aboutsummaryrefslogtreecommitdiff
path: root/arch/powerpc/math-emu
diff options
context:
space:
mode:
Diffstat (limited to 'arch/powerpc/math-emu')
-rw-r--r--arch/powerpc/math-emu/Makefile23
-rw-r--r--arch/powerpc/math-emu/fre.c11
-rw-r--r--arch/powerpc/math-emu/frsqrtes.c11
-rw-r--r--arch/powerpc/math-emu/math.c99
-rw-r--r--arch/powerpc/math-emu/math_efp.c459
-rw-r--r--arch/powerpc/math-emu/mtfsf.c58
6 files changed, 427 insertions, 234 deletions
diff --git a/arch/powerpc/math-emu/Makefile b/arch/powerpc/math-emu/Makefile
index 7d1dba0d57f..1b46ab4f641 100644
--- a/arch/powerpc/math-emu/Makefile
+++ b/arch/powerpc/math-emu/Makefile
@@ -1,14 +1,15 @@
-
-obj-$(CONFIG_MATH_EMULATION) += fabs.o fadd.o fadds.o fcmpo.o fcmpu.o \
- fctiw.o fctiwz.o fdiv.o fdivs.o \
- fmadd.o fmadds.o fmsub.o fmsubs.o \
- fmul.o fmuls.o fnabs.o fneg.o \
- fnmadd.o fnmadds.o fnmsub.o fnmsubs.o \
- fres.o frsp.o frsqrte.o fsel.o lfs.o \
- fsqrt.o fsqrts.o fsub.o fsubs.o \
- mcrfs.o mffs.o mtfsb0.o mtfsb1.o \
- mtfsf.o mtfsfi.o stfiwx.o stfs.o \
- math.o fmr.o lfd.o stfd.o
+math-emu-common-objs = math.o fre.o fsqrt.o fsqrts.o frsqrtes.o mtfsf.o mtfsfi.o
+obj-$(CONFIG_MATH_EMULATION_HW_UNIMPLEMENTED) += $(math-emu-common-objs)
+obj-$(CONFIG_MATH_EMULATION_FULL) += $(math-emu-common-objs) fabs.o fadd.o \
+ fadds.o fcmpo.o fcmpu.o fctiw.o \
+ fctiwz.o fdiv.o fdivs.o fmadd.o \
+ fmadds.o fmsub.o fmsubs.o fmul.o \
+ fmuls.o fnabs.o fneg.o fnmadd.o \
+ fnmadds.o fnmsub.o fnmsubs.o fres.o \
+ frsp.o fsel.o lfs.o frsqrte.o fsub.o \
+ fsubs.o mcrfs.o mffs.o mtfsb0.o \
+ mtfsb1.o stfiwx.o stfs.o math.o \
+ fmr.o lfd.o stfd.o
obj-$(CONFIG_SPE) += math_efp.o
diff --git a/arch/powerpc/math-emu/fre.c b/arch/powerpc/math-emu/fre.c
new file mode 100644
index 00000000000..49ccf2cc6a5
--- /dev/null
+++ b/arch/powerpc/math-emu/fre.c
@@ -0,0 +1,11 @@
+#include <linux/types.h>
+#include <linux/errno.h>
+#include <asm/uaccess.h>
+
+int fre(void *frD, void *frB)
+{
+#ifdef DEBUG
+ printk("%s: %p %p\n", __func__, frD, frB);
+#endif
+ return -ENOSYS;
+}
diff --git a/arch/powerpc/math-emu/frsqrtes.c b/arch/powerpc/math-emu/frsqrtes.c
new file mode 100644
index 00000000000..7e838e38031
--- /dev/null
+++ b/arch/powerpc/math-emu/frsqrtes.c
@@ -0,0 +1,11 @@
+#include <linux/types.h>
+#include <linux/errno.h>
+#include <asm/uaccess.h>
+
+int frsqrtes(void *frD, void *frB)
+{
+#ifdef DEBUG
+ printk("%s: %p %p\n", __func__, frD, frB);
+#endif
+ return 0;
+}
diff --git a/arch/powerpc/math-emu/math.c b/arch/powerpc/math-emu/math.c
index 164d55935bd..ab151f04050 100644
--- a/arch/powerpc/math-emu/math.c
+++ b/arch/powerpc/math-emu/math.c
@@ -7,12 +7,27 @@
#include <asm/uaccess.h>
#include <asm/reg.h>
+#include <asm/switch_to.h>
#include <asm/sfp-machine.h>
#include <math-emu/double.h>
#define FLOATFUNC(x) extern int x(void *, void *, void *, void *)
+/* The instructions list which may be not implemented by a hardware FPU */
+FLOATFUNC(fre);
+FLOATFUNC(frsqrtes);
+FLOATFUNC(fsqrt);
+FLOATFUNC(fsqrts);
+FLOATFUNC(mtfsf);
+FLOATFUNC(mtfsfi);
+
+#ifdef CONFIG_MATH_EMULATION_HW_UNIMPLEMENTED
+#undef FLOATFUNC(x)
+#define FLOATFUNC(x) static inline int x(void *op1, void *op2, void *op3, \
+ void *op4) { }
+#endif
+
FLOATFUNC(fadd);
FLOATFUNC(fadds);
FLOATFUNC(fdiv);
@@ -42,8 +57,6 @@ FLOATFUNC(mcrfs);
FLOATFUNC(mffs);
FLOATFUNC(mtfsb0);
FLOATFUNC(mtfsb1);
-FLOATFUNC(mtfsf);
-FLOATFUNC(mtfsfi);
FLOATFUNC(lfd);
FLOATFUNC(lfs);
@@ -61,8 +74,6 @@ FLOATFUNC(fneg);
FLOATFUNC(fres);
FLOATFUNC(frsqrte);
FLOATFUNC(fsel);
-FLOATFUNC(fsqrt);
-FLOATFUNC(fsqrts);
#define OP31 0x1f /* 31 */
@@ -97,6 +108,7 @@ FLOATFUNC(fsqrts);
#define FSQRTS 0x016 /* 22 */
#define FRES 0x018 /* 24 */
#define FMULS 0x019 /* 25 */
+#define FRSQRTES 0x01a /* 26 */
#define FMSUBS 0x01c /* 28 */
#define FMADDS 0x01d /* 29 */
#define FNMSUBS 0x01e /* 30 */
@@ -109,6 +121,7 @@ FLOATFUNC(fsqrts);
#define FADD 0x015 /* 21 */
#define FSQRT 0x016 /* 22 */
#define FSEL 0x017 /* 23 */
+#define FRE 0x018 /* 24 */
#define FMUL 0x019 /* 25 */
#define FRSQRTE 0x01a /* 26 */
#define FMSUB 0x01c /* 28 */
@@ -150,7 +163,6 @@ FLOATFUNC(fsqrts);
#define XEU 15
#define XFLB 10
-#ifdef CONFIG_MATH_EMULATION
static int
record_exception(struct pt_regs *regs, int eflag)
{
@@ -208,7 +220,6 @@ record_exception(struct pt_regs *regs, int eflag)
return (fpscr & FPSCR_FEX) ? 1 : 0;
}
-#endif /* CONFIG_MATH_EMULATION */
int
do_mathemu(struct pt_regs *regs)
@@ -218,56 +229,13 @@ do_mathemu(struct pt_regs *regs)
signed short sdisp;
u32 insn = 0;
int idx = 0;
-#ifdef CONFIG_MATH_EMULATION
int (*func)(void *, void *, void *, void *);
int type = 0;
int eflag, trap;
-#endif
if (get_user(insn, (u32 *)pc))
return -EFAULT;
-#ifndef CONFIG_MATH_EMULATION
- switch (insn >> 26) {
- case LFD:
- idx = (insn >> 16) & 0x1f;
- sdisp = (insn & 0xffff);
- op0 = (void *)&current->thread.TS_FPR((insn >> 21) & 0x1f);
- op1 = (void *)((idx ? regs->gpr[idx] : 0) + sdisp);
- lfd(op0, op1, op2, op3);
- break;
- case LFDU:
- idx = (insn >> 16) & 0x1f;
- sdisp = (insn & 0xffff);
- op0 = (void *)&current->thread.TS_FPR((insn >> 21) & 0x1f);
- op1 = (void *)((idx ? regs->gpr[idx] : 0) + sdisp);
- lfd(op0, op1, op2, op3);
- regs->gpr[idx] = (unsigned long)op1;
- break;
- case STFD:
- idx = (insn >> 16) & 0x1f;
- sdisp = (insn & 0xffff);
- op0 = (void *)&current->thread.TS_FPR((insn >> 21) & 0x1f);
- op1 = (void *)((idx ? regs->gpr[idx] : 0) + sdisp);
- stfd(op0, op1, op2, op3);
- break;
- case STFDU:
- idx = (insn >> 16) & 0x1f;
- sdisp = (insn & 0xffff);
- op0 = (void *)&current->thread.TS_FPR((insn >> 21) & 0x1f);
- op1 = (void *)((idx ? regs->gpr[idx] : 0) + sdisp);
- stfd(op0, op1, op2, op3);
- regs->gpr[idx] = (unsigned long)op1;
- break;
- case OP63:
- op0 = (void *)&current->thread.TS_FPR((insn >> 21) & 0x1f);
- op1 = (void *)&current->thread.TS_FPR((insn >> 11) & 0x1f);
- fmr(op0, op1, op2, op3);
- break;
- default:
- goto illegal;
- }
-#else /* CONFIG_MATH_EMULATION */
switch (insn >> 26) {
case LFS: func = lfs; type = D; break;
case LFSU: func = lfs; type = DU; break;
@@ -299,9 +267,10 @@ do_mathemu(struct pt_regs *regs)
case FDIVS: func = fdivs; type = AB; break;
case FSUBS: func = fsubs; type = AB; break;
case FADDS: func = fadds; type = AB; break;
- case FSQRTS: func = fsqrts; type = AB; break;
- case FRES: func = fres; type = AB; break;
+ case FSQRTS: func = fsqrts; type = XB; break;
+ case FRES: func = fres; type = XB; break;
case FMULS: func = fmuls; type = AC; break;
+ case FRSQRTES: func = frsqrtes;type = XB; break;
case FMSUBS: func = fmsubs; type = ABC; break;
case FMADDS: func = fmadds; type = ABC; break;
case FNMSUBS: func = fnmsubs; type = ABC; break;
@@ -317,10 +286,11 @@ do_mathemu(struct pt_regs *regs)
case FDIV: func = fdiv; type = AB; break;
case FSUB: func = fsub; type = AB; break;
case FADD: func = fadd; type = AB; break;
- case FSQRT: func = fsqrt; type = AB; break;
+ case FSQRT: func = fsqrt; type = XB; break;
+ case FRE: func = fre; type = XB; break;
case FSEL: func = fsel; type = ABC; break;
case FMUL: func = fmul; type = AC; break;
- case FRSQRTE: func = frsqrte; type = AB; break;
+ case FRSQRTE: func = frsqrte; type = XB; break;
case FMSUB: func = fmsub; type = ABC; break;
case FMADD: func = fmadd; type = ABC; break;
case FNMSUB: func = fnmsub; type = ABC; break;
@@ -410,21 +380,16 @@ do_mathemu(struct pt_regs *regs)
case XE:
idx = (insn >> 16) & 0x1f;
op0 = (void *)&current->thread.TS_FPR((insn >> 21) & 0x1f);
- if (!idx) {
- if (((insn >> 1) & 0x3ff) == STFIWX)
- op1 = (void *)(regs->gpr[(insn >> 11) & 0x1f]);
- else
- goto illegal;
- } else {
- op1 = (void *)(regs->gpr[idx] + regs->gpr[(insn >> 11) & 0x1f]);
- }
-
+ op1 = (void *)((idx ? regs->gpr[idx] : 0)
+ + regs->gpr[(insn >> 11) & 0x1f]);
break;
case XEU:
idx = (insn >> 16) & 0x1f;
+ if (!idx)
+ goto illegal;
op0 = (void *)&current->thread.TS_FPR((insn >> 21) & 0x1f);
- op1 = (void *)((idx ? regs->gpr[idx] : 0)
+ op1 = (void *)(regs->gpr[idx]
+ regs->gpr[(insn >> 11) & 0x1f]);
break;
@@ -459,6 +424,13 @@ do_mathemu(struct pt_regs *regs)
goto illegal;
}
+ /*
+ * If we support a HW FPU, we need to ensure the FP state
+ * is flushed into the thread_struct before attempting
+ * emulation
+ */
+ flush_fp_to_thread(current);
+
eflag = func(op0, op1, op2, op3);
if (insn & 1) {
@@ -479,7 +451,6 @@ do_mathemu(struct pt_regs *regs)
default:
break;
}
-#endif /* CONFIG_MATH_EMULATION */
regs->nip += 4;
return 0;
diff --git a/arch/powerpc/math-emu/math_efp.c b/arch/powerpc/math-emu/math_efp.c
index 41f4ef30e48..28337c9709a 100644
--- a/arch/powerpc/math-emu/math_efp.c
+++ b/arch/powerpc/math-emu/math_efp.c
@@ -1,7 +1,7 @@
/*
* arch/powerpc/math-emu/math_efp.c
*
- * Copyright (C) 2006-2008 Freescale Semiconductor, Inc. All rights reserved.
+ * Copyright (C) 2006-2008, 2010 Freescale Semiconductor, Inc.
*
* Author: Ebony Zhu, <ebony.zhu@freescale.com>
* Yu Liu, <yu.liu@freescale.com>
@@ -20,6 +20,7 @@
*/
#include <linux/types.h>
+#include <linux/prctl.h>
#include <asm/uaccess.h>
#include <asm/reg.h>
@@ -104,6 +105,8 @@
#define FP_EX_MASK (FP_EX_INEXACT | FP_EX_INVALID | FP_EX_DIVZERO | \
FP_EX_UNDERFLOW | FP_EX_OVERFLOW)
+static int have_e500_cpu_a005_erratum;
+
union dw_union {
u64 dp[1];
u32 wp[2];
@@ -169,10 +172,6 @@ static unsigned long insn_type(unsigned long speinsn)
case EFDNABS: ret = XA; break;
case EFDNEG: ret = XA; break;
case EFDSUB: ret = AB; break;
-
- default:
- printk(KERN_ERR "\nOoops! SPE instruction no type found.");
- printk(KERN_ERR "\ninst code: %08lx\n", speinsn);
}
return ret;
@@ -193,7 +192,7 @@ int do_spe_mathemu(struct pt_regs *regs)
type = insn_type(speinsn);
if (type == NOTYPE)
- return -ENOSYS;
+ goto illegal;
func = speinsn & 0x7ff;
fc = (speinsn >> 21) & 0x1f;
@@ -210,12 +209,10 @@ int do_spe_mathemu(struct pt_regs *regs)
__FPU_FPSCR = mfspr(SPRN_SPEFSCR);
-#ifdef DEBUG
- printk("speinsn:%08lx spefscr:%08lx\n", speinsn, __FPU_FPSCR);
- printk("vc: %08x %08x\n", vc.wp[0], vc.wp[1]);
- printk("va: %08x %08x\n", va.wp[0], va.wp[1]);
- printk("vb: %08x %08x\n", vb.wp[0], vb.wp[1]);
-#endif
+ pr_debug("speinsn:%08lx spefscr:%08lx\n", speinsn, __FPU_FPSCR);
+ pr_debug("vc: %08x %08x\n", vc.wp[0], vc.wp[1]);
+ pr_debug("va: %08x %08x\n", va.wp[0], va.wp[1]);
+ pr_debug("vb: %08x %08x\n", vb.wp[0], vb.wp[1]);
switch (src) {
case SPFP: {
@@ -233,10 +230,8 @@ int do_spe_mathemu(struct pt_regs *regs)
break;
}
-#ifdef DEBUG
- printk("SA: %ld %08lx %ld (%ld)\n", SA_s, SA_f, SA_e, SA_c);
- printk("SB: %ld %08lx %ld (%ld)\n", SB_s, SB_f, SB_e, SB_c);
-#endif
+ pr_debug("SA: %ld %08lx %ld (%ld)\n", SA_s, SA_f, SA_e, SA_c);
+ pr_debug("SB: %ld %08lx %ld (%ld)\n", SB_s, SB_f, SB_e, SB_c);
switch (func) {
case EFSABS:
@@ -281,21 +276,13 @@ int do_spe_mathemu(struct pt_regs *regs)
case EFSCTSF:
case EFSCTUF:
- if (!((vb.wp[1] >> 23) == 0xff && ((vb.wp[1] & 0x7fffff) > 0))) {
- /* NaN */
- if (((vb.wp[1] >> 23) & 0xff) == 0) {
- /* denorm */
- vc.wp[1] = 0x0;
- } else if ((vb.wp[1] >> 31) == 0) {
- /* positive normal */
- vc.wp[1] = (func == EFSCTSF) ?
- 0x7fffffff : 0xffffffff;
- } else { /* negative normal */
- vc.wp[1] = (func == EFSCTSF) ?
- 0x80000000 : 0x0;
- }
- } else { /* rB is NaN */
- vc.wp[1] = 0x0;
+ if (SB_c == FP_CLS_NAN) {
+ vc.wp[1] = 0;
+ FP_SET_EXCEPTION(FP_EX_INVALID);
+ } else {
+ SB_e += (func == EFSCTSF ? 31 : 32);
+ FP_TO_INT_ROUND_S(vc.wp[1], SB, 32,
+ (func == EFSCTSF));
}
goto update_regs;
@@ -303,24 +290,34 @@ int do_spe_mathemu(struct pt_regs *regs)
FP_DECL_D(DB);
FP_CLEAR_EXCEPTIONS;
FP_UNPACK_DP(DB, vb.dp);
-#ifdef DEBUG
- printk("DB: %ld %08lx %08lx %ld (%ld)\n",
+
+ pr_debug("DB: %ld %08lx %08lx %ld (%ld)\n",
DB_s, DB_f1, DB_f0, DB_e, DB_c);
-#endif
+
FP_CONV(S, D, 1, 2, SR, DB);
goto pack_s;
}
case EFSCTSI:
- case EFSCTSIZ:
case EFSCTUI:
+ if (SB_c == FP_CLS_NAN) {
+ vc.wp[1] = 0;
+ FP_SET_EXCEPTION(FP_EX_INVALID);
+ } else {
+ FP_TO_INT_ROUND_S(vc.wp[1], SB, 32,
+ ((func & 0x3) != 0));
+ }
+ goto update_regs;
+
+ case EFSCTSIZ:
case EFSCTUIZ:
- if (func & 0x4) {
- _FP_ROUND(1, SB);
+ if (SB_c == FP_CLS_NAN) {
+ vc.wp[1] = 0;
+ FP_SET_EXCEPTION(FP_EX_INVALID);
} else {
- _FP_ROUND_ZERO(1, SB);
+ FP_TO_INT_S(vc.wp[1], SB, 32,
+ ((func & 0x3) != 0));
}
- FP_TO_INT_S(vc.wp[1], SB, 32, ((func & 0x3) != 0));
goto update_regs;
default:
@@ -329,9 +326,8 @@ int do_spe_mathemu(struct pt_regs *regs)
break;
pack_s:
-#ifdef DEBUG
- printk("SR: %ld %08lx %ld (%ld)\n", SR_s, SR_f, SR_e, SR_c);
-#endif
+ pr_debug("SR: %ld %08lx %ld (%ld)\n", SR_s, SR_f, SR_e, SR_c);
+
FP_PACK_SP(vc.wp + 1, SR);
goto update_regs;
@@ -362,12 +358,10 @@ cmp_s:
break;
}
-#ifdef DEBUG
- printk("DA: %ld %08lx %08lx %ld (%ld)\n",
+ pr_debug("DA: %ld %08lx %08lx %ld (%ld)\n",
DA_s, DA_f1, DA_f0, DA_e, DA_c);
- printk("DB: %ld %08lx %08lx %ld (%ld)\n",
+ pr_debug("DB: %ld %08lx %08lx %ld (%ld)\n",
DB_s, DB_f1, DB_f0, DB_e, DB_c);
-#endif
switch (func) {
case EFDABS:
@@ -412,22 +406,13 @@ cmp_s:
case EFDCTSF:
case EFDCTUF:
- if (!((vb.wp[0] >> 20) == 0x7ff &&
- ((vb.wp[0] & 0xfffff) > 0 || (vb.wp[1] > 0)))) {
- /* not a NaN */
- if (((vb.wp[0] >> 20) & 0x7ff) == 0) {
- /* denorm */
- vc.wp[1] = 0x0;
- } else if ((vb.wp[0] >> 31) == 0) {
- /* positive normal */
- vc.wp[1] = (func == EFDCTSF) ?
- 0x7fffffff : 0xffffffff;
- } else { /* negative normal */
- vc.wp[1] = (func == EFDCTSF) ?
- 0x80000000 : 0x0;
- }
- } else { /* NaN */
- vc.wp[1] = 0x0;
+ if (DB_c == FP_CLS_NAN) {
+ vc.wp[1] = 0;
+ FP_SET_EXCEPTION(FP_EX_INVALID);
+ } else {
+ DB_e += (func == EFDCTSF ? 31 : 32);
+ FP_TO_INT_ROUND_D(vc.wp[1], DB, 32,
+ (func == EFDCTSF));
}
goto update_regs;
@@ -435,30 +420,45 @@ cmp_s:
FP_DECL_S(SB);
FP_CLEAR_EXCEPTIONS;
FP_UNPACK_SP(SB, vb.wp + 1);
-#ifdef DEBUG
- printk("SB: %ld %08lx %ld (%ld)\n",
+
+ pr_debug("SB: %ld %08lx %ld (%ld)\n",
SB_s, SB_f, SB_e, SB_c);
-#endif
+
FP_CONV(D, S, 2, 1, DR, SB);
goto pack_d;
}
case EFDCTUIDZ:
case EFDCTSIDZ:
- _FP_ROUND_ZERO(2, DB);
- FP_TO_INT_D(vc.dp[0], DB, 64, ((func & 0x1) == 0));
+ if (DB_c == FP_CLS_NAN) {
+ vc.dp[0] = 0;
+ FP_SET_EXCEPTION(FP_EX_INVALID);
+ } else {
+ FP_TO_INT_D(vc.dp[0], DB, 64,
+ ((func & 0x1) == 0));
+ }
goto update_regs;
case EFDCTUI:
case EFDCTSI:
+ if (DB_c == FP_CLS_NAN) {
+ vc.wp[1] = 0;
+ FP_SET_EXCEPTION(FP_EX_INVALID);
+ } else {
+ FP_TO_INT_ROUND_D(vc.wp[1], DB, 32,
+ ((func & 0x3) != 0));
+ }
+ goto update_regs;
+
case EFDCTUIZ:
case EFDCTSIZ:
- if (func & 0x4) {
- _FP_ROUND(2, DB);
+ if (DB_c == FP_CLS_NAN) {
+ vc.wp[1] = 0;
+ FP_SET_EXCEPTION(FP_EX_INVALID);
} else {
- _FP_ROUND_ZERO(2, DB);
+ FP_TO_INT_D(vc.wp[1], DB, 32,
+ ((func & 0x3) != 0));
}
- FP_TO_INT_D(vc.wp[1], DB, 32, ((func & 0x3) != 0));
goto update_regs;
default:
@@ -467,10 +467,9 @@ cmp_s:
break;
pack_d:
-#ifdef DEBUG
- printk("DR: %ld %08lx %08lx %ld (%ld)\n",
+ pr_debug("DR: %ld %08lx %08lx %ld (%ld)\n",
DR_s, DR_f1, DR_f0, DR_e, DR_c);
-#endif
+
FP_PACK_DP(vc.dp, DR);
goto update_regs;
@@ -507,12 +506,14 @@ cmp_d:
break;
}
-#ifdef DEBUG
- printk("SA0: %ld %08lx %ld (%ld)\n", SA0_s, SA0_f, SA0_e, SA0_c);
- printk("SA1: %ld %08lx %ld (%ld)\n", SA1_s, SA1_f, SA1_e, SA1_c);
- printk("SB0: %ld %08lx %ld (%ld)\n", SB0_s, SB0_f, SB0_e, SB0_c);
- printk("SB1: %ld %08lx %ld (%ld)\n", SB1_s, SB1_f, SB1_e, SB1_c);
-#endif
+ pr_debug("SA0: %ld %08lx %ld (%ld)\n",
+ SA0_s, SA0_f, SA0_e, SA0_c);
+ pr_debug("SA1: %ld %08lx %ld (%ld)\n",
+ SA1_s, SA1_f, SA1_e, SA1_c);
+ pr_debug("SB0: %ld %08lx %ld (%ld)\n",
+ SB0_s, SB0_f, SB0_e, SB0_c);
+ pr_debug("SB1: %ld %08lx %ld (%ld)\n",
+ SB1_s, SB1_f, SB1_e, SB1_c);
switch (func) {
case EVFSABS:
@@ -562,35 +563,60 @@ cmp_d:
cmp = -1;
goto cmp_vs;
- case EVFSCTSF:
- __asm__ __volatile__ ("mtspr 512, %4\n"
- "efsctsf %0, %2\n"
- "efsctsf %1, %3\n"
- : "=r" (vc.wp[0]), "=r" (vc.wp[1])
- : "r" (vb.wp[0]), "r" (vb.wp[1]), "r" (0));
- goto update_regs;
-
case EVFSCTUF:
- __asm__ __volatile__ ("mtspr 512, %4\n"
- "efsctuf %0, %2\n"
- "efsctuf %1, %3\n"
- : "=r" (vc.wp[0]), "=r" (vc.wp[1])
- : "r" (vb.wp[0]), "r" (vb.wp[1]), "r" (0));
+ case EVFSCTSF:
+ if (SB0_c == FP_CLS_NAN) {
+ vc.wp[0] = 0;
+ FP_SET_EXCEPTION(FP_EX_INVALID);
+ } else {
+ SB0_e += (func == EVFSCTSF ? 31 : 32);
+ FP_TO_INT_ROUND_S(vc.wp[0], SB0, 32,
+ (func == EVFSCTSF));
+ }
+ if (SB1_c == FP_CLS_NAN) {
+ vc.wp[1] = 0;
+ FP_SET_EXCEPTION(FP_EX_INVALID);
+ } else {
+ SB1_e += (func == EVFSCTSF ? 31 : 32);
+ FP_TO_INT_ROUND_S(vc.wp[1], SB1, 32,
+ (func == EVFSCTSF));
+ }
goto update_regs;
case EVFSCTUI:
case EVFSCTSI:
+ if (SB0_c == FP_CLS_NAN) {
+ vc.wp[0] = 0;
+ FP_SET_EXCEPTION(FP_EX_INVALID);
+ } else {
+ FP_TO_INT_ROUND_S(vc.wp[0], SB0, 32,
+ ((func & 0x3) != 0));
+ }
+ if (SB1_c == FP_CLS_NAN) {
+ vc.wp[1] = 0;
+ FP_SET_EXCEPTION(FP_EX_INVALID);
+ } else {
+ FP_TO_INT_ROUND_S(vc.wp[1], SB1, 32,
+ ((func & 0x3) != 0));
+ }
+ goto update_regs;
+
case EVFSCTUIZ:
case EVFSCTSIZ:
- if (func & 0x4) {
- _FP_ROUND(1, SB0);
- _FP_ROUND(1, SB1);
+ if (SB0_c == FP_CLS_NAN) {
+ vc.wp[0] = 0;
+ FP_SET_EXCEPTION(FP_EX_INVALID);
+ } else {
+ FP_TO_INT_S(vc.wp[0], SB0, 32,
+ ((func & 0x3) != 0));
+ }
+ if (SB1_c == FP_CLS_NAN) {
+ vc.wp[1] = 0;
+ FP_SET_EXCEPTION(FP_EX_INVALID);
} else {
- _FP_ROUND_ZERO(1, SB0);
- _FP_ROUND_ZERO(1, SB1);
+ FP_TO_INT_S(vc.wp[1], SB1, 32,
+ ((func & 0x3) != 0));
}
- FP_TO_INT_S(vc.wp[0], SB0, 32, ((func & 0x3) != 0));
- FP_TO_INT_S(vc.wp[1], SB1, 32, ((func & 0x3) != 0));
goto update_regs;
default:
@@ -599,10 +625,11 @@ cmp_d:
break;
pack_vs:
-#ifdef DEBUG
- printk("SR0: %ld %08lx %ld (%ld)\n", SR0_s, SR0_f, SR0_e, SR0_c);
- printk("SR1: %ld %08lx %ld (%ld)\n", SR1_s, SR1_f, SR1_e, SR1_c);
-#endif
+ pr_debug("SR0: %ld %08lx %ld (%ld)\n",
+ SR0_s, SR0_f, SR0_e, SR0_c);
+ pr_debug("SR1: %ld %08lx %ld (%ld)\n",
+ SR1_s, SR1_f, SR1_e, SR1_c);
+
FP_PACK_SP(vc.wp, SR0);
FP_PACK_SP(vc.wp + 1, SR1);
goto update_regs;
@@ -633,25 +660,65 @@ update_ccr:
regs->ccr |= (IR << ((7 - ((speinsn >> 23) & 0x7)) << 2));
update_regs:
- __FPU_FPSCR &= ~FP_EX_MASK;
+ /*
+ * If the "invalid" exception sticky bit was set by the
+ * processor for non-finite input, but was not set before the
+ * instruction being emulated, clear it. Likewise for the
+ * "underflow" bit, which may have been set by the processor
+ * for exact underflow, not just inexact underflow when the
+ * flag should be set for IEEE 754 semantics. Other sticky
+ * exceptions will only be set by the processor when they are
+ * correct according to IEEE 754 semantics, and we must not
+ * clear sticky bits that were already set before the emulated
+ * instruction as they represent the user-visible sticky
+ * exception status. "inexact" traps to kernel are not
+ * required for IEEE semantics and are not enabled by default,
+ * so the "inexact" sticky bit may have been set by a previous
+ * instruction without the kernel being aware of it.
+ */
+ __FPU_FPSCR
+ &= ~(FP_EX_INVALID | FP_EX_UNDERFLOW) | current->thread.spefscr_last;
__FPU_FPSCR |= (FP_CUR_EXCEPTIONS & FP_EX_MASK);
mtspr(SPRN_SPEFSCR, __FPU_FPSCR);
+ current->thread.spefscr_last = __FPU_FPSCR;
current->thread.evr[fc] = vc.wp[0];
regs->gpr[fc] = vc.wp[1];
-#ifdef DEBUG
- printk("ccr = %08lx\n", regs->ccr);
- printk("cur exceptions = %08x spefscr = %08lx\n",
+ pr_debug("ccr = %08lx\n", regs->ccr);
+ pr_debug("cur exceptions = %08x spefscr = %08lx\n",
FP_CUR_EXCEPTIONS, __FPU_FPSCR);
- printk("vc: %08x %08x\n", vc.wp[0], vc.wp[1]);
- printk("va: %08x %08x\n", va.wp[0], va.wp[1]);
- printk("vb: %08x %08x\n", vb.wp[0], vb.wp[1]);
-#endif
-
+ pr_debug("vc: %08x %08x\n", vc.wp[0], vc.wp[1]);
+ pr_debug("va: %08x %08x\n", va.wp[0], va.wp[1]);
+ pr_debug("vb: %08x %08x\n", vb.wp[0], vb.wp[1]);
+
+ if (current->thread.fpexc_mode & PR_FP_EXC_SW_ENABLE) {
+ if ((FP_CUR_EXCEPTIONS & FP_EX_DIVZERO)
+ && (current->thread.fpexc_mode & PR_FP_EXC_DIV))
+ return 1;
+ if ((FP_CUR_EXCEPTIONS & FP_EX_OVERFLOW)
+ && (current->thread.fpexc_mode & PR_FP_EXC_OVF))
+ return 1;
+ if ((FP_CUR_EXCEPTIONS & FP_EX_UNDERFLOW)
+ && (current->thread.fpexc_mode & PR_FP_EXC_UND))
+ return 1;
+ if ((FP_CUR_EXCEPTIONS & FP_EX_INEXACT)
+ && (current->thread.fpexc_mode & PR_FP_EXC_RES))
+ return 1;
+ if ((FP_CUR_EXCEPTIONS & FP_EX_INVALID)
+ && (current->thread.fpexc_mode & PR_FP_EXC_INV))
+ return 1;
+ }
return 0;
illegal:
+ if (have_e500_cpu_a005_erratum) {
+ /* according to e500 cpu a005 erratum, reissue efp inst */
+ regs->nip -= 4;
+ pr_debug("re-issue efp inst: %08lx\n", speinsn);
+ return 0;
+ }
+
printk(KERN_ERR "\nOoops! IEEE-754 compliance handler encountered un-supported instruction.\ninst code: %08lx\n", speinsn);
return -ENOSYS;
}
@@ -660,25 +727,98 @@ int speround_handler(struct pt_regs *regs)
{
union dw_union fgpr;
int s_lo, s_hi;
- unsigned long speinsn, type, fc;
+ int lo_inexact, hi_inexact;
+ int fp_result;
+ unsigned long speinsn, type, fb, fc, fptype, func;
if (get_user(speinsn, (unsigned int __user *) regs->nip))
return -EFAULT;
if ((speinsn >> 26) != 4)
return -EINVAL; /* not an spe instruction */
- type = insn_type(speinsn & 0x7ff);
+ func = speinsn & 0x7ff;
+ type = insn_type(func);
if (type == XCR) return -ENOSYS;
+ __FPU_FPSCR = mfspr(SPRN_SPEFSCR);
+ pr_debug("speinsn:%08lx spefscr:%08lx\n", speinsn, __FPU_FPSCR);
+
+ fptype = (speinsn >> 5) & 0x7;
+
+ /* No need to round if the result is exact */
+ lo_inexact = __FPU_FPSCR & (SPEFSCR_FG | SPEFSCR_FX);
+ hi_inexact = __FPU_FPSCR & (SPEFSCR_FGH | SPEFSCR_FXH);
+ if (!(lo_inexact || (hi_inexact && fptype == VCT)))
+ return 0;
+
fc = (speinsn >> 21) & 0x1f;
s_lo = regs->gpr[fc] & SIGN_BIT_S;
s_hi = current->thread.evr[fc] & SIGN_BIT_S;
fgpr.wp[0] = current->thread.evr[fc];
fgpr.wp[1] = regs->gpr[fc];
- __FPU_FPSCR = mfspr(SPRN_SPEFSCR);
+ fb = (speinsn >> 11) & 0x1f;
+ switch (func) {
+ case EFSCTUIZ:
+ case EFSCTSIZ:
+ case EVFSCTUIZ:
+ case EVFSCTSIZ:
+ case EFDCTUIDZ:
+ case EFDCTSIDZ:
+ case EFDCTUIZ:
+ case EFDCTSIZ:
+ /*
+ * These instructions always round to zero,
+ * independent of the rounding mode.
+ */
+ return 0;
+
+ case EFSCTUI:
+ case EFSCTUF:
+ case EVFSCTUI:
+ case EVFSCTUF:
+ case EFDCTUI:
+ case EFDCTUF:
+ fp_result = 0;
+ s_lo = 0;
+ s_hi = 0;
+ break;
+
+ case EFSCTSI:
+ case EFSCTSF:
+ fp_result = 0;
+ /* Recover the sign of a zero result if possible. */
+ if (fgpr.wp[1] == 0)
+ s_lo = regs->gpr[fb] & SIGN_BIT_S;
+ break;
+
+ case EVFSCTSI:
+ case EVFSCTSF:
+ fp_result = 0;
+ /* Recover the sign of a zero result if possible. */
+ if (fgpr.wp[1] == 0)
+ s_lo = regs->gpr[fb] & SIGN_BIT_S;
+ if (fgpr.wp[0] == 0)
+ s_hi = current->thread.evr[fb] & SIGN_BIT_S;
+ break;
+
+ case EFDCTSI:
+ case EFDCTSF:
+ fp_result = 0;
+ s_hi = s_lo;
+ /* Recover the sign of a zero result if possible. */
+ if (fgpr.wp[1] == 0)
+ s_hi = current->thread.evr[fb] & SIGN_BIT_S;
+ break;
- switch ((speinsn >> 5) & 0x7) {
+ default:
+ fp_result = 1;
+ break;
+ }
+
+ pr_debug("round fgpr: %08x %08x\n", fgpr.wp[0], fgpr.wp[1]);
+
+ switch (fptype) {
/* Since SPE instructions on E500 core can handle round to nearest
* and round toward zero with IEEE-754 complied, we just need
* to handle round toward +Inf and round toward -Inf by software.
@@ -687,25 +827,52 @@ int speround_handler(struct pt_regs *regs)
if ((FP_ROUNDMODE) == FP_RND_PINF) {
if (!s_lo) fgpr.wp[1]++; /* Z > 0, choose Z1 */
} else { /* round to -Inf */
- if (s_lo) fgpr.wp[1]++; /* Z < 0, choose Z2 */
+ if (s_lo) {
+ if (fp_result)
+ fgpr.wp[1]++; /* Z < 0, choose Z2 */
+ else
+ fgpr.wp[1]--; /* Z < 0, choose Z2 */
+ }
}
break;
case DPFP:
if (FP_ROUNDMODE == FP_RND_PINF) {
- if (!s_hi) fgpr.dp[0]++; /* Z > 0, choose Z1 */
+ if (!s_hi) {
+ if (fp_result)
+ fgpr.dp[0]++; /* Z > 0, choose Z1 */
+ else
+ fgpr.wp[1]++; /* Z > 0, choose Z1 */
+ }
} else { /* round to -Inf */
- if (s_hi) fgpr.dp[0]++; /* Z < 0, choose Z2 */
+ if (s_hi) {
+ if (fp_result)
+ fgpr.dp[0]++; /* Z < 0, choose Z2 */
+ else
+ fgpr.wp[1]--; /* Z < 0, choose Z2 */
+ }
}
break;
case VCT:
if (FP_ROUNDMODE == FP_RND_PINF) {
- if (!s_lo) fgpr.wp[1]++; /* Z_low > 0, choose Z1 */
- if (!s_hi) fgpr.wp[0]++; /* Z_high word > 0, choose Z1 */
+ if (lo_inexact && !s_lo)
+ fgpr.wp[1]++; /* Z_low > 0, choose Z1 */
+ if (hi_inexact && !s_hi)
+ fgpr.wp[0]++; /* Z_high word > 0, choose Z1 */
} else { /* round to -Inf */
- if (s_lo) fgpr.wp[1]++; /* Z_low < 0, choose Z2 */
- if (s_hi) fgpr.wp[0]++; /* Z_high < 0, choose Z2 */
+ if (lo_inexact && s_lo) {
+ if (fp_result)
+ fgpr.wp[1]++; /* Z_low < 0, choose Z2 */
+ else
+ fgpr.wp[1]--; /* Z_low < 0, choose Z2 */
+ }
+ if (hi_inexact && s_hi) {
+ if (fp_result)
+ fgpr.wp[0]++; /* Z_high < 0, choose Z2 */
+ else
+ fgpr.wp[0]--; /* Z_high < 0, choose Z2 */
+ }
}
break;
@@ -716,5 +883,49 @@ int speround_handler(struct pt_regs *regs)
current->thread.evr[fc] = fgpr.wp[0];
regs->gpr[fc] = fgpr.wp[1];
+ pr_debug(" to fgpr: %08x %08x\n", fgpr.wp[0], fgpr.wp[1]);
+
+ if (current->thread.fpexc_mode & PR_FP_EXC_SW_ENABLE)
+ return (current->thread.fpexc_mode & PR_FP_EXC_RES) ? 1 : 0;
+ return 0;
+}
+
+int __init spe_mathemu_init(void)
+{
+ u32 pvr, maj, min;
+
+ pvr = mfspr(SPRN_PVR);
+
+ if ((PVR_VER(pvr) == PVR_VER_E500V1) ||
+ (PVR_VER(pvr) == PVR_VER_E500V2)) {
+ maj = PVR_MAJ(pvr);
+ min = PVR_MIN(pvr);
+
+ /*
+ * E500 revision below 1.1, 2.3, 3.1, 4.1, 5.1
+ * need cpu a005 errata workaround
+ */
+ switch (maj) {
+ case 1:
+ if (min < 1)
+ have_e500_cpu_a005_erratum = 1;
+ break;
+ case 2:
+ if (min < 3)
+ have_e500_cpu_a005_erratum = 1;
+ break;
+ case 3:
+ case 4:
+ case 5:
+ if (min < 1)
+ have_e500_cpu_a005_erratum = 1;
+ break;
+ default:
+ break;
+ }
+ }
+
return 0;
}
+
+module_init(spe_mathemu_init);
diff --git a/arch/powerpc/math-emu/mtfsf.c b/arch/powerpc/math-emu/mtfsf.c
index dbce92e4f04..44b0fc8214f 100644
--- a/arch/powerpc/math-emu/mtfsf.c
+++ b/arch/powerpc/math-emu/mtfsf.c
@@ -11,48 +11,36 @@ mtfsf(unsigned int FM, u32 *frB)
u32 mask;
u32 fpscr;
- if (FM == 0)
- return 0;
-
- if (FM == 0xff)
- mask = 0x9fffffff;
+ if (likely(FM == 1))
+ mask = 0x0f;
+ else if (likely(FM == 0xff))
+ mask = ~0;
else {
- mask = 0;
- if (FM & (1 << 0))
- mask |= 0x90000000;
- if (FM & (1 << 1))
- mask |= 0x0f000000;
- if (FM & (1 << 2))
- mask |= 0x00f00000;
- if (FM & (1 << 3))
- mask |= 0x000f0000;
- if (FM & (1 << 4))
- mask |= 0x0000f000;
- if (FM & (1 << 5))
- mask |= 0x00000f00;
- if (FM & (1 << 6))
- mask |= 0x000000f0;
- if (FM & (1 << 7))
- mask |= 0x0000000f;
+ mask = ((FM & 1) |
+ ((FM << 3) & 0x10) |
+ ((FM << 6) & 0x100) |
+ ((FM << 9) & 0x1000) |
+ ((FM << 12) & 0x10000) |
+ ((FM << 15) & 0x100000) |
+ ((FM << 18) & 0x1000000) |
+ ((FM << 21) & 0x10000000)) * 15;
}
- __FPU_FPSCR &= ~(mask);
- __FPU_FPSCR |= (frB[1] & mask);
+ fpscr = ((__FPU_FPSCR & ~mask) | (frB[1] & mask)) &
+ ~(FPSCR_VX | FPSCR_FEX | 0x800);
- __FPU_FPSCR &= ~(FPSCR_VX);
- if (__FPU_FPSCR & (FPSCR_VXSNAN | FPSCR_VXISI | FPSCR_VXIDI |
+ if (fpscr & (FPSCR_VXSNAN | FPSCR_VXISI | FPSCR_VXIDI |
FPSCR_VXZDZ | FPSCR_VXIMZ | FPSCR_VXVC |
FPSCR_VXSOFT | FPSCR_VXSQRT | FPSCR_VXCVI))
- __FPU_FPSCR |= FPSCR_VX;
-
- fpscr = __FPU_FPSCR;
- fpscr &= ~(FPSCR_FEX);
- if (((fpscr & FPSCR_VX) && (fpscr & FPSCR_VE)) ||
- ((fpscr & FPSCR_OX) && (fpscr & FPSCR_OE)) ||
- ((fpscr & FPSCR_UX) && (fpscr & FPSCR_UE)) ||
- ((fpscr & FPSCR_ZX) && (fpscr & FPSCR_ZE)) ||
- ((fpscr & FPSCR_XX) && (fpscr & FPSCR_XE)))
+ fpscr |= FPSCR_VX;
+
+ /* The bit order of exception enables and exception status
+ * is the same. Simply shift and mask to check for enabled
+ * exceptions.
+ */
+ if (fpscr & (fpscr >> 22) & 0xf8)
fpscr |= FPSCR_FEX;
+
__FPU_FPSCR = fpscr;
#ifdef DEBUG
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-11-04 08:40:05 +0000