Skip to content
This repository has been archived by the owner. It is now read-only.

T578: Enable CONFIG_BLK_DEV_THROTTLING #17

Merged
merged 1 commit into from Mar 18, 2018

Conversation

@higebu
Copy link
Member

@higebu higebu commented Mar 18, 2018

No description provided.

…dconfig
@c-po c-po merged commit 1230876 into vyos:linux-vyos-4.14.y Mar 18, 2018
c-po pushed a commit that referenced this pull request Aug 20, 2018
commit 67d2f87 upstream.

Commit dec2c92 ("Bluetooth: hci_ldisc:
Use rwlocking to avoid closing proto races") introduced locks in
hci_ldisc that are held while calling the proto functions. These locks
are rwlock's, and hence do not allow sleeping while they are held.
However, the proto functions that hci_bcm registers use mutexes and
hence need to be able to sleep.

In more detail: hci_uart_tty_receive() and hci_uart_dequeue() both
acquire the rwlock, after which they call proto->recv() and
proto->dequeue(), respectively. In the case of hci_bcm these point to
bcm_recv() and bcm_dequeue(). The latter both acquire the
bcm_device_lock, which is a mutex, so doing so results in a call to
might_sleep(). But since we're holding a rwlock in hci_ldisc, that
results in the following BUG (this for the dequeue case - a similar
one for the receive case is omitted for brevity):

  BUG: sleeping function called from invalid context at kernel/locking/mutex.c
  in_atomic(): 1, irqs_disabled(): 0, pid: 7303, name: kworker/7:3
  INFO: lockdep is turned off.
  CPU: 7 PID: 7303 Comm: kworker/7:3 Tainted: G        W  OE   4.13.2+ #17
  Hardware name: Apple Inc. MacBookPro13,3/Mac-A5C67F76ED83108C, BIOS MBP133.8
  Workqueue: events hci_uart_write_work [hci_uart]
  Call Trace:
   dump_stack+0x8e/0xd6
   ___might_sleep+0x164/0x250
   __might_sleep+0x4a/0x80
   __mutex_lock+0x59/0xa00
   ? lock_acquire+0xa3/0x1f0
   ? lock_acquire+0xa3/0x1f0
   ? hci_uart_write_work+0xd3/0x160 [hci_uart]
   mutex_lock_nested+0x1b/0x20
   ? mutex_lock_nested+0x1b/0x20
   bcm_dequeue+0x21/0xc0 [hci_uart]
   hci_uart_write_work+0xe6/0x160 [hci_uart]
   process_one_work+0x253/0x6a0
   worker_thread+0x4d/0x3b0
   kthread+0x133/0x150

We can't replace the mutex in hci_bcm, because there are other calls
there that might sleep. Therefore this replaces the rwlock's in
hci_ldisc with rw_semaphore's (which allow sleeping). This is a safer
approach anyway as it reduces the restrictions on the proto callbacks.
Also, because acquiring write-lock is very rare compared to acquiring
the read-lock, the percpu variant of rw_semaphore is used.

Lastly, because hci_uart_tx_wakeup() may be called from an IRQ context,
we can't block (sleep) while trying acquire the read lock there, so we
use the trylock variant.

Signed-off-by: Ronald Tschalär <ronald@innovation.ch>
Reviewed-by: Lukas Wunner <lukas@wunner.de>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Amit Pundir <amit.pundir@linaro.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
c-po pushed a commit that referenced this pull request Sep 19, 2018
commit a5ba1d9 upstream.

We have reports of the following crash:

    PID: 7 TASK: ffff88085c6d61c0 CPU: 1 COMMAND: "kworker/u25:0"
    #0 [ffff88085c6db710] machine_kexec at ffffffff81046239
    #1 [ffff88085c6db760] crash_kexec at ffffffff810fc248
    #2 [ffff88085c6db830] oops_end at ffffffff81008ae7
    #3 [ffff88085c6db860] no_context at ffffffff81050b8f
    #4 [ffff88085c6db8b0] __bad_area_nosemaphore at ffffffff81050d75
    #5 [ffff88085c6db900] bad_area_nosemaphore at ffffffff81050e83
    #6 [ffff88085c6db910] __do_page_fault at ffffffff8105132e
    #7 [ffff88085c6db9b0] do_page_fault at ffffffff8105152c
    #8 [ffff88085c6db9c0] page_fault at ffffffff81a3f122
    [exception RIP: uart_put_char+149]
    RIP: ffffffff814b67b5 RSP: ffff88085c6dba78 RFLAGS: 00010006
    RAX: 0000000000000292 RBX: ffffffff827c5120 RCX: 0000000000000081
    RDX: 0000000000000000 RSI: 000000000000005f RDI: ffffffff827c5120
    RBP: ffff88085c6dba98 R8: 000000000000012c R9: ffffffff822ea320
    R10: ffff88085fe4db04 R11: 0000000000000001 R12: ffff881059f9c000
    R13: 0000000000000001 R14: 000000000000005f R15: 0000000000000fba
    ORIG_RAX: ffffffffffffffff CS: 0010 SS: 0018
    #9 [ffff88085c6dbaa0] tty_put_char at ffffffff81497544
    #10 [ffff88085c6dbac0] do_output_char at ffffffff8149c91c
    #11 [ffff88085c6dbae0] __process_echoes at ffffffff8149cb8b
    #12 [ffff88085c6dbb30] commit_echoes at ffffffff8149cdc2
    #13 [ffff88085c6dbb60] n_tty_receive_buf_fast at ffffffff8149e49b
    #14 [ffff88085c6dbbc0] __receive_buf at ffffffff8149ef5a
    #15 [ffff88085c6dbc20] n_tty_receive_buf_common at ffffffff8149f016
    #16 [ffff88085c6dbca0] n_tty_receive_buf2 at ffffffff8149f194
    #17 [ffff88085c6dbcb0] flush_to_ldisc at ffffffff814a238a
    #18 [ffff88085c6dbd50] process_one_work at ffffffff81090be2
    #19 [ffff88085c6dbe20] worker_thread at ffffffff81091b4d
    #20 [ffff88085c6dbeb0] kthread at ffffffff81096384
    #21 [ffff88085c6dbf50] ret_from_fork at ffffffff81a3d69f​

after slogging through some dissasembly:

ffffffff814b6720 <uart_put_char>:
ffffffff814b6720:	55                   	push   %rbp
ffffffff814b6721:	48 89 e5             	mov    %rsp,%rbp
ffffffff814b6724:	48 83 ec 20          	sub    $0x20,%rsp
ffffffff814b6728:	48 89 1c 24          	mov    %rbx,(%rsp)
ffffffff814b672c:	4c 89 64 24 08       	mov    %r12,0x8(%rsp)
ffffffff814b6731:	4c 89 6c 24 10       	mov    %r13,0x10(%rsp)
ffffffff814b6736:	4c 89 74 24 18       	mov    %r14,0x18(%rsp)
ffffffff814b673b:	e8 b0 8e 58 00       	callq  ffffffff81a3f5f0 <mcount>
ffffffff814b6740:	4c 8b a7 88 02 00 00 	mov    0x288(%rdi),%r12
ffffffff814b6747:	45 31 ed             	xor    %r13d,%r13d
ffffffff814b674a:	41 89 f6             	mov    %esi,%r14d
ffffffff814b674d:	49 83 bc 24 70 01 00 	cmpq   $0x0,0x170(%r12)
ffffffff814b6754:	00 00
ffffffff814b6756:	49 8b 9c 24 80 01 00 	mov    0x180(%r12),%rbx
ffffffff814b675d:	00
ffffffff814b675e:	74 2f                	je     ffffffff814b678f <uart_put_char+0x6f>
ffffffff814b6760:	48 89 df             	mov    %rbx,%rdi
ffffffff814b6763:	e8 a8 67 58 00       	callq  ffffffff81a3cf10 <_raw_spin_lock_irqsave>
ffffffff814b6768:	41 8b 8c 24 78 01 00 	mov    0x178(%r12),%ecx
ffffffff814b676f:	00
ffffffff814b6770:	89 ca                	mov    %ecx,%edx
ffffffff814b6772:	f7 d2                	not    %edx
ffffffff814b6774:	41 03 94 24 7c 01 00 	add    0x17c(%r12),%edx
ffffffff814b677b:	00
ffffffff814b677c:	81 e2 ff 0f 00 00    	and    $0xfff,%edx
ffffffff814b6782:	75 23                	jne    ffffffff814b67a7 <uart_put_char+0x87>
ffffffff814b6784:	48 89 c6             	mov    %rax,%rsi
ffffffff814b6787:	48 89 df             	mov    %rbx,%rdi
ffffffff814b678a:	e8 e1 64 58 00       	callq  ffffffff81a3cc70 <_raw_spin_unlock_irqrestore>
ffffffff814b678f:	44 89 e8             	mov    %r13d,%eax
ffffffff814b6792:	48 8b 1c 24          	mov    (%rsp),%rbx
ffffffff814b6796:	4c 8b 64 24 08       	mov    0x8(%rsp),%r12
ffffffff814b679b:	4c 8b 6c 24 10       	mov    0x10(%rsp),%r13
ffffffff814b67a0:	4c 8b 74 24 18       	mov    0x18(%rsp),%r14
ffffffff814b67a5:	c9                   	leaveq
ffffffff814b67a6:	c3                   	retq
ffffffff814b67a7:	49 8b 94 24 70 01 00 	mov    0x170(%r12),%rdx
ffffffff814b67ae:	00
ffffffff814b67af:	48 63 c9             	movslq %ecx,%rcx
ffffffff814b67b2:	41 b5 01             	mov    $0x1,%r13b
ffffffff814b67b5:	44 88 34 0a          	mov    %r14b,(%rdx,%rcx,1)
ffffffff814b67b9:	41 8b 94 24 78 01 00 	mov    0x178(%r12),%edx
ffffffff814b67c0:	00
ffffffff814b67c1:	83 c2 01             	add    $0x1,%edx
ffffffff814b67c4:	81 e2 ff 0f 00 00    	and    $0xfff,%edx
ffffffff814b67ca:	41 89 94 24 78 01 00 	mov    %edx,0x178(%r12)
ffffffff814b67d1:	00
ffffffff814b67d2:	eb b0                	jmp    ffffffff814b6784 <uart_put_char+0x64>
ffffffff814b67d4:	66 66 66 2e 0f 1f 84 	data32 data32 nopw %cs:0x0(%rax,%rax,1)
ffffffff814b67db:	00 00 00 00 00

for our build, this is crashing at:

    circ->buf[circ->head] = c;

Looking in uart_port_startup(), it seems that circ->buf (state->xmit.buf)
protected by the "per-port mutex", which based on uart_port_check() is
state->port.mutex. Indeed, the lock acquired in uart_put_char() is
uport->lock, i.e. not the same lock.

Anyway, since the lock is not acquired, if uart_shutdown() is called, the
last chunk of that function may release state->xmit.buf before its assigned
to null, and cause the race above.

To fix it, let's lock uport->lock when allocating/deallocating
state->xmit.buf in addition to the per-port mutex.

v2: switch to locking uport->lock on allocation/deallocation instead of
    locking the per-port mutex in uart_put_char. Note that since
    uport->lock is a spin lock, we have to switch the allocation to
    GFP_ATOMIC.
v3: move the allocation outside the lock, so we can switch back to
    GFP_KERNEL

Signed-off-by: Tycho Andersen <tycho@tycho.ws>
Cc: stable <stable@vger.kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
c-po pushed a commit that referenced this pull request Sep 19, 2018
[ Upstream commit 21b172e ]

Fix the warning below by calling rhashtable_lookup_fast.
Also, make some code movements for better quality and human
readability.

[  342.450870] WARNING: suspicious RCU usage
[  342.455856] 4.18.0-rc2+ #17 Tainted: G           O
[  342.462210] -----------------------------
[  342.467202] ./include/linux/rhashtable.h:481 suspicious rcu_dereference_check() usage!
[  342.476568]
[  342.476568] other info that might help us debug this:
[  342.476568]
[  342.486978]
[  342.486978] rcu_scheduler_active = 2, debug_locks = 1
[  342.495211] 4 locks held by modprobe/3934:
[  342.500265]  #0: 00000000e23116b2 (mlx5_intf_mutex){+.+.}, at:
mlx5_unregister_interface+0x18/0x90 [mlx5_core]
[  342.511953]  #1: 00000000ca16db96 (rtnl_mutex){+.+.}, at: unregister_netdev+0xe/0x20
[  342.521109]  #2: 00000000a46e2c4b (&priv->state_lock){+.+.}, at: mlx5e_close+0x29/0x60
[mlx5_core]
[  342.531642]  #3: 0000000060c5bde3 (mem_id_lock){+.+.}, at: xdp_rxq_info_unreg+0x93/0x6b0
[  342.541206]
[  342.541206] stack backtrace:
[  342.547075] CPU: 12 PID: 3934 Comm: modprobe Tainted: G           O      4.18.0-rc2+ #17
[  342.556621] Hardware name: Dell Inc. PowerEdge R730/0H21J3, BIOS 1.5.4 10/002/2015
[  342.565606] Call Trace:
[  342.568861]  dump_stack+0x78/0xb3
[  342.573086]  xdp_rxq_info_unreg+0x3f5/0x6b0
[  342.578285]  ? __call_rcu+0x220/0x300
[  342.582911]  mlx5e_free_rq+0x38/0xc0 [mlx5_core]
[  342.588602]  mlx5e_close_channel+0x20/0x120 [mlx5_core]
[  342.594976]  mlx5e_close_channels+0x26/0x40 [mlx5_core]
[  342.601345]  mlx5e_close_locked+0x44/0x50 [mlx5_core]
[  342.607519]  mlx5e_close+0x42/0x60 [mlx5_core]
[  342.613005]  __dev_close_many+0xb1/0x120
[  342.617911]  dev_close_many+0xa2/0x170
[  342.622622]  rollback_registered_many+0x148/0x460
[  342.628401]  ? __lock_acquire+0x48d/0x11b0
[  342.633498]  ? unregister_netdev+0xe/0x20
[  342.638495]  rollback_registered+0x56/0x90
[  342.643588]  unregister_netdevice_queue+0x7e/0x100
[  342.649461]  unregister_netdev+0x18/0x20
[  342.654362]  mlx5e_remove+0x2a/0x50 [mlx5_core]
[  342.659944]  mlx5_remove_device+0xe5/0x110 [mlx5_core]
[  342.666208]  mlx5_unregister_interface+0x39/0x90 [mlx5_core]
[  342.673038]  cleanup+0x5/0xbfc [mlx5_core]
[  342.678094]  __x64_sys_delete_module+0x16b/0x240
[  342.683725]  ? do_syscall_64+0x1c/0x210
[  342.688476]  do_syscall_64+0x5a/0x210
[  342.693025]  entry_SYSCALL_64_after_hwframe+0x49/0xbe

Fixes: 8d5d885 ("xdp: rhashtable with allocator ID to pointer mapping")
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Suggested-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Jesper Dangaard Brouer <brouer@redhat.com>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Sasha Levin <alexander.levin@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
c-po pushed a commit that referenced this pull request Oct 1, 2018
[ Upstream commit 34043d2 ]

Matteo reported the following splat, testing the datapath of TC 'sample':

 BUG: KASAN: null-ptr-deref in tcf_sample_act+0xc4/0x310
 Read of size 8 at addr 0000000000000000 by task nc/433

 CPU: 0 PID: 433 Comm: nc Not tainted 4.19.0-rc3-kvm #17
 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS ?-20180531_142017-buildhw-08.phx2.fedoraproject.org-1.fc28 04/01/2014
 Call Trace:
  kasan_report.cold.6+0x6c/0x2fa
  tcf_sample_act+0xc4/0x310
  ? dev_hard_start_xmit+0x117/0x180
  tcf_action_exec+0xa3/0x160
  tcf_classify+0xdd/0x1d0
  htb_enqueue+0x18e/0x6b0
  ? deref_stack_reg+0x7a/0xb0
  ? htb_delete+0x4b0/0x4b0
  ? unwind_next_frame+0x819/0x8f0
  ? entry_SYSCALL_64_after_hwframe+0x44/0xa9
  __dev_queue_xmit+0x722/0xca0
  ? unwind_get_return_address_ptr+0x50/0x50
  ? netdev_pick_tx+0xe0/0xe0
  ? save_stack+0x8c/0xb0
  ? kasan_kmalloc+0xbe/0xd0
  ? __kmalloc_track_caller+0xe4/0x1c0
  ? __kmalloc_reserve.isra.45+0x24/0x70
  ? __alloc_skb+0xdd/0x2e0
  ? sk_stream_alloc_skb+0x91/0x3b0
  ? tcp_sendmsg_locked+0x71b/0x15a0
  ? tcp_sendmsg+0x22/0x40
  ? __sys_sendto+0x1b0/0x250
  ? __x64_sys_sendto+0x6f/0x80
  ? do_syscall_64+0x5d/0x150
  ? entry_SYSCALL_64_after_hwframe+0x44/0xa9
  ? __sys_sendto+0x1b0/0x250
  ? __x64_sys_sendto+0x6f/0x80
  ? do_syscall_64+0x5d/0x150
  ? entry_SYSCALL_64_after_hwframe+0x44/0xa9
  ip_finish_output2+0x495/0x590
  ? ip_copy_metadata+0x2e0/0x2e0
  ? skb_gso_validate_network_len+0x6f/0x110
  ? ip_finish_output+0x174/0x280
  __tcp_transmit_skb+0xb17/0x12b0
  ? __tcp_select_window+0x380/0x380
  tcp_write_xmit+0x913/0x1de0
  ? __sk_mem_schedule+0x50/0x80
  tcp_sendmsg_locked+0x49d/0x15a0
  ? tcp_rcv_established+0x8da/0xa30
  ? tcp_set_state+0x220/0x220
  ? clear_user+0x1f/0x50
  ? iov_iter_zero+0x1ae/0x590
  ? __fget_light+0xa0/0xe0
  tcp_sendmsg+0x22/0x40
  __sys_sendto+0x1b0/0x250
  ? __ia32_sys_getpeername+0x40/0x40
  ? _copy_to_user+0x58/0x70
  ? poll_select_copy_remaining+0x176/0x200
  ? __pollwait+0x1c0/0x1c0
  ? ktime_get_ts64+0x11f/0x140
  ? kern_select+0x108/0x150
  ? core_sys_select+0x360/0x360
  ? vfs_read+0x127/0x150
  ? kernel_write+0x90/0x90
  __x64_sys_sendto+0x6f/0x80
  do_syscall_64+0x5d/0x150
  entry_SYSCALL_64_after_hwframe+0x44/0xa9
 RIP: 0033:0x7fefef2b129d
 Code: ff ff ff ff eb b6 0f 1f 80 00 00 00 00 48 8d 05 51 37 0c 00 41 89 ca 8b 00 85 c0 75 20 45 31 c9 45 31 c0 b8 2c 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 6b f3 c3 66 0f 1f 84 00 00 00 00 00 41 56 41
 RSP: 002b:00007fff2f5350c8 EFLAGS: 00000246 ORIG_RAX: 000000000000002c
 RAX: ffffffffffffffda RBX: 000056118d60c120 RCX: 00007fefef2b129d
 RDX: 0000000000002000 RSI: 000056118d629320 RDI: 0000000000000003
 RBP: 000056118d530370 R08: 0000000000000000 R09: 0000000000000000
 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000002000
 R13: 000056118d5c2a10 R14: 000056118d5c2a10 R15: 000056118d5303b8

tcf_sample_act() tried to update its per-cpu stats, but tcf_sample_init()
forgot to allocate them, because tcf_idr_create() was called with a wrong
value of 'cpustats'. Setting it to true proved to fix the reported crash.

Reported-by: Matteo Croce <mcroce@redhat.com>
Fixes: 65a206c ("net/sched: Change act_api and act_xxx modules to use IDR")
Fixes: 5c5670f ("net/sched: Introduce sample tc action")
Tested-by: Matteo Croce <mcroce@redhat.com>
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
c-po pushed a commit that referenced this pull request Oct 12, 2018
commit a5ba1d9 upstream.

We have reports of the following crash:

    PID: 7 TASK: ffff88085c6d61c0 CPU: 1 COMMAND: "kworker/u25:0"
    #0 [ffff88085c6db710] machine_kexec at ffffffff81046239
    #1 [ffff88085c6db760] crash_kexec at ffffffff810fc248
    #2 [ffff88085c6db830] oops_end at ffffffff81008ae7
    #3 [ffff88085c6db860] no_context at ffffffff81050b8f
    #4 [ffff88085c6db8b0] __bad_area_nosemaphore at ffffffff81050d75
    #5 [ffff88085c6db900] bad_area_nosemaphore at ffffffff81050e83
    #6 [ffff88085c6db910] __do_page_fault at ffffffff8105132e
    #7 [ffff88085c6db9b0] do_page_fault at ffffffff8105152c
    #8 [ffff88085c6db9c0] page_fault at ffffffff81a3f122
    [exception RIP: uart_put_char+149]
    RIP: ffffffff814b67b5 RSP: ffff88085c6dba78 RFLAGS: 00010006
    RAX: 0000000000000292 RBX: ffffffff827c5120 RCX: 0000000000000081
    RDX: 0000000000000000 RSI: 000000000000005f RDI: ffffffff827c5120
    RBP: ffff88085c6dba98 R8: 000000000000012c R9: ffffffff822ea320
    R10: ffff88085fe4db04 R11: 0000000000000001 R12: ffff881059f9c000
    R13: 0000000000000001 R14: 000000000000005f R15: 0000000000000fba
    ORIG_RAX: ffffffffffffffff CS: 0010 SS: 0018
    #9 [ffff88085c6dbaa0] tty_put_char at ffffffff81497544
    #10 [ffff88085c6dbac0] do_output_char at ffffffff8149c91c
    #11 [ffff88085c6dbae0] __process_echoes at ffffffff8149cb8b
    #12 [ffff88085c6dbb30] commit_echoes at ffffffff8149cdc2
    #13 [ffff88085c6dbb60] n_tty_receive_buf_fast at ffffffff8149e49b
    #14 [ffff88085c6dbbc0] __receive_buf at ffffffff8149ef5a
    #15 [ffff88085c6dbc20] n_tty_receive_buf_common at ffffffff8149f016
    #16 [ffff88085c6dbca0] n_tty_receive_buf2 at ffffffff8149f194
    #17 [ffff88085c6dbcb0] flush_to_ldisc at ffffffff814a238a
    #18 [ffff88085c6dbd50] process_one_work at ffffffff81090be2
    #19 [ffff88085c6dbe20] worker_thread at ffffffff81091b4d
    #20 [ffff88085c6dbeb0] kthread at ffffffff81096384
    #21 [ffff88085c6dbf50] ret_from_fork at ffffffff81a3d69f​

