x86/entry/64: Introduce the FIND_PERCPU_BASE macro

GSBASE is used to find per-CPU data in the kernel. But when GSBASE is
unknown, the per-CPU base can be found from the per_cpu_offset table with a
CPU NR.  The CPU NR is extracted from the limit field of the CPUNODE entry
in GDT, or by the RDPID instruction. This is a prerequisite for using
FSGSBASE in the low level entry code.

Also, add the GAS-compatible RDPID macro as binutils 2.23 do not support
it. Support is added in version 2.27.

[ tglx: Massaged changelog ]

Suggested-by: H. Peter Anvin <hpa@zytor.com>
Signed-off-by: Chang S. Bae <chang.seok.bae@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Sasha Levin <sashal@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/r/1557309753-24073-12-git-send-email-chang.seok.bae@intel.com
Link: https://lkml.kernel.org/r/20200528201402.1708239-11-sashal@kernel.org

arch/x86/entry/calling.h

@@ -6,6 +6,7 @@
 #include <asm/percpu.h>
 #include <asm/asm-offsets.h>
 #include <asm/processor-flags.h>
+#include <asm/inst.h>
 
 /*
 
@@ -351,3 +352,36 @@ For 32-bit we have the following conventions - kernel is built with
 	call stackleak_erase
 #endif
 .endm
+
+#ifdef CONFIG_SMP
+
+/*
+ * CPU/node NR is loaded from the limit (size) field of a special segment
+ * descriptor entry in GDT.
+ */
+.macro LOAD_CPU_AND_NODE_SEG_LIMIT reg:req
+	movq	$__CPUNODE_SEG, \reg
+	lsl	\reg, \reg
+.endm
+
+/*
+ * Fetch the per-CPU GSBASE value for this processor and put it in @reg.
+ * We normally use %gs for accessing per-CPU data, but we are setting up
+ * %gs here and obviously can not use %gs itself to access per-CPU data.
+ */
+.macro GET_PERCPU_BASE reg:req
+	ALTERNATIVE \
+		"LOAD_CPU_AND_NODE_SEG_LIMIT \reg", \
+		"RDPID	\reg", \
+		X86_FEATURE_RDPID
+	andq	$VDSO_CPUNODE_MASK, \reg
+	movq	__per_cpu_offset(, \reg, 8), \reg
+.endm
+
+#else
+
+.macro GET_PERCPU_BASE reg:req
+	movq	pcpu_unit_offsets(%rip), \reg
+.endm
+
+#endif /* CONFIG_SMP */