Merge branch 'upstream' of git://git.linux-mips.org/pub/scm/ralf/upstream-linus

Pull MIPS updates from Ralf Baechle:
 "This is the main pull request for MIPS for 4.7.  Here's the summary of
  the changes:

   - ATH79: Support for DTB passuing using the UHI boot protocol
   - ATH79: Remove support for builtin DTB.
   - ATH79: Add zboot debug serial support.
   - ATH79: Add initial support for Dragino MS14 (Dragine 2), Onion Omega
            and DPT-Module.
   - ATH79: Update devicetree clock support for AR9132 and AR9331.
   - ATH79: Cleanup the DT code.
   - ATH79: Support newer SOCs in ath79_ddr_ctrl_init.
   - ATH79: Fix regression in PCI window initialization.
   - BCM47xx: Move SPROM driver to drivers/firmware/
   - BCM63xx: Enable partition parser in defconfig.
   - BMIPS: BMIPS5000 has I cache filing from D cache
   - BMIPS: BMIPS: Add cpu-feature-overrides.h
   - BMIPS: Add Whirlwind support
   - BMIPS: Adjust mips-hpt-frequency for BCM7435
   - BMIPS: Remove maxcpus from BCM97435SVMB DTS
   - BMIPS: Add missing 7038 L1 register cells to BCM7435
   - BMIPS: Various tweaks to initialization code.
   - BMIPS: Enable partition parser in defconfig.
   - BMIPS: Cache tweaks.
   - BMIPS: Add UART, I2C and SATA devices to DT.
   - BMIPS: Add BCM6358 and BCM63268support
   - BMIPS: Add device tree example for BCM6358.
   - BMIPS: Improve Improve BCM6328 and BCM6368 device trees
   - Lantiq: Add support for device tree file from boot loader
   - Lantiq: Allow build with no built-in DT.
   - Loongson 3: Reserve 32MB for RS780E integrated GPU.
   - Loongson 3: Fix build error after ld-version.sh modification
   - Loongson 3: Move chipset ACPI code from drivers to arch.
   - Loongson 3: Speedup irq processing.
   - Loongson 3: Add basic Loongson 3A support.
   - Loongson 3: Set cache flush handlers to nop.
   - Loongson 3: Invalidate special TLBs when needed.
   - Loongson 3: Fast TLB refill handler.
   - MT7620: Fallback strategy for invalid syscfg0.
   - Netlogic: Fix CP0_EBASE redefinition warnings
   - Octeon: Initialization fixes
   - Octeon: Add DTS files for the D-Link DSR-1000N and EdgeRouter Lite
   - Octeon: Enable add Octeon-drivers in cavium_octeon_defconfig
   - Octeon: Correctly handle endian-swapped initramfs images.
   - Octeon: Support CN73xx, CN75xx and CN78xx.
   - Octeon: Remove dead code from cvmx-sysinfo.
   - Octeon: Extend number of supported CPUs past 32.
   - Octeon: Remove some code limiting NR_IRQS to 255.
   - Octeon: Simplify octeon_irq_ciu_gpio_set_type.
   - Octeon: Mark some functions __init in smp.c
   - Octeon: Octeon: Add Octeon III CN7xxx interface detection
   - PIC32: Add serial driver and bindings for it.
   - PIC32: Add PIC32 deadman timer driver and bindings.
   - PIC32: Add PIC32 clock timer driver and bindings.
   - Pistachio: Determine SoC revision during boot
   - Sibyte: Fix Kconfig dependencies of SIBYTE_BUS_WATCHER.
   - Sibyte: Strip redundant comments from bcm1480_regs.h.
   - Panic immediately if panic_on_oops is set.
   - module: fix incorrect IS_ERR_VALUE macro usage.
   - module: Make consistent use of pr_*
   - Remove no longer needed work_on_cpu() call.
   - Remove CONFIG_IPV6_PRIVACY from defconfigs.
   - Fix registers of non-crashing CPUs in dumps.
   - Handle MIPSisms in new vmcore_elf32_check_arch.
   - Select CONFIG_HANDLE_DOMAIN_IRQ and make it work.
   - Allow RIXI to be used on non-R2 or R6 cores.
   - Reserve nosave data for hibernation
   - Fix siginfo.h to use strict POSIX types.
   - Don't unwind user mode with EVA.
   - Fix watchpoint restoration
   - Ptrace watchpoints for R6.
   - Sync icache when it fills from dcache
   - I6400 I-cache fills from dcache.
   - Various MSA fixes.
   - Cleanup MIPS_CPU_* definitions.
   - Signal: Move generic copy_siginfo to signal.h
   - Signal: Fix uapi include in exported asm/siginfo.h
   - Timer fixes for sake of KVM.
   - XPA TLB refill fixes.
   - Treat perf counter feature
   - Update John Crispin's email address
   - Add PIC32 watchdog and bindings.
   - Handle R10000 LL/SC bug in set_pte()
   - cpufreq: Various fixes for Longson1.
   - R6: Fix R2 emulation.
   - mathemu: Cosmetic fix to ADDIUPC emulation, plenty of other small fixes
   - ELF: ABI and FP fixes.
   - Allow for relocatable kernel and use that to support KASLR.
   - Fix CPC_BASE_ADDR mask
   - Plenty fo smp-cps, CM, R6 and M6250 fixes.
   - Make reset_control_ops const.
   - Fix kernel command line handling of leading whitespace.
   - Cleanups to cache handling.
   - Add brcm, bcm6345-l1-intc device tree bindings.
   - Use generic clkdev.h header
   - Remove CLK_IS_ROOT usage.
   - Misc small cleanups.
   - CM: Fix compilation error when !MIPS_CM
   - oprofile: Fix a preemption issue
   - Detect DSP ASE v3 support:1"