after slogging through some dissasembly:

ffffffff814b6720 <uart_put_char>:
ffffffff814b6720:	55                   	push   %rbp
ffffffff814b6721:	48 89 e5             	mov    %rsp,%rbp
ffffffff814b6724:	48 83 ec 20          	sub    $0x20,%rsp
ffffffff814b6728:	48 89 1c 24          	mov    %rbx,(%rsp)
ffffffff814b672c:	4c 89 64 24 08       	mov    %r12,0x8(%rsp)
ffffffff814b6731:	4c 89 6c 24 10       	mov    %r13,0x10(%rsp)
ffffffff814b6736:	4c 89 74 24 18       	mov    %r14,0x18(%rsp)
ffffffff814b673b:	e8 b0 8e 58 00       	callq  ffffffff81a3f5f0 <mcount>
ffffffff814b6740:	4c 8b a7 88 02 00 00 	mov    0x288(%rdi),%r12
ffffffff814b6747:	45 31 ed             	xor    %r13d,%r13d
ffffffff814b674a:	41 89 f6             	mov    %esi,%r14d
ffffffff814b674d:	49 83 bc 24 70 01 00 	cmpq   $0x0,0x170(%r12)
ffffffff814b6754:	00 00
ffffffff814b6756:	49 8b 9c 24 80 01 00 	mov    0x180(%r12),%rbx
ffffffff814b675d:	00
ffffffff814b675e:	74 2f                	je     ffffffff814b678f <uart_put_char+0x6f>
ffffffff814b6760:	48 89 df             	mov    %rbx,%rdi
ffffffff814b6763:	e8 a8 67 58 00       	callq  ffffffff81a3cf10 <_raw_spin_lock_irqsave>
ffffffff814b6768:	41 8b 8c 24 78 01 00 	mov    0x178(%r12),%ecx
ffffffff814b676f:	00
ffffffff814b6770:	89 ca                	mov    %ecx,%edx
ffffffff814b6772:	f7 d2                	not    %edx
ffffffff814b6774:	41 03 94 24 7c 01 00 	add    0x17c(%r12),%edx
ffffffff814b677b:	00
ffffffff814b677c:	81 e2 ff 0f 00 00    	and    $0xfff,%edx
ffffffff814b6782:	75 23                	jne    ffffffff814b67a7 <uart_put_char+0x87>
ffffffff814b6784:	48 89 c6             	mov    %rax,%rsi
ffffffff814b6787:	48 89 df             	mov    %rbx,%rdi
ffffffff814b678a:	e8 e1 64 58 00       	callq  ffffffff81a3cc70 <_raw_spin_unlock_irqrestore>
ffffffff814b678f:	44 89 e8             	mov    %r13d,%eax
ffffffff814b6792:	48 8b 1c 24          	mov    (%rsp),%rbx
ffffffff814b6796:	4c 8b 64 24 08       	mov    0x8(%rsp),%r12
ffffffff814b679b:	4c 8b 6c 24 10       	mov    0x10(%rsp),%r13
ffffffff814b67a0:	4c 8b 74 24 18       	mov    0x18(%rsp),%r14
ffffffff814b67a5:	c9                   	leaveq
ffffffff814b67a6:	c3                   	retq
ffffffff814b67a7:	49 8b 94 24 70 01 00 	mov    0x170(%r12),%rdx
ffffffff814b67ae:	00
ffffffff814b67af:	48 63 c9             	movslq %ecx,%rcx
ffffffff814b67b2:	41 b5 01             	mov    $0x1,%r13b
ffffffff814b67b5:	44 88 34 0a          	mov    %r14b,(%rdx,%rcx,1)
ffffffff814b67b9:	41 8b 94 24 78 01 00 	mov    0x178(%r12),%edx
ffffffff814b67c0:	00
ffffffff814b67c1:	83 c2 01             	add    $0x1,%edx
ffffffff814b67c4:	81 e2 ff 0f 00 00    	and    $0xfff,%edx
ffffffff814b67ca:	41 89 94 24 78 01 00 	mov    %edx,0x178(%r12)
ffffffff814b67d1:	00
ffffffff814b67d2:	eb b0                	jmp    ffffffff814b6784 <uart_put_char+0x64>
ffffffff814b67d4:	66 66 66 2e 0f 1f 84 	data32 data32 nopw %cs:0x0(%rax,%rax,1)
ffffffff814b67db:	00 00 00 00 00

for our build, this is crashing at:

    circ->buf[circ->head] = c;

Looking in uart_port_startup(), it seems that circ->buf (state->xmit.buf)
protected by the "per-port mutex", which based on uart_port_check() is
state->port.mutex. Indeed, the lock acquired in uart_put_char() is
uport->lock, i.e. not the same lock.

Anyway, since the lock is not acquired, if uart_shutdown() is called, the
last chunk of that function may release state->xmit.buf before its assigned
to null, and cause the race above.

