- 23 Jun, 2016 1 commit
-
-
Bart Van Assche authored
The memory needed for the send and receive queues associated with a QP is proportional to the max_sge parameter. The current value of that parameter is such that with an mlx4 HCA the QP buffer size is 8 MB. Since DMA is used for communication between HCA and CPU that buffer either has to be allocated coherently or map_single() must succeed for that buffer. Since large contiguous allocations are fragile and since the maximum segment size for e.g. swiotlb is 256 KB, reduce the max_sge parameter. This patch avoids that the following text appears on the console after SRP logout and relogin on a system equipped with multiple IB HCAs: mlx4_core 0000:05:00.0: swiotlb buffer is full (sz: 8388608 bytes) swiotlb: coherent allocation failed for device 0000:05:00.0 size=8388608 CPU: 11 PID: 148 Comm: kworker/11:1 Not tainted 4.7.0-rc4-dbg+ #1 Call Trace: [<ffffffff812c6d35>] dump_stack+0x67/0x92 [<ffffffff812efe71>] swiotlb_alloc_coherent+0x141/0x150 [<ffffffff810458be>] x86_swiotlb_alloc_coherent+0x3e/0x50 [<ffffffffa03861fa>] mlx4_buf_direct_alloc.isra.5+0x9a/0x120 [mlx4_core] [<ffffffffa0386545>] mlx4_buf_alloc+0x165/0x1a0 [mlx4_core] [<ffffffffa035053d>] create_qp_common.isra.29+0x57d/0xff0 [mlx4_ib] [<ffffffffa03510da>] mlx4_ib_create_qp+0x12a/0x3f0 [mlx4_ib] [<ffffffffa031154a>] ib_create_qp+0x3a/0x250 [ib_core] [<ffffffffa055dd4b>] srpt_cm_handler+0x4bb/0xcad [ib_srpt] [<ffffffffa02c1ab0>] cm_process_work+0x20/0xf0 [ib_cm] [<ffffffffa02c3640>] cm_work_handler+0x1ac0/0x2059 [ib_cm] [<ffffffff810737ed>] process_one_work+0x19d/0x490 [<ffffffff81073b29>] worker_thread+0x49/0x490 [<ffffffff8107a0ea>] kthread+0xea/0x100 [<ffffffff815b25af>] ret_from_fork+0x1f/0x40 Fixes: b99f8e4d ("IB/srpt: convert to the generic RDMA READ/WRITE API") Signed-off-by:
Bart Van Assche <bart.vanassche@sandisk.com> Cc: Laurence Oberman <loberman@redhat.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Sagi Grimberg <sagi@grimberg.me> Signed-off-by:
Doug Ledford <dledford@redhat.com>
-
- 18 Jun, 2016 1 commit
-
-
Bart Van Assche authored
Static source code analysis tools like smatch cannot handle functions that lock or not lock a mutex depending on the value of the arguments. Hence inline the function cma_disable_callback(). Additionally, this patch realizes a small performance optimization by reducing the number of mutex_lock() and mutex_unlock() calls in the modified functions. With this patch applied smatch no longer complains about source file cma.c. Without this patch smatch reports the following for this source file: drivers/infiniband/core/cma.c:1959: cma_req_handler() warn: inconsistent returns 'mutex:&listen_id->handler_mutex'. Locked on: line 1880 line 1959 Unlocked on: line 1941 drivers/infiniband/core/cma.c:2112: iw_conn_req_handler() warn: inconsistent returns 'mutex:&listen_id->handler_mutex'. Locked on: line 2048 Unlocked on: line 2112 Signed-off-by:Sean Hefty <sean.hefty@intel.com> Reviewed-by:
Steve Wise <swise@opengridcomputing.com> Reviewed-by:
Leon Romanovsky <leonro@mellanox.com> Signed-off-by:
-
- 17 Jun, 2016 1 commit
-
-
Jason Gunthorpe authored
When this code was reworked for IBoE support the order of assignments for the sl_tclass_flowlabel got flipped around resulting in TClass & FlowLabel being permanently set to 0 in the packet headers. This breaks IB routers that rely on these headers, but only affects kernel users - libmlx4 does this properly for user space. Cc: stable@vger.kernel.org Fixes: fa417f7b ("IB/mlx4: Add support for IBoE") Signed-off-by:
Jason Gunthorpe <jgunthorpe@obsidianresearch.com> Signed-off-by:
-
- 07 Jun, 2016 20 commits
-
-
Erez Shitrit authored
