summaryrefslogtreecommitdiffstats
Commit message (Collapse)AuthorAgeFilesLines
* IB/cm: Include HCA ACK delay in local ACK timeoutSean Hefty2007-07-105-18/+57
| | | | | | | | | | | The IB CM should include the HCA ACK delay when calculating the local ACK timeout value to use for RC QPs. If the HCA ACK delay is large enough relative to the packet life time, then if it is not taken into account, the calculated timeout value ends up being too small, which can result in "retry exceeded" errors. Signed-off-by: Sean Hefty <sean.hefty@intel.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
* IB/cm: Use spin_lock_irq() instead of spin_lock_irqsave() when possibleSean Hefty2007-07-101-96/+75
| | | | | | | | The ib_cm is a little over zealous about using spin_lock_irqsave, when spin_lock_irq would do. Signed-off-by: Sean Hefty <sean.hefty@intel.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
* IB/sa: Make sure SA queries use default P_KeySean Hefty2007-07-102-35/+53
| | | | | | | | | | | | MADs sent to the SA should use the the default P_Key (0x7fff/0xffff). There's no requirement that the default P_Key is stored at index 0 in the local P_Key table, so add code to the sa_query module to look up the index of the default P_Key when creating an address handle for the SA (which is done any time the P_Key table might change), and use this index for all SA queries. Signed-off-by: Sean Hefty <sean.hefty@intel.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
* IPoIB: Recycle loopback skbs instead of freeing and reallocatingRoland Dreier2007-07-101-16/+17
| | | | | | | | | | | | | | InfiniBand HCAs replicate multicast packets back to the QP that sent them if that QP is attached to the destination multicast group. This means that IPoIB multicasts are often replicated back to the receive queue of the interface that generated them. To avoid confusing the network stack, we drop these duplicates within the IPoIB driver. However, there's no reason to free the skb that received the duplicate and then immediately allocate a new skb to post to the receive queue. We can be more efficient and just repost the same skb. Signed-off-by: Roland Dreier <rolandd@cisco.com>
* IB/mthca: Replace memset(<addr>, 0, PAGE_SIZE) with clear_page(<addr>)Shani Moideen2007-07-102-2/+2
| | | | | | | Signed-off-by: Shani Moideen <shani.moideen@wipro.com> Signed-off-by: Roland Dreier <rolandd@cisco.com> ----
* IPoIB/cm: Fix warning if IPV6 is not enabledRoland Dreier2007-07-101-2/+1
| | | | | | | | | | | | Fix drivers/infiniband/ulp/ipoib/ipoib_cm.c:1151: warning: unused variable 'dev' by getting rid of the variable dev, which is only used if CONFIG_IPV6 is enabled, and replacing the one use of it with the value it is assigned, namely priv->dev. Signed-off-by: Roland Dreier <rolandd@cisco.com>
* IB/core: Take sizeof the correct pointer when calling kmalloc()Dotan Barak2007-07-101-1/+1
| | | | | | | | | When allocating out_mad in show_pma_counter(), take sizeof *out_mad instead of sizeof *in_mad. It is true that today the type of in_mad and out_mad are the same, but this patch will give us a cleaner code. Signed-off-by: Dotan Barak <dotanb@mellanox.co.il> Signed-off-by: Roland Dreier <rolandd@cisco.com>
* IB/ehca: Improve latency by unlocking after triggering the hardwareHoang-Nam Nguyen2007-07-091-3/+2
| | | | | | | | Kick the hardware before unlocking the send/receive queue to overlap processing a little more. Signed-off-by: Joachim Fenkes <fenkes@de.ibm.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
* IB/ehca: Notify consumers of LID/PKEY/SM changes after nondisruptive eventsJoachim Fenkes2007-07-094-31/+101
| | | | | | | | | | When firmware reports a nondisruptive port configuration change event, previous versions of the eHCA driver didn't forward the event to consumers like IPoIB. Add code that determines the type of configuration change by comparing old and new port attributes and reports it. Signed-off-by: Joachim Fenkes <fenkes@de.ibm.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
* IB/ehca: Return QP pointer in poll_cq()Joachim Fenkes2007-07-091-3/+8
| | | | | | | Also add two unlikely() statements. Signed-off-by: Joachim Fenkes <fenkes@de.ibm.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
* IB/ehca: Change idr spinlocks into rwlocksJoachim Fenkes2007-07-096-32/+28
| | | | | | | | This eliminates lock contention among IRQs as well as the need to disable IRQs around idr_find, because there are no IRQ writers. Signed-off-by: Joachim Fenkes <fenkes@de.ibm.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
* IB/ehca: Refactor sync between completions and destroy_cq using atomic_tJoachim Fenkes2007-07-095-39/+29
| | | | | | | | | | - ehca_cq.nr_events is made an atomic_t, eliminating a lot of locking. - The CQ is removed from the CQ idr first now to make sure no more completions are scheduled on that CQ. The "wait for all completions to end" code becomes much simpler this way. Signed-off-by: Joachim Fenkes <fenkes@de.ibm.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
* IB/ehca: Lock renaming, static initializersJoachim Fenkes2007-07-096-36/+27
| | | | | | | | | | | - Rename all spinlock flags to "flags", matching the vast majority of kernel code. - Move hcall_lock into the only file it's used in. - Replaced spin_lock_init() and friends with static initializers for global variables. Signed-off-by: Joachim Fenkes <fenkes@de.ibm.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
* IB/ehca: Report RDMA atomic attributes in query_qp()Hoang-Nam Nguyen2007-07-091-0/+3
| | | | | Signed-off-by: Joachim Fenkes <fenkes@de.ibm.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
* IB/ehca: Set SEND_GRH flag for all non-LL UD QPs on eHCA2Stefan Roscher2007-07-091-0/+11
| | | | | Signed-off-by: Joachim Fenkes <fenkes@de.ibm.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
* IB/ehca: Support UD low-latency QPsStefan Roscher2007-07-091-27/+57
| | | | | Signed-off-by: Joachim Fenkes <fenkes@de.ibm.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
* IB/ehca: add Shared Receive Queue supportJoachim Fenkes2007-07-099-107/+480
| | | | | | | | Support SRQs on eHCA2. Since an SRQ is a QP for eHCA2, a lot of code (structures, create, destroy, post_recv) can be shared between QP and SRQ. Signed-off-by: Joachim Fenkes <fenkes@de.ibm.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
* IB/ehca: QP code restructuring in preparation for SRQJoachim Fenkes2007-07-094-170/+166
| | | | | | | | | | | | | | - Replace init_qp_queues() by a shorter init_qp_queue(), eliminating duplicate code. - hipz_h_alloc_resource_qp() doesn't need a pointer to struct ehca_qp any longer. All input and output data is transferred through the parms parameter. - Change the interface to also support SRQ. Signed-off-by: Joachim Fenkes <fenkes@de.ibm.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
* IB/ehca: HW level, HW caps and MTU autodetectionJoachim Fenkes2007-07-095-11/+104
| | | | | | | | | | | In preparation for support of new eHCA2 features, change adapter probing: - Hardware level is changed to encode major and minor chip version - Hardware capabilities are queried from the firmware - The maximum MTU is queried from the firmware instead of assuming a fixed value Signed-off-by: Joachim Fenkes <fenkes@de.ibm.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
* IB/ehca: Change scaling_code parameter description to match default valueHoang-Nam Nguyen2007-07-091-1/+1
| | | | | Signed-off-by: Joachim Fenkes <fenkes@de.ibm.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
* IB/ipath: return correct PortGUID in NodeInfoSean Hefty2007-07-091-1/+1
| | | | | | | | | Return the PortGUID of the correct port when responding to a NodeInfo query. Returning the SystemImageGUID causes issues when there are multiple HCAs in a single system. Signed-off-by: Sean Hefty <sean.hefty@intel.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
* IB: Update mailing list addressRoland Dreier2007-07-091-3/+3
| | | | | | The InfiniBand / RDMA discussion list has moved. Signed-off-by: Roland Dreier <rolandd@cisco.com>
* IB/ipath: Remove bogus RD_ATOMIC checks from modify_qpArthur Jones2007-07-091-8/+0
| | | | | | | | | | The changeset 3859e39d ("IB/ipath: Support larger IB_QP_MAX_DEST_RD_ATOMIC and IB_QP_MAX_QP_RD_ATOMIC") added support for larger RD_ATOMIC values, but it failed to take out the stricter checks that were before these and hence had no effect. This patch takes out the bogus checks.... Signed-off-by: Arthur Jones <arthur.jones@qlogic.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
* IB/ipath: Test interrupts at driver startupArthur Jones2007-07-093-0/+31
| | | | | | | | | | All too often, interrupts do not get enabled for our card due to BIOS misconfiguration and other issues. This patch checks for that condition on startup and warns the user. This patch is based on work (check LID availability) by Robert Walsh. Signed-off-by: Arthur Jones <arthur.jones@qlogic.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
* IB/ipath: Remove support for preproduction HTX InfiniPath cardsRalph Campbell2007-07-094-48/+12
| | | | | | | Clean up some code by removing support for some older pre-production HTX InfiniPath cards. Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
* IB/ipath: Change version wording to be less confusing with release numberDave Olson2007-07-091-1/+1
| | | | | Signed-off-by: Dave Olson <dave.olson@qlogic.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
* IB/ipath: Lower default number of kernel send buffersRalph Campbell2007-07-091-1/+1
| | | | | | | | | The default calculation for the number of send buffers to allocate to the kernel was too high for the PCIe version of the chip thus leaving fewer than desired send buffers for user MPI applications. Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
* IB/ipath: Update MAINTAINERS entryArthur Jones2007-07-091-3/+4
