From: Milton Miller <miltonm@bga.com>
To: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: linuxppc-dev@ozlabs.org
Subject: powerpc: numa.c: always trim to lmb_end_of_DRAM
Date: Thu, 10 Jul 2008 16:19:06 -0500 (CDT) [thread overview]
Message-ID: <for-27-patch3@bga.com> (raw)
In-Reply-To: <for-27-patch1-0@bga.com>
numa_enforce_memory_limit trys to be smart and only trim the memory it
finds to lmb_end_of_DRAM when a memory limit is set. However, the
early boot code may also limit memory when iommu=off is specified. When
this happens, the page allocator is told of pages not in the linear mapping
and gets a fatal DSI.
Signed-off-by: Milton Miller <miltonm@bga.com>
--
Previously this patch tried to check if iommu=off was specified, but it was
requested that the check just be removed.
http://patchwork.ozlabs.org/linuxppc/patch?id=11774
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index cf4bffb..590406c 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -472,12 +472,10 @@ static unsigned long __init numa_enforce_memory_limit(unsigned long start,
/*
* We use lmb_end_of_DRAM() in here instead of memory_limit because
* we've already adjusted it for the limit and it takes care of
- * having memory holes below the limit.
+ * having memory holes below the limit. Also, in the case of
+ * iommu_is_off, memory_limit is not set but is implicitly enforced.
*/
- if (! memory_limit)
- return size;
-
if (start + size <= lmb_end_of_DRAM())
return size;
next prev parent reply other threads:[~2008-07-10 21:20 UTC|newest]
Thread overview: 28+ messages / expand[flat|nested] mbox.gz Atom feed top
2008-07-10 21:12 [RFC] (almost) booting allyesconfig -- please don't poke super-io without request_region Milton Miller
2008-07-10 21:14 ` mtd: remove __PPC__ hardcoded address from nand/diskonchip and devices/docprobe Milton Miller
2008-07-10 21:14 ` [1/3] powerpc: add _HEAD_GLOBAL to place functions in .text.head Milton Miller
2008-07-10 21:16 ` [2/3] powerpc: head_64.S: put irq vectors " Milton Miller
2008-07-10 21:19 ` Milton Miller [this message]
2008-07-10 21:20 ` powerpc: pseries, cell: use cpu_thread_in_core in smp_init for of_spin_map Milton Miller
2008-07-10 21:22 ` powerpc: find and destroy possible stale kernel added properties Milton Miller
2008-07-10 21:23 ` powerpc: add static and ifdef prom_strtoul and prom_memparse Milton Miller
2008-07-10 21:29 ` [PATCH] spufs: correct kcalloc usage Milton Miller
2008-07-10 23:04 ` Jeremy Kerr
2008-07-10 21:33 ` [lm-sensors] [RFC] (almost) booting allyesconfig -- please don't poke super-io without request_region Hans de Goede
2008-07-10 21:51 ` Milton Miller
2008-07-11 6:52 ` Jean Delvare
2008-07-11 7:27 ` Hans de Goede
2008-07-11 7:36 ` Jean Delvare
2008-07-13 6:31 ` Hans de Goede
2008-07-13 21:11 ` [lm-sensors] " David Hubbard
2008-07-13 21:22 ` Hans de Goede
2008-07-13 21:26 ` David Hubbard
2008-07-14 7:59 ` Jean Delvare
2008-07-14 17:09 ` Milton Miller
2008-07-14 17:30 ` [lm-sensors] " Hans de Goede
2008-07-14 17:55 ` David Hubbard
2008-07-15 8:36 ` Jean Delvare
2008-07-15 15:31 ` David Hubbard
2008-07-16 7:46 ` Jean Delvare
2008-07-16 8:09 ` Rene Herman
2008-07-15 8:28 ` Jean Delvare
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=for-27-patch3@bga.com \
--to=miltonm@bga.com \
--cc=benh@kernel.crashing.org \
--cc=linuxppc-dev@ozlabs.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;
as well as URLs for NNTP newsgroup(s).