- 25 Jan, 2019 2 commits
-
-
Masahiro Yamada authored
Currently, the Kbuild core manipulates header search paths in a crazy way [1]. To fix this mess, I want all Makefiles to add explicit $(srctree)/ to the search paths in the srctree. Some Makefiles are already written in that way, but not all. The goal of this work is to make the notation consistent, and finally get rid of the gross hacks. Having whitespaces after -I does not matter since commit 48f6e3cf ("kbuild: do not drop -I without parameter"). [1]: https://patchwork.kernel.org/patch/9632347/Signed-off-by:
Masahiro Yamada <yamada.masahiro@socionext.com> Acked-by:
Parvi Kaustubhi <pkaustub@cisco.com> Signed-off-by:
Jason Gunthorpe <jgg@mellanox.com>
-
Masahiro Yamada authored
The included headers are located in include/target/. I was able to build these drivers without the extra header search paths. Signed-off-by:
Bart Van Assche <bvanassche@acm.org> Signed-off-by:
-
- 24 Jan, 2019 19 commits
-
-
Yuval Avnery authored
The open-coded variant missed destroy of SELinux created QP, reuse already existing ib_detroy_qp() call and use this opportunity to clean ib_create_qp() from double prints and unclear exit paths. Reported-by:
Parav Pandit <parav@mellanox.com> Fixes: d291f1a6 ("IB/core: Enforce PKey security on QPs") Signed-off-by:
Yuval Avnery <yuvalav@mellanox.com> Reviewed-by:
Daniel Jurgens <danielj@mellanox.com> Signed-off-by:
Leon Romanovsky <leonro@mellanox.com> Signed-off-by:
-
Ira Weiny authored
Similar to the core change commit 5f1d43de ("IB/core: disable memory registration of filesystem-dax vmas") PSM should be prevented from using filesystem DAX pages. Signed-off-by:
Ira Weiny <ira.weiny@intel.com> Signed-off-by:
-
Yangyang Li authored
This patch adds qpc timer and cqc timer allocation support for hardware timeout retransmission in kernel space driver. Signed-off-by:
Yangyang Li <liyangyang20@huawei.com> Signed-off-by:
-
Yangyang Li authored
This patch adds SCC context clear support for DCQCN in kernel space driver. Signed-off-by:
-
Yangyang Li authored
This patch adds SCC context allocation and initialization support for DCQCN in kernel space driver. Signed-off-by:
-
Moni Shoua authored
When CONFIG_INFINIBAND_ON_DEMAND_PAGING is not set there is no caller to ib_alloc_odp_umem() so let's remove it. Signed-off-by:
Moni Shoua <monis@mellanox.com> Reviewed-by:
Artemy Kovalyov <artemyko@mellanox.com> Signed-off-by:
-
Moni Shoua authored
A sub-range in ODP implicit MR should take its write permission from the MR and not be set always to allow. Fixes: d07d1d70 ("IB/umem: Update on demand page (ODP) support") Signed-off-by:
-
Jason Gunthorpe authored
There is no reason for this __GFP_NOFAIL, none of the other routines in this file use it, and there is an error unwind here. NOFAIL should be reserved for special cases, not used by network drivers. Fixes: 6a0b6174 ("rdma/cxgb4: Add support for kernel mode SRQ's") Reported-by:
Nicholas Mc Guire <hofrat@osadl.org> Signed-off-by:
-
Bart Van Assche authored
This patch avoids that sparse complains about missing function declarations. Fixes: c9990ab3 ("RDMA/umem: Move all the ODP related stuff out of ucontext and into per_mm") Signed-off-by:
-
Bart Van Assche authored
This patch avoids that sparse complains about missing function declarations. Fixes: f27a0d50 ("RDMA/umem: Use umem->owning_mm inside ODP") Signed-off-by:
-
Greg Kroah-Hartman authored
When calling debugfs functions, there is no need to ever check the return value. The function can work or not, but the code logic should never do something different based on this. Signed-off-by:
Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by:
-
Greg Kroah-Hartman authored
When calling debugfs functions, there is no need to ever check the return value. The function can work or not, but the code logic should never do something different based on this. Signed-off-by:
-
Greg Kroah-Hartman authored
When calling debugfs functions, there is no need to ever check the return value. The function can work or not, but the code logic should never do something different based on this. Signed-off-by:
-
Greg Kroah-Hartman authored
When calling debugfs functions, there is no need to ever check the return value. The function can work or not, but the code logic should never do something different based on this. Signed-off-by:
-
Greg Kroah-Hartman authored
When calling debugfs functions, there is no need to ever check the return value. The function can work or not, but the code logic should never do something different based on this. Signed-off-by:
-
Greg Kroah-Hartman authored
When calling debugfs functions, there is no need to ever check the return value. The function can work or not, but the code logic should never do something different based on this. Signed-off-by:
-
Greg Kroah-Hartman authored
The macro was just making things harder to follow, and audit, so remove it and call debugfs_create_file() directly. Also, the macro did not need to warn about the call failing as no one should ever care about any debugfs functions failing. Signed-off-by:
-
Greg Kroah-Hartman authored
When calling debugfs functions, there is no need to ever check the return value. The function can work or not, but the code logic should never do something different based on this. Signed-off-by:
Steve Wise <swise@opengridcomputing.com> Signed-off-by:
-
Parav Pandit authored
As the comment block of nonseekable_open() describes, nonseekable_open() can never fail. Several places in kernel depend on this behavior. Therefore, simplify the umad module to depend on this basic kernel functionality. Signed-off-by:
-
- 23 Jan, 2019 1 commit
-
-
Parav Pandit authored
ib_umad_init_port_dev() holds the reference of a ib_umad_device instance. ib_umad_device contains standard core device and cdev. cdev holds the reference of its parent core device. file ops holds the reference to cdev using core kernel. Therefore, there is no need to hold additional reference while opening umad related char devices. While at it, add comments to bring clarity on releasing references to ib_umd_device. Signed-off-by:
-
- 22 Jan, 2019 4 commits
-
-
Maor Gottlieb authored
Two flow specifications can set the ip protocol field in the flow table entry: 1) IB_FLOW_SPEC_TCP/UDP/GRE - set the ip protocol accordingly. 2) IB_FLOW_SPEC_IPV4/6 - has ip_protocol field for users who want to receive specific L4 packets. We need to avoid overriding of the ip_protocol with zeros, in case that the user first put the L4 specification and only then the L3. Fixes: ca0d4753 ('IB/mlx5: Add support in TOS and protocol to flow steering') Signed-off-by:
Maor Gottlieb <maorg@mellanox.com> Signed-off-by:
-
Yishai Hadas authored
Add support for ODP for DEVX indirection mkey, it includes: - Recognizing its type as part of the radix tree lookup. - Use similar flow as done for the MW MKEY type. Signed-off-by:
Yishai Hadas <yishaih@mellanox.com> Reviewed-by:
-
Yishai Hadas authored
Manage indirection mkey upon DEVX flow to support ODP. To support a page fault event on the indirection mkey it needs to be part of the device mkey radix tree. Both the creation and the deletion flows for a DEVX object which is indirection mkey were adapted to handle that. Signed-off-by:
-
Yishai Hadas authored
Once an indirection MKEY is created umem valid bit shouldn't be set as this MKEY doesn't really hold a umem. Signed-off-by:
-
- 21 Jan, 2019 2 commits
-
-
Xiaofei Tan authored
AEQ overflow will be reported by hardware when too many asynchronous events occurred but not be handled in time. Normally, AEQ overflow error is not easy to occur. Once happened, we have to do physical function reset to recover. PF reset is implemented in two steps. Firstly, set reset level with ae_dev->ops->set_default_reset_request. Secondly, run reset with ae_dev->ops->reset_event. Signed-off-by:
Xiaofei Tan <tanxiaofei@huawei.com> Signed-off-by:
Yixian Liu <liuyixian@huawei.com> Signed-off-by:
-
Zhu Yanjun authored
The variable rxe in the function is not used. So it is removed. Signed-off-by:
Zhu Yanjun <yanjun.zhu@oracle.com> Signed-off-by:
-
- 18 Jan, 2019 7 commits
-
-
Israel Rukshin authored
ib_dma_map_sg() augments the SGL into a 'dma mapped SGL'. This process may change the number of entries and the lengths of each entry. Code that touches dma_address is iterating over the 'dma mapped SGL' and must use dma_nents which returned from ib_dma_map_sg(). ib_sg_to_pages() and ib_map_mr_sg() are using dma_address so they must use dma_nents. Fixes: 39405885 ("IB/iser: Port to new fast registration API") Fixes: bfe066e2 ("IB/iser: Reuse ib_sg_to_pages") Signed-off-by:
Israel Rukshin <israelr@mellanox.com> Reviewed-by:
Max Gurtovoy <maxg@mellanox.com> Acked-by:
Sagi Grimberg <sagi@grimberg.me> Signed-off-by:
-
YueHaibing authored
Remove unneeded semicolons. Signed-off-by:
YueHaibing <yuehaibing@huawei.com> Signed-off-by:
-
Mike Marciniszyn authored
These fields were missing from the trace. Add them. Fixes: c6ad9482 ("IB/rdmavt: Add tracing for cq entry and poll") 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:
-
Parav Pandit authored
RDMA cgroup registration routine always returns success, so simplify function to be void and run clang formatter over whole CONFIG_CGROUP_RDMA art of core_priv.h. This reduces unwinding error path for regular registration and future net namespace change functionality for rdma device. Signed-off-by:
Tejun Heo <tj@kernel.org> Signed-off-by:
-
YueHaibing authored
Fixes gcc '-Wunused-but-set-variable' warning: drivers/infiniband/hw/qedr/verbs.c: In function 'qedr_create_srq': drivers/infiniband/hw/qedr/verbs.c:1436:22: warning: variable 'ib_ctx' set but not used [-Wunused-but-set-variable] drivers/infiniband/hw/qedr/verbs.c: In function 'qedr_create_user_qp': drivers/infiniband/hw/qedr/verbs.c:1701:22: warning: variable 'ib_ctx' set but not used [-Wunused-but-set-variable] Fixes: b0ea0fa5 ("IB/{core,hw}: Have ib_umem_get extract the ib_ucontext from ib_udata") Signed-off-by:
-
Jason Gunthorpe authored
No reason to open code this loop. Signed-off-by:
-
Lijun Ou authored
When flush cqe, it needs to get the pointer of rq and sq from db address space of user and update it into qp context by modified qp. if rq does not exist, it will not get the value from db address space of user. Signed-off-by:
Lijun Ou <oulijun@huawei.com> Signed-off-by:
-
- 15 Jan, 2019 2 commits
-
-
Gustavo A. R. Silva authored
Replace kzalloc() function with its 2-factor argument form, kcalloc(). This patch replaces cases of: kzalloc(a * b, gfp) with: kcalloc(a, b, gfp) This code was detected with the help of Coccinelle. Signed-off-by:
Gustavo A. R. Silva <gustavo@embeddedor.com> Acked-by:
-
Raju Rangoju authored
The patch 944661dd: "RDMA/iw_cxgb4: atomically lookup ep and get a reference" from May 6, 2016, leads to the following Smatch complaint: drivers/infiniband/hw/cxgb4/cm.c:2953 terminate() error: we previously assumed 'ep' could be null (see line 2945) Fixes: 944661dd ("RDMA/iw_cxgb4: atomically lookup ep and get a reference") Reported-by:
Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by:
Raju Rangoju <rajur@chelsio.com> Signed-off-by:
-
- 14 Jan, 2019 3 commits
-
-
Myungho Jung authored
If cma_acquire_dev_by_src_ip() returns error in addr_handler(), the device state changes back to RDMA_CM_ADDR_BOUND but the resolved source IP address is still left. After that, if rdma_destroy_id() is called after rdma_listen(), the device is freed without removed from listen_any_list in cma_cancel_operation(). Revert to the previous IP address if acquiring device fails. Reported-by: syzbot+f3ce716af730c8f96637@syzkaller.appspotmail.com Signed-off-by:
Myungho Jung <mhjungk@gmail.com> Reviewed-by:
-
Dan Carpenter authored
This is from static analysis not from testing. Depending on the value of rcfw->cmdq_depth, then this might not cause an issue at runtime. The BITS_TO_LONGS() macro tells us how many longs it take to hold a bitmap. In other words, it divides by the number if bits per long and rounds up. Then we want to take that number and multiple by sizeof(long) to get the number of bytes to allocate. The code here does the multiplication first so the rounding up is done in the wrong place. So imagine we want to allocate 1 bit, then "(1 * 8) / 64 = 1" when we round up. But it should be "(1 / 64) * 8 = 8". In other words, because of the rounding difference we might allocate up to "sizeof(long) - 1" bytes fewer than intended. Fixes: 1ac5a404 ("RDMA/bnxt_re: Add bnxt_re RoCE driver") Signed-off-by:
Devesh Sharma <devesh.sharma@broadcom.com> Signed-off-by:
-
Parav Pandit authored
Introduce and use rdma_device_to_ibdev() API for those drivers which are registering one sysfs group and also use in ib_core. In subsequent patch, device->provider_ibdev one-to-one mapping is no longer holds true during accessing sysfs entries. Therefore, introduce an API rdma_device_to_ibdev() that provides such information. Signed-off-by:
-
