aboutsummaryrefslogtreecommitdiff
path: root/drivers/infiniband
AgeCommit message (Collapse)AuthorFilesLines
2022-12-07RDMA/hns: Fix page size cap from firmwareChengchang Tang1-0/+3
Add verification to make sure the roce page size cap is supported by the system page size. Fixes: ba6bb7e97421 ("RDMA/hns: Add interfaces to get pf capabilities from firmware") Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Chengchang Tang <[email protected]> Signed-off-by: Haoyue Xu <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2022-12-07RDMA/hns: Fix PBL page MTR findChengchang Tang1-1/+2
Now, The address of the first two pages in the MR will be searched, which use to speed up the lookup of the pbl table for hardware. An exception will occur when there is only one page in this MR. This patch fix the number of page to search. Fixes: 9b2cf76c9f05 ("RDMA/hns: Optimize PBL buffer allocation process") Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Chengchang Tang <[email protected]> Signed-off-by: Haoyue Xu <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2022-12-07RDMA/hns: Fix AH attr queried by query_qpChengchang Tang1-0/+2
The queried AH attr is invalid. This patch fix it. This problem is found by rdma-core test test_mr_rereg_pd ERROR: test_mr_rereg_pd (tests.test_mr.MRTest) Test that cover rereg MR's PD with this flow: ---------------------------------------------------------------------- Traceback (most recent call last): File "./tests/test_mr.py", line 157, in test_mr_rereg_pd self.restate_qps() File "./tests/test_mr.py", line 113, in restate_qps self.server.qp.to_rts(self.server_qp_attr) File "qp.pyx", line 1137, in pyverbs.qp.QP.to_rts File "qp.pyx", line 1123, in pyverbs.qp.QP.to_rtr pyverbs.pyverbs_error.PyverbsRDMAError: Failed to modify QP state to RTR. Errno: 22, Invalid argument Fixes: 926a01dc000d ("RDMA/hns: Add QP operations support for hip08 SoC") Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Chengchang Tang <[email protected]> Signed-off-by: Haoyue Xu <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2022-12-07RDMA/hns: Fix the gid problem caused by free mrYixing Liu2-46/+137
After the hns roce driver is loaded, if you modify the mac address of the network port, the following error will appear: __ib_cache_gid_add: unable to add gid fe80:0000:0000:0000:4600:4dff:fe22:abb5 error=-28 hns3 0000:7d:00.0 hns_0: attr path_mtu(1) invalid while modify qp The reason for the error is that the gid being occupied will cause the failure to modify the gid. The gid is occupied by the loopback QP used by free mr. When the mac address is modified, the gid will change. If there is a busy QP at this time, the gid will not be released and the modification will fail. The QP of free mr is created using the ib interface. The ib interface will add a reference count to the gid, resulting in this error scenario. Considering that free mr is solving a bug in HIP08, not an actual business, it is not necessary to use ib interfaces. Fixes: 70f92521584f ("RDMA/hns: Use the reserved loopback QPs to free MR before destroying MPT") Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Yixing Liu <[email protected]> Signed-off-by: Haoyue Xu <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2022-12-07RDMA/cma: Change RoCE packet life time from 18 to 16Chao Leng1-1/+1
The ack timeout retransmission time is affected by the following two factors: one is packet life time, another is the HCA processing time. Now the default packet lifetime(CMA_IBOE_PACKET_LIFETIME) is 18. That means the minimum ack timeout is 2 seconds (2^(18+1)*4us=2.097seconds). The packet lifetime means the maximum transmission time of packets on the network, 2 seconds is too long. Assume the network is a clos topology with three layers, every packet will pass through five hops of switches. Assume the buffer of every switch is 128MB and the port transmission rate is 25 Gbit/s, the maximum transmission time of the packet is 200ms(128MB*5/25Gbit/s). Add double redundancy, it is less than 500ms. So change the CMA_IBOE_PACKET_LIFETIME to 16, the maximum transmission time of the packet will be about 500+ms, it is long enough. Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Chao Leng <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2022-12-07RDMA/hfi1: use sysfs_emit() to instead of scnprintf()ye xingchen1-1/+1
