From: Ashok Raj <ashok.raj@intel.com>
To: linux-kernel@vger.kernel.org
Cc: ashok.raj@intel.com, akpm@osdl.org, ak@muc.de, gregkh@suse.de,
"Pallipadi, Venkatesh" <venkatesh.pallipadi@intel.com>
Subject: Re: [patch 2/2] Convert bigsmp to use flat physical mode
Date: Mon, 21 Nov 2005 17:04:11 -0800 [thread overview]
Message-ID: <20051121170411.A15347@unix-os.sc.intel.com> (raw)
In-Reply-To: <20051122000204.890352000@araj-sfield-2>; from ashok.raj@intel.com on Mon, Nov 21, 2005 at 03:39:16PM -0800
On Mon, Nov 21, 2005 at 03:39:16PM -0800, Ashok Raj wrote:
>
> - if ((num_processors > 8) &&
> - APIC_XAPIC(ver) &&
> - (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL))
> + if (APIC_XAPIC(ver) &&
> + (CPU_HOTPLUG_ENABLED ||
> + ((num_processors > 8) &&
> + (boot_cpu_data.x86_vendor ==
> X86_VENDOR_INTEL))))
> def_to_bigsmp = 1;
Noticed that Andi send one more patch do enable bigsmp for AMD (i386), and the
APIC_XAPIC() check was not properly placed to factor this in. This updated
patch should work for AMD as well, and switch to bigsmp when we have hotplug
enabled.
--
Cheers,
Ashok Raj
- Open Source Technology Center
If we are using hotplug enabled kernel, then make bigsmp the default mode.
Signed-off-by: Ashok Raj <ashok.raj@intel.com>
Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
-------------------------------------------------------
arch/i386/kernel/mpparse.c | 25 ++++++++++++++++++-------
1 files changed, 18 insertions(+), 7 deletions(-)
Index: linux-2.6.15-rc1-mm2/arch/i386/kernel/mpparse.c
===================================================================
--- linux-2.6.15-rc1-mm2.orig/arch/i386/kernel/mpparse.c
+++ linux-2.6.15-rc1-mm2/arch/i386/kernel/mpparse.c
@@ -38,6 +38,12 @@
int smp_found_config;
unsigned int __initdata maxcpus = NR_CPUS;
+#ifdef CONFIG_HOTPLUG_CPU
+#define CPU_HOTPLUG_ENABLED (1)
+#else
+#define CPU_HOTPLUG_ENABLED (0)
+#endif
+
/*
* Various Linux-internal data structures created from the
* MP-table.
@@ -219,13 +225,18 @@ static void __devinit MP_processor_info
cpu_set(num_processors, cpu_possible_map);
num_processors++;
- if ((num_processors > 8) &&
- APIC_XAPIC(ver) &&
- (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL))
- def_to_bigsmp = 1;
- else
- def_to_bigsmp = 0;
-
+ if (CPU_HOTPLUG_ENABLED || (num_processors > 8)) {
+ switch (boot_cpu_data.x86_vendor) {
+ case X86_VENDOR_INTEL:
+ if (!APIC_XAPIC(ver)) {
+ def_to_bigsmp = 0;
+ break;
+ }
+ /* If P4 and above fall through */
+ case X86_VENDOR_AMD:
+ def_to_bigsmp = 1;
+ }
+ }
bios_cpu_apicid[num_processors - 1] = m->mpc_apicid;
}
next prev parent reply other threads:[~2005-11-22 1:04 UTC|newest]
Thread overview: 6+ messages / expand[flat|nested] mbox.gz Atom feed top
2005-11-21 23:39 [patch 0/2] " Ashok Raj
2005-11-21 23:39 ` [patch 1/2] " Ashok Raj
2005-11-21 23:39 ` [patch 2/2] " Ashok Raj
2005-11-22 1:04 ` Ashok Raj [this message]
2005-11-22 8:56 ` Andi Kleen
2005-11-23 4:38 ` Andrew Morton
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=20051121170411.A15347@unix-os.sc.intel.com \
--to=ashok.raj@intel.com \
--cc=ak@muc.de \
--cc=akpm@osdl.org \
--cc=gregkh@suse.de \
--cc=linux-kernel@vger.kernel.org \
--cc=venkatesh.pallipadi@intel.com \
/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
all inboxes | Powered by JetHome®