sparc: fix accurate exception reporting in copy_{from_to}_user for UltraSPARC

The referenced commit introduced exception handlers on user-space memory
references in copy_from_user and copy_to_user. These handlers return from
the respective function and calculate the remaining bytes left to copy
using the current register contents. This commit fixes a couple of bad
calculations. This will fix the return value of copy_from_user and
copy_to_user in the faulting case. The behaviour of memcpy stays unchanged.

Fixes: cb736fd ("sparc64: Convert U1copy_{from,to}_user to accurate exception reporting.")
Tested-by: John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de> # on QEMU 10.0.3
Tested-by: René Rebe <rene@exactcode.com> # on Ultra 5 UltraSparc IIi
Tested-by: Jonathan 'theJPster' Pallant <kernel@thejpster.org.uk> # on Sun Netra T1
Signed-off-by: Michael Karcher <kernel@mkarcher.dialup.fu-berlin.de>
Reviewed-by: Andreas Larsson <andreas@gaisler.com>
Link: https://lore.kernel.org/r/20250905-memcpy_series-v4-1-1ca72dda195b@mkarcher.dialup.fu-berlin.de
Signed-off-by: Andreas Larsson <andreas@gaisler.com>

Author: Michael Karcher

arch/sparc/lib/U1memcpy.S

@@ -164,17 +164,18 @@ ENTRY(U1_gs_40_fp)
 	retl
 	 add		%o0, %o2, %o0
 ENDPROC(U1_gs_40_fp)
-ENTRY(U1_g3_0_fp)
-	VISExitHalf
-	retl
-	 add		%g3, %o2, %o0
-ENDPROC(U1_g3_0_fp)
 ENTRY(U1_g3_8_fp)
 	VISExitHalf
 	add		%g3, 8, %g3
 	retl
 	 add		%g3, %o2, %o0
 ENDPROC(U1_g3_8_fp)
+ENTRY(U1_g3_16_fp)
+	VISExitHalf
+	add		%g3, 16, %g3
+	retl
+	 add		%g3, %o2, %o0
+ENDPROC(U1_g3_16_fp)
 ENTRY(U1_o2_0_fp)
 	VISExitHalf
 	retl
@@ -547,18 +548,18 @@ FUNC_NAME:		/* %o0=dst, %o1=src, %o2=len */
 62:	FINISH_VISCHUNK(o0, f44, f46)
 63:	UNEVEN_VISCHUNK_LAST(o0, f46, f0)
 
-93:	EX_LD_FP(LOAD(ldd, %o1, %f2), U1_g3_0_fp)
+93:	EX_LD_FP(LOAD(ldd, %o1, %f2), U1_g3_8_fp)
 	add		%o1, 8, %o1
 	subcc		%g3, 8, %g3
 	faligndata	%f0, %f2, %f8
-	EX_ST_FP(STORE(std, %f8, %o0), U1_g3_8_fp)
+	EX_ST_FP(STORE(std, %f8, %o0), U1_g3_16_fp)
 	bl,pn		%xcc, 95f
 	 add		%o0, 8, %o0
-	EX_LD_FP(LOAD(ldd, %o1, %f0), U1_g3_0_fp)
+	EX_LD_FP(LOAD(ldd, %o1, %f0), U1_g3_8_fp)
 	add		%o1, 8, %o1
 	subcc		%g3, 8, %g3
 	faligndata	%f2, %f0, %f8
-	EX_ST_FP(STORE(std, %f8, %o0), U1_g3_8_fp)
+	EX_ST_FP(STORE(std, %f8, %o0), U1_g3_16_fp)
 	bge,pt		%xcc, 93b
 	 add		%o0, 8, %o0