Merge branch 'linus' into x86/asm, before applying dependent patch

Signed-off-by: Ingo Molnar <mingo@kernel.org>

26 files changed, 381 insertions, 389 deletions

diff --git a/arch/mips/math-emu/Makefile b/arch/mips/math-emu/Makefile
index 619cfc1a2442..2e5f96275c38 100644
--- a/arch/mips/math-emu/Makefile
+++ b/arch/mips/math-emu/Makefile
@@ -2,12 +2,15 @@
 # Makefile for the Linux/MIPS kernel FPU emulation.
 #
 
-obj-y	+= cp1emu.o ieee754dp.o ieee754sp.o ieee754.o dp_div.o dp_mul.o \
-	   dp_sub.o dp_add.o dp_fsp.o dp_cmp.o dp_simple.o dp_tint.o \
-	   dp_fint.o dp_tlong.o dp_flong.o sp_div.o sp_mul.o sp_sub.o \
-	   sp_add.o sp_fdp.o sp_cmp.o sp_simple.o sp_tint.o sp_fint.o \
-	   sp_tlong.o sp_flong.o dsemul.o
+obj-y	+= cp1emu.o ieee754dp.o ieee754sp.o ieee754.o \
+	   dp_div.o dp_mul.o dp_sub.o dp_add.o dp_fsp.o dp_cmp.o dp_simple.o \
+	   dp_tint.o dp_fint.o \
+	   sp_div.o sp_mul.o sp_sub.o sp_add.o sp_fdp.o sp_cmp.o sp_simple.o \
+	   sp_tint.o sp_fint.o \
+	   dsemul.o
 
-lib-y	+= ieee754d.o dp_sqrt.o sp_sqrt.o
+lib-y	+= ieee754d.o \
+	   dp_tlong.o dp_flong.o dp_sqrt.o \
+	   sp_tlong.o sp_flong.o sp_sqrt.o
 
 obj-$(CONFIG_DEBUG_FS) += me-debugfs.o
diff --git a/arch/mips/math-emu/cp1emu.c b/arch/mips/math-emu/cp1emu.c
index b30bf65c7d7d..d31c537ace1d 100644
--- a/arch/mips/math-emu/cp1emu.c
+++ b/arch/mips/math-emu/cp1emu.c
@@ -45,6 +45,7 @@
 #include <asm/signal.h>
 #include <asm/uaccess.h>
 
+#include <asm/cpu-info.h>
 #include <asm/processor.h>
 #include <asm/fpu_emulator.h>
 #include <asm/fpu.h>
@@ -63,14 +64,14 @@ static int fpux_emu(struct pt_regs *,
 /* Control registers */
 
 #define FPCREG_RID	0	/* $0  = revision id */
+#define FPCREG_FCCR	25	/* $25 = fccr */
+#define FPCREG_FEXR	26	/* $26 = fexr */
+#define FPCREG_FENR	28	/* $28 = fenr */
 #define FPCREG_CSR	31	/* $31 = csr */
 
-/* Determine rounding mode from the RM bits of the FCSR */
-#define modeindex(v) ((v) & FPU_CSR_RM)
-
 /* convert condition code register number to csr bit */
 const unsigned int fpucondbit[8] = {
-	FPU_CSR_COND0,
+	FPU_CSR_COND,
 	FPU_CSR_COND1,
 	FPU_CSR_COND2,
 	FPU_CSR_COND3,
@@ -843,6 +844,127 @@ do {									\
 #define DPTOREG(dp, x)	DITOREG((dp).bits, x)
 
 /*
+ * Emulate a CFC1 instruction.
+ */
+static inline void cop1_cfc(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
+			    mips_instruction ir)
+{
+	u32 fcr31 = ctx->fcr31;
+	u32 value = 0;
+
+	switch (MIPSInst_RD(ir)) {
+	case FPCREG_CSR:
+		value = fcr31;
+		pr_debug("%p gpr[%d]<-csr=%08x\n",
+			 (void *)xcp->cp0_epc, MIPSInst_RT(ir), value);
+		break;
+
+	case FPCREG_FENR:
+		if (!cpu_has_mips_r)
+			break;
+		value = (fcr31 >> (FPU_CSR_FS_S - MIPS_FENR_FS_S)) &
+			MIPS_FENR_FS;
+		value |= fcr31 & (FPU_CSR_ALL_E | FPU_CSR_RM);
+		pr_debug("%p gpr[%d]<-enr=%08x\n",
+			 (void *)xcp->cp0_epc, MIPSInst_RT(ir), value);
+		break;
+
+	case FPCREG_FEXR:
+		if (!cpu_has_mips_r)
+			break;
+		value = fcr31 & (FPU_CSR_ALL_X | FPU_CSR_ALL_S);
+		pr_debug("%p gpr[%d]<-exr=%08x\n",
+			 (void *)xcp->cp0_epc, MIPSInst_RT(ir), value);
+		break;
+
+	case FPCREG_FCCR:
+		if (!cpu_has_mips_r)
+			break;
+		value = (fcr31 >> (FPU_CSR_COND_S - MIPS_FCCR_COND0_S)) &
+			MIPS_FCCR_COND0;
+		value |= (fcr31 >> (FPU_CSR_COND1_S - MIPS_FCCR_COND1_S)) &
+			 (MIPS_FCCR_CONDX & ~MIPS_FCCR_COND0);
+		pr_debug("%p gpr[%d]<-ccr=%08x\n",
+			 (void *)xcp->cp0_epc, MIPSInst_RT(ir), value);
+		break;
+
+	case FPCREG_RID:
+		value = current_cpu_data.fpu_id;
+		break;
+
+	default:
+		break;
+	}
+
+	if (MIPSInst_RT(ir))
+		xcp->regs[MIPSInst_RT(ir)] = value;
+}
+
+/*
+ * Emulate a CTC1 instruction.
+ */
+static inline void cop1_ctc(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
+			    mips_instruction ir)
+{
+	u32 fcr31 = ctx->fcr31;
+	u32 value;
+	u32 mask;
+
+	if (MIPSInst_RT(ir) == 0)
+		value = 0;
+	else
+		value = xcp->regs[MIPSInst_RT(ir)];
+
+	switch (MIPSInst_RD(ir)) {
+	case FPCREG_CSR:
+		pr_debug("%p gpr[%d]->csr=%08x\n",
+			 (void *)xcp->cp0_epc, MIPSInst_RT(ir), value);
+
+		/* Preserve read-only bits.  */
+		mask = current_cpu_data.fpu_msk31;
+		fcr31 = (value & ~mask) | (fcr31 & mask);
+		break;
+
+	case FPCREG_FENR:
+		if (!cpu_has_mips_r)
+			break;
+		pr_debug("%p gpr[%d]->enr=%08x\n",
+			 (void *)xcp->cp0_epc, MIPSInst_RT(ir), value);
+		fcr31 &= ~(FPU_CSR_FS | FPU_CSR_ALL_E | FPU_CSR_RM);
+		fcr31 |= (value << (FPU_CSR_FS_S - MIPS_FENR_FS_S)) &
+			 FPU_CSR_FS;
+		fcr31 |= value & (FPU_CSR_ALL_E | FPU_CSR_RM);
+		break;
+
+	case FPCREG_FEXR:
+		if (!cpu_has_mips_r)
+			break;
+		pr_debug("%p gpr[%d]->exr=%08x\n",
+			 (void *)xcp->cp0_epc, MIPSInst_RT(ir), value);
+		fcr31 &= ~(FPU_CSR_ALL_X | FPU_CSR_ALL_S);
+		fcr31 |= value & (FPU_CSR_ALL_X | FPU_CSR_ALL_S);
+		break;
+
+	case FPCREG_FCCR:
+		if (!cpu_has_mips_r)
+			break;
+		pr_debug("%p gpr[%d]->ccr=%08x\n",
+			 (void *)xcp->cp0_epc, MIPSInst_RT(ir), value);
+		fcr31 &= ~(FPU_CSR_CONDX | FPU_CSR_COND);
+		fcr31 |= (value << (FPU_CSR_COND_S - MIPS_FCCR_COND0_S)) &
+			 FPU_CSR_COND;
+		fcr31 |= (value << (FPU_CSR_COND1_S - MIPS_FCCR_COND1_S)) &
+			 FPU_CSR_CONDX;
+		break;
+
+	default:
+		break;
+	}
+
+	ctx->fcr31 = fcr31;
+}
+
+/*
  * Emulate the single floating point instruction pointed at by EPC.
  * Two instructions if the instruction is in a branch delay slot.
  */
@@ -856,7 +978,6 @@ static int cop1Emulate(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 	int likely, pc_inc;
 	u32 __user *wva;
 	u64 __user *dva;
-	u32 value;
 	u32 wval;
 	u64 dval;
 	int sig;
@@ -1049,42 +1170,12 @@ emul:
 
