aboutsummaryrefslogtreecommitdiff
path: root/drivers/infiniband
AgeCommit message (Collapse)AuthorFilesLines
2020-09-09RDMA/hns: Avoid unncessary initializationLijun Ou6-24/+24
Some variables have been initialized when used. As a result, here removes some unncessary initial assignment. Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Lijun Ou <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2020-09-09RDMA/bnxt_re: Remove set but not used variable 'qplib_ctx'YueHaibing1-2/+0
drivers/infiniband/hw/bnxt_re/main.c:1012:25: warning: variable ‘qplib_ctx’ set but not used [-Wunused-but-set-variable] Fixes: f86b31c6a28f ("RDMA/bnxt_re: Static NQ depth allocation") Link: https://lore.kernel.org/r/[email protected] Signed-off-by: YueHaibing <[email protected]> Reviewed-by: Leon Romanovsky <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2020-09-09RDMA/core: Change how failing destroy is handled during uobj abortJason Gunthorpe1-15/+15
Currently it triggers a WARN_ON and then goes ahead and destroys the uobject anyhow, leaking any driver memory. The only place that leaks driver memory should be during FD close() in uverbs_destroy_ufile_hw(). Drivers are only allowed to fail destroy uobjects if they guarantee destroy will eventually succeed. uverbs_destroy_ufile_hw() provides the loop to give the driver that chance. Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Leon Romanovsky <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2020-09-03RDMA/rxe: Convert tasklets to use new tasklet_setup() APIAllen Pais3-8/+8
In preparation for unconditionally passing the struct tasklet_struct pointer to all tasklet callbacks, switch to using the new tasklet_setup() and from_tasklet() to pass the tasklet pointer explicitly. Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Romain Perier <[email protected]> Signed-off-by: Allen Pais <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2020-09-03RDMA/qib: Convert tasklets to use new tasklet_setup() APIAllen Pais2-9/+8
In preparation for unconditionally passing the struct tasklet_struct pointer to all tasklet callbacks, switch to using the new tasklet_setup() and from_tasklet() to pass the tasklet pointer explicitly. Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Romain Perier <[email protected]> Signed-off-by: Allen Pais <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2020-09-03RDMA/i40iw: Convert tasklets to use new tasklet_setup() APIAllen Pais1-7/+7
In preparation for unconditionally passing the struct tasklet_struct pointer to all tasklet callbacks, switch to using the new tasklet_setup() and from_tasklet() to pass the tasklet pointer explicitly. Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Romain Perier <[email protected]> Signed-off-by: Allen Pais <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2020-09-03RDMA/hfi1: Convert tasklets to use new tasklet_setup() APIAllen Pais1-11/+11
In preparation for unconditionally passing the struct tasklet_struct pointer to all tasklet callbacks, switch to using the new tasklet_setup() and from_tasklet() to pass the tasklet pointer explicitly. Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Romain Perier <[email protected]> Signed-off-by: Allen Pais <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2020-09-03RDMA/bnxt_re: Convert tasklets to use new tasklet_setup() APIAllen Pais2-10/+8
In preparation for unconditionally passing the struct tasklet_struct pointer to all tasklet callbacks, switch to using the new tasklet_setup() and from_tasklet() to pass the tasklet pointer explicitly. Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Romain Perier <[email protected]> Signed-off-by: Allen Pais <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2020-09-03RDMA/mlx5: Fix potential race between destroy and CQE pollLeon Romanovsky1-2/+3
The SRQ can be destroyed right before mlx5_cmd_get_srq is called. In such case the latter will return NULL instead of expected SRQ. Fixes: e126ba97dba9 ("mlx5: Add driver for Mellanox Connect-IB adapters") Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Leon Romanovsky <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2020-09-02RDMA/ucma: Fix resource leak on error pathAlex Dewar1-7/+8
In ucma_process_join(), if the call to xa_alloc() fails, the function will return without freeing mc. Fix this by jumping to the correct line. In the process I renamed the jump labels to something more memorable for extra clarity. Link: https://lore.kernel.org/r/[email protected] Addresses-Coverity-ID: 1496814 ("Resource leak") Fixes: 95fe51096b7a ("RDMA/ucma: Remove mc_list and rely on xarray") Signed-off-by: Alex Dewar <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2020-09-02RDMA/core: Fix reported speed and widthKamal Heib1-1/+1
