[PATCH v9 06/17] x86/entry/64: Introduce the FIND_PERCPU_BASE macro

["Chang S. Bae" <chang.seok.bae@intel.com>]

GS base is used to find per-CPU data in the kernel. But when GS base 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 2.21 does not support
it. Support is added in version 2.27.

Suggested-by: H. Peter Anvin <hpa@zytor.com>
Signed-off-by: Chang S. Bae <chang.seok.bae@intel.com>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Vegard Nossum <vegard.nossum@oracle.com>
---

Changes from v8: none

Changes from v7:
* No code change
* Massaged changelog by Thomas
* Used 'GS base' consistently, instead of 'GSBASE'
---
 arch/x86/entry/calling.h    | 34 ++++++++++++++++++++++++++++++++++
 arch/x86/include/asm/inst.h | 15 +++++++++++++++
 2 files changed, 49 insertions(+)

diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h
index 515c0ce..c222302 100644
--- a/arch/x86/entry/calling.h
+++ b/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>
 
 /*
 
@@ -347,6 +348,39 @@ For 32-bit we have the following conventions - kernel is built with
 #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 GS base 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 */
+
 /*
  * This does 'call enter_from_user_mode' unless we can avoid it based on
  * kernel config or using the static jump infrastructure.
diff --git a/arch/x86/include/asm/inst.h b/arch/x86/include/asm/inst.h
index f5a796d..d063841 100644
--- a/arch/x86/include/asm/inst.h
+++ b/arch/x86/include/asm/inst.h
@@ -306,6 +306,21 @@
 	.endif
 	MODRM 0xc0 movq_r64_xmm_opd1 movq_r64_xmm_opd2
 	.endm
+
+.macro RDPID opd
+	REG_TYPE rdpid_opd_type \opd
+	.if rdpid_opd_type == REG_TYPE_R64
+	R64_NUM rdpid_opd \opd
+	.else
+	R32_NUM rdpid_opd \opd
+	.endif
+	.byte 0xf3
+	.if rdpid_opd > 7
+	PFX_REX rdpid_opd 0
+	.endif
+	.byte 0x0f, 0xc7
+	MODRM 0xc0 rdpid_opd 0x7
+.endm
 #endif
 
 #endif
-- 
2.7.4