aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/infiniband/core
AgeCommit message (Collapse)AuthorFilesLines
2020-05-12RDMA/cm: Remove the cm_free_id() wrapper functionJason Gunthorpe1-7/+2
Just call xa_erase directly during cm_destroy_id() Link: https://lore.kernel.org/r/20200506074701.9775-9-leon@kernel.org Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2020-05-12RDMA/cm: Make find_remote_id() return a cm_id_privateJason Gunthorpe1-15/+12
The only caller doesn't care about the timewait, so acquire and return the cm_id_private from the function. Link: https://lore.kernel.org/r/20200506074701.9775-8-leon@kernel.org Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2020-05-12RDMA/cm: Add a note explaining how the timewait is eventually freedJason Gunthorpe1-0/+5
The way the cm_timewait_info is converted into a work and then freed is very subtle and surprising, add a note clarifying the lifetime here. Link: https://lore.kernel.org/r/20200506074701.9775-7-leon@kernel.org Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2020-05-12RDMA/cm: Pass the cm_id_private into cm_cleanup_timewaitJason Gunthorpe1-9/+9
Also rename it to cm_remove_remote(). This function now removes the tracking of the remote ID/QPN in the redblack trees from a cm_id_private. Replace a open-coded version with a call. The open coded version was deleting only the remote_id, however at this call site the qpn can not have been in the RB tree either, so the cm_remove_remote() will do the same. Link: https://lore.kernel.org/r/20200506074701.9775-6-leon@kernel.org Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2020-05-12RDMA/cm: Pull duplicated code into cm_queue_work_unlock()Jason Gunthorpe1-102/+44
While unlocking a spinlock held by the caller is a disturbing pattern, this extensively duplicated code is even worse. Pull all the duplicates into a function and explain the purpose of the algorithm. The on creation side call in cm_req_handler() which is different has been micro-optimized on the basis that the work_count == -1 during creation, remove that and just use the normal function. Link: https://lore.kernel.org/r/20200506074701.9775-5-leon@kernel.org Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2020-05-12RDMA/cm: Remove unused store to ret in cm_rej_handlerDanit Goldberg1-1/+0
The 'goto out' label doesn't read ret, so don't set it. Link: https://lore.kernel.org/r/20200506074701.9775-4-leon@kernel.org Signed-off-by: Danit Goldberg <danitg@mellanox.com> Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2020-05-12RDMA/cm: Remove return code from add_cm_id_to_port_listJason Gunthorpe1-14/+4
This cannot happen, all callers pass in one of the two pointers. Use a WARN_ON guard instead. Link: https://lore.kernel.org/r/20200506074701.9775-3-leon@kernel.org Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2020-05-12RDMA/addr: Mark addr_resolve as might_sleep()Jason Gunthorpe1-0/+4
Under one path through ib_nl_fetch_ha() this calls nlmsg_new(GFP_KERNEL) which is a sleeping call. This is a very rare path, so mark fetch_ha() and the module external entry point that conditionally calls through to fetch_ha() as might_sleep(). Link: https://lore.kernel.org/r/20200506074701.9775-2-leon@kernel.org Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2020-05-12RDMA/ucma: Return stable IB device index as identifierLeon Romanovsky1-7/+9
The librdmacm uses node_guid as identifier to correlate between IB devices and CMA devices. However FW resets cause to such "connection" to be lost and require from the user to restart its application. Extend UCMA to return IB device index, which is stable identifier. Link: https://lore.kernel.org/r/20200504132541.355710-1-leon@kernel.org Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2020-05-12RDMA/uverbs: Move IB_EVENT_DEVICE_FATAL to destroy_uobjJason Gunthorpe3-7/+10
When multiple async FDs were allowed to exist the idea was for all broadcast events to be delivered to all async FDs, however IB_EVENT_DEVICE_FATAL was missed. Instead of having ib_uverbs_free_hw_resources() special case the global async_fd, have it cause the event during the uobject destruction. Every async fd is now a uobject so simply generate the IB_EVENT_DEVICE_FATAL while destroying the async fd uobject. This ensures every async FD gets a copy of the event. Fixes: d680e88e2013 ("RDMA/core: Add UVERBS_METHOD_ASYNC_EVENT_ALLOC") Link: https://lore.kernel.org/r/20200507063348.98713-3-leon@kernel.org Signed-off-by: Yishai Hadas <yishaih@mellanox.com> Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2020-05-12RDMA/uverbs: Do not discard the IB_EVENT_DEVICE_FATAL eventJason Gunthorpe4-3/+29
The commit below moved all of the destruction to the disassociate step and cleaned up the event channel during destroy_uobj. However, when ib_uverbs_free_hw_resources() pushes IB_EVENT_DEVICE_FATAL and then immediately goes to destroy all uobjects this causes ib_uverbs_free_event_queue() to discard the queued event if userspace hasn't already read() it. Unlike all other event queues async FD needs to defer the ib_uverbs_free_event_queue() until FD release. This still unregisters the handler from the IB device during disassociation. Fixes: 3e032c0e92aa ("RDMA/core: Make ib_uverbs_async_event_file into a uobject") Link: https://lore.kernel.org/r/20200507063348.98713-2-leon@kernel.org Signed-off-by: Yishai Hadas <yishaih@mellanox.com> Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2020-05-12RDMA/core: Fix double put of resourceMaor Gottlieb1-2/+1
