From: Jens Axboe <axboe@suse.de>
To: Ingo Molnar <mingo@elte.hu>
Cc: Byron Stanoszek <gandalf@winds.org>,
linux-kernel@vger.kernel.org, Andrew Morton <akpm@osdl.org>,
Linus Torvalds <torvalds@osdl.org>
Subject: [PATCH] Address space split configuration
Date: Tue, 10 Jan 2006 16:03:31 +0100 [thread overview]
Message-ID: <20060110150331.GN3389@suse.de> (raw)
In-Reply-To: <20060110144412.GA9295@elte.hu>
On Tue, Jan 10 2006, Ingo Molnar wrote:
>
> * Jens Axboe <axboe@suse.de> wrote:
>
> > + Select the wanted split between kernel and user memory.
> > +
> > + If the address range available to the kernel is less than the
> > + physical memory installed, the remaining memory will be available
> > + as "high memory". Accessing high memory is a little more costly
> > + than low memory, as it needs to be mapped into the kernel first.
>
> make it _ALOT_ more clear that mere mortals should not touch this
> option! Also, you do not mention the userspace-VM fragmentation issues.
> Plus, if a user uses a 2G/2G split with more than 2G of RAM, the kernel
> should print a warning that it's running with a non-default split. Do
> the same if the user uses a non-default split with less than 960MB of
> RAM.
I added the < 960MiB warning, but not for the 2G/2G as the option
depends on NOHIGHMEM right now.
I also changed the help text again, hope you are happy with it now.
> > +
> > + Note that selecting anything but the default 3G/1G split will make
> > + your kernel incompatible with binary only modules.
>
> it's not 'will' but 'may', and even then, tons of .config things can
> break bin-only modules, so just skip this paragraph.
Killed.
> looks good to me otherwise, with the text fixes it's:
>
> Acked-by: Ingo Molnar <mingo@elte.hu>
Thanks! Updated patch below.
---
Add option for configuring the page offset, to better optimize the
kernel for higher memory machines. Enables users to get rid of high
memory for eg a 1GiB machine.
Signed-off-by: Jens Axboe <axboe@suse.de>
Acked-by: Ingo Molnar <mingo@elte.hu>
diff --git a/arch/i386/Kconfig b/arch/i386/Kconfig
index d849c68..20d1423 100644
--- a/arch/i386/Kconfig
+++ b/arch/i386/Kconfig
@@ -444,6 +464,35 @@ config HIGHMEM64G
endchoice
+choice
+ depends on NOHIGHMEM && EXPERIMENTAL
+ prompt "Memory split"
+ default DEFAULT_3G
+ help
+ Select the wanted split between kernel and user memory.
+
+ If the address range available to the kernel is less than the
+ physical memory installed, the remaining memory will be available
+ as "high memory". Accessing high memory is a little more costly
+ than low memory, as it needs to be mapped into the kernel first.
+ Note that increasing the kernel address space limits the range
+ available to user programs, making the address space there
+ tighter.
+
+ If you are not absolutely sure what you are doing, leave this
+ option alone!
+
+ config DEFAULT_3G
+ bool "3G/1G user/kernel split"
+ config DEFAULT_3G_OPT
+ bool "3G/1G user/kernel split (for full 1G low memory)"
+ config DEFAULT_2G
+ bool "2G/2G user/kernel split"
+ config DEFAULT_1G
+ bool "1G/3G user/kernel split"
+
+endchoice
+
config HIGHMEM
bool
depends on HIGHMEM64G || HIGHMEM4G
diff --git a/arch/i386/mm/init.c b/arch/i386/mm/init.c
index 7df494b..67f1da0 100644
--- a/arch/i386/mm/init.c
+++ b/arch/i386/mm/init.c
@@ -597,6 +597,12 @@ void __init mem_init(void)
high_memory = (void *) __va(max_low_pfn * PAGE_SIZE - 1) + 1;
#endif
+#if !defined(CONFIG_DEFAULT_3G)
+ /* if the user has less than 960MB of RAM, he should use the default */
+ if (max_low_pfn < (960 * 1024 * 1024 / PAGE_SIZE))
+ printk(KERN_INFO "Memory: less than 960MiB of RAM, you should use the default memory split setting\n");
+#endif
+
/* this will put all low memory onto the freelists */
totalram_pages += free_all_bootmem();
diff --git a/include/asm-i386/page.h b/include/asm-i386/page.h
index 73296d9..7da50a1 100644
--- a/include/asm-i386/page.h
+++ b/include/asm-i386/page.h
@@ -109,11 +109,23 @@ extern int page_is_ram(unsigned long pag
#endif /* __ASSEMBLY__ */
+#if defined(CONFIG_DEFAULT_3G)
+#define __PAGE_OFFSET_RAW (0xC0000000)