When the returned speed from __ethtool_get_link_ksettings() is SPEED_UNKNOWN this will lead to reporting a wrong speed and width for providers that uses ib_get_eth_speed(), fix that by defaulting the netdev_speed to SPEED_1000 in case the returned value from __ethtool_get_link_ksettings() is SPEED_UNKNOWN. Fixes: d41861942fc5 ("IB/core: Add generic function to extract IB speed from netdev") Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Kamal Heib <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2020-09-02RDMA/core: Fix unsafe linked list traversal after failing to allocate CQXi Wang1-2/+2
It's not safe to access the next CQ in list_for_each_entry() after invoking ib_free_cq(), because the CQ has already been freed in current iteration. It should be replaced by list_for_each_entry_safe(). Fixes: c7ff819aefea ("RDMA/core: Introduce shared CQ pool API") Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Xi Wang <[email protected]> Signed-off-by: Weihang Li <[email protected]> Reviewed-by: Jason Gunthorpe <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2020-09-02RDMA/qedr: Fix reported max_pkeysKamal Heib1-1/+1
As qedr driver supports both RoCE and iWarp, make sure to set the max_pkeys only when running in RoCE mode. Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Kamal Heib <[email protected]> Acked-by: Michal Kalderon <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2020-08-31RDMA/qib: Tidy up process_cc()Alex Dewar1-37/+13
This function has a lot of gotos which could be replaced by simple returns, making the function tidier and less bug prone. Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Alex Dewar <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2020-08-31RDMA/qib: Remove superfluous fallthrough statementsAlex Dewar1-2/+0
Commit 36a8f01cd24b ("IB/qib: Add congestion control agent implementation") erroneously marked a couple of switch cases as /* FALLTHROUGH */, which were later converted to fallthrough statements by commit df561f6688fe ("treewide: Use fallthrough pseudo-keyword"). This triggered a Coverity warning about unreachable code. Remove the fallthrough statements. Link: https://lore.kernel.org/r/[email protected] Addresses-Coverity: ("Unreachable code") Fixes: 36a8f01cd24b ("IB/qib: Add congestion control agent implementation") Signed-off-by: Alex Dewar <[email protected]> Reviewed-by: Gustavo A. R. Silva <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2020-08-31Merge tag 'v5.9-rc3' into rdma.git for-nextJason Gunthorpe58-130/+114
Required due to dependencies in following patches. Signed-off-by: Jason Gunthorpe <[email protected]>
2020-08-31RDMA/rxe: Address an issue with hardened user copyBob Pearson3-73/+2
Change rxe pools to use kzalloc instead of kmem_cache to allocate memory for rxe objects. The pools are not really necessary and they trigger hardened user copy warnings as the ioctl framework copies the QP number directly to userspace. Also the general project to move object alloation to the core code will eventually clean these out anyhow. Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Bob Pearson <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2020-08-31RDMA/rxe: Add SPDX hdrs to rxe source filesBob Pearson32-896/+32
Add SPDX headers to all rxe .c and .h files. Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Bob Pearson <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2020-08-31RDMA/core: Trigger a WARN_ON if the driver causes uobjects to become leakedJason Gunthorpe1-1/+2
Drivers that fail destroy can cause uverbs to leak uobjects. Drivers are required to always eventually destroy their ubojects, so trigger a WARN_ON to detect this driver bug. Link: https://lore.kernel.org/r/[email protected] Reviewed-by: Leon Romanovsky <[email protected]> Reviewed-by: Gal Pressman <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2020-08-31RDMA/hns: Get udp sport num dynamically instead of using a fixed valueWeihang Li3-13/+41
