Skip to content

K
Kernel

openeuler / Kernel
接近 2 年 前同步成功

通知 8
Star 0
Fork 0
K
Kernel
切换分支/标签
  1. 04 1月, 2020 1 次提交
  3. 24 11月, 2019 1 次提交
  5. 18 6月, 2019 1 次提交
  7. 02 4月, 2019 1 次提交
  9. 30 3月, 2019 1 次提交
  11. 07 3月, 2019 1 次提交
    • M
      IB/hfi1: Close race condition on user context disable and close · bc5add09
      由 Michael J. Ruhl 提交于 
      When disabling and removing a receive context, it is possible for an
asynchronous event (i.e IRQ) to occur.  Because of this, there is a race
between cleaning up the context, and the context being used by the
asynchronous event.

cpu 0  (context cleanup)
    rc->ref_count-- (ref_count == 0)
    hfi1_rcd_free()
cpu 1  (IRQ (with rcd index))
	rcd_get_by_index()
	lock
	ref_count+++     <-- reference count race (WARNING)
	return rcd
	unlock
cpu 0
    hfi1_free_ctxtdata() <-- incorrect free location
    lock
    remove rcd from array
    unlock
    free rcd

This race will cause the following WARNING trace:

WARNING: CPU: 0 PID: 175027 at include/linux/kref.h:52 hfi1_rcd_get_by_index+0x84/0xa0 [hfi1]
CPU: 0 PID: 175027 Comm: IMB-MPI1 Kdump: loaded Tainted: G OE ------------ 3.10.0-957.el7.x86_64 #1
Hardware name: Intel Corporation S2600KP/S2600KP, BIOS SE5C610.86B.11.01.0076.C4.111920150602 11/19/2015
Call Trace:
  dump_stack+0x19/0x1b
  __warn+0xd8/0x100
  warn_slowpath_null+0x1d/0x20
  hfi1_rcd_get_by_index+0x84/0xa0 [hfi1]
  is_rcv_urgent_int+0x24/0x90 [hfi1]
  general_interrupt+0x1b6/0x210 [hfi1]
  __handle_irq_event_percpu+0x44/0x1c0
  handle_irq_event_percpu+0x32/0x80
  handle_irq_event+0x3c/0x60
  handle_edge_irq+0x7f/0x150
  handle_irq+0xe4/0x1a0
  do_IRQ+0x4d/0xf0
  common_interrupt+0x162/0x162

The race can also lead to a use after free which could be similar to:

general protection fault: 0000 1 SMP
CPU: 71 PID: 177147 Comm: IMB-MPI1 Kdump: loaded Tainted: G W OE ------------ 3.10.0-957.el7.x86_64 #1
Hardware name: Intel Corporation S2600KP/S2600KP, BIOS SE5C610.86B.11.01.0076.C4.111920150602 11/19/2015
task: ffff9962a8098000 ti: ffff99717a508000 task.ti: ffff99717a508000 __kmalloc+0x94/0x230
Call Trace:
  ? hfi1_user_sdma_process_request+0x9c8/0x1250 [hfi1]
  hfi1_user_sdma_process_request+0x9c8/0x1250 [hfi1]
  hfi1_aio_write+0xba/0x110 [hfi1]
  do_sync_readv_writev+0x7b/0xd0
  do_readv_writev+0xce/0x260
  ? handle_mm_fault+0x39d/0x9b0
  ? pick_next_task_fair+0x5f/0x1b0
  ? sched_clock_cpu+0x85/0xc0
  ? __schedule+0x13a/0x890
  vfs_writev+0x35/0x60
  SyS_writev+0x7f/0x110
  system_call_fastpath+0x22/0x27

Use the appropriate kref API to verify access.

Reorder context cleanup to ensure context removal before cleanup occurs
correctly.

Cc: stable@vger.kernel.org # v4.14.0+
Fixes: f683c80c ("IB/hfi1: Resolve kernel panics by reference counting receive contexts")
Reviewed-by: NMike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: NMichael J. Ruhl <michael.j.ruhl@intel.com>
Signed-off-by: NDennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>
      bc5add09
  13. 06 2月, 2019 3 次提交
  15. 01 2月, 2019 2 次提交
  17. 07 12月, 2018 1 次提交
  19. 04 12月, 2018 1 次提交
    • P
      IB/hfi1: Fix an out-of-bounds access in get_hw_stats · 36d84219
      由 Piotr Stankiewicz 提交于 
      When running with KASAN, the following trace is produced:

[   62.535888]

