Commit Graph
20 Commits
Author SHA1 Message Date
Michael Brown 94876f4bb6 [infiniband] Remove the return status code from MAD handlers
MAD handlers have to set the status fields within the MAD itself
anyway, in order to provide a meaningful response MAD; the additional
gPXE return status code is just noise.

Note that we probably don't need to ever explicitly set the status to
IB_MGMT_STATUS_OK, since it should already have this value from the
request.  (By not explicitly setting the status in this way, we can
safely have ib_sma_set_xxx() call ib_sma_get_xxx() in order to
generate the GetResponse MAD without worrying that ib_sma_get_xxx()
will clear any error status set by ib_sma_set_xxx().)
2009-07-17 23:06:35 +01:00
Michael Brown f1d92fa886 [infiniband] Allow external QPN to differ from real QPN
Most IB hardware seems not to allow allocation of the genuine QPNs 0
and 1, so allow for the externally-visible QPN (as constructed and
parsed by ib_packet, where used) to differ from the real
hardware-allocated QPN.
2009-07-17 23:06:34 +01:00
Michael Brown 92cf240020 [infiniband] Always create an SMA and a GMA 2009-07-17 23:06:34 +01:00
Michael Brown 80c41b90d2 [infiniband] Add notion of a queue pair type 2009-07-17 23:06:34 +01:00
Michael Brown 3f4972db9a [infiniband] Allow completion queue operations to be optional
The send completion handler typically will just free the I/O buffer,
so allow this common case to be handled by the Infiniband core.
2009-07-17 23:06:34 +01:00
Michael Brown 0582a84e66 [infiniband] Improve ib_packet debugging messages 2009-07-17 23:06:34 +01:00
Michael Brown 165074c188 [infiniband] Implement SMA as an instance of a GMA
The GMA code was based upon the SMA code.  We can save space by making
the SMA simply an instance of the GMA.
2009-07-17 23:06:34 +01:00
Michael Brown 8a852280eb [infiniband] Pass GMA as a parameter to GMA MAD handlers 2009-07-17 23:06:34 +01:00
Michael Brown cb9ef4dee2 [ipoib] Remove the queue set abstraction
Now that IPoIB has to deal with only one set of queues, the queue set
abstraction becomes merely an inconvenient wrapper.
2009-07-17 23:06:34 +01:00
Michael Brown 0fbf2f6bda [infiniband] Provide a general mechanism for multicast group joins
Generalise out the multicast group membership record code from IPoIB.
2009-07-17 23:06:34 +01:00
Michael Brown 3c77fe73a5 [infiniband] Allow for sending MADs via GMA without retransmission 2009-07-17 23:06:34 +01:00
Michael Brown b4155c4ab5 [infiniband] Make qkey and rate optional parameters to ib_post_send()
The queue key is stored as a property of the queue pair, and so can
optionally be added by the Infiniband core at the time of calling
ib_post_send(), rather than always having to be specified by the
caller.

This allows IPoIB to avoid explicitly keeping track of the data queue
key.
2009-07-17 23:06:33 +01:00
Michael Brown d6b47871de [infiniband] Provide a general mechanism for path record lookups
Generalise out the path record lookup code from IPoIB.
2009-07-17 23:06:33 +01:00
Michael Brown 1d8c85d112 [infiniband] Create a general management agent
Generalise the subnet management agent into a general management agent
capable of sending and responding to MADs, including support for
retransmissions as necessary.
2009-07-17 23:06:33 +01:00
Michael Brown 365b8db5cf [infiniband] Centralise SMA and GMA queue constants 2009-07-17 23:06:33 +01:00
Michael Brown 887d296b88 [infiniband] Poll completion queues automatically
Currently, all Infiniband users must create a process for polling
their completion queues (or rely on a regular hook such as
netdev_poll() in ipoib.c).

Move instead to a model whereby the Infiniband core maintains a single
process calling ib_poll_eq(), and polling the event queue triggers
polls of the applicable completion queues.  (At present, the
Infiniband core simply polls all of the device's completion queues.)
Polling a completion queue will now implicitly refill all attached
receive work queues; this is analogous to the way that netdev_poll()
implicitly refills the RX ring.

Infiniband users no longer need to create a process just to poll their
completion queues and refill their receive rings.
2009-07-17 23:06:33 +01:00
Michael Brown 1f5c0239b4 [infiniband] Centralise assumption of 2048-byte payloads
IPoIB and the SMA have separate constants for the packet size to be
used to I/O buffer allocations.  Merge these into the single
IB_MAX_PAYLOAD_SIZE constant.

(Various other points in the Infiniband stack have hard-coded
assumptions of a 2048-byte payload; we don't currently support
variable MTUs.)
2009-07-17 23:06:33 +01:00
Michael Brown 7ba33f7826 [infiniband] Provide ib_get_hca_info() as a commonly-available function 2009-07-17 23:06:33 +01:00
Michael Brown b25a4b6c8a [infiniband] Split queue set functionality out of ipoib.c to ib_qset.c 2009-07-17 23:06:33 +01:00
Michael Brown 8868956268 [infiniband] Move non-driver-specific code to net/infiniband 2009-07-17 23:04:07 +01:00