- 14 5月, 2009 2 次提交
-
-
由 Stefan Roscher 提交于
In case of large queue pairs there is the possibillity of allocation failures due to memory fragmentation when using kmalloc(). To ensure the memory is allocated even if kmalloc() can not find chunks which are big enough, we fall back to allocating the memory with vmalloc(). Signed-off-by: NStefan Roscher <stefan.roscher@de.ibm.com> Signed-off-by: NRoland Dreier <rolandd@cisco.com>
-
由 Anton Blanchard 提交于
To improve performance of driver resource allocation, replace vmalloc() calls with kmalloc(). Signed-off-by: NStefan Roscher <stefan.roscher@de.ibm.com> Signed-off-by: NRoland Dreier <rolandd@cisco.com>
-
- 09 5月, 2009 1 次提交
-
-
由 Al Viro 提交于
forgot to unlock superblock before calling deactivate_super()... Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>
-
- 08 5月, 2009 1 次提交
-
-
由 Jack Morgenstein 提交于
The low-level mlx4 driver modified the page-list addresses for fast register work requests post send to big-endian, and set a "present" bit. This caused problems later when the consumer attempted to unmap the pages using the page-list (using the list addresses which were assumed to be still in CPU-endian order). Fix the mlx4 driver to allocate two buffers and use a private buffer for the hardware-format bus addresses. This patch fixes <https://bugs.openfabrics.org/show_bug.cgi?id=1571>, an NFS/RDMA server crash. The cause of the crash was found by Vu Pham of Mellanox. The fix is along the lines suggested by Steve Wise in comment #21 in bug 1571. Signed-off-by: NJack Morgenstein <jackm@dev.mellanox.co.il> Signed-off-by: NRoland Dreier <rolandd@cisco.com>
-
- 30 4月, 2009 1 次提交
-
-
由 Steve Wise 提交于
When the SQ is flushed, mark the flushed entries as not signaled so the poll logic doesn't re-insert the CQ entry thinking its an out of order completion. The bug can cause the NFS/RDMA server to crash due to processing the same completed work request twice. Signed-off-by: NSteve Wise <swise@opengridcomputing.com> Signed-off-by: NRoland Dreier <rolandd@cisco.com>
-
- 28 4月, 2009 12 次提交
-
-
由 Chien Tung 提交于
Update version number to 1.5.0.0 Signed-off-by: NChien Tung <chien.tin.tung@intel.com> Signed-off-by: NRoland Dreier <rolandd@cisco.com>
-
由 Faisal Latif 提交于
If reg_phys_mem() fails, we need to free memory allocated for MPA frame with private data before returning the error. Also move nes_add_ref() after the reg_phys_mem() is successful. Signed-off-by: NFaisal Latif <faisal.latif@intel.com> Signed-off-by: NRoland Dreier <rolandd@cisco.com>
-
由 Faisal Latif 提交于
Running large cluster setup, we are hanging after many hours of testing. Fixing this required going over the code and making sure the rexmit entry was properly removed based on the cm_node's state and packet received. Also when receiving a FIN packet, check seq# and make sure there were no errors before calling handle_fin(). Following are the changes done in nes_cm.c: * handle_ack_pkt() needs to return error value, so in case of error, handle_fin() is not called. Some cleanup done while going over the code. * handle_rst_pkt(), handling of cm_node's NES_CM_STATE_LAST_ACK is missing. * process_packet(), in case of FIN only packet is received, call check_seq() before processing. * in handle_fin_pkt(), we are calling cleanup_retrans_entry() for all conditions, even if the packets need to be dropped. Signed-off-by: NFaisal Latif <faisal.latif@intel.com> Signed-off-by: NRoland Dreier <rolandd@cisco.com>
-
由 Faisal Latif 提交于
Under heavy load with large cluster testing, it may take longer to receive a response to MPA requests. Change the driver to wait longer after each rexmit to max time value. Signed-off-by: NFaisal Latif <faisal.latif@intel.com> Signed-off-by: NRoland Dreier <rolandd@cisco.com>
-
由 Faisal Latif 提交于
check_seq() was not checking if the seq#s have wrapped. Fix it. Signed-off-by: NFaisal Latif <faisal.latif@intel.com> Signed-off-by: NRoland Dreier <rolandd@cisco.com>
