talos-op-linux/drivers/infiniband, branch master

IB/mlx5: Use div64_u64 for num_var_hw_entries calculation

2020-02-14T19:21:52+00:00

On i386: ERROR: "__udivdi3" [drivers/infiniband/hw/mlx5/mlx5_ib.ko] undefined! ERROR: "__divdi3" [drivers/infiniband/hw/mlx5/mlx5_ib.ko] undefined! Fixes: f164be8c0366 ("IB/mlx5: Extend caps stage to handle VAR capabilities") Reported-by: Randy Dunlap Acked-by: Randy Dunlap # build-tested Reported-by: Alexander Lobakin Signed-off-by: Jason Gunthorpe

RDMA/core: Fix protection fault in get_pkey_idx_qp_list

2020-02-13T16:31:56+00:00

We don't need to set pkey as valid in case that user set only one of pkey index or port number, otherwise it will be resulted in NULL pointer dereference while accessing to uninitialized pkey list. 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 KASAN PTI CPU: 1 PID: 14753 Comm: syz-executor.2 Not tainted 5.5.0-rc5 #2 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.1-0-ga5cab58e9a3f-prebuilt.qemu.org 04/01/2014 RIP: 0010:get_pkey_idx_qp_list+0x161/0x2d0 Code: 01 00 00 49 8b 5e 20 4c 39 e3 0f 84 b9 00 00 00 e8 e4 42 6e fe 48 8d 7b 10 48 b8 00 00 00 00 00 fc ff df 48 89 fa 48 c1 ea 03 <0f> b6 04 02 84 c0 74 08 3c 01 0f 8e d0 00 00 00 48 8d 7d 04 48 b8 RSP: 0018:ffffc9000bc6f950 EFLAGS: 00010202 RAX: dffffc0000000000 RBX: 0000000000000000 RCX: ffffffff82c8bdec RDX: 0000000000000002 RSI: ffffc900030a8000 RDI: 0000000000000010 RBP: ffff888112c8ce80 R08: 0000000000000004 R09: fffff5200178df1f R10: 0000000000000001 R11: fffff5200178df1f R12: ffff888115dc4430 R13: ffff888115da8498 R14: ffff888115dc4410 R15: ffff888115da8000 FS: 00007f20777de700(0000) GS:ffff88811b100000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000001b2f721000 CR3: 00000001173ca002 CR4: 0000000000360ee0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: port_pkey_list_insert+0xd7/0x7c0 ib_security_modify_qp+0x6fa/0xfc0 _ib_modify_qp+0x8c4/0xbf0 modify_qp+0x10da/0x16d0 ib_uverbs_modify_qp+0x9a/0x100 ib_uverbs_write+0xaa5/0xdf0 __vfs_write+0x7c/0x100 vfs_write+0x168/0x4a0 ksys_write+0xc8/0x200 do_syscall_64+0x9c/0x390 entry_SYSCALL_64_after_hwframe+0x44/0xa9 Fixes: d291f1a65232 ("IB/core: Enforce PKey security on QPs") Link: https://lore.kernel.org/r/20200212080651.GB679970@unreal Signed-off-by: Maor Gottlieb Signed-off-by: Leon Romanovsky Message-Id: <20200212080651.GB679970@unreal>

RDMA/rxe: Fix soft lockup problem due to using tasklets in softirq

2020-02-13T14:51:09+00:00

When run stress tests with RXE, the following Call Traces often occur watchdog: BUG: soft lockup - CPU#2 stuck for 22s! [swapper/2:0] ... Call Trace: create_object+0x3f/0x3b0 kmem_cache_alloc_node_trace+0x129/0x2d0 __kmalloc_reserve.isra.52+0x2e/0x80 __alloc_skb+0x83/0x270 rxe_init_packet+0x99/0x150 [rdma_rxe] rxe_requester+0x34e/0x11a0 [rdma_rxe] rxe_do_task+0x85/0xf0 [rdma_rxe] tasklet_action_common.isra.21+0xeb/0x100 __do_softirq+0xd0/0x298 irq_exit+0xc5/0xd0 smp_apic_timer_interrupt+0x68/0x120 apic_timer_interrupt+0xf/0x20 ... The root cause is that tasklet is actually a softirq. In a tasklet handler, another softirq handler is triggered. Usually these softirq handlers run on the same cpu core. So this will cause "soft lockup Bug". Fixes: 8700e3e7c485 ("Soft RoCE driver") Link: https://lore.kernel.org/r/20200212072635.682689-8-leon@kernel.org Signed-off-by: Zhu Yanjun Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe

RDMA/mlx5: Prevent overflow in mmap offset calculations

2020-02-13T14:39:23+00:00

The cmd and index variables declared as u16 and the result is supposed to be stored in u64. The C arithmetic rules doesn't promote "(index >> 8) << 16" to be u64 and leaves the end result to be u16. Fixes: 7be76bef320b ("IB/mlx5: Introduce VAR object and its alloc/destroy methods") Link: https://lore.kernel.org/r/20200212072635.682689-10-leon@kernel.org Signed-off-by: Leon Romanovsky Reviewed-by: Jason Gunthorpe Signed-off-by: Jason Gunthorpe

IB/umad: Fix kernel crash while unloading ib_umad

2020-02-13T14:00:50+00:00

When disassociating a device from umad we must ensure that the sysfs access is prevented before blocking the fops, otherwise assumptions in syfs don't hold: CPU0 CPU1 ib_umad_kill_port() ibdev_show() port->ib_dev = NULL dev_name(port->ib_dev) The prior patch made an error in moving the device_destroy(), it should have been split into device_del() (above) and put_device() (below). At this point we already have the split, so move the device_del() back to its original place. kernel stack PF: error_code(0x0000) - not-present page Oops: 0000 [#1] SMP DEBUG_PAGEALLOC PTI RIP: 0010:ibdev_show+0x18/0x50 [ib_umad] RSP: 0018:ffffc9000097fe40 EFLAGS: 00010282 RAX: 0000000000000000 RBX: ffffffffa0441120 RCX: ffff8881df514000 RDX: ffff8881df514000 RSI: ffffffffa0441120 RDI: ffff8881df1e8870 RBP: ffffffff81caf000 R08: ffff8881df1e8870 R09: 0000000000000000 R10: 0000000000001000 R11: 0000000000000003 R12: ffff88822f550b40 R13: 0000000000000001 R14: ffffc9000097ff08 R15: ffff8882238bad58 FS: 00007f1437ff3740(0000) GS:ffff888236940000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00000000000004e8 CR3: 00000001e0dfc001 CR4: 00000000001606e0 Call Trace: dev_attr_show+0x15/0x50 sysfs_kf_seq_show+0xb8/0x1a0 seq_read+0x12d/0x350 vfs_read+0x89/0x140 ksys_read+0x55/0xd0 do_syscall_64+0x55/0x1b0 entry_SYSCALL_64_after_hwframe+0x44/0xa9: Fixes: cf7ad3030271 ("IB/umad: Avoid destroying device while it is accessed") Link: https://lore.kernel.org/r/20200212072635.682689-9-leon@kernel.org Signed-off-by: Yonatan Cohen Signed-off-by: Leon Romanovsky Reviewed-by: Jason Gunthorpe Signed-off-by: Jason Gunthorpe

RDMA/mlx5: Fix async events cleanup flows

2020-02-13T13:48:17+00:00

As in the prior patch, the devx code is not fully cleaning up its event_lists before finishing driver_destroy allowing a later read to trigger user after free conditions. Re-arrange things so that the event_list is always empty after destroy and ensure it remains empty until the file is closed. Fixes: f7c8416ccea5 ("RDMA/core: Simplify destruction of FD uobjects") Link: https://lore.kernel.org/r/20200212072635.682689-7-leon@kernel.org Signed-off-by: Yishai Hadas Signed-off-by: Leon Romanovsky Reviewed-by: Jason Gunthorpe Signed-off-by: Jason Gunthorpe