Do not decrease the reference count of resource tracker object twice in the error flow of res_get_common_doit. Fixes: c5dfe0ea6ffa ("RDMA/nldev: Add resource tracker doit callback") Link: https://lore.kernel.org/r/20200507062942.98305-1-leon@kernel.org Signed-off-by: Maor Gottlieb <maorg@mellanox.com> Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2020-05-12IB/core: Fix potential NULL pointer dereference in pkey cacheJack Morgenstein1-2/+5
The IB core pkey cache is populated by procedure ib_cache_update(). Initially, the pkey cache pointer is NULL. ib_cache_update allocates a buffer and populates it with the device's pkeys, via repeated calls to procedure ib_query_pkey(). If there is a failure in populating the pkey buffer via ib_query_pkey(), ib_cache_update does not replace the old pkey buffer cache with the updated one -- it leaves the old cache as is. Since initially the pkey buffer cache is NULL, when calling ib_cache_update the first time, a failure in ib_query_pkey() will cause the pkey buffer cache pointer to remain NULL. In this situation, any calls subsequent to ib_get_cached_pkey(), ib_find_cached_pkey(), or ib_find_cached_pkey_exact() will try to dereference the NULL pkey cache pointer, causing a kernel panic. Fix this by checking the ib_cache_update() return value. Fixes: 8faea9fd4a39 ("RDMA/cache: Move the cache per-port data into the main ib_port_data") Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Link: https://lore.kernel.org/r/20200507071012.100594-1-leon@kernel.org Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il> Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2020-05-06RDMA/cma: Initialize the flow label of CM's route path recordMark Zhang1-0/+23
If flow label is not set by the user or it's not IPv4, initialize it with the cma src/dst based on the "Kernighan and Ritchie's hash function". Link: https://lore.kernel.org/r/20200504051935.269708-5-leon@kernel.org Signed-off-by: Mark Zhang <markz@mellanox.com> Reviewed-by: Maor Gottlieb <maorg@mellanox.com> Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2020-05-06RDMA/core: Consider flow label when building skbMaor Gottlieb1-2/+4
Use rdma_flow_label_to_udp_sport to calculate the UDP source port of the RoCEV2 packet. Link: https://lore.kernel.org/r/20200504051935.269708-3-leon@kernel.org Signed-off-by: Maor Gottlieb <maorg@mellanox.com> Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2020-05-06RDMA: Allow ib_client's to fail when add() is calledJason Gunthorpe8-66/+94
When a client is added it isn't allowed to fail, but all the client's have various failure paths within their add routines. This creates the very fringe condition where the client was added, failed during add and didn't set the client_data. The core code will then still call other client_data centric ops like remove(), rename(), get_nl_info(), and get_net_dev_by_params() with NULL client_data - which is confusing and unexpected. If the add() callback fails, then do not call any more client ops for the device, even remove. Remove all the now redundant checks for NULL client_data in ops callbacks. Update all the add() callbacks to return error codes appropriately. EOPNOTSUPP is used for cases where the ULP does not support the ib_device - eg because it only works with IB. Link: https://lore.kernel.org/r/20200421172440.387069-1-leon@kernel.org Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Acked-by: Ursula Braun <ubraun@linux.ibm.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2020-05-06RDMA/mad: Remove snoop interfaceMaor Gottlieb1-232/+4
Snoop interface is not used. Remove it. Link: https://lore.kernel.org/r/20200413132408.931084-1-leon@kernel.org Signed-off-by: Maor Gottlieb <maorg@mellanox.com> Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2020-05-02RDMA/core: Get xmit slave for LAGMaor Gottlieb1-18/+43
Add a call to rdma_lag_get_ah_roce_slave() when the address handle is created. Lower driver can use it to select the QP's affinity port. Link: https://lore.kernel.org/r/20200430192146.12863-15-maorg@mellanox.com Signed-off-by: Maor Gottlieb <maorg@mellanox.com> Reviewed-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2020-05-02RDMA/core: Add LAG functionalityMaor Gottlieb2-1/+137
Add support to get the RoCE LAG xmit slave by building skb of the RoCE packet and call to master_get_xmit_slave. If driver wants to get the slave assume all slaves are available, then need to set RDMA_LAG_FLAGS_HASH_ALL_SLAVES in flags. Link: https://lore.kernel.org/r/20200430192146.12863-14-maorg@mellanox.com Signed-off-by: Maor Gottlieb <maorg@mellanox.com> Reviewed-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2020-05-02RDMA: Group create AH arguments in structMaor Gottlieb1-1/+4
Following patch adds additional argument to the create AH function, so it make sense to group ah_attr and flags arguments in struct. Link: https://lore.kernel.org/r/20200430192146.12863-13-maorg@mellanox.com Signed-off-by: Maor Gottlieb <maorg@mellanox.com> Acked-by: Devesh Sharma <devesh.sharma@broadcom.com> Acked-by: Gal Pressman <galpress@amazon.com> Acked-by: Weihang Li <liweihang@huawei.com> Reviewed-by: Jason Gunthorpe <jgg@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2020-04-24RDMA/core: Fix race between destroy and release FD objectLeon Romanovsky1-1/+1