-
由 Faisal Latif 提交于
When a connect request comes, apbvt should only be set for non-loopback connections. Signed-off-by: NFaisal Latif <faisal.latif@intel.com> Signed-off-by: NRoland Dreier <rolandd@cisco.com>
-
由 Chien Tung 提交于
Remove the NES_DEBUG that is causing the compile warning about an unused variable when INFINIBAND_NES_DEBUG is not enabled. Signed-off-by: NChien Tung <chien.tin.tung@intel.com> Signed-off-by: NRoland Dreier <rolandd@cisco.com>
-
由 Chien Tung 提交于
/sys/class/infiniband/nes?/fw_ver is not displaying firmware version properly (it shows 0.0.0 with the current code). Fill in the correct firmware version number. Signed-off-by: NChien Tung <chien.tin.tung@intel.com> Signed-off-by: NRoland Dreier <rolandd@cisco.com>
-
由 Chien Tung 提交于
With updated PHY firmware for SFP_D, setting the trace length to 1 inch for SFP_D provides a more stable link. Signed-off-by: NChien Tung <chien.tin.tung@intel.com> Signed-off-by: NRoland Dreier <rolandd@cisco.com>
-
由 Chien Tung 提交于
Enable repause timer for port 1. Without this setting, under stress, the chip may misbehave. Signed-off-by: NChien Tung <chien.tin.tung@intel.com> Signed-off-by: NRoland Dreier <rolandd@cisco.com>
-
由 Chien Tung 提交于
In commit 1b949324 ("RDMA/nes: Fix SFP+ PHY initialization") there is a mistake in the clean up code that removed port 1 CDR loop filter settings for 10G cards other than CX4. Put the correct setting back for appropriate PHY types. Signed-off-by: NChien Tung <chien.tin.tung@intel.com> Signed-off-by: NRoland Dreier <rolandd@cisco.com>
-
由 Chien Tung 提交于
Change thermo mitigation code to flip the SerDes1 reference clock to internal, to match the change in commit a4849fc1 ("RDMA/nes: Add wide_ppm_offset parm for switch compatibility"). Signed-off-by: NChien Tung <chien.tin.tung@intel.com> Signed-off-by: NRoland Dreier <rolandd@cisco.com>
-
- 22 4月, 2009 2 次提交
-
-
由 Miroslaw Walukiewicz 提交于
In error paths where a CQ is not created, pbl is not freeed properly. In nes_destroy_cq(), add the corresponding check for nescq->mcrqf to not call nes_free_resource() when it is already done in nes_create_cq(). Signed-off-by: NMiroslaw Walukiewicz <miroslaw.walukiewicz@intel.com> Signed-off-by: NChien Tung <chien.tin.tung@intel.com> Signed-off-by: NRoland Dreier <rolandd@cisco.com>
-
由 Matt Kraai 提交于
Signed-off-by: NMatt Kraai <kraai@ftbfs.org> Acked-by: NChien Tung <chien.tin.tung@intel.com> Signed-off-by: NRoland Dreier <rolandd@cisco.com>
-
- 21 4月, 2009 5 次提交
-
-
由 Jack Morgenstein 提交于
Commands INIT_HCA, CLOSE_HCA, SYS_EN, SYS_DIS, and CLOSE_IB all have 1 second timeouts. For INIT_HCA this causes problems when had more than 2^18 are QPs configured, since the command takes more than 1 second to complete. All other commands have 60-second timeouts. This patch makes the above commands consistent with the rest of the commands (and with the chip documentation). This patch is an expansion of a patch from Arthur Kepner <akepner@sgi.com> fixing just the INIT_HCA timeout. Signed-off-by: NJack Morgenstein <jackm@dev.mellanox.co.il> Signed-off-by: NRoland Dreier <rolandd@cisco.com>
-
由 Steve Wise 提交于
QP attributes must stay initialized when moving back to IDLE. Zeroing them will crash the system in _flush_qp() if the QP is subsequently moved to ERROR and back to IDLE. Signed-off-by: NSteve Wise <swise@opengridcomputing.com> Signed-off-by: NRoland Dreier <rolandd@cisco.com>
-
由 Don Wood 提交于
The code incorrectly failed memory registration if the buffer was not page aligned. Also, the length field is mangled causing the hardware to think the registration is much larger than it really is. The fix is to remove the page alignment restriction as well the incorrect length adjustment. Also make sure that all buffers after the first start at a page boundary, and all buffers except the last end on a page boundary. Signed-off-by: NDon Wood <donald.e.wood@intel.com> Signed-off-by: NRoland Dreier <rolandd@cisco.com>