| | | | | | | | | Bryan is no longer with QLogic and we now have a public git server and a public email alias for infinipath driver patches. And, as pointed out by Hal Rosenstock, the mailing list has changed as well. Signed-off-by: Arthur Jones <arthur.jones@qlogic.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
* IB/ipath: Be more cautious about coming out of freeze modeDave Olson2007-07-094-20/+80
| | | | | | | | | | We are more careful to be sure that we don't lose information about changes that occurred while we were in freeze mode, when the chip will not notify us, and try to avoid false error interrupts while doing cleanup. Put all of this logic in a new function ipath_clear_freeze(). Signed-off-by: Dave Olson <dave.olson@qlogic.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
* IB/ipath: Add barrier before updating WC head in shared memoryRalph Campbell2007-07-095-1/+12
| | | | | | | | | Add a barrier to make sure the CPU doesn't reorder writes to memory, since user programs can be polling on the head index update and the entry should be written before that. Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
* IB: Use menuconfig for InfiniBand menuJan Engelhardt2007-07-0910-17/+15
| | | | | | | | | | Change Kconfig objects from "menu, config" into "menuconfig" so that the user can disable the whole feature without having to enter the menu first. Signed-off-by: Jan Engelhardt <jengelh@gmx.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Roland Dreier <rolandd@cisco.com>
* RDMA/cxgb3: Check return of kmalloc() in iwch_register_device()WANG Cong2007-07-091-3/+4
| | | | | | | Signed-off-by: WANG Cong <xiyou.wangcong@gmail.com> [ Also remove cast from void * return of kmalloc() as suggested by Jesper Juhl <jesper.juhl@gmail.com>. ] Signed-off-by: Roland Dreier <rolandd@cisco.com>
* RDMA/cxgb3: Don't abort after failures sending the mpa replySteve Wise2007-07-091-1/+0
| | | | | | | | | | | | | | This bug results in an abort request being sent down _after_ the tid has been released. If the tid happens to have been reused, then the subsequent generation of the tid gets incorrectly aborted. The thread running iwch_accecpt_cr() must not abort a connection if an error is returned after being awakened. If any errors did occur while iwch_accept_cr() is blocked, then the connection has already been aborted on the thread processing the error. Signed-off-by: Steve Wise <swise@opengridcomputing.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
* RDMA/cxgb3: Don't post TID_RELEASE messageSteve Wise2007-07-091-3/+10
| | | | | | | | | | The LLD does this for us in cxgb3_remove_tid(). Also fixed active open failure cases where we also shouldn't be releasing the TID. Signed-off-by: Steve Wise <swise@opengridcomputing.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
* RDMA/cxgb3: ctrl-qp init/clear shouldn't set the gen bitSteve Wise2007-07-091-2/+2
| | | | | Signed-off-by: Steve Wise <swise@opengridcomputing.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
* RDMA/cxgb3: Don't count neg_adv abort_req_rss messages as real abortsSteve Wise2007-07-091-7/+7
| | | | | | | | Negative advice messages should _not_ count toward the 2 abort requests needed to indicate an abort request. Signed-off-by: Steve Wise <swise@opengridcomputing.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
* RDMA/cxgb3: TERMINATE WRs can hang the tx ofld queueSteve Wise2007-07-091-3/+3
| | | | | | | | Don't set the gen bits nor length bits in the terminate WR. This is done by the LLD driver. Signed-off-by: Steve Wise <swise@opengridcomputing.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
* RDMA/cxgb3: Streaming -> RDMA mode transition fixesSteve Wise2007-07-096-53/+38
| | | | | | | | | | | | | | | | | | Due to a HW issue, our current scheme to transition the connection from streaming to rdma mode is broken on the passive side. The firmware and driver now support a new transition scheme for the passive side: - driver posts rdma_init_wr (now including the initial receive seqno) - driver posts last streaming message via TX_DATA message (MPA start response) - uP atomically sends the last streaming message and transitions the tcb to rdma mode. - driver waits for wr_ack indicating the last streaming message was ACKed. NOTE: This change also bumps the required firmware version to 4.3. Signed-off-by: Steve Wise <swise@opengridcomputing.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
* mlx4_core: Get the maximum message size from reported device capabilitiesDotan Barak2007-07-095-1/+7
| | | | | | | | | | Get the maximum message size from the device capabilities returned from the QUERY_DEV_CAP firmware command, rather than hard-coding 2 GB. Signed-off-by: Dotan Barak <dotanb@dev.mellanox.co.il> Signed-off-by: Michael S. Tsirkin <mst@dev.mellanox.co.il> Signed-off-by: Roland Dreier <rolandd@cisco.com>
* IB/ipath: Update copyright datesJohn Gregor2007-07-0932-32/+32
