1 files changed, 103 insertions, 27 deletions

diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 984a7bf17f6a..f385eca5407a 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -104,6 +104,7 @@ struct cpuinfo_x86 {
 	__u8			x86_phys_bits;
 	/* CPUID returned core id bits: */
 	__u8			x86_coreid_bits;
+	__u8			cu_id;
 	/* Max extended CPUID function supported: */
 	__u32			extended_cpuid_level;
 	/* Maximum supported CPUID level, -1=no CPUID: */
@@ -137,6 +138,17 @@ struct cpuinfo_x86 {
 	u32			microcode;
 };
 
+struct cpuid_regs {
+	u32 eax, ebx, ecx, edx;
+};
+
+enum cpuid_regs_idx {
+	CPUID_EAX = 0,
+	CPUID_EBX,
+	CPUID_ECX,
+	CPUID_EDX,
+};
+
 #define X86_VENDOR_INTEL	0
 #define X86_VENDOR_CYRIX	1
 #define X86_VENDOR_AMD		2
@@ -178,6 +190,9 @@ extern void identify_secondary_cpu(struct cpuinfo_x86 *);
 extern void print_cpu_info(struct cpuinfo_x86 *);
 void print_cpu_msr(struct cpuinfo_x86 *);
 extern void init_scattered_cpuid_features(struct cpuinfo_x86 *c);
+extern u32 get_scattered_cpuid_leaf(unsigned int level,
+				    unsigned int sub_leaf,
+				    enum cpuid_regs_idx reg);
 extern unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c);
 extern void init_amd_cacheinfo(struct cpuinfo_x86 *c);
 
@@ -205,6 +220,24 @@ static inline void native_cpuid(unsigned int *eax, unsigned int *ebx,
 	    : "memory");
 }
 
+#define native_cpuid_reg(reg)					\
+static inline unsigned int native_cpuid_##reg(unsigned int op)	\
+{								\
+	unsigned int eax = op, ebx, ecx = 0, edx;		\
+								\
+	native_cpuid(&eax, &ebx, &ecx, &edx);			\
+								\
+	return reg;						\
+}
+
+/*
+ * Native CPUID functions returning a single datum.
+ */
+native_cpuid_reg(eax)
+native_cpuid_reg(ebx)
+native_cpuid_reg(ecx)
+native_cpuid_reg(edx)
+
 static inline void load_cr3(pgd_t *pgdir)
 {
 	write_cr3(__pa(pgdir));
@@ -271,7 +304,7 @@ struct x86_hw_tss {
 	u16			reserved5;
 	u16			io_bitmap_base;
 
-} __attribute__((packed)) ____cacheline_aligned;
+} __attribute__((packed));
 #endif
 
 /*
@@ -309,6 +342,16 @@ struct tss_struct {
 
 DECLARE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss);
 
+/*
+ * sizeof(unsigned long) coming from an extra "long" at the end
+ * of the iobitmap.
+ *
+ * -1? seg base+limit should be pointing to the address of the
+ * last valid byte
+ */
+#define __KERNEL_TSS_LIMIT	\
+	(IO_BITMAP_OFFSET + IO_BITMAP_BYTES + sizeof(unsigned long) - 1)
+
 #ifdef CONFIG_X86_32
 DECLARE_PER_CPU(unsigned long, cpu_current_top_of_stack);
 #endif
@@ -588,43 +631,76 @@ static __always_inline void cpu_relax(void)
 	rep_nop();
 }
 
-#define cpu_relax_lowlatency() cpu_relax()
-
-/* Stop speculative execution and prefetching of modified code. */
+/*
+ * This function forces the icache and prefetched instruction stream to
+ * catch up with reality in two very specific cases:
+ *
+ *  a) Text was modified using one virtual address and is about to be executed
+ *     from the same physical page at a different virtual address.
+ *
+ *  b) Text was modified on a different CPU, may subsequently be
+ *     executed on this CPU, and you want to make sure the new version
+ *     gets executed.  This generally means you're calling this in a IPI.
+ *
+ * If you're calling this for a different reason, you're probably doing
+ * it wrong.
+ */
 static inline void sync_core(void)
 {
-	int tmp;
-
-#ifdef CONFIG_M486
 	/*
-	 * Do a CPUID if available, otherwise do a jump.  The jump
-	 * can conveniently enough be the jump around CPUID.
+	 * There are quite a few ways to do this.  IRET-to-self is nice
+	 * because it works on every CPU, at any CPL (so it's compatible
+	 * with paravirtualization), and it never exits to a hypervisor.
+	 * The only down sides are that it's a bit slow (it seems to be
+	 * a bit more than 2x slower than the fastest options) and that
+	 * it unmasks NMIs.  The "push %cs" is needed because, in
+	 * paravirtual environments, __KERNEL_CS may not be a valid CS
+	 * value when we do IRET directly.
+	 *
+	 * In case NMI unmasking or performance ever becomes a problem,
+	 * the next best option appears to be MOV-to-CR2 and an
+	 * unconditional jump.  That sequence also works on all CPUs,
+	 * but it will fault at CPL3 (i.e. Xen PV and lguest).
+	 *
+	 * CPUID is the conventional way, but it's nasty: it doesn't
+	 * exist on some 486-like CPUs, and it usually exits to a
+	 * hypervisor.
+	 *
+	 * Like all of Linux's memory ordering operations, this is a
+	 * compiler barrier as well.
 	 */
-	asm volatile("cmpl %2,%1\n\t"
-		     "jl 1f\n\t"
-		     "cpuid\n"
-		     "1:"
-		     : "=a" (tmp)
-		     : "rm" (boot_cpu_data.cpuid_level), "ri" (0), "0" (1)
-		     : "ebx", "ecx", "edx", "memory");
+	register void *__sp asm(_ASM_SP);
+
+#ifdef CONFIG_X86_32
+	asm volatile (
+		"pushfl\n\t"
+		"pushl %%cs\n\t"
+		"pushl $1f\n\t"
+		"iret\n\t"
+		"1:"
+		: "+r" (__sp) : : "memory");
 #else
-	/*
-	 * CPUID is a barrier to speculative execution.
-	 * Prefetched instructions are automatically
-	 * invalidated when modified.
-	 */
-	asm volatile("cpuid"
-		     : "=a" (tmp)
-		     : "0" (1)
-		     : "ebx", "ecx", "edx", "memory");
+	unsigned int tmp;
+
+	asm volatile (
+		"mov %%ss, %0\n\t"
+		"pushq %q0\n\t"
+		"pushq %%rsp\n\t"
+		"addq $8, (%%rsp)\n\t"
+		"pushfq\n\t"
+		"mov %%cs, %0\n\t"
+		"pushq %q0\n\t"
+		"pushq $1f\n\t"
+		"iretq\n\t"
+		"1:"
+		: "=&r" (tmp), "+r" (__sp) : : "cc", "memory");
 #endif
 }
 
 extern void select_idle_routine(const struct cpuinfo_x86 *c);
-extern void init_amd_e400_c1e_mask(void);
+extern void amd_e400_c1e_apic_setup(void);
 
 extern unsigned long		boot_option_idle_override;
-extern bool			amd_e400_c1e_detected;
 
 enum idle_boot_override {IDLE_NO_OVERRIDE=0, IDLE_HALT, IDLE_NOMWAIT,
 			 IDLE_POLL};