#
2eb999b3 |
|
13-Jan-2024 |
Chengchang Tang <tangchengchang@huawei.com> |
RDMA/hns: Support adaptive PBL hopnum In the current implementation, a fixed addressing level is used for PBL. But in fact, the necessary addressing level is related to page size and the size of MR. This patch calculates the addressing level according to page size and the size of MR, and uses the addressing level to configure the PBL. Signed-off-by: Chengchang Tang <tangchengchang@huawei.com> Signed-off-by: Junxian Huang <huangjunxian6@hisilicon.com> Link: https://lore.kernel.org/r/20240113085935.2838701-6-huangjunxian6@hisilicon.com Signed-off-by: Leon Romanovsky <leon@kernel.org>
|
#
0ff6c977 |
|
13-Jan-2024 |
Chengchang Tang <tangchengchang@huawei.com> |
RDMA/hns: Support flexible umem page size In the current implementation, a fixed page size is used to configure the umem PBL, which is not flexible enough and is not conducive to the performance of the HW. Find a best page size to get better performance. Signed-off-by: Chengchang Tang <tangchengchang@huawei.com> Signed-off-by: Junxian Huang <huangjunxian6@hisilicon.com> Link: https://lore.kernel.org/r/20240113085935.2838701-5-huangjunxian6@hisilicon.com Signed-off-by: Leon Romanovsky <leon@kernel.org>
|
#
6afc8595 |
|
13-Jan-2024 |
Chengchang Tang <tangchengchang@huawei.com> |
RDMA/hns: Alloc MTR memory before alloc_mtt() MTR memory allocation do not depend on allocation of mtt. This patch moves the allocation of mtr before mtt in preparation for the following optimization. Signed-off-by: Chengchang Tang <tangchengchang@huawei.com> Signed-off-by: Junxian Huang <huangjunxian6@hisilicon.com> Link: https://lore.kernel.org/r/20240113085935.2838701-4-huangjunxian6@hisilicon.com Signed-off-by: Leon Romanovsky <leon@kernel.org>
|
#
4f5731b1 |
|
13-Jan-2024 |
Chengchang Tang <tangchengchang@huawei.com> |
RDMA/hns: Refactor mtr_init_buf_cfg() page_shift and page_cnt is only used in mtr_map_bufs(). And these parameter could be calculated indepedently. Strip the computation of page_shift and page_cnt from mtr_init_buf_cfg(), reducing the number of parameters of it. This helps reducing coupling between mtr_init_buf_cfg() and mtr_map_bufs(). Signed-off-by: Chengchang Tang <tangchengchang@huawei.com> Signed-off-by: Junxian Huang <huangjunxian6@hisilicon.com> Link: https://lore.kernel.org/r/20240113085935.2838701-3-huangjunxian6@hisilicon.com Signed-off-by: Leon Romanovsky <leon@kernel.org>
|
#
a4ca3410 |
|
13-Jan-2024 |
Chengchang Tang <tangchengchang@huawei.com> |
RDMA/hns: Refactor mtr find hns_roce_mtr_find() is a collection of multiple functions, and the return value is also difficult to understand, which is not conducive to modification and maintenance. Separate the function of obtaining MTR root BA from this function. And some adjustments has been made to improve readability. Signed-off-by: Chengchang Tang <tangchengchang@huawei.com> Signed-off-by: Junxian Huang <huangjunxian6@hisilicon.com> Link: https://lore.kernel.org/r/20240113085935.2838701-2-huangjunxian6@hisilicon.com Signed-off-by: Leon Romanovsky <leon@kernel.org>
|
#
f31683a5 |
|
07-Dec-2023 |
Chengchang Tang <tangchengchang@huawei.com> |
RDMA/hns: Remove unnecessary checks for NULL in mtr_alloc_bufs() ib_umem_get() never return NULL. Fixes: 3c873161a0d7 ("RDMA/hns: Add support for addressing when hopnum is 0") Signed-off-by: Chengchang Tang <tangchengchang@huawei.com> Signed-off-by: Junxian Huang <huangjunxian6@hisilicon.com> Link: https://lore.kernel.org/r/20231207114231.2872104-5-huangjunxian6@hisilicon.com Signed-off-by: Leon Romanovsky <leon@kernel.org>
|
#
eb7854d6 |
|
14-Nov-2023 |
Junxian Huang <huangjunxian6@hisilicon.com> |
RDMA/hns: Support SW stats with debugfs Support SW stats with debugfs. Query output: $ cat /sys/kernel/debug/hns_roce/hns_0/sw_stat/sw_stat aeqe --- 3341 ceqe --- 0 cmds --- 6764 cmds_err --- 0 posted_mbx --- 3344 polled_mbx --- 3 mbx_event --- 3341 qp_create_err --- 0 qp_modify_err --- 0 cq_create_err --- 0 cq_modify_err --- 0 srq_create_err --- 0 srq_modify_err --- 0 xrcd_alloc_err --- 0 mr_reg_err --- 0 mr_rereg_err --- 0 ah_create_err --- 0 mmap_err --- 0 uctx_alloc_err --- 0 Signed-off-by: Junxian Huang <huangjunxian6@hisilicon.com> Signed-off-by: Chengchang Tang <tangchengchang@huawei.com> Link: https://lore.kernel.org/r/20231114123449.1106162-4-huangjunxian6@hisilicon.com Signed-off-by: Leon Romanovsky <leon@kernel.org>
|
#
7f3969b1 |
|
12-May-2023 |
Chengchang Tang <tangchengchang@huawei.com> |
RDMA/hns: Fix base address table allocation For hns, the specification of an entry like resource (E.g. WQE/CQE/EQE) depends on BT page size, buf page size and hopnum. For user mode, the buf page size depends on UMEM. Therefore, the actual specification is controlled by BT page size and hopnum. The current BT page size and hopnum are obtained from firmware. This makes the driver inflexible and introduces unnecessary constraints. Resource allocation failures occur in many scenarios. This patch will calculate whether the BT page size set by firmware is sufficient before allocating BT, and increase the BT page size if it is insufficient. Fixes: 1133401412a9 ("RDMA/hns: Optimize base address table config flow for qp buffer") Link: https://lore.kernel.org/r/20230512092245.344442-3-huangjunxian6@hisilicon.com Signed-off-by: Chengchang Tang <tangchengchang@huawei.com> Signed-off-by: Junxian Huang <huangjunxian6@hisilicon.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
|
#
a115aa00 |
|
19-Nov-2022 |
Zhengchao Shao <shaozhengchao@huawei.com> |
RDMA/hns: fix memory leak in hns_roce_alloc_mr() When hns_roce_mr_enable() failed in hns_roce_alloc_mr(), mr_key is not released. Compiled test only. Fixes: 9b2cf76c9f05 ("RDMA/hns: Optimize PBL buffer allocation process") Signed-off-by: Zhengchao Shao <shaozhengchao@huawei.com> Link: https://lore.kernel.org/r/20221119070834.48502-1-shaozhengchao@huawei.com Signed-off-by: Leon Romanovsky <leon@kernel.org>
|
#
f0588567 |
|
22-Sep-2022 |
Guofeng Yue <yueguofeng@hisilicon.com> |
RDMA/hns: Unified Log Printing Style The first letter of the log information is changed to lowercase to keep the same style. Link: https://lore.kernel.org/r/20220922123315.3732205-13-xuhaoyue1@hisilicon.com Signed-off-by: Guofeng Yue <yueguofeng@hisilicon.com> Signed-off-by: Haoyue Xu <xuhaoyue1@hisilicon.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
|
#
5f652387 |
|
22-Sep-2022 |
Chengchang Tang <tangchengchang@huawei.com> |
RDMA/hns: Remove redundant 'phy_addr' in hns_roce_hem_list_find_mtt() This parameter has never been used. Remove it to simplify the function. Link: https://lore.kernel.org/r/20220922123315.3732205-8-xuhaoyue1@hisilicon.com Signed-off-by: Chengchang Tang <tangchengchang@huawei.com> Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com> Signed-off-by: Haoyue Xu <xuhaoyue1@hisilicon.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
|
#
241f9a27 |
|
21-Sep-2022 |
Daisuke Matsuda <matsuda-daisuke@fujitsu.com> |