Follow the advice of the Documentation/filesystems/sysfs.rst and show() should only use sysfs_emit() or sysfs_emit_at() when formatting the value to be returned to user space. Signed-off-by: ye xingchen <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Leon Romanovsky <[email protected]>
2022-12-04RDMA/mlx5: no need to kfree NULL pointerLi Zhijian1-4/+2
Goto label 'free' where it will kfree the 'in' is not needed though it's safe to kfree NULL. Return err code directly to simplify the code. 1973 free: 1974 kfree(in); 1975 return err; Signed-off-by: Li Zhijian <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Leon Romanovsky <[email protected]>
2022-12-04RDMA/srp: Fix error return code in srp_parse_options()Wang Yufen1-14/+82
In the previous iteration of the while loop, the "ret" may have been assigned a value of 0, so the error return code -EINVAL may have been incorrectly set to 0. To fix set valid return code before calling to goto. Also investigate each case separately as Andy suggessted. Fixes: e711f968c49c ("IB/srp: replace custom implementation of hex2bin()") Fixes: 2a174df0c602 ("IB/srp: Use kstrtoull() instead of simple_strtoull()") Fixes: 19f313438c77 ("IB/srp: Add RDMA/CM support") Signed-off-by: Wang Yufen <[email protected]> Link: https://lore.kernel.org/r/[email protected] Reviewed-by: Bart Van Assche <[email protected]> Signed-off-by: Leon Romanovsky <[email protected]>
2022-12-04RDMA/hfi1: Fix error return code in parse_platform_config()Wang Yufen1-0/+6
In the previous iteration of the while loop, the "ret" may have been assigned a value of 0, so the error return code -EINVAL may have been incorrectly set to 0. To fix set valid return code before calling to goto. Fixes: 97167e813415 ("staging/rdma/hfi1: Tune for unknown channel if configuration file is absent") Signed-off-by: Wang Yufen <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Leon Romanovsky <[email protected]>
2022-12-04RDMA: Disable IB HW for UMLRandy Dunlap1-0/+2
Disable all of drivers/infiniband/hw/ and rdmavt for UML builds until someone needs it and provides patches to support it. This prevents build errors in hw/qib/qib_wc_x86_64.c. Fixes: 68f5d3f3b654 ("um: add PCI over virtio emulation driver") Signed-off-by: Randy Dunlap <[email protected]> Cc: Jason Gunthorpe <[email protected]> Cc: Dennis Dalessandro <[email protected]> Cc: Christoph Hellwig <[email protected]> Cc: [email protected] Cc: Jeff Dike <[email protected]> Cc: Richard Weinberger <[email protected]> Cc: Anton Ivanov <[email protected]> Cc: Johannes Berg <[email protected]> Cc: [email protected] Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Leon Romanovsky <[email protected]>
2022-12-01RDMA/rxe: Enable atomic write capability for rxe deviceXiao Yang1-0/+5
The capability shows that rxe device supports atomic write operation. Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Xiao Yang <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2022-12-01RDMA/rxe: Implement atomic write completionXiao Yang1-0/+4
Generate an atomic write completion when the atomic write request has been finished. Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Xiao Yang <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2022-12-01RDMA/rxe: Make responder support atomic write on RC serviceXiao Yang1-5/+79
Make responder process an atomic write request and send a read response on RC service. Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Xiao Yang <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2022-12-01RDMA/rxe: Make requester support atomic write on RC serviceXiao Yang1-2/+13
Make requester process and send an atomic write request on RC service. Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Xiao Yang <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2022-12-01RDMA/rxe: Extend rxe packet format to support atomic writeXiao Yang2-0/+21
