aboutsummaryrefslogtreecommitdiff
path: root/drivers/infiniband/hw
AgeCommit message (Collapse)AuthorFilesLines
2011-01-10IB/qib: Improve SERDES tunning on QMH boardsMike Marciniszyn1-3/+23
Improve the QMH SERDES tunning on initial driver load by having the driver go through a link state change. Signed-off-by: Mike Marciniszyn <[email protected]> Signed-off-by: Roland Dreier <[email protected]>
2011-01-10IB/qib: Unnecessary delayed completions on RC connectionMike Marciniszyn1-0/+24
Currently on receipt of a response message (ACKs, RDMA Response, Atomic Responses etc.) if the SDMA completion counter is not advanced the driver delays the completion of the WQE. In most cases this is overly pessimistic as the response (ACK) to a previously transmitted send implies that the send is complete. Ensure that SDMA queue is progressed appropriately before determining if a send has delayed completions. Signed-off-by: Mike Marciniszyn <[email protected]> Signed-off-by: Roland Dreier <[email protected]>
2011-01-10IB/qib: Issue pre-emptive NAKs on eager buffer overflowMike Marciniszyn1-4/+137
Under congestion resulting in eager buffer overflow attempt to send pre-emptive NAKs if header queue entries with TID errors are generated and a valid header is present. This prevents long timeouts and flow restarts if a trailing set of packets are dropped due to eager overflows. Pre-emptive NAKs are currently only supported for RDMA writes. Signed-off-by: Mike Marciniszyn <[email protected]> Signed-off-by: Roland Dreier <[email protected]>
2011-01-10IB/qib: RDMA lkey/rkey validation is inefficient for large MRsMike Marciniszyn3-23/+60
The current code loops during rkey/lkey validiation to isolate the MR for the RDMA, which is expensive when the current operation is inside a very large memory region. This fix optimizes rkey/lkey validation routines for user memory regions and fast memory regions. The MR entry can be isolated by shifts/mods instead of looping. The existing loop is preserved for phys memory regions for now. Signed-off-by: Mike Marciniszyn <[email protected]> Signed-off-by: Roland Dreier <[email protected]>
2011-01-10IB/qib: Change QPN incrementMike Marciniszyn1-1/+1
Changing from +1 to +2 allows for better QP distribution across receive contexts. Signed-off-by: Mike Marciniszyn <[email protected]> Signed-off-by: Roland Dreier <[email protected]>
2011-01-10IB/qib: Add fix missing from earlier patchMike Marciniszyn1-31/+24
The upstream code was missing part of a receive/error race fix from the internal tree. Add the missing part, which makes future merges possible. Signed-off-by: Mike Marciniszyn <[email protected]> Signed-off-by: Roland Dreier <[email protected]>
2011-01-10IB/qib: Change receive queue/QPN selectionMike Marciniszyn4-31/+15
The basic idea is that on SusieQ, the difficult part of mapping QPN to context is handled by the mapping registers so the generic QPN allocation doesn't need to worry about chip specifics. For Monty and Linda, there is no mapping table so the qpt->mask (same as dd->qpn_mask), is used to see if the QPN to context falls within [zero..dd->n_krcv_queues). Signed-off-by: Mike Marciniszyn <[email protected]> Signed-off-by: Roland Dreier <[email protected]>
2011-01-10IB/qib: Fix interrupt mitigationMike Marciniszyn5-8/+12
For SusieQ we need to write to the interrupt timer register before updating the header queue head with interrupt count. This is to ensure that the timer is enabled properly and a receive available interrupt is delivered. Otherwise this interrupt can be lost if the receiver header/eager queues are full before the timer is enabled. Signed-off-by: Mike Marciniszyn <[email protected]> Signed-off-by: Roland Dreier <[email protected]>
2011-01-10IB/qib: Avoid duplicate writes to the rcv head registerMike Marciniszyn1-1/+9
