aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/infiniband (follow)
AgeCommit message (Collapse)AuthorFilesLines
2007-04-26Revert "[POWERPC] Rename get_property to of_get_property: drivers"Paul Mackerras1-1/+1
This reverts commit d05c7a80cf39ae7d0f8d0c3e47c93d51fcd393d3, which included changes which should go via other subsystem maintainers.
2007-04-13[POWERPC] Rename get_property to of_get_property: driversStephen Rothwell1-1/+1
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2007-04-13[POWERPC] get_property returns constStephen Rothwell1-2/+2
This just tidies up some of the remains. Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by: Paul Mackerras <paulus@samba.org>
2007-04-10IPoIB/cm: Fix DMA direction typoMichael S. Tsirkin1-1/+1
Receive buffers need to be mapped with DMA_FROM_DEVICE. Incorrectly mapping with DMA_TO_DEVICE causes a hard lock on ppc64 machines with an IOMMU. This fixes <https://bugs.openfabrics.org/show_bug.cgi?id=431> Signed-off-by: Michael S. Tsirkin <mst@dev.mellanox.co.il> Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-04-05IB/iser: Don't defer connection failure notification to workqueueErez Zilber2-25/+16
When a connection is terminated asynchronously from the iSCSI layer's perspective, iSER needs to notify the iSCSI layer that the connection has failed. This is done using a workqueue (switched to from the iSER tasklet context). Meanwhile, the connection object (that holds the work struct) is released. If the workqueue function wasn't called yet, it will be called later with a NULL pointer, which will crash the kernel. The context switch (tasklet to workqueue) is not required, and everything can be done from the iSER tasklet. This eliminates the NULL work struct bug (and simplifies the code). Signed-off-by: Erez Zilber <erezz@voltaire.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-03-28Merge branch 'for-linus' of master.kernel.org:/pub/scm/linux/kernel/git/roland/infinibandLinus Torvalds3-14/+19
* 'for-linus' of master.kernel.org:/pub/scm/linux/kernel/git/roland/infiniband: IB/iser: Handle aborting a command after it is sent IB/mthca: Fix thinko in init_mr_table() RDMA/cxgb3: Fix resource leak in cxio_hal_init_ctrl_qp()
2007-03-26IB/iser: Handle aborting a command after it is sentErez Zilber1-8/+9
The SCSI midlayer may abort a command that was already sent. If the initiator is still trying to send the command (or data-out PDUs for that command), the QP may time out after the midlayer times out. Therefore, when aborting the command, iSER may still have references for the command's buffers. When sending these PDUs, the sends will complete with an error and their resources will be released then. Signed-off-by: Erez Zilber <erezz@voltaire.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-03-26IB/mthca: Fix thinko in init_mr_table()Michael S. Tsirkin1-2/+2
Commit c20e20ab ("IB/mthca: Merge MR and FMR space on 64-bit systems") swapped the number of MTTs and MPTs when initializing the MR table. As a result, we get a kernel oops when the number of MTT segments allocated exceeds 0x20000. Noted by Troy Benjegerdes <troy@scl.ameslab.gov>, and reproduced by Dotan Barak <dotanb@mellanox.co.il>. This fixes https://bugs.openfabrics.org/show_bug.cgi?id=490 Signed-off-by: Michael S. Tsirkin <mst@dev.mellanox.co.il> Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-03-26RDMA/cxgb3: Fix resource leak in cxio_hal_init_ctrl_qp()Steve Wise1-4/+8
This was spotted by the Coverity checker (CID 1554). Signed-off-by: Steve Wise <swise@opengridcomputing.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-03-25[NET]: Fix neighbour destructor handling.Alexey Kuznetsov1-3/+3
->neigh_destructor() is killed (not used), replaced with ->neigh_cleanup(), which is called when neighbor entry goes to dead state. At this point everything is still valid: neigh->dev, neigh->parms etc. The device should guarantee that dead neighbor entries (neigh->dead != 0) do not get private part initialized, otherwise nobody will cleanup it. I think this is enough for ipoib which is the only user of this thing. Initialization private part of neighbor entries happens in ipib start_xmit routine, which is not reached when device is down. But it would be better to add explicit test for neigh->dead in any case. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-03-22IB/ipoib: Fix thinko in packet length checksMichael S. Tsirkin2-3/+3
The packet length checks in ipoib are broken: we add 4 bytes (IPoIB encapsulation header) when sending a packet, not 20 bytes (hardware address length) to each packet. Therefore, if connected mode is enabled so that the interface MTU is larger than the multicast MTU, IPoIB may end up trying to send too-long multicast packets. For example, multicast is broken if a message of size 2048 bytes is sent on an interface with UD MTU 2048, because 2048 is bigger than the real limit of 2044 but the code tests against the wrong limit of 2060. This patch fixes <https://bugs.openfabrics.org/show_bug.cgi?id=418>, submitted by Scott Weitzenkamp <sweitzen@cisco.com>. Signed-off-by: Michael S. Tsirkin <mst@dev.mellanox.co.il> Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-03-22IPoIB: Fix use-after-free in path_rec_completion()Michael S. Tsirkin1-2/+2