Extend rxe_wr_opcode_info[] and rxe_opcode[] for new atomic write opcode. Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Xiao Yang <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2022-12-01IB/hfi1: Switch to netif_napi_add()Yang Yang1-1/+1
There is no need to use netif_napi_add_weight() when the weight argument is 64. See "net: drop the weight argument from netif_napi_add". Signed-off-by: Yang Yang <[email protected]> Link: https://lore.kernel.org/r/[email protected] Reviewed-by: xu xin <[email protected]> Reviewed-by: Zhang Yunkai <[email protected]> Signed-off-by: Leon Romanovsky <[email protected]>
2022-11-30RDMA/hw/qib/qib_user_pages: remove FOLL_FORCE usageDavid Hildenbrand1-1/+1
FOLL_FORCE is really only for ptrace access. As we unpin the pinned pages using unpin_user_pages_dirty_lock(true), the assumption is that all these pages are writable. FOLL_FORCE in this case seems to be a legacy leftover. Let's just remove it. Link: https://lkml.kernel.org/r/[email protected] Signed-off-by: David Hildenbrand <[email protected]> Cc: Dennis Dalessandro <[email protected]> Cc: Jason Gunthorpe <[email protected]> Cc: Leon Romanovsky <[email protected]> Signed-off-by: Andrew Morton <[email protected]>
2022-11-30RDMA/siw: remove FOLL_FORCE usageDavid Hildenbrand1-5/+4
GUP now supports reliable R/O long-term pinning in COW mappings, such that we break COW early. MAP_SHARED VMAs only use the shared zeropage so far in one corner case (DAXFS file with holes), which can be ignored because GUP does not support long-term pinning in fsdax (see check_vma_flags()). Consequently, FOLL_FORCE | FOLL_WRITE | FOLL_LONGTERM is no longer required for reliable R/O long-term pinning: FOLL_LONGTERM is sufficient. So stop using FOLL_FORCE, which is really only for ptrace access. Link: https://lkml.kernel.org/r/[email protected] Signed-off-by: David Hildenbrand <[email protected]> Reviewed-by: Jason Gunthorpe <[email protected]> Cc: Bernard Metzler <[email protected]> Cc: Leon Romanovsky <[email protected]> Signed-off-by: Andrew Morton <[email protected]>
2022-11-30RDMA/usnic: remove FOLL_FORCE usageDavid Hildenbrand1-5/+4
GUP now supports reliable R/O long-term pinning in COW mappings, such that we break COW early. MAP_SHARED VMAs only use the shared zeropage so far in one corner case (DAXFS file with holes), which can be ignored because GUP does not support long-term pinning in fsdax (see check_vma_flags()). Consequently, FOLL_FORCE | FOLL_WRITE | FOLL_LONGTERM is no longer required for reliable R/O long-term pinning: FOLL_LONGTERM is sufficient. So stop using FOLL_FORCE, which is really only for ptrace access. Link: https://lkml.kernel.org/r/[email protected] Signed-off-by: David Hildenbrand <[email protected]> Reviewed-by: Jason Gunthorpe <[email protected]> Cc: Christian Benvenuti <[email protected]> Cc: Nelson Escobar <[email protected]> Cc: Leon Romanovsky <[email protected]> Signed-off-by: Andrew Morton <[email protected]>
2022-11-30RDMA/umem: remove FOLL_FORCE usageDavid Hildenbrand1-4/+4
GUP now supports reliable R/O long-term pinning in COW mappings, such that we break COW early. MAP_SHARED VMAs only use the shared zeropage so far in one corner case (DAXFS file with holes), which can be ignored because GUP does not support long-term pinning in fsdax (see check_vma_flags()). Consequently, FOLL_FORCE | FOLL_WRITE | FOLL_LONGTERM is no longer required for reliable R/O long-term pinning: FOLL_LONGTERM is sufficient. So stop using FOLL_FORCE, which is really only for ptrace access. Link: https://lkml.kernel.org/r/[email protected] Tested-by: Leon Romanovsky <[email protected]> [over mlx4 and mlx5] Signed-off-by: David Hildenbrand <[email protected]> Reviewed-by: Jason Gunthorpe <[email protected]> Cc: Leon Romanovsky <[email protected]> Signed-off-by: Andrew Morton <[email protected]>
2022-11-30RDMA/nldev: Fix failure to send large messagesMark Zhang1-1/+1