+#elif defined(CONFIG_DEFAULT_3G_OPT)
+#define __PAGE_OFFSET_RAW (0xB0000000)
+#elif defined(CONFIG_DEFAULT_2G)
+#define __PAGE_OFFSET_RAW (0x78000000)
+#elif defined(CONFIG_DEFAULT_1G)
+#define __PAGE_OFFSET_RAW (0x40000000)
+#else
+#error "Bad user/kernel offset"
+#endif
+
#ifdef __ASSEMBLY__
-#define __PAGE_OFFSET (0xC0000000)
+#define __PAGE_OFFSET __PAGE_OFFSET_RAW
#define __PHYSICAL_START CONFIG_PHYSICAL_START
#else
-#define __PAGE_OFFSET (0xC0000000UL)
+#define __PAGE_OFFSET ((unsigned long)__PAGE_OFFSET_RAW)
#define __PHYSICAL_START ((unsigned long)CONFIG_PHYSICAL_START)
#endif
#define __KERNEL_START (__PAGE_OFFSET + __PHYSICAL_START)
--
Jens Axboe
next prev parent reply other threads:[~2006-01-10 15:01 UTC|newest]
Thread overview: 87+ messages / expand[flat|nested] mbox.gz Atom feed top
2006-01-10 12:58 2G memory split Jens Axboe
2006-01-10 13:29 ` Ingo Molnar
2006-01-10 13:37 ` Jens Axboe
2006-01-10 13:43 ` Byron Stanoszek
2006-01-10 13:47 ` Jens Axboe
2006-01-10 14:39 ` Jens Axboe
2006-01-10 14:44 ` Ingo Molnar
2006-01-10 15:03 ` Jens Axboe [this message]
2006-01-10 15:11 ` [PATCH] Address space split configuration Mark Lord
2006-01-10 15:24 ` Mikael Pettersson
2006-01-10 16:14 ` 2G memory split Linus Torvalds
2006-01-10 16:40 ` Mark Lord
2006-01-10 16:52 ` Linus Torvalds
2006-01-10 18:33 ` Coywolf Qi Hunt
2006-01-10 17:07 ` Mark Lord
2006-01-10 17:28 ` Linus Torvalds
2006-01-10 17:32 ` Jens Axboe
2006-01-10 17:37 ` Mark Lord
2006-01-10 18:58 ` Mark Lord
2006-01-10 19:16 ` [PATCH ] VMSPLIT config options (with default config fixed) Mark Lord
2006-01-10 17:37 ` Jeff V. Merkey
2006-01-10 19:27 ` Jens Axboe
2006-01-11 1:13 ` J.A. Magallon
2006-01-11 10:15 ` Jens Axboe
2006-01-11 16:00 ` Greg Norris
2006-01-11 17:13 ` Mark Lord
2006-01-11 17:44 ` Greg Norris
2006-02-05 18:42 ` Barry K. Nathan
2006-02-01 22:23 ` Herbert Poetzl
2006-02-02 11:04 ` Ulrich Mueller
2006-02-02 20:55 ` Jan Engelhardt
2006-02-03 22:39 ` Mark Lord
2006-02-04 10:23 ` Ulrich Mueller
2006-02-04 11:06 ` Jan Engelhardt
2006-02-04 10:36 ` Jens Axboe
2006-02-04 11:05 ` Jan Engelhardt
2006-02-04 13:57 ` Mark Lord
2006-02-05 15:32 ` J.A. Magallon
2006-02-05 15:38 ` Arjan van de Ven
2006-02-05 21:14 ` Jan Engelhardt
2006-02-05 21:19 ` Arjan van de Ven
2006-02-06 14:56 ` Jan Engelhardt
2006-02-07 0:41 ` Herbert Poetzl
2006-02-07 2:51 ` Mark Rustad
2006-02-07 9:38 ` Bernd Petrovitsch
2006-02-07 12:19 ` RFC: add an ADVANCED_USER option Adrian Bunk
2006-02-07 14:05 ` Ulrich Mueller
2006-02-07 14:42 ` Adrian Bunk
2006-02-09 16:06 ` Jan Engelhardt
2006-01-10 17:48 ` 2G memory split Bernd Eckenfels
2006-01-10 16:30 ` [PATCH] " Jeff V. Merkey
2006-01-10 18:50 ` Lennart Sorensen
2006-01-10 17:13 ` Jeff V. Merkey
2006-01-10 19:42 ` Jens Axboe
2006-01-10 20:17 ` Bernd Eckenfels
2006-01-10 20:28 ` Jens Axboe
2006-01-11 8:39 ` Bernd Eckenfels
2006-01-11 10:06 ` Jens Axboe
2006-01-10 18:14 ` Martin Bligh
2006-01-10 18:34 ` Linus Torvalds
2006-01-10 16:56 ` Jeff V. Merkey
2006-01-10 17:01 ` Jeff V. Merkey
2006-01-10 18:45 ` Mark Lord
2006-01-10 18:46 ` Martin Bligh
2006-01-10 18:58 ` Jens Axboe
2006-01-10 17:17 ` Jeff V. Merkey
2006-01-10 20:55 ` Alan Cox
2006-01-10 19:12 ` Jeff V. Merkey
2006-01-10 21:02 ` Jens Axboe
2006-01-10 19:30 ` Jeff V. Merkey
2006-01-10 18:39 ` Martin Bligh
2006-01-10 18:55 ` Dave Hansen
2006-01-10 19:01 ` Mark Lord
2006-01-10 19:05 ` Dave Hansen
2006-01-10 17:07 ` Sergey Vlasov
2006-04-10 14:11 ` Kirill Korotaev
2006-04-10 14:39 ` Mark Lord
2006-01-10 18:28 ` Coywolf Qi Hunt
2006-01-10 13:47 ` Mikael Pettersson
2006-01-10 13:54 ` Jens Axboe
2006-01-10 14:09 ` Gerd Hoffmann
2006-01-10 14:21 ` Jens Axboe
2006-01-10 14:25 ` Jens Axboe
2006-01-10 20:42 ` Jan Engelhardt
2006-01-11 0:25 ` Con Kolivas
2006-01-10 14:12 ` Mark Lord
2006-01-10 14:22 ` Jens Axboe
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=20060110150331.GN3389@suse.de \
--to=axboe@suse.de \
--cc=akpm@osdl.org \
--cc=gandalf@winds.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=torvalds@osdl.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).