On Tue, Jun 29, 2021 at 01:45:35PM +0000, Haakon Bugge wrote:

quoted

quoted

quoted

IMHO it is a bug on the sender side to send GMPs to use a pkey that
doesn't exactly match the data path pkey.

The active connector calls ib_addr_get_pkey(). This function
extracts the pkey from byte 8/9 in the device's bcast
address. However, RFC 4391 explicitly states:

pkeys in CM come only from path records that the SM returns, the above
should only be used to feed into a path record query which could then
return back a limited pkey.

Everything thereafter should use the SM's version of the pkey.

Revisiting this. I think I mis-interpreted the scenario that led to
the P_Key mismatch messages.

The CM retrieves the pkey_index that matched the P_Key in the BTH
(cm_get_bth_pkey()) and thereafter calls ib_get_cached_pkey() to get
the P_Key value of the particular pkey_index.

Assume a full-member sends a REQ. In that case, both P_Keys (BTH and
primary path_rec) are full. Further, assume the recipient is only a
limited member. Since full and limited members of the same partition
are eligible to communicate, the P_Key retrieved by
cm_get_bth_pkey() will be the limited one.

It is incorrect for the issuer of the REQ to put a full pkey in the
REQ message when the target is a limited member.

The CM model in IB has the target fully under the control of the
initiator, and it is up to the initiator to ask the SM how the target
should generate its return traffic. The SM is reponsible to say that
limited->full communication is done using the limited pkey.

The initiator is reponsible to place that limited pkey in the REQ
message.

Somewhere in your system this isn't happening properly, and it is a
bug that the CM is correctly identifying.

Jason