- 28 Feb, 2018 1 commit
-
-
Doug Ledford authored
Merge tag 'mlx5-updates-2018-02-23' of git://git.kernel.org/pub/scm/linux/kernel/git/mellanox/linux into k.o/wip/dl-for-next mlx5-update-2018-02-23 (IB representors) From: Mark Bloch <markb@mellanox.com> ========= Add IB representor when in switchdev mode The following series adds support for an IB (RAW Ethernet only) device representor which is created when the user switches to switchdev mode. Today when switching to switchdev mode the only representors which are created are net devices. Each netdev is a representor of a virtual function and any data sent via the representor is received on the virtual function, and any data sent via the virtual function is received by the representor. For the mlx5 driver the main use of this functionality is to be able to use Open vSwitch on the hypervisor in order to manage/control traffic from/to the virtual functions. Open vSwitch can also work with DPDK devices and not just net devices, this series exposes an IB device, which Mellanox PMD driver uses, which then can be used by Open vSwitch DPDK. An IB device representor exposes only RAW Ethernet QP capabilities and the ability to create flow rules to direct traffic to its RX queues. The state of the IB device (ACTIVE/DOWN etc..) is based on the state of the corresponding net device representor. No other RDMA/RoCE functionality is currently supported and no GID table is exposed. ========= Signed-off-by:
Doug Ledford <dledford@redhat.com>
-
- 23 Feb, 2018 31 commits
-
-
Mark Bloch authored
When in switchdev mode, there is no need to do self loopback checks as we can't receive those packets, we insert steering rules to the eswitch that make sure packets can't be looped back. Signed-off-by:
Mark Bloch <markb@mellanox.com> Reviewed-by:
Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by:
Leon Romanovsky <leon@kernel.org> Signed-off-by:
Saeed Mahameed <saeedm@mellanox.com>
-
Mark Bloch authored
Up until this point it wasn't possible to activate IB representors when switching to switchdev mode, remove this limitation. We trigger reload of the PF IB interface in order to make sure that already allocated resources are invalid and new resources will be opened correctly with all the limitations of switchdev mode applied (only raw packet capabilities, without RoCE). We also move the remove/add to a place where the E-Switch mode is set/unset to better control when to trigger this action, this will allow the IB side to start in the correct mode. For better code reuse, create a function which reloads an interface and export it. Signed-off-by:
-
Mark Bloch authored
This commit adds full support for IB representor: 1) Representors profile, We add two new profiles: nic_rep_profile - This profile will be used to create an IB device that represents the PF/UPLINK. rep_profile - This profile will be used to create an IB device that represents VFs. Each VF will be its own representor. 2) Proper load/unload callbacks, Those are called by the E-Switch when moving to/from switchdev mode. 3) Different flow DB handling for when we in switchdev mode. Signed-off-by:
-
Mark Bloch authored
In order to forward traffic from representor's SQ to the right virtual function, every time an SQ is created also add the corresponding flow rule to the FDB. Signed-off-by:
-
Mark Bloch authored
When enabling many VFs and switching to switchdev mode, the total amount of mkeys we try to allocate when loading representors is very large and may cause timeouts on allocations, the same issues was observed on VFs and we employ the same fix that was done for them. We avoid allocating the full MR cache on load but still allow it to be manipulated once the IB device is loaded. Signed-off-by:
-
Mark Bloch authored
Currently in switchdev mode we allow only for raw packet QPs. Expose the right capabilities and set the gid table length to 0, also make sure we don't try to enable RoCE, so split the function to enable RoCE so representors can enable only the notifier needed for net device events. Signed-off-by:
-
Mark Bloch authored
