- 06 Nov, 2019 13 commits
-
-
Leon Romanovsky authored
Delete never implemented and used MAD functions. Link: https://lore.kernel.org/r/20191029062745.7932-2-leon@kernel.orgSigned-off-by:
Leon Romanovsky <leonro@mellanox.com> Signed-off-by:
Jason Gunthorpe <jgg@mellanox.com>
-
Bart Van Assche authored
Although the mentioned patch fixes a use-after-free bug, it introduces a hang during shutdown. Since the latter is worse, revert this patch. Link: https://lore.kernel.org/r/20191101204756.182162-1-bvanassche@acm.orgReported-by:
Honggang Li <honli@redhat.com> Fixes: 9b64f7d0 ("RDMA/srpt: Postpone HCA removal until after configfs directory removal") Signed-off-by:
Bart Van Assche <bvanassche@acm.org> Acked-by:
-
Kamal Heib authored
There is no need to return always zero for function which is not supported. Fixes: ac1b36e5 ("qedr: Add support for user context verbs") Link: https://lore.kernel.org/r/20191028155931.1114-5-kamalheib1@gmail.comSigned-off-by:
Kamal Heib <kamalheib1@gmail.com> Reviewed-by:
-
Kamal Heib authored
There is no need to return always zero for function which is not supported. Fixes: fe2caefc ("RDMA/ocrdma: Add driver for Emulex OneConnect IBoE RDMA adapter") Link: https://lore.kernel.org/r/20191028155931.1114-4-kamalheib1@gmail.comSigned-off-by:
-
Kamal Heib authored
There is no need to return always zero for function which is not supported. Fixes: 9a443537 ("IB/hns: Add driver files for hns RoCE driver") Link: https://lore.kernel.org/r/20191028155931.1114-3-kamalheib1@gmail.comSigned-off-by:
-
Kamal Heib authored
Improve return code from ib_modify_port() by doing the following: - Use "-EOPNOTSUPP" instead "-ENOSYS" which is the proper return code - Allow only fake IB_PORT_CM_SUP manipulation for RoCE providers that didn't implement the modify_port callback, otherwise return "-EOPNOTSUPP" Fixes: 61e0962d ("IB: Avoid ib_modify_port() failure for RoCE devices") Link: https://lore.kernel.org/r/20191028155931.1114-2-kamalheib1@gmail.comSigned-off-by:
-
Michal Kalderon authored
This patch adds the iWARP specific doorbells to the doorbell recovery mechanism. Link: https://lore.kernel.org/r/20191030094417.16866-9-michal.kalderon@marvell.comSigned-off-by:
Ariel Elior <ariel.elior@marvell.com> Signed-off-by:
Michal Kalderon <michal.kalderon@marvell.com> Signed-off-by:
-
Michal Kalderon authored
Use the doorbell recovery mechanism to register rdma related doorbells that will be restored in case there is a doorbell overflow attention. Link: https://lore.kernel.org/r/20191030094417.16866-8-michal.kalderon@marvell.comSigned-off-by:
-
Michal Kalderon authored
Remove all functions related to mmap from qedr and use the common API. Link: https://lore.kernel.org/r/20191030094417.16866-7-michal.kalderon@marvell.comSigned-off-by:
-
Michal Kalderon authored
Remove the functions related to managing the mmap_xa database. This code is now common in ib_core. Link: https://lore.kernel.org/r/20191030094417.16866-6-michal.kalderon@marvell.comSigned-off-by:
Bernard Metzler <bmt@zurich.ibm.com> Reviewed-by:
-
Michal Kalderon authored
Remove the functions related to managing the mmap_xa database. This code was replaced with common code in ib_core. Link: https://lore.kernel.org/r/20191030094417.16866-5-michal.kalderon@marvell.comSigned-off-by:
-
Michal Kalderon authored
The rdma_user_mmap_io interface created a common interface for drivers to correctly map hw resources and zap them once the ucontext is destroyed enabling the drivers to safely free the hw resources. However, this meant the drivers need to delay freeing the resource to the ucontext destroy phase to ensure they were no longer mapped. The new mechanism for a common way of handling user/driver address mapping enabled notifying the driver if all umap_priv mappings were removed, and enabled freeing the hw resources when they are done with and not delay it until ucontext destroy. Since not all drivers use the mechanism, NULL can be sent to the rdma_user_mmap_io interface to continue working as before. Drivers that use the mmap_xa interface can pass the entry being mapped to the rdma_user_mmap_io function to be linked together. Link: https://lore.kernel.org/r/20191030094417.16866-4-michal.kalderon@marvell.comSigned-off-by:
