nds32: Support FP emulation

The Andes FPU coprocessor does not support denormalized number handling.
According to the specification, FPU generates a denorm input exception
that requires the kernel to deal with this instrution operation when it
encounters denormalized operands. Hence an nds32 FPU ISA emulator in the
kernel is required to meet requirement.

Signed-off-by: Vincent Chen <vincentc@andestech.com>
Signed-off-by: Nickhu <nickhu@andestech.com>
Acked-by: Greentime Hu <greentime@andestech.com>
Signed-off-by: Greentime Hu <greentime@andestech.com>

24 files changed, 1064 insertions, 5 deletions

diff --git a/arch/nds32/Makefile b/arch/nds32/Makefile
index 6dc03206e3c9..0a935c136ec2 100644
--- a/arch/nds32/Makefile
+++ b/arch/nds32/Makefile
@@ -30,6 +30,7 @@ export	TEXTADDR
 
 # If we have a machine-specific directory, then include it in the build.
 core-y				+= arch/nds32/kernel/ arch/nds32/mm/
+core-$(CONFIG_FPU)              += arch/nds32/math-emu/
 libs-y				+= arch/nds32/lib/
 
 ifneq '$(CONFIG_NDS32_BUILTIN_DTB)' '""'
diff --git a/arch/nds32/include/asm/fpu.h b/arch/nds32/include/asm/fpu.h
index f7a7f6b2ea8f..9b1107b58e23 100644
--- a/arch/nds32/include/asm/fpu.h
+++ b/arch/nds32/include/asm/fpu.h
@@ -15,6 +15,7 @@ extern bool has_fpu;
 extern void save_fpu(struct task_struct *__tsk);
 extern void load_fpu(const struct fpu_struct *fpregs);
 extern bool do_fpu_exception(unsigned int subtype, struct pt_regs *regs);
+extern int do_fpuemu(struct pt_regs *regs, struct fpu_struct *fpu);
 
 #define test_tsk_fpu(regs)	(regs->fucop_ctl & FUCOP_CTL_mskCP0EN)
 
diff --git a/arch/nds32/include/asm/fpuemu.h b/arch/nds32/include/asm/fpuemu.h
new file mode 100644
index 000000000000..c4bd0c7faa75
--- /dev/null
+++ b/arch/nds32/include/asm/fpuemu.h
@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2005-2018 Andes Technology Corporation */
+
+#ifndef __ARCH_NDS32_FPUEMU_H
+#define __ARCH_NDS32_FPUEMU_H
+
+/*
+ * single precision
+ */
+
+void fadds(void *ft, void *fa, void *fb);
+void fsubs(void *ft, void *fa, void *fb);
+void fmuls(void *ft, void *fa, void *fb);
+void fdivs(void *ft, void *fa, void *fb);
+void fs2d(void *ft, void *fa);
+void fsqrts(void *ft, void *fa);
+void fnegs(void *ft, void *fa);
+int fcmps(void *ft, void *fa, void *fb, int cop);
+
+/*
+ * double precision
+ */
+void faddd(void *ft, void *fa, void *fb);
+void fsubd(void *ft, void *fa, void *fb);
+void fmuld(void *ft, void *fa, void *fb);
+void fdivd(void *ft, void *fa, void *fb);
+void fsqrtd(void *ft, void *fa);
+void fd2s(void *ft, void *fa);
+void fnegd(void *ft, void *fa);
+int fcmpd(void *ft, void *fa, void *fb, int cop);
+
+#endif /* __ARCH_NDS32_FPUEMU_H */
diff --git a/arch/nds32/include/asm/nds32_fpu_inst.h b/arch/nds32/include/asm/nds32_fpu_inst.h
new file mode 100644
index 000000000000..1e4b86a90a48
--- /dev/null
+++ b/arch/nds32/include/asm/nds32_fpu_inst.h
@@ -0,0 +1,109 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2005-2018 Andes Technology Corporation */
+
+#ifndef __NDS32_FPU_INST_H
+#define __NDS32_FPU_INST_H
+
+#define cop0_op	0x35
+
+/*
+ * COP0 field of opcodes.
+ */
+#define fs1_op	0x0
+#define fs2_op  0x4
+#define fd1_op  0x8
+#define fd2_op  0xc
+
+/*
+ * FS1 opcode.
+ */
+enum fs1 {
+	fadds_op, fsubs_op, fcpynss_op, fcpyss_op,
+	fmadds_op, fmsubs_op, fcmovns_op, fcmovzs_op,
+	fnmadds_op, fnmsubs_op,
+	fmuls_op = 0xc, fdivs_op,
+	fs1_f2op_op = 0xf
+};
+
+/*
+ * FS1/F2OP opcode.
+ */
+enum fs1_f2 {
+	fs2d_op, fsqrts_op,
+	fui2s_op = 0x8, fsi2s_op = 0xc,
+	fs2ui_op = 0x10, fs2ui_z_op = 0x14,
+	fs2si_op = 0x18, fs2si_z_op = 0x1c
+};
+
+/*
+ * FS2 opcode.
+ */
+enum fs2 {
+	fcmpeqs_op, fcmpeqs_e_op, fcmplts_op, fcmplts_e_op,
+	fcmples_op, fcmples_e_op, fcmpuns_op, fcmpuns_e_op
+};
+
+/*
+ * FD1 opcode.
+ */
+enum fd1 {
+	faddd_op, fsubd_op, fcpynsd_op, fcpysd_op,
+	fmaddd_op, fmsubd_op, fcmovnd_op, fcmovzd_op,
+	fnmaddd_op, fnmsubd_op,
+	fmuld_op = 0xc, fdivd_op, fd1_f2op_op = 0xf
+};
+
+/*
+ * FD1/F2OP opcode.