IB: Set IOVA/LENGTH on IB_MR in core/uverbs layers Set 'iova' and 'length' on ib_mr in ib_uverbs and ib_core layers to let all drivers have the members filled. Also, this commit removes redundancy in the respective drivers. Previously, commit 04c0a5fcfcf65 ("IB/uverbs: Set IOVA on IB MR in uverbs layer") changed to set 'iova', but seems to have missed 'length' and the ib_core layer at that time. Fixes: 04c0a5fcfcf65 ("IB/uverbs: Set IOVA on IB MR in uverbs layer") Signed-off-by: Daisuke Matsuda <matsuda-daisuke@fujitsu.com> Link: https://lore.kernel.org/r/20220921080844.1616883-1-matsuda-daisuke@fujitsu.com Signed-off-by: Leon Romanovsky <leon@kernel.org>
|
#
cc377b9b |
|
26-Apr-2022 |
Guo Zhengkui <guozhengkui@vivo.com> |
RDMA/hns: Remove unnecessary ret variable from hns_roce_dereg_mr() Fix the following coccicheck warning: drivers/infiniband/hw/hns/hns_roce_mr.c:343:5-8: Unneeded variable: "ret". Return 0 directly instead. Link: https://lore.kernel.org/r/20220426070858.9098-1-guozhengkui@vivo.com Signed-off-by: Guo Zhengkui <guozhengkui@vivo.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
|
#
70f92521 |
|
09-Mar-2022 |
Yixing Liu <liuyixing1@huawei.com> |
RDMA/hns: Use the reserved loopback QPs to free MR before destroying MPT Before destroying MPT, the reserved loopback QPs send loopback IOs (one write operation per SL). Completing these loopback IOs represents that there isn't any outstanding request in MPT, then it's safe to destroy MPT. Link: https://lore.kernel.org/r/20220310042835.38634-1-liangwenpeng@huawei.com Signed-off-by: Yixing Liu <liuyixing1@huawei.com> Signed-off-by: Wenpeng Liang <liangwenpeng@huawei.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
|
#
904de76c |
|
01-Mar-2022 |
Wenpeng Liang <liangwenpeng@huawei.com> |
RDMA/hns: Clean up the return value check of hns_roce_alloc_cmd_mailbox() hns_roce_alloc_cmd_mailbox() never returns NULL, so the check should be IS_ERR(). And the error code should be converted as the function's return value. Link: https://lore.kernel.org/r/20220302064830.61706-8-liangwenpeng@huawei.com Signed-off-by: Wenpeng Liang <liangwenpeng@huawei.com> Reviewed-by: Leon Romanovsky <leonro@nvidia.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
|
#
cf7f8f5c |
|
01-Mar-2022 |
Chengchang Tang <tangchengchang@huawei.com> |
RDMA/hns: Remove similar code that configures the hardware contexts Remove duplicate code for creating and destroying hardware contexts via mailbox. Link: https://lore.kernel.org/r/20220302064830.61706-7-liangwenpeng@huawei.com Signed-off-by: Chengchang Tang <tangchengchang@huawei.com> Signed-off-by: Wenpeng Liang <liangwenpeng@huawei.com> Reviewed-by: Leon Romanovsky <leonro@nvidia.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
|
#
162e29fe |
|
01-Mar-2022 |
Chengchang Tang <tangchengchang@huawei.com> |
RDMA/hns: Refactor mailbox functions The current mailbox functions have too many parameters, making the code difficult to maintain. So construct a new structure mbox_msg to pass the information needed by mailbox. Link: https://lore.kernel.org/r/20220302064830.61706-6-liangwenpeng@huawei.com Signed-off-by: Chengchang Tang <tangchengchang@huawei.com> Signed-off-by: Wenpeng Liang <liangwenpeng@huawei.com> Reviewed-by: Leon Romanovsky <leonro@nvidia.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
|
#
479dc93b |
|
01-Mar-2022 |
Wenpeng Liang <liangwenpeng@huawei.com> |
RDMA/hns: Remove redundant parameter "mailbox" in the mailbox The parameter "out_param" of the mailbox is always null when the context is destroyed. So remove the function parameter "mailbox". Link: https://lore.kernel.org/r/20220302064830.61706-4-liangwenpeng@huawei.com Signed-off-by: Wenpeng Liang <liangwenpeng@huawei.com> Reviewed-by: Leon Romanovsky <leonro@nvidia.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
|
#
0018ed4b |
|
01-Mar-2022 |
Chengchang Tang <tangchengchang@huawei.com> |
RDMA/hns: Remove fixed parameter “timeout” in the mailbox The value of the function parameter “timeout” is unique. Therefore, it is unnecessary to specify the parameter “timeout” value each time. So remove it. Link: https://lore.kernel.org/r/20220302064830.61706-3-liangwenpeng@huawei.com Signed-off-by: Chengchang Tang <tangchengchang@huawei.com> Signed-off-by: Haoyue Xu <xuhaoyue1@hisilicon.com> Signed-off-by: Wenpeng Liang <liangwenpeng@huawei.com> Reviewed-by: Leon Romanovsky <leonro@nvidia.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
|
#
5a32949d |
|
01-Mar-2022 |
Chengchang Tang <tangchengchang@huawei.com> |
RDMA/hns: Remove the unused parameter "op_modifier" in mailbox The parameter "op_modifier" is only used for HIP06. It is useless for HIP08 and later versions. After removing HIP06, this parameter is no longer used, so remove it. Link: https://lore.kernel.org/r/20220302064830.61706-2-liangwenpeng@huawei.com Signed-off-by: Chengchang Tang <tangchengchang@huawei.com> Signed-off-by: Haoyue Xu <xuhaoyue1@hisilicon.com> Signed-off-by: Wenpeng Liang <liangwenpeng@huawei.com> Reviewed-by: Leon Romanovsky <leonro@nvidia.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
|
#
38d22088 |
|
20-Dec-2021 |
Chengchang Tang <tangchengchang@huawei.com> |
RDMA/hns: Remove support for HIP06 HIP06 is no longer supported. In order to reduce unnecessary maintenance, the code of HIP06 is removed. Link: https://lore.kernel.org/r/20211220130558.61585-1-liangwenpeng@huawei.com Signed-off-by: Chengchang Tang <tangchengchang@huawei.com> Signed-off-by: Wenpeng Liang <liangwenpeng@huawei.com> Reviewed-by: Leon Romanovsky <leonro@nvidia.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
|
#
d147583e |
|
19-Nov-2021 |
Xinhao Liu <liuxinhao5@hisilicon.com> |
RDMA/hns: Correct the type of variables participating in the shift operation The type of the variable participating in the shift operation should be an unsigned type instead of a signed type. Link: https://lore.kernel.org/r/20211119140208.40416-5-liangwenpeng@huawei.com Signed-off-by: Xinhao Liu <liuxinhao5@hisilicon.com> Signed-off-by: Wenpeng Liang <liangwenpeng@huawei.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
|
#
3aecfc38 |
|
19-Nov-2021 |
Xinhao Liu <liuxinhao5@hisilicon.com> |
RDMA/hns: Replace tab with space in the right-side comments There should be a space between the code and the comment on the right. Link: https://lore.kernel.org/r/20211119140208.40416-4-liangwenpeng@huawei.com Signed-off-by: Xinhao Liu <liuxinhao5@hisilicon.com> Signed-off-by: Wenpeng Liang <liangwenpeng@huawei.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
|
#
c4c7d7a4 |
|
04-Aug-2021 |
YueHaibing <yuehaibing@huawei.com> |
RDMA/hns: Fix return in hns_roce_rereg_user_mr() If re-registering an MR in hns_roce_rereg_user_mr(), we should return NULL instead of passing 0 to ERR_PTR for clarity. Fixes: 4e9fc1dae2a9 ("RDMA/hns: Optimize the MR registration process") Link: https://lore.kernel.org/r/20210804125939.20516-1-yuehaibing@huawei.com Signed-off-by: YueHaibing <yuehaibing@huawei.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
|
#
125073e7 |
|
18-Jun-2021 |
Yixing Liu <liuyixing1@huawei.com> |
RDMA/hns: Fix some print issues Remove redundant print and fix a character type mismatch. Fixes: 0e0ab04b5bbe ("RDMA/hns: Refactor the MTR creation flow") Link: https://lore.kernel.org/r/1624011020-16992-4-git-send-email-liweihang@huawei.com Signed-off-by: Yixing Liu <liuyixing1@huawei.com> Signed-off-by: Weihang Li <liweihang@huawei.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
|
#
2a38c0f1 |
|
18-Jun-2021 |