RDMA/core: Add missing list deletion on freeing event queue

2020-02-13T13:44:49+00:00

When the uobject file scheme was revised to allow device disassociation from the file it became possible for read() to still happen the driver destroys the uobject. The old clode code was not tolerant to concurrent read, and when it was moved to the driver destroy it creates a bug. Ensure the event_list is empty after driver destroy by adding the missing list_del(). Otherwise read() can trigger a use after free and double kfree. Fixes: f7c8416ccea5 ("RDMA/core: Simplify destruction of FD uobjects") Link: https://lore.kernel.org/r/20200212072635.682689-6-leon@kernel.org Signed-off-by: Michael Guralnik Reviewed-by: Yishai Hadas Signed-off-by: Leon Romanovsky Reviewed-by: Jason Gunthorpe Signed-off-by: Jason Gunthorpe

RDMA/siw: Remove unwanted WARN_ON in siw_cm_llp_data_ready()

2020-02-11T18:33:58+00:00

Warnings like below can fill up the dmesg while disconnecting RDMA connections. Hence, remove the unwanted WARN_ON. WARNING: CPU: 6 PID: 0 at drivers/infiniband/sw/siw/siw_cm.c:1229 siw_cm_llp_data_ready+0xc1/0xd0 [siw] RIP: 0010:siw_cm_llp_data_ready+0xc1/0xd0 [siw] Call Trace: tcp_data_queue+0x226/0xb40 tcp_rcv_established+0x220/0x620 tcp_v4_do_rcv+0x12a/0x1e0 tcp_v4_rcv+0xb05/0xc00 ip_local_deliver_finish+0x69/0x210 ip_local_deliver+0x6b/0xe0 ip_rcv+0x273/0x362 __netif_receive_skb_core+0xb35/0xc30 netif_receive_skb_internal+0x3d/0xb0 napi_gro_frags+0x13b/0x200 t4_ethrx_handler+0x433/0x7d0 [cxgb4] process_responses+0x318/0x580 [cxgb4] napi_rx_handler+0x14/0x100 [cxgb4] net_rx_action+0x149/0x3b0 __do_softirq+0xe3/0x30a irq_exit+0x100/0x110 do_IRQ+0x7f/0xe0 common_interrupt+0xf/0xf Link: https://lore.kernel.org/r/20200207141429.27927-1-krishna2@chelsio.com Signed-off-by: Krishnamraju Eraparaju Signed-off-by: Jason Gunthorpe

RDMA/iw_cxgb4: initiate CLOSE when entering TERM

2020-02-11T18:28:00+00:00

As per draft-hilland-iwarp-verbs-v1.0, sec 6.2.3, always initiate a CLOSE when entering into TERM state. In c4iw_modify_qp(), disconnect operation should only be performed when the modify_qp call is invoked from ib_core. And all other internal modify_qp calls(invoked within iw_cxgb4) that needs 'disconnect' should call c4iw_ep_disconnect() explicitly after modify_qp. Otherwise, deadlocks like below can occur: Call Trace: schedule+0x2f/0xa0 schedule_preempt_disabled+0xa/0x10 __mutex_lock.isra.5+0x2d0/0x4a0 c4iw_ep_disconnect+0x39/0x430 => tries to reacquire ep lock again c4iw_modify_qp+0x468/0x10d0 rx_data+0x218/0x570 => acquires ep lock process_work+0x5f/0x70 process_one_work+0x1a7/0x3b0 worker_thread+0x30/0x390 kthread+0x112/0x130 ret_from_fork+0x35/0x40 Fixes: d2c33370ae73 ("RDMA/iw_cxgb4: Always disconnect when QP is transitioning to TERMINATE state") Link: https://lore.kernel.org/r/20200204091230.7210-1-krishna2@chelsio.com Signed-off-by: Krishnamraju Eraparaju Signed-off-by: Jason Gunthorpe

IB/mlx5: Return failure when rts2rts_qp_counters_set_id is not supported

2020-02-11T18:23:01+00:00

When binding a QP with a counter and the QP state is not RESET, return failure if the rts2rts_qp_counters_set_id is not supported by the device. This is to prevent cases like manual bind for Connect-IB devices from returning success when the feature is not supported. Fixes: d14133dd4161 ("IB/mlx5: Support set qp counter") Link: https://lore.kernel.org/r/20200126171708.5167-1-leon@kernel.org Signed-off-by: Mark Zhang Reviewed-by: Maor Gottlieb Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe