- 24 Jun, 2019 3 commits
-
-
Israel Rukshin authored
This is a preparation for signature verbs API re-design. In the new design a single MR with IB_MR_TYPE_INTEGRITY type will be used to perform the needed mapping for data integrity operations. Signed-off-by:
Israel Rukshin <israelr@mellanox.com> Signed-off-by:
Max Gurtovoy <maxg@mellanox.com> Reviewed-by:
Sagi Grimberg <sagi@grimberg.me> Reviewed-by:
Bart Van Assche <bvanassche@acm.org> Reviewed-by:
Christoph Hellwig <hch@lst.de> Signed-off-by:
Jason Gunthorpe <jgg@mellanox.com>
-
Max Gurtovoy authored
This is a preparation for the signature verbs API change. This change is needed since the MR type will define, in the upcoming patches, the need for allocating internal resources in LLD for signature handover related operations. It will also help to make sure that signature related functions are called with an appropriate MR type and fail otherwise. Also introduce new mr types IB_MR_TYPE_USER, IB_MR_TYPE_DMA and IB_MR_TYPE_DM for correctness. Signed-off-by:
-
Max Gurtovoy authored
Ease the exhausted ib_verbs.h file and make the code more readable. Signed-off-by:
Leon Romanovsky <leonro@mellanox.com> Reviewed-by:
-
- 21 Jun, 2019 7 commits
-
-
Firas Jahjah authored
For debugging purposes, print destination address if failed to create AH. Signed-off-by:
Firas Jahjah <firasj@amazon.com> Reviewed-by:
Yossi Leybovich <sleybo@amazon.com> Signed-off-by:
Gal Pressman <galpress@amazon.com> Signed-off-by:
Doug Ledford <dledford@redhat.com>
-
Gal Pressman authored
The EFA driver is written with success oriented flows in mind, meaning that functions should mostly end with a return 0 statement. Error flows return their error value on their own instead of assuming that the function will return the error at the end. This commit fixes a bunch of functions that were not aligned with this behavior. Reviewed-by:
-
Gal Pressman authored
Use the ib_umem_find_best_pgsz() and rdma_for_each_block() API when registering an MR instead of coding it in the driver. ib_umem_find_best_pgsz() is used to find the best suitable page size which replaces the existing efa_cont_pages() implementation. rdma_for_each_block() is used to iterate the umem in aligned contiguous memory blocks. Reviewed-by:
Shiraz Saleem <shiraz.saleem@intel.com> Signed-off-by:
-
Mike Marciniszyn authored
Convert all completions to use the new completion routine that fixes a race between post send and completion where fields from a SWQE can be read after SWQE has been freed. This patch also addresses issues reported in https://marc.info/?l=linux-kernel&m=155656897409107&w=2. The reserved operation path has no need for any barrier. The barrier for the other path is addressed by the smp_load_acquire() barrier. Cc: Andrea Parri <andrea.parri@amarulasolutions.com> Reviewed-by:
Michael J. Ruhl <michael.j.ruhl@intel.com> Signed-off-by:
Mike Marciniszyn <mike.marciniszyn@intel.com> Signed-off-by:
Dennis Dalessandro <dennis.dalessandro@intel.com> Signed-off-by:
-
Mike Marciniszyn authored
There is opencoded send completion logic all over all the drivers. We need to convert to this routine to enforce ordering issues for completions. This routine fixes an ordering issue where the read of the SWQE fields necessary for creating the completion can race with a post send if the post send catches a send queue at the edge of being full. Is is possible in that situation to read SWQE fields that are being written. This new routine insures that SWQE fields are read prior to advancing the index that post send uses to determine queue fullness. Reviewed-by:
-
Jason Gunthorpe authored
The ib_dma_unmap_page() must match the length of the ib_dma_map_page(), which is based on odp_shift. Otherwise iommu resources under this API will not be properly freed. Signed-off-by:
-
Jason Gunthorpe authored
Discovered this was available already. Signed-off-by:
-
- 20 Jun, 2019 7 commits
-
-
Leon Romanovsky authored
The "end" variable is declared as unsigned and can't be negative, it leads to the situation where timeout limit is not honored, so let's convert logic to ensure that loop is bounded. drivers/infiniband/hw/hns/hns_roce_hw_v1.c: In function _hns_roce_v1_clear_hem_: drivers/infiniband/hw/hns/hns_roce_hw_v1.c:2471:12: warning: comparison of unsigned expression < 0 is always false [-Wtype-limits] 2471 | if (end < 0) { | ^ Fixes: 669cefb6 ("RDMA/hns: Remove jiffies operation in disable interrupt context") Signed-off-by: -
Leon Romanovsky authored