+ */
+enum fd1_f2 {
+	fd2s_op, fsqrtd_op,
+	fui2d_op = 0x8, fsi2d_op = 0xc,
+	fd2ui_op = 0x10, fd2ui_z_op = 0x14,
+	fd2si_op = 0x18, fd2si_z_op = 0x1c
+};
+
+/*
+ * FD2 opcode.
+ */
+enum fd2 {
+	fcmpeqd_op, fcmpeqd_e_op, fcmpltd_op, fcmpltd_e_op,
+	fcmpled_op, fcmpled_e_op, fcmpund_op, fcmpund_e_op
+};
+
+#define NDS32Insn(x) x
+
+#define I_OPCODE_off			25
+#define NDS32Insn_OPCODE(x)		(NDS32Insn(x) >> I_OPCODE_off)
+
+#define I_OPCODE_offRt			20
+#define I_OPCODE_mskRt			(0x1fUL << I_OPCODE_offRt)
+#define NDS32Insn_OPCODE_Rt(x) \
+	((NDS32Insn(x) & I_OPCODE_mskRt) >> I_OPCODE_offRt)
+
+#define I_OPCODE_offRa			15
+#define I_OPCODE_mskRa			(0x1fUL << I_OPCODE_offRa)
+#define NDS32Insn_OPCODE_Ra(x) \
+	((NDS32Insn(x) & I_OPCODE_mskRa) >> I_OPCODE_offRa)
+
+#define I_OPCODE_offRb			10
+#define I_OPCODE_mskRb			(0x1fUL << I_OPCODE_offRb)
+#define NDS32Insn_OPCODE_Rb(x) \
+	((NDS32Insn(x) & I_OPCODE_mskRb) >> I_OPCODE_offRb)
+
+#define I_OPCODE_offbit1014		10
+#define I_OPCODE_mskbit1014		(0x1fUL << I_OPCODE_offbit1014)
+#define NDS32Insn_OPCODE_BIT1014(x) \
+	((NDS32Insn(x) & I_OPCODE_mskbit1014) >> I_OPCODE_offbit1014)
+
+#define I_OPCODE_offbit69		6
+#define I_OPCODE_mskbit69		(0xfUL << I_OPCODE_offbit69)
+#define NDS32Insn_OPCODE_BIT69(x) \
+	((NDS32Insn(x) & I_OPCODE_mskbit69) >> I_OPCODE_offbit69)
+
+#define I_OPCODE_offCOP0		0
+#define I_OPCODE_mskCOP0		(0x3fUL << I_OPCODE_offCOP0)
+#define NDS32Insn_OPCODE_COP0(x) \
+	((NDS32Insn(x) & I_OPCODE_mskCOP0) >> I_OPCODE_offCOP0)
+
+#endif /* __NDS32_FPU_INST_H */
diff --git a/arch/nds32/include/asm/sfp-machine.h b/arch/nds32/include/asm/sfp-machine.h
new file mode 100644
index 000000000000..b1a5caa332b5
--- /dev/null
+++ b/arch/nds32/include/asm/sfp-machine.h
@@ -0,0 +1,158 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2005-2018 Andes Technology Corporation */
+
+#include <asm/bitfield.h>
+
+#define _FP_W_TYPE_SIZE		32
+#define _FP_W_TYPE		unsigned long
+#define _FP_WS_TYPE		signed long
+#define _FP_I_TYPE		long
+
+#define __ll_B ((UWtype) 1 << (W_TYPE_SIZE / 2))
+#define __ll_lowpart(t) ((UWtype) (t) & (__ll_B - 1))
+#define __ll_highpart(t) ((UWtype) (t) >> (W_TYPE_SIZE / 2))
+
+#define _FP_MUL_MEAT_S(R, X, Y)				\
+	_FP_MUL_MEAT_1_wide(_FP_WFRACBITS_S, R, X, Y, umul_ppmm)
+#define _FP_MUL_MEAT_D(R, X, Y)				\
+	_FP_MUL_MEAT_2_wide(_FP_WFRACBITS_D, R, X, Y, umul_ppmm)
+#define _FP_MUL_MEAT_Q(R, X, Y)				\
+	_FP_MUL_MEAT_4_wide(_FP_WFRACBITS_Q, R, X, Y, umul_ppmm)
+
+#define _FP_MUL_MEAT_DW_S(R, X, Y)			\
+	_FP_MUL_MEAT_DW_1_wide(_FP_WFRACBITS_S, R, X, Y, umul_ppmm)
+#define _FP_MUL_MEAT_DW_D(R, X, Y)			\
+	_FP_MUL_MEAT_DW_2_wide(_FP_WFRACBITS_D, R, X, Y, umul_ppmm)
+
+#define _FP_DIV_MEAT_S(R, X, Y)	_FP_DIV_MEAT_1_udiv_norm(S, R, X, Y)
+#define _FP_DIV_MEAT_D(R, X, Y)	_FP_DIV_MEAT_2_udiv(D, R, X, Y)
+
+#define _FP_NANFRAC_S		((_FP_QNANBIT_S << 1) - 1)
+#define _FP_NANFRAC_D		((_FP_QNANBIT_D << 1) - 1), -1
+#define _FP_NANFRAC_Q		((_FP_QNANBIT_Q << 1) - 1), -1, -1, -1
+#define _FP_NANSIGN_S		0
+#define _FP_NANSIGN_D		0
+#define _FP_NANSIGN_Q		0
+
+#define _FP_KEEPNANFRACP 1
+#define _FP_QNANNEGATEDP 0
+
+#define _FP_CHOOSENAN(fs, wc, R, X, Y, OP)			\
+do {								\
+	if ((_FP_FRAC_HIGH_RAW_##fs(X) & _FP_QNANBIT_##fs)	\
+	  && !(_FP_FRAC_HIGH_RAW_##fs(Y) & _FP_QNANBIT_##fs)) { \
+		R##_s = Y##_s;					\
+		_FP_FRAC_COPY_##wc(R, Y);			\
+	} else {						\
+		R##_s = X##_s;					\
+		_FP_FRAC_COPY_##wc(R, X);			\
+	}							\
+	R##_c = FP_CLS_NAN;					\
+} while (0)
+
+#define __FPU_FPCSR	(current->thread.fpu.fpcsr)
+
+/* Obtain the current rounding mode. */
+#define FP_ROUNDMODE                    \
+({                                      \
+	__FPU_FPCSR & FPCSR_mskRM;      \
+})
+
+#define FP_RND_NEAREST		0
+#define FP_RND_PINF		1
+#define FP_RND_MINF		2
+#define FP_RND_ZERO		3
+
+#define FP_EX_INVALID		FPCSR_mskIVO
+#define FP_EX_DIVZERO		FPCSR_mskDBZ
+#define FP_EX_OVERFLOW		FPCSR_mskOVF
+#define FP_EX_UNDERFLOW		FPCSR_mskUDF
+#define FP_EX_INEXACT		FPCSR_mskIEX
+
+#define SF_CEQ	2
+#define SF_CLT	1
+#define SF_CGT	3
