Skip site navigation (1)Skip section navigation (2)
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>