[patch 4/4] x86: apic_is_clustered_box to indicate unsynched TSC's on multiboard vSMP systems

!MAILaRCHIVE_VOTE_RePLACE
Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]
To: Andrew Morton <akpm@...>, Ingo Molnar <mingo@...>
Cc: <linux-kernel@...>, Glauber de Oliveira Costa <gcosta@...>, Andi Kleen <ak@...>, <shai@...>
Date: Thursday, March 20, 2008 - 3:45 am

Indicate TSCs are unreliable as time sources if the platform is
a multi chassi ScaleMP vSMPowered machine.

Signed-off-by: Ravikiran Thirumalai <kiran@scalex86.org>

Index: linux.git.trees/arch/x86/kernel/apic_64.c
===================================================================
--- linux.git.trees.orig/arch/x86/kernel/apic_64.c	2008-03-19 20:42:28.187659497 -0700
+++ linux.git.trees/arch/x86/kernel/apic_64.c	2008-03-19 21:24:17.705515003 -0700
@@ -1208,7 +1208,7 @@ __cpuinit int apic_is_clustered_box(void
 	 * will be [4, 0x23] or [8, 0x27] could be thought to
 	 * vsmp box still need checking...
 	 */
-	if (!is_vsmp_box() && (boot_cpu_data.x86_vendor == X86_VENDOR_AMD))
+	if ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD) && !is_vsmp_box())
 		return 0;
 
 	bios_cpu_apicid = x86_bios_cpu_apicid_early_ptr;
@@ -1248,6 +1248,12 @@ __cpuinit int apic_is_clustered_box(void
 			++zeros;
 	}
 
+	/* ScaleMP vSMPowered boxes have one cluster per board and TSCs are
+	 * not guaranteed to be synced between boards
+	 */
+	if (is_vsmp_box() && clusters > 1)
+		return 1;
+
 	/*
 	 * If clusters > 2, then should be multi-chassis.
 	 * May have to revisit this when multi-core + hyperthreaded CPUs come
--
Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]

Messages in current thread:
[patch 0/4] x86: vSMP updates, Ravikiran G Thirumalai, (Thu Mar 20, 3:37 am)
Re: [patch 0/4] x86: vSMP updates, Ingo Molnar, (Fri Mar 21, 4:54 am)
[patch 4/4] x86: apic_is_clustered_box to indicate unsynched..., Ravikiran G Thirumalai, (Thu Mar 20, 3:45 am)
Re: [patch 4/4] x86: apic_is_clustered_box to indicate unsyn..., Ravikiran G Thirumalai, (Thu Mar 20, 3:02 pm)
Re: [patch 4/4] x86: apic_is_clustered_box to indicate unsyn..., Ravikiran G Thirumalai, (Fri Mar 21, 2:52 pm)
Re: [patch 4/4] x86: apic_is_clustered_box to indicate unsyn..., Ravikiran G Thirumalai, (Sat Mar 22, 2:59 pm)
Re: [patch 4/4] x86: apic_is_clustered_box to indicate unsyn..., Ravikiran G Thirumalai, (Mon Mar 24, 5:48 pm)
[patch 3/4] x86: vSMP: Use pvops only if platform has the ca..., Ravikiran G Thirumalai, (Thu Mar 20, 3:43 am)
[patch 2/4] x86: Fix build breakage when PCI is define and P..., Ravikiran G Thirumalai, (Thu Mar 20, 3:41 am)
Re: [patch 2/4] x86: Fix build breakage when PCI is define a..., Jeremy Fitzhardinge, (Fri Mar 21, 12:30 am)
Re: [patch 2/4] x86: Fix build breakage when PCI is define a..., Ravikiran G Thirumalai, (Fri Mar 21, 2:54 pm)
Re: [patch 2/4] x86: Fix build breakage when PCI is define a..., Jeremy Fitzhardinge, (Fri Mar 21, 10:19 pm)
[patch 1/4] x86: vSMP: Fix is_vsmp_box(), Ravikiran G Thirumalai, (Thu Mar 20, 3:39 am)
Re: [patch 1/4] x86: vSMP: Fix is_vsmp_box(), Yinghai Lu, (Thu Mar 20, 3:44 am)
Re: [patch 1/4] x86: vSMP: Fix is_vsmp_box(), Ravikiran G Thirumalai, (Thu Mar 20, 2:40 pm)
Re: [patch 1/4] x86: vSMP: Fix is_vsmp_box(), Ingo Molnar, (Fri Mar 21, 5:11 am)
Re: [patch 1/4] x86: vSMP: Fix is_vsmp_box(), Ravikiran G Thirumalai, (Fri Mar 21, 1:59 pm)
Re: [patch 1/4] x86: vSMP: Fix is_vsmp_box(), Yinghai Lu, (Fri Mar 21, 5:17 am)