Yixing Liu <liuyixing1@huawei.com> |
RDMA/hns: Fix uninitialized variable A random value will be returned if the condition below is not met, so it needs to be initialized. Fixes: 9ea9a53ea93b ("RDMA/hns: Add mapped page count checking for MTR") Link: https://lore.kernel.org/r/1624011020-16992-3-git-send-email-liweihang@huawei.com Signed-off-by: Yixing Liu <liuyixing1@huawei.com> Signed-off-by: Weihang Li <liweihang@huawei.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
|
#
d38936f0 |
|
10-Jun-2021 |
Yangyang Li <liyangyang20@huawei.com> |
RDMA/hns: Use IDA interface to manage mtpt index Switch mtpt index allocation and release from hns own bitmap interface to IDA interface. Link: https://lore.kernel.org/r/1623325814-55737-5-git-send-email-liweihang@huawei.com Signed-off-by: Yangyang Li <liyangyang20@huawei.com> Signed-off-by: Weihang Li <liweihang@huawei.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
|
#
38e375b7 |
|
10-Jun-2021 |
Yangyang Li <liyangyang20@huawei.com> |
RDMA/hns: Remove unused RR mechanism Round-robin (RR) is no longer used in the allocation of the bitmap table, and all the function input parameters that use this mechanism are BITMAP_NO_RR. The code that defines and uses the RR needs to be deleted. Link: https://lore.kernel.org/r/1623325814-55737-4-git-send-email-liweihang@huawei.com Signed-off-by: Yangyang Li <liyangyang20@huawei.com> Signed-off-by: Weihang Li <liweihang@huawei.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
|
#
7b0006db |
|
21-May-2021 |
Xi Wang <wangxi11@huawei.com> |
RDMA/hns: Optimize the base address table config for MTR The base address table is allocated by dma allocator, and the size is always aligned to PAGE_SIZE. If a fixed size is used to allocate the table, the number of base address entries stored in the table will be smaller than that can actually stored. Link: https://lore.kernel.org/r/1621589395-2435-2-git-send-email-liweihang@huawei.com Signed-off-by: Xi Wang <wangxi11@huawei.com> Signed-off-by: Weihang Li <liweihang@huawei.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
|
#
9ea9a53e |
|
05-Feb-2021 |
Xi Wang <wangxi11@huawei.com> |
RDMA/hns: Add mapped page count checking for MTR Add the mapped page count checking flow to avoid invalid page size when creating MTR. Fixes: 38389eaa4db1 ("RDMA/hns: Add mtr support for mixed multihop addressing") Link: https://lore.kernel.org/r/1612517974-31867-4-git-send-email-liweihang@huawei.com Signed-off-by: Xi Wang <wangxi11@huawei.com> Signed-off-by: Weihang Li <liweihang@huawei.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
|
#
4e9fc1da |
|
23-Jan-2021 |
Lang Cheng <chenglang@huawei.com> |
RDMA/hns: Optimize the MR registration process When creating or re-registering an MR, storing the PDN, access flag and IOVA information ASAP can simplify the number of parameters passed into the subsequent process. Link: https://lore.kernel.org/r/1611395282-991-3-git-send-email-liweihang@huawei.com Reported-by: kernel test robot <lkp@intel.com> Signed-off-by: Lang Cheng <chenglang@huawei.com> Signed-off-by: Weihang Li <liweihang@huawei.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
|
#
0e0ab04b |
|
23-Jan-2021 |
Xi Wang <wangxi11@huawei.com> |
RDMA/hns: Refactor the MTR creation flow Split the hns_roce_mtr_create() into serval small functions, remove unused member in 'struct hns_roce_buf_attr' and delete unnecessary MTR page count check flow to make the MTR creation related codes clearer. Link: https://lore.kernel.org/r/1611395282-991-2-git-send-email-liweihang@huawei.com Signed-off-by: Xi Wang <wangxi11@huawei.com> Signed-off-by: Weihang Li <liweihang@huawei.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
|
#
779f2f5e |
|
21-Jan-2021 |
Lee Jones <lee.jones@linaro.org> |
RDMA/hw/hns/hns_roce_mr: Add missing description for 'hr_dev' param Fixes the following W=1 kernel build warning(s): drivers/infiniband/hw/hns/hns_roce_mr.c:1003: warning: Function parameter or member 'hr_dev' not described in 'hns_roce_mtr_create' Link: https://lore.kernel.org/r/20210121094519.2044049-6-lee.jones@linaro.org Cc: Lijun Ou <oulijun@huawei.com> Cc: Weihang Li <liweihang@huawei.com> Cc: Doug Ledford <dledford@redhat.com> Cc: Jason Gunthorpe <jgg@ziepe.ca> Cc: linux-rdma@vger.kernel.org Signed-off-by: Lee Jones <lee.jones@linaro.org> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
|
#
61918e9b |
|
10-Dec-2020 |
Yixing Liu <liuyixing1@huawei.com> |
RDMA/hns: Fix inaccurate prints Some %d in print format string should be %u, and some prints miss the useful errno or are in nonstandard format. Just fix above issues. Link: https://lore.kernel.org/r/1607650657-35992-11-git-send-email-liweihang@huawei.com Signed-off-by: Yixing Liu <liuyixing1@huawei.com> Signed-off-by: Weihang Li <liweihang@huawei.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
|
#
dcdc366a |
|
10-Dec-2020 |
Wenpeng Liang <liangwenpeng@huawei.com> |
RDMA/hns: Fix incorrect symbol types Types of some fields, variables and parameters of some functions should be unsigned. Link: https://lore.kernel.org/r/1607650657-35992-10-git-send-email-liweihang@huawei.com Signed-off-by: Wenpeng Liang <liangwenpeng@huawei.com> Signed-off-by: Weihang Li <liweihang@huawei.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
|
#
dc93a0d9 |
|
10-Dec-2020 |
Lang Cheng <chenglang@huawei.com> |
RDMA/hns: Fix coding style issues Just format the code without modifying anything, including fixing some redundant and missing blanks and spaces and changing the variable definition order. Link: https://lore.kernel.org/r/1607650657-35992-8-git-send-email-liweihang@huawei.com Signed-off-by: Lang Cheng <chenglang@huawei.com> Signed-off-by: Weihang Li <liweihang@huawei.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
|
#
6e0954b1 |
|
30-Nov-2020 |
Jason Gunthorpe <jgg@ziepe.ca> |
RDMA/uverbs: Allow drivers to create a new HW object during rereg_mr mlx5 has an ugly flow where it tries to allocate a new MR and replace the existing MR in the same memory during rereg. This is very complicated and buggy. Instead of trying to replace in-place inside the driver, provide support from uverbs to change the entire HW object assigned to a handle during rereg_mr. Since destroying a MR is allowed to fail (ie if a MW is pointing at it) and can't be detected in advance, the algorithm creates a completely new uobject to hold the new MR and swaps the IDR entries of the two objects. The old MR in the temporary IDR entry is destroyed, and if it fails rereg_mr succeeds and destruction is deferred to FD release. This complexity is why this cannot live in a driver safely. Link: https://lore.kernel.org/r/20201130075839.278575-4-leon@kernel.org Signed-off-by: Leon Romanovsky <leonro@nvidia.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
|
#
6f6e2dcb |
|
14-Nov-2020 |
Xi Wang <wangxi11@huawei.com> |
RDMA/hns: Refactor the hns_roce_buf allocation flow Add a group of flags to control the 'struct hns_roce_buf' allocation flow, this is used to support the caller running in atomic context. Link: https://lore.kernel.org/r/1605347916-15964-1-git-send-email-liweihang@huawei.com Signed-off-by: Xi Wang <wangxi11@huawei.com> Signed-off-by: Weihang Li <liweihang@huawei.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
|
#
d18bb3e1 |