Avoid duplicate writes to the head register as this can lead to lost interrupts if the context goes full before the second write is done. Signed-off-by: Mike Marciniszyn <[email protected]> Signed-off-by: Roland Dreier <[email protected]>
2011-01-10IB/qib: Add a few new SERDES tuningsMike Marciniszyn1-3/+26
Add new SERDES tuning to aid manufacturing. Signed-off-by: Mike Marciniszyn <[email protected]> Signed-off-by: Roland Dreier <[email protected]>
2011-01-10IB/qib: Reset packet list after freeingMike Marciniszyn1-0/+1
Reset the list pointers after freeing the SDMA packet list. This is done to any potential double-free cases. Signed-off-by: Mike Marciniszyn <[email protected]> Signed-off-by: Roland Dreier <[email protected]>
2011-01-10IB/qib: New SERDES init routine and improvements to SI qualityMike Marciniszyn1-15/+255
Implement new SERDES initialization routine and improvements to signal integrity -- disable LE1 adaptation, disable LOS after link-up, set better SERDES parameters. Signed-off-by: Mike Marciniszyn <[email protected]> Signed-off-by: Roland Dreier <[email protected]>
2011-01-10IB/qib: Clear WAIT_SEND flags when setting QP to error stateMike Marciniszyn1-0/+4
If these flags are set when the QP is transitioned to the error state, it will wait until the flags are cleared, which may never happen if the error transition is due to a link going down. Signed-off-by: Mike Marciniszyn <[email protected]> Signed-off-by: Roland Dreier <[email protected]>
2011-01-10IB/qib: Fix context allocation with multiple HCAsMike Marciniszyn1-5/+5
The driver was incorrectly choosing HCAs on which to allocate new user contexts based on overall count of usable ports regardless whether the usable port was on the currently selected HCA. Signed-off-by: Mike Marciniszyn <[email protected]> Signed-off-by: Roland Dreier <[email protected]>
2011-01-10IB/qib: Fix multi-Florida HCA host panic on rebootMike Marciniszyn1-2/+4
Add check when setting configured contexts that the value does not exceed the number of contexts allocated for the card. If the value exceeds the already allocated count, set it to what is already allocated. Signed-off-by: Mike Marciniszyn <[email protected]> Signed-off-by: Roland Dreier <[email protected]>
2011-01-10IB/qib: Handle transitions from ACTIVE_DEFERRED to ACTIVE betterMike Marciniszyn1-1/+2
When the link transitions from ACTIVE_DEFERRED to ACTIVE, the driver only sees the ACTIVE state. With this change, it will check whether the state was already ACTIVE and if so, it will not generated IB events and will not clear symbol error counts. Signed-off-by: Mike Marciniszyn <[email protected]> Signed-off-by: Roland Dreier <[email protected]>
2011-01-10IB/qib: UD send with immediate receive completion has wrong sizeMike Marciniszyn1-1/+1
The code to generate receive completion entries for UD send with immediate contains the wrong payload length. This is because when the code to compute the payload size was moved, the value of hdrsize didn't get moved too. The fix is to update tlen directly. Signed-off-by: Mike Marciniszyn <[email protected]> Signed-off-by: Roland Dreier <[email protected]>
2011-01-10IB/qib: Set port physical state even if other fields are invalidMike Marciniszyn1-20/+25
The IBTA vol. 1 release 1.2.1 spec. says: C14-24.2.1: If PortInfo:Portstate=Down, then a SubnSet(PortInfo) shall make any changes it specifies to PortInfo:PortPhysicalState; any other result is vendor-dependent. The patch changes the error handling so that the reply says there are invalid fields but still attempts to set fields that are in range including PortInfo:PortPhysicalState. Signed-off-by: Mike Marciniszyn <[email protected]> Signed-off-by: Roland Dreier <[email protected]>
2011-01-10IB/qib: Generate completion callback on errorsMike Marciniszyn1-1/+2
According to IBTA vol. 1, C11-30.1.1, a notification callback is invoked if the CQ is armed for the next solicited completion event or an error completion. The error case wasn't being generated correctly. Signed-off-by: Mike Marciniszyn <[email protected]> Signed-off-by: Roland Dreier <[email protected]>
2011-01-10IB/qib: Add support for the new QME7362 cardMike Marciniszyn1-0/+4
Add support to recognize another board variation named QME7362. Signed-off-by: Mike Marciniszyn <[email protected]> Signed-off-by: Roland Dreier <[email protected]>
2011-01-10IB/qib: Add receive header queue size module parametersMike Marciniszyn1-4/+24
The receive header queue sizes need to modified for performance tuning. Three module parameters are added to support this. Signed-off-by: Mike Marciniszyn <[email protected]> Signed-off-by: Roland Dreier <[email protected]>
2011-01-10IB/qib: Remove IB latency turnoffMike Marciniszyn1-2/+0
This is required for hardware testing. Signed-off-by: Mike Marciniszyn <[email protected]> Signed-off-by: Roland Dreier <[email protected]>
2011-01-10RDMA/nes: Fix string continuation lineJoe Perches1-2/+2
Signed-off-by: Joe Perches <[email protected]> Signed-off-by: Roland Dreier <[email protected]>
2011-01-10IB/mthca: Handle -ENOMEM in forward_trap()Dan Carpenter1-0/+2
ib_create_send_mad() can return ERR_PTR(-ENOMEM) here. Signed-off-by: Dan Carpenter <[email protected]> Signed-off-by: Roland Dreier <[email protected]>
2011-01-10IB/mlx4: Handle -ENOMEM in forward_trap()Dan Carpenter1-0/+2
ib_create_send_mad() can return ERR_PTR(-ENOMEM) here. Signed-off-by: Dan Carpenter <[email protected]> Signed-off-by: Roland Dreier <[email protected]>
2011-01-10IB/mlx4: Don't call dma_free_coherent() with irqs disabledVladimir Sokolovsky1-1/+8
mlx4_ib_free_cq_buf() should not be called under spin_lock_irq() since it calls dma_free_coherent(), which needs irqs enabled. Fix this by deferring the free to outside the locked region. This was found due to the WARN_ON(irqs_disabled()); in swiotlb_free_coherent(). Signed-off-by: Vladimir Sokolovsky <[email protected]> Signed-off-by: Roland Dreier <[email protected]>
2011-01-10IB/ipath: Use printf extension %pR for struct resourceJoe Perches1-3/+2
Using %pR standardizes the struct resource output. Signed-off-by: Joe Perches <[email protected]> Signed-off-by: Roland Dreier <[email protected]>
2011-01-10RDMA/cxgb4: Don't re-init wait object in init/fini pathsSteve Wise1-2/+0
Re-initializing the wait object in rdma_init()/rdma_fini() causes a timing window which can lead to a deadlock during close. Once this deadlock hits, all RDMA activity over the T4 device will be stuck. There's no need to re-init the wait object, so remove it. Signed-off-by: Steve Wise <[email protected]> Cc: <[email protected]> Signed-off-by: Roland Dreier <[email protected]>
2011-01-10RDMA/cxgb3,cxgb4: Remove dead codeStephen Hemminger5-89/+2
This removes unused code found by running 'make namespacecheck'; compile tested only. Signed-off-by: Stephen Hemminger <[email protected]> Acked-by: Steve Wise <[email protected]> Signed-off-by: Roland Dreier <[email protected]>
2011-01-07Merge branch 'vfs-scale-working' of ↵Linus Torvalds2-10/+3
git://git.kernel.org/pub/scm/linux/kernel/git/npiggin/linux-npiggin * 'vfs-scale-working' of git://git.kernel.org/pub/scm/linux/kernel/git/npiggin/linux-npiggin: (57 commits) fs: scale mntget/mntput fs: rename vfsmount counter helpers fs: implement faster dentry memcmp fs: prefetch inode data in dcache lookup fs: improve scalability of pseudo filesystems fs: dcache per-inode inode alias locking fs: dcache per-bucket dcache hash locking bit_spinlock: add required includes kernel: add bl_list xfs: provide simple rcu-walk ACL implementation btrfs: provide simple rcu-walk ACL implementation ext2,3,4: provide simple rcu-walk ACL implementation fs: provide simple rcu-walk generic_check_acl implementation fs: provide rcu-walk aware permission i_ops fs: rcu-walk aware d_revalidate method fs: cache optimise dentry and inode for rcu-walk fs: dcache reduce branches in lookup path fs: dcache remove d_mounted fs: fs_struct use seqlock fs: rcu-walk for path lookup ...