==================================================================
[   62.544930] BUG: KASAN: slab-out-of-bounds in
gut_hw_stats+0x122/0x230 [hfi1]
[   62.553856] Write of size 8 at addr ffff88080e8d6330 by task
kworker/0:1/14

[   62.565333] CPU: 0 PID: 14 Comm: kworker/0:1 Not tainted
4.19.0-test-build-kasan+ #8
[   62.575087] Hardware name: Intel Corporation S2600KPR/S2600KPR, BIOS
SE5C610.86B.01.01.0019.101220160604 10/12/2016
[   62.587951] Workqueue: events work_for_cpu_fn
[   62.594050] Call Trace:
[   62.598023]  dump_stack+0xc6/0x14c
[   62.603089]  ? dump_stack_print_info.cold.1+0x2f/0x2f
[   62.610041]  ? kmsg_dump_rewind_nolock+0x59/0x59
[   62.616615]  ? get_hw_stats+0x122/0x230 [hfi1]
[   62.622985]  print_address_description+0x6c/0x23c
[   62.629744]  ? get_hw_stats+0x122/0x230 [hfi1]
[   62.636108]  kasan_report.cold.6+0x241/0x308
[   62.642365]  get_hw_stats+0x122/0x230 [hfi1]
[   62.648703]  ? hfi1_alloc_rn+0x40/0x40 [hfi1]
[   62.655088]  ? __kmalloc+0x110/0x240
[   62.660695]  ? hfi1_alloc_rn+0x40/0x40 [hfi1]
[   62.667142]  setup_hw_stats+0xd8/0x430 [ib_core]
[   62.673972]  ? show_hfi+0x50/0x50 [hfi1]
[   62.680026]  ib_device_register_sysfs+0x165/0x180 [ib_core]
[   62.687995]  ib_register_device+0x5a2/0xa10 [ib_core]
[   62.695340]  ? show_hfi+0x50/0x50 [hfi1]
[   62.701421]  ? ib_unregister_device+0x2e0/0x2e0 [ib_core]
[   62.709222]  ? __vmalloc_node_range+0x2d0/0x380
[   62.716131]  ? rvt_driver_mr_init+0x11f/0x2d0 [rdmavt]
[   62.723735]  ? vmalloc_node+0x5c/0x70
[   62.729697]  ? rvt_driver_mr_init+0x11f/0x2d0 [rdmavt]
[   62.737347]  ? rvt_driver_mr_init+0x1f5/0x2d0 [rdmavt]
[   62.744998]  ? __rvt_alloc_mr+0x110/0x110 [rdmavt]
[   62.752315]  ? rvt_rc_error+0x140/0x140 [rdmavt]
[   62.759434]  ? rvt_vma_open+0x30/0x30 [rdmavt]
[   62.766364]  ? mutex_unlock+0x1d/0x40
[   62.772445]  ? kmem_cache_create_usercopy+0x15d/0x230
[   62.780115]  rvt_register_device+0x1f6/0x360 [rdmavt]
[   62.787823]  ? rvt_get_port_immutable+0x180/0x180 [rdmavt]
[   62.796058]  ? __get_txreq+0x400/0x400 [hfi1]
[   62.802969]  ? memcpy+0x34/0x50
[   62.808611]  hfi1_register_ib_device+0xde6/0xeb0 [hfi1]
[   62.816601]  ? hfi1_get_npkeys+0x10/0x10 [hfi1]
[   62.823760]  ? hfi1_init+0x89f/0x9a0 [hfi1]
[   62.830469]  ? hfi1_setup_eagerbufs+0xad0/0xad0 [hfi1]
[   62.838204]  ? pcie_capability_clear_and_set_word+0xcd/0xe0
[   62.846429]  ? pcie_capability_read_word+0xd0/0xd0
[   62.853791]  ? hfi1_pcie_init+0x187/0x4b0 [hfi1]
[   62.860958]  init_one+0x67f/0xae0 [hfi1]
[   62.867301]  ? hfi1_init+0x9a0/0x9a0 [hfi1]
[   62.873876]  ? wait_woken+0x130/0x130
[   62.879860]  ? read_word_at_a_time+0xe/0x20
[   62.886329]  ? strscpy+0x14b/0x280
[   62.891998]  ? hfi1_init+0x9a0/0x9a0 [hfi1]
[   62.898405]  local_pci_probe+0x70/0xd0
[   62.904295]  ? pci_device_shutdown+0x90/0x90
[   62.910833]  work_for_cpu_fn+0x29/0x40
[   62.916750]  process_one_work+0x584/0x960
[   62.922974]  ? rcu_work_rcufn+0x40/0x40
[   62.928991]  ? __schedule+0x396/0xdc0
[   62.934806]  ? __sched_text_start+0x8/0x8
[   62.941020]  ? pick_next_task_fair+0x68b/0xc60
[   62.947674]  ? run_rebalance_domains+0x260/0x260
[   62.954471]  ? __list_add_valid+0x29/0xa0
[   62.960607]  ? move_linked_works+0x1c7/0x230
[   62.967077]  ?
trace_event_raw_event_workqueue_execute_start+0x140/0x140
[   62.976248]  ? mutex_lock+0xa6/0x100
[   62.982029]  ? __mutex_lock_slowpath+0x10/0x10
[   62.988795]  ? __switch_to+0x37a/0x710
[   62.994731]  worker_thread+0x62e/0x9d0
[   63.000602]  ? max_active_store+0xf0/0xf0
[   63.006828]  ? __switch_to_asm+0x40/0x70
[   63.012932]  ? __switch_to_asm+0x34/0x70
[   63.019013]  ? __switch_to_asm+0x40/0x70
[   63.025042]  ? __switch_to_asm+0x34/0x70
[   63.031030]  ? __switch_to_asm+0x40/0x70
[   63.037006]  ? __schedule+0x396/0xdc0
[   63.042660]  ? kmem_cache_alloc_trace+0xf3/0x1f0
[   63.049323]  ? kthread+0x59/0x1d0
[   63.054594]  ? ret_from_fork+0x35/0x40
[   63.060257]  ? __sched_text_start+0x8/0x8
[   63.066212]  ? schedule+0xcf/0x250
[   63.071529]  ? __wake_up_common+0x110/0x350
[   63.077794]  ? __schedule+0xdc0/0xdc0
[   63.083348]  ? wait_woken+0x130/0x130
[   63.088963]  ? finish_task_switch+0x1f1/0x520
[   63.095258]  ? kasan_unpoison_shadow+0x30/0x40
[   63.101792]  ? __init_waitqueue_head+0xa0/0xd0
[   63.108183]  ? replenish_dl_entity.cold.60+0x18/0x18
[   63.115151]  ? _raw_spin_lock_irqsave+0x25/0x50
[   63.121754]  ? max_active_store+0xf0/0xf0
[   63.127753]  kthread+0x1ae/0x1d0
[   63.132894]  ? kthread_bind+0x30/0x30
[   63.138422]  ret_from_fork+0x35/0x40

