(void)
>  	/* already set me in cpu_online_mask in boot_cpu_init() */
>  	cpumask_set_cpu(me, cpu_callout_mask);
>  	cpu_set_state_online(me);
> +	native_pv_lock_init();
>  }

Aah, this is where that goes.. OK that works too.