+#define SF_CUN	4
+
+#include <asm/byteorder.h>
+
+#ifdef __BIG_ENDIAN__
+#define __BYTE_ORDER __BIG_ENDIAN
+#define __LITTLE_ENDIAN 0
+#else
+#define __BYTE_ORDER __LITTLE_ENDIAN
+#define __BIG_ENDIAN 0
+#endif
+
+#define abort() do { } while (0)
+#define umul_ppmm(w1, w0, u, v)						\
+do {									\
+	UWtype __x0, __x1, __x2, __x3;                                  \
+	UHWtype __ul, __vl, __uh, __vh;                                 \
+									\
+	__ul = __ll_lowpart(u);						\
+	__uh = __ll_highpart(u);					\
+	__vl = __ll_lowpart(v);						\
+	__vh = __ll_highpart(v);					\
+									\
+	__x0 = (UWtype) __ul * __vl;                                    \
+	__x1 = (UWtype) __ul * __vh;                                    \
+	__x2 = (UWtype) __uh * __vl;                                    \
+	__x3 = (UWtype) __uh * __vh;                                    \
+									\
+	__x1 += __ll_highpart(__x0);					\
+	__x1 += __x2;							\
+	if (__x1 < __x2)						\
+		__x3 += __ll_B;						\
+									\
+	(w1) = __x3 + __ll_highpart(__x1);				\
+	(w0) = __ll_lowpart(__x1) * __ll_B + __ll_lowpart(__x0);	\
+} while (0)
+
+#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
+do { \
+	UWtype __x; \
+	__x = (al) + (bl); \
+	(sh) = (ah) + (bh) + (__x < (al)); \
+	(sl) = __x; \
+} while (0)
+
+#define sub_ddmmss(sh, sl, ah, al, bh, bl) \
+do { \
+	UWtype __x; \
+	__x = (al) - (bl); \
+	(sh) = (ah) - (bh) - (__x > (al)); \
+	(sl) = __x; \
+} while (0)
+
+#define udiv_qrnnd(q, r, n1, n0, d)				\
+do {								\
+	UWtype __d1, __d0, __q1, __q0, __r1, __r0, __m;		\
+	__d1 = __ll_highpart(d);				\
+	__d0 = __ll_lowpart(d);					\
+								\
+	__r1 = (n1) % __d1;					\
+	__q1 = (n1) / __d1;					\
+	__m = (UWtype) __q1 * __d0;				\
+	__r1 = __r1 * __ll_B | __ll_highpart(n0);		\
+	if (__r1 < __m)	{					\
+		__q1--, __r1 += (d);				\
+		if (__r1 >= (d))				\
+			if (__r1 < __m)				\
+				__q1--, __r1 += (d);		\
+	}							\
+	__r1 -= __m;						\
+	__r0 = __r1 % __d1;					\
+	__q0 = __r1 / __d1;					\
+	__m = (UWtype) __q0 * __d0;				\
+	__r0 = __r0 * __ll_B | __ll_lowpart(n0);		\
+	if (__r0 < __m)	{					\
+		__q0--, __r0 += (d);				\
+		if (__r0 >= (d))				\
+			if (__r0 < __m)				\
+				__q0--, __r0 += (d);		\
+	}							\
+	__r0 -= __m;						\
+	(q) = (UWtype) __q1 * __ll_B | __q0;			\
+	(r) = __r0;						\
+} while (0)
diff --git a/arch/nds32/kernel/fpu.c b/arch/nds32/kernel/fpu.c
index e55a1e190e97..2942df6f93e6 100644
--- a/arch/nds32/kernel/fpu.c
+++ b/arch/nds32/kernel/fpu.c
@@ -183,10 +183,10 @@ inline void fill_sigfpe_signo(unsigned int fpcsr, int *signo)
 {
 	if (fpcsr & FPCSR_mskOVFT)
 		*signo = FPE_FLTOVF;
-	else if (fpcsr & FPCSR_mskUDFT)
-		*signo = FPE_FLTUND;
 	else if (fpcsr & FPCSR_mskIVOT)
 		*signo = FPE_FLTINV;
+	else if (fpcsr & FPCSR_mskUDFT)
+		*signo = FPE_FLTUND;
 	else if (fpcsr & FPCSR_mskDBZT)
 		*signo = FPE_FLTDIV;
 	else if (fpcsr & FPCSR_mskIEXT)
@@ -201,16 +201,37 @@ inline void handle_fpu_exception(struct pt_regs *regs)
 	lose_fpu();
 	fpcsr = current->thread.fpu.fpcsr;
 
-	if (fpcsr & FPCSR_mskRIT) {
+	if (fpcsr & FPCSR_mskDNIT) {
+		si_signo = do_fpuemu(regs, &current->thread.fpu);
+		fpcsr = current->thread.fpu.fpcsr;
+		if (!si_signo)
+			goto done;
+	} else if (fpcsr & FPCSR_mskRIT) {
 		if (!user_mode(regs))
 			do_exit(SIGILL);
 		si_signo = SIGILL;
+	}
+
+
+	switch (si_signo) {
+	case SIGFPE:
+		fill_sigfpe_signo(fpcsr, &si_code);
+		break;
+	case SIGILL:
 		show_regs(regs);
 		si_code = ILL_COPROC;
-	} else
-		fill_sigfpe_signo(fpcsr, &si_code);
+		break;
+	case SIGBUS:
+		si_code = BUS_ADRERR;
+		break;
+	default:
+		break;
+	}
+
 	force_sig_fault(si_signo, si_code,
 			(void __user *)instruction_pointer(regs), current);
+done:
+	own_fpu();
 }
 
 bool do_fpu_exception(unsigned int subtype, struct pt_regs *regs)
diff --git a/arch/nds32/math-emu/Makefile b/arch/nds32/math-emu/Makefile
new file mode 100644
index 000000000000..947fe0c3d52f
--- /dev/null
+++ b/arch/nds32/math-emu/Makefile
@@ -0,0 +1,7 @@
+#
+# Makefile for the Linux/nds32 kernel FPU emulation.