| | | | | | | | Now that it's June, it's about time to update the copyright notices of files that have changed. Signed-off-by: John Gregor <john.gregor@qlogic.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
* IB/ipath: Clean send flags properly on QP resetRobert Walsh2007-07-091-1/+1
| | | | | | Signed-off-by: Robert Walsh <robert.walsh@qlogic.com> Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
* IB/ipath: ipath_poll fixups and enhancementsRobert Walsh2007-07-094-51/+131
| | | | | | | | | Fix ipath_poll and enhance it so we can poll for urgent packets or regular packets and receive notifications of when a header queue overflows. Signed-off-by: Robert Walsh <robert.walsh@qlogic.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
* IB/ipath: Send ACK invalid where appropriateRobert Walsh2007-07-092-10/+25
| | | | | | | | The IB specification ch. 9.9.3 table 58 says that a QP which isn't set up for the operation should return a NAK invalid request. Signed-off-by: Robert Walsh <robert.walsh@qlogic.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
* IB/ipath: Add capability to modify PBC wordMichael Albaugh2007-07-092-6/+52
| | | | | | | | | | | | | During compliance testing and when debugging some interconnect issues, it is very useful to be able to send malformed packets, without having the device signal them as malformed (drop, or terminate with EBP). The hardware supports this, but the driver "diagnostic packet" interface did not. Extend capability to send specific malformed packets for testing. Signed-off-by: Michael Albaugh <Michael.Albaugh@qlogic.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
* IB/ipath: Make handling of one subport consistentMark Debbage2007-07-091-2/+2
| | | | | | | | | | | | | Previously the driver and userspace code handled the case of 1 subport somewhat inconsistently. The new interpretation of this situation is that if one subport is requested, the driver turns on the subport mechanism and arranges for the port to be "shared" by one process. In normal use the userspace library does not use this configuration and instead arranges for the port not to be shared at all. This particular idiom can be useful for testing purposes. Signed-off-by: Mark Debbage <mark.debbage@qlogic.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
* IB/ipath: Correct checking of swminor version field when using subportsMark Debbage2007-07-091-9/+55
| | | | | | | | | | | | When subports are required to run a program, this patch checks that the driver and the userspace library have compatible subport implementations. This is achieved through checks on the swminor version field built into the driver and userspace library. Bad combinations are reported through syslog and result in an error when opening the port. Signed-off-by: Mark Debbage <mark.debbage@qlogic.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
* IB/ipath: Duplicate RDMA reads can cause responder to NAK inappropriatelyRalph Campbell2007-07-092-5/+34
| | | | | | | | | | | | | | | A duplicate RDMA read request can fool the responder into NAKing a new RDMA read request because the responder wasn't keeping track of whether the queue of RDMA read requests had been sent at least once. For example, requester sends 4 2K byte RDMA read requests, times out, and resends the first, then sees the 4 responses, then sends a 5th RDMA read or atomic operation. The responder sees the 4 requests, sends 4 responses, sees the resent 1st request, rewinds the queue, then sees the 5th request but thinks the queue is full and that the requester is invalidly sending a 5th new request. Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
* IB/ipath: Fix possible data corruption if multiple SGEs used for receiveRalph Campbell2007-07-093-2/+10
| | | | | | | | | | | | The code to copy data from the receive queue buffers to the IB SGEs doesn't check the SGE length, only the memory region/page length when copying data. This could overwrite parts of the user's memory that were not intended to be written. It can only happen if multiple SGEs are used to describe a receive buffer which almost never happens in practice. Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
* IB/ipath: Wait for PIO available interruptRalph Campbell2007-07-092-4/+3
| | | | | | | | | | The send function is called when posting new send work requests. There is no point in trying to send a packet if the QP is already waiting for a HW send buffer so don't clear the busy bit until the buffer available interrupt happens. Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
* IB/ipath: Fix RDMA read retry codeRalph Campbell2007-07-091-19/+38
| | | | | | | | | | | A RDMA read response or atomic response can ACK earlier sends and RDMA writes. In this case, the wrong work request pointer was being used to store the read first response or atomic result. Also, if a RDMA read request is retried, the code to compute which request to resend was incorrect. Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
OpenPOWER on IntegriCloud