[   63.146973] Allocated by task 14:
[   63.152077]  kasan_kmalloc+0xbf/0xe0
[   63.157471]  __kmalloc+0x110/0x240
[   63.162804]  init_cntrs+0x34d/0xdf0 [hfi1]
[   63.168883]  hfi1_init_dd+0x29a3/0x2f90 [hfi1]
[   63.175244]  init_one+0x551/0xae0 [hfi1]
[   63.181065]  local_pci_probe+0x70/0xd0
[   63.186759]  work_for_cpu_fn+0x29/0x40
[   63.192310]  process_one_work+0x584/0x960
[   63.198163]  worker_thread+0x62e/0x9d0
[   63.203843]  kthread+0x1ae/0x1d0
[   63.208874]  ret_from_fork+0x35/0x40

[   63.217203] Freed by task 1:
[   63.221844]  __kasan_slab_free+0x12e/0x180
[   63.227844]  kfree+0x92/0x1a0
[   63.232570]  single_release+0x3a/0x60
[   63.238024]  __fput+0x1d9/0x480
[   63.242911]  task_work_run+0x139/0x190
[   63.248440]  exit_to_usermode_loop+0x191/0x1a0
[   63.254814]  do_syscall_64+0x301/0x330
[   63.260283]  entry_SYSCALL_64_after_hwframe+0x44/0xa9

[   63.270199] The buggy address belongs to the object at
ffff88080e8d5500
 which belongs to the cache kmalloc-4096 of size 4096
[   63.287247] The buggy address is located 3632 bytes inside of
 4096-byte region [ffff88080e8d5500, ffff88080e8d6500)
[   63.303564] The buggy address belongs to the page:
[   63.310447] page:ffffea00203a3400 count:1 mapcount:0
mapping:ffff88081380e840 index:0x0 compound_mapcount: 0
[   63.323102] flags: 0x2fffff80008100(slab|head)
[   63.329775] raw: 002fffff80008100 0000000000000000 0000000100000001
ffff88081380e840
[   63.340175] raw: 0000000000000000 0000000000070007 00000001ffffffff
0000000000000000
[   63.350564] page dumped because: kasan: bad access detected

