| Message ID | 20231205002322.10143-1-rpearsonhpe@gmail.com (mailing list archive) |
|---|---|
| Headers | show |
| Series | RDMA/rxe: Make multicast work | expand |
Add David S. Miller and David Ahern. They are the maintainers in netdev and very familiar with mcast. Zhu Yanjun 在 2023/12/5 8:23, Bob Pearson 写道: > After developing a test program which exercises node to node > testing of RoCE multicast it became clear that there are a > number of issues with the current rdma_rxe multicast implementation. > > The issues seen include: > - There is no support for IPV4 multicast addresses. > - Once a multicast MAC is added it is not removed. > - Multicast packets are sent with the wrong QP number. > - Multicast IP addresses are not created and without > them no multicast packets received on the interface > are delivered to the rdma_rxe driver. > - The implementation in rxe_mcast.c is potentially > racy if multiple simultaneous attach/detach operations > are issued. > > This patch set fixes these issues. > --- > v5: > Missed previous fix in error path. Add sock lock around > ipv6_sock_mm_drop() in rxe_mcast_add6(). > v4: > Corrected a lockdep bug reported by Zhu Yanjun. > v3: > Removed rxe_loop_and_send(). It turns out it is not needed. > Added module parameters to set mcast limits to small values when > driver is loaded to enable mcast limit testing. > Rebased to current for-next branch. > v2: > Respond to comments by Zhu. > Added more Fixes lines. > Added some more explanation in the commit messages. > Fixed an error in rxe_lookup_mcg. Should have checked > the return from rxe_get_mcg(). > > Bob Pearson (7): > RDMA/rxe: Cleanup rxe_ah/av_chk_attr > RDMA/rxe: Fix sending of mcast packets > RDMA/rxe: Register IP mcast address > RDMA/rxe: Let rxe_lookup_mcg use rcu_read_lock > RDMA/rxe: Split multicast lock > RDMA/rxe: Cleanup mcg lifetime > RDMA/rxe: Add module parameters for mcast limits > > drivers/infiniband/sw/rxe/Makefile | 3 +- > drivers/infiniband/sw/rxe/rxe.c | 8 +- > drivers/infiniband/sw/rxe/rxe_av.c | 50 +-- > drivers/infiniband/sw/rxe/rxe_loc.h | 6 +- > drivers/infiniband/sw/rxe/rxe_mcast.c | 526 +++++++++++-------------- > drivers/infiniband/sw/rxe/rxe_net.c | 6 +- > drivers/infiniband/sw/rxe/rxe_net.h | 1 + > drivers/infiniband/sw/rxe/rxe_opcode.h | 2 +- > drivers/infiniband/sw/rxe/rxe_param.c | 23 ++ > drivers/infiniband/sw/rxe/rxe_param.h | 4 + > drivers/infiniband/sw/rxe/rxe_qp.c | 4 +- > drivers/infiniband/sw/rxe/rxe_recv.c | 11 +- > drivers/infiniband/sw/rxe/rxe_req.c | 11 +- > drivers/infiniband/sw/rxe/rxe_verbs.c | 5 +- > drivers/infiniband/sw/rxe/rxe_verbs.h | 5 +- > 15 files changed, 305 insertions(+), 360 deletions(-) > create mode 100644 drivers/infiniband/sw/rxe/rxe_param.c >
On 12/4/23 10:50 PM, Zhu Yanjun wrote: > Add David S. Miller and David Ahern. > > They are the maintainers in netdev and very familiar with mcast. > I am nowhere close to being an expert on multicast, but many members of the netdev community are. This set seems to be refactoring rxe code vs new use of Linux networking stack. If there is something specific, please Cc netdev on the entire patch set with a request in the cover letter for specific reviews of individual patches.