linux-toradex.git/drivers/infiniband, branch v4.9.25

IB/mlx5: Verify that Q counters are supported

2017-03-18T11:14:35+00:00

commit 45bded2c216da6010184ac5ebe88c27f73439009 upstream.

Make sure that the Q counters are supported by the FW before trying
to allocate/deallocte them, this will avoid driver load failure when
they aren't supported by the FW.

Fixes: 0837e86a7a34 ('IB/mlx5: Add per port counters')
Signed-off-by: Kamal Heib 
Reviewed-by: Mark Bloch 
Signed-off-by: Leon Romanovsky 
Signed-off-by: Doug Ledford 
Signed-off-by: Greg Kroah-Hartman

IB/srp: Fix race conditions related to task management

2017-03-15T02:02:44+00:00

commit 0a6fdbdeb1c25e31763c1fb333fa2723a7d2aba6 upstream.

Avoid that srp_process_rsp() overwrites the status information
in ch if the SRP target response timed out and processing of
another task management function has already started. Avoid that
issuing multiple task management functions concurrently triggers
list corruption. This patch prevents that the following stack
trace appears in the system log:

WARNING: CPU: 8 PID: 9269 at lib/list_debug.c:52 __list_del_entry_valid+0xbc/0xc0
list_del corruption. prev->next should be ffffc90004bb7b00, but was ffff8804052ecc68
CPU: 8 PID: 9269 Comm: sg_reset Tainted: G        W       4.10.0-rc7-dbg+ #3
Call Trace:
 dump_stack+0x68/0x93
 __warn+0xc6/0xe0
 warn_slowpath_fmt+0x4a/0x50
 __list_del_entry_valid+0xbc/0xc0
 wait_for_completion_timeout+0x12e/0x170
 srp_send_tsk_mgmt+0x1ef/0x2d0 [ib_srp]
 srp_reset_device+0x5b/0x110 [ib_srp]
 scsi_ioctl_reset+0x1c7/0x290
 scsi_ioctl+0x12a/0x420
 sd_ioctl+0x9d/0x100
 blkdev_ioctl+0x51e/0x9f0
 block_ioctl+0x38/0x40
 do_vfs_ioctl+0x8f/0x700
 SyS_ioctl+0x3c/0x70
 entry_SYSCALL_64_fastpath+0x18/0xad

Signed-off-by: Bart Van Assche 
Cc: Israel Rukshin 
Cc: Max Gurtovoy 
Cc: Laurence Oberman 
Cc: Steve Feeley 
Signed-off-by: Doug Ledford 
Signed-off-by: Greg Kroah-Hartman

IB/srp: Avoid that duplicate responses trigger a kernel bug

2017-03-15T02:02:44+00:00

commit 6cb72bc1b40bb2c1750ee7a5ebade93bed49a5fb upstream.

After srp_process_rsp() returns there is a short time during which
the scsi_host_find_tag() call will return a pointer to the SCSI
command that is being completed. If during that time a duplicate
response is received, avoid that the following call stack appears:

BUG: unable to handle kernel NULL pointer dereference at           (null)
IP: srp_recv_done+0x450/0x6b0 [ib_srp]
Oops: 0000 [#1] SMP
CPU: 10 PID: 0 Comm: swapper/10 Not tainted 4.10.0-rc7-dbg+ #1
Call Trace:
 
 __ib_process_cq+0x4b/0xd0 [ib_core]
 ib_poll_handler+0x1d/0x70 [ib_core]
 irq_poll_softirq+0xba/0x120
 __do_softirq+0xba/0x4c0
 irq_exit+0xbe/0xd0
 smp_apic_timer_interrupt+0x38/0x50
 apic_timer_interrupt+0x90/0xa0
 
RIP: srp_recv_done+0x450/0x6b0 [ib_srp] RSP: ffff88046f483e20

Signed-off-by: Bart Van Assche 
Cc: Israel Rukshin 
Cc: Max Gurtovoy 
Cc: Laurence Oberman 
Cc: Steve Feeley 
Reviewed-by: Leon Romanovsky 
Signed-off-by: Doug Ledford 
Signed-off-by: Greg Kroah-Hartman

IB/SRP: Avoid using IB_MR_TYPE_SG_GAPS

2017-03-15T02:02:44+00:00

commit d6c58dc40fec35ff6cdb350b53bce0fcf9143709 upstream.