The call to ->lookup_put() was too early and it caused an unlock of the read/write protection of the uobject after the FD was put. This allows a race: CPU1 CPU2 rdma_lookup_put_uobject() lookup_put_fd_uobject() fput() fput() uverbs_uobject_fd_release() WARN_ON(uverbs_try_lock_object(uobj, UVERBS_LOOKUP_WRITE)); atomic_dec(usecnt) Fix the code by changing the order, first unlock and call to ->lookup_put() after that. Fixes: 3832125624b7 ("IB/core: Add support for idr types") Link: https://lore.kernel.org/r/20200423060122.6182-1-leon@kernel.org Suggested-by: Jason Gunthorpe <jgg@mellanox.com> Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2020-04-22RDMA/core: Fix overwriting of uobj in case of errorLeon Romanovsky1-3/+2
In case of failure to get file, the uobj is overwritten and causes to supply bad pointer as an input to uverbs_uobject_put(). BUG: KASAN: null-ptr-deref in atomic_fetch_sub include/asm-generic/atomic-instrumented.h:199 [inline] BUG: KASAN: null-ptr-deref in refcount_sub_and_test include/linux/refcount.h:253 [inline] BUG: KASAN: null-ptr-deref in refcount_dec_and_test include/linux/refcount.h:281 [inline] BUG: KASAN: null-ptr-deref in kref_put include/linux/kref.h:64 [inline] BUG: KASAN: null-ptr-deref in uverbs_uobject_put+0x22/0x90 drivers/infiniband/core/rdma_core.c:57 Write of size 4 at addr 0000000000000030 by task syz-executor.4/1691 CPU: 1 PID: 1691 Comm: syz-executor.4 Not tainted 5.6.0 #17 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.1-0-ga5cab58e9a3f-prebuilt.qemu.org 04/01/2014 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x94/0xce lib/dump_stack.c:118 __kasan_report+0x10c/0x190 mm/kasan/report.c:515 kasan_report+0x32/0x50 mm/kasan/common.c:625 check_memory_region_inline mm/kasan/generic.c:187 [inline] check_memory_region+0x16d/0x1c0 mm/kasan/generic.c:193 atomic_fetch_sub include/asm-generic/atomic-instrumented.h:199 [inline] refcount_sub_and_test include/linux/refcount.h:253 [inline] refcount_dec_and_test include/linux/refcount.h:281 [inline] kref_put include/linux/kref.h:64 [inline] uverbs_uobject_put+0x22/0x90 drivers/infiniband/core/rdma_core.c:57 alloc_begin_fd_uobject+0x1d0/0x250 drivers/infiniband/core/rdma_core.c:486 rdma_alloc_begin_uobject+0xa8/0xf0 drivers/infiniband/core/rdma_core.c:509 __uobj_alloc include/rdma/uverbs_std_types.h:117 [inline] ib_uverbs_create_comp_channel+0x16d/0x230 drivers/infiniband/core/uverbs_cmd.c:982 ib_uverbs_write+0xaa5/0xdf0 drivers/infiniband/core/uverbs_main.c:665 __vfs_write+0x7c/0x100 fs/read_write.c:494 vfs_write+0x168/0x4a0 fs/read_write.c:558 ksys_write+0xc8/0x200 fs/read_write.c:611 do_syscall_64+0x9c/0x390 arch/x86/entry/common.c:295 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x466479 Code: f7 d8 64 89 02 b8 ff ff ff ff c3 66 0f 1f 44 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 bc ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007efe9f6a7c48 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 000000000073bf00 RCX: 0000000000466479 RDX: 0000000000000018 RSI: 0000000020000040 RDI: 0000000000000003 RBP: 00007efe9f6a86bc R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000005 R13: 0000000000000bf2 R14: 00000000004cb80a R15: 00000000006fefc0 Fixes: 849e149063bd ("RDMA/core: Do not allow alloc_commit to fail") Link: https://lore.kernel.org/r/20200421082929.311931-3-leon@kernel.org Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2020-04-22RDMA/core: Prevent mixed use of FDs between shared ufilesLeon Romanovsky1-1/+1
FDs can only be used on the ufile that created them, they cannot be mixed to other ufiles. We are lacking a check to prevent it. BUG: KASAN: null-ptr-deref in atomic64_sub_and_test include/asm-generic/atomic-instrumented.h:1547 [inline] BUG: KASAN: null-ptr-deref in atomic_long_sub_and_test include/asm-generic/atomic-long.h:460 [inline] BUG: KASAN: null-ptr-deref in fput_many+0x1a/0x140 fs/file_table.c:336 Write of size 8 at addr 0000000000000038 by task syz-executor179/284 CPU: 0 PID: 284 Comm: syz-executor179 Not tainted 5.5.0-rc5+ #1 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.1-0-ga5cab58e9a3f-prebuilt.qemu.org 04/01/2014 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x94/0xce lib/dump_stack.c:118 __kasan_report+0x18f/0x1b7 mm/kasan/report.c:510 kasan_report+0xe/0x20 mm/kasan/common.c:639 check_memory_region_inline mm/kasan/generic.c:185 [inline] check_memory_region+0x15d/0x1b0 mm/kasan/generic.c:192 atomic64_sub_and_test include/asm-generic/atomic-instrumented.h:1547 [inline] atomic_long_sub_and_test include/asm-generic/atomic-long.h:460 [inline] fput_many+0x1a/0x140 fs/file_table.c:336 rdma_lookup_put_uobject+0x85/0x130 drivers/infiniband/core/rdma_core.c:692 uobj_put_read include/rdma/uverbs_std_types.h:96 [inline] _ib_uverbs_lookup_comp_file drivers/infiniband/core/uverbs_cmd.c:198 [inline] create_cq+0x375/0xba0 drivers/infiniband/core/uverbs_cmd.c:1006 ib_uverbs_create_cq+0x114/0x140 drivers/infiniband/core/uverbs_cmd.c:1089 ib_uverbs_write+0xaa5/0xdf0 drivers/infiniband/core/uverbs_main.c:769 __vfs_write+0x7c/0x100 fs/read_write.c:494 vfs_write+0x168/0x4a0 fs/read_write.c:558 ksys_write+0xc8/0x200 fs/read_write.c:611 do_syscall_64+0x9c/0x390 arch/x86/entry/common.c:294 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x44ef99 Code: 00 b8 00 01 00 00 eb e1 e8 74 1c 00 00 0f 1f 40 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 c4 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007ffc0b74c028 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 00007ffc0b74c030 RCX: 000000000044ef99 RDX: 0000000000000040 RSI: 0000000020000040 RDI: 0000000000000005 RBP: 00007ffc0b74c038 R08: 0000000000401830 R09: 0000000000401830 R10: 00007ffc0b74c038 R11: 0000000000000246 R12: 0000000000000000 R13: 0000000000000000 R14: 00000000006be018 R15: 0000000000000000 Fixes: cf8966b3477d ("IB/core: Add support for fd objects") Link: https://lore.kernel.org/r/20200421082929.311931-2-leon@kernel.org Suggested-by: Jason Gunthorpe <jgg@mellanox.com> Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2020-04-22RDMA/uverbs: Fix a race with disassociate and exit_mmap()Jason Gunthorpe1-0/+4