 		case cfc_op:
 			/* cop control register rd -> gpr[rt] */
-			if (MIPSInst_RD(ir) == FPCREG_CSR) {
-				value = ctx->fcr31;
-				value = (value & ~FPU_CSR_RM) | modeindex(value);
-				pr_debug("%p gpr[%d]<-csr=%08x\n",
-					 (void *) (xcp->cp0_epc),
-					 MIPSInst_RT(ir), value);
-			}
-			else if (MIPSInst_RD(ir) == FPCREG_RID)
-				value = 0;
-			else
-				value = 0;
-			if (MIPSInst_RT(ir))
-				xcp->regs[MIPSInst_RT(ir)] = value;
+			cop1_cfc(xcp, ctx, ir);
 			break;
 
 		case ctc_op:
 			/* copregister rd <- rt */
-			if (MIPSInst_RT(ir) == 0)
-				value = 0;
-			else
-				value = xcp->regs[MIPSInst_RT(ir)];
-
-			/* we only have one writable control reg
-			 */
-			if (MIPSInst_RD(ir) == FPCREG_CSR) {
-				pr_debug("%p gpr[%d]->csr=%08x\n",
-					 (void *) (xcp->cp0_epc),
-					 MIPSInst_RT(ir), value);
-
-				/*
-				 * Don't write reserved bits,
-				 * and convert to ieee library modes
-				 */
-				ctx->fcr31 = (value & ~(FPU_CSR_RSVD | FPU_CSR_RM)) |
-					     modeindex(value);
-			}
+			cop1_ctc(xcp, ctx, ir);
 			if ((ctx->fcr31 >> 5) & ctx->fcr31 & FPU_CSR_ALL_E) {
 				return SIGFPE;
 			}
@@ -1103,17 +1194,18 @@ emul:
 			likely = 0;
 			switch (MIPSInst_RT(ir) & 3) {
 			case bcfl_op:
-				likely = 1;
+				if (cpu_has_mips_2_3_4_5_r)
+					likely = 1;
+				/* Fall through */
 			case bcf_op:
 				cond = !cond;
 				break;
 			case bctl_op:
-				likely = 1;
+				if (cpu_has_mips_2_3_4_5_r)
+					likely = 1;
+				/* Fall through */
 			case bct_op:
 				break;
-			default:
-				/* thats an illegal instruction */
-				return SIGILL;
 			}
 
 			set_delay_slot(xcp);
@@ -1121,6 +1213,14 @@ emul:
 				/*
 				 * Branch taken: emulate dslot instruction
 				 */
+				unsigned long bcpc;
+
+				/*
+				 * Remember EPC at the branch to point back
+				 * at so that any delay-slot instruction
+				 * signal is not silently ignored.
+				 */
+				bcpc = xcp->cp0_epc;
 				xcp->cp0_epc += dec_insn.pc_inc;
 
 				contpc = MIPSInst_SIMM(ir);
@@ -1146,63 +1246,77 @@ emul:
 						 * Single step the non-CP1
 						 * instruction in the dslot.
 						 */
-						return mips_dsemul(xcp, ir, contpc);
+						sig = mips_dsemul(xcp, ir,
+								  contpc);
+						if (sig)
+							xcp->cp0_epc = bcpc;
+						/*
+						 * SIGILL forces out of
+						 * the emulation loop.
+						 */
+						return sig ? sig : SIGILL;
 					}
 				} else
 					contpc = (xcp->cp0_epc + (contpc << 2));
 
 				switch (MIPSInst_OPCODE(ir)) {
 				case lwc1_op:
-					goto emul;
-
 				case swc1_op:
 					goto emul;
 
 				case ldc1_op:
 				case sdc1_op:
-					if (cpu_has_mips_2_3_4_5 ||
-					    cpu_has_mips64)
+					if (cpu_has_mips_2_3_4_5_r)
 						goto emul;
 
-					return SIGILL;
-					goto emul;
+					goto bc_sigill;
 
 				case cop1_op:
 					goto emul;
 
 				case cop1x_op:
-					if (cpu_has_mips_4_5 || cpu_has_mips64 || cpu_has_mips32r2)
+					if (cpu_has_mips_4_5_64_r2_r6)
 						/* its one of ours */
 						goto emul;
 
-					return SIGILL;
+					goto bc_sigill;
 
 				case spec_op:
-					if (!cpu_has_mips_4_5_r)
-						return SIGILL;
+					switch (MIPSInst_FUNC(ir)) {
+					case movc_op:
+						if (cpu_has_mips_4_5_r)
+							goto emul;
 
-					if (MIPSInst_FUNC(ir) == movc_op)
-						goto emul;
+						goto bc_sigill;
+					}
 					break;
+
+				bc_sigill:
+					xcp->cp0_epc = bcpc;
+					return SIGILL;
 				}
 
 				/*
 				 * Single step the non-cp1
 				 * instruction in the dslot
 				 */
-				return mips_dsemul(xcp, ir, contpc);
+				sig = mips_dsemul(xcp, ir, contpc);
+				if (sig)
+					xcp->cp0_epc = bcpc;
+				/* SIGILL forces out of the emulation loop.  */
+				return sig ? sig : SIGILL;
 			} else if (likely) {	/* branch not taken */
-					/*
-					 * branch likely nullifies
-					 * dslot if not taken
-					 */
-					xcp->cp0_epc += dec_insn.pc_inc;
-					contpc += dec_insn.pc_inc;
-					/*
-					 * else continue & execute
-					 * dslot as normal insn
-					 */
-				}
+				/*
+				 * branch likely nullifies
+				 * dslot if not taken
+				 */
+				xcp->cp0_epc += dec_insn.pc_inc;
+				contpc += dec_insn.pc_inc;
+				/*
+				 * else continue & execute
+				 * dslot as normal insn
+				 */
+			}
 			break;
 
 		default:
@@ -1216,7 +1330,7 @@ emul:
 		break;
 
 	case cop1x_op:
-		if (!cpu_has_mips_4_5 && !cpu_has_mips64 && !cpu_has_mips32r2)
+		if (!cpu_has_mips_4_5_64_r2_r6)
 			return SIGILL;
 
 		sig = fpux_emu(xcp, ctx, ir, fault_addr);
@@ -1549,7 +1663,7 @@ static int fpu_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 
 			/* unary  ops */
 		case fsqrt_op:
-			if (!cpu_has_mips_4_5_r)
+			if (!cpu_has_mips_2_3_4_5_r)
 				return SIGILL;
 