Tests have shown that the following error message is reported when
using SG-GAPS registration with an mlx5 adapter:

scsi host1: ib_srp: failed RECV status WR flushed (5) for CQE ffff880bd4270eb0
00000000 00000000 00000000 00000000
00000000 00000000 00000000 00000000
00000000 00000000 00000000 00000000
00000000 0f007806 2500002a ad9fafd1
scsi host1: ib_srp: reconnect succeeded
mlx5_0:dump_cqe:262:(pid 7369): dump error cqe
00000000 00000000 00000000 00000000
00000000 00000000 00000000 00000000
00000000 00000000 00000000 00000000
00000000 0f007806 25000032 00105dd0
scsi host1: ib_srp: failed FAST REG status memory management operation error (6) for CQE ffff880b92860138

Hence avoid using SG-GAPS memory registrations. Additionally,
always configure the blk_queue_virt_boundary() to avoid to trigger
a mapping failure when using adapters that support SG-GAPS (e.g.
mlx5).

Fixes: commit ad8e66b4a801 ("IB/srp: fix mr allocation when the device supports sg gaps")
Fixes: commit 509c5f33f4f6 ("IB/srp: Prevent mapping failures")
Reported-by: Laurence Oberman 
Signed-off-by: Bart Van Assche 
Cc: Israel Rukshin 
Cc: Max Gurtovoy 
Cc: Leon Romanovsky 
Cc: Mark Bloch 
Cc: Yuval Shaia 
Signed-off-by: Doug Ledford 
Signed-off-by: Greg Kroah-Hartman

IB/mlx5: Fix out-of-bound access

2017-03-15T02:02:43+00:00

commit 0fd27a88c2e4f548937fd7d93fc6e65c4ad7c278 upstream.

When we initialize buffer to create SRQ in kernel,
the number of pages was less than actually used in
following mlx5_fill_page_array().

Fixes: e126ba97dba9 ("mlx5: Add driver for Mellanox Connect-IB adapters")
Signed-off-by: Leon Romanovsky 
Reviewed-by: Eli Cohen 
Signed-off-by: Leon Romanovsky 
Signed-off-by: Doug Ledford 
Signed-off-by: Greg Kroah-Hartman

IB/IPoIB: Add destination address when re-queue packet

2017-03-15T02:02:43+00:00

commit 2b0841766a898aba84630fb723989a77a9d3b4e6 upstream.

When sending packet to destination that was not resolved yet
via path query, the driver keeps the skb and tries to re-send it
again when the path is resolved.

But when re-sending via dev_queue_xmit the kernel doesn't call
to dev_hard_header, so IPoIB needs to keep 20 bytes in the skb
and to put the destination address inside them.

In that way the dev_start_xmit will have the correct destination,
and the driver won't take the destination from the skb->data, while
nothing exists there, which causes to packet be be dropped.

The test flow is:
1. Run the SM on remote node,
2. Restart the driver.
4. Ping some destination,
3. Observe that first ICMP request will be dropped.

Fixes: fc791b633515 ("IB/ipoib: move back IB LL address into the hard header")
Signed-off-by: Erez Shitrit 
Signed-off-by: Noa Osherovich 
Signed-off-by: Leon Romanovsky 
Tested-by: Yuval Shaia 
Signed-off-by: Doug Ledford 
Signed-off-by: Greg Kroah-Hartman

IB/ipoib: Fix deadlock between rmmod and set_mode

2017-03-15T02:02:43+00:00

commit 0a0007f28304cb9fc87809c86abb80ec71317f20 upstream.

When calling set_mode from sys/fs, the call flow locks the sys/fs lock
first and then tries to lock rtnl_lock (when calling ipoib_set_mod).
On the other hand, the rmmod call flow takes the rtnl_lock first
(when calling unregister_netdev) and then tries to take the sys/fs
lock. Deadlock a->b, b->a.