+#
+
+obj-y	:= fpuemu.o \
+	   fdivd.o fmuld.o fsubd.o faddd.o fs2d.o fsqrtd.o fcmpd.o fnegs.o \
+	   fdivs.o fmuls.o fsubs.o fadds.o fd2s.o fsqrts.o fcmps.o fnegd.o
diff --git a/arch/nds32/math-emu/faddd.c b/arch/nds32/math-emu/faddd.c
new file mode 100644
index 000000000000..f7fd4e3c3904
--- /dev/null
+++ b/arch/nds32/math-emu/faddd.c
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2005-2018 Andes Technology Corporation
+#include <linux/uaccess.h>
+
+#include <asm/sfp-machine.h>
+#include <math-emu/soft-fp.h>
+#include <math-emu/double.h>
+void faddd(void *ft, void *fa, void *fb)
+{
+	FP_DECL_D(A);
+	FP_DECL_D(B);
+	FP_DECL_D(R);
+	FP_DECL_EX;
+
+	FP_UNPACK_DP(A, fa);
+	FP_UNPACK_DP(B, fb);
+
+	FP_ADD_D(R, A, B);
+
+	FP_PACK_DP(ft, R);
+
+	__FPU_FPCSR |= FP_CUR_EXCEPTIONS;
+
+}
diff --git a/arch/nds32/math-emu/fadds.c b/arch/nds32/math-emu/fadds.c
new file mode 100644
index 000000000000..f5af6ca8cca5
--- /dev/null
+++ b/arch/nds32/math-emu/fadds.c
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2005-2018 Andes Technology Corporation
+#include <linux/uaccess.h>
+
+#include <asm/sfp-machine.h>
+#include <math-emu/soft-fp.h>
+#include <math-emu/single.h>
+void fadds(void *ft, void *fa, void *fb)
+{
+	FP_DECL_S(A);
+	FP_DECL_S(B);
+	FP_DECL_S(R);
+	FP_DECL_EX;
+
+	FP_UNPACK_SP(A, fa);
+	FP_UNPACK_SP(B, fb);
+
+	FP_ADD_S(R, A, B);
+
+	FP_PACK_SP(ft, R);
+
+	__FPU_FPCSR |= FP_CUR_EXCEPTIONS;
+
+}
diff --git a/arch/nds32/math-emu/fcmpd.c b/arch/nds32/math-emu/fcmpd.c
new file mode 100644
index 000000000000..0ea225abe880
--- /dev/null
+++ b/arch/nds32/math-emu/fcmpd.c
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2005-2018 Andes Technology Corporation
+#include <asm/sfp-machine.h>
+#include <math-emu/soft-fp.h>
+#include <math-emu/double.h>
+int fcmpd(void *ft, void *fa, void *fb, int cmpop)
+{
+	FP_DECL_D(A);
+	FP_DECL_D(B);
+	FP_DECL_EX;
+	long cmp;
+
+	FP_UNPACK_DP(A, fa);
+	FP_UNPACK_DP(B, fb);
+
+	FP_CMP_D(cmp, A, B, SF_CUN);
+	cmp += 2;
+	if (cmp == SF_CGT)
+		*(long *)ft = 0;
+	else
+		*(long *)ft = (cmp & cmpop) ? 1 : 0;
+
+	return 0;
+}
diff --git a/arch/nds32/math-emu/fcmps.c b/arch/nds32/math-emu/fcmps.c
new file mode 100644
index 000000000000..681480758213
--- /dev/null
+++ b/arch/nds32/math-emu/fcmps.c
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2005-2018 Andes Technology Corporation
+#include <asm/sfp-machine.h>
+#include <math-emu/soft-fp.h>
+#include <math-emu/single.h>
+int fcmps(void *ft, void *fa, void *fb, int cmpop)
+{
+	FP_DECL_S(A);
+	FP_DECL_S(B);
+	FP_DECL_EX;
+	long cmp;
+
+	FP_UNPACK_SP(A, fa);
+	FP_UNPACK_SP(B, fb);
+
+	FP_CMP_S(cmp, A, B, SF_CUN);
+	cmp += 2;
+	if (cmp == SF_CGT)
+		*(int *)ft = 0x0;
+	else
+		*(int *)ft = (cmp & cmpop) ? 0x1 : 0x0;
+
+	return 0;
+}
diff --git a/arch/nds32/math-emu/fd2s.c b/arch/nds32/math-emu/fd2s.c
new file mode 100644
index 000000000000..1328371e8170
--- /dev/null
+++ b/arch/nds32/math-emu/fd2s.c
@@ -0,0 +1,22 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2005-2018 Andes Technology Corporation
+#include <linux/uaccess.h>
+
+#include <asm/sfp-machine.h>
+#include <math-emu/double.h>
+#include <math-emu/single.h>
+#include <math-emu/soft-fp.h>
+void fd2s(void *ft, void *fa)
+{
+	FP_DECL_D(A);
+	FP_DECL_S(R);
+	FP_DECL_EX;
+
+	FP_UNPACK_DP(A, fa);
+
+	FP_CONV(S, D, 1, 2, R, A);
+
+	FP_PACK_SP(ft, R);
+
+	__FPU_FPCSR |= FP_CUR_EXCEPTIONS;
+}
diff --git a/arch/nds32/math-emu/fdivd.c b/arch/nds32/math-emu/fdivd.c
