From 9267b4b3880d00dc2dab90f1d817c856939114f7 Mon Sep 17 00:00:00 2001
From: Ivan Kokshaysky <ink@jurassic.park.msu.ru>
Date: Sat, 21 Jun 2008 03:25:39 +0400
Subject: [PATCH] alpha: fix module load failures on smp (bug #10926)

To calculate addresses of locally defined variables, GCC uses 32-bit
displacement from the GP. Which doesn't work for per cpu variables in
modules, as an offset to the kernel per cpu area is way above 4G.

The workaround is to force allocation of a GOT entry for per cpu variable
using ldq instruction with a 'literal' relocation.
I had to use custom asm/percpu.h, as a required argument magic doesn't
work with asm-generic/percpu.h macros.

Signed-off-by: Ivan Kokshaysky <ink@jurassic.park.msu.ru>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/asm-alpha/percpu.h | 72 +++++++++++++++++++++++++++++++++++++-
 1 file changed, 71 insertions(+), 1 deletion(-)

diff --git a/include/asm-alpha/percpu.h b/include/asm-alpha/percpu.h
index 48348fe34c..82e8a94b4b 100644
--- a/include/asm-alpha/percpu.h
+++ b/include/asm-alpha/percpu.h
@@ -1,6 +1,76 @@
 #ifndef __ALPHA_PERCPU_H
 #define __ALPHA_PERCPU_H
+#include <linux/compiler.h>
+#include <linux/threads.h>
 
-#include <asm-generic/percpu.h>
+/*
+ * Determine the real variable name from the name visible in the
+ * kernel sources.
+ */
+#define per_cpu_var(var) per_cpu__##var
+
+#ifdef CONFIG_SMP
+
+/*
+ * per_cpu_offset() is the offset that has to be added to a
+ * percpu variable to get to the instance for a certain processor.
+ */
+extern unsigned long __per_cpu_offset[NR_CPUS];
+
+#define per_cpu_offset(x) (__per_cpu_offset[x])
+
+#define __my_cpu_offset per_cpu_offset(raw_smp_processor_id())
+#ifdef CONFIG_DEBUG_PREEMPT
+#define my_cpu_offset per_cpu_offset(smp_processor_id())
+#else
+#define my_cpu_offset __my_cpu_offset
+#endif
+
+#ifndef MODULE
+#define SHIFT_PERCPU_PTR(var, offset) RELOC_HIDE(&per_cpu_var(var), (offset))
+#define PER_CPU_ATTRIBUTES
+#else
+/*
+ * To calculate addresses of locally defined variables, GCC uses 32-bit
+ * displacement from the GP. Which doesn't work for per cpu variables in
+ * modules, as an offset to the kernel per cpu area is way above 4G.
+ *
+ * This forces allocation of a GOT entry for per cpu variable using
+ * ldq instruction with a 'literal' relocation.
+ */
+#define SHIFT_PERCPU_PTR(var, offset) ({		\
+	extern int simple_identifier_##var(void);	\
+	unsigned long __ptr, tmp_gp;			\
+	asm (  "br	%1, 1f		  	      \n\
+	1:	ldgp	%1, 0(%1)	    	      \n\
+		ldq %0, per_cpu__" #var"(%1)\t!literal"		\
+		: "=&r"(__ptr), "=&r"(tmp_gp));		\
+	(typeof(&per_cpu_var(var)))(__ptr + (offset)); })
+
+#define PER_CPU_ATTRIBUTES	__used
+
+#endif /* MODULE */
+
+/*
+ * A percpu variable may point to a discarded regions. The following are
+ * established ways to produce a usable pointer from the percpu variable
+ * offset.
+ */
+#define per_cpu(var, cpu) \
+	(*SHIFT_PERCPU_PTR(var, per_cpu_offset(cpu)))
+#define __get_cpu_var(var) \
+	(*SHIFT_PERCPU_PTR(var, my_cpu_offset))
+#define __raw_get_cpu_var(var) \
+	(*SHIFT_PERCPU_PTR(var, __my_cpu_offset))
+
+#else /* ! SMP */
+
+#define per_cpu(var, cpu)		(*((void)(cpu), &per_cpu_var(var)))
+#define __get_cpu_var(var)		per_cpu_var(var)
+#define __raw_get_cpu_var(var)		per_cpu_var(var)
+
+#endif /* SMP */
+
+#define DECLARE_PER_CPU(type, name) extern __typeof__(type) per_cpu_var(name)
 
 #endif /* __ALPHA_PERCPU_H */
-- 
2.39.5