If uverbs_user_mmap_disassociate() is called while the mmap is concurrently doing exit_mmap then the ordering of the rdma_user_mmap_entry_put() is not reliable. The put must be done before uvers_user_mmap_disassociate() returns, otherwise there can be a use after free on the ucontext, and a left over entry in the xarray. If the put is not done here then it is done during rdma_umap_close() later. Add the missing put to the error exit path. WARNING: CPU: 7 PID: 7111 at drivers/infiniband/core/rdma_core.c:810 uverbs_destroy_ufile_hw+0x2a5/0x340 [ib_uverbs] Modules linked in: bonding ipip tunnel4 geneve ip6_udp_tunnel udp_tunnel ip6_gre ip6_tunnel tunnel6 ip_gre ip_tunnel gre mlx5_ib mlx5_core mlxfw pci_hyperv_intf act_ct nf_flow_table ptp pps_core rdma_ucm ib_uverbs ib_ipoib ib_umad 8021q garp mrp openvswitch nsh nf_conncount nfsv3 nfs_acl xt_MASQUERADE nf_conntrack_netlink nfnetlink iptable_nat xt_addrtype iptable_filter xt_conntrack br_netfilter bridge stp llc rpcsec_gss_krb5 auth_rpcgss nfsv4 dns_resolver nfs lockd grace fscache overlay rpcrdma ib_isert iscsi_target_mod ib_iser kvm_intel ib_srpt iTCO_wdt target_core_mod iTCO_vendor_support kvm ib_srp nf_nat irqbypass crc32_pclmul crc32c_intel nf_conntrack rfkill nf_defrag_ipv6 virtio_net nf_defrag_ipv4 pcspkr ghash_clmulni_intel i2c_i801 net_failover failover i2c_core lpc_ich mfd_core rdma_cm ib_cm iw_cm button ib_core sunrpc sch_fq_codel ip_tables serio_raw [last unloaded: tunnel4] CPU: 7 PID: 7111 Comm: python3 Tainted: G W 5.6.0-rc6-for-upstream-dbg-2020-03-21_06-41-26-18 #1 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.12.1-0-ga5cab58e9a3f-prebuilt.qemu.org 04/01/2014 RIP: 0010:uverbs_destroy_ufile_hw+0x2a5/0x340 [ib_uverbs] Code: ff df 48 89 fa 48 c1 ea 03 80 3c 02 00 75 74 49 8b 84 24 08 01 00 00 48 85 c0 0f 84 13 ff ff ff 48 89 ef ff d0 e9 09 ff ff ff <0f> 0b e9 77 ff ff ff e8 0f d8 fa e0 e9 c5 fd ff ff e8 05 d8 fa e0 RSP: 0018:ffff88840e0779a0 EFLAGS: 00010286 RAX: dffffc0000000000 RBX: ffff8882a7721c00 RCX: 0000000000000000 RDX: 1ffff11054ee469f RSI: ffffffff8446d7e0 RDI: ffff8882a77234f8 RBP: ffff8882a7723400 R08: ffffed1085c0112c R09: 0000000000000001 R10: 0000000000000001 R11: ffffed1085c0112b R12: ffff888403c30000 R13: 0000000000000002 R14: ffff8882a7721cb0 R15: ffff8882a7721cd0 FS: 00007f2046089700(0000) GS:ffff88842de00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f7cfe9a6e20 CR3: 000000040b8ac006 CR4: 0000000000360ee0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: ib_uverbs_remove_one+0x273/0x480 [ib_uverbs] ? up_write+0x15c/0x4a0 remove_client_context+0xa6/0xf0 [ib_core] disable_device+0x12d/0x200 [ib_core] ? remove_client_context+0xf0/0xf0 [ib_core] ? mnt_get_count+0x1d0/0x1d0 __ib_unregister_device+0x79/0x150 [ib_core] ib_unregister_device+0x21/0x30 [ib_core] __mlx5_ib_remove+0x91/0x110 [mlx5_ib] ? __mlx5_ib_remove+0x110/0x110 [mlx5_ib] mlx5_remove_device+0x241/0x310 [mlx5_core] mlx5_unregister_device+0x4d/0x1e0 [mlx5_core] mlx5_unload_one+0xc0/0x260 [mlx5_core] remove_one+0x5c/0x160 [mlx5_core] pci_device_remove+0xef/0x2a0 ? pcibios_free_irq+0x10/0x10 device_release_driver_internal+0x1d8/0x470 unbind_store+0x152/0x200 ? sysfs_kf_write+0x3b/0x180 ? sysfs_file_ops+0x160/0x160 kernfs_fop_write+0x284/0x460 ? __sb_start_write+0x243/0x3a0 vfs_write+0x197/0x4a0 ksys_write+0x156/0x1e0 ? __x64_sys_read+0xb0/0xb0 ? do_syscall_64+0x73/0x1330 ? do_syscall_64+0x73/0x1330 do_syscall_64+0xe7/0x1330 ? down_write_nested+0x3e0/0x3e0 ? syscall_return_slowpath+0x970/0x970 ? entry_SYSCALL_64_after_hwframe+0x3e/0xbe ? lockdep_hardirqs_off+0x1de/0x2d0 ? trace_hardirqs_off_thunk+0x1a/0x1c entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x7f20a3ff0cdb Code: 53 48 89 d5 48 89 f3 48 83 ec 18 48 89 7c 24 08 e8 5a fd ff ff 48 89 ea 41 89 c0 48 89 de 48 8b 7c 24 08 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 31 44 89 c7 48 89 44 24 08 e8 90 fd ff ff 48 RSP: 002b:00007f2046087040 EFLAGS: 00000293 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 00007f2038016df0 RCX: 00007f20a3ff0cdb RDX: 000000000000000d RSI: 00007f2038016df0 RDI: 0000000000000018 RBP: 000000000000000d R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000100 R11: 0000000000000293 R12: 00007f2046e29630 R13: 00007f20280035a0 R14: 0000000000000018 R15: 00007f2038016df0 Fixes: c043ff2cfb7f ("RDMA: Connect between the mmap entry and the umap_priv structure") Link: https://lore.kernel.org/r/20200413132136.930388-1-leon@kernel.org Signed-off-by: Yishai Hadas <yishaih@mellanox.com> Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Reviewed-by: Jason Gunthorpe <jgg@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2020-04-15RDMA/rw: use DIV_ROUND_UP to calculate nr_opsMax Gurtovoy1-1/+1