* 'upstream' of git://git.linux-mips.org/pub/scm/ralf/upstream-linus: (275 commits)
  MIPS: pic32mzda: fix getting timer clock rate.
  MIPS: ath79: fix regression in PCI window initialization
  MIPS: ath79: make ath79_ddr_ctrl_init() compatible for newer SoCs
  MIPS: Fix VZ probe gas errors with binutils <2.24
  MIPS: perf: Fix I6400 event numbers
  MIPS: DEC: Export `ioasic_ssr_lock' to modules
  MIPS: MSA: Fix a link error on `_init_msa_upper' with older GCC
  MIPS: CM: Fix compilation error when !MIPS_CM
  MIPS: Fix genvdso error on rebuild
  USB: ohci-jz4740: Remove obsolete driver
  MIPS: JZ4740: Probe OHCI platform device via DT
  MIPS: JZ4740: Qi LB60: Remove support for AVT2 variant
  MIPS: pistachio: Determine SoC revision during boot
  MIPS: BMIPS: Adjust mips-hpt-frequency for BCM7435
  mips: mt7620: fallback to SDRAM when syscfg0 does not have a valid value for the memory type
  MIPS: Prevent "restoration" of MSA context in non-MSA kernels
  MIPS: cevt-r4k: Dynamically calculate min_delta_ns
  MIPS: malta-time: Take seconds into account
  MIPS: malta-time: Start GIC count before syncing to RTC
  MIPS: Force CPUs to lose FP context during mode switches
  ...

15 files changed, 139 insertions, 582 deletions

diff --git a/arch/mips/math-emu/Makefile b/arch/mips/math-emu/Makefile
index a19641d3ac23..e9bbc2a6526f 100644
--- a/arch/mips/math-emu/Makefile
+++ b/arch/mips/math-emu/Makefile
@@ -4,9 +4,9 @@
 
 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_maddf.o dp_msubf.o dp_2008class.o dp_fmin.o dp_fmax.o \
+	   dp_tint.o dp_fint.o dp_maddf.o dp_2008class.o dp_fmin.o dp_fmax.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_maddf.o sp_msubf.o sp_2008class.o sp_fmin.o sp_fmax.o \
+	   sp_tint.o sp_fint.o sp_maddf.o sp_2008class.o sp_fmin.o sp_fmax.o \
 	   dsemul.o
 
 lib-y	+= ieee754d.o \
diff --git a/arch/mips/math-emu/cp1emu.c b/arch/mips/math-emu/cp1emu.c
index cdfd44ffa51c..d96e912b9d44 100644
--- a/arch/mips/math-emu/cp1emu.c
+++ b/arch/mips/math-emu/cp1emu.c
@@ -445,9 +445,11 @@ static int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn,
 	case spec_op:
 		switch (insn.r_format.func) {
 		case jalr_op:
-			regs->regs[insn.r_format.rd] =
-				regs->cp0_epc + dec_insn.pc_inc +
-				dec_insn.next_pc_inc;
+			if (insn.r_format.rd != 0) {
+				regs->regs[insn.r_format.rd] =
+					regs->cp0_epc + dec_insn.pc_inc +
+					dec_insn.next_pc_inc;
+			}
 			/* Fall through */
 		case jr_op:
 			/* For R6, JR already emulated in jalr_op */
@@ -973,9 +975,10 @@ static int cop1Emulate(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 		struct mm_decoded_insn dec_insn, void *__user *fault_addr)
 {
 	unsigned long contpc = xcp->cp0_epc + dec_insn.pc_inc;
-	unsigned int cond, cbit;
+	unsigned int cond, cbit, bit0;
 	mips_instruction ir;
 	int likely, pc_inc;
+	union fpureg *fpr;
 	u32 __user *wva;
 	u64 __user *dva;
 	u32 wval;
@@ -1187,14 +1190,14 @@ emul:
 				return SIGILL;
 
 			cond = likely = 0;
+			fpr = &current->thread.fpu.fpr[MIPSInst_RT(ir)];
+			bit0 = get_fpr32(fpr, 0) & 0x1;
 			switch (MIPSInst_RS(ir)) {
 			case bc1eqz_op:
-				if (get_fpr32(&current->thread.fpu.fpr[MIPSInst_RT(ir)], 0) & 0x1)
-				    cond = 1;
+				cond = bit0 == 0;
 				break;
 			case bc1nez_op:
-				if (!(get_fpr32(&current->thread.fpu.fpr[MIPSInst_RT(ir)], 0) & 0x1))
-				    cond = 1;
+				cond = bit0 != 0;
 				break;
 			}
 			goto branch_common;
@@ -1674,7 +1677,7 @@ static int fpu_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 			union ieee754sp(*b) (union ieee754sp, union ieee754sp);
 			union ieee754sp(*u) (union ieee754sp);
 		} handler;
-		union ieee754sp fs, ft;
+		union ieee754sp fd, fs, ft;
 
 		switch (MIPSInst_FUNC(ir)) {
 			/* binary ops */
@@ -1945,6 +1948,17 @@ copcsr:
 			rfmt = w_fmt;
 			goto copcsr;
 
+		case fsel_op:
+			if (!cpu_has_mips_r6)
+				return SIGILL;
+
+			SPFROMREG(fd, MIPSInst_FD(ir));
+			if (fd.bits & 0x1)
+				SPFROMREG(rv.s, MIPSInst_FT(ir));
+			else
+				SPFROMREG(rv.s, MIPSInst_FS(ir));
+			break;
+
 		case fcvtl_op:
 			if (!cpu_has_mips_3_4_5_64_r2_r6)
 				return SIGILL;
@@ -1993,7 +2007,7 @@ copcsr:
 	}
 
 	case d_fmt: {
-		union ieee754dp fs, ft;
+		union ieee754dp fd, fs, ft;
 		union {
 			union ieee754dp(*b) (union ieee754dp, union ieee754dp);
 			union ieee754dp(*u) (union ieee754dp);
@@ -2243,6 +2257,17 @@ dcopuop:
 			rfmt = w_fmt;
 			goto copcsr;
 
+		case fsel_op:
+			if (!cpu_has_mips_r6)
+				return SIGILL;
+
+			DPFROMREG(fd, MIPSInst_FD(ir));
+			if (fd.bits & 0x1)
+				DPFROMREG(rv.d, MIPSInst_FT(ir));
+			else
+				DPFROMREG(rv.d, MIPSInst_FS(ir));
+			break;
+
 		case fcvtl_op:
 			if (!cpu_has_mips_3_4_5_64_r2_r6)
 				return SIGILL;
diff --git a/arch/mips/math-emu/dp_maddf.c b/arch/mips/math-emu/dp_maddf.c
index 119eda9fa1ea..4a2d03c72959 100644
--- a/arch/mips/math-emu/dp_maddf.c
+++ b/arch/mips/math-emu/dp_maddf.c
@@ -14,8 +14,12 @@
 
 #include "ieee754dp.h"
 
-union ieee754dp ieee754dp_maddf(union ieee754dp z, union ieee754dp x,
-				union ieee754dp y)
+enum maddf_flags {
+	maddf_negate_product	= 1 << 0,
+};
+
+static union ieee754dp _dp_maddf(union ieee754dp z, union ieee754dp x,
+				 union ieee754dp y, enum maddf_flags flags)
 {
 	int re;
 	int rs;
@@ -32,16 +36,15 @@ union ieee754dp ieee754dp_maddf(union ieee754dp z, union ieee754dp x,
 
 	COMPXDP;
 	COMPYDP;
-
-	u64 zm; int ze; int zs __maybe_unused; int zc;
+	COMPZDP;
 
 	EXPLODEXDP;
 	EXPLODEYDP;
-	EXPLODEDP(z, zc, zs, ze, zm)
+	EXPLODEZDP;
 
 	FLUSHXDP;
 	FLUSHYDP;
-	FLUSHDP(z, zc, zs, ze, zm);
+	FLUSHZDP;
 
 	ieee754_clearcx();
 
@@ -50,7 +53,7 @@ union ieee754dp ieee754dp_maddf(union ieee754dp z, union ieee754dp x,
 		ieee754_setcx(IEEE754_INVALID_OPERATION);
 		return ieee754dp_nanxcpt(z);
 	case IEEE754_CLASS_DNORM:
-		DPDNORMx(zm, ze);
+		DPDNORMZ;
 	/* QNAN is handled separately below */
 	}
 
@@ -154,13 +157,15 @@ union ieee754dp ieee754dp_maddf(union ieee754dp z, union ieee754dp x,
 
 	re = xe + ye;
 	rs = xs ^ ys;
+	if (flags & maddf_negate_product)
+		rs ^= 1;
 
 	/* shunt to top of word */
 	xm <<= 64 - (DP_FBITS + 1);
 	ym <<= 64 - (DP_FBITS + 1);
 
 	/*
-	 * Multiply 32 bits xm, ym to give high 32 bits rm with stickness.
+	 * Multiply 64 bits xm, ym to give high 64 bits rm with stickness.
 	 */
 
 	/* 32 * 32 => 64 */
@@ -198,7 +203,7 @@ union ieee754dp ieee754dp_maddf(union ieee754dp z, union ieee754dp x,
 	if ((s64) rm < 0) {
 		rm = (rm >> (64 - (DP_FBITS + 1 + 3))) |
 		     ((rm << (DP_FBITS + 1 + 3)) != 0);
-			re++;
+		re++;
 	} else {
 		rm = (rm >> (64 - (DP_FBITS + 1 + 3 + 1))) |
 		     ((rm << (DP_FBITS + 1 + 3 + 1)) != 0);
@@ -263,3 +268,15 @@ union ieee754dp ieee754dp_maddf(union ieee754dp z, union ieee754dp x,
 