|
02-Sep-2020 |
Leon Romanovsky <leon@kernel.org> |
RDMA: Clean MW allocation and free flows Move allocation and destruction of memory windows under ib_core responsibility and clean drivers to ensure that no updates to MW ib_core structures are done in driver layer. Link: https://lore.kernel.org/r/20200902081623.746359-2-leon@kernel.org Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
|
#
cf9ce3c8 |
|
04-Sep-2020 |
Jason Gunthorpe <jgg@ziepe.ca> |
RDMA/hns: Use ib_umem_num_dma_blocks() instead of opencoding mtr_umem_page_count() does the same thing, replace it with the core code. Also, ib_umem_find_best_pgsz() should always be called to check that the umem meets the page_size requirement. If there is a limited set of page_sizes that work it the pgsz_bitmap should be set to that set. 0 is a failure and the umem cannot be used. Lightly tidy the control flow to implement this flow properly. Link: https://lore.kernel.org/r/12-v2-270386b7e60b+28f4-umem_1_jgg@nvidia.com Acked-by: Weihang Li <liweihang@huawei.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
|
#
a2f3d447 |
|
08-Sep-2020 |
Lijun Ou <oulijun@huawei.com> |
RDMA/hns: Avoid unncessary initialization Some variables have been initialized when used. As a result, here removes some unncessary initial assignment. Link: https://lore.kernel.org/r/1599547944-30671-1-git-send-email-oulijun@huawei.com Signed-off-by: Lijun Ou <oulijun@huawei.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
|
#
79d52083 |
|
14-Jul-2020 |
Xi Wang <wangxi11@huawei.com> |
RDMA/hns: Fix wrong PBL offset when VA is not aligned to PAGE_SIZE ROCE uses "VA % buf_page_size" to caclulate the offset in the PBL's first page, the actual PA corresponding to the MR's VA is equal to MR's PA plus this offset. The first PA in PBL has already been aligned to PAGE_SIZE after calling ib_umem_get(), but the MR's VA may not. If the buf_page_size is smaller than the PAGE_SIZE, this will lead the HW to access the wrong memory because the offset is smaller than expected. Fixes: 9b2cf76c9f05 ("RDMA/hns: Optimize PBL buffer allocation process") Link: https://lore.kernel.org/r/1594726935-45666-1-git-send-email-liweihang@huawei.com Signed-off-by: Xi Wang <wangxi11@huawei.com> Signed-off-by: Weihang Li <liweihang@huawei.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
|
#
cc33b23e |
|
30-Jun-2020 |
Xi Wang <wangxi11@huawei.com> |
RDMA/hns: Optimize MTR level-0 addressing to access huge page If hns ROCEE is set to level-0 addressing, the length of the entire buffer can be used as the page size. The driver needn't to split the buffer into small units because all pages are continuous. Link: https://lore.kernel.org/r/1593525696-12570-1-git-send-email-liweihang@huawei.com Signed-off-by: Xi Wang <wangxi11@huawei.com> Signed-off-by: Weihang Li <liweihang@huawei.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
|
#
42a3b153 |
|
06-Jul-2020 |
Gal Pressman <galpress@amazon.com> |
RDMA: Remove the udata parameter from alloc_mr callback Allocating an MR flow can only be initiated by kernel users, and not from userspace so a udata parameter is redundant. Link: https://lore.kernel.org/r/20200706120343.10816-4-galpress@amazon.com Signed-off-by: Gal Pressman <galpress@amazon.com> Reviewed-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
|
#
98a61519 |
|
16-Jun-2020 |
Yangyang Li <liyangyang20@huawei.com> |
RDMA/hns: Fix a calltrace when registering MR from userspace ibmr.device is assigned after MR is successfully registered, but both write_mtpt() and frmr_write_mtpt() accesses it during the mr registration process, which may cause the following error when trying to register MR in userspace and pbl_hop_num is set to 0. pc : hns_roce_mtr_find+0xa0/0x200 [hns_roce] lr : set_mtpt_pbl+0x54/0x118 [hns_roce_hw_v2] sp : ffff00023e73ba20 x29: ffff00023e73ba20 x28: ffff00023e73bad8 x27: 0000000000000000 x26: 0000000000000000 x25: 0000000000000002 x24: 0000000000000000 x23: ffff00023e73bad0 x22: 0000000000000000 x21: ffff0000094d9000 x20: 0000000000000000 x19: ffff8020a6bdb2c0 x18: 0000000000000000 x17: 0000000000000000 x16: 0000000000000000 x15: 0000000000000000 x14: 0000000000000000 x13: 0140000000000000 x12: 0040000000000041 x11: ffff000240000000 x10: 0000000000001000 x9 : 0000000000000000 x8 : ffff802fb7558480 x7 : ffff802fb7558480 x6 : 000000000003483d x5 : ffff00023e73bad0 x4 : 0000000000000002 x3 : ffff00023e73bad8 x2 : 0000000000000000 x1 : 0000000000000000 x0 : ffff0000094d9708 Call trace: hns_roce_mtr_find+0xa0/0x200 [hns_roce] set_mtpt_pbl+0x54/0x118 [hns_roce_hw_v2] hns_roce_v2_write_mtpt+0x14c/0x168 [hns_roce_hw_v2] hns_roce_mr_enable+0x6c/0x148 [hns_roce] hns_roce_reg_user_mr+0xd8/0x130 [hns_roce] ib_uverbs_reg_mr+0x14c/0x2e0 [ib_uverbs] ib_uverbs_write+0x27c/0x3e8 [ib_uverbs] __vfs_write+0x60/0x190 vfs_write+0xac/0x1c0 ksys_write+0x6c/0xd8 __arm64_sys_write+0x24/0x30 el0_svc_common+0x78/0x130 el0_svc_handler+0x38/0x78 el0_svc+0x8/0xc Solve above issue by adding a pointer of structure hns_roce_dev as a parameter of write_mtpt() and frmr_write_mtpt(), so that both of these functions can access it before finishing MR's registration. Fixes: 9b2cf76c9f05 ("RDMA/hns: Optimize PBL buffer allocation process") Link: https://lore.kernel.org/r/1592314629-51715-1-git-send-email-liweihang@huawei.com Signed-off-by: Yangyang Li <liyangyang20@huawei.com> Signed-off-by: Weihang Li <liweihang@huawei.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
#
8e029d38 |
|
20-May-2020 |
Xi Wang <wangxi11@huawei.com> |
RDMA/hns: Optimize the usage of MTR Currently, the MTR region is configed before hns_roce_mtr_map() is invoked, but in some scenarios, the region is configed at MTR creation, the caller need to store this config and call hns_roce_mtr_map() later. So optimize the usage by wrapping the MTR region config into MTR. Link: https://lore.kernel.org/r/1589982799-28728-10-git-send-email-liweihang@huawei.com Signed-off-by: Xi Wang <wangxi11@huawei.com> Signed-off-by: Weihang Li <liweihang@huawei.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
#
82d07a4e |
|
20-May-2020 |
Weihang Li <liweihang@huawei.com> |
RDMA/hns: Change all page_shift to unsigned page_shift is used to calculate the page size, it's always non-negative, and should be in type of unsigned. Link: https://lore.kernel.org/r/1589982799-28728-7-git-send-email-liweihang@huawei.com Signed-off-by: Weihang Li <liweihang@huawei.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
#
9581a356 |
|
08-May-2020 |
Xi Wang <wangxi11@huawei.com> |
RDMA/hns: Rename macro for defining hns hardware page size Rename the PAGE_ADDR_SHIFT as HNS_HW_PAGE_SHIFT to make code more readable. Link: https://lore.kernel.org/r/1588931159-56875-9-git-send-email-liweihang@huawei.com Signed-off-by: Xi Wang <wangxi11@huawei.com> Signed-off-by: Weihang Li <liweihang@huawei.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
#
7b611d2f |
|
08-May-2020 |
Lang Cheng <chenglang@huawei.com> |
RDMA/hns: Store mr len information into mr obj The length information should be stored in the struct ib_mr object, otherwise the length value of a valid mr object would always be 0. Link: https://lore.kernel.org/r/1588931159-56875-7-git-send-email-liweihang@huawei.com Signed-off-by: Lang Cheng <chenglang@huawei.com> Signed-off-by: Weihang Li <liweihang@huawei.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
