Move xen patchset to new version's subdir.

[people/teissler/ipfire-2.x.git] / src / patches / suse-2.6.27.31 / patches.xen / xen3-x2APIC_PATCH_40_of_41_bbb65d2d365efe9951290e61678dcf81ec60add4

From: Suresh Siddha <suresh.b.siddha@intel.com>
Subject: x86: use cpuid vector 0xb when available for detecting cpu topology
References: fate #303948 and fate #303984
Patch-Mainline: queued for .28
Commit-ID: bbb65d2d365efe9951290e61678dcf81ec60add4

Signed-off-by: Thomas Renninger <trenn@suse.de>

cpuid leaf 0xb provides extended topology enumeration. This interface provides
the 32-bit x2APIC id of the logical processor and it also provides a new
mechanism to detect SMT and core siblings (which provides increased
addressability).

Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

Automatically created from "patches.arch/x2APIC_PATCH_40_of_41_bbb65d2d365efe9951290e61678dcf81ec60add4" by xen-port-patches.py

Index: head-2008-10-13/arch/x86/kernel/cpu/addon_cpuid_features.c
===================================================================
--- head-2008-10-13.orig/arch/x86/kernel/cpu/addon_cpuid_features.c	2008-10-13 13:52:01.000000000 +0200
+++ head-2008-10-13/arch/x86/kernel/cpu/addon_cpuid_features.c	2008-10-13 15:49:03.000000000 +0200
@@ -69,7 +69,7 @@ void __cpuinit init_scattered_cpuid_feat
  */
 void __cpuinit detect_extended_topology(struct cpuinfo_x86 *c)
 {
-#ifdef CONFIG_SMP
+#if defined(CONFIG_SMP) && !defined(CONFIG_XEN)
 	unsigned int eax, ebx, ecx, edx, sub_index;
 	unsigned int ht_mask_width, core_plus_mask_width;
 	unsigned int core_select_mask, core_level_siblings;
Index: linux-2.6.26/include/asm-x86/mach-xen/asm/processor.h
===================================================================
--- linux-2.6.26.orig/include/asm-x86/mach-xen/asm/processor.h
+++ linux-2.6.26/include/asm-x86/mach-xen/asm/processor.h
@@ -161,6 +161,7 @@ extern void init_scattered_cpuid_feature
 extern unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c);
 extern unsigned short num_cache_leaves;
 
+extern void detect_extended_topology(struct cpuinfo_x86 *c);
 #if defined(CONFIG_X86_HT) || defined(CONFIG_X86_64)
 extern void detect_ht(struct cpuinfo_x86 *c);
 #else