From: Nick Piggin <nickpiggin@yahoo.com.au>
To: Hugh Dickins <hugh@veritas.com>
Cc: Andrew Morton <akpm@osdl.org>, linux-kernel@vger.kernel.org
Subject: Re: [PATCH 11/15] ptwalk: copy_pte_range hang
Date: Thu, 10 Mar 2005 10:25:42 +1100 [thread overview]
Message-ID: <422F85F6.40305@yahoo.com.au> (raw)
In-Reply-To: <Pine.LNX.4.61.0503092212440.6070@goblin.wat.veritas.com>
Hugh Dickins wrote:
> This patch is the odd-one-out of the sequence. The one before adjusted
> copy_pte_range from a for loop to a do while loop, and it was therefore
> simplest to check for lockbreak before copying pte: possibility that it
> might keep getting preempted without making progress under some loads.
>
> Some loads such as startup: 2*HT*P4 with preemption cannot even reach
> multiuser login. Suspect needs_lockbreak is broken, can get in a state
> when it remains forever true. Investigate that later: for now, and for
> all time, it makes sense to aim for a little progress before breaking
> out; and we can manage more pte_nones than copies.
>
(Just to reiterate a private mail sent to Hugh earlier)
Yeah I think lockbreak is broken. Because the inner spinlock never
has a cond_resched_lock performed on it, so its break_lock is
never set to 0, but need_lockbreak still always returns 1 for it.
IMO, spin_lock should set break_lock to 0, then cond_resched_lock
need not bother with it.
next prev parent reply other threads:[~2005-03-09 23:26 UTC|newest]
Thread overview: 20+ messages / expand[flat|nested] mbox.gz Atom feed top
2005-03-09 22:05 [PATCH 0/15] ptwalk: pagetable walker cleanup Hugh Dickins
2005-03-09 22:06 ` [PATCH 1/15] ptwalk: p?d_none_or_clear_bad Hugh Dickins
2005-03-09 22:07 ` [PATCH 2/15] ptwalk: change_protection Hugh Dickins
2005-03-09 22:08 ` [PATCH 3/15] ptwalk: sync_page_range Hugh Dickins
2005-03-09 22:08 ` [PATCH 4/15] ptwalk: unuse_mm Hugh Dickins
2005-03-09 22:09 ` [PATCH 5/15] ptwalk: map and unmap_vm_area Hugh Dickins
2005-03-09 22:10 ` [PATCH 6/15] ptwalk: ioremap_page_range Hugh Dickins
2005-03-09 22:10 ` [PATCH 7/15] ptwalk: remap_pfn_range Hugh Dickins
2005-03-09 22:11 ` [PATCH 8/15] ptwalk: zeromap_page_range Hugh Dickins
2005-03-09 22:12 ` [PATCH 9/15] ptwalk: unmap_page_range Hugh Dickins
2005-03-09 22:12 ` [PATCH 10/15] ptwalk: copy_page_range Hugh Dickins
2005-03-09 22:13 ` [PATCH 11/15] ptwalk: copy_pte_range hang Hugh Dickins
2005-03-09 23:25 ` Nick Piggin [this message]
2005-03-09 22:14 ` [PATCH 12/15] ptwalk: clear_page_range Hugh Dickins
2005-03-09 22:14 ` [PATCH 13/15] ptwalk: move p?d_none_or_clear_bad Hugh Dickins
2005-03-09 22:15 ` [PATCH 14/15] ptwalk: inline pmd_range and pud_range Hugh Dickins
2005-03-09 22:16 ` [PATCH 15/15] ptwalk: pud and pmd folded Hugh Dickins
2005-03-10 0:39 ` [PATCH 0/15] ptwalk: pagetable walker cleanup Benjamin Herrenschmidt
2005-03-10 1:02 ` David S. Miller
2005-03-10 1:08 ` Benjamin Herrenschmidt
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=422F85F6.40305@yahoo.com.au \
--to=nickpiggin@yahoo.com.au \
--cc=akpm@osdl.org \
--cc=hugh@veritas.com \
--cc=linux-kernel@vger.kernel.org \
/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
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox