x86/cpu: Relocate sync_core() to sync_core.h

Having sync_core() in processor.h is problematic since it is not possible
to check for hardware capabilities via the *cpu_has() family of macros.
The latter needs the definitions in processor.h.

It also looks more intuitive to relocate the function to sync_core.h.

This changeset does not make changes in functionality.
Signed-off-by: Ricardo Neri <ricardo.neri-calderon@linux.intel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Link: https://lore.kernel.org/r/20200727043132.15082-3-ricardo.neri-calderon@linux.intel.com

arch/x86/include/asm/processor.h

@@ -678,70 +678,6 @@ static inline unsigned int cpuid_edx(unsigned int op)
 	return edx;
 }
 
-/*
- * 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)
-{
-	/*
-	 * 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).
-	 *
-	 * 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.
-	 */
-#ifdef CONFIG_X86_32
-	asm volatile (
-		"pushfl\n\t"
-		"pushl %%cs\n\t"
-		"pushl $1f\n\t"
-		"iret\n\t"
-		"1:"
-		: ASM_CALL_CONSTRAINT : : "memory");
-#else
-	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), ASM_CALL_CONSTRAINT : : "cc", "memory");
-#endif
-}
-
 extern void select_idle_routine(const struct cpuinfo_x86 *c);
 extern void amd_e400_c1e_apic_setup(void);
 

arch/x86/include/asm/sync_core.h

@@ -6,6 +6,70 @@
 #include <asm/processor.h>
 #include <asm/cpufeature.h>
 
+/*
+ * 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)
+{
+	/*
+	 * 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).
+	 *
+	 * 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.
+	 */
+#ifdef CONFIG_X86_32
+	asm volatile (
+		"pushfl\n\t"
+		"pushl %%cs\n\t"
+		"pushl $1f\n\t"
+		"iret\n\t"
+		"1:"
+		: ASM_CALL_CONSTRAINT : : "memory");
+#else
+	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), ASM_CALL_CONSTRAINT : : "cc", "memory");
+#endif
+}
+
 /*
  * Ensure that a core serializing instruction is issued before returning
  * to user-mode. x86 implements return to user-space through sysexit,

arch/x86/kernel/alternative.c

@@ -15,6 +15,7 @@
 #include <linux/kprobes.h>
 #include <linux/mmu_context.h>
 #include <linux/bsearch.h>
+#include <linux/sync_core.h>
 #include <asm/text-patching.h>
 #include <asm/alternative.h>
 #include <asm/sections.h>

arch/x86/kernel/cpu/mce/core.c

@@ -42,6 +42,7 @@
 #include <linux/export.h>
 #include <linux/jump_label.h>
 #include <linux/set_memory.h>
+#include <linux/sync_core.h>
 #include <linux/task_work.h>
 #include <linux/hardirq.h>
 

drivers/misc/sgi-gru/grufault.c

@@ -20,6 +20,7 @@
 #include <linux/io.h>
 #include <linux/uaccess.h>
 #include <linux/security.h>
+#include <linux/sync_core.h>
 #include <linux/prefetch.h>
 #include "gru.h"
 #include "grutables.h"

drivers/misc/sgi-gru/gruhandles.c

@@ -16,6 +16,7 @@
 #define GRU_OPERATION_TIMEOUT	(((cycles_t) local_cpu_data->itc_freq)*10)
 #define CLKS2NSEC(c)		((c) *1000000000 / local_cpu_data->itc_freq)
 #else
+#include <linux/sync_core.h>
 #include <asm/tsc.h>
 #define GRU_OPERATION_TIMEOUT	((cycles_t) tsc_khz*10*1000)
 #define CLKS2NSEC(c)		((c) * 1000000 / tsc_khz)

drivers/misc/sgi-gru/grukservices.c

@@ -16,6 +16,7 @@
 #include <linux/miscdevice.h>
 #include <linux/proc_fs.h>
 #include <linux/interrupt.h>
+#include <linux/sync_core.h>
 #include <linux/uaccess.h>
 #include <linux/delay.h>
 #include <linux/export.h>