Return "-EMSGSIZE" instead of "-EINVAL" when filling a QP entry, so that new SKBs will be allocated if there's not enough room in current SKB. Fixes: 65959522f806 ("RDMA: Add support to dump resource tracker in RAW format") Signed-off-by: Mark Zhang <[email protected]> Reviewed-by: Patrisious Haddad <[email protected]> Link: https://lore.kernel.org/r/b5e9c62f6b8369acab5648b661bf539cbceeffdc.1669636336.git.leonro@nvidia.com Signed-off-by: Leon Romanovsky <[email protected]>
2022-11-30RDMA/nldev: Add NULL check to silence false warningsOr Har-Toov1-8/+36
Using nlmsg_put causes static analysis tools to many false positives of not checking the return value of nlmsg_put. In all uses in nldev.c, payload parameter is 0 so NULL will never be returned. So let's add useless checks to silence the warnings. Signed-off-by: Or Har-Toov <[email protected]> Reviewed-by: Michael Guralnik <[email protected]> Link: https://lore.kernel.org/r/bd924da89d5b4f5291a4a01d9b5ae47c0a9b6a3f.1669636336.git.leonro@nvidia.com Signed-off-by: Leon Romanovsky <[email protected]>
2022-11-29net/mlx5: Generalize name of UMR alignment definitionTariq Toukan2-9/+8
Per the device spec, MLX5_UMR_MTT_ALIGNMENT is good not only for UMR MTT entries, but for all other entries as well, like KLMs and KSMs. Signed-off-by: Tariq Toukan <[email protected]> Reviewed-by: Gal Pressman <[email protected]> Signed-off-by: Saeed Mahameed <[email protected]>
2022-11-29RDMA/mlx4: Remove NULL check before dev_{put, hold}zhang songyi1-8/+4
The call netdev_{put, hold} of dev_{put, hold} will check NULL, so there is no need to check before using dev_{put, hold}. Fix the following coccicheck warnings: /drivers/infiniband/hw/mlx4/main.c:1311:2-10: WARNING: WARNING NULL check before dev_{put, hold} functions is not needed. /drivers/infiniband/hw/mlx4/main.c:148:2-10: WARNING: WARNING NULL check before dev_{put, hold} functions is not needed. /drivers/infiniband/hw/mlx4/main.c:1959:3-11: WARNING: WARNING NULL check before dev_{put, hold} functions is not needed. /drivers/infiniband/hw/mlx4/main.c:1962:3-10: WARNING: WARNING NULL check before dev_{put, hold} functions is not needed. Signed-off-by: zhang songyi <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Leon Romanovsky <[email protected]>
2022-11-28RDMA/nldev: Add checks for nla_nest_start() in fill_stat_counter_qps()Yuan Can1-0/+2
As the nla_nest_start() may fail with NULL returned, the return value needs to be checked. Fixes: c4ffee7c9bdb ("RDMA/netlink: Implement counter dumpit calback") Signed-off-by: Yuan Can <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Leon Romanovsky <[email protected]>
2022-11-28RDMA: Add netdevice_tracker to ib_device_set_netdev()Jason Gunthorpe1-2/+4
This will cause an informative backtrace to print if the user of ib_device_set_netdev() isn't careful about tearing down the ibdevice before its the netdevice parent is destroyed. Such as like this: unregister_netdevice: waiting for vlan0 to become free. Usage count = 2 leaked reference. ib_device_set_netdev+0x266/0x730 siw_newlink+0x4e0/0xfd0 nldev_newlink+0x35c/0x5c0 rdma_nl_rcv_msg+0x36d/0x690 rdma_nl_rcv+0x2ee/0x430 netlink_unicast+0x543/0x7f0 netlink_sendmsg+0x918/0xe20 sock_sendmsg+0xcf/0x120 ____sys_sendmsg+0x70d/0x8b0 ___sys_sendmsg+0x11d/0x1b0 __sys_sendmsg+0xfa/0x1d0 do_syscall_64+0x35/0xb0 entry_SYSCALL_64_after_hwframe+0x63/0xcd This will help debug the issues syzkaller is seeing. Signed-off-by: Jason Gunthorpe <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Leon Romanovsky <[email protected]>
2022-11-25use less confusing names for iov_iter direction initializersAl Viro1-1/+1
READ/WRITE proved to be actively confusing - the meanings are "data destination, as used with read(2)" and "data source, as used with write(2)", but people keep interpreting those as "we read data from it" and "we write data to it", i.e. exactly the wrong way. Call them ITER_DEST and ITER_SOURCE - at least that is harder to misinterpret... Signed-off-by: Al Viro <[email protected]>
2022-11-25[infiniband] READ is "data destination", not source...Al Viro1-1/+1
Signed-off-by: Al Viro <[email protected]>
2022-11-24RDMA/erdma: Notify the latest PI to FW for reflushing when necessaryCheng Xu2-9/+26