 			handler.u = ieee754sp_sqrt;
@@ -1561,14 +1675,14 @@ static int fpu_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 		 * achieve full IEEE-754 accuracy - however this emulator does.
 		 */
 		case frsqrt_op:
-			if (!cpu_has_mips_4_5_r2_r6)
+			if (!cpu_has_mips_4_5_64_r2_r6)
 				return SIGILL;
 
 			handler.u = fpemu_sp_rsqrt;
 			goto scopuop;
 
 		case frecip_op:
-			if (!cpu_has_mips_4_5_r2_r6)
+			if (!cpu_has_mips_4_5_64_r2_r6)
 				return SIGILL;
 
 			handler.u = fpemu_sp_recip;
@@ -1670,19 +1784,19 @@ copcsr:
 		case ftrunc_op:
 		case fceil_op:
 		case ffloor_op:
-			if (!cpu_has_mips_2_3_4_5 && !cpu_has_mips64)
+			if (!cpu_has_mips_2_3_4_5_r)
 				return SIGILL;
 
 			oldrm = ieee754_csr.rm;
 			SPFROMREG(fs, MIPSInst_FS(ir));
-			ieee754_csr.rm = modeindex(MIPSInst_FUNC(ir));
+			ieee754_csr.rm = MIPSInst_FUNC(ir);
 			rv.w = ieee754sp_tint(fs);
 			ieee754_csr.rm = oldrm;
 			rfmt = w_fmt;
 			goto copcsr;
 
 		case fcvtl_op:
-			if (!cpu_has_mips_3_4_5 && !cpu_has_mips64)
+			if (!cpu_has_mips_3_4_5_64_r2_r6)
 				return SIGILL;
 
 			SPFROMREG(fs, MIPSInst_FS(ir));
@@ -1694,12 +1808,12 @@ copcsr:
 		case ftruncl_op:
 		case fceill_op:
 		case ffloorl_op:
-			if (!cpu_has_mips_3_4_5 && !cpu_has_mips64)
+			if (!cpu_has_mips_3_4_5_64_r2_r6)
 				return SIGILL;
 
 			oldrm = ieee754_csr.rm;
 			SPFROMREG(fs, MIPSInst_FS(ir));
-			ieee754_csr.rm = modeindex(MIPSInst_FUNC(ir));
+			ieee754_csr.rm = MIPSInst_FUNC(ir);
 			rv.l = ieee754sp_tlong(fs);
 			ieee754_csr.rm = oldrm;
 			rfmt = l_fmt;
@@ -1763,13 +1877,13 @@ copcsr:
 		 * achieve full IEEE-754 accuracy - however this emulator does.
 		 */
 		case frsqrt_op:
-			if (!cpu_has_mips_4_5_r2_r6)
+			if (!cpu_has_mips_4_5_64_r2_r6)
 				return SIGILL;
 
 			handler.u = fpemu_dp_rsqrt;
 			goto dcopuop;
 		case frecip_op:
-			if (!cpu_has_mips_4_5_r2_r6)
+			if (!cpu_has_mips_4_5_64_r2_r6)
 				return SIGILL;
 
 			handler.u = fpemu_dp_recip;
@@ -1852,14 +1966,14 @@ dcopuop:
 
 			oldrm = ieee754_csr.rm;
 			DPFROMREG(fs, MIPSInst_FS(ir));
-			ieee754_csr.rm = modeindex(MIPSInst_FUNC(ir));
+			ieee754_csr.rm = MIPSInst_FUNC(ir);
 			rv.w = ieee754dp_tint(fs);
 			ieee754_csr.rm = oldrm;
 			rfmt = w_fmt;
 			goto copcsr;
 
 		case fcvtl_op:
-			if (!cpu_has_mips_3_4_5 && !cpu_has_mips64)
+			if (!cpu_has_mips_3_4_5_64_r2_r6)
 				return SIGILL;
 
 			DPFROMREG(fs, MIPSInst_FS(ir));
@@ -1871,12 +1985,12 @@ dcopuop:
 		case ftruncl_op:
 		case fceill_op:
 		case ffloorl_op:
-			if (!cpu_has_mips_3_4_5 && !cpu_has_mips64)
+			if (!cpu_has_mips_3_4_5_64_r2_r6)
 				return SIGILL;
 
 			oldrm = ieee754_csr.rm;
 			DPFROMREG(fs, MIPSInst_FS(ir));
-			ieee754_csr.rm = modeindex(MIPSInst_FUNC(ir));
+			ieee754_csr.rm = MIPSInst_FUNC(ir);
 			rv.l = ieee754dp_tlong(fs);
 			ieee754_csr.rm = oldrm;
 			rfmt = l_fmt;
@@ -1930,7 +2044,7 @@ dcopuop:
 
 	case l_fmt:
 
-		if (!cpu_has_mips_3_4_5 && !cpu_has_mips64)
+		if (!cpu_has_mips_3_4_5_64_r2_r6)
 			return SIGILL;
 
 		DIFROMREG(bits, MIPSInst_FS(ir));
@@ -1994,7 +2108,7 @@ dcopuop:
 		SITOREG(rv.w, MIPSInst_FD(ir));
 		break;
 	case l_fmt:
-		if (!cpu_has_mips_3_4_5 && !cpu_has_mips64)
+		if (!cpu_has_mips_3_4_5_64_r2_r6)
 			return SIGILL;
 
 		DITOREG(rv.l, MIPSInst_FD(ir));
@@ -2081,10 +2195,8 @@ int fpu_emulator_cop1Handler(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 			xcp->cp0_epc += dec_insn.pc_inc;	/* Skip NOPs */
 		else {
 			/*
-			 * The 'ieee754_csr' is an alias of
-			 * ctx->fcr31.	No need to copy ctx->fcr31 to
-			 * ieee754_csr.	 But ieee754_csr.rm is ieee
-			 * library modes. (not mips rounding mode)
+			 * The 'ieee754_csr' is an alias of ctx->fcr31.
+			 * No need to copy ctx->fcr31 to ieee754_csr.
 			 */
 			sig = cop1Emulate(xcp, ctx, dec_insn, fault_addr);
 		}
diff --git a/arch/mips/math-emu/dp_add.c b/arch/mips/math-emu/dp_add.c
index 7f64577df984..8954ef031f84 100644
--- a/arch/mips/math-emu/dp_add.c
+++ b/arch/mips/math-emu/dp_add.c
@@ -37,19 +37,20 @@ union ieee754dp ieee754dp_add(union ieee754dp x, union ieee754dp y)
 	FLUSHYDP;
 
 	switch (CLPAIR(xc, yc)) {
-	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_SNAN):
-	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_SNAN):
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_SNAN):
 	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_SNAN):
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_SNAN):
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_SNAN):
+		return ieee754dp_nanxcpt(y);
+
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_ZERO):
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_NORM):
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_DNORM):
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF):
-		ieee754_setcx(IEEE754_INVALID_OPERATION);
-		return ieee754dp_nanxcpt(ieee754dp_indef());
+		return ieee754dp_nanxcpt(x);
 
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN):
@@ -150,8 +151,6 @@ union ieee754dp ieee754dp_add(union ieee754dp x, union ieee754dp y)
 		 * leaving result in xm, xs and xe.
 		 */
 		xm = xm + ym;
-		xe = xe;
-		xs = xs;
 
 		if (xm >> (DP_FBITS + 1 + 3)) { /* carry out */
 			xm = XDPSRS1(xm);
@@ -160,11 +159,8 @@ union ieee754dp ieee754dp_add(union ieee754dp x, union ieee754dp y)
 	} else {
 		if (xm >= ym) {
 			xm = xm - ym;
-			xe = xe;
-			xs = xs;
 		} else {
 			xm = ym - xm;
-			xe = xe;
 			xs = ys;
 		}
 		if (xm == 0)
diff --git a/arch/mips/math-emu/dp_cmp.c b/arch/mips/math-emu/dp_cmp.c
index 30f95f6e9ac4..a29880e29ae4 100644
--- a/arch/mips/math-emu/dp_cmp.c
+++ b/arch/mips/math-emu/dp_cmp.c
@@ -35,16 +35,11 @@ int ieee754dp_cmp(union ieee754dp x, union ieee754dp y, int cmp, int sig)
 	FLUSHYDP;
 	ieee754_clearcx();	/* Even clear inexact flag here */
 