ipoib_neigh_get unconditionally updates the "alive" variable member on any packet send. This prevents the neighbor garbage collection from cleaning out a dead neighbor entry if we are still queueing packets for it. If the queue for this neighbor is full, then don't update the alive timestamp. That way the neighbor can time out even if packets are still being queued as long as none of them are being sent. Fixes: b63b70d8 ("IPoIB: Use a private hash table for path lookup in xmit path") Signed-off-by:
Erez Shitrit <erezsh@mellanox.com> Signed-off-by:
Leon Romanovsky <leon@kernel.org> Signed-off-by:
-
Achiad Shochat authored
Userspace flag IBV_QP_ALT_PATH is supposed to set the alternate path including fields alt_pkey_index and alt_timeout. Added IB_QP_PKEY_INDEX and IB_QP_TIMEOUT to the attribute mask when calling mlx5_set_path for the alternate path to force setting the alt_pkey_index and alt_timeout values. Fixes: bf24481a3a7c4 ('IB/mlx5: Consider alternate path in pkey ...') Signed-off-by:Achiad Shochat <achiad@mellanox.com> Signed-off-by:
Noa Osherovich <noaos@mellanox.com> Reviewed-by:
Jack Morgenstein <jackm@dev.mellanox.co.il> Signed-off-by:
-
Noa Osherovich authored
Pkey index fields in the QP context path record are extended to 16 bits, as required by IB spec (version 1.3). This change affects all QP commands which include path records. To enable this change, moved the free adaptive routing flag bit (free_ar) to the most significant byte of the QP path record. Fixes: e126ba97 ('mlx5: Add driver for Mellanox Connect-IB ...') Signed-off-by:
-
Noa Osherovich authored
Verify that number of entries is less than device capability. Add an appropriate warning message for error flow. Fixes: bde51583 ('IB/mlx5: Add support for resize CQ') Signed-off-by:
Majd Dibbiny <majd@mellanox.com> Signed-off-by:
-
Noa Osherovich authored
Number of entries shouldn't be greater than the device's max capability. This should be checked before rounding the entries number to power of two. Fixes: 51ee86a4 ('IB/mlx5: Fix check of number of entries...') Signed-off-by:
Sagi Grimberg <sagi@grimberg.me> Signed-off-by:
-
Noa Osherovich authored
BlueFlame support is reported only for PFs when the HCA capability is on. Fixes: 938fe83c ('net/mlx5_core: New device capabilities...') Signed-off-by:
-
Noa Osherovich authored
Some variables were not initialized properly: max_recv_wr, max_recv_sge, max_send_wr, qp_context and max_inline_data. Fixes: e126ba97 ('mlx5: Add driver for Mellanox Connect-IB...') Signed-off-by:
-
Noa Osherovich authored
When PAGE_SIZE is larger than 4K, the user shouldn't be able to query the HCA core clock. This counter is within 4KB boundary and the user-space shall not read information that's after this boundary. Fixes: b368d7cb ('IB/mlx5: Add hca_core_clock_offset to...') Signed-off-by:
-
Eran Ben Elisha authored
Add a 4-digit padding to show FW version in proper format. Fixes: 9603b61d ('mlx5: Move pci device handling from...') Signed-off-by:
Eran Ben Elisha <eranbe@mellanox.com> Signed-off-by:
-
Noa Osherovich authored
FW port-change events are fired on Active <-> non Active port state transitions only. When the port state changes from Active to Initializing (Active -> Down -> Initializing), a single event is fired. The HCA transitions from Down to Initializing unless prevented from doing so, hence the driver should also propagate events when the port state is Initializing to consumers so they'll be aware that the port is no longer Active and act accordingly. Fixes: e126ba97 ('mlx5: Add driver for Mellanox Connect-IB...') Signed-off-by:
-
Maor Gottlieb authored
Flow steering is supported by mlx5 device when the following features are supported by firmware: 1. NIC RX flow table. 2. Device has enough flow steering levels. 3. Atomic modification of flow table entry. 4. Flow tables chaining. To check if flow steering is supported it's enough to check if the driver opened the mlx5 bypass namespace. Signed-off-by:
Maor Gottlieb <maorg@mellanox.com> Signed-off-by:
-
Max Gurtovoy authored
Replace the few u64 casts with ULL to match the rest of the casts. Signed-off-by:
Max Gurtovoy <maxg@mellanox.com> Signed-off-by:
-
Max Gurtovoy authored
ib_device_cap_flags 64-bit expansion caused caps overlapping and made consumers read wrong device capabilities. For example IB_DEVICE_SG_GAPS_REG was falsely read by the iser driver causing it to use a non-existing capability. This happened because signed int becomes sign extended when converted it to u64. Fix this by casting IB_DEVICE_ON_DEMAND_PAGING enumeration to ULL. Fixes: f5aa9159 ('IB/core: Add arbitrary sg_list support') Reported-by:
Robert LeBlanc <robert@leblancnet.us> Cc: Stable <stable@vger.kernel.org> #[v4.6+] Acked-by:
Matan Barak <matanb@mellanox.com> Reviewed-by:
Christoph Hellwig <hch@lst.de> Signed-off-by:
-
Mark Bloch authored
For dynamically allocated sysfs attributes there is a need to call sysfs_attr_init in order to comply with lockdep, not calling it will result in error complaining key is not in .data section. Fixes: b40f4757 ("IB/core: Make device counter infrastructure dynamic") Signed-off-by:
Mark Bloch <markb@mellanox.com> Signed-off-by:
-
Mark Bloch authored
Align locking usage when touching device address with rest of the kernel. Lock the bottom half when doing so using netif_addr_lock_bh. This also solves the following case as reported by lockdep: CPU0 CPU1 ---- ---- lock(_xmit_INFINIBAND); local_irq_disable(); lock(&(&mc->mca_lock)->rlock); lock(_xmit_INFINIBAND); <Interrupt> lock(&(&mc->mca_lock)->rlock); *** DEADLOCK *** Fixes: 492a7e67 ("IB/IPoIB: Allow setting the device address") Signed-off-by:
-
Aviv Heller authored
When deleting a default GID from the cache, its gid_type field is set to 0. This could set the gid_type to RoCE v1 for a RoCE v2 default GID, essentially making it inaccessible to future modifications, since it is no longer found by find_gid(). This fix preserves the gid_type value for default gids during cache operations. Fixes: b39ffa1d ('IB/core: Add gid_type to gid attribute') Signed-off-by:
Aviv Heller <avivh@mellanox.com> Signed-off-by:
-
Erez Shitrit authored
In ipoib_remove_one the driver holds the rtnl_lock and tries to do some operation like dev_change_flags or unregister_netdev, while sysfs callback like ipoib_vlan_delete holds sysfs mutex and tries to hold the rtnl_lock via rtnl_trylock() and restart_syscall() if the lock is not free, meanwhile ipoib_remove_one tries to get the sysfs lock in order to free its sysfs directory, and we will get a->b, b->a deadlock. Trace like the following: schedule+0x37/0x80 schedule_preempt_disabled+0xe/0x10 __mutex_lock_slowpath+0xb5/0x120 mutex_lock+0x23/0x40 rtnl_lock+0x15/0x20 netdev_run_todo+0x17c/0x320 rtnl_unlock+0xe/0x10 ipoib_vlan_delete+0x11b/0x1b0 [ib_ipoib] delete_child+0x54/0x80 [ib_ipoib] dev_attr_store+0x18/0x30 sysfs_kf_write+0x37/0x40 mutex_lock+0x16/0x40 SyS_write+0x55/0xc0 entry_SYSCALL_64_fastpath+0x16/0x75 And schedule+0x37/0x80 __kernfs_remove+0x1a8/0x260 ? wake_atomic_t_function+0x60/0x60 kernfs_remove+0x25/0x40 sysfs_remove_dir+0x50/0x80 kobject_del+0x18/0x50 device_del+0x19f/0x260 netdev_unregister_kobject+0x6a/0x80 rollback_registered_many+0x1fd/0x340 rollback_registered+0x3c/0x70 unregister_netdevice_queue+0x55/0xc0 unregister_netdev+0x20/0x30 ipoib_remove_one+0x114/0x1b0 [ib_ipoib] ib_unregister_client+0x4a/0x170 [ib_core] ? find_module_all+0x71/0xa0 ipoib_cleanup_module+0x10/0x94 [ib_ipoib] SyS_delete_module+0x1b5/0x210 entry_SYSCALL_64_fastpath+0x16/0x75 The fix is by checking the flag IPOIB_FLAG_INTF_ON_DESTROY in order to get out from the sysfs function. Fixes: 862096a8 ("IB/ipoib: Add more rtnl_link_ops callbacks") Fixes: 9baa0b03 ("IB/ipoib: Add rtnl_link_ops support") Signed-off-by: -
Eli Cohen authored
Currently ib_query_port always attempts to to read the subnet prefix by calling ib_query_gid(). For RoCE/iWARP there is no subnet manager and no subnet prefix. Fix this by querying GID[0] only for IB networks. Fixes: fad61ad4 ('IB/core: Add subnet prefix to port info') Signed-off-by:
Eli Cohen <eli@mellanox.com> Signed-off-by:
-
Doug Ledford authored
Between the initial and final versions of the function setup_hw_stats, the order of variable initialization was changed. However, the unwind flow on error did not properly keep up with the flow changes. Make the unwind flow match a proper unwind of the allocation flow, then remove no longer needed variable initializations. Fixes: b40f4757 (IB/core: Make device counter infrastructure dynamic) Signed-off-by:
-
Doug Ledford authored
The new sysfs hw_counters code had an off by one in its array allocation length. Fix that and the comment along with it. Reported-by:
-
- 06 Jun, 2016 15 commits
-
-
Bart Van Assche authored
Avoid that sparse reports the following warnings for the hfi1 driver: trace.c:217:13: warning: no previous prototype for ‘print_u64_array’ [-Wmissing-prototypes] user_sdma.c:1361:17: warning: dubious: !x & y Signed-off-by:
-
Bart Van Assche authored
The first argument of test_bit() and clear_bit() is a bit number and not a bitmask. Hence change that first argument from (1 << 0) into 0. This patch avoids that smatch reports the following warnings: user_sdma.c:1059: sdma_cache_evict() warn: test_bit() takes a bit number user_sdma.c:1590: sdma_rb_remove() warn: test_bit() takes a bit number Signed-off-by:
-
Bart Van Assche authored
Make the indentation of the source code consistent. Detected by smatch. Signed-off-by:
-
Bart Van Assche authored
This patch avoids that sparse reports the following warning: rdmavt/qp.c:507:17: warning: context imbalance in 'rvt_reset_qp' - unexpected unlock Signed-off-by:
-
Bart Van Assche authored
Make indentation consistent. Detected by smatch. Signed-off-by:
Ira Weiny <ira.weiny@intel.com> Reviewed-by:
Hal Rosenstock <hal@mellanox.com> Reviewed-by:
-
Bart Van Assche authored
Make indentation consistent. Detected by smatch. Signed-off-by:
Sagi Grimberg <sagi@gimberg.me> Signed-off-by:
-
Bart Van Assche authored
Because patch "IB/srp: Move common code into the caller" was applied partially srp_map_sg_dma() doesn't work properly. Fix this by applying the remainder of that patch. See also http://thread.gmane.org/gmane.linux.drivers.rdma/35803/focus=35811. Fixes: 3849e44d ("IB/srp: Move common code into the caller") Signed-off-by:
-
Bart Van Assche authored
Avoid that mapping fails due to use_fast_reg != 0 or use_fmr != 0 if both member variables should be zero (if never_register == 1 or if neither FMR nor FR is supported). Remove an initialization that became superfluous due to changing a kmalloc() into a kzalloc() call. Fixes: 509c5f33 ("IB/srp: Prevent mapping failures") Cc: Sagi Grimberg <sai@grimberg.m> Cc: Christoph Hellwig <hch@lst.de> Cc: Laurence Oberman <loberman@redhat.com> Signed-off-by:
-
Bart Van Assche authored
Perform the test for device managed flow steering support even if memory windows are not supported. I noticed this because smatch reported inconsistent indentation for the device managed flow steering support test. Signed-off-by:
-
Krzysztof Kozlowski authored
The DMA attributes are set but never used. Signed-off-by:
Krzysztof Kozlowski <k.kozlowski@samsung.com> Signed-off-by:
-
Colin Ian King authored
The current error handling in setup_hw_stats has a couple of issues. It is possible to generate a null pointer deference on the kfree of hsag->attrs[i] because two of the early error exit paths jump to the kfree when hsags NULL and not allocated. Fix this by moving the kfree on stats and jumping to that, avoiding the hsag freeing. Secondly, there is a memory leak of stats if the hsag allocation fails; instead of returning, jump to the kfree on stats. Signed-off-by:
Colin Ian King <colin.king@canonical.com> Signed-off-by:
-
Dan Carpenter authored
We should return the error code if ib_add_ibnl_clients() fails. The current code returns success. Fixes: 735c631a ('IB/core: Register SA ibnl client during ib_core initialization') Signed-off-by:
Dan Carpenter <dan.carpenter@oracle.com> Reviewed-by:
-
Leon Romanovsky authored
When CONFIG_FRAME_WARN is set to 1024 bytes, which is useful to find stack consumers, we get a warning in hfi1 driver. drivers/infiniband/hw/hfi1/affinity.c: In function ‘hfi1_get_proc_affinity’: drivers/infiniband/hw/hfi1/affinity.c:415:1: warning: the frame size of 1056 bytes is larger than 1024 bytes [-Wframe-larger-than=] This change removes unneeded buf[1024] declaration and usage. Fixes: f48ad614 ("IB/hfi1: Move driver out of staging") Signed-off-by:
Dennis Dalessandro <dennis.dalessandro@intel.com> Signed-off-by:
-
Dan Carpenter authored
That extra tabs are misleading. Signed-off-by:
-
Bart Van Assche authored
ib_cm_notify() can be called from interrupt context. Hence do not reenable interrupts unconditionally in cm_establish(). This patch avoids that lockdep reports the following warning: WARNING: CPU: 0 PID: 23317 at kernel/locking/lockdep.c:2624 trace _hardirqs_on_caller+0x112/0x1b0 DEBUG_LOCKS_WARN_ON(current->hardirq_context) Call Trace: <IRQ> [<ffffffff812bd0e5>] dump_stack+0x67/0x92 [<ffffffff81056f21>] __warn+0xc1/0xe0 [<ffffffff81056f8a>] warn_slowpath_fmt+0x4a/0x50 [<ffffffff810a5932>] trace_hardirqs_on_caller+0x112/0x1b0 [<ffffffff810a59dd>] trace_hardirqs_on+0xd/0x10 [<ffffffff815992c7>] _raw_spin_unlock_irq+0x27/0x40 [<ffffffffa0382e9c>] ib_cm_notify+0x25c/0x290 [ib_cm] [<ffffffffa068fbc1>] srpt_qp_event+0xa1/0xf0 [ib_srpt] [<ffffffffa04efb97>] mlx4_ib_qp_event+0x67/0xd0 [mlx4_ib] [<ffffffffa034ec0a>] mlx4_qp_event+0x5a/0xc0 [mlx4_core] [<ffffffffa03365f8>] mlx4_eq_int+0x3d8/0xcf0 [mlx4_core] [<ffffffffa0336f9c>] mlx4_msi_x_interrupt+0xc/0x20 [mlx4_core] [<ffffffff810b0914>] handle_irq_event_percpu+0x64/0x100 [<ffffffff810b09e4>] handle_irq_event+0x34/0x60 [<ffffffff810b3a6a>] handle_edge_irq+0x6a/0x150 [<ffffffff8101ad05>] handle_irq+0x15/0x20 [<ffffffff8101a66c>] do_IRQ+0x5c/0x110 [<ffffffff8159a2c9>] common_interrupt+0x89/0x89 [<ffffffff81297a17>] blk_run_queue_async+0x37/0x40 [<ffffffffa0163e53>] rq_completed+0x43/0x70 [dm_mod] [<ffffffffa0164896>] dm_softirq_done+0x176/0x280 [dm_mod] [<ffffffff812a26c2>] blk_done_softirq+0x52/0x90 [<ffffffff8105bc1f>] __do_softirq+0x10f/0x230 [<ffffffff8105bec8>] irq_exit+0xa8/0xb0 [<ffffffff8103653e>] smp_trace_call_function_single_interrupt+0x2e/0x30 [<ffffffff81036549>] smp_call_function_single_interrupt+0x9/0x10 [<ffffffff8159a959>] call_function_single_interrupt+0x89/0x90 <EOI> Fixes: commit be4b4993 (IB/cm: Do not queue work to a device that's going away) Signed-off-by:
-
- 05 Jun, 2016 2 commits
-
-
Linus Torvalds authored
-
git://git.kernel.org/pub/scm/linux/kernel/git/deller/parisc-linuxLinus Torvalds authored
Pull parisc fixes from Helge Deller: - Fix printk time stamps on SMP systems which got wrong due to a patch which was added during the merge window - Fix two bugs in the stack backtrace code: Races in module unloading and possible invalid accesses to memory due to wrong instruction decoding (Mikulas Patocka) - Fix userspace crash when syscalls access invalid unaligned userspace addresses. Those syscalls will now return EFAULT as expected. (tagged for stable kernel series) * 'parisc-4.7-2' of git://git.kernel.org/pub/scm/linux/kernel/git/deller/parisc-linux: parisc: Move die_if_kernel() prototype into traps.h header parisc: Fix pagefault crash in unaligned __get_user() call parisc: Fix printk time during boot parisc: Fix backtrace on PA-RISC
-
