linux.git/drivers/infiniband, branch v4.13-rc2

RDMA/core: Initialize port_num in qp_attr

2017-07-20T15:24:13+00:00

Initialize the port_num for iWARP in rdma_init_qp_attr.

Fixes: 5ecce4c9b17b("Check port number supplied by user verbs cmds")
Cc:  # v2.6.14+
Reviewed-by: Steve Wise 
Signed-off-by: Mustafa Ismail 
Tested-by: Mike Marciniszyn 
Signed-off-by: Doug Ledford

RDMA/uverbs: Fix the check for port number

2017-07-20T15:24:13+00:00

The port number is only valid if IB_QP_PORT is set in the mask.
So only check port number if it is valid to prevent modify_qp from
failing due to an invalid port number.

Fixes: 5ecce4c9b17b("Check port number supplied by user verbs cmds")
Cc:  # v2.6.14+
Reviewed-by: Steve Wise 
Signed-off-by: Mustafa Ismail 
Tested-by: Mike Marciniszyn 
Signed-off-by: Doug Ledford

RDMA/iser: don't send an rkey if all data is written as immadiate-data

2017-07-20T15:20:50+00:00

We might get some bogus error completions in case the target will
remotely invalidate the rkey and the HCA will need to retransmit
from this buffer.

Signed-off-by: Sagi Grimberg 
Signed-off-by: Doug Ledford

rxe: fix broken receive queue draining

2017-07-20T15:20:50+00:00

If we modified the qp to ERROR state, and
drained the recieve queue, post_recv must
trigger the responder task to complete
the drain work request.

Cc: Bart Van Assche 
Signed-off-by: Vijay Immanuel 
Signed-off-by: Sagi Grimberg 
Reviewed-by: Bart Van Assche --
Signed-off-by: Doug Ledford

RDMA/qedr: Prevent memory overrun in verbs' user responses

2017-07-20T15:20:50+00:00

Wrap ib_copy_to_udata with a function that ensures that the data
being copied over to user space isn't longer than the allowed.

Fixes: cecbcddf6461 ("qedr: Add support for QP verbs")
Fixes: a7efd7773e31 ("qedr: Add support for PD,PKEY and CQ verbs")
Fixes: ac1b36e55a51 ("qedr: Add support for user context verbs")
Signed-off-by: Ram Amrani 
Signed-off-by: Doug Ledford

iw_cxgb4: don't use WR keys/addrs for 0 byte reads

2017-07-20T15:20:50+00:00

Only use the read sge lkey/addr and the remote rkey/addr if the
length of the read is not zero. Otherwise the read response might
be treated as the RTR read response and not delivered to the
application. Or worse Terminator hardware will fail a 0B read
if the STAG is 0 even if the read length is 0.

Signed-off-by: Steve Wise 
Signed-off-by: Ganesh Goudar 
Signed-off-by: Doug Ledford

IB/mlx4: Fix CM REQ retries in paravirt mode

2017-07-20T15:20:50+00:00

CM REQs cannot be successfully retried, because a new pv_cm_id is
created for each request, without checking if one already exists.

By checking if an id exists before creating one, the bug is fixed.

This bug can be provoked by running an RDMA CM user-land application,
but inserting a five seconds delay before the rdma_accept() call on
the passive side. This delay is larger than the default CMA timeout,
and triggers a retry from the active side. The retried REQ will use
another pv_cm_id (the cm_id on the wire). This confuses the CM
protocol and two REJs are sent from the passive side.

Here is an excerpt from ibdump running without the patch:

3.285092       LID: 4 -> LID: 4       SDP 290 CM: ConnectRequest(SDP Hello)
7.382711       LID: 4 -> LID: 4       SDP 290 CM: ConnectRequest(SDP Hello)
7.382861       LID: 4 -> LID: 4       InfiniBand 290 CM: ConnectReject
7.387644       LID: 4 -> LID: 4       InfiniBand 290 CM: ConnectReject

and here is the same with bug fix applied:

3.251010       LID: 4 -> LID: 4       SDP 290 CM: ConnectRequest(SDP Hello)
7.349387       LID: 4 -> LID: 4       SDP 290 CM: ConnectRequest(SDP Hello)
8.258443       LID: 4 -> LID: 4       SDP 290 CM: ConnectReply(SDP Hello)
8.259890       LID: 4 -> LID: 4       InfiniBand 290 CM: ReadyToUse

Suggested-by: Venkat Venkatsubra 
Signed-off-by: Håkon Bugge 
Reported-by: Wei Lin Guay 
Tested-by: Wei Lin Guay 
Reviewed-by: Yuval Shaia 
Acked-by: Jack Morgenstein 
Signed-off-by: Doug Ledford

IB/rdmavt: Setting of QP timeout can overflow jiffies computation

2017-07-20T15:20:50+00:00

Current computation of qp->timeout_jiffies in rvt_modify_qp() will cause
overflow due to the fact that the input to the function usecs_to_jiffies
is only 32-bit ( unsigned int). Overflow will occur when attr->timeout is
equal to or greater than 30. The consequence is unnecessarily excessive
retry and thus degradation of the system performance.

This patch fixes the problem by limiting the input to 5-bit and calling
usecs_to_jiffies() before multiplying the scaling factor.

Reviewed-by: Mike Marciniszyn 
Signed-off-by: Kaike Wan 
Signed-off-by: Dennis Dalessandro 
Signed-off-by: Doug Ledford

IB/core: Fix sparse warnings

2017-07-20T15:20:50+00:00

Delete unused variables to prevent sparse warnings.

Fixes: db1b5ddd5336 ("IB/core: Rename uverbs event file structure")
Fixes: fd3c7904db6e ("IB/core: Change idr objects to use the new schema")

Signed-off-by: Doug Ledford

RDMA/bnxt_re: Fix the value reported for local ack delay

2017-07-20T15:20:50+00:00

Local ack delay exposed by the driver is 0 which means infinite QP
timeout. Reporting the default value to 16 (approx 260ms)

Signed-off-by: Selvin Xavier 
Signed-off-by: Doug Ledford