ARM: pxa: add iwmmx support for PJ4

iwmmxt is used in XScale, XScale3, Mohawk and PJ4 core. But the instructions
of accessing CP0 and CP1 is changed in PJ4. Append more files to support
iwmmxt in PJ4 core.

Signed-off-by: Zhou Zhu <zzhu3@marvell.com>
Signed-off-by: Haojian Zhuang <haojian.zhuang@marvell.com>
Acked-by: Nicolas Pitre <nico@fluxnic.net>
Signed-off-by: Eric Miao <eric.y.miao@gmail.com>

arch/arm/Kconfig

@@ -999,8 +999,8 @@ source arch/arm/mm/Kconfig
 
 config IWMMXT
 	bool "Enable iWMMXt support"
-	depends on CPU_XSCALE || CPU_XSC3 || CPU_MOHAWK
-	default y if PXA27x || PXA3xx || ARCH_MMP
+	depends on CPU_XSCALE || CPU_XSC3 || CPU_MOHAWK || CPU_PJ4
+	default y if PXA27x || PXA3xx || PXA95x || ARCH_MMP
 	help
 	  Enable support for iWMMXt context switching at run time if
 	  running on a CPU that supports it.

arch/arm/kernel/Makefile

@@ -50,6 +50,7 @@ AFLAGS_crunch-bits.o		:= -Wa,-mcpu=ep9312
 obj-$(CONFIG_CPU_XSCALE)	+= xscale-cp0.o
 obj-$(CONFIG_CPU_XSC3)		+= xscale-cp0.o
 obj-$(CONFIG_CPU_MOHAWK)	+= xscale-cp0.o
+obj-$(CONFIG_CPU_PJ4)		+= pj4-cp0.o
 obj-$(CONFIG_IWMMXT)		+= iwmmxt.o
 obj-$(CONFIG_CPU_HAS_PMU)	+= pmu.o
 obj-$(CONFIG_HW_PERF_EVENTS)	+= perf_event.o

arch/arm/kernel/iwmmxt.S

@@ -19,6 +19,14 @@
 #include <asm/thread_info.h>
 #include <asm/asm-offsets.h>
 
+#if defined(CONFIG_CPU_PJ4)
+#define PJ4(code...)		code
+#define XSC(code...)
+#else
+#define PJ4(code...)
+#define XSC(code...)		code
+#endif
+
 #define MMX_WR0		 	(0x00)
 #define MMX_WR1		 	(0x08)
 #define MMX_WR2		 	(0x10)
@@ -58,11 +66,17 @@
 
 ENTRY(iwmmxt_task_enable)
 
-	mrc	p15, 0, r2, c15, c1, 0
-	tst	r2, #0x3			@ CP0 and CP1 accessible?
+	XSC(mrc	p15, 0, r2, c15, c1, 0)
+	PJ4(mrc p15, 0, r2, c1, c0, 2)
+	@ CP0 and CP1 accessible?
+	XSC(tst	r2, #0x3)
+	PJ4(tst	r2, #0xf)
 	movne	pc, lr				@ if so no business here
-	orr	r2, r2, #0x3			@ enable access to CP0 and CP1
-	mcr	p15, 0, r2, c15, c1, 0
+	@ enable access to CP0 and CP1
+	XSC(orr	r2, r2, #0x3)
+	XSC(mcr	p15, 0, r2, c15, c1, 0)
+	PJ4(orr	r2, r2, #0xf)
+	PJ4(mcr	p15, 0, r2, c1, c0, 2)
 
 	ldr	r3, =concan_owner
 	add	r0, r10, #TI_IWMMXT_STATE	@ get task Concan save area
@@ -179,17 +193,26 @@ ENTRY(iwmmxt_task_disable)
 	teqne	r1, r2				@ or specified one?
 	bne	1f				@ no: quit
 
-	mrc	p15, 0, r4, c15, c1, 0
-	orr	r4, r4, #0x3			@ enable access to CP0 and CP1
-	mcr	p15, 0, r4, c15, c1, 0
+	@ enable access to CP0 and CP1
+	XSC(mrc	p15, 0, r4, c15, c1, 0)
+	XSC(orr	r4, r4, #0xf)
+	XSC(mcr	p15, 0, r4, c15, c1, 0)
+	PJ4(mrc p15, 0, r4, c1, c0, 2)
+	PJ4(orr	r4, r4, #0x3)
+	PJ4(mcr	p15, 0, r4, c1, c0, 2)
+
 	mov	r0, #0				@ nothing to load
 	str	r0, [r3]			@ no more current owner
 	mrc	p15, 0, r2, c2, c0, 0
 	mov	r2, r2				@ cpwait
 	bl	concan_save
 