-
由 Chien Tung 提交于
Initialize pbl_count_256 to 0 to get rid of the warning: drivers/infiniband/hw/nes/nes_verbs.c: In function 'nes_reg_mr': drivers/infiniband/hw/nes/nes_verbs.c:1955: warning: 'pbl_count_256' may be used uninitialized in this function Reported-by: NRoland Dreier <rdreier@cisco.com> Signed-off-by: NChien Tung <chien.tin.tung@intel.com> Signed-off-by: NRoland Dreier <rolandd@cisco.com>
-
由 Steve Wise 提交于
NFS/RDMA currently fails to set up connections if peer2peer is on. This is due to the fact that the NFS/RDMA client sets its ORD to 0. If peer2peer is set, make sure the active side ORD is >= 1 and the passive side IRD is >=1. Signed-off-by: NSteve Wise <swise@opengridcomputing.com> Signed-off-by: NRoland Dreier <rolandd@cisco.com>
-
- 09 4月, 2009 6 次提交
-
-
由 Chien Tung 提交于
Add new register settings for new SFP+ PHY/firmware. Add new PHY to to nes_netdev_get/set_settings. Signed-off-by: NChien Tung <chien.tin.tung@intel.com> Signed-off-by: NRoland Dreier <rolandd@cisco.com>
-
由 Chien Tung 提交于
We have observed unstable link with a new BNT switch. Add wide_ppm_offset parameter to allow the user to control the clock ppm offset on the CX4 interface for better compatibility. Default is 100ppm, setting it to 1 will increase it to 300ppm. Change default SerDes1 reference clock to external source. Signed-off-by: NChien Tung <chien.tin.tung@intel.com> Signed-off-by: NRoland Dreier <rolandd@cisco.com>
-
由 Chien Tung 提交于
SFP+ PHY initialization has very long delays, incorrect settings for direct attach copper cables, and inconsistent link detection. Adjust delays to the minimum required by the PHY. Worst case is now less than 4 seconds. Add new register settings for direct attach cables. Change link detection logic to use two new registers for more consistent link state detection. Reorganize code to shorten line length. Signed-off-by: NChien Tung <chien.tin.tung@intel.com> Signed-off-by: NRoland Dreier <rolandd@cisco.com>
-
由 Faisal Latif 提交于
We are getting crash or hung situation when we are running network cable pull tests during RDMA traffic. In schedule_nes_timer(), we return an error if nes_nic_cm_xmit() returns failure. This is changed to success as skb is being put on the timer routines to be processed later. In send_syn() case, we are indicating connect failure once from nes_connect() and the other when the rexmit retries expires. The other issue is skb->users which we are incrementing before calling nes_nic_cm_xmit() which calls dev_queue_xmit() but in case of failure we are decrementing the skb->users at the same time putting the skb on the rexmit path. Even if dev_queue_xmit() fails, the skb->users is decremented already. We are removing the decrement of skb->users in case of failure from both schedule_nes_timer() as well as from nes_cm_timer_tick(). There is also extra check in nes_cm_timer_tick() for rexmit failure which does a break from the loop is removed. This causes problem as the other nodes have their cm_node->ref_count incremented and are not processed. Signed-off-by: NFaisal Latif <faisal.latif@intel.com> Signed-off-by: NRoland Dreier <rolandd@cisco.com>
-
由 Faisal Latif 提交于
Fix issues found by static code analysis: (1) Check if cm_node was successfully created for loopback connection. (2) schedule_nes_timer() does not free up allocated memory after encountering an error. There is a WARN_ON() for this condition. (3) there is a cm_node->freed flag which is set but not used. Reported-by: NDan Carpenter <error27@gmail.com> Signed-off-by: NFaisal Latif <faisal.latif@intel.com> Signed-off-by: NRoland Dreier <rolandd@cisco.com>
-
由 Don Wood 提交于
The were some incorrect casts to unsigned long that caused 64-bit values to be truncated on 32-bit architectures and made the driver pass invalid adresses and lengths to the hardware. The problems were primarily seen with kernels with highmem configured but some could show up in non-highmem kernels, too. Signed-off-by: NDon Wood <donald.e.wood@intel.com> Signed-off-by: NRoland Dreier <rolandd@cisco.com>