-
Michal Kalderon authored
Create some common API's for adding entries to a xa_mmap. Searching for an entry and freeing one. The general approach is copied from the EFA driver and improved to be more general and do more to help the drivers. Integration with the core allows a reference counted scheme with a free function so that the driver can know when its mmaps are all gone. This significant new functionality will be helpful for drivers to have the correct lifetime model for mmap objects. Link: https://lore.kernel.org/r/20191030094417.16866-3-michal.kalderon@marvell.comSigned-off-by:
-
- 05 Nov, 2019 1 commit
-
-
Michal Kalderon authored
Move functionality that is called by the driver, which is related to umap, to a new file that will be linked in ib_core. This is a first step in later enabling ib_uverbs to be optional. vm_ops is now initialized in ib_uverbs_mmap instead of priv_init to avoid having to move all the rdma_umap functions as well. Link: https://lore.kernel.org/r/20191030094417.16866-2-michal.kalderon@marvell.comSuggested-by:
-
- 31 Oct, 2019 2 commits
-
-
Michael Guralnik authored
Linux can run in all sorts of physical machines and VMs where write combining may or may not be supported. Currently there is no way to reliably tell if the system supports WC, or not. The driver uses WC to optimize posting work to the HCA, and getting this wrong in either direction can cause a significant performance loss. Add a test in mlx5_ib initialization process to test whether write-combining is supported on the machine. The test will run as part of the enable_driver callback to ensure that the test runs after the device is setup and can create and modify the QP needed, but runs before the device is exposed to the users. The test opens UD QP and posts NOP WQEs, the WQE written to the BlueFlame is different from the WQE in memory, requesting CQE only on the BlueFlame WQE. By checking whether we received a completion on one of these WQEs we can know if BlueFlame succeeded and this write-combining must be supported. Change reporting of BlueFlame support to be dependent on write-combining support instead of the FW's guess as to what the machine can do. Link: https://lore.kernel.org/r/20191027062234.10993-1-leon@kernel.orgSigned-off-by:
Michael Guralnik <michaelgur@mellanox.com> Signed-off-by:
-
Leon Romanovsky authored
Returned value from mlx5_mr_cache_alloc() is checked to be error or real pointer. Return proper error code instead of NULL which is not checked later. Fixes: 81713d37 ("IB/mlx5: Add implicit MR support") Link: https://lore.kernel.org/r/20191029055721.7192-1-leon@kernel.orgSigned-off-by:
-
- 29 Oct, 2019 1 commit
-
-
Arnd Bergmann authored
This is not the first attempt to fix building random configurations, unfortunately the attempt in commit a07fc0bb ("RDMA/hns: Fix build error") caused a new problem when CONFIG_INFINIBAND_HNS_HIP06=m and CONFIG_INFINIBAND_HNS_HIP08=y: drivers/infiniband/hw/hns/hns_roce_main.o:(.rodata+0xe60): undefined reference to `__this_module' Revert commits a07fc0bb ("RDMA/hns: Fix build error") and a3e2d4c7 ("RDMA/hns: remove obsolete Kconfig comment") to get back to the previous state, then fix the issues described there differently, by adding more specific dependencies: INFINIBAND_HNS can now only be built-in if at least one of HNS or HNS3 are built-in, and the individual back-ends are only available if that code is reachable from the main driver. Fixes: a07fc0bb ("RDMA/hns: Fix build error") Fixes: a3e2d4c7 ("RDMA/hns: remove obsolete Kconfig comment") Fixes: dd74282d ("RDMA/hns: Initialize the PCI device for hip08 RoCE") Fixes: 08805fdb ("RDMA/hns: Split hw v1 driver from hns roce driver") Link: https://lore.kernel.org/r/20191007211826.3361202-1-arnd@arndb.deSigned-off-by:
Arnd Bergmann <arnd@arndb.de> Signed-off-by:
-
- 28 Oct, 2019 23 commits
-
-
Jason Gunthorpe authored
Jason Gunthorpe says: ==================== In order to hoist the interval tree code out of the drivers and into the mmu_notifiers it is necessary for the drivers to not use the interval tree for other things. This series replaces the interval tree with an xarray and along the way re-aligns all the locking to use a sensible SRCU model where the 'update' step is done by modifying an xarray. The result is overall much simpler and with less locking in the critical path. Many functions were reworked for clarity and small details like using 'imr' to refer to the implicit MR make the entire code flow here more readable. This also squashes at least two race bugs on its own, and quite possibily more that haven't been identified. ==================== Merge conflicts with the odp statistics patch resolved. * branch 'odp_rework': RDMA/odp: Remove broken debugging call to invalidate_range RDMA/mlx5: Do not race with mlx5_ib_invalidate_range during create and destroy RDMA/mlx5: Do not store implicit children in the odp_mkeys xarray RDMA/mlx5: Rework implicit ODP destroy RDMA/mlx5: Avoid double lookups on the pagefault path RDMA/mlx5: Reduce locking in implicit_mr_get_data() RDMA/mlx5: Use an xarray for the children of an implicit ODP RDMA/mlx5: Split implicit handling from pagefault_mr RDMA/mlx5: Set the HW IOVA of the child MRs to their place in the tree RDMA/mlx5: Lift implicit_mr_alloc() into the two routines that call it RDMA/mlx5: Rework implicit_mr_get_data RDMA/mlx5: Delete struct mlx5_priv->mkey_table RDMA/mlx5: Use a dedicated mkey xarray for ODP RDMA/mlx5: Split sig_err MR data into its own xarray RDMA/mlx5: Use SRCU properly in ODP prefetch Signed-off-by: -
Jason Gunthorpe authored
invalidate_range() also obtains the umem_mutex which is being held at this point, so if this path were was ever called it would deadlock. Thus conclude the debugging never triggers and rework it into a simple WARN_ON and leave things as they are. While here add a note to explain how we could possibly get inconsistent page pointers. Link: https://lore.kernel.org/r/20191009160934.3143-16-jgg@ziepe.caSigned-off-by:
-
Jason Gunthorpe authored
For creation, as soon as the umem_odp is created the notifier can be called, however the underlying MR may not have been setup yet. This would cause problems if mlx5_ib_invalidate_range() runs. There is some confusing/ulocked/racy code that might by trying to solve this, but without locks it isn't going to work right. Instead trivially solve the problem by short-circuiting the invalidation if there are not yet any DMA mapped pages. By definition there is nothing to invalidate in this case. The create code will have the umem fully setup before anything is DMA mapped, and npages is fully locked by the umem_mutex. For destroy, invalidate the entire MR at the HW to stop DMA then DMA unmap the pages before destroying the MR. This drives npages to zero and prevents similar racing with invalidate while the MR is undergoing destruction. Arguably it would be better if the umem was created after the MR and destroyed before, but that would require a big rework of the MR code. Fixes: 6aec21f6 ("IB/mlx5: Page faults handling infrastructure") Link: https://lore.kernel.org/r/20191009160934.3143-15-jgg@ziepe.caReviewed-by:
Artemy Kovalyov <artemyko@mellanox.com> Signed-off-by:
-
Jason Gunthorpe authored
These mkeys are entirely internal and are never used by the HW for page fault. They should also never be used by userspace for prefetch. Simplify & optimize things by not including them in the xarray. Since the prefetch path can now never see a child mkey there is no need for the second synchronize_srcu() during imr destroy. Link: https://lore.kernel.org/r/20191009160934.3143-14-jgg@ziepe.caReviewed-by:
-
Jason Gunthorpe authored
Use SRCU in a sensible way by removing all MRs in the implicit tree from the two xarrays (the update operation), then a synchronize, followed by a normal single threaded teardown. This is only a little unusual from the normal pattern as there can still be some work pending in the unbound wq that may also require a workqueue flush. This is tracked with a single atomic, consolidating the redundant existing atomics and wait queue. For understand-ability the entire ODP implicit create/destroy flow now largely exists in a single pair of functions within odp.c, with a few support functions for tearing down an unused child. Link: https://lore.kernel.org/r/20191009160934.3143-13-jgg@ziepe.caReviewed-by:
-
Jason Gunthorpe authored
Now that the locking is simplified combine pagefault_implicit_mr() with implicit_mr_get_data() so that we sweep over the idx range only once, and do the single xlt update at the end, after the child umems are setup. This avoids double iteration/xa_loads plus the sketchy failure path if the xa_load() fails. Link: https://lore.kernel.org/r/20191009160934.3143-12-jgg@ziepe.caReviewed-by:
-
Jason Gunthorpe authored
Now that the child MRs are stored in an xarray we can rely on the SRCU lock to protect the xa_load and use xa_cmpxchg on the slow allocation path to resolve races with concurrent page fault. This reduces the scope of the critical section of umem_mutex for implicit MRs to only cover mlx5_ib_update_xlt, and avoids taking a lock at all if the child MR is already in the xarray. This makes it consistent with the normal ODP MR critical section for umem_lock, and the locking approach used for destroying an unusued implicit child MR. The MLX5_IB_UPD_XLT_ATOMIC is no longer needed in implicit_get_child_mr() since it is no longer called with any locks. Link: https://lore.kernel.org/r/20191009160934.3143-11-jgg@ziepe.caReviewed-by:
-
Jason Gunthorpe authored
Currently the child leaves are stored in the shared interval tree and every lookup for a child must be done under the interval tree rwsem. This is further complicated by dropping the rwsem during iteration (ie the odp_lookup(), odp_next() pattern), which requires a very tricky an difficult to understand locking scheme with SRCU. Instead reserve the interval tree for the exclusive use of the mmu notifier related code in umem_odp.c and give each implicit MR a xarray containing all the child MRs. Since the size of each child is 1GB of VA, a 1 level xarray will index 64G of VA, and a 2 level will index 2TB, making xarray a much better data structure choice than an interval tree. The locking properties of xarray will be used in the next patches to rework the implicit ODP locking scheme into something simpler. At this point, the xarray is locked by the implicit MR's umem_mutex, and read can also be locked by the odp_srcu. Link: https://lore.kernel.org/r/20191009160934.3143-10-jgg@ziepe.caReviewed-by:
-
Jason Gunthorpe authored
The single routine has a very confusing scheme to advance to the next child MR when working on an implicit parent. This scheme can only be used when working with an implicit parent and must not be triggered when working on a normal MR. Re-arrange things by directly putting all the single-MR stuff into one function and calling it in a loop for the implicit case. Simplify some of the error handling in the new pagefault_real_mr() to remove unneeded gotos. Link: https://lore.kernel.org/r/20191009160934.3143-9-jgg@ziepe.caReviewed-by:
-
Jason Gunthorpe authored
Instead of rewriting all the IOVA's to 0 as things progress down the tree make the IOVA of the children equal to placement in the tree. This makes things easier to understand by keeping mmkey.iova == HW configuration. Link: https://lore.kernel.org/r/20191009160934.3143-8-jgg@ziepe.caReviewed-by:
-
Jason Gunthorpe authored
This makes the routines easier to understand, particularly with respect the locking requirements of the entire sequence. The implicit_mr_alloc() had a lot of ifs specializing it to each of the callers, and only a very small amount of code was actually shared. Following patches will cause the flow in the two functions to diverge further. Link: https://lore.kernel.org/r/20191009160934.3143-7-jgg@ziepe.caReviewed-by:
-
Jason Gunthorpe authored
This function is intended to loop across each MTT chunk in the implicit parent that intersects the range [io_virt, io_virt+bnct). But it is has a confusing construction, so: - Consistently use imr and odp_imr to refer to the implicit parent to avoid confusion with the normal mr and odp of the child - Directly compute the inclusive start/end indexes by shifting. This is clearer to understand the intent and avoids any errors from unaligned values of addr - Iterate directly over the range of MTT indexes, do not make a loop out of goto - Follow 'success oriented flow', with goto error unwind - Directly calculate the range of idx's that need update_xlt - Ensure that any leaf MR added to the interval tree always results in an update to the XLT Link: https://lore.kernel.org/r/20191009160934.3143-6-jgg@ziepe.caReviewed-by:
-
Jason Gunthorpe authored
No users are left, delete it. Link: https://lore.kernel.org/r/20191009160934.3143-5-jgg@ziepe.caReviewed-by:
-
Jason Gunthorpe authored
There is a per device xarray storing mkeys that is used to store every mkey in the system. However, this xarray is now only read by ODP for certain ODP designated MRs (ODP, implicit ODP, MW, DEVX_INDIRECT). Create an xarray only for use by ODP, that only contains ODP related MKeys. This xarray is protected by SRCU and all erases are protected by a synchronize. This improves performance: - All MRs in the odp_mkeys xarray are ODP MRs, so some tests for is_odp() can be deleted. The xarray will also consume fewer nodes. - normal MR's are never mixed with ODP MRs in a SRCU data structure so performance sucking synchronize_srcu() on every MR destruction is not needed. - No smp_load_acquire(live) and xa_load() double barrier on read Due to the SRCU locking scheme care must be taken with the placement of the xa_store(). Once it completes the MR is immediately visible to other threads and only through a xa_erase() & synchronize_srcu() cycle could it be destroyed. Link: https://lore.kernel.org/r/20191009160934.3143-4-jgg@ziepe.caReviewed-by:
-
Jason Gunthorpe authored
The locking model for signature is completely different than ODP, do not share the same xarray that relies on SRCU locking to support ODP. Simply store the active mlx5_core_sig_ctx's in an xarray when signature MRs are created and rely on trivial xarray locking to serialize everything. The overhead of storing only a handful of SIG related MRs is going to be much less than an xarray full of every mkey. Link: https://lore.kernel.org/r/20191009160934.3143-3-jgg@ziepe.caReviewed-by:
Max Gurtovoy <maxg@mellanox.com> Signed-off-by:
-
Jason Gunthorpe authored
When working with SRCU protected xarrays the xarray itself should be the SRCU 'update' point. Instead prefetch is using live as the SRCU update point and this prevents switching the locking design to use the xarray instead. To solve this the prefetch must only read from the xarray once, and hold on to the actual MR pointer for the duration of the async operation. Incrementing num_pending_prefetch delays destruction of the MR, so it is suitable. Prefetch calls directly to the pagefault_mr using the MR pointer and only does a single xarray lookup. All the testing if a MR is prefetchable or not is now done only in the prefetch code and removed from the pagefault critical path. Link: https://lore.kernel.org/r/20191009160934.3143-2-jgg@ziepe.caReviewed-by:
-
Jason Gunthorpe authored
Linux 5.4-rc5 For dependencies in the next patches Conflict resolved by keeping the delete of the unlock. Signed-off-by: -