Firmware is responsible for flushing WRs in HW, and it's a little difficult for firmware to get the latest PI of QPs, especially for RQs after QP state being changed to ERROR. So we introduce a new CMDQ command, by which driver can notify to latest PI to FW, and then FW can flush all posted WRs. Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Cheng Xu <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2022-11-24RDMA/erdma: Implement the lifecycle of reflushing work for each QPCheng Xu3-0/+28
Each QP has a work for reflushing purpose. In the work, driver will report the latest pi to hardware. Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Cheng Xu <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2022-11-24RDMA/erdma: Add a workqueue for WRs reflushingCheng Xu2-2/+13
ERDMA driver use a workqueue for asynchronous reflush command posting. Implement the lifecycle of this workqueue. Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Cheng Xu <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2022-11-24RDMA/erdma: Fix a typo in annotationCheng Xu1-1/+1
A non-ASCII character was wrongly put in a comment, use the ACSII version. Fixes: bee85e0e31ec ("RDMA/erdma: Add main include file") Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Cheng Xu <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2022-11-24driver core: make struct class.devnode() take a const *Greg Kroah-Hartman3-4/+4
The devnode() in struct class should not be modifying the device that is passed into it, so mark it as a const * and propagate the function signature changes out into all relevant subsystems that use this callback. Cc: Fenghua Yu <[email protected]> Cc: Reinette Chatre <[email protected]> Cc: Thomas Gleixner <[email protected]> Cc: Ingo Molnar <[email protected]> Cc: Borislav Petkov <[email protected]> Cc: Dave Hansen <[email protected]> Cc: [email protected] Cc: "H. Peter Anvin" <[email protected]> Cc: FUJITA Tomonori <[email protected]> Cc: Jens Axboe <[email protected]> Cc: Justin Sanders <[email protected]> Cc: Arnd Bergmann <[email protected]> Cc: Sumit Semwal <[email protected]> Cc: Benjamin Gaignard <[email protected]> Cc: Liam Mark <[email protected]> Cc: Laura Abbott <[email protected]> Cc: Brian Starkey <[email protected]> Cc: John Stultz <[email protected]> Cc: "Christian König" <[email protected]> Cc: Maarten Lankhorst <[email protected]> Cc: Maxime Ripard <[email protected]> Cc: Thomas Zimmermann <[email protected]> Cc: David Airlie <[email protected]> Cc: Daniel Vetter <[email protected]> Cc: Jason Gunthorpe <[email protected]> Cc: Leon Romanovsky <[email protected]> Cc: Dennis Dalessandro <[email protected]> Cc: Dmitry Torokhov <[email protected]> Cc: Mauro Carvalho Chehab <[email protected]> Cc: Sean Young <[email protected]> Cc: Frank Haverkamp <[email protected]> Cc: Jiri Slaby <[email protected]> Cc: "Michael S. Tsirkin" <[email protected]> Cc: Jason Wang <[email protected]> Cc: Alex Williamson <[email protected]> Cc: Cornelia Huck <[email protected]> Cc: Kees Cook <[email protected]> Cc: Anton Vorontsov <[email protected]> Cc: Colin Cross <[email protected]> Cc: Tony Luck <[email protected]> Cc: Jaroslav Kysela <[email protected]> Cc: Takashi Iwai <[email protected]> Cc: Hans Verkuil <[email protected]> Cc: Christophe JAILLET <[email protected]> Cc: Xie Yongji <[email protected]> Cc: Gautam Dawar <[email protected]> Cc: Dan Carpenter <[email protected]> Cc: Eli Cohen <[email protected]> Cc: Parav Pandit <[email protected]> Cc: Maxime Coquelin <[email protected]> Cc: [email protected] Cc: [email protected] Cc: [email protected] Cc: [email protected] Cc: [email protected] Cc: [email protected] Cc: [email protected] Cc: [email protected] Cc: [email protected] Cc: [email protected] Cc: [email protected] Cc: [email protected] Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Greg Kroah-Hartman <[email protected]>
2022-11-24driver core: make struct class.dev_uevent() take a const *Greg Kroah-Hartman1-1/+1