-
- 07 4月, 2009 2 次提交
-
-
由 Yang Hongyang 提交于
Replace all DMA_32BIT_MASK macro with DMA_BIT_MASK(32) Signed-off-by: Yang Hongyang<yanghy@cn.fujitsu.com> Signed-off-by: NAndrew Morton <akpm@linux-foundation.org> Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
-
由 Yang Hongyang 提交于
Replace all DMA_64BIT_MASK macro with DMA_BIT_MASK(64) Signed-off-by: Yang Hongyang<yanghy@cn.fujitsu.com> Signed-off-by: NAndrew Morton <akpm@linux-foundation.org> Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
-
- 30 3月, 2009 3 次提交
-
-
由 Steve Wise 提交于
The cxgb3 l2t entry, hwtid, and dst entry were being released before all the iwch_ep references were released. This can cause a crash in t3_l2t_send_slow() and other places where the l2t entry is used. The fix is to defer releasing these resources until all endpoint references are gone. Details: - move flags field to the iwch_ep_common struct. - add a flag indicating resources are to be released. - release resources at endpoint free time instead of close/abort time. Signed-off-by: NSteve Wise <swise@opengridcomputing.com> Signed-off-by: NRoland Dreier <rolandd@cisco.com>
-
由 Steve Wise 提交于
- wrap calls into cxgb3 and fail them if we're in the middle of a PCI EEH event. - correctly unwind and release endpoint and other resources when we are in an EEH event. - dispatch IB_EVENT_DEVICE_FATAL event when cxgb3 notifies iw_cxgb3 of a fatal error. Signed-off-by: NSteve Wise <swise@opengridcomputing.com> Signed-off-by: NRoland Dreier <rolandd@cisco.com>
-
由 Roland Dreier 提交于
The PAT work on x86 has finally made pgprot_writecombine() a usable API for modular drivers. As the comment indicates, this is exactly what we want to use in mlx4_ib to map BlueFlame pages up to userspace, since using WC for these pages improves small message latency significantly. Signed-off-by: NRoland Dreier <rolandd@cisco.com>
-
- 27 3月, 2009 1 次提交
-
-
由 Roland Dreier 提交于
When net-next and infiniband were merged upstream, each branch deleted one of a pair of adjacent lines from nes_nic.c, but when Linus fixed the conflict up, he brought back both of the lines. Fix up to the intended final tree state. Signed-off-by: NRoland Dreier <rolandd@cisco.com> Acked-by: NDavid S. Miller <davem@davemloft.net> Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
-
- 25 3月, 2009 1 次提交
-
-
由 Steve Wise 提交于
The cxgb3 NIC driver can handle more firmware versions than iw_cxgb3, and since commit 8207befa ("cxgb3: untie strict FW matching") cxgb3 will load with firmware versions that iw_cxgb3 can't handle. The FW major number indicates a specific interface between the FW and iw_cxgb3. Thus if the major number of the running firmware does not match the required version compiled into iw_cxgb3, then iw_cxgb3 must not register that device. Signed-off-by: NSteve Wise <swise@opengridcomputing.com> Signed-off-by: NRoland Dreier <rolandd@cisco.com>
-
- 22 3月, 2009 2 次提交
-
-
由 Stephen Hemminger 提交于
Also, removed unnecessary memset() since alloc_netdev returns zeroed memory. Signed-off-by: NStephen Hemminger <shemminger@vyatta.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Stephen Hemminger 提交于
Convert this driver to new net_device_ops infrastructure. Also use default net_device get-stats infrastructure Signed-off-by: NStephen Hemminger <shemminger@vyatta.com> Reviewed-by: NSteve Wise <swise@opengridcomputing.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
- 19 3月, 2009 1 次提交
-
-
由 Yevgeny Petrilin 提交于
According to the ConnectX programmer's reference manual, all operations should be stopped, all QPs should be torn down and all WQEs flushed before the CLOSE_PORT command is invoked. In some cases reversing the order of operations (as implemented now) could cause a loss of completions. Signed-off-by: NYevgeny Petrilin <yevgenyp@mellanox.co.il> Signed-off-by: NRoland Dreier <rolandd@cisco.com>
-