 	return ieee754dp_format(zs, ze, zm);
 }
+
+union ieee754dp ieee754dp_maddf(union ieee754dp z, union ieee754dp x,
+				union ieee754dp y)
+{
+	return _dp_maddf(z, x, y, 0);
+}
+
+union ieee754dp ieee754dp_msubf(union ieee754dp z, union ieee754dp x,
+				union ieee754dp y)
+{
+	return _dp_maddf(z, x, y, maddf_negate_product);
+}
diff --git a/arch/mips/math-emu/dp_msubf.c b/arch/mips/math-emu/dp_msubf.c
deleted file mode 100644
index 12241262f856..000000000000
--- a/arch/mips/math-emu/dp_msubf.c
+++ /dev/null
@@ -1,269 +0,0 @@
-/*
- * IEEE754 floating point arithmetic
- * double precision: MSUB.f (Fused Multiply Subtract)
- * MSUBF.fmt: FPR[fd] = FPR[fd] - (FPR[fs] x FPR[ft])
- *
- * MIPS floating point support
- * Copyright (C) 2015 Imagination Technologies, Ltd.
- * Author: Markos Chandras <markos.chandras@imgtec.com>
- *
- *  This program is free software; you can distribute it and/or modify it
- *  under the terms of the GNU General Public License as published by the
- *  Free Software Foundation; version 2 of the License.
- */
-
-#include "ieee754dp.h"
-
-union ieee754dp ieee754dp_msubf(union ieee754dp z, union ieee754dp x,
-				union ieee754dp y)
-{
-	int re;
-	int rs;
-	u64 rm;
-	unsigned lxm;
-	unsigned hxm;
-	unsigned lym;
-	unsigned hym;
-	u64 lrm;
-	u64 hrm;
-	u64 t;
-	u64 at;
-	int s;
-
-	COMPXDP;
-	COMPYDP;
-
-	u64 zm; int ze; int zs __maybe_unused; int zc;
-
-	EXPLODEXDP;
-	EXPLODEYDP;
-	EXPLODEDP(z, zc, zs, ze, zm)
-
-	FLUSHXDP;
-	FLUSHYDP;
-	FLUSHDP(z, zc, zs, ze, zm);
-
-	ieee754_clearcx();
-
-	switch (zc) {
-	case IEEE754_CLASS_SNAN:
-		ieee754_setcx(IEEE754_INVALID_OPERATION);
-		return ieee754dp_nanxcpt(z);
-	case IEEE754_CLASS_DNORM:
-		DPDNORMx(zm, ze);
-	/* QNAN is handled separately below */
-	}
-
-	switch (CLPAIR(xc, yc)) {
-	case CLPAIR(IEEE754_CLASS_QNAN, 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):
-		return ieee754dp_nanxcpt(x);
-
-	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN):
-	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN):
-	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_QNAN):
-	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_QNAN):
-		return y;
-
-	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN):
-	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_ZERO):
-	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_NORM):
-	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_DNORM):
-	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_INF):
-		return x;
-
-
-	/*
-	 * Infinity handling
-	 */
-	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_ZERO):
-	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_INF):
-		if (zc == IEEE754_CLASS_QNAN)
-			return z;
-		ieee754_setcx(IEEE754_INVALID_OPERATION);
-		return ieee754dp_indef();
-
-	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_INF):
-	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_INF):
-	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_NORM):
-	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_DNORM):
-	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF):
-		if (zc == IEEE754_CLASS_QNAN)
-			return z;
-		return ieee754dp_inf(xs ^ ys);
-
-	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO):
-	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_NORM):
-	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_DNORM):
-	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_ZERO):
-	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_ZERO):
-		if (zc == IEEE754_CLASS_INF)
-			return ieee754dp_inf(zs);
-		/* Multiplication is 0 so just return z */
-		return z;
-
-	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM):
-		DPDNORMX;
-
-	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_DNORM):
-		if (zc == IEEE754_CLASS_QNAN)
-			return z;
-		else if (zc == IEEE754_CLASS_INF)
-			return ieee754dp_inf(zs);
-		DPDNORMY;
-		break;
-
-	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_NORM):
-		if (zc == IEEE754_CLASS_QNAN)
-			return z;
-		else if (zc == IEEE754_CLASS_INF)
-			return ieee754dp_inf(zs);
-		DPDNORMX;
-		break;
-
-	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_NORM):
-		if (zc == IEEE754_CLASS_QNAN)
-			return z;
-		else if (zc == IEEE754_CLASS_INF)
-			return ieee754dp_inf(zs);
-		/* fall through to real computations */
-	}
-
-	/* Finally get to do some computation */
-
-	/*
-	 * Do the multiplication bit first
-	 *
-	 * rm = xm * ym, re = xe + ye basically
-	 *
-	 * At this point xm and ym should have been normalized.
-	 */
-	assert(xm & DP_HIDDEN_BIT);
-	assert(ym & DP_HIDDEN_BIT);
-
-	re = xe + ye;
-	rs = xs ^ ys;
-
-	/* shunt to top of word */
-	xm <<= 64 - (DP_FBITS + 1);
-	ym <<= 64 - (DP_FBITS + 1);
-
-	/*
-	 * Multiply 32 bits xm, ym to give high 32 bits rm with stickness.
-	 */
-
-	/* 32 * 32 => 64 */
-#define DPXMULT(x, y)	((u64)(x) * (u64)y)
-
-	lxm = xm;
-	hxm = xm >> 32;
-	lym = ym;
-	hym = ym >> 32;
-
-	lrm = DPXMULT(lxm, lym);
-	hrm = DPXMULT(hxm, hym);
-
-	t = DPXMULT(lxm, hym);
-
-	at = lrm + (t << 32);
-	hrm += at < lrm;
-	lrm = at;
-
-	hrm = hrm + (t >> 32);
-
-	t = DPXMULT(hxm, lym);
-
-	at = lrm + (t << 32);
-	hrm += at < lrm;
-	lrm = at;
-
-	hrm = hrm + (t >> 32);
-
-	rm = hrm | (lrm != 0);
-
-	/*
-	 * Sticky shift down to normal rounding precision.
-	 */
-	if ((s64) rm < 0) {
-		rm = (rm >> (64 - (DP_FBITS + 1 + 3))) |
-		     ((rm << (DP_FBITS + 1 + 3)) != 0);
-			re++;
-	} else {
-		rm = (rm >> (64 - (DP_FBITS + 1 + 3 + 1))) |
-		     ((rm << (DP_FBITS + 1 + 3 + 1)) != 0);
-	}
-	assert(rm & (DP_HIDDEN_BIT << 3));
-
-	/* And now the subtraction */
-
-	/* flip sign of r and handle as add */
-	rs ^= 1;
-
-	assert(zm & DP_HIDDEN_BIT);
-
-	/*
-	 * Provide guard,round and stick bit space.
-	 */
-	zm <<= 3;
-
-	if (ze > re) {
-		/*
-		 * Have to shift y fraction right to align.
-		 */
-		s = ze - re;
-		rm = XDPSRS(rm, s);
-		re += s;
-	} else if (re > ze) {
-		/*
-		 * Have to shift x fraction right to align.
-		 */
-		s = re - ze;
-		zm = XDPSRS(zm, s);
-		ze += s;
-	}
-	assert(ze == re);
-	assert(ze <= DP_EMAX);
-
-	if (zs == rs) {
-		/*
-		 * Generate 28 bit result of adding two 27 bit numbers
-		 * leaving result in xm, xs and xe.
-		 */
-		zm = zm + rm;
-
-		if (zm >> (DP_FBITS + 1 + 3)) { /* carry out */
-			zm = XDPSRS1(zm);
-			ze++;
-		}
-	} else {
-		if (zm >= rm) {
-			zm = zm - rm;
-		} else {
-			zm = rm - zm;
-			zs = rs;
-		}
-		if (zm == 0)
-			return ieee754dp_zero(ieee754_csr.rm == FPU_CSR_RD);
-
-		/*
-		 * Normalize to rounding precision.
-		 */
-		while ((zm >> (DP_FBITS + 3)) == 0) {
-			zm <<= 1;
-			ze--;
-		}
-	}
-
-	return ieee754dp_format(zs, ze, zm);
-}
diff --git a/arch/mips/math-emu/dp_mul.c b/arch/mips/math-emu/dp_mul.c
index d0901f03fa19..87d0b44b0614 100644
--- a/arch/mips/math-emu/dp_mul.c
+++ b/arch/mips/math-emu/dp_mul.c
@@ -125,7 +125,7 @@ union ieee754dp ieee754dp_mul(union ieee754dp x, union ieee754dp y)
 	ym <<= 64 - (DP_FBITS + 1);
 