-	bic	r4, r4, #0x3			@ disable access to CP0 and CP1
-	mcr	p15, 0, r4, c15, c1, 0
+	@ disable access to CP0 and CP1
+	XSC(bic	r4, r4, #0x3)
+	XSC(mcr	p15, 0, r4, c15, c1, 0)
+	PJ4(bic	r4, r4, #0xf)
+	PJ4(mcr	p15, 0, r4, c1, c0, 2)
+
 	mrc	p15, 0, r2, c2, c0, 0
 	mov	r2, r2				@ cpwait
 
@@ -277,8 +300,11 @@ ENTRY(iwmmxt_task_restore)
  */
 ENTRY(iwmmxt_task_switch)
 
-	mrc	p15, 0, r1, c15, c1, 0
-	tst	r1, #0x3			@ CP0 and CP1 accessible?
+	XSC(mrc	p15, 0, r1, c15, c1, 0)
+	PJ4(mrc	p15, 0, r1, c1, c0, 2)
+	@ CP0 and CP1 accessible?
+	XSC(tst	r1, #0x3)
+	PJ4(tst	r1, #0xf)
 	bne	1f				@ yes: block them for next task
 
 	ldr	r2, =concan_owner
@@ -287,8 +313,11 @@ ENTRY(iwmmxt_task_switch)
 	teq	r2, r3				@ next task owns it?
 	movne	pc, lr				@ no: leave Concan disabled
 
-1:	eor	r1, r1, #3			@ flip Concan access
-	mcr	p15, 0, r1, c15, c1, 0
+1:	@ flip Conan access
+	XSC(eor	r1, r1, #0x3)
+	XSC(mcr	p15, 0, r1, c15, c1, 0)
+	PJ4(eor r1, r1, #0xf)
+	PJ4(mcr	p15, 0, r1, c1, c0, 2)
 
 	mrc	p15, 0, r1, c2, c0, 0
 	sub	pc, lr, r1, lsr #32		@ cpwait and return

arch/arm/kernel/pj4-cp0.c

@@ -0,0 +1,94 @@
+/*
+ * linux/arch/arm/kernel/pj4-cp0.c
+ *
+ * PJ4 iWMMXt coprocessor context switching and handling
+ *
+ * Copyright (c) 2010 Marvell International Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/signal.h>
+#include <linux/sched.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <asm/thread_notify.h>
+
+static int iwmmxt_do(struct notifier_block *self, unsigned long cmd, void *t)
+{
+	struct thread_info *thread = t;
+
+	switch (cmd) {
+	case THREAD_NOTIFY_FLUSH:
+		/*
+		 * flush_thread() zeroes thread->fpstate, so no need
+		 * to do anything here.
+		 *
+		 * FALLTHROUGH: Ensure we don't try to overwrite our newly
+		 * initialised state information on the first fault.
+		 */
+
+	case THREAD_NOTIFY_EXIT:
+		iwmmxt_task_release(thread);
+		break;
+
+	case THREAD_NOTIFY_SWITCH:
+		iwmmxt_task_switch(thread);
+		break;
+	}
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block iwmmxt_notifier_block = {
+	.notifier_call	= iwmmxt_do,
+};
+
+
+static u32 __init pj4_cp_access_read(void)
+{
+	u32 value;
+
+	__asm__ __volatile__ (
+		"mrc	p15, 0, %0, c1, c0, 2\n\t"
+		: "=r" (value));
+	return value;
+}
+
+static void __init pj4_cp_access_write(u32 value)
+{
+	u32 temp;
+
+	__asm__ __volatile__ (
+		"mcr	p15, 0, %1, c1, c0, 2\n\t"
+		"mrc	p15, 0, %0, c1, c0, 2\n\t"
+		"mov	%0, %0\n\t"
+		"sub	pc, pc, #4\n\t"
+		: "=r" (temp) : "r" (value));
+}
+
+
+/*
+ * Disable CP0/CP1 on boot, and let call_fpe() and the iWMMXt lazy
+ * switch code handle iWMMXt context switching.
+ */
+static int __init pj4_cp0_init(void)
+{
+	u32 cp_access;
+
+	cp_access = pj4_cp_access_read() & ~0xf;
+	pj4_cp_access_write(cp_access);
+
+	printk(KERN_INFO "PJ4 iWMMXt coprocessor enabled.\n");
+	elf_hwcap |= HWCAP_IWMMXT;
+	thread_register_notifier(&iwmmxt_notifier_block);
+
+	return 0;
+}
+
+late_initcall(pj4_cp0_init);