Currently we listen to netdev register/unregister event based on PCI device. When in switchdev mode PF and representors share the same PCI device, so in order to pair ib device and netdev in switchdev mode compare the netdev that triggered the event to that of the representor. Expose a function that lets you receive the netdev associated what a given representor. Signed-off-by:
-
Mark Bloch authored
When we point to a representor, it means we are in switchdev mode. The flow db is shared between PF and virtual function representors so each rule created needs to have a match on its specific source port. Signed-off-by:
-
Mark Bloch authored
A flow DB is a shared resource between PF and representors, need to allocate it only when creating the PF IB device. Once we add IB representors, they will use the flow db which was created by the PF. Signed-off-by:
-
Mark Bloch authored
Create the basic infrastructure of registering and unregistering IB representors. The load/unload callbacks are left empty and proper implementation will be introduced in following patches. Signed-off-by:
-
Mark Bloch authored
Create a new representor type: REP_IB. which will be initialized by an IB device that is used as a logical representor of a eswitch vport (VF or uplink) just like we have a net device today in switchdev mode. Signed-off-by:
-
Mark Bloch authored
Under switchdev mode we insert an eswitch miss rule causing any unmatched traffic to be sent towards the PF vport. This miss rule can be optimized if we break it to two, one case is for multicast traffic and the other for unicast. Breaking the miss rule into two (unicast and multicast) allows the firmware to program the hardware in a more efficient way. Using ConncetX-5 Ex with IXIA and testpmd (which use IB representors): IXIA -> NIC -> PF -> IB representor -> NIC -> VF: - Without this optimization: 9.2 MPPS. - With this optimization: 18 MPPS. VF -> NIC -> IB representor-> PF -> NIC -> IXIA: - Without this optimization: 17 MPPS. - With this optimization: 23.4 MPPS. Signed-off-by: -
Mark Bloch authored
The max FTE number should be the max number of SQs that can be opened. Ethernet representors open one SQ each. Once we add IB representor this will increase (depends on the user). For now lets start with 31 per IB representor and if needed increase in the future. This increase only affects the number of FTEs in the slow path FDB, offloaded rules (done via TC on the fast path portion of the FDB) aren't affected. Signed-off-by:
-
Mark Bloch authored
In preparation for IB representors, move representors structs to a global scope, also expose functions needed for registration, unregistration, eswitch mode and creating a flow rule to direct traffic from SQs to the right VF. Signed-off-by:
-
Mark Bloch authored
Add a callback interface to get a protocol device (per representor type). The Ethernet representors will expose their netdev via this interface. This functionality can be later used by IB representor in order to find the corresponding net device representor. Signed-off-by:
-
Leon Romanovsky authored
The proper return error is -EOPNOTSUPP and not -ENOSYS, so update all places in verbs.c to match this semantics. Signed-off-by:
Leon Romanovsky <leonro@mellanox.com> Signed-off-by:
-
Leon Romanovsky authored
Simplify the code by directly checking the availability of extended command flog instead of doing multiple shift operations. Signed-off-by:
-
Leon Romanovsky authored
The internal to kernel variable declarations don't need to be declared with user types. This patch converts such occurrences appeared in ib_uverbs_write(). Signed-off-by:
-
Leon Romanovsky authored
Move all header validation logic to be performed before SRCU read lock. Signed-off-by:
-
Leon Romanovsky authored
The SRCU read lock protects the IB device pointer and doesn't need to be called before copying user provided header. Signed-off-by:
-
Leon Romanovsky authored
There is no need to take SRCU lock before checking file->ucontext, so move it do it before it. Signed-off-by:
-
Leon Romanovsky authored
The check based on index is not sufficient because IB_USER_VERBS_EX_CMD_CREATE_CQ = IB_USER_VERBS_CMD_CREATE_CQ and IB_USER_VERBS_CMD_CREATE_CQ <= IB_USER_VERBS_CMD_OPEN_QP, so if we execute IB_USER_VERBS_EX_CMD_CREATE_CQ this code checks ib_dev->uverbs_cmd_mask not ib_dev->uverbs_ex_cmd_mask. Signed-off-by:
-
Leon Romanovsky authored
Move all command header processing into separate function and perform those checks before acquiring SRCU read lock. Signed-off-by:
-
Leon Romanovsky authored
The non-existing command is supposed to return -EOPNOTSUPP, but the current code returns different errors for different flows for the same failure. This patch unifies those flows. Signed-off-by:
-
Leon Romanovsky authored
Command that doesn't exist means that it is not supported, so update code to return -EOPNOTSUPP in case of failure. Signed-off-by:
-
Leon Romanovsky authored
Fail as early as possible if not enough header data was provided. Signed-off-by:
-
Leon Romanovsky authored
Since commit f21519b2 ("IB/core: extended command: an improved infrastructure for uverbs commands"), the uverbs supports extra flags as an input to the command interface. However actually, there is only one flag available and used, so it is better to refactor the code, so the resolution and report to the users is done as early as possible. As part of this change, we changed the return value of failure case from ENOSYS to be EINVAL to be consistent with the rest flags checks. Signed-off-by:
-
Leon Romanovsky authored
Update sizeof() users to be consistent with coding style. Reviewed-by:
Dennis Dalessandro <dennis.dalessandro@intel.com> Signed-off-by:
-
Leon Romanovsky authored
The function validate_command_mask() returns only two results: success or failure, so convert it to return bool instead of 0 and -1. Reported-by:
Noa Osherovich <noaos@mellanox.com> Reviewed-by:
Matan Barak <matanb@mellanox.com> Reviewed-by:
-
Doug Ledford authored
There is a 14 patch series waiting to come into for-next that has a dependecy on code submitted into this kernel's for-rc series. So, merge the for-rc branch into the current for-next in order to make the patch series apply cleanly. Signed-off-by: -
Doug Ledford authored
Merge tag 'mlx5-updates-2018-02-21' of git://git.kernel.org/pub/scm/linux/kernel/git/mellanox/linux into k.o/wip/dl-for-next mlx5-updates-2018-02-21 This series includes shared code updates for mlx5 core driver for both netdev and rdma subsystems. By Saeed, First six patches of the series are meant to address a performance issue and should provide a performance boost for multi core IRQ interrupt hungry workloads. The issue is fixed in the first patch, all other patches are meant to refactor the code in light of this fix. The problem it comes to fix, is a shared spinlock accessed across all HCA IRQs which protects the CQ database. To solve this we simply move the CQ database and its spinlock to be per EQ (IRQ), thus per core. By Yonatan, Fragmented completion queue (CQ) for RDMA, core driver implementation to create fragmented CQ buffers rather than one large contiguous memory buffer, the implementation scheme already exist and used by the netdev CQs, the patch shares that code with the rdma CQ creation flow and makes use of the new API in mlx5_ib driver. Thanks, Saeed. Merged into rdma-next tree as well as net-next tree to prevent conflicts in future patches between the two trees. Signed-off-by:
-
- 21 Feb, 2018 1 commit
-
-
Leon Romanovsky authored
Attempt to modify XRC_TGT QP type from the user space (ibv_xsrq_pingpong invocation) will trigger the following kernel panic. It is caused by the fact that such QPs missed uobject initialization. [ 17.408845] BUG: unable to handle kernel NULL pointer dereference at 0000000000000048 [ 17.412645] IP: rdma_lookup_put_uobject+0x9/0x50 [ 17.416567] PGD 0 P4D 0 [ 17.419262] Oops: 0000 [#1] SMP PTI [ 17.422915] CPU: 0 PID: 455 Comm: ibv_xsrq_pingpo Not tainted 4.16.0-rc1+ #86 [ 17.424765] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.7.5-0-ge51488c-20140602_164612-nilsson.home.kraxel.org 04/01/2014 [ 17.427399] RIP: 0010:rdma_lookup_put_uobject+0x9/0x50 [ 17.428445] RSP: 0018:ffffb8c7401e7c90 EFLAGS: 00010246 [ 17.429543] RAX: 0000000000000000 RBX: ffffb8c7401e7cf8 RCX: 0000000000000000 [ 17.432426] RDX: 0000000000000001 RSI: 0000000000000000 RDI: 0000000000000000 [ 17.437448] RBP: 0000000000000000 R08: 00000000000218f0 R09: ffffffff8ebc4cac [ 17.440223] R10: fffff6038052cd80 R11: ffff967694b36400 