Don't open-code DIV_ROUND_UP() kernel macro. Link: https://lore.kernel.org/r/20200413133905.933343-1-leon@kernel.org Signed-off-by: Max Gurtovoy <maxg@mellanox.com> Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2020-04-14RDMA/cma: Limit the scope of rdma_is_consumer_reject functionLeon Romanovsky1-2/+7
The function is local to cma.c, so let's limit its scope. Link: https://lore.kernel.org/r/20200413132323.930869-1-leon@kernel.org Reviewed-by: Maor Gottlieb <maorg@mellanox.com> Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2020-04-14IB: Fix some documentation warningsMauro Carvalho Chehab1-2/+5
Parsing verbs.c with kernel-doc produce some warnings: ./drivers/infiniband/core/verbs.c:2579: WARNING: Unexpected indentation. ./drivers/infiniband/core/verbs.c:2581: WARNING: Block quote ends without a blank line; unexpected unindent. ./drivers/infiniband/core/verbs.c:2613: WARNING: Unexpected indentation. ./drivers/infiniband/core/verbs.c:2579: WARNING: Unexpected indentation. ./drivers/infiniband/core/verbs.c:2581: WARNING: Block quote ends without a blank line; unexpected unindent. ./drivers/infiniband/core/verbs.c:2613: WARNING: Unexpected indentation. Address them by adding an extra blank line and converting the parameters on one of the arguments to a table. Link: https://lore.kernel.org/r/4c5466d0f450c5a9952138150c3485740b37f9c5.1586881715.git.mchehab+huawei@kernel.org Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2020-04-14RDMA: Remove a few extra calls to ib_get_client_data()Jason Gunthorpe1-9/+6
These four places already have easy access to the client data, just use that instead. Link: https://lore.kernel.org/r/0-v1-fae83f600b4a+68-less_get_client_data%25jgg@mellanox.com Acked-by: Ursula Braun <ubraun@linux.ibm.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2020-04-14RDMA/cm: Fix an error check in cm_alloc_id_priv()Dan Carpenter1-1/+1
The xa_alloc_cyclic_irq() function returns either 0 or 1 on success and negatives on error. This code treats 1 as an error and returns ERR_PTR(1) which will cause an Oops in the caller. Fixes: ae78ff3a0f0c ("RDMA/cm: Convert local_id_table to XArray") Link: https://lore.kernel.org/r/20200407093714.GA80285@mwanda Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com> Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2020-04-14RDMA/uverbs: Make the event_queue fds return POLLERR when disassociatedJason Gunthorpe1-0/+2
If is_closed is set, and the event list is empty, then read() will return -EIO without blocking. After setting is_closed in ib_uverbs_free_event_queue(), we do trigger a wake_up on the poll_wait, but the fops->poll() function does not check it, so poll will continue to sleep on an empty list. Fixes: 14e23bd6d221 ("RDMA/core: Fix locking in ib_uverbs_event_read") Link: https://lore.kernel.org/r/0-v1-ace813388969+48859-uverbs_poll_fix%25jgg@mellanox.com Reviewed-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2020-04-14RDMA/cm: Fix missing RDMA_CM_EVENT_REJECTED event after receiving REJ messageLeon Romanovsky1-11/+13
The cm_reset_to_idle() call before formatting event changed the CM_ID state from IB_CM_REQ_RCVD to be IB_CM_IDLE. It caused to wrong value of CM_REJ_MESSAGE_REJECTED field. The result of that was that rdma_reject() calls in the passive side didn't generate RDMA_CM_EVENT_REJECTED event in the active side. Fixes: 81ddb41f876d ("RDMA/cm: Allow ib_send_cm_rej() to be done under lock") Link: https://lore.kernel.org/r/20200406173242.1465911-1-leon@kernel.org Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2020-04-01Merge tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdmaLinus Torvalds12-406/+601
Pull rdma updates from Jason Gunthorpe: "The majority of the patches are cleanups, refactorings and clarity improvements. This cycle saw some more activity from Syzkaller, I think we are now clean on all but one of those bugs, including the long standing and obnoxious rdma_cm locking design defect. Continue to see many drivers getting cleanups, with a few new user visible features. Summary: - Various driver updates for siw, bnxt_re, rxe, efa, mlx5, hfi1 - Lots of cleanup patches for hns - Convert more places to use refcount - Aggressively lock the RDMA CM code that syzkaller says isn't working - Work to clarify ib_cm - Use the new ib_device lifecycle model in bnxt_re - Fix mlx5's MR cache which seems to be failing more often with the new ODP code - mlx5 'dynamic uar' and 'tx steering' user interfaces" * tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (144 commits) RDMA/bnxt_re: make bnxt_re_ib_init static IB/qib: Delete struct qib_ivdev.qp_rnd RDMA/hns: Fix uninitialized variable bug RDMA/hns: Modify the mask of QP number for CQE of hip08 RDMA/hns: Reduce the maximum number of extend SGE per WQE RDMA/hns: Reduce PFC frames in congestion scenarios RDMA/mlx5: Add support for RDMA TX flow table net/mlx5: Add support for RDMA TX steering IB/hfi1: Call kobject_put() when kobject_init_and_add() fails IB/hfi1: Fix memory leaks in sysfs registration and unregistration IB/mlx5: Move to fully dynamic UAR mode once user space supports it IB/mlx5: Limit the scope of struct mlx5_bfreg_info to mlx5_ib IB/mlx5: Extend QP creation to get uar page index from user space IB/mlx5: Extend CQ creation to get uar page index from user space IB/mlx5: Expose UAR object and its alloc/destroy commands IB/hfi1: Get rid of a warning RDMA/hns: Remove redundant judgment of qp_type RDMA/hns: Remove redundant assignment of wc->smac when polling cq RDMA/hns: Remove redundant qpc setup operations RDMA/hns: Remove meaningless prints ...
