Re: Adaptive RW locks

To: Takashi YAMAMOTO <yamt9999%gmail.com@localhost>
Subject: Re: Adaptive RW locks
From: Andrew Doran <ad%netbsd.org@localhost>
Date: Mon, 20 Jan 2020 13:39:10 +0000

Hi,

On Mon, Jan 20, 2020 at 02:18:15PM +0900, Takashi YAMAMOTO wrote:

> >         http://www.netbsd.org/~ad/2020/rwlock.diff
> 
> 
> i guess in rw_downgrade
> newown = (owner & RW_NODEBUG) | RW_SPIN;
> 
> should be
> newown = (owner & (RW_NODEBUG | RW_SPIN));
> 
> as the owner might have failed to record the lock on acquisition.

Right.  I'll fix it and add a comment.  Good catch, thank you.

Andrew

Follow-Ups:
- Re: Adaptive RW locks
  - From: Andrew Doran

References:
- Adaptive RW locks
  - From: Andrew Doran
- Re: Adaptive RW locks
  - From: Takashi YAMAMOTO

Prev by Date: Re: libc.so's vmobjlock / v_interlock
Next by Date: Re: x86 bootstrap features
Previous by Thread: Re: Adaptive RW locks
Next by Thread: Re: Adaptive RW locks
Indexes:

Home | Main Index | Thread Index | Old Index