- 25 Jan, 2008 40 commits
-
-
Hoang-Nam Nguyen authored
Signed-off-by: Hoang-Nam Nguyen <hnguyen@de.ibm.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
-
Erez Zilber authored
Add a .change_queue_depth handler to the scsi_host_template in the iSER driver. iscsi_change_queue_depth was added to iscsi_tcp in order to solve the problem of queue depth which was too high for some targets. It is also applicable for iSER. Signed-off-by: Erez Zilber <erezz@voltaire.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
-
Erez Zilber authored
Some RDMA CM events are not supported or not handled in iSER. This patch adds some info (printk) for the user about them. Signed-off-by: Erez Zilber <erezz@voltaire.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
-
Olaf Kirch authored
When a FMR is released via ib_fmr_pool_unmap(), the FMR usually ends up on the free_list rather than the dirty_list (because we allow a certain number of remappings before actually requiring a flush). However, ib_fmr_batch_release() only looks at dirty_list when flushing out old mappings. This means that when ib_fmr_pool_flush() is used to force a flush of the FMR pool, some dirty FMRs that have not reached their maximum remap count will not actually be flushed. Fix this by flushing all FMRs that have been used at least once in ib_fmr_batch_release(). Signed-off-by: Olaf Kirch <olaf.kirch@oracle.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
-
Olaf Kirch authored
Normally, the serial numbers for flush requests and flushes executed for an FMR pool should be in sync. However, if the FMR pool flushes dirty FMRs because the dirty_watermark was reached, we wake up the cleanup thread and let it do its stuff. As a side effect, the cleanup thread increments pool->flush_ser, which leaves it one higher than pool->req_ser. The next time the user calls ib_flush_fmr_pool(), the cleanup thread will be woken up, but ib_flush_fmr_pool() won't wait for the flush to complete because flush_ser is already past req_ser. This means the FMRs that the user expects to be flushed may not have all been flushed when the function returns. Fix this by telling the cleanup thread to do work exclusively by incrementing req_ser, and by moving the comparison of dirty_len and dirty_watermark into ib_fmr_pool_unmap(). Signed-off-by: Olaf Kirch <olaf.kirch@oracle.com>
-
Roland Dreier authored
In addition to being overly complex, the locking in user_mad.c is broken: there were multiple reports of deadlocks and lockdep warnings. In particular it seems that a single thread may end up trying to take the same rwsem for reading more than once, which is explicitly forbidden in the comments in <linux/rwsem.h>. To solve this, we change the locking to use plain mutexes instead of rwsems. There is one mutex per open file, which protects the contents of the struct ib_umad_file, including the array of agents and list of queued packets; and there is one mutex per struct ib_umad_port, which protects the contents, including the list of open files. We never hold the file mutex across calls to functions like ib_unregister_mad_agent(), which can call back into other ib_umad code to queue a packet, and we always hold the port mutex as long as we need to make sure that a device is not hot-unplugged from under us. This even makes things nicer for users of the -rt patch, since we remove calls to downgrade_write() (which is not implemented in -rt). Signed-off-by: Roland Dreier <rolandd@cisco.com>
-
Roland Dreier authored
There are a few places in the ipath driver where a variable is re-declared within a block where it is already in scope. Most of these extra declarations can simply be removed, since the variable from the outer scope is used in a way so that it does not need to keep its variable across the block with the re-declaration. Signed-off-by: Roland Dreier <rolandd@cisco.com>
-
Roland Dreier authored
t3_rdma_init_wr.irs is a big-endian field, so declare it as __be32. This fixes one sparse warning. Signed-off-by: Roland Dreier <rolandd@cisco.com>
-
Anton Blanchard authored
Use round_jiffies() to align ehca's 1-second timer with other timers and potentially save power by sleeping cores for longer. Signed-off-by: Anton Blanchard <anton@samba.org> Acked-by: Hoang-Nam Nguyen <hnguyen@de.ibm.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
-
Sean Hefty authored
By default, the responder_resources parameter is set to that received in a connection request. The passive side may override this value when accepting the connection. Use the value provided by the passive side when transitioning the QP to RTR state, rather than the value given in the connect request. Without this change, the RTR transition may fail if the passive side supports fewer responder_resources than that in the request. For code consistency and to protect against QP destruction, restructure overriding initiator_depth to match how responder_resources is set. Signed-off-by: Sean Hefty <sean.hefty@intel.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
-
Dave Olson authored
The original QHT7040 had significant performance issues so there was an additional check in the driver for a newer serial number. Support for the small quantities of that board shipped has been dropped, so this patch removes the special checks to simplify the code. Signed-off-by: Dave Olson <dave.olson@qlogic.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
-
Arthur Jones authored
Different chips have different width interrupt status registers, so add a flag and accessor function to decide which width register read to use. Signed-off-by: Arthur Jones <arthur.jones@qlogic.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
-
Ralph Campbell authored
The 6110 had a bug that caused some registers to be swapped; it was fixed for the 7220 (and didn't affect the 6120 because it had fewer registers). This adds a flag and related code to handle that, and includes some minor cleanups in the same area. Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
-
Ralph Campbell authored
The number of configured ports for the 7220 changes the number of eager TIDs available per port, for all but port 0 (kernel port) which remains constant, so add a field to give port0 count separate from the portdata structure. Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
-
Ralph Campbell authored
User registers have different alignments on different chips (4KB on older, 64KB on 7220). Allow mapping the user registers on kernels with page sizes up to 64K. Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
-
Dave Olson authored
Signed-off-by: Dave Olson <dave.olson@qlogic.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
-
Ralph Campbell authored
Various hardware counters are exported via the ipath file system (since it is binary data). The old file format was very dependent on the HW offsets for these registers. Newer HCA chips can have different counters at different offsets. This patch adds a level of indirection to make the file format consistent across HCAs. Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
-
Ralph Campbell authored
Add support for QLogic HCAs which have hardware performance sampling registers for PortSamplesControl and PortSamplesResult MADs. Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
-
David Dillow authored
When you have multiple targets, it gets really confusing when you try to track down who did a reset when there is no identifying information in the log message, especially when the same extension ID is mapped through two different local IB ports. So, add an identifier that can be used to track back to which local IB port/remote target pair is the one having problems. Signed-off-by: David Dillow <dillowda@ornl.gov> Acked-by: Pete Wyckoff <pw@osc.edu> Signed-off-by: Roland Dreier <rolandd@cisco.com>
-
Pradeep Satyanarayana authored
Some HCAs (such as ehca2) support SRQ, but only support fewer than 16 SG entries for SRQs. Currently IPoIB/CM implicitly assumes all HCAs will support 16 SG entries for SRQs (to handle a 64K MTU with 4K pages). This patch removes that restriction by limiting the maximum MTU in connected mode to what the maximum number of SRQ SG entries allows. This patch addresses <https://bugs.openfabrics.org/show_bug.cgi?id=728> Signed-off-by: Pradeep Satyanarayana <pradeeps@linux.vnet.ibm.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
-
David Dillow authored
By default, the SCSI mid-layer seems to send down 512KB requests (sg_tablesize = 256), with some requests occasionally combined. By allowing the mid-layer to chain requests, we can easily grow to 1024KB or larger -- I've tested 4096KB I/O requests with no problems. I looked through the DMA paths on the hardware drivers to ensure they could take advantage of the SG chaining, and it seems that every one except ipath uses the system's DMA routines, which have been converted to handle chaining. ipath looks like it should be OK, but I have no way to test it. Signed-off-by: David Dillow <dillowda@ornl.gov> [ Tested on ipath. - Roland ] Signed-off-by: Roland Dreier <rolandd@cisco.com>
-
David Dillow authored
The current SRP initiator will send requests even if it has no credits available. The results of sending extra requests are vendor specific, but on some devices, overrunning credits will cost 85% of peak performance -- e.g. 100 MB/s vs 720 MB/s. Other devices may just drop the requests. This patch will tell the SCSI midlayer to queue requests if there are fewer than two credits remaining, and will not issue a task management request if there are no credits remaining. The mid-layer will retry the queued command once an outstanding command completes. The patch also removes the unlikely() in __srp_get_tx_iu(), as it is not at all unlikely to hit this limit under heavy load. Signed-off-by: David Dillow <dillowda@ornl.gov> Signed-off-by: Roland Dreier <rolandd@cisco.com>
-
Rolf Manderscheid authored
An IPoIB subnet on an IB fabric that spans multiple IB subnets can't use link-local scope in multicast GIDs. The existing routines that map IP/IPv6 multicast addresses into IB link-level addresses hard-code the scope to link-local, and they also leave the partition key field uninitialised. This patch adds a parameter (the link-level broadcast address) to the mapping routines, allowing them to initialise both the scope and the P_Key appropriately, and fixes up the call sites. The next step will be to add a way to configure the scope for an IPoIB interface. Signed-off-by: Rolf Manderscheid <rvm@obsidianresearch.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
-
Dave Olson authored
This patch moves some arrays that were defined per-device to be variables defined in the per context data structure, thus avoiding extra kzalloc() calls. Signed-off-by: Dave Olson <dave.olson@qlogic.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
-
Dave Olson authored
In preparation for upcoming chips that have different values for INFINIPATH_R_PORTENABLE_SHIFT, INFINIPATH_R_INTRAVAIL_SHIFT, INFINIPATH_R_TAILUPD_SHIFT, and portcfg_shift, remove the shared #defines and use device-specific variables instead. Signed-off-by: Dave Olson <dave.olson@qlogic.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
