MIPS: Implement __multi3 for GCC7 MIPS64r6 builds

GCC7 is a bit too eager to generate suboptimal __multi3 calls (128bit
multiply with 128bit result) for MIPS64r6 builds, even in code which
doesn't explicitly use 128bit types, such as the following:

unsigned long func(unsigned long a, unsigned long b)
{
	return a > (~0UL) / b;
}

Which GCC rearanges to:

return (unsigned __int128)a * (unsigned __int128)b > 0xffffffffffffffff;

Therefore implement __multi3, but only for MIPS64r6 with GCC7 as under
normal circumstances we wouldn't expect any calls to __multi3 to be
generated from kernel code.
Reported-by: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
Signed-off-by: James Hogan <jhogan@kernel.org>
Tested-by: Waldemar Brodkorb <wbx@openadk.org>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Maciej W. Rozycki <macro@mips.com>
Cc: Matthew Fortune <matthew.fortune@mips.com>
Cc: Florian Fainelli <florian@openwrt.org>
Cc: linux-mips@linux-mips.org
Patchwork: https://patchwork.linux-mips.org/patch/17890/

arch/mips/lib/Makefile

@@ -16,4 +16,5 @@ obj-$(CONFIG_CPU_R3000)		+= r3k_dump_tlb.o
 obj-$(CONFIG_CPU_TX39XX)	+= r3k_dump_tlb.o
 
 # libgcc-style stuff needed in the kernel
-obj-y += ashldi3.o ashrdi3.o bswapsi.o bswapdi.o cmpdi2.o lshrdi3.o ucmpdi2.o
+obj-y += ashldi3.o ashrdi3.o bswapsi.o bswapdi.o cmpdi2.o lshrdi3.o multi3.o \
+	 ucmpdi2.o

arch/mips/lib/libgcc.h

@@ -10,10 +10,18 @@ typedef int word_type __attribute__ ((mode (__word__)));
 struct DWstruct {
 	int high, low;
 };
+
+struct TWstruct {
+	long long high, low;
+};
 #elif defined(__LITTLE_ENDIAN)
 struct DWstruct {
 	int low, high;
 };
+
+struct TWstruct {
+	long long low, high;
+};
 #else
 #error I feel sick.
 #endif
@@ -23,4 +31,13 @@ typedef union {
 	long long ll;
 } DWunion;
 
+#if defined(CONFIG_64BIT) && defined(CONFIG_CPU_MIPSR6)
+typedef int ti_type __attribute__((mode(TI)));
+
+typedef union {
+	struct TWstruct s;
+	ti_type ti;
+} TWunion;
+#endif
+
 #endif /* __ASM_LIBGCC_H */

arch/mips/lib/multi3.c

+// SPDX-License-Identifier: GPL-2.0
+#include <linux/export.h>
+
+#include "libgcc.h"
+
+/*
+ * GCC 7 suboptimally generates __multi3 calls for mips64r6, so for that
+ * specific case only we'll implement it here.
+ *
+ * See https://gcc.gnu.org/bugzilla/show_bug.cgi?id=82981
+ */
+#if defined(CONFIG_64BIT) && defined(CONFIG_CPU_MIPSR6) && (__GNUC__ == 7)
+
+/* multiply 64-bit values, low 64-bits returned */
+static inline long long notrace dmulu(long long a, long long b)
+{
+	long long res;
+
+	asm ("dmulu %0,%1,%2" : "=r" (res) : "r" (a), "r" (b));
+	return res;
+}
+
+/* multiply 64-bit unsigned values, high 64-bits of 128-bit result returned */
+static inline long long notrace dmuhu(long long a, long long b)
+{
+	long long res;
+
+	asm ("dmuhu %0,%1,%2" : "=r" (res) : "r" (a), "r" (b));
+	return res;
+}
+
+/* multiply 128-bit values, low 128-bits returned */
+ti_type notrace __multi3(ti_type a, ti_type b)
+{
+	TWunion res, aa, bb;
+
+	aa.ti = a;
+	bb.ti = b;
+
+	/*
+	 * a * b =           (a.lo * b.lo)
+	 *         + 2^64  * (a.hi * b.lo + a.lo * b.hi)
+	 *        [+ 2^128 * (a.hi * b.hi)]
+	 */
+	res.s.low = dmulu(aa.s.low, bb.s.low);
+	res.s.high = dmuhu(aa.s.low, bb.s.low);
+	res.s.high += dmulu(aa.s.high, bb.s.low);
+	res.s.high += dmulu(aa.s.low, bb.s.high);
+
+	return res.ti;
+}
+EXPORT_SYMBOL(__multi3);
+
+#endif /* 64BIT && CPU_MIPSR6 && GCC7 */