The dev_uevent() in struct class should not be modifying the device that is passed into it, so mark it as a const * and propagate the function signature changes out into all relevant subsystems that use this callback. Cc: Jens Axboe <[email protected]> Cc: Luis Chamberlain <[email protected]> Cc: Russ Weight <[email protected]> Cc: Jean Delvare <[email protected]> Cc: Johan Hovold <[email protected]> Cc: Jason Gunthorpe <[email protected]> Cc: Leon Romanovsky <[email protected]> Cc: Karsten Keil <[email protected]> Cc: Mauro Carvalho Chehab <[email protected]> Cc: Keith Busch <[email protected]> Cc: Christoph Hellwig <[email protected]> Cc: Sagi Grimberg <[email protected]> Cc: Dominik Brodowski <[email protected]> Cc: "David S. Miller" <[email protected]> Cc: Eric Dumazet <[email protected]> Cc: Jakub Kicinski <[email protected]> Cc: Paolo Abeni <[email protected]> Cc: Johannes Berg <[email protected]> Cc: Wolfram Sang <[email protected]> Cc: Raed Salem <[email protected]> Cc: Chen Zhongjin <[email protected]> Cc: Tetsuo Handa <[email protected]> Cc: Avihai Horon <[email protected]> Cc: "Matthew Wilcox (Oracle)" <[email protected]> Cc: Alan Stern <[email protected]> Cc: Colin Ian King <[email protected]> Cc: Geert Uytterhoeven <[email protected]> Cc: Jakob Koschel <[email protected]> Cc: Antoine Tenart <[email protected]> Cc: Frederic Weisbecker <[email protected]> Cc: Wang Yufen <[email protected]> Cc: [email protected] Cc: [email protected] Cc: [email protected] Cc: [email protected] Cc: [email protected] Cc: [email protected] Cc: [email protected] Cc: [email protected] Cc: [email protected] Acked-by: Sebastian Reichel <[email protected]> Acked-by: Rafael J. Wysocki <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Greg Kroah-Hartman <[email protected]>
2022-11-24Backmerge tag 'v6.1-rc6' into drm-nextDave Airlie9-21/+30
Linux 6.1-rc6 This is needed for drm-misc-next and tegra. Signed-off-by: Dave Airlie <[email protected]>
2022-11-22RDMA/rxe: Fix NULL-ptr-deref in rxe_qp_do_cleanup() when socket create failedZhang Xiaoxu1-3/+3
There is a null-ptr-deref when mount.cifs over rdma: BUG: KASAN: null-ptr-deref in rxe_qp_do_cleanup+0x2f3/0x360 [rdma_rxe] Read of size 8 at addr 0000000000000018 by task mount.cifs/3046 CPU: 2 PID: 3046 Comm: mount.cifs Not tainted 6.1.0-rc5+ #62 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.14.0-1.fc3 Call Trace: <TASK> dump_stack_lvl+0x34/0x44 kasan_report+0xad/0x130 rxe_qp_do_cleanup+0x2f3/0x360 [rdma_rxe] execute_in_process_context+0x25/0x90 __rxe_cleanup+0x101/0x1d0 [rdma_rxe] rxe_create_qp+0x16a/0x180 [rdma_rxe] create_qp.part.0+0x27d/0x340 ib_create_qp_kernel+0x73/0x160 rdma_create_qp+0x100/0x230 _smbd_get_connection+0x752/0x20f0 smbd_get_connection+0x21/0x40 cifs_get_tcp_session+0x8ef/0xda0 mount_get_conns+0x60/0x750 cifs_mount+0x103/0xd00 cifs_smb3_do_mount+0x1dd/0xcb0 smb3_get_tree+0x1d5/0x300 vfs_get_tree+0x41/0xf0 path_mount+0x9b3/0xdd0 __x64_sys_mount+0x190/0x1d0 do_syscall_64+0x35/0x80 entry_SYSCALL_64_after_hwframe+0x46/0xb0 The root cause of the issue is the socket create failed in rxe_qp_init_req(). So move the reset rxe_qp_do_cleanup() after the NULL ptr check. Fixes: 8700e3e7c485 ("Soft RoCE driver") Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Zhang Xiaoxu <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2022-11-22RDMA/rxe: Do not NULL deref on debugging failure pathJason Gunthorpe1-1/+1
Correct the mistake, mr is obviously NULL in this code path. Fixes: 2778b72b1df0 ("RDMA/rxe: Replace pr_xxx by rxe_dbg_xxx in rxe_mr.c") Link: https://lore.kernel.org/r/Y3eeJW0AdyJYhYyQ@kili Reported-by: Dan Carpenter <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2022-11-22RDMA/hns: fix memory leak in hns_roce_alloc_mr()Zhengchao Shao1-2/+2
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 <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Leon Romanovsky <[email protected]>
2022-11-22RDMA/irdma: Initialize net_type before checking itMustafa Ismail1-0/+1
The av->net_type is not initialized before it is checked in irdma_modify_qp_roce. This leads to an incorrect update to the ARP cache and QP context. RoCEv2 connections might fail as result. Set the net_type using rdma_gid_attr_network_type. Fixes: 80005c43d4c8 ("RDMA/irdma: Use net_type to check network type") Signed-off-by: Mustafa Ismail <[email protected]> Signed-off-by: Shiraz Saleem <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Leon Romanovsky <[email protected]>