The problem starts when ipoib_set_mod frees it's rtnl_lck and tries
to get it after that.

    set_mod:
    [] ? check_preempt_curr+0x6d/0x90
    [] __mutex_lock_slowpath+0x13e/0x180
    [] ? __rtnl_unlock+0x15/0x20
    [] mutex_lock+0x2b/0x50
    [] rtnl_lock+0x15/0x20
    [] ipoib_set_mode+0x97/0x160 [ib_ipoib]
    [] set_mode+0x3b/0x80 [ib_ipoib]
    [] dev_attr_store+0x20/0x30
    [] sysfs_write_file+0xe5/0x170
    [] vfs_write+0xb8/0x1a0
    [] sys_write+0x51/0x90
    [] system_call_fastpath+0x16/0x1b

    rmmod:
    [] ? put_dec+0x10c/0x110
    [] ? number+0x2ee/0x320
    [] schedule_timeout+0x215/0x2e0
    [] ? vsnprintf+0x484/0x5f0
    [] ? string+0x40/0x100
    [] wait_for_common+0x123/0x180
    [] ? default_wake_function+0x0/0x20
    [] ? ifind_fast+0x5e/0xb0
    [] wait_for_completion+0x1d/0x20
    [] sysfs_addrm_finish+0x228/0x270
    [] sysfs_remove_dir+0xa3/0xf0
    [] kobject_del+0x16/0x40
    [] device_del+0x184/0x1e0
    [] netdev_unregister_kobject+0xab/0xc0
    [] rollback_registered+0xae/0x130
    [] unregister_netdevice+0x22/0x70
    [] unregister_netdev+0x1e/0x30
    [] ipoib_remove_one+0xe0/0x120 [ib_ipoib]
    [] ib_unregister_device+0x4f/0x100 [ib_core]
    [] mlx4_ib_remove+0x41/0x180 [mlx4_ib]
    [] mlx4_remove_device+0x71/0x90 [mlx4_core]

Fixes: 862096a8bbf8 ("IB/ipoib: Add more rtnl_link_ops callbacks")
Cc: Or Gerlitz 
Signed-off-by: Feras Daoud 
Signed-off-by: Erez Shitrit 
Signed-off-by: Leon Romanovsky 
Signed-off-by: Doug Ledford 
Signed-off-by: Greg Kroah-Hartman

rdma_cm: fail iwarp accepts w/o connection params

2017-03-12T05:41:50+00:00

commit f2625f7db4dd0bbd16a9c7d2950e7621f9aa57ad upstream.

cma_accept_iw() needs to return an error if conn_params is NULL.
Since this is coming from user space, we can crash.

Reported-by: Shaobo He 
Acked-by: Sean Hefty 
Signed-off-by: Steve Wise 
Signed-off-by: Doug Ledford 
Signed-off-by: Greg Kroah-Hartman

IB/rxe: Fix mem_check_range integer overflow

2017-02-14T23:25:42+00:00

commit 647bf3d8a8e5777319da92af672289b2a6c4dc66 upstream.

Update the range check to avoid integer-overflow in edge case.
Resolves CVE 2016-8636.

Signed-off-by: Eyal Itkin 
Signed-off-by: Dan Carpenter 
Reviewed-by: Leon Romanovsky 
Signed-off-by: Doug Ledford 
Signed-off-by: Greg Kroah-Hartman

IB/rxe: Fix resid update

2017-02-14T23:25:42+00:00

commit 628f07d33c1f2e7bf31e0a4a988bb07914bd5e73 upstream.

Update the response's resid field when larger than MTU, instead of only
updating the local resid variable.

Fixes: 8700e3e7c485 ("Soft RoCE driver")
Signed-off-by: Eyal Itkin 
Signed-off-by: Dan Carpenter 
Reviewed-by: Leon Romanovsky 
Signed-off-by: Doug Ledford 
Signed-off-by: Greg Kroah-Hartman