Hi,
Le jeudi 28 novembre 2013 à 20:47 +0100, Hannes Weisbach a écrit :
> > But adding "const" should not break compilation of existing userspace
> > program.
> That was my thought too. However, because those functions are defined
> in as inline in a header, they actually do break user code. F
Hi.
> Two days ago I started to work on a kernel patchset to address similar
> concerns on the verbs/RDMA APIs
Nice.
>
> BTW, it's easier to change the kernel "internal" API than the public
> userspace API of the library. But adding "const" should not break
> compilation of existing userspace prog
Hi,
Le mercredi 27 novembre 2013 à 19:00 +0100, Hannes Weisbach a écrit :
> I just started working with librdmacm and I was wondering if there is a
> specific reason why rdma_reg_* functions and rdma_post_send/write functions
> take the local memory address as non-const pointer "void * addr". T
> I just started working with librdmacm and I was wondering if there is a
> specific reason why rdma_reg_* functions and rdma_post_send/write functions
> take the local memory address as non-const pointer "void * addr". These
> functions shouldn't and don't change the memory pointed to by addr. I t
Hi,
I just started working with librdmacm and I was wondering if there is a
specific reason why rdma_reg_* functions and rdma_post_send/write functions
take the local memory address as non-const pointer "void * addr". These
functions shouldn't and don't change the memory pointed to by addr. I t