- 10 Jun, 2019 3 commits
-
-
Jason Gunthorpe authored
No reason for every driver to emit code to set this, just make it part of the driver's existing static const ops structure. Signed-off-by:
Jason Gunthorpe <jgg@mellanox.com> Reviewed-by:
Leon Romanovsky <leonro@mellanox.com> Signed-off-by:
-
Jason Gunthorpe authored
No reason for every driver to emit code to set this, just make it part of the driver's existing static const ops structure. Signed-off-by:
-
Jason Gunthorpe authored
This has been marked CONFIG_BROKEN for over a year now with no complaints. Delete the whole thing for good. The module provided the /dev/infiniband/ucmX interface. Signed-off-by:
-
- 07 Jun, 2019 7 commits
-
-
Matthew Wilcox authored
Signed-off-by:
Matthew Wilcox <willy@infradead.org> Signed-off-by:
-
Matthew Wilcox authored
Signed-off-by:
-
Gustavo A. R. Silva authored
Make use of the struct_size() helper instead of an open-coded version in order to avoid any potential type mistakes. This code was detected with the help of Coccinelle. Signed-off-by:
Gustavo A. R. Silva <gustavo@embeddedor.com> Signed-off-by:
-
Lijun Ou authored
When user post recv a srq with multiple sges, the hardware will get the last correct sge and count the sge numbers according to the specific identifier with lkey. For example, when the driver fills the sges with every wr less than the max sge that the user configured when creating srq, the hardware will stop getting the sge according to the specific lkey in the sge. However, it will always end with the first sge in the current post srq recv interface implementation. Fixes: c7bcb134 ("RDMA/hns: Add SRQ support for hip08 kernel mode") Signed-off-by:
Lijun Ou <oulijun@huawei.com> Signed-off-by:
-
Colin Ian King authored
A previous change incorrectly changed the inverted logic and logically negated the readl rather than the shifted readl result. Fix this by adding in missing parentheses around the expression that needs to be logically negated. Addresses-Coverity: ("Logically dead code") Fixes: 669cefb6 ("RDMA/hns: Remove jiffies operation in disable interrupt context") Signed-off-by:Colin Ian King <colin.king@canonical.com> Signed-off-by:
-
Bart Van Assche authored
The function srp_parse_in() is used both for parsing source address specifications and for target address specifications. Target addresses must have a port number. Having to specify a port number for source addresses is inconvenient. Make sure that srp_parse_in() supports again parsing addresses with no port number. Cc: <stable@vger.kernel.org> Fixes: c62adb7d ("IB/srp: Fix IPv6 address parsing") Signed-off-by:
Bart Van Assche <bvanassche@acm.org> Signed-off-by:
-
Kamal Heib authored
Add support for reporting link state for ipoib net devices. $ ip l set dev mlx4_ib0 up $ ethtool mlx4_ib0 | grep Link Link detected: yes $ ip l set dev mlx4_ib0 down $ ethtool mlx4_ib0 | grep Link Link detected: no Signed-off-by:
Kamal Heib <kamalheib1@gmail.com> Reviewed-by:
-
- 31 May, 2019 1 commit
-
-
Lijun Ou authored
When the user submits more than 32 work request to a srq queue at a time, it needs to find the corresponding number of entries in the bitmap in the idx queue. However, the original lookup function named ffs only processes 32 bits of the array element, When the number of srq wqe issued exceeds 32, the ffs will only process the lower 32 bits of the elements, it will not be able to get the correct wqe index for srq wqe. Signed-off-by:
Xi Wang <wangxi11@huawei.com> Signed-off-by:
-
- 30 May, 2019 4 commits
-
-
Dan Carpenter authored
If the kzalloc() fails then we should return ERR_PTR(-ENOMEM). In the current code it's possible that the kzalloc() fails and the radix_tree_insert() inserts the NULL pointer successfully and we return the NULL "elm" pointer to the caller. That results in a NULL pointer dereference. Fixes: 9ed3e5f4 ("IB/uverbs: Build the specs into a radix tree at runtime") Signed-off-by:
Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by:
-
Gustavo A. R. Silva authored
Make use of the struct_size() helper instead of an open-coded version in order to avoid any potential type mistakes, in particular in the context in which this code is being used. So, replace the following form: sizeof(struct opa_port_status_rsp) + num_vls * sizeof(struct _vls_pctrs) with: struct_size(rsp, vls, num_vls) and so on... Also, notice that variable size is unnecessary, hence it is removed. This code was detected with the help of Coccinelle. Signed-off-by:
Dennis Dalessandro <dennis.dalessandro@intel.com> Signed-off-by:
-
Gustavo A. R. Silva authored
Make use of the struct_size() helper instead of an open-coded version in order to avoid any potential type mistakes, in particular in the context in which this code is being used. So, replace the following form: sizeof(*pkt) + sizeof(pkt->addr[0])*n with: struct_size(pkt, addr, n) Also, notice that variable size is unnecessary, hence it is removed. This code was detected with the help of Coccinelle. Signed-off-by:
-
Gustavo A. R. Silva authored
Make use of the struct_size() helper instead of an open-coded version in order to avoid any potential type mistakes, in particular in the context in which this code is being used. So, replace the following form: sizeof(struct rvt_sge) * init_attr->cap.max_send_sge + sizeof(struct rvt_swqe) with: struct_size(swq, sg_list, init_attr->cap.max_send_sge) and so on... Also, notice that variable size is unnecessary, hence it is removed. This code was detected with the help of Coccinelle. Signed-off-by:
-
- 29 May, 2019 5 commits
-
-
Gal Pressman authored
Remove leftover includes that are no longer used from the driver. Reviewed-by:
Firas JahJah <firasj@amazon.com> Reviewed-by:
Yossi Leybovich <sleybo@amazon.com> Signed-off-by:
Gal Pressman <galpress@amazon.com> Signed-off-by:
-
Gal Pressman authored
When creating the chunks list the rdma_for_each_block() iterator is used in order to iterate over the payload in EFA_CHUNK_PAYLOAD_SIZE (device defined) strides. Reviewed-by:
Shiraz Saleem <shiraz.saleem@intel.com> Signed-off-by:
-
Gal Pressman authored
The admin commands abort flow is buggy (use-after-free) and not really necessary as it is guaranteed that after ib_unregister_device() is called there are no user verbs threads running in parallel, delete it. Suggested-by:
Jason Gunthorpe <jgg@ziepe.ca> Reviewed-by:
-
Gal Pressman authored
Use kvzalloc which attempts to allocate a physically continuous buffer and fallbacks to virtually continuous on failure instead of open coding it in the driver. The is_vmalloc_addr function is used to determine whether the buffer is physically continuous or not (which determines direct vs indirect MR registration mode). Suggested-by:
-
Dennis Dalessandro authored
A recent patch to hfi1 left behind a checkpatch error. Fixes: fb24ea52 ("drivers: Remove explicit invocations of mmiowb()") Signed-off-by:
-
- 27 May, 2019 13 commits
-
-
John Hubbard authored
For infiniband code that retains pages via get_user_pages*(), release those pages via the new put_user_page(), or put_user_pages*(), instead of put_page() This is a tiny part of the second step of fixing the problem described in [1]. The steps are: 1) Provide put_user_page*() routines, intended to be used for releasing pages that were pinned via get_user_pages*(). 2) Convert all of the call sites for get_user_pages*(), to invoke put_user_page*(), instead of put_page(). This involves dozens of call sites, and will take some time. 3) After (2) is complete, use get_user_pages*() and put_user_page*() to implement tracking of these pages. This tracking will be separate from the existing struct page refcounting. 4) Use the tracking and identification of these pages, to implement special handling (especially in writeback paths) when the pages are backed by a filesystem. Again, [1] provides details as to why that is desirable. [1] https://lwn.net/Articles/753027/ : "The Trouble with get_user_pages()" Reviewed-by:
Jan Kara <jack@suse.cz> Reviewed-by:
Ira Weiny <ira.weiny@intel.com> Reviewed-by:
Jérôme Glisse <jglisse@redhat.com> Acked-by:
John Hubbard <jhubbard@nvidia.com> Signed-off-by:
-
YueHaibing authored
Fixes gcc '-Wunused-but-set-variable' warning: drivers/infiniband/hw/hfi1/tid_rdma.c: In function tid_rdma_rcv_error: drivers/infiniband/hw/hfi1/tid_rdma.c:2029:7: warning: variable offset set but not used [-Wunused-but-set-variable] drivers/infiniband/hw/hfi1/tid_rdma.c: In function hfi1_rc_rcv_tid_rdma_ack: drivers/infiniband/hw/hfi1/tid_rdma.c:4555:35: warning: variable fspsn set but not used [-Wunused-but-set-variable] 'offset' is never used since introduction in commit d0d564a1 ("IB/hfi1: Add functions to receive TID RDMA READ request") 'fspsn' is never used since introduciotn in commit 9e93e967 ("IB/hfi1: Add a function to receive TID RDMA ACK packet") Signed-off-by:
YueHaibing <yuehaibing@huawei.com> Signed-off-by:
-
Lijun Ou authored
This patch makes the code more readable by removing magic numbers. Signed-off-by:
-
Lang Cheng authored
In some functions, the jiffies operation is unnecessary, and we can control delay using mdelay and udelay functions only. Especially, in hns_roce_v1_clear_hem, the function calls spin_lock_irqsave, the context disables interrupt, so we can not use jiffies and msleep functions. Signed-off-by:
Lang Cheng <chenglang@huawei.com> Signed-off-by:
-
Lang Cheng authored
When hip08 set gid, it will call spin_unlock_bh when send cmq. if main.ko call spin_lock_irqsave firstly, and the kernel is before commit f71b74bc ("irq/softirqs: Use lockdep to assert IRQs are disabled/enabled"), it will cause WARN_ON_ONCE because of calling spin_unlock_bh in disable context. In fact, the spin_lock_irqsave in main.ko is only used for hip06, and should be placed in hns_roce_hw_v1.c. hns_roce_hw_v2.c uses its own spin_unlock_bh and does not need main.ko manage spin_lock. Signed-off-by:
-
Lijun Ou authored
According to hip08 UM, the maximum number of CQEs supported by each CQ is 4M. Signed-off-by:
-
Yixian Liu authored
There is no need to print when communication is established, especially while lots of qp used by application. Signed-off-by:
Yixian Liu <liuyixian@huawei.com> Signed-off-by:
-
Nirranjan Kirubaharan authored
Add await in destroy_qp() so that all references to qp are dereferenced and qp is freed in destroy_qp() itself. This ensures freeing of all QPs before invocation of dealloc_ucontext(), which prevents loss of in use qpids stored in the ucontext. Signed-off-by:
Nirranjan Kirubaharan <nirranjan@chelsio.com> Reviewed-by:
Potnuri Bharat Teja <bharat@chelsio.com> Signed-off-by:
-
Leon Romanovsky authored
Change unconditional print of DMA address to be printed with special printk format type specifier. Signed-off-by:
-
Leon Romanovsky authored
Convert various sizeof call sites to be written in standard format sizeof(). Signed-off-by:
-
Leon Romanovsky authored
Resize CQ implementation was guarded by undeclared "notyet" define while cxgb3 was added to the kernel. Twelve years later, this call is still unimplemented, so safely delete it and fix improper return error code when .resize_cq() is not implemented. Fixes: b038ced7 ("RDMA/cxgb3: Add driver for Chelsio T3 RNIC") Signed-off-by:
-
Leon Romanovsky authored
DMA addresses like all other kernel addresses should be printed with special %p* formatter. It is needed to allow control of exposure of such information through a dedicated knob. Signed-off-by:
-
Leon Romanovsky authored
sizeof(a), sizeof a and sizeof (a) are all valid notations, but first is more readable format recommended by checkpatch.pl. Let's canonize it in cxgb3 drivers, so latter patches won't emit checkpatch warnings. As part of this change, a redundant memset() was removed. Signed-off-by:
-
- 22 May, 2019 1 commit
-
-
Leon Romanovsky authored
Drivers cannot check the udata for validity when doing destroy as there will be no way to report this error back to the uverbs. Since udata is new for destroy no driver should start to use it - instead drivers should opt for the ioctl interface and define it in a way where it cannot fail due to incorrect data. Remove the checks on udata construction so EFA is consistent with everything else. Signed-off-by:
-
- 21 May, 2019 6 commits
-
-
Leon Romanovsky authored
The same wait queue is initialized a couple of lines above. Fixes: 3c2d774c ("RDMA/nes: Add a driver for NetEffect RNICs") Signed-off-by:
-
Leon Romanovsky authored
There is no need to check existence of structures to be destroyed. Signed-off-by:
-
Leon Romanovsky authored
The destroy functions are always called with relevant structs, there is no need to check their existence. Signed-off-by:
-
Leon Romanovsky authored
Kernel destroy CQ flows can't fail and the returned value of ib_destroy_cq() is not interested in those flows. Signed-off-by:
-
Leon Romanovsky authored
There are nothing to do from user side with knowledge that destroy CQ fails. Signed-off-by:
-
Leon Romanovsky authored
There is no value in checking ib_destroy_cq() result and skipping to clear struct ic fields. This connection needs to be reinitialized anyway. Signed-off-by:
Santosh Shilimkar <santosh.shilimkar@oracle.com> Signed-off-by:
-