-
Ralph Campbell authored
kreceive is now portdata * instead of devdata * and other kreceive related cleanups.... Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
-
Ralph Campbell authored
Remove an unused parameter and fix up the comment. Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
-
Ralph Campbell authored
This patch fixes a couple of minor problems with RNR NAK handling: - The insertion sort was causing extra delay when inserting ahead vs. behind an existing entry on the list. - A resend of a first packet of a message which is still not ready, needs another RNR NAK (i.e., it was suppressed when it shouldn't). - Also, the resend tasklet doesn't need to be woken up unless the ACK/NAK actually indicates progress has been made. Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
-
Hoang-Nam Nguyen authored
This patch allows ehca to forward event client-reregister-required to registered clients. One such event is generated by a switch eg. after its reboot. Signed-off-by: Hoang-Nam Nguyen <hnguyen@de.ibm.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
-
Roland Dreier authored
Rather than byte-swapping cqe->g_mlpath_rqpn each time we extract a field from it, byte-swap it once into a temporary variable. This results in smaller, better code -- eg, on 32-bit x86: add/remove: 0/0 grow/shrink: 0/1 up/down: 0/-5 (-5) function old new delta mlx4_ib_poll_cq 1188 1183 -5 Signed-off-by: Roland Dreier <rolandd@cisco.com>
-
Adrian Bunk authored
Remove MSI support from the mthca driver, as scheduled. There is no reason to use MSI instead of MSI-X, since MSI-X performs better. No one has spoken up since MSI support was deprecated in commit f6be6fbe ("IB/mthca: Schedule MSI support for removal"), so apparently the MSI support is unused. Signed-off-by: Adrian Bunk <bunk@kernel.org> Signed-off-by: Roland Dreier <rolandd@cisco.com>
-
Oliver Pinter authored
Signed-off-by: Oliver Pinter <oliver.pntr@gmail.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
-
Erez Zilber authored
Signed-off-by: Erez Zilber <erezz@voltaire.com>
-
Sean Hefty authored
This is based on user feedback from Doug Ledford at RedHat: Events that occur on an rdma_cm_id are reported to userspace through an event channel. Connection request events are reported on the event channel associated with the listen. When the connection is accepted, a new rdma_cm_id is created and automatically uses the listen event channel. This is suboptimal where the user only wants listen events on that channel. Additionally, it may be desirable to have events related to connection establishment use a different event channel than those related to already established connections. Allow the user to migrate an rdma_cm_id between event channels. All pending events associated with the rdma_cm_id are moved to the new event channel. Signed-off-by: Sean Hefty <sean.hefty@intel.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
-
Vladimir Sokolovsky authored
Enable conn_id remove on the passive side after connection establishment. This corrects an issue where the IB driver can't be unloaded after running applications over RDS. The 'dev_remove' counter does not reach 0 for established connections on the passive side. This problem is limited to device removal, and only occurs on the passive side if there are established connections. Signed-off-by: Vladimir Sokolovsky <vlad@mellanox.co.il> Reviewed-by: Sean Hefty <sean.hefty@intel.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
-
Sean Hefty authored
In cancel_mads(), MADs are moved from the wait_list and local_list to a cancel_list for processing. However, the structures on these two lists are not the same. The wait_list references struct ib_mad_send_wr_private, but local_list references struct ib_mad_local_private. Cancel_mads() treats all items moved to the cancel_list as struct ib_mad_send_wr_private. This leads to a system crash when requests are moved from the local_list to the cancel_list. Fix this by leaving local_list alone. All requests on the local_list have completed are just awaiting processing by a queued worker thread. Bug (crash) reported by Dotan Barak <dotanb@dev.mellanox.co.il>. Problem with local_list access reported by Robert Reynolds <rreynolds@opengridcomputing.com>. Signed-off-by: Sean Hefty <sean.hefty@intel.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
-
Sean Hefty authored
Add performance/debug counters to track sent/received messages, retries, and duplicates. Counters are tracked per CM message type, per port. The counters are always enabled, so intrusive state tracking is not done. Signed-off-by: Sean Hefty <sean.hefty@intel.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
-
Sean Hefty authored
To allow ULPs to tune timeout values and capture retry statistics, report the number of times that a mad send operation was retried. For RMPP mads, report the total number of times that the any portion (send window) of the send operation was retried. Signed-off-by: Sean Hefty <sean.hefty@intel.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
-
Sean Hefty authored
P_key changes can invalidate multicast groups. Report errors on all multicast groups affected by a pkey change. Signed-off-by: Sean Hefty <sean.hefty@intel.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
-
Joe Perches authored
Signed-off-by: Joe Perches <joe@perches.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
-