Date: Fri, 14 Jul 2006 12:35:38 -0700 From: Alfred Perlstein <alfred@freebsd.org> To: Alexander Leidinger <netchild@FreeBSD.org> Cc: cvs-src@FreeBSD.org, src-committers@FreeBSD.org, cvs-all@FreeBSD.org Subject: Re: cvs commit: src/sys/fs/pseudofs pseudofs_vnops.c src/sys/compat/linux linux_misc.c src/sys/compat/linprocfs linprocfs.c Message-ID: <20060714193538.GN25976@elvis.mu.org> In-Reply-To: <200607081406.k68E6u3w049339@repoman.freebsd.org> References: <200607081406.k68E6u3w049339@repoman.freebsd.org>
next in thread | previous in thread | raw e-mail | index | archive | help
Could the KASSERT here be changed to a warning log message instead?
I don't like the idea of kernel modules failing catastrophically
when they could fail gracefully by just emitting an error.
Is that OK?
+ KASSERT(kp.ki_stat <= sizeof(linux_state),
+ ("linprocfs: don't know how to handle unknown FreeBSD state"));
-Alfred
* Alexander Leidinger <netchild@FreeBSD.org> [060708 07:06] wrote:
> netchild 2006-07-08 14:06:56 UTC
>
> FreeBSD src repository
>
> Modified files: (Branch: RELENG_6)
> sys/fs/pseudofs pseudofs_vnops.c
> sys/compat/linux linux_misc.c
> sys/compat/linprocfs linprocfs.c
> Log:
> MFC:
> - linux_misc.c 1.179
> Don't copyout/do unneccesary work if the buffer is a NULL pointer.
>
> Noticed by: Dmitry Ganenko <dima@apk-inform.com>
> Reviewed by: rdivacky (the original version as in emulation@)
>
> - linprocfs.c 1.96:
> Improve linprovfs to provide/fix the
> - process state (idle, sleeping, running, ...) [1]
> - the process group ID of the process which owns the connected tty
> - some page fault stats
> - time spend in kernel/userland
> - priority/nice value
> - starttime [1]
> - memory/swap stats
> - scheduling policy
>
> Additionally add some new fields and correct some not filled out ones.
>
> This brings us down to 15 dummy fields.
>
> The fields marked with [1] are needed to get Oracle 10 running. The starttime
> field is not completely right, since it displays the _same_ starttime for
> _every_ process, but at least it is not 0 and Oracle accepts this.
>
> Noticed by: Dmitry Ganenko <dima@apk-inform.com> [1]
> Reviewed by: des, rdivacky
>
> - pseudofs_vnops.c 1.60:
> Correctly calculate a buffer length. It was off by one so a read() returned
> one byte less than needed.
>
> Noticed by: Dmitry Ganenko <dima@apk-inform.com>
> Testcase by: Dmitry Ganenko <dima@apk-inform.com>
> Reviewed by: des
> Submitted by: rdivacky
> Sponsored by: Google SoC 2006
>
> All of those are needed for Oracle 10. Since previous Oracle versions work
> just fine without those fixes, these patches can be seen as regression fixes
> too. Because of this I think they are a RELENG_6_x candidate (MFC reminder
> set).
>
> MFC after: 1 month
>
> Revision Changes Path
> 1.89.2.4 +51 -27 src/sys/compat/linprocfs/linprocfs.c
> 1.170.2.1 +13 -11 src/sys/compat/linux/linux_misc.c
> 1.56.2.4 +1 -1 src/sys/fs/pseudofs/pseudofs_vnops.c
--
- Alfred Perlstein
- coder / sysadmin / FreeBSD Hacker / All that jazz -
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20060714193538.GN25976>