The connected mode code added the possibility that an neigh struct gets freed in the list_for_each_entry() loop in path_rec_completion(), which causes a use-after-free. Fix this by changing to the _safe variant of the list walking macro. This was spotted by the Coverity checker (CID 1567). Signed-off-by: Michael S. Tsirkin <mst@dev.mellanox.co.il> Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-03-22IB/ehca: Make scaling code work without CPU hotplugJoachim Fenkes1-0/+8
eHCA scaling code must not depend on register_cpu_notifier() if CONFIG_HOTPLUG_CPU is not set, so put all related code into #ifdefs. Signed-off-by: Joachim Fenkes <fenkes@de.ibm.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-03-22RDMA/cxgb3: Handle build_phys_page_list() failure in iwch_reregister_phys_mem()Steve Wise1-1/+4
Signed-off-by: Steve Wise <swise@opengridcomputing.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-03-22IB/ipath: Check return value of lookup_one_lenBryan O'Sullivan1-1/+15
This fixes kernel.org bug 8003. Signed-off-by: Bryan O'Sullivan <bryan.osullivan@qlogic.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-03-22IPoIB: Fix race in detaching from mcast group before attachingSean Hefty1-3/+3
There's a race between ipoib_mcast_leave() and ipoib_mcast_join_finish() where we can try to detach from a multicast group before we've attached to it. Fix this by reordering the code in ipoib_mcast_leave to free the multicast group first, which waits for the multicast callback thread (which calls ipoib_mcast_join_finish()) to complete before detaching from the group. Signed-off-by: Sean Hefty <sean.hefty@intel.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-03-22IPoIB/cm: Fix reaping of stale connectionsMichael S. Tsirkin1-1/+1
The sense of the time_after_eq() test in ipoib_cm_stale_task() is reversed so that only non-stale connections are reaped. Fix this by changing to time_before_eq(). Noticed by Pradeep Satyanarayana <pradeep@us.ibm.com>. Signed-off-by: Michael S. Tsirkin <mst@dev.mellanox.co.il> Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-03-14[PATCH] fix ipath_dma_free_coherent() prototypeAl Viro1-1/+1
method gets u64, not dma_addr_t Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-03-08IPoIB: Turn on interface's carrier after broadcast group is joinedShirley Ma1-1/+4
Do netif_carrier_on() right after the IPv4 broadcast multicast group is joined, rather than waiting for all of the initial set of multicast group joins to finish. This allows at least IPv4 traffic to limp along on broken fabrics where not all multicast groups can be joined. Signed-off-by: Shirley Ma <xma@us.ibm.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-03-06RDMA/ucma: Avoid sending reject if backlog is fullSean Hefty1-1/+1
Change the returned error code to ENOMEM if the connection event backlog is full. This prevents the ib_cm from issuing a reject on the connection, which can allow retries to succeed. Signed-off-by: Sean Hefty <sean.hefty@intel.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-03-06RDMA/cxgb3: Fix MR permission problemsSteve Wise3-41/+18
Fix memory region permission problems: - remove useless and redundant iwch_mem_perms enum. - create ib_to_tpt_access_rights() for mapping ib access rights to T3 TPT permissions. - create ib_to_mwbind_access_rights() for mapping ib access rights to T3 MWBIND WR permissions. - fix up the mem reg code to utilize the new functions. Signed-off-by: Steve Wise <swise@opengridcomputing.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-03-06RDMA/cxgb3: Don't reuse skbs that are non-linear or clonedSteve Wise1-2/+1
Signed-off-by: Steve Wise <swise@opengridcomputing.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-03-06RDMA/cxgb3: Squelch logging AE errorsSteve Wise1-6/+6
Only print one AE error for a given connection in the kernel log. Signed-off-by: Steve Wise <swise@opengridcomputing.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-03-06RDMA/cxgb3: Stop EP timer when MPA exchange is aborted by peerSteve Wise1-0/+2
Stop the endpoint timer when the MPA exchange is aborted by the peer. Signed-off-by: Steve Wise <swise@opengridcomputing.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-03-06RDMA/cxgb3: Move QP to error on destroy if the state is IDLESteve Wise1-4/+2
Change iwch_destroy_qp() to always move the QP to ERROR and let iwch_modify_qp() decide what to do. Signed-off-by: Steve Wise <swise@opengridcomputing.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-03-06RDMA/cxgb3: Fixes for "normal close" failuresSteve Wise1-4/+7