new file mode 100644
index 000000000000..458e7e98b08e
--- /dev/null
+++ b/arch/nds32/math-emu/fdivd.c
@@ -0,0 +1,27 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2005-2018 Andes Technology Corporation
+
+#include <linux/uaccess.h>
+#include <asm/sfp-machine.h>
+#include <math-emu/soft-fp.h>
+#include <math-emu/double.h>
+
+void fdivd(void *ft, void *fa, void *fb)
+{
+	FP_DECL_D(A);
+	FP_DECL_D(B);
+	FP_DECL_D(R);
+	FP_DECL_EX;
+
+	FP_UNPACK_DP(A, fa);
+	FP_UNPACK_DP(B, fb);
+
+	if (B_c == FP_CLS_ZERO && A_c != FP_CLS_ZERO)
+		FP_SET_EXCEPTION(FP_EX_DIVZERO);
+
+	FP_DIV_D(R, A, B);
+
+	FP_PACK_DP(ft, R);
+
+	__FPU_FPCSR |= FP_CUR_EXCEPTIONS;
+}
diff --git a/arch/nds32/math-emu/fdivs.c b/arch/nds32/math-emu/fdivs.c
new file mode 100644
index 000000000000..c7d202159ce2
--- /dev/null
+++ b/arch/nds32/math-emu/fdivs.c
@@ -0,0 +1,26 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2005-2018 Andes Technology Corporation
+#include <linux/uaccess.h>
+
+#include <asm/sfp-machine.h>
+#include <math-emu/soft-fp.h>
+#include <math-emu/single.h>
+void fdivs(void *ft, void *fa, void *fb)
+{
+	FP_DECL_S(A);
+	FP_DECL_S(B);
+	FP_DECL_S(R);
+	FP_DECL_EX;
+
+	FP_UNPACK_SP(A, fa);
+	FP_UNPACK_SP(B, fb);
+
+	if (B_c == FP_CLS_ZERO && A_c != FP_CLS_ZERO)
+		FP_SET_EXCEPTION(FP_EX_DIVZERO);
+
+	FP_DIV_S(R, A, B);
+
+	FP_PACK_SP(ft, R);
+
+	__FPU_FPCSR |= FP_CUR_EXCEPTIONS;
+}
diff --git a/arch/nds32/math-emu/fmuld.c b/arch/nds32/math-emu/fmuld.c
new file mode 100644
index 000000000000..f3c77a45ddc2
--- /dev/null
+++ b/arch/nds32/math-emu/fmuld.c
@@ -0,0 +1,23 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2005-2018 Andes Technology Corporation
+#include <linux/uaccess.h>
+
+#include <asm/sfp-machine.h>
+#include <math-emu/soft-fp.h>
+#include <math-emu/double.h>
+void fmuld(void *ft, void *fa, void *fb)
+{
+	FP_DECL_D(A);
+	FP_DECL_D(B);
+	FP_DECL_D(R);
+	FP_DECL_EX;
+
+	FP_UNPACK_DP(A, fa);
+	FP_UNPACK_DP(B, fb);
+
+	FP_MUL_D(R, A, B);
+
+	FP_PACK_DP(ft, R);
+
+	__FPU_FPCSR |= FP_CUR_EXCEPTIONS;
+}
diff --git a/arch/nds32/math-emu/fmuls.c b/arch/nds32/math-emu/fmuls.c
new file mode 100644
index 000000000000..cf150df938f9
--- /dev/null
+++ b/arch/nds32/math-emu/fmuls.c
@@ -0,0 +1,23 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2005-2018 Andes Technology Corporation
+#include <linux/uaccess.h>
+
+#include <asm/sfp-machine.h>
+#include <math-emu/soft-fp.h>
+#include <math-emu/single.h>
+void fmuls(void *ft, void *fa, void *fb)
+{
+	FP_DECL_S(A);
+	FP_DECL_S(B);
+	FP_DECL_S(R);
+	FP_DECL_EX;
+
+	FP_UNPACK_SP(A, fa);
+	FP_UNPACK_SP(B, fb);
+
+	FP_MUL_S(R, A, B);
+
+	FP_PACK_SP(ft, R);
+
+	__FPU_FPCSR |= FP_CUR_EXCEPTIONS;
+}
diff --git a/arch/nds32/math-emu/fnegd.c b/arch/nds32/math-emu/fnegd.c
new file mode 100644
index 000000000000..de7ea6a0873e
--- /dev/null
+++ b/arch/nds32/math-emu/fnegd.c
@@ -0,0 +1,21 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2005-2018 Andes Technology Corporation
+#include <linux/uaccess.h>
+
+#include <asm/sfp-machine.h>
+#include <math-emu/soft-fp.h>
+#include <math-emu/double.h>
+void fnegd(void *ft, void *fa)
+{
+	FP_DECL_D(A);
+	FP_DECL_D(R);
+	FP_DECL_EX;
+
+	FP_UNPACK_DP(A, fa);
+
+	FP_NEG_D(R, A);
+
+	FP_PACK_DP(ft, R);
+
+	__FPU_FPCSR |= FP_CUR_EXCEPTIONS;
+}
diff --git a/arch/nds32/math-emu/fnegs.c b/arch/nds32/math-emu/fnegs.c
new file mode 100644
index 000000000000..07270b326a77
--- /dev/null