2020-03-26RDMA/cm: Update num_paths in cma_resolve_iboe_route error flowAvihai Horon1-0/+1
After a successful allocation of path_rec, num_paths is set to 1, but any error after such allocation will leave num_paths uncleared. This causes to de-referencing a NULL pointer later on. Hence, num_paths needs to be set back to 0 if such an error occurs. The following crash from syzkaller revealed it. kasan: CONFIG_KASAN_INLINE enabled kasan: GPF could be caused by NULL-ptr deref or user memory access general protection fault: 0000 [#1] SMP DEBUG_PAGEALLOC KASAN PTI CPU: 0 PID: 357 Comm: syz-executor060 Not tainted 4.18.0+ #311 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.11.0-0-g63451fca13-prebuilt.qemu-project.org 04/01/2014 RIP: 0010:ib_copy_path_rec_to_user+0x94/0x3e0 Code: f1 f1 f1 f1 c7 40 0c 00 00 f4 f4 65 48 8b 04 25 28 00 00 00 48 89 45 c8 31 c0 e8 d7 60 24 ff 48 8d 7b 4c 48 89 f8 48 c1 e8 03 <42> 0f b6 14 30 48 89 f8 83 e0 07 83 c0 03 38 d0 7c 08 84 d2 0f 85 RSP: 0018:ffff88006586f980 EFLAGS: 00010207 RAX: 0000000000000009 RBX: 0000000000000000 RCX: 1ffff1000d5fe475 RDX: ffff8800621e17c0 RSI: ffffffff820d45f9 RDI: 000000000000004c RBP: ffff88006586fa50 R08: ffffed000cb0df73 R09: ffffed000cb0df72 R10: ffff88006586fa70 R11: ffffed000cb0df73 R12: 1ffff1000cb0df30 R13: ffff88006586fae8 R14: dffffc0000000000 R15: ffff88006aff2200 FS: 00000000016fc880(0000) GS:ffff88006d000000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000020000040 CR3: 0000000063fec000 CR4: 00000000000006b0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: ? ib_copy_path_rec_from_user+0xcc0/0xcc0 ? __mutex_unlock_slowpath+0xfc/0x670 ? wait_for_completion+0x3b0/0x3b0 ? ucma_query_route+0x818/0xc60 ucma_query_route+0x818/0xc60 ? ucma_listen+0x1b0/0x1b0 ? sched_clock_cpu+0x18/0x1d0 ? sched_clock_cpu+0x18/0x1d0 ? ucma_listen+0x1b0/0x1b0 ? ucma_write+0x292/0x460 ucma_write+0x292/0x460 ? ucma_close_id+0x60/0x60 ? sched_clock_cpu+0x18/0x1d0 ? sched_clock_cpu+0x18/0x1d0 __vfs_write+0xf7/0x620 ? ucma_close_id+0x60/0x60 ? kernel_read+0x110/0x110 ? time_hardirqs_on+0x19/0x580 ? lock_acquire+0x18b/0x3a0 ? finish_task_switch+0xf3/0x5d0 ? _raw_spin_unlock_irq+0x29/0x40 ? _raw_spin_unlock_irq+0x29/0x40 ? finish_task_switch+0x1be/0x5d0 ? __switch_to_asm+0x34/0x70 ? __switch_to_asm+0x40/0x70 ? security_file_permission+0x172/0x1e0 vfs_write+0x192/0x460 ksys_write+0xc6/0x1a0 ? __ia32_sys_read+0xb0/0xb0 ? entry_SYSCALL_64_after_hwframe+0x3e/0xbe ? do_syscall_64+0x1d/0x470 do_syscall_64+0x9e/0x470 entry_SYSCALL_64_after_hwframe+0x49/0xbe Fixes: 3c86aa70bf67 ("RDMA/cm: Add RDMA CM support for IBoE devices") Link: https://lore.kernel.org/r/20200318101741.47211-1-leon@kernel.org Signed-off-by: Avihai Horon <avihaih@mellanox.com> Reviewed-by: Maor Gottlieb <maorg@mellanox.com> Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2020-03-24RDMA/core: Ensure security pkey modify is not lostMike Marciniszyn1-8/+3
The following modify sequence (loosely based on ipoib) will lose a pkey modifcation: - Modify (pkey index, port) - Modify (new pkey index, NO port) After the first modify, the qp_pps list will have saved the pkey and the unit on the main list. During the second modify, get_new_pps() will fetch the port from qp_pps and read the new pkey index from qp_attr->pkey_index. The state will still be zero, or IB_PORT_PKEY_NOT_VALID. Because of the invalid state, the new values will never replace the one in the qp pps list, losing the new pkey. This happens because the following if statements will never correct the state because the first term will be false. If the code had been executed, it would incorrectly overwrite valid values. if ((qp_attr_mask & IB_QP_PKEY_INDEX) && (qp_attr_mask & IB_QP_PORT)) new_pps->main.state = IB_PORT_PKEY_VALID; if (!(qp_attr_mask & (IB_QP_PKEY_INDEX | IB_QP_PORT)) && qp_pps) { new_pps->main.port_num = qp_pps->main.port_num; new_pps->main.pkey_index = qp_pps->main.pkey_index; if (qp_pps->main.state != IB_PORT_PKEY_NOT_VALID) new_pps->main.state = IB_PORT_PKEY_VALID; } Fix by joining the two if statements with an or test to see if qp_pps is non-NULL and in the correct state. Fixes: 1dd017882e01 ("RDMA/core: Fix protection fault in get_pkey_idx_qp_list") Link: https://lore.kernel.org/r/20200313124704.14982.55907.stgit@awfm-01.aw.intel.com Reviewed-by: Kaike Wan <kaike.wan@intel.com> Signed-off-by: Mike Marciniszyn <mike.marciniszyn@intel.com> Reviewed-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2020-03-17RDMA/cm: Make sure the cm_id is in the IB_CM_IDLE state in destroyJason Gunthorpe1-20/+21
The first switch statement in cm_destroy_id() tries to move the ID to either IB_CM_IDLE or IB_CM_TIMEWAIT. Both states will block concurrent MAD handlers from progressing. Previous patches removed the unreliably lock/unlock sequences in this flow, this patch removes the extra locking steps and adds the missing parts to guarantee that destroy reaches IB_CM_IDLE. There is no point in leaving the ID in the IB_CM_TIMEWAIT state the memory about to be kfreed. Rework things to hold the lock across all the state transitions and directly assert when done that it ended up in IB_CM_IDLE as expected. This was accompanied by a careful audit of all the state transitions here, which generally did end up in IDLE on their success and non-racy paths. Link: https://lore.kernel.org/r/20200310092545.251365-16-leon@kernel.org Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2020-03-17RDMA/cm: Allow ib_send_cm_sidr_rep() to be done under lockJason Gunthorpe1-30/+28