The UDP source port number in RoCE v2 is used to create entropy for network routers (ECMP), load balancers and 802.3ad link aggregation switching that are not aware of RoCE IB headers. Considering that the IB core has achieved a new interface to get a hashed value of it, the fixed value of it in QPC and UD WQE in hns driver could be fixed and the port number is to be set dynamically now. For QPC of RC, the value could be hashed from flow_lable if the user pass it in or from remote qpn and local qpn. For WQE of UD, it is set according to fl or as a random value. Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Weihang Li <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2020-08-27RDMA/rxe: Fix style warningsBob Pearson4-6/+4
Fixed several minor checkpatch warnings in existing rxe source. Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Bob Pearson <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2020-08-27RDMA/hns: Add a check for current state before modifying QPLang Cheng1-2/+4
It should be considered an illegal operation if the ULP attempts to modify a QP from another state to the current hardware state. Otherwise, the ULP can modify some fields of QPC at any time. For example, for a QP in state of RTS, modify it from RTR to RTS can change the PSN, which is always not as expected. Fixes: 9a4435375cd1 ("IB/hns: Add driver files for hns RoCE driver") Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Lang Cheng <[email protected]> Signed-off-by: Weihang Li <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2020-08-27RDMA/bnxt_re: Remove the qp from list only if the qp destroy succeedsSelvin Xavier1-11/+11
Driver crashes when destroy_qp is re-tried because of an error returned. This is because the qp entry was removed from the qp list during the first call. Remove qp from the list only if destroy_qp returns success. The driver will still trigger a WARN_ON due to the memory leaking, but at least it isn't corrupting memory too. Fixes: 8dae419f9ec7 ("RDMA/bnxt_re: Refactor queue pair creation code") Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Selvin Xavier <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2020-08-27RDMA/bnxt_re: Fix driver crash on unaligned PSN entry addressNaresh Kumar PBS1-2/+2
When computing the first psn entry, driver checks for page alignment. If this address is not page aligned,it attempts to compute the offset in that page for later use by using ALIGN macro. ALIGN macro does not return offset bytes but the requested aligned address and hence cannot be used directly to store as offset. Since driver was using the address itself instead of offset, it resulted in invalid address when filling the psn buffer. Fixed driver to use PAGE_MASK macro to calculate the offset. Fixes: fddcbbb02af4 ("RDMA/bnxt_re: Simplify obtaining queue entry from hw ring") Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Naresh Kumar PBS <[email protected]> Signed-off-by: Selvin Xavier <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2020-08-27RDMA/bnxt_re: Restrict the max_gids to 256Naresh Kumar PBS2-1/+2
Some adapters report more than 256 gid entries. Restrict it to 256 for now. Fixes: 1ac5a4047975("RDMA/bnxt_re: Add bnxt_re RoCE driver") Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Naresh Kumar PBS <[email protected]> Signed-off-by: Selvin Xavier <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2020-08-27RDMA/bnxt_re: Static NQ depth allocationNaresh Kumar PBS1-2/+1
At first, driver allocates memory for NQ based on qplib_ctx->cq_count and qplib_ctx->srqc_count. Later when creating ring, it uses a static value of 128K -1. Fixing this with a static value for now. Fixes: b08fe048a69d ("RDMA/bnxt_re: Refactor net ring allocation function") Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Naresh Kumar PBS <[email protected]> Signed-off-by: Selvin Xavier <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2020-08-27RDMA/bnxt_re: Fix the qp table indexingSelvin Xavier3-12/+25
qp->id can be a value outside the max number of qp. Indexing the qp table with the id can cause out of bounds crash. So changing the qp table indexing by (qp->id % max_qp -1). Allocating one extra entry for QP1. Some adapters create one more than the max_qp requested to accommodate QP1. If the qp->id is 1, store the inforamtion in the last entry of the qp table. Fixes: f218d67ef004 ("RDMA/bnxt_re: Allow posting when QPs are in error") Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Selvin Xavier <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2020-08-27RDMA/bnxt_re: Do not report transparent vlan from QP1Selvin Xavier1-3/+18
QP1 Rx CQE reports transparent VLAN ID in the completion and this is used while reporting the completion for received MAD packet. Check if the vlan id is configured before reporting it in the work completion. Fixes: 84511455ac5b ("RDMA/bnxt_re: report vlan_id and sl in qp1 recv completion") Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Selvin Xavier <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2020-08-27RDMA/mlx4: Read pkey table length instead of hardcoded valueMark Bloch1-1/+2
