Re: [PATCH] x86/spinlocks: Fix regression in spinlock contention detection

[Tahsin Erdogan]

The conversion to signed happens with types shorter than int
(__ticket_t is either u8 or u16).

By changing Raghavendra's program to use unsigned short int, you can
see the problem:

================
#include <stdio.h>

#define LOCK_INC 2

int main()
{
        unsigned short int head = 32700, tail=2;

        if ((tail - head) > LOCK_INC)
                printf(" tail - head > LOCK_INC \n");
        else
                printf(" tail - head < LOCK_INC \n");

        return 0;
}

================
gcc -g -o t main.c
./t
 tail - head < LOCK_INC

However, having just unsigned int returns the opposite result
(unsigned int head = 32700, tail=2;)

gcc -g -o t main.c
./t
 tail - head > LOCK_INC

On Tue, May 5, 2015 at 3:58 AM, Peter Zijlstra <peterz@xxxxxxxxxxxxx> wrote:
> On Tue, May 05, 2015 at 04:08:22PM +0530, Raghavendra K T wrote:
>> ================
>> #include <stdio.h>
>>
>> #define LOCK_INC 2
>
> Note that to be completely identical to the kernel code you should've
> written:
>
> #define LOCK_INC        ((unsigned int)2)
>
> as per:
>
> #define TICKET_LOCK_INC ((__ticket_t)__TICKET_LOCK_INC)
>
>
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/