Fixes for "normal close" failures: - Start normal close timer when moving to CLOSING state. - Handle ABORTING state in close_con_rpl(). - Stop timer correctly on abort during a normal close. Signed-off-by: Steve Wise <swise@opengridcomputing.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-03-06RDMA/cxgb3: Fix build on sparc64David Miller1-0/+1
cxgb3 uses dma_alloc_coherent() et al. thus needs linux/dma-mapping.h include in order to build reliably. Noticed on sparc64. Signed-off-by: David S. Miller <davem@davemloft.net> Acked-by: Steve Wise <swise@opengridcomputing.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-03-06RDMA/cma: Initialize rdma_bind_list in cma_alloc_any_port()Sean Hefty1-1/+1
The struct rdma_bind_list fields for hlist are not being initialized, resulting in a corrupted list. Fix this by using kzalloc() to make sure all pointers are NULL. Signed-off-by: Sean Hefty <sean.hefty@intel.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-03-06RDMA/cxgb3: Don't use mm after it's freed in iwch_mmap()Steve Wise1-4/+6
Signed-off-by: Steve Wise <swise@opengridcomputing.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-03-06RDMA/cxgb3: Start ep timer on a MPA rejectSteve Wise1-2/+1
If the consumer rejects the connection we end up under-referencing the endpoint structure. The fix is to call iwch_ep_disconnect() instead of the low level disconnect functions so that the endpoint close timer is started correctly. Signed-off-by: Steve Wise <swise@opengridcomputing.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-03-01IB/mthca: Fix error path in mthca_alloc_memfree()Roland Dreier1-5/+5
The garbled logic in mthca_alloc_memfree() causes it to return 0, even if it fails to allocate all doorbell records. Fix it to return -ENOMEM when it fails. Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-03-01IB/ehca: Fix sync between completion handler and destroy cqHoang-Nam Nguyen4-25/+60
This patch fixes two issues reported by Roland Dreier and Christoph Hellwig: - Mismatched sync/locking between completion handler and destroy cq We introduced a counter nr_events per cq to track number of irq events seen. This counter is incremented when an event queue entry is seen and decremented after completion handler has been called regardless if scaling code is active or not. Note that nr_callbacks tracks number of events assigned to a cpu and both counters can potentially diverge. The sync between running completion handler and destroy cq is done by using the global spin lock ehca_cq_idr_lock. - Replace yield by wait_event on the counter above to become zero. Signed-off-by: Hoang-Nam Nguyen <hnguyen@de.ibm.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-02-27IPoIB: Only handle async events for one portRoland Dreier1-6/+7
An asynchronous event carries the port number that the event occurred on, so there's no reason for an IPoIB interface to process an event associated with a different local HCA port. Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-02-26IPoIB: Correct debugging output when path record lookup failsRoland Dreier1-1/+1
If path_rec_completion() is passed a non-NULL path record pointer along with an unsuccessful status value, the tracing code incorrectly prints the (invalid) DLID from the path record rather than the more interesting status code. The actual logic of the function correctly uses the path record only if the status indicates a successful lookup. Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-02-23RDMA/cxgb3: Stop the EP Timer on BAD CLOSESteve Wise1-0/+1
Stop the ep timer in ec_status() if the status indicates a bad close. Signed-off-by: Steve Wise <swise@opengridcomputing.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-02-23RDMA/cxgb3: cleanupsAdrian Bunk8-61/+27
- don't mark static functions in C files as inline - gcc should know best whether inlining makes sense - never compile the unused cxio_dbg.c - make the following needlessly global functions static: - cxio_hal.c: cxio_hal_clear_qp_ctx() - iwch_provider.c: iwch_get_qp() - remove the following unused global functions: - cxio_hal.c: cxio_allocate_stag() - cxio_resource.: cxio_hal_get_rhdl() - cxio_resource.: cxio_hal_put_rhdl() Signed-off-by: Adrian Bunk <bunk@stusta.de> Acked-by: Steve Wise <swise@opengridcomputing.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-02-22RDMA/cma: Remove unused node_guid from cma_device structureSean Hefty1-2/+0
Signed-off-by: Sean Hefty <sean.hefty@intel.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-02-22IB/cm: Remove ca_guid from cm_device structureSean Hefty1-6/+4
The cm_device references an ib_device, which already contains the node_guid. Signed-off-by: Sean Hefty <sean.hefty@intel.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-02-22RDMA/cma: Request reversible paths onlySean Hefty1-1/+3
The rdma_cm requires that path records be reversible. Set the reversible bit when issuing an path record query. Signed-off-by: Sean Hefty <sean.hefty@intel.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-02-22IB/core: Set hop limit in ib_init_ah_from_wc correctlySean Hefty1-1/+1
