diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 67c9d73b31fa..e21ec970d41a 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -670,7 +670,6 @@ extern struct desc_ptr		early_gdt_descr;
 extern void switch_to_new_gdt(int);
 extern void load_direct_gdt(int);
 extern void load_fixmap_gdt(int);
-extern void load_percpu_segment(int);
 extern void cpu_init(void);
 extern void cpu_init_secondary(void);
 extern void cpu_init_exception_handling(void);
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 3e508f239098..c09abee6f4d5 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -701,16 +701,6 @@ static const char *table_lookup_model(struct cpuinfo_x86 *c)
 __u32 cpu_caps_cleared[NCAPINTS + NBUGINTS] __aligned(sizeof(unsigned long));
 __u32 cpu_caps_set[NCAPINTS + NBUGINTS] __aligned(sizeof(unsigned long));
 
-void load_percpu_segment(int cpu)
-{
-#ifdef CONFIG_X86_32
-	loadsegment(fs, __KERNEL_PERCPU);
-#else
-	__loadsegment_simple(gs, 0);
-	wrmsrl(MSR_GS_BASE, cpu_kernelmode_gs_base(cpu));
-#endif
-}
-
 #ifdef CONFIG_X86_32
 /* The 32-bit entry code needs to find cpu_entry_area. */
 DEFINE_PER_CPU(struct cpu_entry_area *, cpu_entry_area);
@@ -738,16 +728,41 @@ void load_fixmap_gdt(int cpu)
 }
 EXPORT_SYMBOL_GPL(load_fixmap_gdt);
 
-/*
- * Current gdt points %fs at the "master" per-cpu area: after this,
- * it's on the real one.
+/**
+ * switch_to_new_gdt - Switch form early GDT to the direct one
+ * @cpu:	The CPU number for which this is invoked
+ *
+ * Invoked during early boot to switch from early GDT and early per CPU
+ * (%fs on 32bit, GS_BASE on 64bit) to the direct GDT and the runtime per
+ * CPU area.
  */
 void switch_to_new_gdt(int cpu)
 {
-	/* Load the original GDT */
 	load_direct_gdt(cpu);
-	/* Reload the per-cpu base */
-	load_percpu_segment(cpu);
+
+#ifdef CONFIG_X86_64
+	/*
+	 * No need to load %gs. It is already correct.
+	 *
+	 * Writing %gs on 64bit would zero GSBASE which would make any per
+	 * CPU operation up to the point of the wrmsrl() fault.
+	 *
+	 * Set GSBASE to the new offset. Until the wrmsrl() happens the
+	 * early mapping is still valid. That means the GSBASE update will
+	 * lose any prior per CPU data which was not copied over in
+	 * setup_per_cpu_areas().
+	 */
+	wrmsrl(MSR_GS_BASE, cpu_kernelmode_gs_base(cpu));
+#else
+	/*
+	 * %fs is already set to __KERNEL_PERCPU, but after switching GDT
+	 * it is required to load FS again so that the 'hidden' part is
+	 * updated from the new GDT. Up to this point the early per CPU
+	 * translation is active. Any content of the early per CPU data
+	 * which was not copied over in setup_per_cpu_areas() is lost.
+	 */
+	loadsegment(fs, __KERNEL_PERCPU);
+#endif
 }
 
 static const struct cpu_dev *cpu_devs[X86_VENDOR_NUM] = {};