#
2929c40f |
|
28-Apr-2020 |
Xi Wang <wangxi11@huawei.com> |
RDMA/hns: Remove unused MTT functions The MTT (Memory Translate Table) interface is no longer used to configure the buffer address to BT (Base Address Table) that requires driver mapping. Because the MTT is not compatible with multi-hop addressing of the hip08, it is replaced by MTR (Memory Translate Region) interface, and all the MTT functions should be removed. Link: https://lore.kernel.org/r/1588071823-40200-3-git-send-email-liweihang@huawei.com Signed-off-by: Xi Wang <wangxi11@huawei.com> Signed-off-by: Weihang Li <liweihang@huawei.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
#
9b2cf76c |
|
28-Apr-2020 |
Xi Wang <wangxi11@huawei.com> |
RDMA/hns: Optimize PBL buffer allocation process PBL table has its own implementation for multi-hop addressing currently, but for the hardware, all table's addressing use the same logic, there is no need to implement repeatedly. So optimize the PBL buffer allocation process by using the mtr's interfaces. Link: https://lore.kernel.org/r/1588071823-40200-2-git-send-email-liweihang@huawei.com Signed-off-by: Xi Wang <wangxi11@huawei.com> Signed-off-by: Lang Cheng <chenglang@huawei.com> Signed-off-by: Weihang Li <liweihang@huawei.com> Reported-by: kbuild test robot <lkp@intel.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
#
cc23267a |
|
13-Apr-2020 |
Xi Wang <wangxi11@huawei.com> |
RDMA/hns: Optimize hns buffer allocation flow When the value of nbufs is 1, the buffer is in direct mode, which may cause confusion. So optimizes current codes to make it easier to maintain and understand. Link: https://lore.kernel.org/r/1586779091-51410-3-git-send-email-liweihang@huawei.com Signed-off-by: Xi Wang <wangxi11@huawei.com> Signed-off-by: Lang Cheng <chenglang@huawei.com> Signed-off-by: Weihang Li <liweihang@huawei.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
#
3c873161 |
|
13-Apr-2020 |
Xi Wang <wangxi11@huawei.com> |
RDMA/hns: Add support for addressing when hopnum is 0 Currently, WQE and EQE table have already used the mtr interface to config and access memory by multi-hop addressing when hopnum is from 1 to 3. But if hopnum is 0, each table need write its own but repetitive logic, and many duplicate code exists in the mtr interfaces invoke process. So wraps the public logic as 3 functions: hns_roce_mtr_create(), hns_roce_mtr_destroy() and hns_roce_mtr_map() to support hopnum ranges from 0 to 3. In addition, makes the mtr interfaces easier to use. Link: https://lore.kernel.org/r/1586779091-51410-2-git-send-email-liweihang@huawei.com Signed-off-by: Xi Wang <wangxi11@huawei.com> Signed-off-by: Weihang Li <liweihang@huawei.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
#
30d41e18 |
|
19-Mar-2020 |
Weihang Li <liweihang@huawei.com> |
RDMA/hns: Fix a wrong judgment of return value hns_roce_alloc_mtt_range() never return -1, ret should be checked whether it is zero instead of -1. Fixes: 1ceb0b11a8a2 ("RDMA/hns: Fix non-standard error codes") Link: https://lore.kernel.org/r/1584674622-52773-3-git-send-email-liweihang@huawei.com Signed-off-by: Weihang Li <liweihang@huawei.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
#
c320e527 |
|
15-Jan-2020 |
Moni Shoua <monis@mellanox.com> |
IB: Allow calls to ib_umem_get from kernel ULPs So far the assumption was that ib_umem_get() and ib_umem_odp_get() are called from flows that start in UVERBS and therefore has a user context. This assumption restricts flows that are initiated by ULPs and need the service that ib_umem_get() provides. This patch changes ib_umem_get() and ib_umem_odp_get() to get IB device directly by relying on the fact that both UVERBS and ULPs sets that field correctly. Reviewed-by: Guy Levi <guyle@mellanox.com> Signed-off-by: Moni Shoua <monis@mellanox.com> Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
|
#
eca44507 |
|
06-Jan-2020 |
Wenpeng Liang <liangwenpeng@huawei.com> |
RDMA/hns: Avoid printing address of mtt page Address of a page shouldn't be printed in case of security issues. Link: https://lore.kernel.org/r/1578313276-29080-2-git-send-email-liweihang@huawei.com Signed-off-by: Wenpeng Liang <liangwenpeng@huawei.com> Signed-off-by: Weihang Li <liweihang@huawei.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
#
72b894b0 |
|
13-Nov-2019 |
Christoph Hellwig <hch@lst.de> |
IB/umem: remove the dmasync argument to ib_umem_get The argument is always ignored, so remove it. Link: https://lore.kernel.org/r/20191113073214.9514-3-hch@lst.de Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Jason Gunthorpe <jgg@mellanox.com> Acked-by: Michal Kalderon <michal.kalderon@marvell.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
#
1ceb0b11 |
|
05-Nov-2019 |
Yixian Liu <liuyixian@huawei.com> |
RDMA/hns: Fix non-standard error codes It is better to return a linux error code than define a private constant. Link: https://lore.kernel.org/r/1572952082-6681-9-git-send-email-liweihang@hisilicon.com Signed-off-by: Yixian Liu <liuyixian@huawei.com> Signed-off-by: Wenpeng Liang <liangwenpeng@huawei.com> Signed-off-by: Weihang Li <liweihang@hisilicon.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
#
6eef5242 |
|
05-Nov-2019 |
Yixing Liu <liuyixing1@huawei.com> |
RDMA/hns: Replace not intuitive function/macro names Replace "sw2hw" and "hw2sw" which is hard to understand with "create" and "destroy". Link: https://lore.kernel.org/r/1572952082-6681-6-git-send-email-liweihang@hisilicon.com Signed-off-by: Yixing Liu <liuyixing1@huawei.com> Signed-off-by: Weihang Li <liweihang@hisilicon.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
#
bfe86035 |
|
21-Aug-2019 |
Lang Cheng <chenglang@huawei.com> |
RDMA/hns: Fix cast from or to restricted __le32 for driver Sparse is whining about the u32 and __le32 mixed usage in the driver. The roce_set_field() is used to __le32 data of hardware only. If a variable is not delivered to the hardware, the __le32 type and related operations are not required. Signed-off-by: Lang Cheng <chenglang@huawei.com> Link: https://lore.kernel.org/r/1566393276-42555-6-git-send-email-oulijun@huawei.com Signed-off-by: Doug Ledford <dledford@redhat.com>
|
#
6def7de6 |
|
08-Aug-2019 |
Lang Cheng <chenglang@huawei.com> |
RDMA/hns: Update some comments style Here removes some useless comments and adds necessary spaces to another comments. Signed-off-by: Lang Cheng <chenglang@huawei.com> Link: https://lore.kernel.org/r/1565276034-97329-7-git-send-email-oulijun@huawei.com Signed-off-by: Doug Ledford <dledford@redhat.com>
|
#
3ee0e170 |
|
08-Jul-2019 |
Lijun Ou <oulijun@huawei.com> |
RDMA/hns: Package for hns_roce_rereg_user_mr function Move some code of the hns_roce_rereg_user_mr() function into an independent function in oder to improve readability. Link: https://lore.kernel.org/r/1562593285-8037-8-git-send-email-oulijun@huawei.com Signed-off-by: Lang Cheng <chenglang@huawei.com> Signed-off-by: Lijun Ou <oulijun@huawei.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
#
89b4b70b |
|
08-Jul-2019 |
chenglang <chenglang@huawei.com> |
