linux-kernel - Re: [PATCH v2 2/2] locking/rwsem: Make reader optimistic spinning optional

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: <20230904151058.GB25717@noisy.programming.kicks-ass.net>
Date:   Mon, 4 Sep 2023 17:10:58 +0200
From:   Peter Zijlstra <peterz@...radead.org>
To:     Bongkyu Kim <bongkyu7.kim@...sung.com>
Cc:     mingo@...hat.com, will@...nel.org, longman@...hat.com,
        boqun.feng@...il.com, linux-kernel@...r.kernel.org,
        gregkh@...uxfoundation.org, kernel test robot <lkp@...el.com>
Subject: Re: [PATCH v2 2/2] locking/rwsem: Make reader optimistic spinning
 optional

On Fri, Sep 01, 2023 at 10:07:04AM +0900, Bongkyu Kim wrote:

> diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c
> index 9c0462d515c1..47c467880af5 100644
> --- a/kernel/locking/rwsem.c
> +++ b/kernel/locking/rwsem.c
> @@ -117,6 +117,17 @@
>  # define DEBUG_RWSEMS_WARN_ON(c, sem)
>  #endif
>  
> +static bool __ro_after_init rwsem_opt_rspin;
> +
> +static int __init opt_rspin(char *str)
> +{
> +        rwsem_opt_rspin = true;
> +
> +        return 0;
> +}
> +
> +early_param("rwsem.opt_rspin", opt_rspin);
> +
>  /*
>   * On 64-bit architectures, the bit definitions of the count are:
>   *
> @@ -1083,7 +1094,7 @@ static inline bool rwsem_reader_phase_trylock(struct rw_semaphore *sem,
>  	return false;
>  }
>  
> -static inline bool rwsem_no_spinners(sem)
> +static inline bool rwsem_no_spinners(struct rw_semaphore *sem)
>  {
>  	return false;
>  }
> @@ -1157,6 +1168,9 @@ rwsem_down_read_slowpath(struct rw_semaphore *sem, long count, unsigned int stat
>  		return sem;
>  	}
>  
> +	if (!IS_ENABLED(CONFIG_RWSEM_SPIN_ON_OWNER) || !rwsem_opt_rspin)
> +		goto queue;
> +

At the very least this should be a static_branch(), but I still very
much want an answer on how all this interacts with the handoff stuff.