cvs commit: src/sys/fs/pseudofs pseudofs_vnops.c src/sys/compat/linux linux_misc.c src/sys/compat/linprocfs linprocfs.c

[Robert Watson]

On Fri, 14 Jul 2006, Alfred Perlstein wrote:

> 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"));

Or, if this is really just a structure size thing, we should pick it up at 
compile-time with CTASSERT?

Robert N M Watson
Computer Laboratory
University of Cambridge

>
> -Alfred
>
> * Alexander Leidinger <netchild at 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 at 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 at 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 at apk-inform.com>
>>     Testcase by:    Dmitry Ganenko <dima at 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 -
>