Update ib_umem_release() to behave similarly to kfree() and allow submitting NULL pointer as safe input to this function. Fixes: a52c8e24 ("RDMA: Clean destroy CQ in drivers do not return errors") Signed-off-by:
-
Lang Cheng authored
During removing the driver, we needs to notify the roce engine to stop working immediately,and symmetrically recycle the hardware resources requested during initialization. The hardware provides a command called function clear that can package these operations,so that the driver can only focus on releasing resources that applied from the operating system. This patch implements the call of this command. Signed-off-by:
Lang Cheng <chenglang@huawei.com> Signed-off-by:
Lijun Ou <oulijun@huawei.com> Signed-off-by:
-
Leon Romanovsky authored
All callers of destroy WQ are always success and there is no need to check their return value, so convert destroy_wq to be void. Signed-off-by:
Yuval Shaia <yuval.shaia@oracle.com> Signed-off-by:
-
Lijun Ou authored
hip08 can support up to 32768 wqes in one qp. currently if the wqe num is larger than 16384, the driver will lead a calltrace as follows. [21361.393725] Call trace: [21361.398605] hns_roce_v2_modify_qp+0xbcc/0x1360 [hns_roce_hw_v2] [21361.410627] hns_roce_modify_qp+0x1d8/0x2f8 [hns_roce] [21361.420906] _ib_modify_qp+0x70/0x118 [21361.428222] ib_modify_qp+0x14/0x1c [21361.435193] rt_ktest_modify_qp+0xb8/0x650 [rdma_test] [21361.445472] exec_modify_qp_cmd+0x110/0x4d8 [rdma_test] [21361.455924] rt_ktest_dispatch_cmd_3+0xa94/0x2edc [rdma_test] [21361.467422] rt_ktest_dispatch_cmd_2+0x9c/0x108 [rdma_test] [21361.478570] rt_ktest_dispatch_cmd+0x138/0x904 [rdma_test] [21361.489545] rt_ktest_dev_write+0x328/0x4b0 [rdma_test] [21361.499998] __vfs_write+0x38/0x15c [21361.506966] vfs_write+0xa8/0x1a0 [21361.513586] ksys_write+0x50/0xb0 [21361.520206] sys_write+0xc/0x14 [21361.526479] el0_svc_naked+0x30/0x34 [21361.533622] Code: 1ac10841 d37d7c22 0b000021 d37df021 (f86268c0) [21361.545815] ---[ end trace e2a1feb2c3d7f13c ]--- When the wqe num is larger than 16384, hns_roce_table_find will return an invalid mtt, this will lead an kernel paging requet error if the driver try to access it. It's the mtt design defect which can't support up to the max wqe num of hip08. This patch fixs it by replacing mtt with mtr for wqe. Fixes: 926a01dc ("RDMA/hns: Add QP operations support for hip08 SoC") Signed-off-by:
Xi Wang <wangxi11@huawei.com> Signed-off-by:
-
Lijun Ou authored
Currently, the code for getting umem and kmem buffers exist many files, this patch adds a group interfaces to simplify the buffers getting flow. Signed-off-by:
-
Lijun Ou authored
Currently, the MTT(memory translate table) design required a buffer space must has the same hopnum, but the hip08 hw can support mixed hopnum config in a buffer space. This patch adds the MTR(memory translate region) design for supporting mixed multihop. Signed-off-by:
-
- 19 Jun, 2019 8 commits
-
-
Doug Ledford authored
Sort the netlink policy array by netlink attribute name. This will make it easier in the future to find the entry you are looking for when you need to make changes, or to make sure you don't add the same entry twice. Fix the whitespace while we are there. Reviewed-by:
-
Maor Gottlieb authored
If FDB flow tables support decap operation, enable it on creation, This allows to perform decapsulation of tunnelled packets by steering rules. If FDB flow tables support reformat operation, enable it on creation as well. Signed-off-by:
Maor Gottlieb <maorg@mellanox.com> Reviewed-by:
Petr Vorel <pvorel@suse.cz> Signed-off-by:
-
Maor Gottlieb authored
When flow steering is created, then the encap support should consider the eswitch encap mode. If the eswitch flow table (FDB) supports encap then it shouldn't be supported on NIC RX flow tables. Fixes: 4adda112 ('RDMA/mlx5: Enable decap and packet reformat on flow tables') Signed-off-by:
-
Doug Ledford authored
Take mlx5-next so we can take a dependent two patch series next. Signed-off-by: -
Jason Gunthorpe authored
If invalidate_start returns with EAGAIN then the umem_rwsem needs to be unlocked as no invalidate_end will be called. Cc: <stable@vger.kernel.org> Fixes: ca748c39 ("RDMA/umem: Get rid of per_mm->notifier_count") Signed-off-by:
-
Geert Uytterhoeven authored
Signed-off-by:
Geert Uytterhoeven <geert+renesas@glider.be> Signed-off-by:
-
Jason Gunthorpe authored
Update the struct ib_client for all modules exporting cdevs related to the ibdevice to also implement RDMA_NLDEV_CMD_GET_CHARDEV. All cdevs are now autoloadable and discoverable by userspace over netlink instead of relying on sysfs. uverbs also exposes the DRIVER_ID for drivers that are able to support driver id binding in rdma-core. Signed-off-by:
-
Jason Gunthorpe authored
Allow userspace to issue a netlink query against the ib_device for something like "uverbs" and get back the char dev name, inode major/minor, and interface ABI information for "uverbs0". Since we are now in netlink this can also trigger a module autoload to make the uverbs device come into existence. Largely this will let us replace searching and reading inside sysfs to setup devices, and provides an alternative (using driver_id) to device name based provider binding for things like rxe. Signed-off-by:
-
- 17 Jun, 2019 1 commit
-
-
Jason Gunthorpe authored
This enum is exposed over the sysfs file 'node_type' and over netlink via RDMA_NLDEV_ATTR_DEV_NODE_TYPE, so declare it in the uapi headers. Signed-off-by:
-
- 16 Jun, 2019 2 commits
-
-
Maor Gottlieb authored
Add API to get the current Eswitch encap mode. It will be used in downstream patches to check if flow table can be created with encap support or not. Signed-off-by:
Parav Pandit <parav@mellanox.com>
-
Leon Romanovsky authored
Devlink has UAPI declaration for encap mode, so there is no need to be loose on the data get/set by drivers. Update call sites to use enum devlink_eswitch_encap_mode instead of plain u8. Suggested-by:
Jiri Pirko <jiri@mellanox.com> Reviewed-by:
-
- 13 Jun, 2019 12 commits
-
-
Yuval Avnery authored
Previously, EQ joined the chain notifier on creation. This forced the caller to be ready to handle events before creating the EQ through eq_create_generic interface. To help the caller control when the created EQ will be attached to the IRQ, add enable/disable API. Signed-off-by:
Yuval Avnery <yuvalav@mellanox.com> Signed-off-by:
Saeed Mahameed <saeedm@mellanox.com>
-
Ariel Levkovich authored
The patch modifies the IRQ allocation so that all async EQs are assigned to the same IRQ resulting in more available IRQs for completion EQs. The changes are using the support for IRQ sharing and EQ polling budget that was introduced in previous patches so when the shared interrupt is triggered, the kernel will serially call the handler of each of the sharing EQs with a certain budget of EQEs to poll in order to prevent starvation. Signed-off-by:
Ariel Levkovich <lariel@mellanox.com> Signed-off-by:
-
Yuval Avnery authored
struct mlx5_irq_info is an active object and not just info. Signed-off-by:
-
Yuval Avnery authored
Finalize IRQ separation and expose irq interface. Signed-off-by:
-
Yuval Avnery authored
IRQ interface should operate within the irq_table context. It should be independent of any EQ data structure. The interface that will be exposed: init/clenup, create/destroy, attach/detach Signed-off-by:
-
Yuval Avnery authored
IRQ allocation should be part of the IRQ table life-cycle. Signed-off-by:
-
Yuval Avnery authored
Affinity set/clear is part of the IRQ life-cycle. Signed-off-by:
-
Yuval Avnery authored
Rmap creation/deletion is part of the IRQ life-cycle. Signed-off-by:
-
Yuval Avnery authored
IRQ table should only exist for mlx5_core_dev for PF and VF only. EQ table of mediated devices should hold a pointer to the IRQ table of the parent PCI device. Signed-off-by:
-
Yuval Avnery authored
Instead of requesting IRQ with eq creation, IRQs will be requested before EQ table creation. Instead of freeing the IRQs after EQ destroy, free IRQs after eq table destroy. Signed-off-by:
-
Yuval Avnery authored
Multiple EQs may share the same IRQ in subsequent patches. Instead of calling the IRQ handler directly, the EQ will register to an atomic chain notfier. The Linux built-in shared IRQ is not used because it forces the caller to disable the IRQ and clear affinity before free_irq() can be called. This patch is the first step in the separation of IRQ and EQ logic. Signed-off-by:
-
Yuval Avnery authored
Multiple EQs may share the same irq in subsequent patches. To avoid starvation, a budget is set per EQ's interrupt handler. Because of this change, it is no longer required to check that MLX5_NUM_SPARE_EQE eqes were polled (to detect that arm is required). It is guaranteed that MLX5_NUM_SPARE_EQE > budget, therefore the handler will arm and exit the handler before all the entries in the eq are polled. In the scenario where the handler is out of budget and there are more EQEs to poll, arming the EQ guarantees that the HW will send another interrupt and the handler will be called again. Signed-off-by:
-