The first thing ib_send_cm_sidr_rep() does is obtain the lock, so use the usual unlocked wrapper, locked actor pattern here. Get rid of the cm_reject_sidr_req() wrapper so each call site can call the locked or unlocked version as required. This avoids a sketchy lock/unlock sequence (which could allow state to change) during cm_destroy_id(). Link: https://lore.kernel.org/r/20200310092545.251365-15-leon@kernel.org Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2020-03-17RDMA/cm: Allow ib_send_cm_rej() to be done under lockJason Gunthorpe1-40/+52
The first thing ib_send_cm_rej() does is obtain the lock, so use the usual unlocked wrapper, locked actor pattern here. This avoids a sketchy lock/unlock sequence (which could allow state to change) during cm_destroy_id(). While here simplify some of the logic in the implementation. Link: https://lore.kernel.org/r/20200310092545.251365-14-leon@kernel.org Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2020-03-17RDMA/cm: Allow ib_send_cm_drep() to be done under lockJason Gunthorpe1-22/+33
The first thing ib_send_cm_drep() does is obtain the lock, so use the usual unlocked wrapper, locked actor pattern here. This avoids a sketchy lock/unlock sequence (which could allow state to change) during cm_destroy_id(). Link: https://lore.kernel.org/r/20200310092545.251365-13-leon@kernel.org Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2020-03-17RDMA/cm: Allow ib_send_cm_dreq() to be done under lockJason Gunthorpe1-20/+34
The first thing ib_send_cm_dreq() does is obtain the lock, so use the usual unlocked wrapper, locked actor pattern here. This avoids a sketchy lock/unlock sequence (which could allow state to change) during cm_destroy_id(). Link: https://lore.kernel.org/r/20200310092545.251365-12-leon@kernel.org Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2020-03-17RDMA/cm: Add some lockdep assertions for cm_id_priv->lockJason Gunthorpe1-0/+6
These functions all touch state, so must be called under the lock. Inspection shows this is currently true. Link: https://lore.kernel.org/r/20200310092545.251365-11-leon@kernel.org Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2020-03-17RDMA/cm: Add missing locking around id.state in cm_dup_req_handlerJason Gunthorpe1-1/+5
All accesses to id.state must be done under the spinlock. Fixes: a977049dacde ("[PATCH] IB: Add the kernel CM implementation") Link: https://lore.kernel.org/r/20200310092545.251365-10-leon@kernel.org Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2020-03-17RDMA/cm: Make it clearer how concurrency works in cm_req_handler()Jason Gunthorpe1-42/+57
ib_crate_cm_id() immediately places the id in the xarray, and publishes it into the remote_id and remote_qpn rbtrees. This makes it visible to other threads before it is fully set up. It appears the thinking here was that the states IB_CM_IDLE and IB_CM_REQ_RCVD do not allow any MAD handler or lookup in the remote_id and remote_qpn rbtrees to advance. However, cm_rej_handler() does take an action on IB_CM_REQ_RCVD, which is not really expected by the design. Make the whole thing clearer: - Keep the new cm_id out of the xarray until it is completely set up. This directly prevents MAD handlers and all rbtree lookups from seeing the pointer. - Move all the trivial setup right to the top so it is obviously done before any concurrency begins - Move the mutation of the cm_id_priv out of cm_match_id() and into the caller so the state transition is obvious - Place the manipulation of the work_list at the end, under lock, after the cm_id is placed in the xarray. The work_count cannot change on an ID outside the xarray. - Add some comments Link: https://lore.kernel.org/r/20200310092545.251365-9-leon@kernel.org Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2020-03-17RDMA/cm: Make it clear that there is no concurrency in cm_sidr_req_handler()Jason Gunthorpe1-27/+37
ib_create_cm_id() immediately places the id in the xarray, so it is visible to network traffic. The state is initially set to IB_CM_IDLE and all the MAD handlers will test this state under lock and refuse to advance from IDLE, so adding to the xarray is harmless. Further, the set to IB_CM_SIDR_REQ_RCVD also excludes all MAD handlers. However, the local_id isn't even used for SIDR mode, and there will be no input MADs related to the newly created ID. So, make the whole flow simpler so it can be understood: - Do not put the SIDR cm_id in the xarray. This directly shows that there is no concurrency - Delete the confusing work_count and pending_list manipulations. This mechanism is only used by MAD handlers and timewait, neither of which apply to SIDR. - Add a few comments and rename 'cur_cm_id_priv' to 'listen_cm_id_priv' - Move other loose sets up to immediately after cm_id creation so that the cm_id is fully configured right away. This fixes an oversight where the service_id will not be returned back on a IB_SIDR_UNSUPPORTED reject. Link: https://lore.kernel.org/r/20200310092545.251365-8-leon@kernel.org Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2020-03-17RDMA/cm: Read id.state under lock when doing pr_debug()Jason Gunthorpe1-4/+4
