x86-64: Move current task from PDA to per-cpu and consolidate with 32-bit.

Signed-off-by: Brian Gerst <brgerst@gmail.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
diff --git a/arch/x86/include/asm/system.h b/arch/x86/include/asm/system.h
index 8e626ea..4399aac 100644
--- a/arch/x86/include/asm/system.h
+++ b/arch/x86/include/asm/system.h
@@ -94,7 +94,7 @@
 	     "call __switch_to\n\t"					  \
 	     ".globl thread_return\n"					  \
 	     "thread_return:\n\t"					  \
-	     "movq %%gs:%P[pda_pcurrent],%%rsi\n\t"			  \
+	     "movq "__percpu_seg_str"%P[current_task],%%rsi\n\t"	  \
 	     "movq %P[thread_info](%%rsi),%%r8\n\t"			  \
 	     LOCK_PREFIX "btr  %[tif_fork],%P[ti_flags](%%r8)\n\t"	  \
 	     "movq %%rax,%%rdi\n\t" 					  \
@@ -106,7 +106,7 @@
 	       [ti_flags] "i" (offsetof(struct thread_info, flags)),	  \
 	       [tif_fork] "i" (TIF_FORK),			  	  \
 	       [thread_info] "i" (offsetof(struct task_struct, stack)),   \
-	       [pda_pcurrent] "i" (offsetof(struct x8664_pda, pcurrent))  \
+	       [current_task] "m" (per_cpu_var(current_task))		  \
 	     : "memory", "cc" __EXTRA_CLOBBER)
 #endif