2011-01-07fs: dcache rationalise dget variantsNick Piggin2-2/+2
dget_locked was a shortcut to avoid the lazy lru manipulation when we already held dcache_lock (lru manipulation was relatively cheap at that point). However, how that the lru lock is an innermost one, we never hold it at any caller, so the lock cost can now be avoided. We already have well working lazy dcache LRU, so it should be fine to defer LRU manipulations to scan time. Signed-off-by: Nick Piggin <[email protected]>
2011-01-07fs: dcache remove dcache_lockNick Piggin2-8/+1
dcache_lock no longer protects anything. remove it. Signed-off-by: Nick Piggin <[email protected]>
2011-01-07fs: dcache scale dentry refcountNick Piggin2-2/+2
Make d_count non-atomic and protect it with d_lock. This allows us to ensure a 0 refcount dentry remains 0 without dcache_lock. It is also fairly natural when we start protecting many other dentry members with d_lock. Signed-off-by: Nick Piggin <[email protected]>
2010-12-26Merge branch 'master' of ↵David S. Miller3-8/+7
master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6 Conflicts: net/ipv4/fib_frontend.c
2010-12-22Merge branch 'master' into for-nextJiri Kosina3-8/+7
Conflicts: MAINTAINERS arch/arm/mach-omap2/pm24xx.c drivers/scsi/bfa/bfa_fcpim.c Needed to update to apply fixes for which the old branch was too outdated.
2010-12-02Merge branch 'for-linus' of ↵Linus Torvalds2-7/+7
git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband * 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband: IB: Fix information leak in marshalling code IB/pack: Remove some unused code added by the IBoE patches IB/mlx4: Fix IBoE link state IB/mlx4: Fix IBoE reported link rate mlx4_core: Workaround firmware bug in query dev cap IB/mlx4: Fix memory ordering of VLAN insertion control bits MAINTAINERS: Update NetEffect entry
2010-12-01IB/mlx4: Fix IBoE link stateEli Cohen1-1/+1
Use netif_running() and netif_carrier_ok() to report link state, exactly as is done to report Ethernet link state in sysfs. Signed-off-by: Eli Cohen <[email protected]> Signed-off-by: Roland Dreier <[email protected]>
2010-12-01IB/mlx4: Fix IBoE reported link rateEli Cohen1-1/+1
The link rate is the product of the link speed in the link width. For Etherent ports the rate is 10G, so we use 1 for the width and 4 for speed to get the correct rate. Signed-off-by: Eli Cohen <[email protected]> Signed-off-by: Roland Dreier <[email protected]>
2010-12-01IB/mlx4: Fix memory ordering of VLAN insertion control bitsEli Cohen1-5/+5
We must fully update the control segment before marking it as valid, so that hardware doesn't start executing it before we're ready. Signed-off-by: Eli Cohen <[email protected]> [ Move VLAN control bit setting to before wmb(). - Roland ] Signed-off-by: Roland Dreier <[email protected]>
2010-11-24infiniband: remove dev_base_lock useEric Dumazet1-3/+3
dev_base_lock is the legacy way to lock the device list, and is planned to disappear. (writers hold RTNL, readers hold RCU lock) Convert rdma_translate_ip() and update_ipv6_gids() to RCU locking. Signed-off-by: Eric Dumazet <[email protected]> Acked-by: Roland Dreier <[email protected]> Signed-off-by: David S. Miller <[email protected]>
2010-11-17BKL: remove extraneous #include <smp_lock.h>Arnd Bergmann1-1/+0
The big kernel lock has been removed from all these files at some point, leaving only the #include. Remove this too as a cleanup. Signed-off-by: Arnd Bergmann <[email protected]> Signed-off-by: Linus Torvalds <[email protected]>
2010-11-15infiniband: Only include mutex.h once in drivers/infiniband/hw/cxgb4/iw_cxgb4.hJesper Juhl1-1/+0
Only include the header linux/mutex.h once inside drivers/infiniband/hw/cxgb4/iw_cxgb4.h Signed-off-by: Jesper Juhl <[email protected]> Signed-off-by: Jiri Kosina <[email protected]>