If the pkey_table is not available (which is the case when RoCE is not supported), the cited commit caused a regression where mlx4_devices without RoCE are not created. Fix this by returning a pkey table length of zero in procedure eth_link_query_port() if the pkey-table length reported by the device is zero. Link: https://lore.kernel.org/r/[email protected] Cc: <[email protected]> Fixes: 1901b91f9982 ("IB/core: Fix potential NULL pointer dereference in pkey cache") Fixes: fa417f7b520e ("IB/mlx4: Add support for IBoE") Signed-off-by: Mark Bloch <[email protected]> Reviewed-by: Maor Gottlieb <[email protected]> Signed-off-by: Leon Romanovsky <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2020-08-27RDMA/rxe: Fix panic when calling kmem_cache_create()Kamal Heib3-0/+11
To avoid the following kernel panic when calling kmem_cache_create() with a NULL pointer from pool_cache(), Block the rxe_param_set_add() from running if the rdma_rxe module is not initialized. BUG: unable to handle kernel NULL pointer dereference at 000000000000000b PGD 0 P4D 0 Oops: 0000 [#1] SMP NOPTI CPU: 4 PID: 8512 Comm: modprobe Kdump: loaded Not tainted 4.18.0-231.el8.x86_64 #1 Hardware name: HPE ProLiant DL385 Gen10/ProLiant DL385 Gen10, BIOS A40 10/02/2018 RIP: 0010:kmem_cache_alloc+0xd1/0x1b0 Code: 8b 57 18 45 8b 77 1c 48 8b 5c 24 30 0f 1f 44 00 00 5b 48 89 e8 5d 41 5c 41 5d 41 5e 41 5f c3 81 e3 00 00 10 00 75 0e 4d 89 fe <41> f6 47 0b 04 0f 84 6c ff ff ff 4c 89 ff e8 cc da 01 00 49 89 c6 RSP: 0018:ffffa2b8c773f9d0 EFLAGS: 00010246 RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000005 RDX: 0000000000000004 RSI: 00000000006080c0 RDI: 0000000000000000 RBP: ffff8ea0a8634fd0 R08: ffffa2b8c773f988 R09: 00000000006000c0 R10: 0000000000000000 R11: 0000000000000230 R12: 00000000006080c0 R13: ffffffffc0a97fc8 R14: 0000000000000000 R15: 0000000000000000 FS: 00007f9138ed9740(0000) GS:ffff8ea4ae800000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000000000000000b CR3: 000000046d59a000 CR4: 00000000003406e0 Call Trace: rxe_alloc+0xc8/0x160 [rdma_rxe] rxe_get_dma_mr+0x25/0xb0 [rdma_rxe] __ib_alloc_pd+0xcb/0x160 [ib_core] ib_mad_init_device+0x296/0x8b0 [ib_core] add_client_context+0x11a/0x160 [ib_core] enable_device_and_get+0xdc/0x1d0 [ib_core] ib_register_device+0x572/0x6b0 [ib_core] ? crypto_create_tfm+0x32/0xe0 ? crypto_create_tfm+0x7a/0xe0 ? crypto_alloc_tfm+0x58/0xf0 rxe_register_device+0x19d/0x1c0 [rdma_rxe] rxe_net_add+0x3d/0x70 [rdma_rxe] ? dev_get_by_name_rcu+0x73/0x90 rxe_param_set_add+0xaf/0xc0 [rdma_rxe] parse_args+0x179/0x370 ? ref_module+0x1b0/0x1b0 load_module+0x135e/0x17e0 ? ref_module+0x1b0/0x1b0 ? __do_sys_init_module+0x13b/0x180 __do_sys_init_module+0x13b/0x180 do_syscall_64+0x5b/0x1a0 entry_SYSCALL_64_after_hwframe+0x65/0xca RIP: 0033:0x7f9137ed296e This can be triggered if a user tries to use the 'module option' which is not actually a real module option but some idiotic (and thankfully no obsolete) sysfs interface. Fixes: 8700e3e7c485 ("Soft RoCE driver") Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Kamal Heib <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2020-08-27RDMA/usnic: Remove the query_pkey callbackKamal Heib3-15/+0
Now that the query_pkey() isn't mandatory by the RDMA core, this callback can be removed from the usnic provider. The libfabric userspace never touches the pkey. Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Kamal Heib <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2020-08-27RDMA/rxe: Fix memleak in rxe_mem_init_userDinghao Liu1-0/+1
When page_address() fails, umem should be freed just like when rxe_mem_alloc() fails. Fixes: 8700e3e7c485 ("Soft RoCE driver") Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Dinghao Liu <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2020-08-27RDMA/ucma: Remove closing and the close_wqJason Gunthorpe1-34/+15
Use cancel_work_sync() to ensure that the wq is not running and simply assign NULL to ctx->cm_id to indicate if the work ran or not. Delete the close_wq since flush_workqueue() is no longer needed. Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Leon Romanovsky <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2020-08-27RDMA/ucma: Rework how new connections are passed through event deliveryJason Gunthorpe1-126/+96
When a new connection is established the RDMA CM creates a new cm_id and passes it through to the event handler. However inside the UCMA the new ID is not assigned a ucma_context until the user retrieves the event from a syscall. This creates a weird edge condition where a cm_id's context can continue to point at the listening_id that created it, and a number of additional edge conditions on event list clean up related to destroying half created IDs. There is also a race condition in ucma_get_events() where the cm_id->context is being assigned without holding the handler_mutex. Simplify all of this by creating the ucma_context inside the event handler itself and eliminating the edge case of a half created cm_id. All cm_id's can be uniformly destroyed via __destroy_id() or via the close_work. Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Leon Romanovsky <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2020-08-27RDMA/ucma: Narrow file->mut in ucma_event_handler()Jason Gunthorpe1-9/+7
Since the backlog is now an atomic the file->mut is now only protecting the event_list and ctx_list. Narrow its scope to make it clear Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Leon Romanovsky <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2020-08-27RDMA/ucma: Change backlog into an atomicJason Gunthorpe1-7/+8
There is no reason to grab the file->mut just to do this inc/dec work. Use an atomic. Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Leon Romanovsky <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2020-08-27RDMA/ucma: Add missing locking around rdma_leave_multicast()Jason Gunthorpe1-0/+2
All entry points to the rdma_cm from a ULP must be single threaded, even this error unwinds. Add the missing locking. Fixes: 7c11910783a1 ("RDMA/ucma: Put a lock around every call to the rdma_cm layer") Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Leon Romanovsky <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2020-08-27RDMA/ucma: Fix locking for ctx->events_reportedJason Gunthorpe1-1/+3
This value is locked under the file->mut, ensure it is held whenever touching it. The case in ucma_migrate_id() is a race, while in ucma_free_uctx() it is already not possible for the write side to run, the movement is just for clarity. Fixes: 88314e4dda1e ("RDMA/cma: add support for rdma_migrate_id()") Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Leon Romanovsky <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2020-08-27RDMA/ucma: Fix the locking of ctx->fileJason Gunthorpe1-1/+5
ctx->file is changed under the file->mut lock by ucma_migrate_id(), which is impossible to lock correctly. Instead change ctx->file under the handler_lock and ctx_table lock and revise all places touching ctx->file to use this locking when reading ctx->file. Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Leon Romanovsky <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2020-08-27RDMA/ucma: Do not use file->mut to lock destroyingJason Gunthorpe1-3/+11
The only reader of destroying is inside a handler under the handler_mutex, so directly use the handler_mutex when setting it instead of the larger file->mut. As the refcount could be zero here, and the cm_id already freed, and additional refcount grab around the locking is required to touch the cm_id. Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Leon Romanovsky <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2020-08-27RDMA/cma: Add missing locking to rdma_accept()Jason Gunthorpe2-7/+30
In almost all cases rdma_accept() is called under the handler_mutex by ULPs from their handler callbacks. The one exception was ucma which did not get the handler_mutex. To improve the understand-ability of the locking scheme obtain the mutex for ucma as well. This improves how ucma works by allowing it to directly use handler_mutex for some of its internal locking against the handler callbacks intead of the global file->mut lock. There does not seem to be a serious bug here, other than a DISCONNECT event can be delivered concurrently with accept succeeding. Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Leon Romanovsky <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2020-08-27RDMA/ucma: Remove mc_list and rely on xarrayJason Gunthorpe1-37/+22
It is not really necessary to keep a linked list of mcs associated with each context when we can just scan the xarray to find the right things. The removes another overloading of file->mut by relying on the xarray locking for mc instead. Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Leon Romanovsky <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2020-08-27RDMA/ucma: Fix error cases around ucma_alloc_ctx()Jason Gunthorpe1-26/+42
