x86: clean up and fix setup_clear/force_cpu_cap handling

setup_force_cpu_cap() only have one user (Xen guest code),
but it should not reuse cleared_cpu_cpus, otherwise it
will have problems on SMP.

Need to have a separate cpu_cpus_set array too, for forced-on
flags, beyond the forced-off flags.

Also need to setup handling before all cpus caps are combined.

[ Impact: fix the forced-set CPU feature flag logic ]

Cc: H. Peter Anvin <hpa@linux.intel.com>
Cc: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Yinghai Lu <yinghai.lu@kernel.org>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index ccc1061..13cc6a5 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -192,11 +192,11 @@
 #define clear_cpu_cap(c, bit)	clear_bit(bit, (unsigned long *)((c)->x86_capability))
 #define setup_clear_cpu_cap(bit) do { \
 	clear_cpu_cap(&boot_cpu_data, bit);	\
-	set_bit(bit, (unsigned long *)cleared_cpu_caps); \
+	set_bit(bit, (unsigned long *)cpu_caps_cleared); \
 } while (0)
 #define setup_force_cpu_cap(bit) do { \
 	set_cpu_cap(&boot_cpu_data, bit);	\
-	clear_bit(bit, (unsigned long *)cleared_cpu_caps);	\
+	set_bit(bit, (unsigned long *)cpu_caps_set);	\
 } while (0)
 
 #define cpu_has_fpu		boot_cpu_has(X86_FEATURE_FPU)
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index c2cceae..fed93fe 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -135,7 +135,8 @@
 extern struct cpuinfo_x86	new_cpu_data;
 
 extern struct tss_struct	doublefault_tss;
-extern __u32			cleared_cpu_caps[NCAPINTS];
+extern __u32			cpu_caps_cleared[NCAPINTS];
+extern __u32			cpu_caps_set[NCAPINTS];
 
 #ifdef CONFIG_SMP
 DECLARE_PER_CPU_SHARED_ALIGNED(struct cpuinfo_x86, cpu_info);
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index c4f6678..e7fd5c4 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -292,7 +292,8 @@
 	return NULL;		/* Not found */
 }
 
-__u32 cleared_cpu_caps[NCAPINTS] __cpuinitdata;
+__u32 cpu_caps_cleared[NCAPINTS] __cpuinitdata;
+__u32 cpu_caps_set[NCAPINTS] __cpuinitdata;
 
 void load_percpu_segment(int cpu)
 {
@@ -806,6 +807,16 @@
 #endif
 
 	init_hypervisor(c);
+
+	/*
+	 * Clear/Set all flags overriden by options, need do it
+	 * before following smp all cpus cap AND.
+	 */
+	for (i = 0; i < NCAPINTS; i++) {
+		c->x86_capability[i] &= ~cpu_caps_cleared[i];
+		c->x86_capability[i] |= cpu_caps_set[i];
+	}
+
 	/*
 	 * On SMP, boot_cpu_data holds the common feature set between
 	 * all CPUs; so make sure that we indicate which features are
@@ -818,10 +829,6 @@
 			boot_cpu_data.x86_capability[i] &= c->x86_capability[i];
 	}
 
-	/* Clear all flags overriden by options */
-	for (i = 0; i < NCAPINTS; i++)
-		c->x86_capability[i] &= ~cleared_cpu_caps[i];
-
 #ifdef CONFIG_X86_MCE
 	/* Init Machine Check Exception if available. */
 	mcheck_init(c);