2022-11-22RDMA/hfi: Decrease PCI device reference count in error pathXiongfeng Wang1-0/+2
pci_get_device() will increase the reference count for the returned pci_dev, and also decrease the reference count for the input parameter *from* if it is not NULL. If we break out the loop in node_affinity_init() with 'dev' not NULL, we need to call pci_dev_put() to decrease the reference count. Add missing pci_dev_put() in error path. Fixes: c513de490f80 ("IB/hfi1: Invalid NUMA node information can cause a divide by zero") Signed-off-by: Xiongfeng Wang <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Leon Romanovsky <[email protected]>
2022-11-21IB/isert: use the ISCSI_LOGIN_CURRENT_STAGE macroMaurizio Lombardi1-3/+2
Use the proper macro to get the current_stage value. Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Maurizio Lombardi <[email protected]> Reviewed-by: Mike Christie <[email protected]> Acked-by: Sagi Grimberg <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2022-11-21Merge 6.1-rc6 into driver-core-nextGreg Kroah-Hartman9-21/+30
We need the kernfs changes in here as well. Signed-off-by: Greg Kroah-Hartman <[email protected]>
2022-11-21RDMA/qib: don't pass bogus GFP_ flags to dma_alloc_coherentChristoph Hellwig2-18/+5
dma_alloc_coherent is an opaque allocator that only uses the GFP_ flags for allocation context control. Don't pass GFP_USER which doesn't make sense for a kernel DMA allocation or __GFP_COMP which makes no sense for an allocation that can't in any way be converted to a page pointer. Signed-off-by: Christoph Hellwig <[email protected]> Acked-by: Jason Gunthorpe <[email protected]>
2022-11-21RDMA/hfi1: don't pass bogus GFP_ flags to dma_alloc_coherentChristoph Hellwig1-18/+3
dma_alloc_coherent is an opaque allocator that only uses the GFP_ flags for allocation context control. Don't pass GFP_USER which doesn't make sense for a kernel DMA allocation or __GFP_COMP which makes no sense for an allocation that can't in any way be converted to a page pointer. Signed-off-by: Christoph Hellwig <[email protected]> Acked-by: Jason Gunthorpe <[email protected]> Acked-by: Dean Luick <[email protected]> Tested-by: Dean Luick <[email protected]>
2022-11-18RDMA/hns: Fix incorrect sge nums calculationLuoyouming4-30/+110
The user usually configures the number of sge through the max_send_sge parameter when creating qp, and configures the maximum size of inline data that can be sent through max_inline_data. Inline uses sge to fill data to send. Expect the following: 1) When the sge space cannot hold inline data, the sge space needs to be expanded to accommodate all inline data 2) When the sge space is enough to accommodate inline data, the upper limit of inline data can be increased so that users can send larger inline data Currently case one is not implemented. When the inline data is larger than the sge space, an error of insufficient sge space occurs. This part of the code needs to be reimplemented according to the expected rules. The calculation method of sge num is modified to take the maximum value of max_send_sge and the sge for max_inline_data to solve this problem. Fixes: 05201e01be93 ("RDMA/hns: Refactor process of setting extended sge") Fixes: 30b707886aeb ("RDMA/hns: Support inline data in extented sge space for RC") Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Luoyouming <[email protected]> Signed-off-by: Haoyue Xu <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2022-11-18RDMA/hns: Fix ext_sge num error when post sendLuoyouming1-2/+11