+++ b/arch/nds32/math-emu/fnegs.c
@@ -0,0 +1,21 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2005-2018 Andes Technology Corporation
+#include <linux/uaccess.h>
+
+#include <asm/sfp-machine.h>
+#include <math-emu/soft-fp.h>
+#include <math-emu/single.h>
+void fnegs(void *ft, void *fa)
+{
+	FP_DECL_S(A);
+	FP_DECL_S(R);
+	FP_DECL_EX;
+
+	FP_UNPACK_SP(A, fa);
+
+	FP_NEG_S(R, A);
+
+	FP_PACK_SP(ft, R);
+
+	__FPU_FPCSR |= FP_CUR_EXCEPTIONS;
+}
diff --git a/arch/nds32/math-emu/fpuemu.c b/arch/nds32/math-emu/fpuemu.c
new file mode 100644
index 000000000000..2a01333d6e5f
--- /dev/null
+++ b/arch/nds32/math-emu/fpuemu.c
@@ -0,0 +1,352 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2005-2018 Andes Technology Corporation
+
+#include <asm/bitfield.h>
+#include <asm/uaccess.h>
+#include <asm/sfp-machine.h>
+#include <asm/fpuemu.h>
+#include <asm/nds32_fpu_inst.h>
+
+#define DPFROMREG(dp, x) (dp = (void *)((unsigned long *)fpu_reg + 2*x))
+#ifdef __NDS32_EL__
+#define SPFROMREG(sp, x)\
+	((sp) = (void *)((unsigned long *)fpu_reg + (x^1)))
+#else
+#define SPFROMREG(sp, x) ((sp) = (void *)((unsigned long *)fpu_reg + x))
+#endif
+
+#define DEF3OP(name, p, f1, f2) \
+void fpemu_##name##p(void *ft, void *fa, void *fb) \
+{ \
+	f1(fa, fa, fb); \
+	f2(ft, ft, fa); \
+}
+
+#define DEF3OPNEG(name, p, f1, f2, f3) \
+void fpemu_##name##p(void *ft, void *fa, void *fb) \
+{ \
+	f1(fa, fa, fb); \
+	f2(ft, ft, fa); \
+	f3(ft, ft); \
+}
+DEF3OP(fmadd, s, fmuls, fadds);
+DEF3OP(fmsub, s, fmuls, fsubs);
+DEF3OP(fmadd, d, fmuld, faddd);
+DEF3OP(fmsub, d, fmuld, fsubd);
+DEF3OPNEG(fnmadd, s, fmuls, fadds, fnegs);
+DEF3OPNEG(fnmsub, s, fmuls, fsubs, fnegs);
+DEF3OPNEG(fnmadd, d, fmuld, faddd, fnegd);
+DEF3OPNEG(fnmsub, d, fmuld, fsubd, fnegd);
+
+static const unsigned char cmptab[8] = {
+	SF_CEQ,
+	SF_CEQ,
+	SF_CLT,
+	SF_CLT,
+	SF_CLT | SF_CEQ,
+	SF_CLT | SF_CEQ,
+	SF_CUN,
+	SF_CUN
+};
+
+enum ARGTYPE {
+	S1S = 1,
+	S2S,
+	S1D,
+	CS,
+	D1D,
+	D2D,
+	D1S,
+	CD
+};
+union func_t {
+	void (*t)(void *ft, void *fa, void *fb);
+	void (*b)(void *ft, void *fa);
+};
+/*
+ * Emulate a single FPU arithmetic instruction.
+ */
+static int fpu_emu(struct fpu_struct *fpu_reg, unsigned long insn)
+{
+	int rfmt;		/* resulting format */
+	union func_t func;
+	int ftype = 0;
+
+	switch (rfmt = NDS32Insn_OPCODE_COP0(insn)) {
+	case fs1_op:{
+			switch (NDS32Insn_OPCODE_BIT69(insn)) {
+			case fadds_op:
+				func.t = fadds;
+				ftype = S2S;
+				break;
+			case fsubs_op:
+				func.t = fsubs;
+				ftype = S2S;
+				break;
+			case fmadds_op:
+				func.t = fpemu_fmadds;
+				ftype = S2S;
+				break;
+			case fmsubs_op:
+				func.t = fpemu_fmsubs;
+				ftype = S2S;
+				break;
+			case fnmadds_op:
+				func.t = fpemu_fnmadds;
+				ftype = S2S;
+				break;
+			case fnmsubs_op:
+				func.t = fpemu_fnmsubs;
+				ftype = S2S;
+				break;
+			case fmuls_op:
+				func.t = fmuls;
+				ftype = S2S;
+				break;
+			case fdivs_op:
+				func.t = fdivs;
+				ftype = S2S;
+				break;
+			case fs1_f2op_op:
+				switch (NDS32Insn_OPCODE_BIT1014(insn)) {
+				case fs2d_op:
+					func.b = fs2d;
+					ftype = S1D;
+					break;
+				case fsqrts_op:
+					func.b = fsqrts;
+					ftype = S1S;
+					break;
+				default:
+					return SIGILL;
+				}
+				break;
+			default:
+				return SIGILL;
+			}
+			break;
+		}
+	case fs2_op:
+		switch (NDS32Insn_OPCODE_BIT69(insn)) {
+		case fcmpeqs_op:
+		case fcmpeqs_e_op:
+		case fcmplts_op:
+		case fcmplts_e_op:
+		case fcmples_op:
+		case fcmples_e_op:
+		case fcmpuns_op:
+		case fcmpuns_e_op:
+			ftype = CS;
+			break;
+		default:
+			return SIGILL;
+		}
+		break;
+	case fd1_op:{
+			switch (NDS32Insn_OPCODE_BIT69(insn)) {
+			case faddd_op:
+				func.t = faddd;
+				ftype = D2D;
+				break;
+			case fsubd_op:
+				func.t = fsubd;
+				ftype = D2D;
+				break;
+			case fmaddd_op:
+				func.t = fpemu_fmaddd;
+				ftype = D2D;
+				break;
+			case fmsubd_op:
+				func.t = fpemu_fmsubd;
+				ftype = D2D;
+				break;
+			case fnmaddd_op:
+				func.t = fpemu_fnmaddd;
+				ftype = D2D;
+				break;
+			case fnmsubd_op:
+				func.t = fpemu_fnmsubd;
+				ftype = D2D;
+				break;
+			case fmuld_op:
+				func.t = fmuld;
+				ftype = D2D;
+				break;
+			case fdivd_op:
+				func.t = fdivd;
+				ftype = D2D;
+				break;
+			case fd1_f2op_op:
+				switch (NDS32Insn_OPCODE_BIT1014(insn)) {
+				case fd2s_op:
+					func.b = fd2s;
+					ftype = D1S;
+					break;
+				case fsqrtd_op:
+					func.b = fsqrtd;
+					ftype = D1D;
+					break;
+				default:
+					return SIGILL;
+				}
+				break;
+			default:
+				return SIGILL;
+
+			}
+			break;
+		}
+
+	case fd2_op:
+		switch (NDS32Insn_OPCODE_BIT69(insn)) {
+		case fcmpeqd_op:
+		case fcmpeqd_e_op:
+		case fcmpltd_op:
+		case fcmpltd_e_op:
+		case fcmpled_op:
+		case fcmpled_e_op:
+		case fcmpund_op:
+		case fcmpund_e_op:
+			ftype = CD;
+			break;
+		default:
+			return SIGILL;
+		}
+		break;
+
+	default:
+		return SIGILL;
+	}
+
+	switch (ftype) {
+	case S1S:{
+			void *ft, *fa;
+
+			SPFROMREG(ft, NDS32Insn_OPCODE_Rt(insn));
+			SPFROMREG(fa, NDS32Insn_OPCODE_Ra(insn));
+			func.b(ft, fa);
+			break;
+		}
+	case S2S:{
+			void *ft, *fa, *fb;
+
+			SPFROMREG(ft, NDS32Insn_OPCODE_Rt(insn));
+			SPFROMREG(fa, NDS32Insn_OPCODE_Ra(insn));
+			SPFROMREG(fb, NDS32Insn_OPCODE_Rb(insn));
+			func.t(ft, fa, fb);
+			break;
+		}
+	case S1D:{
+			void *ft, *fa;
+
+			DPFROMREG(ft, NDS32Insn_OPCODE_Rt(insn));
+			SPFROMREG(fa, NDS32Insn_OPCODE_Ra(insn));
+			func.b(ft, fa);
+			break;
+		}
+	case CS:{
+			unsigned int cmpop = NDS32Insn_OPCODE_BIT69(insn);
+			void *ft, *fa, *fb;
+
+			SPFROMREG(ft, NDS32Insn_OPCODE_Rt(insn));
+			SPFROMREG(fa, NDS32Insn_OPCODE_Ra(insn));
+			SPFROMREG(fb, NDS32Insn_OPCODE_Rb(insn));
+			if (cmpop < 0x8) {
+				cmpop = cmptab[cmpop];
+				fcmps(ft, fa, fb, cmpop);
+			} else
+				return SIGILL;
+			break;
+		}
+	case D1D:{
+			void *ft, *fa;
+
+			DPFROMREG(ft, NDS32Insn_OPCODE_Rt(insn));
+			DPFROMREG(fa, NDS32Insn_OPCODE_Ra(insn));
+			func.b(ft, fa);
+			break;
+		}
+	case D2D:{
+			void *ft, *fa, *fb;
+
+			DPFROMREG(ft, NDS32Insn_OPCODE_Rt(insn));
+			DPFROMREG(fa, NDS32Insn_OPCODE_Ra(insn));
+			DPFROMREG(fb, NDS32Insn_OPCODE_Rb(insn));
+			func.t(ft, fa, fb);
+			break;
+		}
+	case D1S:{
+			void *ft, *fa;
+
+			SPFROMREG(ft, NDS32Insn_OPCODE_Rt(insn));
+			DPFROMREG(fa, NDS32Insn_OPCODE_Ra(insn));
+			func.b(ft, fa);
+			break;
+		}
+	case CD:{
+			unsigned int cmpop = NDS32Insn_OPCODE_BIT69(insn);
+			void *ft, *fa, *fb;
+
+			SPFROMREG(ft, NDS32Insn_OPCODE_Rt(insn));
+			DPFROMREG(fa, NDS32Insn_OPCODE_Ra(insn));
+			DPFROMREG(fb, NDS32Insn_OPCODE_Rb(insn));
+			if (cmpop < 0x8) {
+				cmpop = cmptab[cmpop];
+				fcmpd(ft, fa, fb, cmpop);
+			} else
+				return SIGILL;
+			break;
+		}
+	default:
+		return SIGILL;
+	}
+
+	/*
+	 * If an exception is required, generate a tidy SIGFPE exception.