-	if (ieee754dp_isnan(x) || ieee754dp_isnan(y)) {
-		if (sig || xc == IEEE754_CLASS_SNAN || yc == IEEE754_CLASS_SNAN)
+	if (ieee754_class_nan(xc) || ieee754_class_nan(yc)) {
+		if (sig ||
+		    xc == IEEE754_CLASS_SNAN || yc == IEEE754_CLASS_SNAN)
 			ieee754_setcx(IEEE754_INVALID_OPERATION);
-		if (cmp & IEEE754_CUN)
-			return 1;
-		if (cmp & (IEEE754_CLT | IEEE754_CGT)) {
-			if (sig && ieee754_setandtestcx(IEEE754_INVALID_OPERATION))
-				return 0;
-		}
-		return 0;
+		return (cmp & IEEE754_CUN) != 0;
 	} else {
 		vx = x.bits;
 		vy = y.bits;
diff --git a/arch/mips/math-emu/dp_div.c b/arch/mips/math-emu/dp_div.c
index bef0e55e5938..f4746f7c5f63 100644
--- a/arch/mips/math-emu/dp_div.c
+++ b/arch/mips/math-emu/dp_div.c
@@ -39,19 +39,20 @@ union ieee754dp ieee754dp_div(union ieee754dp x, union ieee754dp y)
 	FLUSHYDP;
 
 	switch (CLPAIR(xc, yc)) {
-	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_SNAN):
-	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_SNAN):
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_SNAN):
 	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_SNAN):
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_SNAN):
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_SNAN):
+		return ieee754dp_nanxcpt(y);
+
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_ZERO):
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_NORM):
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_DNORM):
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF):
-		ieee754_setcx(IEEE754_INVALID_OPERATION);
-		return ieee754dp_nanxcpt(ieee754dp_indef());
+		return ieee754dp_nanxcpt(x);
 
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN):
diff --git a/arch/mips/math-emu/dp_fsp.c b/arch/mips/math-emu/dp_fsp.c
index ffb69c5830b0..57d09ca5403a 100644
--- a/arch/mips/math-emu/dp_fsp.c
+++ b/arch/mips/math-emu/dp_fsp.c
@@ -22,6 +22,12 @@
 #include "ieee754sp.h"
 #include "ieee754dp.h"
 
+static inline union ieee754dp ieee754dp_nan_fsp(int xs, u64 xm)
+{
+	return builddp(xs, DP_EMAX + 1 + DP_EBIAS,
+		       xm << (DP_FBITS - SP_FBITS));
+}
+
 union ieee754dp ieee754dp_fsp(union ieee754sp x)
 {
 	COMPXSP;
@@ -34,15 +40,11 @@ union ieee754dp ieee754dp_fsp(union ieee754sp x)
 
 	switch (xc) {
 	case IEEE754_CLASS_SNAN:
-		ieee754_setcx(IEEE754_INVALID_OPERATION);
-		return ieee754dp_nanxcpt(ieee754dp_indef());
+		return ieee754dp_nanxcpt(ieee754dp_nan_fsp(xs, xm));
 
 	case IEEE754_CLASS_QNAN:
-		return ieee754dp_nanxcpt(builddp(xs,
-						 DP_EMAX + 1 + DP_EBIAS,
-						 ((u64) xm
-						  << (DP_FBITS -
-						      SP_FBITS))));
+		return ieee754dp_nan_fsp(xs, xm);
+
 	case IEEE754_CLASS_INF:
 		return ieee754dp_inf(xs);
 
diff --git a/arch/mips/math-emu/dp_mul.c b/arch/mips/math-emu/dp_mul.c
index d3acdedb5b9d..d0901f03fa19 100644
--- a/arch/mips/math-emu/dp_mul.c
+++ b/arch/mips/math-emu/dp_mul.c
@@ -47,19 +47,20 @@ union ieee754dp ieee754dp_mul(union ieee754dp x, union ieee754dp y)
 	FLUSHYDP;
 
 	switch (CLPAIR(xc, yc)) {
-	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_SNAN):
-	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_SNAN):
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_SNAN):
 	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_SNAN):
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_SNAN):
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_SNAN):
+		return ieee754dp_nanxcpt(y);
+
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_ZERO):
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_NORM):
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_DNORM):
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF):
-		ieee754_setcx(IEEE754_INVALID_OPERATION);
-		return ieee754dp_nanxcpt(ieee754dp_indef());
+		return ieee754dp_nanxcpt(x);
 
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN):
diff --git a/arch/mips/math-emu/dp_simple.c b/arch/mips/math-emu/dp_simple.c
index bccbe90efceb..926d56bf37f2 100644
--- a/arch/mips/math-emu/dp_simple.c
+++ b/arch/mips/math-emu/dp_simple.c
@@ -23,44 +23,27 @@
 
 union ieee754dp ieee754dp_neg(union ieee754dp x)
 {
-	COMPXDP;
-
-	EXPLODEXDP;
-	ieee754_clearcx();
-	FLUSHXDP;
-
-	/*
-	 * Invert the sign ALWAYS to prevent an endless recursion on
-	 * pow() in libc.
-	 */
-	/* quick fix up */
-	DPSIGN(x) ^= 1;
-
-	if (xc == IEEE754_CLASS_SNAN) {
-		union ieee754dp y = ieee754dp_indef();
-		ieee754_setcx(IEEE754_INVALID_OPERATION);
-		DPSIGN(y) = DPSIGN(x);
-		return ieee754dp_nanxcpt(y);
-	}
-
-	return x;
+	unsigned int oldrm;
+	union ieee754dp y;
+
+	oldrm = ieee754_csr.rm;
+	ieee754_csr.rm = FPU_CSR_RD;
+	y = ieee754dp_sub(ieee754dp_zero(0), x);
+	ieee754_csr.rm = oldrm;
+	return y;
 }
 
 union ieee754dp ieee754dp_abs(union ieee754dp x)
 {
-	COMPXDP;
-
-	EXPLODEXDP;
-	ieee754_clearcx();
-	FLUSHXDP;
-
-	/* Clear sign ALWAYS, irrespective of NaN */
-	DPSIGN(x) = 0;
-
-	if (xc == IEEE754_CLASS_SNAN) {
-		ieee754_setcx(IEEE754_INVALID_OPERATION);
-		return ieee754dp_nanxcpt(ieee754dp_indef());
-	}
-
-	return x;
+	unsigned int oldrm;
+	union ieee754dp y;
+
+	oldrm = ieee754_csr.rm;
+	ieee754_csr.rm = FPU_CSR_RD;
+	if (DPSIGN(x))
+		y = ieee754dp_sub(ieee754dp_zero(0), x);
+	else
+		y = ieee754dp_add(ieee754dp_zero(0), x);
+	ieee754_csr.rm = oldrm;
+	return y;
 }
diff --git a/arch/mips/math-emu/dp_sqrt.c b/arch/mips/math-emu/dp_sqrt.c
index 041bbb6124bb..cd5bc083001e 100644
--- a/arch/mips/math-emu/dp_sqrt.c
+++ b/arch/mips/math-emu/dp_sqrt.c
@@ -42,13 +42,12 @@ union ieee754dp ieee754dp_sqrt(union ieee754dp x)
 
