Dynamically loaded library handles are saved in a list and dlclosed() on
exit. The list of struct ibv_driver *, as well as the global
struct ibv_device ** list are free()d.
Signed-off-by: Hannes Weisbach hannes_weisb...@gmx.net
---
src/device.c | 10 ++
src/init.c | 51
This patch adds the function idm_free() to free all entries of an index
map. A call to this function is added in the ucma_cleanup destructor.
The ucma_idm struct index_map is cleaned.
Signed-off-by: Hannes Weisbach hannes_weisb...@gmx.net
---
src/cma.c | 1 +
src/indexer.c | 8
src
Am 11.04.2014 um 19:00 schrieb Yann Droneaud ydrone...@opteya.com:
Hi,
Thanks for your quick reply.
Please adds some explanation, in particular the purpose of the changes.
Your commit message only explain how, but you should also explain
why.
Ok.
In C, empty prototype declare a function
Is the array always full ?
No, but it has to be zero-initialized and free(NULL) is fine.
idm_set() does:
if (!idm-array[idx_array_index(index)]) {
if (idm_grow(idm, index) 0)
(idm_grow does calloc().)
So I concluded unused entries have to be zero already and I don't put
a
() on pinned memory/I/O memory should fail, i.e. return EINVAL,
EIO or ENOMEM (I didn’t test what happens when you call
madvise(MADV_DONTNEED) on I/O mem.)
. RDMA actions on madvise()’d memory should fail.
Best regards,
Hannes Weisbach--
To unsubscribe from this list: send the line unsubscribe linux
Am 30.01.2014 um 22:36 schrieb Anuj Kalia anujkaliai...@gmail.com:
Hannes,
Have you tried marking the memory that is being read as volatile“?
Thanks for the suggestion, but I don’t think that this solves the
problem, because when I do:
memset(…);
rdma_post_read(…);
/* wait */
memcmp(…);
Am 31.01.2014 um 15:26 schrieb Anuj Kalia anujkaliai...@gmail.com:
Are you sure that the compiler knows that post_send() has side effects?
No, thats why I tested with the mentioned memcmpv. I examined the
emitted code with objdump and the compiler issued the mov instructions
to read the bytes
the work completion reports IBV_SUCCESS.
I hope you can give me some hints on how to proceed.
I apologize if my problem description was too brief; please ask for
details if I left important information out.
Best regards,
Hannes Weisbach--
To unsubscribe from this list: send the line unsubscribe linux-rdma
think
this should be made explicit by using the type const void * for addr.
In case you agree, I would volunteer to make the necessary changes.
Best regards,
Hannes Weisbach--
To unsubscribe from this list: send the line unsubscribe linux-rdma in
the body of a message to majord...@vger.kernel.org