 	/*
-	 * Multiply 32 bits xm, ym to give high 32 bits rm with stickness.
+	 * Multiply 64 bits xm, ym to give high 64 bits rm with stickness.
 	 */
 
 	/* 32 * 32 => 64 */
@@ -163,7 +163,7 @@ union ieee754dp ieee754dp_mul(union ieee754dp x, union ieee754dp y)
 	if ((s64) rm < 0) {
 		rm = (rm >> (64 - (DP_FBITS + 1 + 3))) |
 		     ((rm << (DP_FBITS + 1 + 3)) != 0);
-			re++;
+		re++;
 	} else {
 		rm = (rm >> (64 - (DP_FBITS + 1 + 3 + 1))) |
 		     ((rm << (DP_FBITS + 1 + 3 + 1)) != 0);
diff --git a/arch/mips/math-emu/dsemul.c b/arch/mips/math-emu/dsemul.c
index 46b964d2b79c..d4ceacd4fa12 100644
--- a/arch/mips/math-emu/dsemul.c
+++ b/arch/mips/math-emu/dsemul.c
@@ -60,7 +60,7 @@ int mips_dsemul(struct pt_regs *regs, mips_instruction ir, unsigned long cpc)
 			unsigned int rs;
 			s32 v;
 
-			rs = (((insn.mm_a_format.rs + 0x1e) & 0xf) + 2);
+			rs = (((insn.mm_a_format.rs + 0xe) & 0xf) + 2);
 			v = regs->cp0_epc & ~3;
 			v += insn.mm_a_format.simmediate << 2;
 			regs->regs[rs] = (long)v;
diff --git a/arch/mips/math-emu/ieee754dp.c b/arch/mips/math-emu/ieee754dp.c
index 47d26c805eac..465a0342ed4c 100644
--- a/arch/mips/math-emu/ieee754dp.c
+++ b/arch/mips/math-emu/ieee754dp.c
@@ -54,10 +54,13 @@ union ieee754dp __cold ieee754dp_nanxcpt(union ieee754dp r)
 	assert(ieee754dp_issnan(r));
 
 	ieee754_setcx(IEEE754_INVALID_OPERATION);
-	if (ieee754_csr.nan2008)
+	if (ieee754_csr.nan2008) {
 		DPMANT(r) |= DP_MBIT(DP_FBITS - 1);
-	else
-		r = ieee754dp_indef();
+	} else {
+		DPMANT(r) &= ~DP_MBIT(DP_FBITS - 1);
+		if (!ieee754dp_isnan(r))
+			DPMANT(r) |= DP_MBIT(DP_FBITS - 2);
+	}
 
 	return r;
 }
diff --git a/arch/mips/math-emu/ieee754dp.h b/arch/mips/math-emu/ieee754dp.h
index e2babd98fee3..9ba023004eb6 100644
--- a/arch/mips/math-emu/ieee754dp.h
+++ b/arch/mips/math-emu/ieee754dp.h
@@ -60,6 +60,7 @@ static inline int ieee754dp_finite(union ieee754dp x)
 	while ((m >> DP_FBITS) == 0) { m <<= 1; e--; }
 #define DPDNORMX	DPDNORMx(xm, xe)
 #define DPDNORMY	DPDNORMx(ym, ye)
+#define DPDNORMZ	DPDNORMx(zm, ze)
 
 static inline union ieee754dp builddp(int s, int bx, u64 m)
 {
diff --git a/arch/mips/math-emu/ieee754int.h b/arch/mips/math-emu/ieee754int.h
index ed7bb277b3e0..8bc2f6963324 100644
--- a/arch/mips/math-emu/ieee754int.h
+++ b/arch/mips/math-emu/ieee754int.h
@@ -55,6 +55,9 @@ static inline int ieee754_class_nan(int xc)
 #define COMPYSP \
 	unsigned ym; int ye; int ys; int yc
 
+#define COMPZSP \
+	unsigned zm; int ze; int zs; int zc
+
 #define EXPLODESP(v, vc, vs, ve, vm)					\
 {									\
 	vs = SPSIGN(v);							\
@@ -81,6 +84,7 @@ static inline int ieee754_class_nan(int xc)
 }
 #define EXPLODEXSP EXPLODESP(x, xc, xs, xe, xm)
 #define EXPLODEYSP EXPLODESP(y, yc, ys, ye, ym)
+#define EXPLODEZSP EXPLODESP(z, zc, zs, ze, zm)
 
 
 #define COMPXDP \
@@ -89,6 +93,9 @@ static inline int ieee754_class_nan(int xc)
 #define COMPYDP \
 	u64 ym; int ye; int ys; int yc
 
+#define COMPZDP \
+	u64 zm; int ze; int zs; int zc
+
 #define EXPLODEDP(v, vc, vs, ve, vm)					\
 {									\
 	vm = DPMANT(v);							\
@@ -115,6 +122,7 @@ static inline int ieee754_class_nan(int xc)
 }
 #define EXPLODEXDP EXPLODEDP(x, xc, xs, xe, xm)
 #define EXPLODEYDP EXPLODEDP(y, yc, ys, ye, ym)
+#define EXPLODEZDP EXPLODEDP(z, zc, zs, ze, zm)
 
 #define FLUSHDP(v, vc, vs, ve, vm)					\
 	if (vc==IEEE754_CLASS_DNORM) {					\
@@ -140,7 +148,9 @@ static inline int ieee754_class_nan(int xc)
 
 #define FLUSHXDP FLUSHDP(x, xc, xs, xe, xm)
 #define FLUSHYDP FLUSHDP(y, yc, ys, ye, ym)
+#define FLUSHZDP FLUSHDP(z, zc, zs, ze, zm)
 #define FLUSHXSP FLUSHSP(x, xc, xs, xe, xm)
 #define FLUSHYSP FLUSHSP(y, yc, ys, ye, ym)
+#define FLUSHZSP FLUSHSP(z, zc, zs, ze, zm)
 
 #endif /* __IEEE754INT_H  */
diff --git a/arch/mips/math-emu/ieee754sp.c b/arch/mips/math-emu/ieee754sp.c
index e0b2c450b963..260e68965907 100644
--- a/arch/mips/math-emu/ieee754sp.c
+++ b/arch/mips/math-emu/ieee754sp.c
@@ -54,10 +54,13 @@ union ieee754sp __cold ieee754sp_nanxcpt(union ieee754sp r)
 	assert(ieee754sp_issnan(r));
 
 	ieee754_setcx(IEEE754_INVALID_OPERATION);
-	if (ieee754_csr.nan2008)
+	if (ieee754_csr.nan2008) {
 		SPMANT(r) |= SP_MBIT(SP_FBITS - 1);
-	else
-		r = ieee754sp_indef();
+	} else {
+		SPMANT(r) &= ~SP_MBIT(SP_FBITS - 1);
+		if (!ieee754sp_isnan(r))
+			SPMANT(r) |= SP_MBIT(SP_FBITS - 2);
+	}
 
 	return r;
 }
@@ -138,7 +141,8 @@ union ieee754sp ieee754sp_format(int sn, int xe, unsigned xm)
 		} else {
 			/* sticky right shift es bits
 			 */
-			SPXSRSXn(es);
+			xm = XSPSRS(xm, es);
+			xe += es;
 			assert((xm & (SP_HIDDEN_BIT << 3)) == 0);
 			assert(xe == SP_EMIN);
 		}
diff --git a/arch/mips/math-emu/ieee754sp.h b/arch/mips/math-emu/ieee754sp.h
index 374a3f00a589..8476067075fe 100644
--- a/arch/mips/math-emu/ieee754sp.h
+++ b/arch/mips/math-emu/ieee754sp.h
@@ -46,25 +46,24 @@ static inline int ieee754sp_finite(union ieee754sp x)
 }
 
 /* 3bit extended single precision sticky right shift */
-#define SPXSRSXn(rs)							\
-	(xe += rs,							\
-	 xm = (rs > (SP_FBITS+3))?1:((xm) >> (rs)) | ((xm) << (32-(rs)) != 0))
+#define XSPSRS(v, rs)						\
+	((rs > (SP_FBITS+3))?1:((v) >> (rs)) | ((v) << (32-(rs)) != 0))
 
-#define SPXSRSX1() \
-	(xe++, (xm = (xm >> 1) | (xm & 1)))
+#define XSPSRS1(m) \
+	((m >> 1) | (m & 1))
 
-#define SPXSRSYn(rs)								\
-	(ye+=rs,								\
-	 ym = (rs > (SP_FBITS+3))?1:((ym) >> (rs)) | ((ym) << (32-(rs)) != 0))
+#define SPXSRSX1() \
+	(xe++, (xm = XSPSRS1(xm)))
 
 #define SPXSRSY1() \
-	(ye++, (ym = (ym >> 1) | (ym & 1)))
+	(ye++, (ym = XSPSRS1(ym)))
 
 /* convert denormal to normalized with extended exponent */
 #define SPDNORMx(m,e) \
 	while ((m >> SP_FBITS) == 0) { m <<= 1; e--; }
 #define SPDNORMX	SPDNORMx(xm, xe)
 #define SPDNORMY	SPDNORMx(ym, ye)
+#define SPDNORMZ	SPDNORMx(zm, ze)
 
 static inline union ieee754sp buildsp(int s, int bx, unsigned m)
 {
diff --git a/arch/mips/math-emu/sp_add.c b/arch/mips/math-emu/sp_add.c
index f1c87b07d3b4..c55c0c00bca8 100644
--- a/arch/mips/math-emu/sp_add.c
+++ b/arch/mips/math-emu/sp_add.c
@@ -132,13 +132,15 @@ union ieee754sp ieee754sp_add(union ieee754sp x, union ieee754sp y)
 		 * Have to shift y fraction right to align.
 		 */
 		s = xe - ye;
-		SPXSRSYn(s);
+		ym = XSPSRS(ym, s);
+		ye += s;
 	} else if (ye > xe) {
 		/*
 		 * Have to shift x fraction right to align.
 		 */
 		s = ye - xe;
-		SPXSRSXn(s);
+		xm = XSPSRS(xm, s);
+		xe += s;
 	}
 	assert(xe == ye);
 	assert(xe <= SP_EMAX);
diff --git a/arch/mips/math-emu/sp_maddf.c b/arch/mips/math-emu/sp_maddf.c
index dd1dd83e34eb..a8cd8b4f235e 100644
--- a/arch/mips/math-emu/sp_maddf.c
+++ b/arch/mips/math-emu/sp_maddf.c
@@ -14,8 +14,12 @@
 
 #include "ieee754sp.h"
 
-union ieee754sp ieee754sp_maddf(union ieee754sp z, union ieee754sp x,
-				union ieee754sp y)
+enum maddf_flags {
+	maddf_negate_product	= 1 << 0,
+};
+
+static union ieee754sp _sp_maddf(union ieee754sp z, union ieee754sp x,
+				 union ieee754sp y, enum maddf_flags flags)
 {
 	int re;
 	int rs;
@@ -32,15 +36,15 @@ union ieee754sp ieee754sp_maddf(union ieee754sp z, union ieee754sp x,
 
 	COMPXSP;
 	COMPYSP;
-	u32 zm; int ze; int zs __maybe_unused; int zc;
+	COMPZSP;
 
 	EXPLODEXSP;
 	EXPLODEYSP;
-	EXPLODESP(z, zc, zs, ze, zm)
+	EXPLODEZSP;
 
 	FLUSHXSP;
 	FLUSHYSP;
-	FLUSHSP(z, zc, zs, ze, zm);
+	FLUSHZSP;
 
 	ieee754_clearcx();
 
@@ -49,7 +53,7 @@ union ieee754sp ieee754sp_maddf(union ieee754sp z, union ieee754sp x,
 		ieee754_setcx(IEEE754_INVALID_OPERATION);
 		return ieee754sp_nanxcpt(z);
 	case IEEE754_CLASS_DNORM:
-		SPDNORMx(zm, ze);
+		SPDNORMZ;
 	/* QNAN is handled separately below */
 	}
 
@@ -154,6 +158,8 @@ union ieee754sp ieee754sp_maddf(union ieee754sp z, union ieee754sp x,
 
 	re = xe + ye;
 	rs = xs ^ ys;
+	if (flags & maddf_negate_product)
+		rs ^= 1;
 
 	/* shunt to top of word */
 	xm <<= 32 - (SP_FBITS + 1);
@@ -208,16 +214,18 @@ union ieee754sp ieee754sp_maddf(union ieee754sp z, union ieee754sp x,
 
 	if (ze > re) {
 		/*
-		 * Have to shift y fraction right to align.
+		 * Have to shift r fraction right to align.
 		 */
 		s = ze - re;
-		SPXSRSYn(s);
+		rm = XSPSRS(rm, s);
+		re += s;
 	} else if (re > ze) {
 		/*
-		 * Have to shift x fraction right to align.
+		 * Have to shift z fraction right to align.
 		 */
 		s = re - ze;
-		SPXSRSYn(s);
+		zm = XSPSRS(zm, s);
+		ze += s;
 	}
 	assert(ze == re);
 	assert(ze <= SP_EMAX);
@@ -230,7 +238,8 @@ union ieee754sp ieee754sp_maddf(union ieee754sp z, union ieee754sp x,
 		zm = zm + rm;
 
