LKML Archive on lore.kernel.org
help / color / mirror / Atom feed
From: Yinghai Lu <Yinghai.Lu@Sun.COM>
To: Andi Kleen <andi@firstfloor.org>, Ingo Molnar <mingo@elte.hu>
Cc: Andrew Morton <akpm@linux-foundation.org>,
	Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
	kiran@scalemp.com, shai@scalemp.com
Subject: Re: [PATCH] x86_64: make amd quad core 8 socket system not be clustered_box v2
Date: Sun, 24 Feb 2008 17:52:34 -0800	[thread overview]
Message-ID: <200802241752.34918.yinghai.lu@sun.com> (raw)
In-Reply-To: <200802241500.52860.yinghai.lu@sun.com>

On Sunday 24 February 2008 03:00:52 pm Yinghai Lu wrote:
> On Sunday 24 February 2008 04:29:03 am Andi Kleen wrote:
> > On Sat, Feb 23, 2008 at 09:48:42PM -0800, Yinghai Lu wrote:
> > > 
> > > quad core 8 socket system will have apic id lifting.the apic id range could
> > > be [4, 0x23]. and apic_is_clustered_box will think that need to three clusters
> > > and that is large than 2. So it is treated as clustered_box.
> > 
> > Ok I see you chose the quick hack over doing it properly ...
> > 
> > > 
> > > and will get
> > > 
> > > Marking TSC unstable due to TSCs unsynchronized
> > > 
> > > even the CPUs have X86_FEATURE_CONSTANT_TSC set.
> > 
> > I doubt that will do the right thing on AMD based vSMP,
> > which also required the cluster check on AMD iirc.
> > 
> > Cc'ed Kiran/Shai. damage has already hit x86 tree I believe.
> 
> do you have bootlog for these box?
> 
> IBM summit2, Unisys es70000, and system from scalemp..
> 
> DMI could tell the difference?

i produced one patch against linus tree. but it can not be applied to x86/testing

x86/testing has
obj-$(CONFIG_PARAVIRT)          += vsmp_64.o

so my question: is the vsmp the real HW or just in paravirt?

YH

----

[PATCH] x86_64: make amd quad core 8 socket system not be clustered_box v3

quad core 8 socket system will have apic id lifting.the apic id range could
be [4, 0x23]. and apic_is_clustered_box will think that need to three clusters
and that is large than 2. So it is treated as clustered_box.

and will get

Marking TSC unstable due to TSCs unsynchronized

even the CPUs have X86_FEATURE_CONSTANT_TSC set.

this patch will check if the cpu is from AMD.

also vsmp still need that checking...

Signed-off-by: Yinghai Lu <yinghai.lu@sun.com>

diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 4eb5ce8..2bec799 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -60,7 +60,7 @@ obj-$(CONFIG_KEXEC)		+= relocate_kernel_$(BITS).o crash.o
 obj-$(CONFIG_CRASH_DUMP)	+= crash_dump_$(BITS).o
 obj-$(CONFIG_X86_NUMAQ)		+= numaq_32.o
 obj-$(CONFIG_X86_SUMMIT_NUMA)	+= summit_32.o
-obj-$(CONFIG_X86_VSMP)		+= vsmp_64.o
+obj-y				+= vsmp_64.o
 obj-$(CONFIG_KPROBES)		+= kprobes.o
 obj-$(CONFIG_MODULES)		+= module_$(BITS).o
 obj-$(CONFIG_ACPI_SRAT) 	+= srat_32.o
diff --git a/arch/x86/kernel/apic_64.c b/arch/x86/kernel/apic_64.c
index d8d03e0..1427ec3 100644
--- a/arch/x86/kernel/apic_64.c
+++ b/arch/x86/kernel/apic_64.c
@@ -1180,9 +1180,20 @@ __cpuinit int apic_is_clustered_box(void)
 {
 	int i, clusters, zeros;
 	unsigned id;
-	u16 *bios_cpu_apicid = x86_bios_cpu_apicid_early_ptr;
+	u16 *bios_cpu_apicid;
 	DECLARE_BITMAP(clustermap, NUM_APIC_CLUSTERS);
 
+	/*
+	 * there is not this kind of box with AMD CPU yet.
+	 * Some AMD box with quadcore cpu and 8 sockets apicid
+	 * will be [4, 0x23] or [8, 0x27] could be thought to
+	 * have three apic_clusters. So go out early.
+	 * vsmp box still need checking...
+	 */
+	if (!is_vsmp_box() && (boot_cpu_data.x86_vendor == X86_VENDOR_AMD))
+		return 0;
+
+	bios_cpu_apicid = x86_bios_cpu_apicid_early_ptr;
 	bitmap_zero(clustermap, NUM_APIC_CLUSTERS);
 
 	for (i = 0; i < NR_CPUS; i++) {
diff --git a/arch/x86/kernel/vsmp_64.c b/arch/x86/kernel/vsmp_64.c
index d971210..2780df1 100644
--- a/arch/x86/kernel/vsmp_64.c
+++ b/arch/x86/kernel/vsmp_64.c
@@ -16,19 +16,35 @@
 #include <asm/pci-direct.h>
 #include <asm/io.h>
 
+static int vsmp = -1;
+
+__cpuinit int is_vsmp_box(void)
+{
+	if (vsmp != -1)
+		return vsmp;
+
+	vsmp = 0;
+	if (!early_pci_allowed())
+		return vsmp;
+
+	/* Check if we are running on a ScaleMP vSMP box */
+	if (read_pci_config(0, 0x1f, 0, PCI_VENDOR_ID) ==
+	     (PCI_VENDOR_ID_SCALEMP || (PCI_DEVICE_ID_SCALEMP_VSMP_CTL << 16)))
+		vsmp = 1;
+
+	return vsmp;
+}
+
+#ifdef CONFIG_X86_VSMP
 static int __init vsmp_init(void)
 {
 	void *address;
 	unsigned int cap, ctl;
 