 	/* x == INF or NAN? */
 	switch (xc) {
-	case IEEE754_CLASS_QNAN:
-		/* sqrt(Nan) = Nan */
+	case IEEE754_CLASS_SNAN:
 		return ieee754dp_nanxcpt(x);
 
-	case IEEE754_CLASS_SNAN:
-		ieee754_setcx(IEEE754_INVALID_OPERATION);
-		return ieee754dp_nanxcpt(ieee754dp_indef());
+	case IEEE754_CLASS_QNAN:
+		/* sqrt(Nan) = Nan */
+		return x;
 
 	case IEEE754_CLASS_ZERO:
 		/* sqrt(0) = 0 */
@@ -58,7 +57,7 @@ union ieee754dp ieee754dp_sqrt(union ieee754dp x)
 		if (xs) {
 			/* sqrt(-Inf) = Nan */
 			ieee754_setcx(IEEE754_INVALID_OPERATION);
-			return ieee754dp_nanxcpt(ieee754dp_indef());
+			return ieee754dp_indef();
 		}
 		/* sqrt(+Inf) = Inf */
 		return x;
@@ -71,7 +70,7 @@ union ieee754dp ieee754dp_sqrt(union ieee754dp x)
 		if (xs) {
 			/* sqrt(-x) = Nan */
 			ieee754_setcx(IEEE754_INVALID_OPERATION);
-			return ieee754dp_nanxcpt(ieee754dp_indef());
+			return ieee754dp_indef();
 		}
 		break;
 	}
diff --git a/arch/mips/math-emu/dp_sub.c b/arch/mips/math-emu/dp_sub.c
index 7a174029043a..fc17a781b9ae 100644
--- a/arch/mips/math-emu/dp_sub.c
+++ b/arch/mips/math-emu/dp_sub.c
@@ -37,19 +37,20 @@ union ieee754dp ieee754dp_sub(union ieee754dp x, union ieee754dp y)
 	FLUSHYDP;
 
 	switch (CLPAIR(xc, yc)) {
-	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_SNAN):
-	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_SNAN):
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_SNAN):
 	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_SNAN):
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_SNAN):
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_SNAN):
+		return ieee754dp_nanxcpt(y);
+
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_ZERO):
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_NORM):
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_DNORM):
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF):
-		ieee754_setcx(IEEE754_INVALID_OPERATION);
-		return ieee754dp_nanxcpt(ieee754dp_indef());
+		return ieee754dp_nanxcpt(x);
 
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN):
@@ -153,8 +154,6 @@ union ieee754dp ieee754dp_sub(union ieee754dp x, union ieee754dp y)
 		/* generate 28 bit result of adding two 27 bit numbers
 		 */
 		xm = xm + ym;
-		xe = xe;
-		xs = xs;
 
 		if (xm >> (DP_FBITS + 1 + 3)) { /* carry out */
 			xm = XDPSRS1(xm);	/* shift preserving sticky */
@@ -163,11 +162,8 @@ union ieee754dp ieee754dp_sub(union ieee754dp x, union ieee754dp y)
 	} else {
 		if (xm >= ym) {
 			xm = xm - ym;
-			xe = xe;
-			xs = xs;
 		} else {
 			xm = ym - xm;
-			xe = xe;
 			xs = ys;
 		}
 		if (xm == 0) {
diff --git a/arch/mips/math-emu/dsemul.c b/arch/mips/math-emu/dsemul.c
index 4f514f3724cb..e0b5cc27d78b 100644
--- a/arch/mips/math-emu/dsemul.c
+++ b/arch/mips/math-emu/dsemul.c
@@ -94,9 +94,9 @@ int mips_dsemul(struct pt_regs *regs, mips_instruction ir, unsigned long cpc)
 	regs->cp0_epc = ((unsigned long) &fr->emul) |
 		get_isa16_mode(regs->cp0_epc);
 
-	flush_cache_sigtramp((unsigned long)&fr->badinst);
+	flush_cache_sigtramp((unsigned long)&fr->emul);
 
-	return SIGILL;		/* force out of emulation loop */
+	return 0;
 }
 
 int do_dsemulret(struct pt_regs *xcp)
@@ -158,6 +158,6 @@ int do_dsemulret(struct pt_regs *xcp)
 
 	/* Set EPC to return to post-branch instruction */
 	xcp->cp0_epc = epc;
-
+	MIPS_FPU_EMU_INC_STATS(ds_emul);
 	return 1;
 }
diff --git a/arch/mips/math-emu/ieee754.h b/arch/mips/math-emu/ieee754.h
index 43c4fb522ac2..a5ca108ce467 100644
--- a/arch/mips/math-emu/ieee754.h
+++ b/arch/mips/math-emu/ieee754.h
@@ -126,84 +126,21 @@ enum {
 #define IEEE754_CGT	0x04
 #define IEEE754_CUN	0x08
 
-/* "normal" comparisons
-*/
-static inline int ieee754sp_eq(union ieee754sp x, union ieee754sp y)
-{
-	return ieee754sp_cmp(x, y, IEEE754_CEQ, 0);
-}
-
-static inline int ieee754sp_ne(union ieee754sp x, union ieee754sp y)
-{
-	return ieee754sp_cmp(x, y,
-			     IEEE754_CLT | IEEE754_CGT | IEEE754_CUN, 0);
-}
-
-static inline int ieee754sp_lt(union ieee754sp x, union ieee754sp y)
-{
-	return ieee754sp_cmp(x, y, IEEE754_CLT, 0);
-}
-
-static inline int ieee754sp_le(union ieee754sp x, union ieee754sp y)
-{
-	return ieee754sp_cmp(x, y, IEEE754_CLT | IEEE754_CEQ, 0);
-}
-
-static inline int ieee754sp_gt(union ieee754sp x, union ieee754sp y)
-{
-	return ieee754sp_cmp(x, y, IEEE754_CGT, 0);
-}
-
-
-static inline int ieee754sp_ge(union ieee754sp x, union ieee754sp y)
-{
-	return ieee754sp_cmp(x, y, IEEE754_CGT | IEEE754_CEQ, 0);
-}
-
-static inline int ieee754dp_eq(union ieee754dp x, union ieee754dp y)
-{
-	return ieee754dp_cmp(x, y, IEEE754_CEQ, 0);
-}
-
-static inline int ieee754dp_ne(union ieee754dp x, union ieee754dp y)
-{
-	return ieee754dp_cmp(x, y,
-			     IEEE754_CLT | IEEE754_CGT | IEEE754_CUN, 0);
-}
-
-static inline int ieee754dp_lt(union ieee754dp x, union ieee754dp y)
-{
-	return ieee754dp_cmp(x, y, IEEE754_CLT, 0);
-}
-
-static inline int ieee754dp_le(union ieee754dp x, union ieee754dp y)
-{
-	return ieee754dp_cmp(x, y, IEEE754_CLT | IEEE754_CEQ, 0);
-}
-
-static inline int ieee754dp_gt(union ieee754dp x, union ieee754dp y)
-{
-	return ieee754dp_cmp(x, y, IEEE754_CGT, 0);
-}
-
-static inline int ieee754dp_ge(union ieee754dp x, union ieee754dp y)
-{
-	return ieee754dp_cmp(x, y, IEEE754_CGT | IEEE754_CEQ, 0);
-}
-
 /*
  * The control status register
  */
 struct _ieee754_csr {
-	__BITFIELD_FIELD(unsigned pad0:7,
-	__BITFIELD_FIELD(unsigned nod:1,	/* set 1 for no denormalised numbers */
-	__BITFIELD_FIELD(unsigned c:1,		/* condition */
-	__BITFIELD_FIELD(unsigned pad1:5,
+	__BITFIELD_FIELD(unsigned fcc:7,	/* condition[7:1] */
+	__BITFIELD_FIELD(unsigned nod:1,	/* set 1 for no denormals */
+	__BITFIELD_FIELD(unsigned c:1,		/* condition[0] */
+	__BITFIELD_FIELD(unsigned pad0:3,
+	__BITFIELD_FIELD(unsigned abs2008:1,	/* IEEE 754-2008 ABS/NEG.fmt */
+	__BITFIELD_FIELD(unsigned nan2008:1,	/* IEEE 754-2008 NaN mode */
 	__BITFIELD_FIELD(unsigned cx:6,		/* exceptions this operation */
 	__BITFIELD_FIELD(unsigned mx:5,		/* exception enable  mask */
 	__BITFIELD_FIELD(unsigned sx:5,		/* exceptions total */
 	__BITFIELD_FIELD(unsigned rm:2,		/* current rounding mode */
-	;))))))))
+	;))))))))))
 };
 #define ieee754_csr (*(struct _ieee754_csr *)(&current->thread.fpu.fcr31))
 