The lock should not be dropped before doing the pr_debug() print as it is accessing data protected by the lock, such as id.state. Fixes: 119bf81793ea ("IB/cm: Add debug prints to ib_cm") Link: https://lore.kernel.org/r/20200310092545.251365-7-leon@kernel.org Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2020-03-17RDMA/cm: Simplify establishing a listen cm_idJason Gunthorpe1-83/+116
Any manipulation of cm_id->state must be done under the cm_id_priv->lock, the two routines that added listens did not follow this rule, because they never participate in any concurrent access around the state. However, since this exception makes the code hard to understand, simplify the flow so that it can be fully locked: - Move manipulation of listen_sharecount into cm_insert_listen() so it is trivially under the cm.lock without having to expose the cm.lock to the caller. - Push the cm.lock down into cm_insert_listen() and have the function increment the reference count before returning an existing pointer. - Split ib_cm_listen() into an cm_init_listen() and do not call ib_cm_listen() from ib_cm_insert_listen() - Make both ib_cm_listen() and ib_cm_insert_listen() directly call cm_insert_listen() under their cm_id_priv->lock which does both a collision detect and, if needed, the insert (atomically) - Enclose all state manipulation within the cm_id_priv->lock, notice this set can be done safely after cm_insert_listen() as no reader is allowed to read the state without holding the lock. - Do not set the listen cm_id in the xarray, as it is never correct to look it up. This makes the concurrency simpler to understand. Many needless error unwinds are removed in the process. Link: https://lore.kernel.org/r/20200310092545.251365-6-leon@kernel.org Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2020-03-17RDMA/cm: Make the destroy_id flow more robustJason Gunthorpe1-5/+8
Too much of the destruction is very carefully sensitive to the state and various other things. Move more code to the unconditional path and add several WARN_ONs to check consistency. Link: https://lore.kernel.org/r/20200310092545.251365-5-leon@kernel.org Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2020-03-17RDMA/cm: Remove a race freeing timewait_infoJason Gunthorpe1-10/+15
When creating a cm_id during REQ the id immediately becomes visible to the other MAD handlers, and shortly after the state is moved to IB_CM_REQ_RCVD This allows cm_rej_handler() to run concurrently and free the work: CPU 0 CPU1 cm_req_handler() ib_create_cm_id() cm_match_req() id_priv->state = IB_CM_REQ_RCVD cm_rej_handler() cm_acquire_id() spin_lock(&id_priv->lock) switch (id_priv->state) case IB_CM_REQ_RCVD: cm_reset_to_idle() kfree(id_priv->timewait_info); goto destroy destroy: kfree(id_priv->timewait_info); id_priv->timewait_info = NULL Causing a double free or worse. Do not free the timewait_info without also holding the id_priv->lock. Simplify this entire flow by making the free unconditional during cm_destroy_id() and removing the confusing special case error unwind during creation of the timewait_info. This also fixes a leak of the timewait if cm_destroy_id() is called in IB_CM_ESTABLISHED with an XRC TGT QP. The state machine will be left in ESTABLISHED while it needed to transition through IB_CM_TIMEWAIT to release the timewait pointer. Also fix a leak of the timewait_info if the caller mis-uses the API and does ib_send_cm_reqs(). Fixes: a977049dacde ("[PATCH] IB: Add the kernel CM implementation") Link: https://lore.kernel.org/r/20200310092545.251365-4-leon@kernel.org Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2020-03-17RDMA/cm: Fix checking for allowed duplicate listensJason Gunthorpe1-1/+2
The test here typod the cm_id_priv to use, it used the one that was freshly allocated. By definition the allocated one has the matching cm_handler and zero context, so the condition was always true. Instead check that the existing listening ID is compatible with the proposed handler so that it can be shared, as was originally intended. Fixes: 067b171b8679 ("IB/cm: Share listening CM IDs") Link: https://lore.kernel.org/r/20200310092545.251365-3-leon@kernel.org Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2020-03-17RDMA/cm: Fix ordering of xa_alloc_cyclic() in ib_create_cm_id()Jason Gunthorpe1-16/+11
xa_alloc_cyclic() is a SMP release to be paired with some later acquire during xa_load() as part of cm_acquire_id(). As such, xa_alloc_cyclic() must be done after the cm_id is fully initialized, in particular, it absolutely must be after the refcount_set(), otherwise the refcount_inc() in cm_acquire_id() may not see the set. As there are several cases where a reader will be able to use the id.local_id after cm_acquire_id in the IB_CM_IDLE state there needs to be an unfortunate split into a NULL allocate and a finalizing xa_store. Fixes: a977049dacde ("[PATCH] IB: Add the kernel CM implementation") Link: https://lore.kernel.org/r/20200310092545.251365-2-leon@kernel.org Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2020-03-13RDMA/cm: Delete not implemented CM peer to peer communicationLeon Romanovsky1-7/+0
Peer to peer support was never implemented, so delete it to make code less clutter. Link: https://lore.kernel.org/r/20200310091438.248429-6-leon@kernel.org Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Reviewed-by: Mark Zhang <markz@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Copyright © 1996 – 2026 Jason A. Donenfeld. All Rights Reverse Engineered.