To fix it, let's lock uport->lock when allocating/deallocating
state->xmit.buf in addition to the per-port mutex.

v2: switch to locking uport->lock on allocation/deallocation instead of
    locking the per-port mutex in uart_put_char. Note that since
    uport->lock is a spin lock, we have to switch the allocation to
    GFP_ATOMIC.
v3: move the allocation outside the lock, so we can switch back to
    GFP_KERNEL

Signed-off-by: Tycho Andersen <tycho@tycho.ws>
Cc: stable <stable@vger.kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
c-po pushed a commit that referenced this pull request Oct 12, 2018
[ Upstream commit 34043d2 ]

Matteo reported the following splat, testing the datapath of TC 'sample':

 BUG: KASAN: null-ptr-deref in tcf_sample_act+0xc4/0x310
 Read of size 8 at addr 0000000000000000 by task nc/433

 CPU: 0 PID: 433 Comm: nc Not tainted 4.19.0-rc3-kvm #17
 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS ?-20180531_142017-buildhw-08.phx2.fedoraproject.org-1.fc28 04/01/2014
 Call Trace:
  kasan_report.cold.6+0x6c/0x2fa
  tcf_sample_act+0xc4/0x310
  ? dev_hard_start_xmit+0x117/0x180
  tcf_action_exec+0xa3/0x160
  tcf_classify+0xdd/0x1d0
  htb_enqueue+0x18e/0x6b0
  ? deref_stack_reg+0x7a/0xb0
  ? htb_delete+0x4b0/0x4b0
  ? unwind_next_frame+0x819/0x8f0
  ? entry_SYSCALL_64_after_hwframe+0x44/0xa9
  __dev_queue_xmit+0x722/0xca0
  ? unwind_get_return_address_ptr+0x50/0x50
  ? netdev_pick_tx+0xe0/0xe0
  ? save_stack+0x8c/0xb0
  ? kasan_kmalloc+0xbe/0xd0
  ? __kmalloc_track_caller+0xe4/0x1c0
  ? __kmalloc_reserve.isra.45+0x24/0x70
  ? __alloc_skb+0xdd/0x2e0
  ? sk_stream_alloc_skb+0x91/0x3b0
  ? tcp_sendmsg_locked+0x71b/0x15a0
  ? tcp_sendmsg+0x22/0x40
  ? __sys_sendto+0x1b0/0x250
  ? __x64_sys_sendto+0x6f/0x80
  ? do_syscall_64+0x5d/0x150
  ? entry_SYSCALL_64_after_hwframe+0x44/0xa9
  ? __sys_sendto+0x1b0/0x250
  ? __x64_sys_sendto+0x6f/0x80
  ? do_syscall_64+0x5d/0x150
  ? entry_SYSCALL_64_after_hwframe+0x44/0xa9
  ip_finish_output2+0x495/0x590
  ? ip_copy_metadata+0x2e0/0x2e0
  ? skb_gso_validate_network_len+0x6f/0x110
  ? ip_finish_output+0x174/0x280
  __tcp_transmit_skb+0xb17/0x12b0
  ? __tcp_select_window+0x380/0x380
  tcp_write_xmit+0x913/0x1de0
  ? __sk_mem_schedule+0x50/0x80
  tcp_sendmsg_locked+0x49d/0x15a0
  ? tcp_rcv_established+0x8da/0xa30
  ? tcp_set_state+0x220/0x220
  ? clear_user+0x1f/0x50
  ? iov_iter_zero+0x1ae/0x590
  ? __fget_light+0xa0/0xe0
  tcp_sendmsg+0x22/0x40
  __sys_sendto+0x1b0/0x250
  ? __ia32_sys_getpeername+0x40/0x40
  ? _copy_to_user+0x58/0x70
  ? poll_select_copy_remaining+0x176/0x200
  ? __pollwait+0x1c0/0x1c0
  ? ktime_get_ts64+0x11f/0x140
  ? kern_select+0x108/0x150
  ? core_sys_select+0x360/0x360
  ? vfs_read+0x127/0x150
  ? kernel_write+0x90/0x90
  __x64_sys_sendto+0x6f/0x80
  do_syscall_64+0x5d/0x150
  entry_SYSCALL_64_after_hwframe+0x44/0xa9
 RIP: 0033:0x7fefef2b129d
 Code: ff ff ff ff eb b6 0f 1f 80 00 00 00 00 48 8d 05 51 37 0c 00 41 89 ca 8b 00 85 c0 75 20 45 31 c9 45 31 c0 b8 2c 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 6b f3 c3 66 0f 1f 84 00 00 00 00 00 41 56 41
 RSP: 002b:00007fff2f5350c8 EFLAGS: 00000246 ORIG_RAX: 000000000000002c
 RAX: ffffffffffffffda RBX: 000056118d60c120 RCX: 00007fefef2b129d
 RDX: 0000000000002000 RSI: 000056118d629320 RDI: 0000000000000003
 RBP: 000056118d530370 R08: 0000000000000000 R09: 0000000000000000
 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000002000
 R13: 000056118d5c2a10 R14: 000056118d5c2a10 R15: 000056118d5303b8

tcf_sample_act() tried to update its per-cpu stats, but tcf_sample_init()
forgot to allocate them, because tcf_idr_create() was called with a wrong
value of 'cpustats'. Setting it to true proved to fix the reported crash.

Reported-by: Matteo Croce <mcroce@redhat.com>
Fixes: 65a206c ("net/sched: Change act_api and act_xxx modules to use IDR")
Fixes: 5c5670f ("net/sched: Introduce sample tc action")
Tested-by: Matteo Croce <mcroce@redhat.com>
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
c-po pushed a commit that referenced this pull request Jun 18, 2019
[ Upstream commit 4d8e3e951a856777720272ce27f2c738a3eeef8c ]

During early system resume on Exynos5422 with performance counters enabled
the following kernel oops happens:

    Internal error: Oops - undefined instruction: 0 [#1] PREEMPT SMP ARM
    Modules linked in:
    CPU: 0 PID: 1433 Comm: bash Tainted: G        W         5.0.0-rc5-next-20190208-00023-gd5fb5a8a13e6-dirty #5480
    Hardware name: SAMSUNG EXYNOS (Flattened Device Tree)
    ...
    Flags: nZCv  IRQs off  FIQs off  Mode SVC_32  ISA ARM  Segment none
    Control: 10c5387d  Table: 4451006a  DAC: 00000051
    Process bash (pid: 1433, stack limit = 0xb7e0e22f)
    ...
    (reset_ctrl_regs) from [<c0112ad0>] (dbg_cpu_pm_notify+0x1c/0x24)
    (dbg_cpu_pm_notify) from [<c014c840>] (notifier_call_chain+0x44/0x84)
    (notifier_call_chain) from [<c014cbc0>] (__atomic_notifier_call_chain+0x7c/0x128)
    (__atomic_notifier_call_chain) from [<c01ffaac>] (cpu_pm_notify+0x30/0x54)
    (cpu_pm_notify) from [<c055116c>] (syscore_resume+0x98/0x3f4)
    (syscore_resume) from [<c0189350>] (suspend_devices_and_enter+0x97c/0xe74)
    (suspend_devices_and_enter) from [<c0189fb8>] (pm_suspend+0x770/0xc04)
    (pm_suspend) from [<c0187740>] (state_store+0x6c/0xcc)
    (state_store) from [<c09fa698>] (kobj_attr_store+0x14/0x20)
    (kobj_attr_store) from [<c030159c>] (sysfs_kf_write+0x4c/0x50)
    (sysfs_kf_write) from [<c0300620>] (kernfs_fop_write+0xfc/0x1e0)
    (kernfs_fop_write) from [<c0282be8>] (__vfs_write+0x2c/0x160)
    (__vfs_write) from [<c0282ea4>] (vfs_write+0xa4/0x16c)
    (vfs_write) from [<c0283080>] (ksys_write+0x40/0x8c)
    (ksys_write) from [<c0101000>] (ret_fast_syscall+0x0/0x28)

Undefined instruction is triggered during CP14 reset, because bits: #16
(Secure privileged invasive debug disabled) and #17 (Secure privileged
noninvasive debug disable) are set in DSCR. Those bits depend on SPNIDEN
and SPIDEN lines, which are provided by Secure JTAG hardware block. That
block in turn is powered from cluster 0 (big/Eagle), but the Exynos5422
boots on cluster 1 (LITTLE/KFC).

To fix this issue it is enough to turn on the power on the cluster 0 for
a while. This lets the Secure JTAG block to propagate the needed signals
to LITTLE/KFC cores and change their DSCR.

Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
c-po pushed a commit that referenced this pull request Aug 17, 2019
[ Upstream commit 04e03d9a616c19a47178eaca835358610e63a1dd ]

The mapper may be NULL when called from register_ftrace_function_probe()
with probe->data == NULL.

This issue can be reproduced as follow (it may be covered by compiler
optimization sometime):

/ # cat /sys/kernel/debug/tracing/set_ftrace_filter
#### all functions enabled ####
/ # echo foo_bar:dump > /sys/kernel/debug/tracing/set_ftrace_filter
[  206.949100] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000
[  206.952402] Mem abort info:
[  206.952819]   ESR = 0x96000006
[  206.955326]   Exception class = DABT (current EL), IL = 32 bits
[  206.955844]   SET = 0, FnV = 0
[  206.956272]   EA = 0, S1PTW = 0
[  206.956652] Data abort info:
[  206.957320]   ISV = 0, ISS = 0x00000006
[  206.959271]   CM = 0, WnR = 0
[  206.959938] user pgtable: 4k pages, 48-bit VAs, pgdp=0000000419f3a000
[  206.960483] [0000000000000000] pgd=0000000411a87003, pud=0000000411a83003, pmd=0000000000000000
[  206.964953] Internal error: Oops: 96000006 [#1] SMP
[  206.971122] Dumping ftrace buffer:
[  206.973677]    (ftrace buffer empty)
[  206.975258] Modules linked in:
[  206.976631] Process sh (pid: 281, stack limit = 0x(____ptrval____))
[  206.978449] CPU: 10 PID: 281 Comm: sh Not tainted 5.2.0-rc1+ #17
[  206.978955] Hardware name: linux,dummy-virt (DT)
[  206.979883] pstate: 60000005 (nZCv daif -PAN -UAO)
[  206.980499] pc : free_ftrace_func_mapper+0x2c/0x118
[  206.980874] lr : ftrace_count_free+0x68/0x80
[  206.982539] sp : ffff0000182f3ab0
[  206.983102] x29: ffff0000182f3ab0 x28: ffff8003d0ec1700
[  206.983632] x27: ffff000013054b40 x26: 0000000000000001
[  206.984000] x25: ffff00001385f000 x24: 0000000000000000
[  206.984394] x23: ffff000013453000 x22: ffff000013054000
[  206.984775] x21: 0000000000000000 x20: ffff00001385fe28
[  206.986575] x19: ffff000013872c30 x18: 0000000000000000
[  206.987111] x17: 0000000000000000 x16: 0000000000000000
[  206.987491] x15: ffffffffffffffb0 x14: 0000000000000000
[  206.987850] x13: 000000000017430e x12: 0000000000000580
[  206.988251] x11: 0000000000000000 x10: cccccccccccccccc
[  206.988740] x9 : 0000000000000000 x8 : ffff000013917550
[  206.990198] x7 : ffff000012fac2e8 x6 : ffff000012fac000
[  206.991008] x5 : ffff0000103da588 x4 : 0000000000000001
[  206.991395] x3 : 0000000000000001 x2 : ffff000013872a28
[  206.991771] x1 : 0000000000000000 x0 : 0000000000000000
[  206.992557] Call trace:
[  206.993101]  free_ftrace_func_mapper+0x2c/0x118
[  206.994827]  ftrace_count_free+0x68/0x80
[  206.995238]  release_probe+0xfc/0x1d0
[  206.995555]  register_ftrace_function_probe+0x4a8/0x868
[  206.995923]  ftrace_trace_probe_callback.isra.4+0xb8/0x180
[  206.996330]  ftrace_dump_callback+0x50/0x70
[  206.996663]  ftrace_regex_write.isra.29+0x290/0x3a8
[  206.997157]  ftrace_filter_write+0x44/0x60
[  206.998971]  __vfs_write+0x64/0xf0
[  206.999285]  vfs_write+0x14c/0x2f0
[  206.999591]  ksys_write+0xbc/0x1b0
[  206.999888]  __arm64_sys_write+0x3c/0x58
[  207.000246]  el0_svc_common.constprop.0+0x408/0x5f0
[  207.000607]  el0_svc_handler+0x144/0x1c8
[  207.000916]  el0_svc+0x8/0xc
[  207.003699] Code: aa0003f8 a9025bf5 aa0103f5 f946ea80 (f9400303)
[  207.008388] ---[ end trace 7b6d11b5f542bdf1 ]---
[  207.010126] Kernel panic - not syncing: Fatal exception
[  207.011322] SMP: stopping secondary CPUs
[  207.013956] Dumping ftrace buffer:
[  207.014595]    (ftrace buffer empty)
[  207.015632] Kernel Offset: disabled
[  207.017187] CPU features: 0x002,20006008
[  207.017985] Memory Limit: none
[  207.019825] ---[ end Kernel panic - not syncing: Fatal exception ]---