[   63.361974] Memory state around the buggy address:
[   63.369137]  ffff88080e8d6200: 00 00 00 00 00 00 00 00 00 00 00 00 00
00 00 00
[   63.379082]  ffff88080e8d6280: 00 00 00 00 00 00 00 00 00 00 00 00 00
00 00 00
[   63.389032] >ffff88080e8d6300: 00 00 00 00 00 00 fc fc fc fc fc fc fc
fc fc fc
[   63.398944]                                      ^
[   63.406141]  ffff88080e8d6380: fc fc fc fc fc fc fc fc fc fc fc fc fc
fc fc fc
[   63.416109]  ffff88080e8d6400: fc fc fc fc fc fc fc fc fc fc fc fc fc
fc fc fc
[   63.426099]
==================================================================

The trace happens because get_hw_stats() assumes there is room in the
memory allocated in init_cntrs() to accommodate the driver counters.
Unfortunately, that routine only allocated space for the device
counters.

Fix by insuring the allocation has room for the additional driver
counters.

Cc: <Stable@vger.kernel.org> # v4.14+
Fixes: b7481944 ("IB/hfi1: Show statistics counters under IB stats interface")
Reviewed-by: NMike Marciniczyn <mike.marciniszyn@intel.com>
Reviewed-by: NMike Ruhl <michael.j.ruhl@intel.com>
Signed-off-by: NPiotr Stankiewicz <piotr.stankiewicz@intel.com>
Signed-off-by: NDennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>
      36d84219
  21. 17 10月, 2018 1 次提交
  23. 01 9月, 2018 6 次提交
  25. 22 6月, 2018 7 次提交
  27. 20 6月, 2018 3 次提交
  29. 05 6月, 2018 1 次提交
  31. 24 5月, 2018 3 次提交
  33. 10 5月, 2018 3 次提交
    • S
      IB/{hfi1, rdmavt, qib}: Implement CQ completion vector support · 5d18ee67
      由 Sebastian Sanchez 提交于 
      Currently the driver doesn't support completion vectors. These
are used to indicate which sets of CQs should be grouped together
into the same vector. A vector is a CQ processing thread that
runs on a specific CPU.

If an application has several CQs bound to different completion
vectors, and each completion vector runs on different CPUs, then
the completion queue workload is balanced. This helps scale as more
nodes are used.

Implement CQ completion vector support using a global workqueue
where a CQ entry is queued to the CPU corresponding to the CQ's
completion vector. Since the workqueue is global, it's guaranteed
to always be there when queueing CQ entries; Therefore, the RCU
locking for cq->rdi->worker in the hot path is superfluous.

Each completion vector is assigned to a different CPU. The number of
completion vectors available is computed by taking the number of
online, physical CPUs from the local NUMA node and subtracting the
CPUs used for kernel receive queues and the general interrupt.
Special use cases:

  * If there are no CPUs left for completion vectors, the same CPU
    for the general interrupt is used; Therefore, there would only
    be one completion vector available.

  * For multi-HFI systems, the number of completion vectors available
    for each device is the total number of completion vectors in
    the local NUMA node divided by the number of devices in the same
    NUMA node. If there's a division remainder, the first device to
    get initialized gets an extra completion vector.

Upon a CQ creation, an invalid completion vector could be specified.
Handle it as follows:

  * If the completion vector is less than 0, set it to 0.

  * Set the completion vector to the result of the passed completion
    vector moded with the number of device completion vectors
    available.
Reviewed-by: NMike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: NSebastian Sanchez <sebastian.sanchez@intel.com>
Signed-off-by: NDennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>
      5d18ee67
    • M
      IB/hfi1: Rework fault injection machinery · a74d5307
      由 Mitko Haralanov 提交于 
      The packet fault injection code present in the HFI1 driver had some
issues which not only fragment the code but also created user
confusion. Furthermore, it suffered from the following issues:

  1. The fault_packet method only worked for received packets. This
     meant that the only fault injection mode available for sent
     packets is fault_opcode, which did not allow for random packet
     drops on all egressing packets.
  2. The mask available for the fault_opcode mode did not really work
     due to the fact that the opcode values are not bits in a bitmask but
     rather sequential integer values. Creating a opcode/mask pair that
     would successfully capture a set of packets was nearly impossible.
  3. The code was fragmented and used too many debugfs entries to
     operate and control. This was confusing to users.
  4. It did not allow filtering fault injection on a per direction basis -
     egress vs. ingress.

