MIPS: Loongson-3: Enable COP2 usage in kernel

Loongson-3's COP2 is Multi-Media coprocessor, it is disabled in kernel
mode by default. However, gslq/gssq (16-bytes load/store instructions)
overrides the instruction format of lwc2/swc2. If we wan't to use gslq/
gssq for optimization in kernel, we should enable COP2 usage in kernel.

Please pay attention that in this patch we only enable COP2 in kernel,
which means it will lose ST0_CU2 when a process go to user space (try
to use COP2 in user space will trigger an exception and then grab COP2,
which is similar to FPU). And as a result, we need to modify the context
switching code because the new scheduled process doesn't contain ST0_CU2
in its THERAD_STATUS probably.

For zboot, we disable gslq/gssq be generated by toolchain.
Signed-off-by: Huacai Chen <chenhc@lemote.com>
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>

arch/mips/boot/compressed/Makefile

@@ -22,6 +22,11 @@ KBUILD_CFLAGS := $(filter-out -pg, $(KBUILD_CFLAGS))
 
 KBUILD_CFLAGS := $(filter-out -fstack-protector, $(KBUILD_CFLAGS))
 
+# Disable lq/sq in zboot
+ifdef CONFIG_CPU_LOONGSON64
+KBUILD_CFLAGS := $(filter-out -march=loongson3a, $(KBUILD_CFLAGS)) -march=mips64r2
+endif
+
 KBUILD_CFLAGS := $(KBUILD_CFLAGS) -D__KERNEL__ -D__DISABLE_EXPORTS \
 	-DBOOT_HEAP_SIZE=$(BOOT_HEAP_SIZE) -D"VMLINUX_LOAD_ADDRESS_ULL=$(VMLINUX_LOAD_ADDRESS)ull"
 

arch/mips/include/asm/mipsregs.h

@@ -389,6 +389,13 @@
 #define ST0_CU3			0x80000000
 #define ST0_XX			0x80000000	/* MIPS IV naming */
 
+/* in-kernel enabled CUs */
+#ifdef CONFIG_CPU_LOONGSON64
+#define ST0_KERNEL_CUMASK      (ST0_CU0 | ST0_CU2)
+#else
+#define ST0_KERNEL_CUMASK      ST0_CU0
+#endif
+
 /*
  * Bitfields and bit numbers in the coprocessor 0 IntCtl register. (MIPSR2)
  */

arch/mips/include/asm/stackframe.h

@@ -450,7 +450,7 @@
  */
 		.macro	CLI
 		mfc0	t0, CP0_STATUS
-		li	t1, ST0_CU0 | STATMASK
+		li	t1, ST0_KERNEL_CUMASK | STATMASK
 		or	t0, t1
 		xori	t0, STATMASK
 		mtc0	t0, CP0_STATUS
@@ -463,7 +463,7 @@
  */
 		.macro	STI
 		mfc0	t0, CP0_STATUS
-		li	t1, ST0_CU0 | STATMASK
+		li	t1, ST0_KERNEL_CUMASK | STATMASK
 		or	t0, t1
 		xori	t0, STATMASK & ~1
 		mtc0	t0, CP0_STATUS
@@ -477,7 +477,7 @@
  */
 		.macro	KMODE
 		mfc0	t0, CP0_STATUS
-		li	t1, ST0_CU0 | (STATMASK & ~1)
+		li	t1, ST0_KERNEL_CUMASK | (STATMASK & ~1)
 #if defined(CONFIG_CPU_R3000) || defined(CONFIG_CPU_TX39XX)
 		andi	t2, t0, ST0_IEP
 		srl	t2, 2

arch/mips/kernel/head.S

@@ -35,7 +35,7 @@
 	.macro	setup_c0_status set clr
 	.set	push
 	mfc0	t0, CP0_STATUS
-	or	t0, ST0_CU0|\set|0x1f|\clr
+	or	t0, ST0_KERNEL_CUMASK|\set|0x1f|\clr
 	xor	t0, 0x1f|\clr
 	mtc0	t0, CP0_STATUS
 	.set	noreorder

arch/mips/kernel/process.c

@@ -68,7 +68,7 @@ void start_thread(struct pt_regs * regs, unsigned long pc, unsigned long sp)
 	unsigned long status;
 
 	/* New thread loses kernel privileges. */
-	status = regs->cp0_status & ~(ST0_CU0|ST0_CU1|ST0_FR|KU_MASK);
+	status = regs->cp0_status & ~(ST0_CU0|ST0_CU1|ST0_CU2|ST0_FR|KU_MASK);
 	status |= KU_USER;
 	regs->cp0_status = status;
 	lose_fpu(0);
@@ -133,7 +133,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp,
 	childregs = (struct pt_regs *) childksp - 1;
 	/*  Put the stack after the struct pt_regs.  */
 	childksp = (unsigned long) childregs;
-	p->thread.cp0_status = read_c0_status() & ~(ST0_CU2|ST0_CU1);
+	p->thread.cp0_status = (read_c0_status() & ~(ST0_CU2|ST0_CU1)) | ST0_KERNEL_CUMASK;
 	if (unlikely(p->flags & PF_KTHREAD)) {
 		/* kernel thread */
 		unsigned long status = p->thread.cp0_status;

arch/mips/kernel/traps.c

@@ -2192,7 +2192,7 @@ static void configure_status(void)
 	 * flag that some firmware may have left set and the TS bit (for
 	 * IP27).  Set XX for ISA IV code to work.
 	 */
-	unsigned int status_set = ST0_CU0;
+	unsigned int status_set = ST0_KERNEL_CUMASK;
 #ifdef CONFIG_64BIT
 	status_set |= ST0_FR|ST0_KX|ST0_SX|ST0_UX;
 #endif