Bryan Tan authored
This change allows the RDMA stack to use physical resource numbers if they are passed up from the device. This is accomplished by separating the concept of the QP number from the QP handle. Previously, the two were the same, as the QP number was exposed to the guest and also used to reference a virtual QP in the device backend. With physical resource numbers exposed, the QP number given to the guest is the number assigned from the physical HCA's QP, while the QP handle is still the internal handle used to reference a virtual QP. Regardless of whether the device is exposing physical ids, the driver will still try to pick up the QP handle from the backend if possible. The MR keys exposed to the guest will also be the MR keys created by the physical HCA, instead of virtual MR keys. The distinction between handle and keys is already present for MRs so there is no need to do anything special here. A new version of the create QP response has been added to the device API to pass up the QP number and handle. The driver will also report these to userspace in the udata response if userspace supports it or not create the queuepair if not. I also had to do a refactor of the destroy qp code to reuse it if we fail to copy to userspace. Link: https://lore.kernel.org/r/20191028181444.19448-1-aditr@vmware.comReviewed-by:
Jorgen Hansen <jhansen@vmware.com> Signed-off-by:
Adit Ranadive <aditr@vmware.com> Signed-off-by:
Bryan Tan <bryantan@vmware.com> Signed-off-by:
-
Bart Van Assche authored
The dma_set_max_seg_size() call in setup_dma_device() does not have any effect since device->dev.dma_parms is NULL. Fix this by initializing device->dev.dma_parms first. Link: https://lore.kernel.org/r/20191025225830.257535-5-bvanassche@acm.org Fixes: d10bcf94 ("RDMA/umem: Combine contiguous PAGE_SIZE regions in SGEs") Signed-off-by:
-
Bart Van Assche authored
Increase the DMA max_segment_size parameter from 64 KB to 2 GB. Link: https://lore.kernel.org/r/20191025225830.257535-4-bvanassche@acm.orgSigned-off-by:
-
Bart Van Assche authored
Increase the DMA max_segment_size parameter from 64 KB to 2 GB. Link: https://lore.kernel.org/r/20191025225830.257535-3-bvanassche@acm.orgSigned-off-by:
-
Bart Van Assche authored
If dev->dma_device->params == NULL then the maximum DMA segment size is 64 KB. See also the dma_get_max_seg_size() implementation. This patch fixes the following kernel warning: DMA-API: infiniband rxe0: mapping sg segment longer than device claims to support [len=126976] [max=65536] WARNING: CPU: 4 PID: 4848 at kernel/dma/debug.c:1220 debug_dma_map_sg+0x3d9/0x450 RIP: 0010:debug_dma_map_sg+0x3d9/0x450 Call Trace: srp_queuecommand+0x626/0x18d0 [ib_srp] scsi_queue_rq+0xd02/0x13e0 [scsi_mod] __blk_mq_try_issue_directly+0x2b3/0x3f0 blk_mq_request_issue_directly+0xac/0xf0 blk_insert_cloned_request+0xdf/0x170 dm_mq_queue_rq+0x43d/0x830 [dm_mod] __blk_mq_try_issue_directly+0x2b3/0x3f0 blk_mq_request_issue_directly+0xac/0xf0 blk_mq_try_issue_list_directly+0xb8/0x170 blk_mq_sched_insert_requests+0x23c/0x3b0 blk_mq_flush_plug_list+0x529/0x730 blk_flush_plug_list+0x21f/0x260 blk_mq_make_request+0x56b/0xf20 generic_make_request+0x196/0x660 submit_bio+0xae/0x290 blkdev_direct_IO+0x822/0x900 generic_file_direct_write+0x110/0x200 __generic_file_write_iter+0x124/0x2a0 blkdev_write_iter+0x168/0x270 aio_write+0x1c4/0x310 io_submit_one+0x971/0x1390 __x64_sys_io_submit+0x12a/0x390 do_syscall_64+0x6f/0x2e0 entry_SYSCALL_64_after_hwframe+0x49/0xbe Link: https://lore.kernel.org/r/20191025225830.257535-2-bvanassche@acm.org Cc: <stable@vger.kernel.org> Fixes: 0b5cb330 ("RDMA/srp: Increase max_segment_size") Signed-off-by:
-
Bernard Metzler authored
Do not release qp state lock if not previously acquired. Fixes: cf049bb3 ("RDMA/siw: Fix SQ/RQ drain logic") Link: https://lore.kernel.org/r/20191025142903.20625-1-bmt@zurich.ibm.comReported-by:
Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by:
-