In order to improve or fix the above issues, the following changes have
been made:

   1. The fault injection methods have been combined into a single fault
      injection facility. As such, the fault injection has been plugged
      into both the send and receive code paths. Regardless of method used
      the fault injection will operate on both egress and ingress packets.
   2. The type of fault injection - by packet or by opcode - is now controlled
      by changing the boolean value of the file "opcode_mode". When the value
      is set to True, fault injection is done by opcode. Otherwise, by
      packet.
   2. The masking ability has been removed in favor of a bitmap that holds
      opcodes of interest (one bit per opcode, a total of 256 bits). This
      works in tandem with the "opcode_mode" value. When the value of
      "opcode_mode" is False, this bitmap is ignored. When the value is
      True, the bitmap lists all opcodes to be considered for fault injection.
      By default, the bitmap is empty. When the user wants to filter by opcode,
      the user sets the corresponding bit in the bitmap by echo'ing the bit
      position into the 'opcodes' file. This gets around the issue that the set
      of opcodes does not lend itself to effective masks and allow for extremely
      fine-grained filtering by opcode.
   4. fault_packet and fault_opcode methods have been combined. Hence, there
      is only one debugfs directory controlling the entire operation of the
      fault injection machinery. This reduces the number of debugfs entries
      and provides a more unified user experience.
   5. A new control files - "direction" - is provided to allow the user to
      control the direction of packets, which are subject to fault injection.
   6. A new control file - "skip_usec" - is added that would allow the user
      to specify a "timeout" during which no fault injection will occur.

In addition, the following bug fixes have been applied:

   1. The fault injection code has been split into its own header and source
      files. This was done to better organize the code and support conditional
      compilation without littering the code with #ifdef's.
   2. The method by which the TX PIO packets were being marked for drop
      conflicted with the way send contexts were being setup. As a result,
      the send context was repeatedly being reset.
   3. The fault injection only makes sense when the user can control it
      through the debugfs entries. However, a kernel configuration can
      enable fault injection but keep fault injection debugfs entries
      disabled. Therefore, it makes sense that the HFI fault injection
      code depends on both.
   4. Error suppression did not take into account the method by which PIO
      packets were being dropped. Therefore, even with error suppression
      turned on, errors would still be displayed to the screen. A larger
      enough packet drop percentage would case the kernel to crash because
      the driver would be stuck printing errors.
Reviewed-by: NDennis Dalessandro <dennis.dalessandro@intel.com>
Reviewed-by: NDon Hiatt <don.hiatt@intel.com>
Reviewed-by: NMike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: NMitko Haralanov <mitko.haralanov@intel.com>
Signed-off-by: NDennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>
      a74d5307
    • A
      IB/{hfi1, qib}: Add handling of kernel restart · 8d3e7113
      由 Alex Estrin 提交于 
      A warm restart will fail to unload the driver, leaving link state
potentially flapping up to the point the BIOS resets the adapter.
Correct the issue by hooking the shutdown pci method,
which will bring port down.

Cc: <stable@vger.kernel.org> # 4.9.x
Reviewed-by: NMike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: NAlex Estrin <alex.estrin@intel.com>
Signed-off-by: NDennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>
      8d3e7113
  35. 04 5月, 2018 1 次提交
    • M
      IB/hfi1: Fix handling of FECN marked multicast packet · f59fb9e0
      由 Mike Marciniszyn 提交于 
      The code for handling a marked UD packet unconditionally returns the
dlid in the header of the FECN marked packet.  This is not correct
for multicast packets where the DLID is in the multicast range.

The subsequent attempt to send the CNP with the multicast lid will
cause the chip to halt the ack send context because the source
lid doesn't match the chip programming.   The send context will
be halted and flush any other pending packets in the pio ring causing
the CNP to not be sent.

A part of investigating the fix, it was determined that the 16B work
broke the FECN routine badly with inconsistent use of 16 bit and 32 bits
types for lids and pkeys.  Since the port's source lid was correctly 32
bits the type mixmatches need to be dealt with at the same time as
fixing the CNP header issue.

Fix these issues by:
- Using the ports lid for as the SLID for responding to FECN marked UD
  packets
- Insure pkey is always 16 bit in this and subordinate routines
- Insure lids are 32 bits in this and subordinate routines

Cc: <stable@vger.kernel.org> # 4.14.x
Fixes: 88733e3b ("IB/hfi1: Add 16B UD support")
Reviewed-by: NDon Hiatt <don.hiatt@intel.com>
Reviewed-by: NMichael J. Ruhl <michael.j.ruhl@intel.com>
Signed-off-by: NMike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: NDennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>
      f59fb9e0
  37. 14 3月, 2018 1 次提交
  39. 02 2月, 2018 1 次提交