@@ -257,23 +194,23 @@ static inline int ieee754_sxtest(unsigned n)
 union ieee754sp ieee754sp_dump(char *s, union ieee754sp x);
 union ieee754dp ieee754dp_dump(char *s, union ieee754dp x);
 
-#define IEEE754_SPCVAL_PZERO	0
-#define IEEE754_SPCVAL_NZERO	1
-#define IEEE754_SPCVAL_PONE	2
-#define IEEE754_SPCVAL_NONE	3
-#define IEEE754_SPCVAL_PTEN	4
-#define IEEE754_SPCVAL_NTEN	5
-#define IEEE754_SPCVAL_PINFINITY	6
-#define IEEE754_SPCVAL_NINFINITY	7
-#define IEEE754_SPCVAL_INDEF	8
-#define IEEE754_SPCVAL_PMAX	9	/* +max norm */
-#define IEEE754_SPCVAL_NMAX	10	/* -max norm */
-#define IEEE754_SPCVAL_PMIN	11	/* +min norm */
-#define IEEE754_SPCVAL_NMIN	12	/* +min norm */
-#define IEEE754_SPCVAL_PMIND	13	/* +min denorm */
-#define IEEE754_SPCVAL_NMIND	14	/* +min denorm */
-#define IEEE754_SPCVAL_P1E31	15	/* + 1.0e31 */
-#define IEEE754_SPCVAL_P1E63	16	/* + 1.0e63 */
+#define IEEE754_SPCVAL_PZERO		0	/* +0.0 */
+#define IEEE754_SPCVAL_NZERO		1	/* -0.0 */
+#define IEEE754_SPCVAL_PONE		2	/* +1.0 */
+#define IEEE754_SPCVAL_NONE		3	/* -1.0 */
+#define IEEE754_SPCVAL_PTEN		4	/* +10.0 */
+#define IEEE754_SPCVAL_NTEN		5	/* -10.0 */
+#define IEEE754_SPCVAL_PINFINITY	6	/* +inf */
+#define IEEE754_SPCVAL_NINFINITY	7	/* -inf */
+#define IEEE754_SPCVAL_INDEF		8	/* quiet NaN */
+#define IEEE754_SPCVAL_PMAX		9	/* +max norm */
+#define IEEE754_SPCVAL_NMAX		10	/* -max norm */
+#define IEEE754_SPCVAL_PMIN		11	/* +min norm */
+#define IEEE754_SPCVAL_NMIN		12	/* -min norm */
+#define IEEE754_SPCVAL_PMIND		13	/* +min denorm */
+#define IEEE754_SPCVAL_NMIND		14	/* -min denorm */
+#define IEEE754_SPCVAL_P1E31		15	/* + 1.0e31 */
+#define IEEE754_SPCVAL_P1E63		16	/* + 1.0e63 */
 
 extern const union ieee754dp __ieee754dp_spcvals[];
 extern const union ieee754sp __ieee754sp_spcvals[];
diff --git a/arch/mips/math-emu/ieee754dp.c b/arch/mips/math-emu/ieee754dp.c
index 068f45a415fc..522d843f2ffd 100644
--- a/arch/mips/math-emu/ieee754dp.c
+++ b/arch/mips/math-emu/ieee754dp.c
@@ -30,9 +30,9 @@ int ieee754dp_class(union ieee754dp x)
 	return xc;
 }
 
-int ieee754dp_isnan(union ieee754dp x)
+static inline int ieee754dp_isnan(union ieee754dp x)
 {
-	return ieee754dp_class(x) >= IEEE754_CLASS_SNAN;
+	return ieee754_class_nan(ieee754dp_class(x));
 }
 
 static inline int ieee754dp_issnan(union ieee754dp x)
@@ -42,23 +42,16 @@ static inline int ieee754dp_issnan(union ieee754dp x)
 }
 
 
+/*
+ * Raise the Invalid Operation IEEE 754 exception
+ * and convert the signaling NaN supplied to a quiet NaN.
+ */
 union ieee754dp __cold ieee754dp_nanxcpt(union ieee754dp r)
 {
-	assert(ieee754dp_isnan(r));
-
-	if (!ieee754dp_issnan(r))	/* QNAN does not cause invalid op !! */
-		return r;
-
-	if (!ieee754_setandtestcx(IEEE754_INVALID_OPERATION)) {
-		/* not enabled convert to a quiet NaN */
-		DPMANT(r) &= (~DP_MBIT(DP_FBITS-1));
-		if (ieee754dp_isnan(r))
-			return r;
-		else
-			return ieee754dp_indef();
-	}
+	assert(ieee754dp_issnan(r));
 
-	return r;
+	ieee754_setcx(IEEE754_INVALID_OPERATION);
+	return ieee754dp_indef();
 }
 
 static u64 ieee754dp_get_rounding(int sn, u64 xm)
diff --git a/arch/mips/math-emu/ieee754dp.h b/arch/mips/math-emu/ieee754dp.h
index 61fd6fd31350..e2babd98fee3 100644
--- a/arch/mips/math-emu/ieee754dp.h
+++ b/arch/mips/math-emu/ieee754dp.h
@@ -77,6 +77,5 @@ static inline union ieee754dp builddp(int s, int bx, u64 m)
 	return r;
 }
 
-extern int ieee754dp_isnan(union ieee754dp);
 extern union ieee754dp __cold ieee754dp_nanxcpt(union ieee754dp);
 extern union ieee754dp ieee754dp_format(int, int, u64);
diff --git a/arch/mips/math-emu/ieee754int.h b/arch/mips/math-emu/ieee754int.h
index f0365bb86747..05389d5e3a93 100644
--- a/arch/mips/math-emu/ieee754int.h
+++ b/arch/mips/math-emu/ieee754int.h
@@ -44,6 +44,11 @@ static inline int ieee754_setandtestcx(const unsigned int x)
 	return ieee754_csr.mx & x;
 }
 
+static inline int ieee754_class_nan(int xc)
+{
+	return xc >= IEEE754_CLASS_SNAN;
+}
+
 #define COMPXSP \
 	unsigned xm; int xe; int xs __maybe_unused; int xc
 
diff --git a/arch/mips/math-emu/ieee754sp.c b/arch/mips/math-emu/ieee754sp.c
index ba88301579c2..ca8e35e33bf7 100644
--- a/arch/mips/math-emu/ieee754sp.c
+++ b/arch/mips/math-emu/ieee754sp.c
@@ -30,9 +30,9 @@ int ieee754sp_class(union ieee754sp x)
 	return xc;
 }
 
-int ieee754sp_isnan(union ieee754sp x)
+static inline int ieee754sp_isnan(union ieee754sp x)
 {
-	return ieee754sp_class(x) >= IEEE754_CLASS_SNAN;
+	return ieee754_class_nan(ieee754sp_class(x));
 }
 
 static inline int ieee754sp_issnan(union ieee754sp x)
@@ -42,23 +42,16 @@ static inline int ieee754sp_issnan(union ieee754sp x)
 }
 
