MIPS: Outline udelay and fix a few issues.

Outlining fixes the issue were on certain CPUs such as the R10000 family
the delay loop would need an extra cycle if it overlaps a cacheline
boundary.

The rewrite also fixes build errors with GCC 4.4 which was changed in
way incompatible with the kernel's inline assembly.

Relying on pure C for computation of the delay value removes the need for
explicit.  The price we pay is a slight slowdown of the computation - to
be fixed on another day.

Signed-off-by: Ralf Baechle <ralf@linux-mips.org>

2 files changed, 58 insertions, 2 deletions

diff --git a/arch/mips/lib/Makefile b/arch/mips/lib/Makefile
index c13c7ad2cdae..2adead5a8a37 100644
--- a/arch/mips/lib/Makefile
+++ b/arch/mips/lib/Makefile
@@ -2,8 +2,8 @@
 # Makefile for MIPS-specific library files..
 #
 
-lib-y	+= csum_partial.o memcpy.o memcpy-inatomic.o memset.o strlen_user.o \
-	   strncpy_user.o strnlen_user.o uncached.o
+lib-y	+= csum_partial.o delay.o memcpy.o memcpy-inatomic.o memset.o \
+	   strlen_user.o strncpy_user.o strnlen_user.o uncached.o
 
 obj-y			+= iomap.o
 obj-$(CONFIG_PCI)	+= iomap-pci.o
diff --git a/arch/mips/lib/delay.c b/arch/mips/lib/delay.c
new file mode 100644
index 000000000000..f69c6b569eb3
--- /dev/null
+++ b/arch/mips/lib/delay.c
@@ -0,0 +1,56 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 1994 by Waldorf Electronics
+ * Copyright (C) 1995 - 2000, 01, 03 by Ralf Baechle
+ * Copyright (C) 1999, 2000 Silicon Graphics, Inc.
+ * Copyright (C) 2007  Maciej W. Rozycki
+ */
+#include <linux/module.h>
+#include <linux/param.h>
+#include <linux/smp.h>
+
+#include <asm/compiler.h>
+#include <asm/war.h>
+
+inline void __delay(unsigned int loops)
+{
+	__asm__ __volatile__ (
+	"	.set	noreorder				\n"
+	"	.align	3					\n"
+	"1:	bnez	%0, 1b					\n"
+	"	subu	%0, 1					\n"
+	"	.set	reorder					\n"
+	: "=r" (loops)
+	: "0" (loops));
+}
+EXPORT_SYMBOL(__delay);
+
+/*
+ * Division by multiplication: you don't have to worry about
+ * loss of precision.
+ *
+ * Use only for very small delays ( < 1 msec).  Should probably use a
+ * lookup table, really, as the multiplications take much too long with
+ * short delays.  This is a "reasonable" implementation, though (and the
+ * first constant multiplications gets optimized away if the delay is
+ * a constant)
+ */
+
+void __udelay(unsigned long us)
+{
+	unsigned int lpj = current_cpu_data.udelay_val;
+
+	__delay((us * 0x000010c7 * HZ * lpj) >> 32);
+}
+EXPORT_SYMBOL(__udelay);
+
+void __ndelay(unsigned long ns)
+{
+	unsigned int lpj = current_cpu_data.udelay_val;
+
+	__delay((us * 0x00000005 * HZ * lpj) >> 32);
+}
+EXPORT_SYMBOL(__ndelay);