 		if (zm >> (SP_FBITS + 1 + 3)) { /* carry out */
-			SPXSRSX1();
+			zm = XSPSRS1(zm);
+			ze++;
 		}
 	} else {
 		if (zm >= rm) {
@@ -253,3 +262,15 @@ union ieee754sp ieee754sp_maddf(union ieee754sp z, union ieee754sp x,
 	}
 	return ieee754sp_format(zs, ze, zm);
 }
+
+union ieee754sp ieee754sp_maddf(union ieee754sp z, union ieee754sp x,
+				union ieee754sp y)
+{
+	return _sp_maddf(z, x, y, 0);
+}
+
+union ieee754sp ieee754sp_msubf(union ieee754sp z, union ieee754sp x,
+				union ieee754sp y)
+{
+	return _sp_maddf(z, x, y, maddf_negate_product);
+}
diff --git a/arch/mips/math-emu/sp_msubf.c b/arch/mips/math-emu/sp_msubf.c
deleted file mode 100644
index 81c38b980d69..000000000000
--- a/arch/mips/math-emu/sp_msubf.c
+++ /dev/null
@@ -1,258 +0,0 @@
-/*
- * IEEE754 floating point arithmetic
- * single precision: MSUB.f (Fused Multiply Subtract)
- * MSUBF.fmt: FPR[fd] = FPR[fd] - (FPR[fs] x FPR[ft])
- *
- * MIPS floating point support
- * Copyright (C) 2015 Imagination Technologies, Ltd.
- * Author: Markos Chandras <markos.chandras@imgtec.com>
- *
- *  This program is free software; you can distribute it and/or modify it
- *  under the terms of the GNU General Public License as published by the
- *  Free Software Foundation; version 2 of the License.
- */
-
-#include "ieee754sp.h"
-
-union ieee754sp ieee754sp_msubf(union ieee754sp z, union ieee754sp x,
-				union ieee754sp y)
-{
-	int re;
-	int rs;
-	unsigned rm;
-	unsigned short lxm;
-	unsigned short hxm;
-	unsigned short lym;
-	unsigned short hym;
-	unsigned lrm;
-	unsigned hrm;
-	unsigned t;
-	unsigned at;
-	int s;
-
-	COMPXSP;
-	COMPYSP;
-	u32 zm; int ze; int zs __maybe_unused; int zc;
-
-	EXPLODEXSP;
-	EXPLODEYSP;
-	EXPLODESP(z, zc, zs, ze, zm)
-
-	FLUSHXSP;
-	FLUSHYSP;
-	FLUSHSP(z, zc, zs, ze, zm);
-
-	ieee754_clearcx();
-
-	switch (zc) {
-	case IEEE754_CLASS_SNAN:
-		ieee754_setcx(IEEE754_INVALID_OPERATION);
-		return ieee754sp_nanxcpt(z);
-	case IEEE754_CLASS_DNORM:
-		SPDNORMx(zm, ze);
-	/* QNAN is handled separately below */
-	}
-
-	switch (CLPAIR(xc, yc)) {
-	case CLPAIR(IEEE754_CLASS_QNAN, 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):
-		return ieee754sp_nanxcpt(x);
-
-	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN):
-	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN):
-	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_QNAN):
-	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_QNAN):
-		return y;
-
-	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN):
-	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_ZERO):
-	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_NORM):
-	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_DNORM):
-	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_INF):
-		return x;
-
-	/*
-	 * Infinity handling
-	 */
-	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_ZERO):
-	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_INF):
-		if (zc == IEEE754_CLASS_QNAN)
-			return z;
-		ieee754_setcx(IEEE754_INVALID_OPERATION);
-		return ieee754sp_indef();
-
-	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_INF):
-	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_INF):
-	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_NORM):
-	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_DNORM):
-	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF):
-		if (zc == IEEE754_CLASS_QNAN)
-			return z;
-		return ieee754sp_inf(xs ^ ys);
-
-	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO):
-	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_NORM):
-	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_DNORM):
-	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_ZERO):
-	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_ZERO):
-		if (zc == IEEE754_CLASS_INF)
-			return ieee754sp_inf(zs);
-		/* Multiplication is 0 so just return z */
-		return z;
-
-	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM):
-		SPDNORMX;
-
-	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_DNORM):
-		if (zc == IEEE754_CLASS_QNAN)
-			return z;
-		else if (zc == IEEE754_CLASS_INF)
-			return ieee754sp_inf(zs);
-		SPDNORMY;
-		break;
-
-	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_NORM):
-		if (zc == IEEE754_CLASS_QNAN)
-			return z;
-		else if (zc == IEEE754_CLASS_INF)
-			return ieee754sp_inf(zs);
-		SPDNORMX;
-		break;
-
-	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_NORM):
-		if (zc == IEEE754_CLASS_QNAN)
-			return z;
-		else if (zc == IEEE754_CLASS_INF)
-			return ieee754sp_inf(zs);
-		/* fall through to real compuation */
-	}
-
-	/* Finally get to do some computation */
-
-	/*
-	 * Do the multiplication bit first
-	 *
-	 * rm = xm * ym, re = xe + ye basically
-	 *
-	 * At this point xm and ym should have been normalized.
-	 */
-
-	/* rm = xm * ym, re = xe+ye basically */
-	assert(xm & SP_HIDDEN_BIT);
-	assert(ym & SP_HIDDEN_BIT);
-
-	re = xe + ye;
-	rs = xs ^ ys;
-
-	/* shunt to top of word */
-	xm <<= 32 - (SP_FBITS + 1);
-	ym <<= 32 - (SP_FBITS + 1);
-
-	/*
-	 * Multiply 32 bits xm, ym to give high 32 bits rm with stickness.
-	 */
-	lxm = xm & 0xffff;
-	hxm = xm >> 16;
-	lym = ym & 0xffff;
-	hym = ym >> 16;
-
-	lrm = lxm * lym;	/* 16 * 16 => 32 */
-	hrm = hxm * hym;	/* 16 * 16 => 32 */
-
-	t = lxm * hym; /* 16 * 16 => 32 */
-	at = lrm + (t << 16);
-	hrm += at < lrm;
-	lrm = at;
-	hrm = hrm + (t >> 16);
-
-	t = hxm * lym; /* 16 * 16 => 32 */
-	at = lrm + (t << 16);
-	hrm += at < lrm;
-	lrm = at;
-	hrm = hrm + (t >> 16);
-
-	rm = hrm | (lrm != 0);
-
-	/*
-	 * Sticky shift down to normal rounding precision.
-	 */
-	if ((int) rm < 0) {
-		rm = (rm >> (32 - (SP_FBITS + 1 + 3))) |
-		    ((rm << (SP_FBITS + 1 + 3)) != 0);
-		re++;
-	} else {
-		rm = (rm >> (32 - (SP_FBITS + 1 + 3 + 1))) |
-		     ((rm << (SP_FBITS + 1 + 3 + 1)) != 0);
-	}
-	assert(rm & (SP_HIDDEN_BIT << 3));
-
-	/* And now the subtraction */
-
-	/* Flip sign of r and handle as add */
-	rs ^= 1;
-
-	assert(zm & SP_HIDDEN_BIT);
-
-	/*
-	 * Provide guard,round and stick bit space.
-	 */
-	zm <<= 3;
-
-	if (ze > re) {
-		/*
-		 * Have to shift y fraction right to align.
-		 */
-		s = ze - re;
-		SPXSRSYn(s);
-	} else if (re > ze) {
-		/*
-		 * Have to shift x fraction right to align.
-		 */
-		s = re - ze;
-		SPXSRSYn(s);
-	}
-	assert(ze == re);
-	assert(ze <= SP_EMAX);
-
-	if (zs == rs) {
-		/*
-		 * Generate 28 bit result of adding two 27 bit numbers
-		 * leaving result in zm, zs and ze.
-		 */
-		zm = zm + rm;
-
-		if (zm >> (SP_FBITS + 1 + 3)) { /* carry out */
-			SPXSRSX1(); /* shift preserving sticky */
-		}
-	} else {
-		if (zm >= rm) {
-			zm = zm - rm;
-		} else {
-			zm = rm - zm;
-			zs = rs;
-		}
-		if (zm == 0)
-			return ieee754sp_zero(ieee754_csr.rm == FPU_CSR_RD);
-
-		/*
-		 * Normalize in extended single precision
-		 */
-		while ((zm >> (SP_MBITS + 3)) == 0) {
-			zm <<= 1;
-			ze--;
-		}
-
-	}
-	return ieee754sp_format(zs, ze, zm);
-}
diff --git a/arch/mips/math-emu/sp_sub.c b/arch/mips/math-emu/sp_sub.c
index ec5f937a8b3e..dc998ed47295 100644
--- a/arch/mips/math-emu/sp_sub.c
+++ b/arch/mips/math-emu/sp_sub.c
@@ -134,13 +134,15 @@ union ieee754sp ieee754sp_sub(union ieee754sp x, union ieee754sp y)
 		 * have to shift y fraction right to align
 		 */
 		s = xe - ye;
-		SPXSRSYn(s);
+		ym = XSPSRS(ym, s);
+		ye += s;
 	} else if (ye > xe) {
 		/*
 		 * have to shift x fraction right to align
 		 */
 		s = ye - xe;
-		SPXSRSXn(s);
+		xm = XSPSRS(xm, s);
+		xe += s;
 	}
 	assert(xe == ye);
 	assert(xe <= SP_EMAX);