 
+/*
+ * Raise the Invalid Operation IEEE 754 exception
+ * and convert the signaling NaN supplied to a quiet NaN.
+ */
 union ieee754sp __cold ieee754sp_nanxcpt(union ieee754sp r)
 {
-	assert(ieee754sp_isnan(r));
-
-	if (!ieee754sp_issnan(r))	/* QNAN does not cause invalid op !! */
-		return r;
-
-	if (!ieee754_setandtestcx(IEEE754_INVALID_OPERATION)) {
-		/* not enabled convert to a quiet NaN */
-		SPMANT(r) &= (~SP_MBIT(SP_FBITS-1));
-		if (ieee754sp_isnan(r))
-			return r;
-		else
-			return ieee754sp_indef();
-	}
+	assert(ieee754sp_issnan(r));
 
-	return r;
+	ieee754_setcx(IEEE754_INVALID_OPERATION);
+	return ieee754sp_indef();
 }
 
 static unsigned ieee754sp_get_rounding(int sn, unsigned xm)
diff --git a/arch/mips/math-emu/ieee754sp.h b/arch/mips/math-emu/ieee754sp.h
index ad268e332318..374a3f00a589 100644
--- a/arch/mips/math-emu/ieee754sp.h
+++ b/arch/mips/math-emu/ieee754sp.h
@@ -82,6 +82,5 @@ static inline union ieee754sp buildsp(int s, int bx, unsigned m)
 	return r;
 }
 
-extern int ieee754sp_isnan(union ieee754sp);
 extern union ieee754sp __cold ieee754sp_nanxcpt(union ieee754sp);
 extern union ieee754sp ieee754sp_format(int, int, unsigned);
diff --git a/arch/mips/math-emu/me-debugfs.c b/arch/mips/math-emu/me-debugfs.c
index becdd63e14a9..f308e0f05fc5 100644
--- a/arch/mips/math-emu/me-debugfs.c
+++ b/arch/mips/math-emu/me-debugfs.c
@@ -61,6 +61,7 @@ do {									\
 	FPU_STAT_CREATE(ieee754_overflow);
 	FPU_STAT_CREATE(ieee754_zerodiv);
 	FPU_STAT_CREATE(ieee754_invalidop);
+	FPU_STAT_CREATE(ds_emul);
 
 	return 0;
 }
diff --git a/arch/mips/math-emu/sp_add.c b/arch/mips/math-emu/sp_add.c
index 2d84d460cb67..f1c87b07d3b4 100644
--- a/arch/mips/math-emu/sp_add.c
+++ b/arch/mips/math-emu/sp_add.c
@@ -37,19 +37,20 @@ union ieee754sp ieee754sp_add(union ieee754sp x, union ieee754sp y)
 	FLUSHYSP;
 
 	switch (CLPAIR(xc, yc)) {
-	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_SNAN):
-	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_SNAN):
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_SNAN):
 	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_SNAN):
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_SNAN):
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_SNAN):
+		return ieee754sp_nanxcpt(y);
+
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_ZERO):
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_NORM):
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_DNORM):
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF):
-		ieee754_setcx(IEEE754_INVALID_OPERATION);
-		return ieee754sp_nanxcpt(ieee754sp_indef());
+		return ieee754sp_nanxcpt(x);
 
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN):
@@ -148,8 +149,6 @@ union ieee754sp ieee754sp_add(union ieee754sp x, union ieee754sp y)
 		 * leaving result in xm, xs and xe.
 		 */
 		xm = xm + ym;
-		xe = xe;
-		xs = xs;
 
 		if (xm >> (SP_FBITS + 1 + 3)) { /* carry out */
 			SPXSRSX1();
@@ -157,11 +156,8 @@ union ieee754sp ieee754sp_add(union ieee754sp x, union ieee754sp y)
 	} else {
 		if (xm >= ym) {
 			xm = xm - ym;
-			xe = xe;
-			xs = xs;
 		} else {
 			xm = ym - xm;
-			xe = xe;
 			xs = ys;
 		}
 		if (xm == 0)
diff --git a/arch/mips/math-emu/sp_cmp.c b/arch/mips/math-emu/sp_cmp.c
index addbccb2f556..67b82f1e2c4a 100644
--- a/arch/mips/math-emu/sp_cmp.c
+++ b/arch/mips/math-emu/sp_cmp.c
@@ -35,16 +35,11 @@ int ieee754sp_cmp(union ieee754sp x, union ieee754sp y, int cmp, int sig)
 	FLUSHYSP;
 	ieee754_clearcx();	/* Even clear inexact flag here */
 
-	if (ieee754sp_isnan(x) || ieee754sp_isnan(y)) {
-		if (sig || xc == IEEE754_CLASS_SNAN || yc == IEEE754_CLASS_SNAN)
+	if (ieee754_class_nan(xc) || ieee754_class_nan(yc)) {
+		if (sig ||
+		    xc == IEEE754_CLASS_SNAN || yc == IEEE754_CLASS_SNAN)
 			ieee754_setcx(IEEE754_INVALID_OPERATION);
-		if (cmp & IEEE754_CUN)
-			return 1;
-		if (cmp & (IEEE754_CLT | IEEE754_CGT)) {
-			if (sig && ieee754_setandtestcx(IEEE754_INVALID_OPERATION))
-				return 0;
-		}
-		return 0;
+		return (cmp & IEEE754_CUN) != 0;
 	} else {
 		vx = x.bits;
 		vy = y.bits;
diff --git a/arch/mips/math-emu/sp_div.c b/arch/mips/math-emu/sp_div.c
index 721f317aa877..27f6db3a0a4c 100644
--- a/arch/mips/math-emu/sp_div.c
+++ b/arch/mips/math-emu/sp_div.c
@@ -39,19 +39,20 @@ union ieee754sp ieee754sp_div(union ieee754sp x, union ieee754sp y)
 	FLUSHYSP;
 
 	switch (CLPAIR(xc, yc)) {
-	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_SNAN):
-	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_SNAN):
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_SNAN):
 	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_SNAN):
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_SNAN):
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_SNAN):
+		return ieee754sp_nanxcpt(y);
+
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_ZERO):
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_NORM):
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_DNORM):
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF):
-		ieee754_setcx(IEEE754_INVALID_OPERATION);
-		return ieee754sp_nanxcpt(ieee754sp_indef());
+		return ieee754sp_nanxcpt(x);
 
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN):
diff --git a/arch/mips/math-emu/sp_fdp.c b/arch/mips/math-emu/sp_fdp.c
index 1b266fb16973..3797148893ad 100644
--- a/arch/mips/math-emu/sp_fdp.c
+++ b/arch/mips/math-emu/sp_fdp.c
@@ -22,12 +22,19 @@
 #include "ieee754sp.h"
 #include "ieee754dp.h"
 
+static inline union ieee754sp ieee754sp_nan_fdp(int xs, u64 xm)
+{
+	return buildsp(xs, SP_EMAX + 1 + SP_EBIAS,
+		       xm >> (DP_FBITS - SP_FBITS));
+}
+
 union ieee754sp ieee754sp_fdp(union ieee754dp x)
 {
+	union ieee754sp y;
 	u32 rm;
 
 	COMPXDP;
-	union ieee754sp nan;
+	COMPYSP;
 
 	EXPLODEXDP;
 
@@ -37,15 +44,14 @@ union ieee754sp ieee754sp_fdp(union ieee754dp x)
 
 	switch (xc) {
 	case IEEE754_CLASS_SNAN:
-		ieee754_setcx(IEEE754_INVALID_OPERATION);
-		return ieee754sp_nanxcpt(ieee754sp_indef());
+		return ieee754sp_nanxcpt(ieee754sp_nan_fdp(xs, xm));
 
 	case IEEE754_CLASS_QNAN:
-		nan = buildsp(xs, SP_EMAX + 1 + SP_EBIAS, (u32)
-				(xm >> (DP_FBITS - SP_FBITS)));
-		if (!ieee754sp_isnan(nan))
-			nan = ieee754sp_indef();
-		return ieee754sp_nanxcpt(nan);
+		y = ieee754sp_nan_fdp(xs, xm);
+		EXPLODEYSP;
+		if (!ieee754_class_nan(yc))
+			y = ieee754sp_indef();
+		return y;
 
 	case IEEE754_CLASS_INF:
 		return ieee754sp_inf(xs);
diff --git a/arch/mips/math-emu/sp_mul.c b/arch/mips/math-emu/sp_mul.c
index 890c13a2965e..d910c43a6f30 100644
--- a/arch/mips/math-emu/sp_mul.c
+++ b/arch/mips/math-emu/sp_mul.c
@@ -47,19 +47,20 @@ union ieee754sp ieee754sp_mul(union ieee754sp x, union ieee754sp y)
 	FLUSHYSP;
 
 	switch (CLPAIR(xc, yc)) {
-	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_SNAN):
-	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_SNAN):
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_SNAN):
 	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_SNAN):
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_SNAN):
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_SNAN):
+		return ieee754sp_nanxcpt(y);
+
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_ZERO):
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_NORM):
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_DNORM):
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF):
-		ieee754_setcx(IEEE754_INVALID_OPERATION);
-		return ieee754sp_nanxcpt(ieee754sp_indef());
+		return ieee754sp_nanxcpt(x);
 
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN):
diff --git a/arch/mips/math-emu/sp_simple.c b/arch/mips/math-emu/sp_simple.c
index f1ffaa9a17e0..c50e9451f2d2 100644
--- a/arch/mips/math-emu/sp_simple.c
+++ b/arch/mips/math-emu/sp_simple.c
@@ -23,44 +23,27 @@
 
 union ieee754sp ieee754sp_neg(union ieee754sp x)
 {
-	COMPXSP;
-
-	EXPLODEXSP;
-	ieee754_clearcx();
-	FLUSHXSP;
-
-	/*
-	 * Invert the sign ALWAYS to prevent an endless recursion on
-	 * pow() in libc.
-	 */
-	/* quick fix up */
-	SPSIGN(x) ^= 1;
-
-	if (xc == IEEE754_CLASS_SNAN) {
-		union ieee754sp y = ieee754sp_indef();
-		ieee754_setcx(IEEE754_INVALID_OPERATION);
-		SPSIGN(y) = SPSIGN(x);
-		return ieee754sp_nanxcpt(y);
-	}
-
-	return x;
+	unsigned int oldrm;
+	union ieee754sp y;
+
+	oldrm = ieee754_csr.rm;
+	ieee754_csr.rm = FPU_CSR_RD;
+	y = ieee754sp_sub(ieee754sp_zero(0), x);
+	ieee754_csr.rm = oldrm;
+	return y;
 }
 
 union ieee754sp ieee754sp_abs(union ieee754sp x)
 {
-	COMPXSP;
-
-	EXPLODEXSP;
-	ieee754_clearcx();
-	FLUSHXSP;
-
-	/* Clear sign ALWAYS, irrespective of NaN */
-	SPSIGN(x) = 0;
-
-	if (xc == IEEE754_CLASS_SNAN) {
-		ieee754_setcx(IEEE754_INVALID_OPERATION);
-		return ieee754sp_nanxcpt(ieee754sp_indef());
-	}
-
-	return x;
+	unsigned int oldrm;
+	union ieee754sp y;
+
+	oldrm = ieee754_csr.rm;
+	ieee754_csr.rm = FPU_CSR_RD;
+	if (SPSIGN(x))
+		y = ieee754sp_sub(ieee754sp_zero(0), x);
+	else
+		y = ieee754sp_add(ieee754sp_zero(0), x);
+	ieee754_csr.rm = oldrm;
+	return y;
 }
diff --git a/arch/mips/math-emu/sp_sqrt.c b/arch/mips/math-emu/sp_sqrt.c
index b7c098a86f95..67059c33a250 100644
--- a/arch/mips/math-emu/sp_sqrt.c
+++ b/arch/mips/math-emu/sp_sqrt.c
@@ -35,13 +35,12 @@ union ieee754sp ieee754sp_sqrt(union ieee754sp x)
 
 	/* x == INF or NAN? */
 	switch (xc) {
-	case IEEE754_CLASS_QNAN:
-		/* sqrt(Nan) = Nan */
+	case IEEE754_CLASS_SNAN:
 		return ieee754sp_nanxcpt(x);
 
-	case IEEE754_CLASS_SNAN:
-		ieee754_setcx(IEEE754_INVALID_OPERATION);
-		return ieee754sp_nanxcpt(ieee754sp_indef());
+	case IEEE754_CLASS_QNAN:
+		/* sqrt(Nan) = Nan */
+		return x;
 
 	case IEEE754_CLASS_ZERO:
 		/* sqrt(0) = 0 */
@@ -51,7 +50,7 @@ union ieee754sp ieee754sp_sqrt(union ieee754sp x)
 		if (xs) {
 			/* sqrt(-Inf) = Nan */
 			ieee754_setcx(IEEE754_INVALID_OPERATION);
-			return ieee754sp_nanxcpt(ieee754sp_indef());
+			return ieee754sp_indef();
 		}
 		/* sqrt(+Inf) = Inf */
 		return x;
@@ -61,7 +60,7 @@ union ieee754sp ieee754sp_sqrt(union ieee754sp x)
 		if (xs) {
 			/* sqrt(-x) = Nan */
 			ieee754_setcx(IEEE754_INVALID_OPERATION);
-			return ieee754sp_nanxcpt(ieee754sp_indef());
+			return ieee754sp_indef();
 		}
 		break;
 	}
diff --git a/arch/mips/math-emu/sp_sub.c b/arch/mips/math-emu/sp_sub.c
index 8592e49032b8..ec5f937a8b3e 100644
--- a/arch/mips/math-emu/sp_sub.c
+++ b/arch/mips/math-emu/sp_sub.c
@@ -37,19 +37,20 @@ union ieee754sp ieee754sp_sub(union ieee754sp x, union ieee754sp y)
 	FLUSHYSP;
 
 	switch (CLPAIR(xc, yc)) {
-	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_SNAN):
-	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_SNAN):
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_SNAN):
 	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_SNAN):
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_SNAN):
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_SNAN):
+		return ieee754sp_nanxcpt(y);
+
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_ZERO):
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_NORM):
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_DNORM):
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF):
-		ieee754_setcx(IEEE754_INVALID_OPERATION);
-		return ieee754sp_nanxcpt(ieee754sp_indef());
+		return ieee754sp_nanxcpt(x);
 
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN):
@@ -148,8 +149,6 @@ union ieee754sp ieee754sp_sub(union ieee754sp x, union ieee754sp y)
 		/* generate 28 bit result of adding two 27 bit numbers
 		 */
 		xm = xm + ym;
-		xe = xe;
-		xs = xs;
 
 		if (xm >> (SP_FBITS + 1 + 3)) { /* carry out */
 			SPXSRSX1();	/* shift preserving sticky */
@@ -157,11 +156,8 @@ union ieee754sp ieee754sp_sub(union ieee754sp x, union ieee754sp y)
 	} else {
 		if (xm >= ym) {
 			xm = xm - ym;
-			xe = xe;
-			xs = xs;
 		} else {
 			xm = ym - xm;
-			xe = xe;
 			xs = ys;
 		}
 		if (xm == 0) {