From owner-freebsd-hackers Sat May 29 14:20:32 1999 Delivered-To: freebsd-hackers@freebsd.org Received: from iquest3.iquest.net (iquest3.iquest.net [209.43.20.203]) by hub.freebsd.org (Postfix) with SMTP id 4161614C42 for ; Sat, 29 May 1999 14:20:21 -0700 (PDT) (envelope-from toor@sd5.mailbank.com) Received: (qmail 18304 invoked from network); 29 May 1999 21:20:19 -0000 Received: from dyson.iquest.net (HELO y.dyson.net) (198.70.144.127) by iquest3.iquest.net with SMTP; 29 May 1999 21:20:19 -0000 Received: (from toor@localhost) by y.dyson.net (8.9.3/8.9.1) id QAA84464; Sat, 29 May 1999 16:20:17 -0500 (EST) Message-Id: <199905292120.QAA84464@y.dyson.net> Subject: Re: Possible race in pipe device driver, esp on multi-cpu machines. In-Reply-To: <199905290846.BAA29926@apollo.backplane.com> from Matthew Dillon at "May 29, 99 01:46:44 am" To: dillon@apollo.backplane.com (Matthew Dillon) Date: Sat, 29 May 1999 16:20:16 -0500 (EST) Cc: hackers@FreeBSD.ORG From: "John S. Dyson" Reply-To: dyson@iquest.net X-Mailer: ELM [version 2.4ME+ PL38 (25)] MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-freebsd-hackers@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG Matthew Dillon said: > > We are attempting to reproduce the problem with a smaller dataset, but > if anyone is hot on the pipe code in the kernel and can give it a once-over > we may be able to find the bug more quickly. > After a quick code inspection (and I really don't remember the details much anymore), it seems that there is a possibility for parts of the state of a pipe to be grabbed before certain locking operations (e.g. pipelock), and that state might change. This could be worse in a multi-writer or multi-reader situation. Just a hint. -- John | Never try to teach a pig to sing, dyson@iquest.net | it makes one look stupid jdyson@nc.com | and it irritates the pig. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hackers" in the body of the message