In the HNS ROCE driver, The sge is divided into standard sge and extended sge. There are 2 standard sge in RC/XRC, and the UD standard sge is 0. In the scenario of RC SQ inline, if the data does not exceed 32bytes, the standard sge will be used. If it exceeds, only the extended sge will be used to fill the data. Currently, when filling the extended sge, max_gs is directly used as the number of the extended sge, which did not subtract the number of standard sge. There is a logical error. The new algorithm subtracts the number of standard sge from max_gs to get the actual number of extended sge. Fixes: 30b707886aeb ("RDMA/hns: Support inline data in extented sge space for RC") Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Luoyouming <[email protected]> Signed-off-by: Haoyue Xu <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2022-11-18RDMA/rxe: Fix mr->map double freeLi Zhijian1-7/+2
rxe_mr_cleanup() which tries to free mr->map again will be called when rxe_mr_init_user() fails: CPU: 0 PID: 4917 Comm: rdma_flush_serv Kdump: loaded Not tainted 6.1.0-rc1-roce-flush+ #25 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014 Call Trace: <TASK> dump_stack_lvl+0x45/0x5d panic+0x19e/0x349 end_report.part.0+0x54/0x7c kasan_report.cold+0xa/0xf rxe_mr_cleanup+0x9d/0xf0 [rdma_rxe] __rxe_cleanup+0x10a/0x1e0 [rdma_rxe] rxe_reg_user_mr+0xb7/0xd0 [rdma_rxe] ib_uverbs_reg_mr+0x26a/0x480 [ib_uverbs] ib_uverbs_handler_UVERBS_METHOD_INVOKE_WRITE+0x1a2/0x250 [ib_uverbs] ib_uverbs_cmd_verbs+0x1397/0x15a0 [ib_uverbs] This issue was firstly exposed since commit b18c7da63fcb ("RDMA/rxe: Fix memory leak in error path code") and then we fixed it in commit 8ff5f5d9d8cf ("RDMA/rxe: Prevent double freeing rxe_map_set()") but this fix was reverted together at last by commit 1e75550648da (Revert "RDMA/rxe: Create duplicate mapping tables for FMRs") Simply let rxe_mr_cleanup() always handle freeing the mr->map once it is successfully allocated. Fixes: 1e75550648da ("Revert "RDMA/rxe: Create duplicate mapping tables for FMRs"") Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Li Zhijian <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2022-11-18RDMA/rxe: Remove reliable datagram supportZhu Yanjun1-1/+0
The rdma_rxe driver does not actually support the reliable datagram transport but contains a variable with RD opcodes in driver code. And this variable is never used. So remove it. Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Zhu Yanjun <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2022-11-18IB/hfi1: Replace 1-element array with singletonKees Cook1-11/+11
Zero-length arrays are deprecated[1] and are being replaced with flexible array members in support of the ongoing efforts to tighten the FORTIFY_SOURCE routines on memcpy(), correctly instrument array indexing with UBSAN_BOUNDS, and to globally enable -fstrict-flex-arrays=3. Replace zero-length array with flexible-array member "lvs" in struct opa_port_data_counters_msg and struct opa_port_error_counters64_msg. Additionally, the "port" member of several structs is defined as a single-element, but is only ever accessed at index 0. Replace it with a singleton so that flexible array usage is sane. This results in no differences in binary output. [1] https://github.com/KSPP/linux/issues/78 Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Kees Cook <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2022-11-18treewide: use get_random_u32_inclusive() when possibleJason A. Donenfeld2-4/+3
These cases were done with this Coccinelle: @@ expression H; expression L; @@ - (get_random_u32_below(H) + L) + get_random_u32_inclusive(L, H + L - 1) @@ expression H; expression L; expression E; @@ get_random_u32_inclusive(L, H - + E - - E ) @@ expression H; expression L; expression E; @@ get_random_u32_inclusive(L, H - - E - + E ) @@ expression H; expression L; expression E; expression F; @@ get_random_u32_inclusive(L, H - - E + F - + E ) @@ expression H; expression L; expression E; expression F; @@ get_random_u32_inclusive(L, H - + E + F - - E ) And then subsequently cleaned up by hand, with several automatic cases rejected if it didn't make sense contextually. Reviewed-by: Kees Cook <[email protected]> Reviewed-by: Greg Kroah-Hartman <[email protected]> Reviewed-by: Jason Gunthorpe <[email protected]> # for infiniband Signed-off-by: Jason A. Donenfeld <[email protected]>
Powered by cgit, Gruvboxed by Blaster4385.