The hop_limit value in the ah_attr should be 0xFF, not the value read from the received GRH (which should be 0). See 13.5.4.4 in the 1.2 IB spec. Signed-off-by: Sean Hefty <sean.hefty@intel.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-02-22IB/uverbs: Return correct error for invalid PD in register MRRoland Dreier1-1/+3
If no matching PD is found in ib_uverbs_reg_mr(), then the function jumps to err_release without setting the return value ret. This means that ret will hold the return value of the call to ib_umem_get() a few lines earlier; if the function reaches the point where it looks for the PD, we know that ib_umem_get() must have returned 0, so ib_uverbs_reg_mr() ends up return 0 for a bad PD ID. Fix this by setting ret to -EINVAL before jumping to the exit path when no PD is found. Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-02-21IPoIB: Remove unused local_rate trackingRoland Dreier2-6/+3
Now that low-level drivers handle the conversion from an absolute rate to a relative rate, there's no need for the IPoIB driver to keep track of the local port's data rate. Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-02-20IPoIB/cm: Improve small message bandwidthMichael S. Tsirkin1-19/+27
Avoid the overhead of freeing/reallocating and mapping/unmapping for DMA pages that have not been written to by hardware. Signed-off-by: Michael S. Tsirkin <mst@mellanox.co.il> Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-02-20IB/mthca: Make 2 functions staticAdrian Bunk1-4/+6
This patch makes the needlessly global functions mthca_tavor_write_mtt_seg() and mthca_arbel_write_mtt_seg() static. Signed-off-by: Adrian Bunk <bunk@stusta.de> Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-02-19Merge git://git.kernel.org/pub/scm/linux/kernel/git/bunk/trivialLinus Torvalds2-2/+2
* git://git.kernel.org/pub/scm/linux/kernel/git/bunk/trivial: (25 commits) Documentation/kernel-docs.txt update. arch/cris: typo in KERN_INFO Storage class should be before const qualifier kernel/printk.c: comment fix update I/O sched Kconfig help texts - CFQ is now default, not AS. Remove duplicate listing of Cris arch from README kbuild: more doc. cleanups doc: make doc. for maxcpus= more visible drivers/net/eexpress.c: remove duplicate comment add a help text for BLK_DEV_GENERIC correct a dead URL in the IP_MULTICAST help text fix the BAYCOM_SER_HDX help text fix SCSI_SCAN_ASYNC help text trivial documentation patch for platform.txt Fix typos concerning hierarchy Fix comment typo "spin_lock_irqrestore". Fix misspellings of "agressive". drivers/scsi/a100u2w.c: trivial typo patch Correct trivial typo in log2.h. Remove useless FIND_FIRST_BIT() macro from cardbus.c. ...
2007-02-17Various typo fixes.Robert P. J. Day2-2/+2
Correct mis-spellings of "algorithm", "appear", "consistent" and (shame, shame) "kernel". Signed-off-by: Robert P. J. Day <rpjday@mindspring.com> Signed-off-by: Adrian Bunk <bunk@stusta.de>
2007-02-16IB/core: Set static rate in ib_init_ah_from_path()Roland Dreier1-0/+1
The static rate from the path record should be put into the address vector -- a long time ago the rate in the address attributes needed to be a relative rate, which required more munging, but now that the conversion from absolute to relative is done in the low-level driver, it's easy for ib_init_ah_from_path() to put the absolute rate in. Cc: Jason Gunthorpe <jgunthorpe@obsidianresearch.com> Cc: Sean Hefty <sean.hefty@intel.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-02-16IB/ipath: Make ipath_map_sg() staticRoland Dreier1-2/+2
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-02-16IB/core: Fix sparse warnings about shadowed declarationsRoland Dreier2-4/+2
Change a couple of variable names to avoid sparse warnings about symbols being shadowed. Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-02-16RDMA/cma: Add multicast communication supportSean Hefty2-47/+516
Extend rdma_cm to support multicast communication. Multicast support is added to the existing RDMA_PS_UDP port space, as well as a new RDMA_PS_IPOIB port space. The latter port space allows joining the multicast groups used by IPoIB, which enables offloading IPoIB traffic to a separate QP. The port space determines the signature used in the MGID when joining the group. The newly added RDMA_PS_IPOIB also allows for unicast operations, similar to RDMA_PS_UDP. Supporting the RDMA_PS_IPOIB requires changing how UD QPs are initialized, since we can no longer assume that the qkey is constant. This requires saving the Q_Key to use when attaching to a device, so that it is available when creating the QP. The Q_Key information is exported to the user through the existing rdma_init_qp_attr() interface. Multicast support is also exported to userspace through the rdma_ucm. Signed-off-by: Roland Dreier <rolandd@cisco.com>
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.