__div64_const32(): improve the generic C version

Let's rework that code to avoid large immediate values and convert some
64-bit variables to 32-bit ones when possible. This allows gcc to
produce smaller and better code. This even produces optimal code on
RISC-V.
Signed-off-by: Nicolas Pitre <nico@fluxnic.net>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>

include/asm-generic/div64.h

@@ -178,7 +178,8 @@ static inline uint64_t __arch_xprod_64(const uint64_t m, uint64_t n, bool bias)
 	uint32_t m_hi = m >> 32;
 	uint32_t n_lo = n;
 	uint32_t n_hi = n >> 32;
-	uint64_t res, tmp;
+	uint64_t res;
+	uint32_t res_lo, res_hi, tmp;
 
 	if (!bias) {
 		res = ((uint64_t)m_lo * n_lo) >> 32;
@@ -187,8 +188,9 @@ static inline uint64_t __arch_xprod_64(const uint64_t m, uint64_t n, bool bias)
 		res = (m + (uint64_t)m_lo * n_lo) >> 32;
 	} else {
 		res = m + (uint64_t)m_lo * n_lo;
-		tmp = (res < m) ? (1ULL << 32) : 0;
-		res = (res >> 32) + tmp;
+		res_lo = res >> 32;
+		res_hi = (res_lo < m_hi);
+		res = res_lo | ((uint64_t)res_hi << 32);
 	}
 
 	if (!(m & ((1ULL << 63) | (1ULL << 31)))) {
@@ -197,10 +199,12 @@ static inline uint64_t __arch_xprod_64(const uint64_t m, uint64_t n, bool bias)
 		res += (uint64_t)m_hi * n_lo;
 		res >>= 32;
 	} else {
-		tmp = res += (uint64_t)m_lo * n_hi;
+		res += (uint64_t)m_lo * n_hi;
+		tmp = res >> 32;
 		res += (uint64_t)m_hi * n_lo;
-		tmp = (res < tmp) ? (1ULL << 32) : 0;
-		res = (res >> 32) + tmp;
+		res_lo = res >> 32;
+		res_hi = (res_lo < tmp);
+		res = res_lo | ((uint64_t)res_hi << 32);
 	}
 
 	res += (uint64_t)m_hi * n_hi;