sparc: fix accurate exception reporting in copy_{from,to}_user for M7

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: 34060b8fffa7 ("arch/sparc: Add accurate exception reporting in M7memcpy")
Tested-by: John Paul Adrian Glaubitz <[e-mail]> # on Oracle SPARC S7
Tested-by: Tony Rodriguez <[e-mail]> # S7, see https://lore.kernel.org/r/[e-mail]
Signed-off-by: Michael Karcher <[e-mail]>
Reviewed-by: Andreas Larsson <[e-mail]>
Link: https://lore.kernel.org/r/[e-mail]
Signed-off-by: Andreas Larsson <[e-mail]>

arch/sparc/lib/M7memcpy.S

···
 	EX_LD_FP(LOAD(ldd, %o4+40, %f26), memcpy_retl_o2_plus_o5_plus_40)
 	faligndata %f24, %f26, %f10
 	EX_ST_FP(STORE(std, %f6, %o0+24), memcpy_retl_o2_plus_o5_plus_40)
-	EX_LD_FP(LOAD(ldd, %o4+48, %f28), memcpy_retl_o2_plus_o5_plus_40)
+	EX_LD_FP(LOAD(ldd, %o4+48, %f28), memcpy_retl_o2_plus_o5_plus_32)
 	faligndata %f26, %f28, %f12
-	EX_ST_FP(STORE(std, %f8, %o0+32), memcpy_retl_o2_plus_o5_plus_40)
+	EX_ST_FP(STORE(std, %f8, %o0+32), memcpy_retl_o2_plus_o5_plus_32)
 	add	%o4, 64, %o4
-	EX_LD_FP(LOAD(ldd, %o4-8, %f30), memcpy_retl_o2_plus_o5_plus_40)
+	EX_LD_FP(LOAD(ldd, %o4-8, %f30), memcpy_retl_o2_plus_o5_plus_24)
 	faligndata %f28, %f30, %f14
-	EX_ST_FP(STORE(std, %f10, %o0+40), memcpy_retl_o2_plus_o5_plus_40)
-	EX_ST_FP(STORE(std, %f12, %o0+48), memcpy_retl_o2_plus_o5_plus_40)
+	EX_ST_FP(STORE(std, %f10, %o0+40), memcpy_retl_o2_plus_o5_plus_24)
+	EX_ST_FP(STORE(std, %f12, %o0+48), memcpy_retl_o2_plus_o5_plus_16)
 	add	%o0, 64, %o0
-	EX_ST_FP(STORE(std, %f14, %o0-8), memcpy_retl_o2_plus_o5_plus_40)
+	EX_ST_FP(STORE(std, %f14, %o0-8), memcpy_retl_o2_plus_o5_plus_8)
 	fsrc2	%f30, %f14
 	bgu,pt	%xcc, .Lunalign_sloop
 	 prefetch [%o4 + (8 * BLOCK_SIZE)], 20
···
 	add	%o4, 8, %o4
 	faligndata %f0, %f2, %f16
 	subcc	%o5, 8, %o5
-	EX_ST_FP(STORE(std, %f16, %o0), memcpy_retl_o2_plus_o5)
+	EX_ST_FP(STORE(std, %f16, %o0), memcpy_retl_o2_plus_o5_plus_8)
 	fsrc2	%f2, %f0
 	bgu,pt	%xcc, .Lunalign_by8
 	 add	%o0, 8, %o0
···
 	subcc	%o5, 0x20, %o5
 	EX_ST(STORE(stx, %o3, %o0 + 0x00), memcpy_retl_o2_plus_o5_plus_32)
 	EX_ST(STORE(stx, %g2, %o0 + 0x08), memcpy_retl_o2_plus_o5_plus_24)
-	EX_ST(STORE(stx, %g7, %o0 + 0x10), memcpy_retl_o2_plus_o5_plus_24)
+	EX_ST(STORE(stx, %g7, %o0 + 0x10), memcpy_retl_o2_plus_o5_plus_16)
 	EX_ST(STORE(stx, %o4, %o0 + 0x18), memcpy_retl_o2_plus_o5_plus_8)
 	bne,pt	%xcc, 1b
 	 add	%o0, 0x20, %o0
···
 	brz,pt	%o3, 2f
 	 sub	%o2, %o3, %o2
 
-1:	EX_LD(LOAD(ldub, %o1 + 0x00, %g2), memcpy_retl_o2_plus_g1)
+1:	EX_LD(LOAD(ldub, %o1 + 0x00, %g2), memcpy_retl_o2_plus_o3)
 	add	%o1, 1, %o1
 	subcc	%o3, 1, %o3
 	add	%o0, 1, %o0
 	bne,pt	%xcc, 1b
-	 EX_ST(STORE(stb, %g2, %o0 - 0x01), memcpy_retl_o2_plus_g1_plus_1)
+	 EX_ST(STORE(stb, %g2, %o0 - 0x01), memcpy_retl_o2_plus_o3_plus_1)
 2:
 	and	%o1, 0x7, %o3
 	brz,pn	%o3, .Lmedium_noprefetch_cp

arch/sparc/lib/Memcpy_utils.S

···
 	ba,pt	%xcc, __restore_asi
 	 add	%o2, 8, %o0
 ENDPROC(memcpy_retl_o2_plus_63_8)
+ENTRY(memcpy_retl_o2_plus_o3)
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, %o3, %o0
+ENDPROC(memcpy_retl_o2_plus_o3)
+ENTRY(memcpy_retl_o2_plus_o3_plus_1)
+	add	%o3, 1, %o3
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, %o3, %o0
+ENDPROC(memcpy_retl_o2_plus_o3_plus_1)
 ENTRY(memcpy_retl_o2_plus_o5)
 	ba,pt	%xcc, __restore_asi
 	 add	%o2, %o5, %o0