2010-11-01tree-wide: fix comment/printk typosUwe Kleine-König2-2/+2
"gadget", "through", "command", "maintain", "maintain", "controller", "address", "between", "initiali[zs]e", "instead", "function", "select", "already", "equal", "access", "management", "hierarchy", "registration", "interest", "relative", "memory", "offset", "already", Signed-off-by: Uwe Kleine-König <[email protected]> Signed-off-by: Jiri Kosina <[email protected]>
2010-10-29convert get_sb_single() usersAl Viro2-14/+14
Signed-off-by: Al Viro <[email protected]>
2010-10-26Merge branch 'for-linus' of ↵Linus Torvalds2-0/+2
git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6 * 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6: (52 commits) split invalidate_inodes() fs: skip I_FREEING inodes in writeback_sb_inodes fs: fold invalidate_list into invalidate_inodes fs: do not drop inode_lock in dispose_list fs: inode split IO and LRU lists fs: switch bdev inode bdi's correctly fs: fix buffer invalidation in invalidate_list fsnotify: use dget_parent smbfs: use dget_parent exportfs: use dget_parent fs: use RCU read side protection in d_validate fs: clean up dentry lru modification fs: split __shrink_dcache_sb fs: improve DCACHE_REFERENCED usage fs: use percpu counter for nr_dentry and nr_dentry_unused fs: simplify __d_free fs: take dcache_lock inside __d_path fs: do not assign default i_ino in new_inode fs: introduce a per-cpu last_ino allocator new helper: ihold() ...
2010-10-26Merge branch 'for-linus' of ↵Linus Torvalds39-538/+1520
git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband * 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband: (63 commits) IB/qib: clean up properly if pci_set_consistent_dma_mask() fails IB/qib: Allow driver to load if PCIe AER fails IB/qib: Fix uninitialized pointer if CONFIG_PCI_MSI not set IB/qib: Fix extra log level in qib_early_err() RDMA/cxgb4: Remove unnecessary KERN_<level> use RDMA/cxgb3: Remove unnecessary KERN_<level> use IB/core: Add link layer type information to sysfs IB/mlx4: Add VLAN support for IBoE IB/core: Add VLAN support for IBoE IB/mlx4: Add support for IBoE mlx4_en: Change multicast promiscuous mode to support IBoE mlx4_core: Update data structures and constants for IBoE mlx4_core: Allow protocol drivers to find corresponding interfaces IB/uverbs: Return link layer type to userspace for query port operation IB/srp: Sync buffer before posting send IB/srp: Use list_first_entry() IB/srp: Reduce number of BUSY conditions IB/srp: Eliminate two forward declarations IB/mlx4: Signal node desc changes to SM by using FW to generate trap 144 IB: Replace EXTRA_CFLAGS with ccflags-y ...
2010-10-26Merge branches 'amso1100', 'cma', 'cxgb3', 'cxgb4', 'ehca', 'iboe', 'ipoib', ↵Roland Dreier39-538/+1520
'misc', 'mlx4', 'nes', 'qib' and 'srp' into for-next
2010-10-26IB/qib: clean up properly if pci_set_consistent_dma_mask() failsJason Gunthorpe1-1/+3
Clean up properly if pci_set_consistent_dma_mask() fails. Signed-off-by: Jason Gunthorpe <[email protected]> Signed-off-by: Roland Dreier <[email protected]>
2010-10-26IB/qib: Allow driver to load if PCIe AER failsRalph Campbell1-1/+3
Some PCIe root complex chip sets don't support advanced error reporting. Allow the driver to load OK if pci_enable_pcie_error_reporting() fails. Signed-off-by: Ralph Campbell <[email protected]> Signed-off-by: Roland Dreier <[email protected]>
2010-10-26IB/qib: Fix uninitialized pointer if CONFIG_PCI_MSI not setRalph Campbell1-0/+1
If CONFIG_PCI_MSI is not set, and a QLE7140 is present, the pointer "dd" is uninitialized. Signed-off-by: Ralph Campbell <[email protected]> Signed-off-by: Roland Dreier <[email protected]>
Powered by cgit, Gruvboxed by Blaster4385.