The store to ctx->cm_id was based on the idea that _ucma_find_context() would not return the ctx until it was fully setup. Without locking this doesn't work properly. Split things so that the xarray is allocated with NULL to reserve the ID and once everything is final set the cm_id and store. Along the way this shows that the error unwind in ucma_get_event() if a new ctx is created is wrong, fix it up. Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Leon Romanovsky <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2020-08-27RDMA/ucma: Consolidate the two destroy flowsJason Gunthorpe1-42/+22
ucma_close() is open coding the tail end of ucma_destroy_id(), consolidate this duplicated code into a function. Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Leon Romanovsky <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2020-08-27RDMA/ucma: Remove unnecessary locking of file->ctx_list in closeJason Gunthorpe1-4/+7
During the file_operations release function it is already not possible that write() can be running concurrently, remove the extra locking around the ctx_list. Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Leon Romanovsky <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2020-08-27RDMA/ucma: Fix refcount 0 incr in ucma_get_ctx()Jason Gunthorpe1-2/+2
Both ucma_destroy_id() and ucma_close_id() (triggered from an event via a wq) can drive the refcount to zero. ucma_get_ctx() was wrongly assuming that the refcount can only go to zero from ucma_destroy_id() which also removes it from the xarray. Use refcount_inc_not_zero() instead. Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Leon Romanovsky <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2020-08-27IB/mlx5: Add DCT RoCE LAG supportMark Zhang1-1/+8
When DCT QPs work in RoCE LAG mode: 1. DCT creation is allowed only when it is supported 2. The "port" of a DCT QP is assigned in a round-robin way Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Mark Zhang <[email protected]> Reviewed-by: Maor Gottlieb <[email protected]> Signed-off-by: Leon Romanovsky <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2020-08-27IB/mlx5: Add tx_affinity support for DCI QPMark Zhang1-8/+6
DCI QP supports tx_affinity as well. Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Mark Zhang <[email protected]> Reviewed-by: Maor Gottlieb <[email protected]> Signed-off-by: Leon Romanovsky <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2020-08-24RDMA/cm: Add tracepoints to track MAD send operationsChuck Lever2-2/+125
Surface the operation of MAD exchanges during connection establishment. Some samples: [root@klimt ~]# trace-cmd report -F ib_cma cpus=4 kworker/0:4-123 [000] 60.677388: icm_send_rep: local_id=1965336542 remote_id=1096195961 state=REQ_RCVD lap_state=LAP_UNINIT kworker/u8:11-391 [002] 60.678808: icm_send_req: local_id=1982113758 remote_id=0 state=IDLE lap_state=LAP_UNINIT kworker/0:4-123 [000] 60.679652: icm_send_rtu: local_id=1982113758 remote_id=1079418745 state=REP_RCVD lap_state=LAP_UNINIT nfsd-1954 [001] 60.691350: icm_send_rep: local_id=1998890974 remote_id=1129750393 state=MRA_REQ_SENT lap_state=LAP_UNINIT nfsd-1954 [003] 62.017931: icm_send_drep: local_id=1998890974 remote_id=1129750393 state=TIMEWAIT lap_state=LAP_UNINIT Link: https://lore.kernel.org/r/159767240197.2968.12048458026453596018.stgit@klimt.1015granger.net Signed-off-by: Chuck Lever <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
2020-08-24RDMA/cm: Replace pr_debug() call sites with tracepointsChuck Lever4-55/+351
In the interest of converging on a common instrumentation infrastructure, modernize the pr_debug() call sites added by commit 119bf81793ea ("IB/cm: Add debug prints to ib_cm"). The new tracepoints appear in a new "ib_cma" subsystem. The conversion is somewhat mechanical. Someone more familiar with the semantics of the recorded information might suggest additional data capture. Some benefits include: - Tracepoints enable "always on" reporting of these errors - The error records are structured and compact - Tracepoints provide hooks for eBPF scripts Sample output: nfsd-1954 [003] 62.017901: icm_dreq_skipped: local_id=1998890974 remote_id=1129750393 state=DREQ_RCVD lap_state=LAP_UNINIT Link: https://lore.kernel.org/r/159767239665.2968.10613294222688696646.stgit@klimt.1015granger.net Signed-off-by: Chuck Lever <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>