+	 */
+	if ((fpu_reg->fpcsr << 5) & fpu_reg->fpcsr & FPCSR_mskALLE)
+		return SIGFPE;
+	return 0;
+}
+
+
+int do_fpuemu(struct pt_regs *regs, struct fpu_struct *fpu)
+{
+	unsigned long insn = 0, addr = regs->ipc;
+	unsigned long emulpc, contpc;
+	unsigned char *pc = (void *)&insn;
+	char c;
+	int i = 0, ret;
+
+	for (i = 0; i < 4; i++) {
+		if (__get_user(c, (unsigned char *)addr++))
+			return SIGBUS;
+		*pc++ = c;
+	}
+
+	insn = be32_to_cpu(insn);
+
+	emulpc = regs->ipc;
+	contpc = regs->ipc + 4;
+
+	if (NDS32Insn_OPCODE(insn) != cop0_op)
+		return SIGILL;
+	switch (NDS32Insn_OPCODE_COP0(insn)) {
+	case fs1_op:
+	case fs2_op:
+	case fd1_op:
+	case fd2_op:
+		{
+			/* a real fpu computation instruction */
+			ret = fpu_emu(fpu, insn);
+			if (!ret)
+				regs->ipc = contpc;
+		}
+		break;
+
+	default:
+		return SIGILL;
+	}
+
+	return ret;
+}
diff --git a/arch/nds32/math-emu/fs2d.c b/arch/nds32/math-emu/fs2d.c
new file mode 100644
index 000000000000..0e8db9035631
--- /dev/null
+++ b/arch/nds32/math-emu/fs2d.c
@@ -0,0 +1,23 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2005-2018 Andes Technology Corporation
+
+#include <linux/uaccess.h>
+#include <asm/sfp-machine.h>
+#include <math-emu/double.h>
+#include <math-emu/single.h>
+#include <math-emu/soft-fp.h>
+
+void fs2d(void *ft, void *fa)
+{
+	FP_DECL_S(A);
+	FP_DECL_D(R);
+	FP_DECL_EX;
+
+	FP_UNPACK_SP(A, fa);
+
+	FP_CONV(D, S, 2, 1, R, A);
+
+	FP_PACK_DP(ft, R);
+
+	__FPU_FPCSR |= FP_CUR_EXCEPTIONS;
+}
diff --git a/arch/nds32/math-emu/fsqrtd.c b/arch/nds32/math-emu/fsqrtd.c
new file mode 100644
index 000000000000..c3a8dbd81d4e
--- /dev/null
+++ b/arch/nds32/math-emu/fsqrtd.c
@@ -0,0 +1,21 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2005-2018 Andes Technology Corporation
+
+#include <linux/uaccess.h>
+#include <asm/sfp-machine.h>
+#include <math-emu/soft-fp.h>
+#include <math-emu/double.h>
+void fsqrtd(void *ft, void *fa)
+{
+	FP_DECL_D(A);
+	FP_DECL_D(R);
+	FP_DECL_EX;
+
+	FP_UNPACK_DP(A, fa);
+
+	FP_SQRT_D(R, A);
+
+	FP_PACK_DP(ft, R);
+
+	__FPU_FPCSR |= FP_CUR_EXCEPTIONS;
+}
diff --git a/arch/nds32/math-emu/fsqrts.c b/arch/nds32/math-emu/fsqrts.c
new file mode 100644
index 000000000000..4c6f94b27328
--- /dev/null
+++ b/arch/nds32/math-emu/fsqrts.c
@@ -0,0 +1,21 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2005-2018 Andes Technology Corporation
+
+#include <linux/uaccess.h>
+#include <asm/sfp-machine.h>
+#include <math-emu/soft-fp.h>
+#include <math-emu/single.h>
+void fsqrts(void *ft, void *fa)
+{
+	FP_DECL_S(A);
+	FP_DECL_S(R);
+	FP_DECL_EX;
+
+	FP_UNPACK_SP(A, fa);
+
+	FP_SQRT_S(R, A);
+
+	FP_PACK_SP(ft, R);
+
+	__FPU_FPCSR |= FP_CUR_EXCEPTIONS;
+}
diff --git a/arch/nds32/math-emu/fsubd.c b/arch/nds32/math-emu/fsubd.c
new file mode 100644
index 000000000000..81b6a0d02a1f
--- /dev/null
+++ b/arch/nds32/math-emu/fsubd.c
@@ -0,0 +1,27 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2005-2018 Andes Technology Corporation
+#include <linux/uaccess.h>
+
+#include <asm/sfp-machine.h>
+#include <math-emu/soft-fp.h>
+#include <math-emu/double.h>
+void fsubd(void *ft, void *fa, void *fb)
+{
+
+	FP_DECL_D(A);
+	FP_DECL_D(B);
+	FP_DECL_D(R);
+	FP_DECL_EX;
+
+	FP_UNPACK_DP(A, fa);
+	FP_UNPACK_DP(B, fb);
+
+	if (B_c != FP_CLS_NAN)
+		B_s ^= 1;
+
+	FP_ADD_D(R, A, B);
+
+	FP_PACK_DP(ft, R);
+
+	__FPU_FPCSR |= FP_CUR_EXCEPTIONS;
+}
diff --git a/arch/nds32/math-emu/fsubs.c b/arch/nds32/math-emu/fsubs.c
new file mode 100644
index 000000000000..61ddd9708465
--- /dev/null
+++ b/arch/nds32/math-emu/fsubs.c
@@ -0,0 +1,27 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2005-2018 Andes Technology Corporation
+#include <linux/uaccess.h>
+
+#include <asm/sfp-machine.h>
+#include <math-emu/soft-fp.h>
+#include <math-emu/single.h>
+void fsubs(void *ft, void *fa, void *fb)
+{
+
+	FP_DECL_S(A);
+	FP_DECL_S(B);
+	FP_DECL_S(R);
+	FP_DECL_EX;
+
+	FP_UNPACK_SP(A, fa);
+	FP_UNPACK_SP(B, fb);
+
+	if (B_c != FP_CLS_NAN)
+		B_s ^= 1;
+
+	FP_ADD_S(R, A, B);
+
+	FP_PACK_SP(ft, R);
+
+	__FPU_FPCSR |= FP_CUR_EXCEPTIONS;
+}