/*
 *  linux/arch/arm/vfp/vfpsingle.c
 *
 * This code is derived in part from John R. Housers softfloat library, which
 * carries the following notice:
 *
 * ===========================================================================
 * This C source file is part of the SoftFloat IEC/IEEE Floating-point
 * Arithmetic Package, Release 2.
 *
 * Written by John R. Hauser.  This work was made possible in part by the
 * International Computer Science Institute, located at Suite 600, 1947 Center
 * Street, Berkeley, California 94704.  Funding was partially provided by the
 * National Science Foundation under grant MIP-9311980.  The original version
 * of this code was written as part of a project to build a fixed-point vector
 * processor in collaboration with the University of California at Berkeley,
 * overseen by Profs. Nelson Morgan and John Wawrzynek.  More information
 * is available through the web page `http://HTTP.CS.Berkeley.EDU/~jhauser/
 * arithmetic/softfloat.html'.
 *
 * THIS SOFTWARE IS DISTRIBUTED AS IS, FOR FREE.  Although reasonable effort
 * has been made to avoid it, THIS SOFTWARE MAY CONTAIN FAULTS THAT WILL AT
 * TIMES RESULT IN INCORRECT BEHAVIOR.  USE OF THIS SOFTWARE IS RESTRICTED TO
 * PERSONS AND ORGANIZATIONS WHO CAN AND WILL TAKE FULL RESPONSIBILITY FOR ANY
 * AND ALL LOSSES, COSTS, OR OTHER PROBLEMS ARISING FROM ITS USE.
 *
 * Derivative works are acceptable, even for commercial purposes, so long as
 * (1) they include prominent notice that the work is derivative, and (2) they
 * include prominent notice akin to these three paragraphs for those parts of
 * this code that are retained.
 * ===========================================================================
 */
#include <linux/kernel.h>
#include <linux/bitops.h>

#include <asm/div64.h>
#include <asm/vfp.h>

#include "vfpinstr.h"
#include "vfp.h"

static struct vfp_single vfp_single_default_qnan = {
	.exponent	= 255,
	.sign		= 0,
	.significand	= VFP_SINGLE_SIGNIFICAND_QNAN,
};

static void vfp_single_dump(const char *str, struct vfp_single *s)
{
	pr_debug("VFP: %s: sign=%d exponent=%d significand=%08x\n",
		 str, s->sign != 0, s->exponent, s->significand);
}

static void vfp_single_normalise_denormal(struct vfp_single *vs)
{
	int bits = 31 - fls(vs->significand);

	vfp_single_dump("normalise_denormal: in", vs);

	if (bits) {
		vs->exponent -= bits - 1;
		vs->significand <<= bits;
	}

	vfp_single_dump("normalise_denormal: out", vs);
}

#ifndef DEBUG
#define vfp_single_normaliseround(sd,vsd,fpscr,except,func) __vfp_single_normaliseround(sd,vsd,fpscr,except)
u32 __vfp_single_normaliseround(int sd, struct vfp_single *vs, u32 fpscr, u32 exceptions)
#else
u32 vfp_single_normaliseround(int sd, struct vfp_single *vs, u32 fpscr, u32 exceptions, const char *func)
#endif
{
	u32 significand, incr, rmode;
	int exponent, shift, underflow;

	vfp_single_dump("pack: in", vs);

	/*
	 * Infinities and NaNs are a special case.
	 */
	if (vs->exponent == 255 && (vs->significand == 0 || exceptions))
		goto pack;

	/*
	 * Special-case zero.
	 */
	if (vs->significand == 0) {
		vs->exponent = 0;
		goto pack;
	}

	exponent = vs->exponent;
	significand = vs->significand;

	/*
	 * Normalise first.  Note that we shift the significand up to
	 * bit 31, so we have VFP_SINGLE_LOW_BITS + 1 below the least
	 * significant bit.
	 */
	shift = 32 - fls(significand);
	if (shift < 32 && shift) {
		exponent -= shift;
		significand <<= shift;
	}

#ifdef DEBUG
	vs->exponent = exponent;
	vs->significand = significand;
	vfp_single_dump("pack: normalised", vs);
#endif

