LKML Archive on lore.kernel.org
help / color / mirror / Atom feed
From: David Miller <davem@davemloft.net>
To: tony.luck@intel.com
Cc: mingo@elte.hu, rdreier@cisco.com, linux-kernel@vger.kernel.org
Subject: Re: Strange hang on ia64 with CONFIG_PRINTK_TIME=y
Date: Wed, 13 Feb 2008 17:04:52 -0800 (PST) [thread overview]
Message-ID: <20080213.170452.68851396.davem@davemloft.net> (raw)
In-Reply-To: <12c511ca0802131659u6e4407d9w96148fe72d6e11d7@mail.gmail.com>
From: "Tony Luck" <tony.luck@intel.com>
Date: Wed, 13 Feb 2008 16:59:30 -0800
> > It is legal to access per-cpu data as early as you like,
> > it just evaluates to the static copy in the per-cpu section
> > of the kernel image until the per-cpu areas are setup.
>
> On ia64 per-cpu variables are mapped into the top 64K
> of the address space. Accessing them before the
> resources to handle the access to that virtual address
> have been set up would cause problems.
That's right. I thought you guys had something that would handle that
early on, but looking at how the trick works in the vmlinux.lds.S ia64
uses that isn't the case.
I guess we really can't do per-cpu accesses early on.
This is extremely fragile, we should find some way to formalize this
to make accidental early per-cpu references trap at build time or
similar.
next prev parent reply other threads:[~2008-02-14 1:04 UTC|newest]
Thread overview: 21+ messages / expand[flat|nested] mbox.gz Atom feed top
2008-02-13 6:24 Roland Dreier
2008-02-13 7:01 ` David Miller
2008-02-13 12:57 ` Ingo Molnar
2008-02-13 13:02 ` Ingo Molnar
2008-02-14 0:26 ` Roland Dreier
2008-02-13 13:03 ` David Miller
2008-02-13 13:06 ` Ingo Molnar
2008-02-14 0:59 ` Tony Luck
2008-02-14 1:04 ` David Miller [this message]
2008-02-14 3:33 ` Tony Luck
2008-02-14 3:47 ` Roland Dreier
2008-02-14 18:24 ` Luck, Tony
2008-02-14 21:27 ` Tony Luck
2008-02-14 22:04 ` Roland Dreier
2008-02-14 22:23 ` Luck, Tony
2008-02-15 2:17 ` Tony Luck
2008-02-19 22:40 ` Tony Luck
2008-02-20 8:12 ` Ingo Molnar
2008-02-20 8:15 ` David Miller
2008-02-20 23:35 ` Roland Dreier
2008-02-20 23:36 ` Roland Dreier
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20080213.170452.68851396.davem@davemloft.net \
--to=davem@davemloft.net \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=rdreier@cisco.com \
--cc=tony.luck@intel.com \
--subject='Re: Strange hang on ia64 with CONFIG_PRINTK_TIME=y' \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).