Date: Fri, 25 Jun 1999 16:52:03 +0000 (GMT) From: Terry Lambert <tlambert@primenet.com> To: mike@smith.net.au (Mike Smith) Cc: julian@whistle.com, smp@FreeBSD.ORG Subject: Re: Call to arms..-SMP (fwd) Message-ID: <199906251652.JAA25770@usr01.primenet.com> In-Reply-To: <199906250714.AAA00587@dingo.cdrom.com> from "Mike Smith" at Jun 25, 99 00:14:13 am
next in thread | previous in thread | raw e-mail | index | archive | help
> > Not much assembly is need. All we need to do is to make SYSCALL_LOCK a nop, > > and handle the locking in syscall() the C function. > > Don't even do it here; put the lock acquisitions/releases in the > syscall implementation functions themselves. Last time I looked, portions of the trap code and the signal trampoline were not process reentrant. This should not be done until they are, since a user space call conversion scheduler or use of async system calls (e.g. aioread) that occurred simultaneously with a subsequent call could result in a kernel stack corruption of the already pending async call. Terry Lambert terry@lambert.org --- Any opinions in this posting are my own and not those of my present or previous employers. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?199906251652.JAA25770>