-	if (!early_pci_allowed())
+	if (!vsmp)
 		return 0;
 
-	/* Check if we are running on a ScaleMP vSMP box */
-	if ((read_pci_config_16(0, 0x1f, 0, PCI_VENDOR_ID) !=
-	     PCI_VENDOR_ID_SCALEMP) ||
-	    (read_pci_config_16(0, 0x1f, 0, PCI_DEVICE_ID) !=
-	     PCI_DEVICE_ID_SCALEMP_VSMP_CTL))
+	if (!early_pci_allowed())
 		return 0;
 
 	/* set vSMP magic bits to indicate vSMP capable kernel */
@@ -50,3 +66,4 @@ static int __init vsmp_init(void)
 }
 
 core_initcall(vsmp_init);
+#endif
diff --git a/include/asm-x86/apic.h b/include/asm-x86/apic.h
index bcfc07f..d69f596 100644
--- a/include/asm-x86/apic.h
+++ b/include/asm-x86/apic.h
@@ -130,6 +130,7 @@ extern u8 setup_APIC_eilvt_mce(u8 vector, u8 msg_type, u8 mask);
 extern u8 setup_APIC_eilvt_ibs(u8 vector, u8 msg_type, u8 mask);
 
 extern int apic_is_clustered_box(void);
+extern int is_vsmp_box(void);
 
 #else /* !CONFIG_X86_LOCAL_APIC */
 static inline void lapic_shutdown(void) { }

  reply	other threads:[~2008-02-25  1:44 UTC|newest]

Thread overview: 48+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2008-02-21 10:58 [PATCH] x86_64: make amd quad core 8 socket system not be clustered_box Yinghai Lu
2008-02-22 12:25 ` Andi Kleen
2008-02-22 19:02   ` Yinghai Lu
2008-02-22 19:00     ` Andi Kleen
2008-02-22 19:04       ` Yinghai Lu
2008-02-22 19:07         ` Andi Kleen
2008-02-22 19:07           ` Yinghai Lu
2008-02-22 19:10             ` Andi Kleen
2008-02-23  8:55               ` Yinghai Lu
2008-02-24  5:48       ` [PATCH] x86_64: make amd quad core 8 socket system not be clustered_box v2 Yinghai Lu
2008-02-24  7:50         ` Ingo Molnar
2008-02-24 12:29         ` Andi Kleen
2008-02-24 23:00           ` Yinghai Lu
2008-02-25  1:52             ` Yinghai Lu [this message]
2008-02-25  2:32             ` Yinghai Lu
2008-02-25  5:36               ` [PATCH] x86_64: for apic_is_clustered_box for vsmp v2 Yinghai Lu
2008-02-25  6:43                 ` [PATCH] x86: vSMP selection in config Yinghai Lu
2008-02-26 19:40                   ` Kconfig configuration restore bug [Was: x86: vSMP selection in config] Sam Ravnborg
2008-02-27  2:59                     ` Roman Zippel
2008-02-29  4:09                     ` [PATCH 1/3] fix recursive dependencies Roman Zippel
2008-02-29  5:05                       ` Yinghai Lu
2008-02-29 13:22                         ` Roman Zippel
2008-02-29 17:40                           ` Sam Ravnborg
2008-02-29 20:05                             ` Ingo Molnar
2008-02-29 20:04                       ` Ingo Molnar
2008-02-29  4:10                     ` [PATCH 2/3] fix choice dependency check Roman Zippel
2008-04-28 21:08                       ` Sam Ravnborg
2008-02-29  4:11                     ` [PATCH 3/3] add named choice group Roman Zippel
2008-02-26 20:05                   ` [PATCH] x86: vSMP selection in config Sam Ravnborg
2008-02-26 21:03                     ` Yinghai Lu
2008-02-25  5:39           ` [PATCH] x86_64: make amd quad core 8 socket system not be clustered_box v2 Yinghai Lu
2008-02-25 19:08           ` Ravikiran Thirumalai
2008-02-25 22:05             ` Yinghai Lu
2008-02-26  3:39               ` Ravikiran Thirumalai
2008-02-26  3:46                 ` Andi Kleen
2008-02-26  4:05                   ` Ravikiran Thirumalai
2008-02-26  5:27                     ` Yinghai Lu
2008-02-26 18:42                       ` Ravikiran Thirumalai
2008-02-26 19:00                         ` Yinghai Lu
2008-02-26 20:32                           ` Ravikiran Thirumalai
2008-02-26 21:09                             ` Yinghai Lu
2008-02-26 21:10                             ` Yinghai Lu
2008-02-26 21:24                               ` Ravikiran Thirumalai
2008-02-26 23:16                                 ` Yinghai Lu
2008-02-26 23:31                                   ` Ravikiran Thirumalai
2008-02-26 23:41                                     ` Yinghai Lu
2008-02-22 19:08     ` [PATCH] x86_64: make amd quad core 8 socket system not be clustered_box Yinghai Lu
2008-02-22 18:59       ` Andi Kleen

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=200802241752.34918.yinghai.lu@sun.com \
    --to=yinghai.lu@sun.com \
    --cc=akpm@linux-foundation.org \
    --cc=andi@firstfloor.org \
    --cc=kiran@scalemp.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@elte.hu \
    --cc=shai@scalemp.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;
as well as URLs for NNTP newsgroup(s).