R12: ffff96769391f800 [ 17.442184] R13: ffffb8c7401e7cd8 R14: 0000000000000000 R15: ffff967699f60000 [ 17.443971] FS: 00007fc29207d700(0000) GS:ffff96769fc00000(0000) knlGS:0000000000000000 [ 17.446623] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 17.448059] CR2: 0000000000000048 CR3: 000000001397a000 CR4: 00000000000006b0 [ 17.449677] Call Trace: [ 17.450247] modify_qp.isra.20+0x219/0x2f0 [ 17.451151] ib_uverbs_modify_qp+0x90/0xe0 [ 17.452126] ib_uverbs_write+0x1d2/0x3c0 [ 17.453897] ? __handle_mm_fault+0x93c/0xe40 [ 17.454938] __vfs_write+0x36/0x180 [ 17.455875] vfs_write+0xad/0x1e0 [ 17.456766] SyS_write+0x52/0xc0 [ 17.457632] do_syscall_64+0x75/0x180 [ 17.458631] entry_SYSCALL_64_after_hwframe+0x21/0x86 [ 17.460004] RIP: 0033:0x7fc29198f5a0 [ 17.460982] RSP: 002b:00007ffccc71f018 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 [ 17.463043] RAX: ffffffffffffffda RBX: 0000000000000078 RCX: 00007fc29198f5a0 [ 17.464581] RDX: 0000000000000078 RSI: 00007ffccc71f050 RDI: 0000000000000003 [ 17.466148] RBP: 0000000000000000 R08: 0000000000000078 R09: 00007ffccc71f050 [ 17.467750] R10: 000055b6cf87c248 R11: 0000000000000246 R12: 00007ffccc71f300 [ 17.469541] R13: 000055b6cf8733a0 R14: 0000000000000000 R15: 0000000000000000 [ 17.471151] Code: 00 00 0f 1f 44 00 00 48 8b 47 48 48 8b 00 48 8b 40 10 e9 0b 8b 68 00 90 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 55 53 89 f5 <48> 8b 47 48 48 89 fb 40 0f b6 f6 48 8b 00 48 8b 40 20 e8 e0 8a [ 17.475185] RIP: rdma_lookup_put_uobject+0x9/0x50 RSP: ffffb8c7401e7c90 [ 17.476841] CR2: 0000000000000048 [ 17.477764] ---[ end trace 1dbcc5354071a712 ]--- [ 17.478880] Kernel panic - not syncing: Fatal exception [ 17.480277] Kernel Offset: 0xd000000 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff) Fixes: 2f08ee36 ("RDMA/restrack: don't use uaccess_kernel()") Signed-off-by:
-
- 20 Feb, 2018 5 commits
-
-
Selvin Xavier authored
BNXT_RE_FLAG_TASK_IN_PROG doesn't handle multiple work requests posted together. Track schedule of multiple workqueue items by maintaining a per device counter and proceed with IB dereg only if this counter is zero. flush_workqueue is no longer required from NETDEV_UNREGISTER path. Signed-off-by:
Selvin Xavier <selvin.xavier@broadcom.com> Signed-off-by:
-
Selvin Xavier authored
During driver unload, the driver proceeds with cleanup without waiting for the scheduled events. So the device pointers get freed up and driver crashes when the events are scheduled later. Flush the bnxt_re_task work queue before starting device removal. Signed-off-by:
-
Selvin Xavier authored
Avoid system crash when destroy_qp is invoked while the driver is processing the poll_cq. Synchronize these functions using the cq_lock. Signed-off-by:
-
Devesh Sharma authored
Driver leaves the QP memory pinned if QP create command fails from the FW. Avoids this scenario by adding a proper exit path if the FW command fails. Signed-off-by:
Devesh Sharma <devesh.sharma@broadcom.com> Signed-off-by:
-
Devesh Sharma authored
More testing needs to be done before enabling this feature. Disabling the feature temporarily Signed-off-by:
-
- 16 Feb, 2018 2 commits
-
-
Steve Wise authored
uaccess_kernel() isn't sufficient to determine if an rdma resource is user-mode or not. For example, resources allocated in the add_one() function of an ib_client get falsely labeled as user mode, when they are kernel mode allocations. EG: mad qps. The result is that these qps are skipped over during a nldev query because of an erroneous namespace mismatch. So now we determine if the resource is user-mode by looking at the object struct's uobject or similar pointer to know if it was allocated for user mode applications. Fixes: 02d8883f ("RDMA/restrack: Add general infrastructure to track RDMA resources") Signed-off-by:
Steve Wise <swise@opengridcomputing.com> Signed-off-by:
Jason Gunthorpe <jgg@mellanox.com>
-
Leon Romanovsky authored
Update all the flows to ensure that function pointer exists prior to accessing it. This is much safer than checking the uverbs_ex_mask variable, especially since we know that test isn't working properly and will be removed in -next. This prevents a user triggereable oops. Signed-off-by:
-