RDMA/hns: Optimize hns_roce_mhop_alloc function. Move some lines for allocating multi-hop addressing into independent functions in order to improve readability. Link: https://lore.kernel.org/r/1562593285-8037-7-git-send-email-oulijun@huawei.com Signed-off-by: Lang Cheng <chenglang@huawei.com> Signed-off-by: Lijun Ou <oulijun@huawei.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
#
e9816ddf |
|
19-Jun-2019 |
Lijun Ou <oulijun@huawei.com> |
RDMA/hns: Cleanup unnecessary exported symbols This patch removes the hns-roce.ko for cleanup all the exported symbols in common part. Signed-off-by: Xi Wang <wangxi11@huawei.com> Signed-off-by: Lijun Ou <oulijun@huawei.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
#
836a0fbb |
|
16-Jun-2019 |
Leon Romanovsky <leon@kernel.org> |
RDMA: Check umem pointer validity prior to release Update ib_umem_release() to behave similarly to kfree() and allow submitting NULL pointer as safe input to this function. Fixes: a52c8e2469c3 ("RDMA: Clean destroy CQ in drivers do not return errors") Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
|
#
38389eaa |
|
08-Jun-2019 |
Lijun Ou <oulijun@huawei.com> |
RDMA/hns: Add mtr support for mixed multihop addressing 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: Xi Wang <wangxi11@huawei.com> Signed-off-by: Lijun Ou <oulijun@huawei.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
|
#
2a3d923f |
|
24-May-2019 |
Lijun Ou <oulijun@huawei.com> |
RDMA/hns: Replace magic numbers with #defines This patch makes the code more readable by removing magic numbers. Signed-off-by: Xi Wang <wangxi11@huawei.com> Signed-off-by: Lijun Ou <oulijun@huawei.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
#
4772e03d |
|
06-Apr-2019 |
Lijun Ou <oulijun@huawei.com> |
RDMA/hns: Fix bug that caused srq creation to fail Due to the incorrect use of the seg and obj information, the position of the mtt is calculated incorrectly, and the free space of the page is not enough to store the entire mtt, resulting in access to the next page. This patch fixes this problem. Unable to handle kernel paging request at virtual address ffff00006e3cd000 ... Call trace: hns_roce_write_mtt+0x154/0x2f0 [hns_roce] hns_roce_buf_write_mtt+0xa8/0xd8 [hns_roce] hns_roce_create_srq+0x74c/0x808 [hns_roce] ib_create_srq+0x28/0xc8 Fixes: 0203b14c4f32 ("RDMA/hns: Unify the calculation for hem index in hip08") Signed-off-by: chenglang <chenglang@huawei.com> Signed-off-by: Lijun Ou <oulijun@huawei.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
#
c4367a26 |
|
31-Mar-2019 |
Shamir Rabinovitch <shamir.rabinovitch@oracle.com> |
IB: Pass uverbs_attr_bundle down ib_x destroy path The uverbs_attr_bundle with the ucontext is sent down to the drivers ib_x destroy path as ib_udata. The next patch will use the ib_udata to free the drivers destroy path from the dependency in 'uobject->context' as we already did for the create path. Signed-off-by: Shamir Rabinovitch <shamir.rabinovitch@oracle.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
#
3856ec55 |
|
11-Feb-2019 |
Shiraz, Saleem <shiraz.saleem@intel.com> |
RDMA/hns: Use for_each_sg_dma_page iterator on umem SGL Use the for_each_sg_dma_page iterator variant to walk the umem DMA-mapped SGL and get the page DMA address. This avoids the extra loop to iterate pages in the SGE when for_each_sg iterator is used. Additionally, purge umem->page_shift usage in the driver as its only relevant for ODP MRs. Use system page size and shift instead. Signed-off-by: Shiraz, Saleem <shiraz.saleem@intel.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
#
b0ea0fa5 |
|
09-Jan-2019 |
Jason Gunthorpe <jgg@ziepe.ca> |
IB/{core,hw}: Have ib_umem_get extract the ib_ucontext from ib_udata ib_umem_get() can only be called in a method callback, which always has a udata parameter. This allows ib_umem_get() to derive the ucontext pointer directly from the udata without requiring the drivers to find it in some way or another. Signed-off-by: Jason Gunthorpe <jgg@mellanox.com> Signed-off-by: Shamir Rabinovitch <shamir.rabinovitch@oracle.com>
|
#
4af07f01 |
|
08-Dec-2018 |
Lijun Ou <oulijun@huawei.com> |
RDMA/hns: Fix the bug while use multi-hop of pbl It will prevent multiply overflow when defines the pbl for u64 type. Signed-off-by: Lijun Ou <oulijun@huawei.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
#
c7bcb134 |
|
24-Nov-2018 |
Lijun Ou <oulijun@huawei.com> |
RDMA/hns: Add SRQ support for hip08 kernel mode This patch implements the SRQ(Share Receive Queue) verbs and update the poll cq verbs to deal with SRQ complentions. Signed-off-by: Lijun Ou <oulijun@huawei.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
#
68a997c5 |
|
05-Oct-2018 |
Yixian Liu <liuyixian@huawei.com> |
RDMA/hns: Add FRMR support for hip08 This patch adds fast register physical memory region (FRMR) support for hip08. Signed-off-by: Yixian Liu <liuyixian@huawei.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
#
c7c28191 |
|
23-Sep-2018 |
Yixian Liu <liuyixian@huawei.com> |
RDMA/hns: Add MW support for hip08 This patch adds memory window (mw) support in the kernel space. Signed-off-by: Yixian Liu <liuyixian@huawei.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
#
fad953ce |
|
12-Jun-2018 |
Kees Cook <keescook@chromium.org> |
treewide: Use array_size() in vzalloc() The vzalloc() function has no 2-factor argument form, so multiplication factors need to be wrapped in array_size(). This patch replaces cases of: vzalloc(a * b) with: vzalloc(array_size(a, b)) as well as handling cases of: vzalloc(a * b * c) with: vzalloc(array3_size(a, b, c)) This does, however, attempt to ignore constant size factors like: vzalloc(4 * 1024) though any constants defined via macros get caught up in the conversion. Any factors with a sizeof() of "unsigned char", "char", and "u8" were dropped, since they're redundant. The Coccinelle script used for this was: // Fix redundant parens around sizeof(). @@ type TYPE; expression THING, E; @@ ( vzalloc( - (sizeof(TYPE)) * E + sizeof(TYPE) * E , ...) | vzalloc( - (sizeof(THING)) * E + sizeof(THING) * E , ...) ) // Drop single-byte sizes and redundant parens. @@ expression COUNT; typedef u8; typedef __u8; @@ ( vzalloc( - sizeof(u8) * (COUNT) + COUNT , ...) | vzalloc( - sizeof(__u8) * (COUNT) + COUNT , ...) | vzalloc( - sizeof(char) * (COUNT) + COUNT , ...) | vzalloc( - sizeof(unsigned char) * (COUNT) + COUNT , ...) | vzalloc( - sizeof(u8) * COUNT + COUNT , ...) | vzalloc( - sizeof(__u8) * COUNT + COUNT , ...) | vzalloc( - sizeof(char) * COUNT + COUNT , ...) | vzalloc( - sizeof(unsigned char) * COUNT + COUNT , ...) ) // 2-factor product with sizeof(type/expression) and identifier or constant. @@ type TYPE; expression THING; identifier COUNT_ID; constant COUNT_CONST; @@ ( vzalloc( - sizeof(TYPE) * (COUNT_ID) + array_size(COUNT_ID, sizeof(TYPE)) , ...) | vzalloc( - sizeof(TYPE) * COUNT_ID + array_size(COUNT_ID, sizeof(TYPE)) , ...) | vzalloc( - sizeof(TYPE) * (COUNT_CONST) + array_size(COUNT_CONST, sizeof(TYPE)) , ...) | vzalloc( - sizeof(TYPE) * COUNT_CONST + array_size(COUNT_CONST, sizeof(TYPE)) , ...) | vzalloc( - sizeof(THING) * (COUNT_ID) + array_size(COUNT_ID, sizeof(THING)) , ...) | vzalloc( - sizeof(THING) * COUNT_ID + array_size(COUNT_ID, sizeof(THING)) , ...) | vzalloc( - sizeof(THING) * (COUNT_CONST) + array_size(COUNT_CONST, sizeof(THING)) , ...) | vzalloc( - sizeof(THING) * COUNT_CONST + array_size(COUNT_CONST, sizeof(THING)) , ...) ) // 2-factor product, only identifiers. @@ identifier SIZE, COUNT; @@ vzalloc( - SIZE * COUNT + array_size(COUNT, SIZE) , ...) // 3-factor product with 1 sizeof(type) or sizeof(expression), with // redundant parens removed. @@ expression THING; identifier STRIDE, COUNT; type TYPE; @@ ( vzalloc( - sizeof(TYPE) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | vzalloc( - sizeof(TYPE) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | vzalloc( - sizeof(TYPE) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | vzalloc( - sizeof(TYPE) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | vzalloc( - sizeof(THING) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | vzalloc( - sizeof(THING) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | vzalloc( - sizeof(THING) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | vzalloc( - sizeof(THING) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) ) // 3-factor product with 2 sizeof(variable), with redundant parens removed. @@ expression THING1, THING2; identifier COUNT; type TYPE1, TYPE2; @@ ( vzalloc( - sizeof(TYPE1) * sizeof(TYPE2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | vzalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | vzalloc( - sizeof(THING1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | vzalloc( - sizeof(THING1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | vzalloc( - sizeof(TYPE1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) | vzalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) ) // 3-factor product, only identifiers, with redundant parens removed. @@ identifier STRIDE, SIZE, COUNT; @@ ( vzalloc( - (COUNT) * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | vzalloc( - COUNT * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | vzalloc( - COUNT * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | vzalloc( - (COUNT) * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | vzalloc( - COUNT * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | vzalloc( - (COUNT) * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | vzalloc( - (COUNT) * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | vzalloc( - COUNT * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) ) // Any remaining multi-factor products, first at least 3-factor products // when they're not all constants... @@ expression E1, E2, E3; constant C1, C2, C3; @@ ( vzalloc(C1 * C2 * C3, ...) | vzalloc( - E1 * E2 * E3 + array3_size(E1, E2, E3) , ...) ) // And then all remaining 2 factors products when they're not all constants. @@ expression E1, E2; constant C1, C2; @@ ( vzalloc(C1 * C2, ...) | vzalloc( - E1 * E2 + array_size(E1, E2) , ...) ) Signed-off-by: Kees Cook <keescook@chromium.org>
|
#
5e6e78db |
|
11-May-2018 |
Yixian Liu <liuyixian@huawei.com> |
RDMA/hns: Add 64KB page size support for hip08 This patch adds the support of 64KB page size for hip08 in kernel. Signed-off-by: Yixian Liu <liuyixian@huawei.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
#
d480bb50 |
|
07-Feb-2018 |
oulijun <oulijun@huawei.com> |
RDMA/hns: Use free_pages function instead of free_page It need to use free_pages function for free the memory allocated by __get_free_pages function. Signed-off-by: Lijun Ou <oulijun@huawei.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
#
a2c80b7b |
|
26-Oct-2017 |
Wei Hu(Xavier) <xavier.huwei@huawei.com> |
RDMA/hns: Add rereg mr support for hip08 This patch adds rereg mr support for hip08. Signed-off-by: Shaobo Xu <xushaobo2@huawei.com> Signed-off-by: Wei Hu (Xavier) <xavier.huwei@huawei.com> Signed-off-by: Lijun Ou <oulijun@huawei.com> Signed-off-by: Yixian Liu <liuyixian@huawei.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
|
#
9a8982dc |
|
18-Oct-2017 |
Wei Hu(Xavier) <xavier.huwei@huawei.com> |
RDMA/hns: Support WQE/CQE/PBL page size configurable feature in hip08 This patch updates to support WQE, CQE and PBL page size configurable feature, which includes base address page size and buffer page size. Signed-off-by: Shaobo Xu <xushaobo2@huawei.com> Signed-off-by: Wei Hu (Xavier) <xavier.huwei@huawei.com> Signed-off-by: Lijun Ou <oulijun@huawei.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
|
#
e930b4d8 |
|
29-Sep-2017 |
Colin Ian King <colin.king@canonical.com> |
RDMA/hns: remove redundant assignment to variable j Variable j is being assigned to loop_j and then later being assigned to a new value in for loops. The first initialization is therefore redundant and can be removed. Cleans up clang warning: warning: Value stored to 'j' is never read Signed-off-by: Colin Ian King <colin.king@canonical.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
|
#
ff795f71 |
|
30-Aug-2017 |
Wei Hu(Xavier) <xavier.huwei@huawei.com> |
RDMA/hns: Support multi hop addressing for PBL in hip08 The block base address in the MR can be retrieved by the block number which is calculated with the VA in the SGE and MTPT. In hip08, the PBL supports multi hop addressing to retrieve the block base address by the block number. This patch is to add the interfaces in the MR to support multi hop addressing for the PBL. Signed-off-by: Shaobo Xu <xushaobo2@huawei.com> Signed-off-by: Lijun Ou <oulijun@huawei.com> Signed-off-by: Wei Hu (Xavier) <xavier.huwei@huawei.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
|
#
9766edc3 |
|
30-Aug-2017 |
Shaobo Xu <xushaobo2@huawei.com> |
RDMA/hns: Split CQE from MTT in hip08 In hip08, the SQWQE/SGE/RQWQE and CQE have different hop num and page size, so we need to manage the base address table of the SQWQE/SGE/RQWQE and CQE separately. This patch is to split CQE from MTT(SQWQE/SGE/RQWQE). Signed-off-by: Shaobo Xu <xushaobo2@huawei.com> Signed-off-by: Lijun Ou <oulijun@huawei.com> Signed-off-by: Wei Hu (Xavier) <xavier.huwei@huawei.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
|
#
6a93c77a |
|
30-Aug-2017 |
Shaobo Xu <xushaobo2@huawei.com> |
RDMA/hns: Update the interfaces for MTT/CQE multi hop addressing in hip08 The MTT(SQWQE/SGE/RQWQE) and CQE in hip08 can support multi hop addressing. The address of MTT/CQE can be retrieved by the BT (Base Address Table) with multi hop addressing. This patch is to update the interfaces in HEM to support multi hop addressing for the MTT/CQE. Signed-off-by: Shaobo Xu <xushaobo2@huawei.com> Signed-off-by: Lijun Ou <oulijun@huawei.com> Signed-off-by: Wei Hu (Xavier) <xavier.huwei@huawei.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
|
#
13ca970e |
|
30-Aug-2017 |
Wei Hu(Xavier) <xavier.huwei@huawei.com> |
RDMA/hns: Modify assignment device variable to support both PCI device and platform device In order to support the scalability of the hardware version, the features irrelevant to the hardware will be located in the hns-roce.ko, and the hardware relevant operations will be located in hns_roce_hw_v1.ko or hns_roce_hw_v2.ko based on the series chips. The hip08 RoCE engine is a PCI device, hip06 RoCE engine is a platform device. In order to support both platform device and PCI device, We replace &hr_dev->pdev->dev with hr_dev->dev in hns-roce.ko as belows: Before modification: struct device *dev = hr_dev->dev; After modification: struct device *dev = &hr_dev->pdev->dev; The related structure: struct hns_roce_dev { ... struct platform_device *pdev; struct pci_dev *pci_dev; struct device *dev; ... } Signed-off-by: Lijun Ou <oulijun@huawei.com> Signed-off-by: Shaobo Xu <xushaobo2@huawei.com> Signed-off-by: Wei Hu (Xavier) <xavier.huwei@huawei.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
