lib: mul_u64_u64_div_u64(): optimise multiply on 32bit x86

gcc generates horrid code for both ((u64)u32_a * u32_b) and (u64_a +
u32_b).  As well as the extra instructions it can generate a lot of spills
to stack (including spills of constant zeros and even multiplies by
constant zero).

mul_u32_u32() already exists to optimise the multiply.  Add a similar
add_u64_32() for the addition.  Disable both for clang - it generates
better code without them.

Move the 64x64 => 128 multiply into a static inline helper function for
code clarity.  No need for the a/b_hi/lo variables, the implicit casts on
the function calls do the work for us.  Should have minimal effect on the
generated code.

Use mul_u32_u32() and add_u64_u32() in the 64x64 => 128 multiply in
mul_u64_add_u64_div_u64().

Link: https://lkml.kernel.org/r/20251105201035.64043-8-david.laight.linux@gmail.com
Signed-off-by: David Laight <david.laight.linux@gmail.com>
Reviewed-by: Nicolas Pitre <npitre@baylibre.com>
Cc: Biju Das <biju.das.jz@bp.renesas.com>
Cc: Borislav Betkov <bp@alien8.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Li RongQing <lirongqing@baidu.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleinxer <tglx@linutronix.de>
Cc: Uwe Kleine-König <u.kleine-koenig@baylibre.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

arch/x86/include/asm/div64.h

@@ -60,6 +60,12 @@ static inline u64 div_u64_rem(u64 dividend, u32 divisor, u32 *remainder)
 }
 #define div_u64_rem	div_u64_rem
 
+/*
+ * gcc tends to zero extend 32bit values and do full 64bit maths.
+ * Define asm functions that avoid this.
+ * (clang generates better code for the C versions.)
+ */
+#ifndef __clang__
 static inline u64 mul_u32_u32(u32 a, u32 b)
 {
 	u32 high, low;
@@ -71,6 +77,19 @@ static inline u64 mul_u32_u32(u32 a, u32 b)
 }
 #define mul_u32_u32 mul_u32_u32
 
+static inline u64 add_u64_u32(u64 a, u32 b)
+{
+	u32 high = a >> 32, low = a;
+
+	asm ("addl %[b], %[low]; adcl $0, %[high]"
+		: [low] "+r" (low), [high] "+r" (high)
+		: [b] "rm" (b) );
+
+	return low | (u64)high << 32;
+}
+#define add_u64_u32 add_u64_u32
+#endif
+
 /*
  * __div64_32() is never called on x86, so prevent the
  * generic definition from getting built.

include/linux/math64.h

@@ -158,6 +158,17 @@ static inline u64 mul_u32_u32(u32 a, u32 b)
 }
 #endif
 
+#ifndef add_u64_u32
+/*
+ * Many a GCC version also messes this up.
+ * Zero extending b and then spilling everything to stack.
+ */
+static inline u64 add_u64_u32(u64 a, u32 b)
+{
+	return a + b;
+}
+#endif
+
 #if defined(CONFIG_ARCH_SUPPORTS_INT128) && defined(__SIZEOF_INT128__)
 
 #ifndef mul_u64_u32_shr

lib/math/div64.c

@@ -186,33 +186,45 @@ EXPORT_SYMBOL(iter_div_u64_rem);
 #endif
 
 #if !defined(mul_u64_add_u64_div_u64) || defined(test_mul_u64_add_u64_div_u64)
-u64 mul_u64_add_u64_div_u64(u64 a, u64 b, u64 c, u64 d)
-{
+
+#define mul_add(a, b, c) add_u64_u32(mul_u32_u32(a, b), c)
+
 #if defined(__SIZEOF_INT128__) && !defined(test_mul_u64_add_u64_div_u64)
 
+static inline u64 mul_u64_u64_add_u64(u64 *p_lo, u64 a, u64 b, u64 c)
+{
 	/* native 64x64=128 bits multiplication */
 	u128 prod = (u128)a * b + c;
-	u64 n_lo = prod, n_hi = prod >> 64;
+
+	*p_lo = prod;
+	return prod >> 64;
+}
 
 #else
 
-	/* perform a 64x64=128 bits multiplication manually */
-	u32 a_lo = a, a_hi = a >> 32, b_lo = b, b_hi = b >> 32;
+static inline u64 mul_u64_u64_add_u64(u64 *p_lo, u64 a, u64 b, u64 c)
+{
+	/* perform a 64x64=128 bits multiplication in 32bit chunks */
 	u64 x, y, z;
 
 	/* Since (x-1)(x-1) + 2(x-1) == x.x - 1 two u32 can be added to a u64 */
-	x = (u64)a_lo * b_lo + (u32)c;
-	y = (u64)a_lo * b_hi + (u32)(c >> 32);
-	y += (u32)(x >> 32);
-	z = (u64)a_hi * b_hi + (u32)(y >> 32);
-	y = (u64)a_hi * b_lo + (u32)y;
-	z += (u32)(y >> 32);
-	x = (y << 32) + (u32)x;
-
-	u64 n_lo = x, n_hi = z;
+	x = mul_add(a, b, c);
+	y = mul_add(a, b >> 32, c >> 32);
+	y = add_u64_u32(y, x >> 32);
+	z = mul_add(a >> 32, b >> 32, y >> 32);
+	y = mul_add(a >> 32, b, y);
+	*p_lo = (y << 32) + (u32)x;
+	return add_u64_u32(z, y >> 32);
+}
 
 #endif
 
+u64 mul_u64_add_u64_div_u64(u64 a, u64 b, u64 c, u64 d)
+{
+	u64 n_lo, n_hi;
+
+	n_hi = mul_u64_u64_add_u64(&n_lo, a, b, c);
+
 	if (!n_hi)
 		return div64_u64(n_lo, d);