Link: http://lkml.kernel.org/r/20190606031754.10798-1-liwei391@huawei.com

Signed-off-by: Wei Li <liwei391@huawei.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
c-po pushed a commit that referenced this pull request Aug 17, 2019
commit d0a255e795ab976481565f6ac178314b34fbf891 upstream.

A deadlock with this stacktrace was observed.

The loop thread does a GFP_KERNEL allocation, it calls into dm-bufio
shrinker and the shrinker depends on I/O completion in the dm-bufio
subsystem.

In order to fix the deadlock (and other similar ones), we set the flag
PF_MEMALLOC_NOIO at loop thread entry.

PID: 474    TASK: ffff8813e11f4600  CPU: 10  COMMAND: "kswapd0"
   #0 [ffff8813dedfb938] __schedule at ffffffff8173f405
   #1 [ffff8813dedfb990] schedule at ffffffff8173fa27
   #2 [ffff8813dedfb9b0] schedule_timeout at ffffffff81742fec
   #3 [ffff8813dedfba60] io_schedule_timeout at ffffffff8173f186
   #4 [ffff8813dedfbaa0] bit_wait_io at ffffffff8174034f
   #5 [ffff8813dedfbac0] __wait_on_bit at ffffffff8173fec8
   #6 [ffff8813dedfbb10] out_of_line_wait_on_bit at ffffffff8173ff81
   #7 [ffff8813dedfbb90] __make_buffer_clean at ffffffffa038736f [dm_bufio]
   #8 [ffff8813dedfbbb0] __try_evict_buffer at ffffffffa0387bb8 [dm_bufio]
   #9 [ffff8813dedfbbd0] dm_bufio_shrink_scan at ffffffffa0387cc3 [dm_bufio]
  #10 [ffff8813dedfbc40] shrink_slab at ffffffff811a87ce
  #11 [ffff8813dedfbd30] shrink_zone at ffffffff811ad778
  #12 [ffff8813dedfbdc0] kswapd at ffffffff811ae92f
  #13 [ffff8813dedfbec0] kthread at ffffffff810a8428
  #14 [ffff8813dedfbf50] ret_from_fork at ffffffff81745242

  PID: 14127  TASK: ffff881455749c00  CPU: 11  COMMAND: "loop1"
   #0 [ffff88272f5af228] __schedule at ffffffff8173f405
   #1 [ffff88272f5af280] schedule at ffffffff8173fa27
   #2 [ffff88272f5af2a0] schedule_preempt_disabled at ffffffff8173fd5e
   #3 [ffff88272f5af2b0] __mutex_lock_slowpath at ffffffff81741fb5
   #4 [ffff88272f5af330] mutex_lock at ffffffff81742133
   #5 [ffff88272f5af350] dm_bufio_shrink_count at ffffffffa03865f9 [dm_bufio]
   #6 [ffff88272f5af380] shrink_slab at ffffffff811a86bd
   #7 [ffff88272f5af470] shrink_zone at ffffffff811ad778
   #8 [ffff88272f5af500] do_try_to_free_pages at ffffffff811adb34
   #9 [ffff88272f5af590] try_to_free_pages at ffffffff811adef8
  #10 [ffff88272f5af610] __alloc_pages_nodemask at ffffffff811a09c3
  #11 [ffff88272f5af710] alloc_pages_current at ffffffff811e8b71
  #12 [ffff88272f5af760] new_slab at ffffffff811f4523
  #13 [ffff88272f5af7b0] __slab_alloc at ffffffff8173a1b5
  #14 [ffff88272f5af880] kmem_cache_alloc at ffffffff811f484b
  #15 [ffff88272f5af8d0] do_blockdev_direct_IO at ffffffff812535b3
  #16 [ffff88272f5afb00] __blockdev_direct_IO at ffffffff81255dc3
  #17 [ffff88272f5afb30] xfs_vm_direct_IO at ffffffffa01fe3fc [xfs]
  #18 [ffff88272f5afb90] generic_file_read_iter at ffffffff81198994
  #19 [ffff88272f5afc50] __dta_xfs_file_read_iter_2398 at ffffffffa020c970 [xfs]
  #20 [ffff88272f5afcc0] lo_rw_aio at ffffffffa0377042 [loop]
  #21 [ffff88272f5afd70] loop_queue_work at ffffffffa0377c3b [loop]
  #22 [ffff88272f5afe60] kthread_worker_fn at ffffffff810a8a0c
  #23 [ffff88272f5afec0] kthread at ffffffff810a8428
  #24 [ffff88272f5aff50] ret_from_fork at ffffffff81745242

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Cc: stable@vger.kernel.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
2 participants