|
#
08805fdb |
|
30-Aug-2017 |
Wei Hu(Xavier) <xavier.huwei@huawei.com> |
RDMA/hns: Split hw v1 driver from hns roce driver The hardware relevant definitions and operations are implemented in hns_roce_hw_v* file. According to the diversity chips, the file is named as hns_roce_hw_v1.c or hns_roce_hw_v2.c etc. The general software process flow, common structures and allocated algorithms are implemented in other files located in hns roce driver. In order to support the scalability of the hardware version, the common driver features are in the hns-roce.ko, and the hardware relevant operations are in hns_roce_hw_v1.ko or hns_roce_hw_v2.ko based on the series chips. Signed-off-by: Lijun Ou <oulijun@huawei.com> Signed-off-by: Shaobo Xu <xushaobo2@huawei.com> Signed-off-by: Wei Hu (Xavier) <xavier.huwei@huawei.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
|
#
e89bf462 |
|
08-Jun-2017 |
Matan Barak <matanb@mellanox.com> |
IB/hns: Support compile test for hns RoCE driver Compiling the hns RoCE driver requires ARM architecture. In order to simplify development of IB/core, support compile test. Add the necessary includes for that too. Signed-off-by: Matan Barak <matanb@mellanox.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
|
#
ad61dd30 |
|
08-May-2017 |
Stephen Boyd <sboyd@codeaurora.org> |
scripts/spelling.txt: add regsiter -> register spelling mistake This typo is quite common. Fix it and add it to the spelling file so that checkpatch catches it earlier. Link: http://lkml.kernel.org/r/20170317011131.6881-2-sboyd@codeaurora.org Signed-off-by: Stephen Boyd <sboyd@codeaurora.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
|
#
3e7e1193 |
|
05-Apr-2017 |
Artemy Kovalyov <artemyko@mellanox.com> |
IB: Replace ib_umem page_size by page_shift Size of pages are held by struct ib_umem in page_size field. It is better to store it as an exponent, because page size by nature is always power-of-two and used as a factor, divisor or ilog2's argument. The conversion of page_size to be page_shift allows to have portable code and avoid following error while compiling on ARM: ERROR: "__aeabi_uldivmod" [drivers/infiniband/core/ib_core.ko] undefined! CC: Selvin Xavier <selvin.xavier@broadcom.com> CC: Steve Wise <swise@chelsio.com> CC: Lijun Ou <oulijun@huawei.com> CC: Shiraz Saleem <shiraz.saleem@intel.com> CC: Adit Ranadive <aditr@vmware.com> CC: Dennis Dalessandro <dennis.dalessandro@intel.com> CC: Ram Amrani <Ram.Amrani@Cavium.com> Signed-off-by: Artemy Kovalyov <artemyko@mellanox.com> Signed-off-by: Leon Romanovsky <leon@kernel.org> Acked-by: Ram Amrani <Ram.Amrani@cavium.com> Acked-by: Shiraz Saleem <shiraz.saleem@intel.com> Acked-by: Selvin Xavier <selvin.xavier@broadcom.com> Acked-by: Selvin Xavier <selvin.xavier@broadcom.com> Acked-by: Adit Ranadive <aditr@vmware.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
|
#
4418b27b |
|
16-Feb-2017 |
Markus Elfring <elfring@users.sourceforge.net> |
IB/hns: Use kcalloc() in hns_roce_buddy_init() * Multiplications for the size determination of memory allocations indicated that array data structures should be processed. Thus use the corresponding function "kcalloc". This issue was detected by using the Coccinelle software. * Replace the specification of data types by pointer dereferences to make the corresponding size determinations a bit safer according to the Linux coding style convention. Signed-off-by: Markus Elfring <elfring@users.sourceforge.net> Signed-off-by: Doug Ledford <dledford@redhat.com>
|
#
bfcc681b |
|
29-Nov-2016 |
Shaobo Xu <xushaobo2@huawei.com> |
IB/hns: Fix the bug when free mr If the resources of mr are freed while executing the user case, hardware can not been notified in hip06 SoC. Then hardware will hold on when it reads the payload by the PA which has been released. In order to slove this problem, RoCE driver creates 8 reserved loopback QPs to ensure zero wqe when free mr. When the mac address is reset, in order to avoid loopback failure, we need to release the reserved loopback QPs and recreate them. Signed-off-by: Shaobo Xu <xushaobo2@huawei.com> Reviewed-by: Wei Hu (Xavier) <xavier.huwei@huawei.com> Signed-off-by: Salil Mehta <salil.mehta@huawei.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
|
#
5e6ff78a |
|
23-Nov-2016 |
Wei Hu (Xavier) <xavier.huwei@huawei.com> |
IB/hns: Change qpn allocation to round-robin mode. When using CM to establish connections, qp number that was freed just now will be rejected by ib core. To fix these problem, We change qpn allocation to round-robin mode. We added the round-robin mode for allocating resources using bitmap. We use round-robin mode for qp number and non round-robing mode for other resources like cq number, pd number etc. Signed-off-by: Wei Hu (Xavier) <xavier.huwei@huawei.com> Signed-off-by: Salil Mehta <salil.mehta@huawei.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
|
#
6b877c32 |
|
23-Nov-2016 |
Wei Hu (Xavier) <xavier.huwei@huawei.com> |
IB/hns: Modify the macro for the timeout when cmd process This patch modified the macro for the timeout when cmd is processing as follows: Before modification: enum { HNS_ROCE_CMD_TIME_CLASS_A = 10000, HNS_ROCE_CMD_TIME_CLASS_B = 10000, HNS_ROCE_CMD_TIME_CLASS_C = 10000, }; After modification: #define HNS_ROCE_CMD_TIMEOUT_MSECS 10000 Signed-off-by: Wei Hu (Xavier) <xavier.huwei@huawei.com> Signed-off-by: Salil Mehta <salil.mehta@huawei.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
|
#
8d497eb0 |
|
23-Nov-2016 |
Wei Hu (Xavier) <xavier.huwei@huawei.com> |
IB/hns: Optimize the logic of allocating memory using APIs This patch modified the logic of allocating memory using APIs in hns RoCE driver. We used kcalloc instead of kmalloc_array and bitmap_zero. And When kcalloc failed, call vzalloc to alloc memory. Signed-off-by: Wei Hu (Xavier) <xavier.huwei@huawei.com> Signed-off-by: Ping Zhang <zhangping5@huawei.com> Signed-off-by: Salil Mehta <salil.mehta@huawei.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
|
#
1cd11064 |
|
20-Sep-2016 |
Lijun Ou <oulijun@huawei.com> |
IB/hns: Fix bug of memory leakage for registering user mr While the page size attribute of umem is illegal, we should release umem that get by ib_umem_get interface. Also, we should return a non-zero value while pbl number is wrong. Signed-off-by: Lijun Ou <oulijun@huawei.com> Signed-off-by: Dongdong Huang(Donald) <hdd.huang@huawei.com> Reviewed-by: Wei Hu (Xavier) <xavier.huwei@huawei.com> Signed-off-by: Salil Mehta <salil.mehta@huawei.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
|
#
9a443537 |
|
21-Jul-2016 |
oulijun <oulijun@huawei.com> |
IB/hns: Add driver files for hns RoCE driver These are the various new source code files for the Hisilicon RoCE driver for ARM architecture. Signed-off-by: Wei Hu <xavier.huwei@huawei.com> Signed-off-by: Nenglong Zhao <zhaonenglong@hisilicon.com> Signed-off-by: Lijun Ou <oulijun@huawei.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
|