	/*
	 * Tiny number?
	 */
	underflow = exponent < 0;
	if (underflow) {
		significand = vfp_shiftright32jamming(significand, -exponent);
		exponent = 0;
#ifdef DEBUG
		vs->exponent = exponent;
		vs->significand = significand;
		vfp_single_dump("pack: tiny number", vs);
#endif
		if (!(significand & ((1 << (VFP_SINGLE_LOW_BITS + 1)) - 1)))
			underflow = 0;
	}

	/*
	 * Select rounding increment.
	 */
	incr = 0;
	rmode = fpscr & FPSCR_RMODE_MASK;

	if (rmode == FPSCR_ROUND_NEAREST) {
		incr = 1 << VFP_SINGLE_LOW_BITS;
		if ((significand & (1 << (VFP_SINGLE_LOW_BITS + 1))) == 0)
			incr -= 1;
	} else if (rmode == FPSCR_ROUND_TOZERO) {
		incr = 0;
	} else if ((rmode == FPSCR_ROUND_PLUSINF) ^ (vs->sign != 0))
		incr = (1 << (VFP_SINGLE_LOW_BITS + 1)) - 1;

	pr_debug("VFP: rounding increment = 0x%08x\n", incr);

	/*
	 * Is our rounding going to overflow?
	 */
	if ((significand + incr) < significand) {
		exponent += 1;
		significand = (significand >> 1) | (significand & 1);
		incr >>= 1;
#ifdef DEBUG
		vs->exponent = exponent;
		vs->significand = significand;
		vfp_single_dump("pack: overflow", vs);
#endif
	}

	/*
	 * If any of the low bits (which will be shifted out of the
	 * number) are non-zero, the result is inexact.
	 */
	if (significand & ((1 << (VFP_SINGLE_LOW_BITS + 1)) - 1))
		exceptions |= FPSCR_IXC;

	/*
	 * Do our rounding.
	 */
	significand += incr;

	/*
	 * Infinity?
	 */
	if (exponent >= 254) {
		exceptions |= FPSCR_OFC | FPSCR_IXC;
		if (incr == 0) {
			vs->exponent = 253;
			vs->significand = 0x7fffffff;
		} else {
			vs->exponent = 255;		/* infinity */
			vs->significand = 0;
		}
	} else {
		if (significand >> (VFP_SINGLE_LOW_BITS + 1) == 0)
			exponent = 0;
		if (exponent || significand > 0x80000000)
			underflow = 0;
		if (underflow)
			exceptions |= FPSCR_UFC;
		vs->exponent = exponent;
		vs->significand = significand >> 1;
	}

 pack:
	vfp_single_dump("pack: final", vs);
	{
		s32 d = vfp_single_pack(vs);
#ifdef DEBUG
		pr_debug("VFP: %s: d(s%d)=%08x exceptions=%08x\n", func,
			 sd, d, exceptions);
#endif
		vfp_put_float(d, sd);
	}

	return exceptions;
}

/*
 * Propagate the NaN, setting exceptions if it is signalling.
 * 'n' is always a NaN.  'm' may be a number, NaN or infinity.
 */
static u32
vfp_propagate_nan(struct vfp_single *vsd, struct vfp_single *vsn,
		  struct vfp_single *vsm, u32 fpscr)
{
	struct vfp_single *nan;
	int tn, tm = 0;

	tn = vfp_single_type(vsn);

	if (vsm)
		tm = vfp_single_type(vsm);

	if (fpscr & FPSCR_DEFAULT_NAN)
		/*
		 * Default NaN mode - always returns a quiet NaN
		 */
		nan = &vfp_single_default_qnan;
	else {
		/*
		 * Contemporary mode - select the first signalling
		 * NAN, or if neither are signalling, the first
		 * quiet NAN.
		 */
		if (tn == VFP_SNAN || (tm != VFP_SNAN && tn == VFP_QNAN))
			nan = vsn;
		else
			nan = vsm;
		/*
		 * Make the NaN quiet.
		 */
		nan->significand |= VFP_SINGLE_SIGNIFICAND_QNAN;
	}

	*vsd = *nan;

	/*
	 * If one was a signalling NAN, raise invalid operation.
	 */
	return tn == VFP_SNAN || tm == VFP_SNAN ? FPSCR_IOC : VFP_NAN_FLAG;
}


/*
 * Extended operations
 */
static u32 vfp_single_fabs(int sd, int unused, s32 m, u32 fpscr)
{
	vfp_put_float(vfp_single_packed_abs(m), sd);
	return 0;
}

static u32 vfp_single_fcpy(int sd, int unused, s32 m, u32 fpscr)
{
	vfp_put_float(m, sd);
	return 0;
}

static u32 vfp_single_fneg(int sd, int unused, s32 m, u32 fpscr)
{
	vfp_put_float(vfp_single_packed_negate(m), sd);
	return 0;
}

static const u16 sqrt_oddadjust[] = {
	0x0004, 0x0022, 0x005d, 0x00b1, 0x011d, 0x019f, 0x0236, 0x02e0,
	0x039c, 0x0468, 0x0545, 0x0631, 0x072b, 0x0832, 0x0946, 0x0a67
};

static const u16 sqrt_evenadjust[] = {
	0x0a2d, 0x08af, 0x075a, 0x0629, 0x051a, 0x0429, 0x0356, 0x029e,
	0x0200, 0x0179, 0x0109, 0x00af, 0x0068, 0x0034, 0x0012, 0x0002
};

u32 vfp_estimate_sqrt_significand(u32 exponent, u32 significand)
{
	int index;
	u32 z, a;

	if ((significand & 0xc0000000) != 0x40000000) {
		printk(KERN_WARNING "VFP: estimate_sqrt: invalid significand\n");
	}

	a = significand << 1;
	index = (a >> 27) & 15;
	if (exponent & 1) {
		z = 0x4000 + (a >> 17) - sqrt_oddadjust[index];
		z = ((a / z) << 14) + (z << 15);
		a >>= 1;
	} else {
		z = 0x8000 + (a >> 17) - sqrt_evenadjust[index];
		z = a / z + z;
		z = (z >= 0x20000) ? 0xffff8000 : (z << 15);
		if (z <= a)
			return (s32)a >> 1;
	}
	{
		u64 v = (u64)a << 31;
		do_div(v, z);
		return v + (z >> 1);
	}
}

static u32 vfp_single_fsqrt(int sd, int unused, s32 m, u32 fpscr)
{
	struct vfp_single vsm, vsd;
	int ret, tm;

	vfp_single_unpack(&vsm, m);
	tm = vfp_single_type(&vsm);
	if (tm & (VFP_NAN|VFP_INFINITY)) {
		struct vfp_single *vsp = &vsd;

		if (tm & VFP_NAN)
			ret = vfp_propagate_nan(vsp, &vsm, NULL, fpscr);
		else if (vsm.sign == 0) {
 sqrt_copy:
			vsp = &vsm;
			ret = 0;
		} else {
 sqrt_invalid:
			vsp = &vfp_single_default_qnan;
			ret = FPSCR_IOC;
		}
		vfp_put_float(vfp_single_pack(vsp), sd);
		return ret;
	}

	/*
	 * sqrt(+/- 0) == +/- 0
	 */
	if (tm & VFP_ZERO)
		goto sqrt_copy;

	/*
	 * Normalise a denormalised number
	 */
	if (tm & VFP_DENORMAL)
		vfp_single_normalise_denormal(&vsm);

	/*
	 * sqrt(<0) = invalid
	 */
	if (vsm.sign)
		goto sqrt_invalid;

	vfp_single_dump("sqrt", &vsm);

	/*
	 * Estimate the square root.
	 */
	vsd.sign = 0;
	vsd.exponent = ((vsm.exponent - 127) >> 1) + 127;
	vsd.significand = vfp_estimate_sqrt_significand(vsm.exponent, vsm.significand) + 2;

	vfp_single_dump("sqrt estimate", &vsd);

	/*
	 * And now adjust.
	 */
	if ((vsd.significand & VFP_SINGLE_LOW_BITS_MASK) <= 5) {
		if (vsd.significand < 2) {
			vsd.significand = 0xffffffff;
		} else {
			u64 term;
			s64 rem;
			vsm.significand <<= !(vsm.exponent & 1);
			term = (u64)vsd.significand * vsd.significand;
			rem = ((u64)vsm.significand << 32) - term;

			pr_debug("VFP: term=%016llx rem=%016llx\n", term, rem);

			while (rem < 0) {
				vsd.significand -= 1;
				rem += ((u64)vsd.significand << 1) | 1;
			}
			vsd.significand |= rem != 0;
		}
	}
	vsd.significand = vfp_shiftright32jamming(vsd.significand, 1);

	return vfp_single_normaliseround(sd, &vsd, fpscr, 0, "fsqrt");
}

/*
 * Equal	:= ZC
 * Less than	:= N
 * Greater than	:= C
 * Unordered	:= CV
 */
static u32 vfp_compare(int sd, int signal_on_qnan, s32 m, u32 fpscr)
{
	s32 d;
	u32 ret = 0;

	d = vfp_get_float(sd);
	if (vfp_single_packed_exponent(m) == 255 && vfp_single_packed_mantissa(m)) {
		ret |= FPSCR_C | FPSCR_V;
		if (signal_on_qnan || !(vfp_single_packed_mantissa(m) & (1 << (VFP_SINGLE_MANTISSA_BITS - 1))))
			/*
			 * Signalling NaN, or signalling on quiet NaN
			 */
			ret |= FPSCR_IOC;
	}

	if (vfp_single_packed_exponent(d) == 255 && vfp_single_packed_mantissa(d)) {
		ret |= FPSCR_C | FPSCR_V;
		if (signal_on_qnan || !(vfp_single_packed_mantissa(d) & (1 << (VFP_SINGLE_MANTISSA_BITS - 1))))
			/*
			 * Signalling NaN, or signalling on quiet NaN
			 */
			ret |= FPSCR_IOC;
	}

	if (ret == 0) {
		if (d == m || vfp_single_packed_abs(d | m) == 0) {
			/*
			 * equal
			 */
			ret |= FPSCR_Z | FPSCR_C;
		} else if (vfp_single_packed_sign(d ^ m)) {
			/*
			 * different signs
			 */
			if (vfp_single_packed_sign(d))
				/*
				 * d is negative, so d < m
				 */
				ret |= FPSCR_N;
			else
				/*
				 * d is positive, so d > m
				 */
				ret |= FPSCR_C;
		} else if ((vfp_single_packed_sign(d) != 0) ^ (d < m)) {
			/*
			 * d < m
			 */
			ret |= FPSCR_N;
		} else if ((vfp_single_packed_sign(d) != 0) ^ (d > m)) {
			/*
			 * d > m
			 */
			ret |= FPSCR_C;
		}
	}
	return ret;
}

static u32 vfp_single_fcmp(int sd, int unused, s32 m, u32 fpscr)
{
	return vfp_compare(sd, 0, m, fpscr);
}

static u32 vfp_single_fcmpe(int sd, int unused, s32 m, u32 fpscr)
{
	return vfp_compare(sd, 1, m, fpscr);
}

static u32 vfp_single_fcmpz(int sd, int unused, s32 m, u32 fpscr)
{
	return vfp_compare(sd, 0, 0, fpscr);
}

static u32 vfp_single_fcmpez(int sd, int unused, s32 m, u32 fpscr)
{
	return vfp_compare(sd, 1, 0, fpscr);
}

static u32 vfp_single_fcvtd(int dd, int unused, s32 m, u32 fpscr)
{
	struct vfp_single vsm;
	struct vfp_double vdd;
	int tm;
	u32 exceptions = 0;

	vfp_single_unpack(&vsm, m);

	tm = vfp_single_type(&vsm);

	/*
	 * If we have a signalling NaN, signal invalid operation.
	 */
	if (tm == VFP_SNAN)
		exceptions = FPSCR_IOC;

	if (tm & VFP_DENORMAL)
		vfp_single_normalise_denormal(&vsm);

	vdd.sign = vsm.sign;
	vdd.significand = (u64)vsm.significand << 32;

	/*
	 * If we have an infinity or NaN, the exponent must be 2047.
	 */
	if (tm & (VFP_INFINITY|VFP_NAN)) {
		vdd.exponent = 2047;
		if (tm == VFP_QNAN)
			vdd.significand |= VFP_DOUBLE_SIGNIFICAND_QNAN;
		goto pack_nan;
	} else if (tm & VFP_ZERO)
		vdd.exponent = 0;
	else
		vdd.exponent = vsm.exponent + (1023 - 127);

	return vfp_double_normaliseround(dd, &vdd, fpscr, exceptions, "fcvtd");

 pack_nan:
	vfp_put_double(vfp_double_pack(&vdd), dd);
	return exceptions;
}