diff options
| author | David Laight <david.laight.linux@gmail.com> | 2025-11-05 20:10:30 +0000 |
|---|---|---|
| committer | Andrew Morton <akpm@linux-foundation.org> | 2025-11-20 14:03:41 -0800 |
| commit | 6480241f31f543333ed0c7a209962412461f6e41 (patch) | |
| tree | 7eb37452b8203568f3f390727df630470d0138a6 /lib | |
| parent | d91f891d588557874a45a5f584b6da0b433acee7 (diff) | |
lib: add mul_u64_add_u64_div_u64() and mul_u64_u64_div_u64_roundup()
The existing mul_u64_u64_div_u64() rounds down, a 'rounding up' variant
needs 'divisor - 1' adding in between the multiply and divide so cannot
easily be done by a caller.
Add mul_u64_add_u64_div_u64(a, b, c, d) that calculates (a * b + c)/d and
implement the 'round down' and 'round up' using it.
Update the x86-64 asm to optimise for 'c' being a constant zero.
Add kerndoc definitions for all three functions.
Link: https://lkml.kernel.org/r/20251105201035.64043-5-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>
Diffstat (limited to 'lib')
| -rw-r--r-- | lib/math/div64.c | 14 |
1 files changed, 8 insertions, 6 deletions
diff --git a/lib/math/div64.c b/lib/math/div64.c index 4a4b1aa9e6e1..a88391b8ada0 100644 --- a/lib/math/div64.c +++ b/lib/math/div64.c @@ -183,13 +183,13 @@ u32 iter_div_u64_rem(u64 dividend, u32 divisor, u64 *remainder) } EXPORT_SYMBOL(iter_div_u64_rem); -#ifndef mul_u64_u64_div_u64 -u64 mul_u64_u64_div_u64(u64 a, u64 b, u64 d) +#ifndef mul_u64_add_u64_div_u64 +u64 mul_u64_add_u64_div_u64(u64 a, u64 b, u64 c, u64 d) { #if defined(__SIZEOF_INT128__) /* native 64x64=128 bits multiplication */ - u128 prod = (u128)a * b; + u128 prod = (u128)a * b + c; u64 n_lo = prod, n_hi = prod >> 64; #else @@ -198,8 +198,10 @@ u64 mul_u64_u64_div_u64(u64 a, u64 b, u64 d) u32 a_lo = a, a_hi = a >> 32, b_lo = b, b_hi = b >> 32; u64 x, y, z; - x = (u64)a_lo * b_lo; - y = (u64)a_lo * b_hi + (u32)(x >> 32); + /* 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); @@ -265,5 +267,5 @@ u64 mul_u64_u64_div_u64(u64 a, u64 b, u64 d) return res; } -EXPORT_SYMBOL(mul_u64_u64_div_u64); +EXPORT_SYMBOL(mul_u64_add_u64_div_u64); #endif |