linux-stable.git/drivers, branch v5.2.14

Revert "mmc: core: do not retry CMD6 in __mmc_switch()"

2019-09-10T09:35:26+00:00

commit 8ad8e02c2fa70cfddc1ded53ba9001c9d444075d upstream.

Turns out the commit 3a0681c7448b ("mmc: core: do not retry CMD6 in
__mmc_switch()") breaks initialization of a Toshiba THGBMNG5 eMMC card,
when using the meson-gx-mmc.c driver on a custom board based on Amlogic
A113D.

The CMD6 that switches the card into HS200 mode is then one that fails and
according to the below printed messages from the log:

[    1.648951] mmc0: mmc_select_hs200 failed, error -84
[    1.648988] mmc0: error -84 whilst initialising MMC card

After some analyze, it turns out that adding a delay of ~5ms inside
mmc_select_bus_width() but after mmc_compare_ext_csds() has been executed,
also fixes the problem. Adding yet some more debug code, trying to figure
out if potentially the card could be in a busy state, both by using CMD13
and ->card_busy() ops concluded that this was not the case.

Therefore, let's simply revert the commit that dropped support for retrying
of CMD6, as this also fixes the problem.

Fixes: 3a0681c7448b ("mmc: core: do not retry CMD6 in __mmc_switch()")
Cc: stable@vger.kernel.org
Signed-off-by: Jan Kaisrlik 
Signed-off-by: Ulf Hansson 
Signed-off-by: Greg Kroah-Hartman

gpio: Fix irqchip initialization order

2019-09-10T09:35:25+00:00

[ Upstream commit 48057ed1840fde9239b1e000bea1a0a1f07c5e99 ]

The new API for registering a gpio_irq_chip along with a
gpio_chip has a different semantic ordering than the old
API which added the irqchip explicitly after registering
the gpio_chip.

Move the calls to add the gpio_irq_chip *last* in the
function, so that the different hooks setting up OF and
ACPI and machine gpio_chips are called *before* we try
to register the interrupts, preserving the elder semantic
order.

This cropped up in the PL061 driver which used to work
fine with no special ACPI quirks, but started to misbehave
using the new API.

Fixes: e0d897289813 ("gpio: Implement tighter IRQ chip integration")
Cc: Thierry Reding 
Cc: Grygorii Strashko 
Cc: Andy Shevchenko 
Reported-by: Wei Xu 
Tested-by: Wei Xu 
Reported-by: Andy Shevchenko 
Signed-off-by: Linus Walleij 
Link: https://lore.kernel.org/r/20190820080527.11796-1-linus.walleij@linaro.org
Signed-off-by: Sasha Levin

RDMA/bnxt_re: Fix stack-out-of-bounds in bnxt_qplib_rcfw_send_message

2019-09-10T09:35:25+00:00

[ Upstream commit d37b1e534071ab1983e7c85273234b132c77591a ]

Driver copies FW commands to the HW queue as  units of 16 bytes. Some
of the command structures are not exact multiple of 16. So while copying
the data from those structures, the stack out of bounds messages are
reported by KASAN. The following error is reported.

[ 1337.530155] ==================================================================
[ 1337.530277] BUG: KASAN: stack-out-of-bounds in bnxt_qplib_rcfw_send_message+0x40a/0x850 [bnxt_re]
[ 1337.530413] Read of size 16 at addr ffff888725477a48 by task rmmod/2785

[ 1337.530540] CPU: 5 PID: 2785 Comm: rmmod Tainted: G           OE     5.2.0-rc6+ #75
[ 1337.530541] Hardware name: Dell Inc. PowerEdge R730/0599V5, BIOS 1.0.4 08/28/2014
[ 1337.530542] Call Trace:
[ 1337.530548]  dump_stack+0x5b/0x90
[ 1337.530556]  ? bnxt_qplib_rcfw_send_message+0x40a/0x850 [bnxt_re]
[ 1337.530560]  print_address_description+0x65/0x22e
[ 1337.530568]  ? bnxt_qplib_rcfw_send_message+0x40a/0x850 [bnxt_re]
[ 1337.530575]  ? bnxt_qplib_rcfw_send_message+0x40a/0x850 [bnxt_re]
[ 1337.530577]  __kasan_report.cold.3+0x37/0x77
[ 1337.530581]  ? _raw_write_trylock+0x10/0xe0
[ 1337.530588]  ? bnxt_qplib_rcfw_send_message+0x40a/0x850 [bnxt_re]
[ 1337.530590]  kasan_report+0xe/0x20
[ 1337.530592]  memcpy+0x1f/0x50
[ 1337.530600]  bnxt_qplib_rcfw_send_message+0x40a/0x850 [bnxt_re]
[ 1337.530608]  ? bnxt_qplib_creq_irq+0xa0/0xa0 [bnxt_re]
[ 1337.530611]  ? xas_create+0x3aa/0x5f0
[ 1337.530613]  ? xas_start+0x77/0x110
[ 1337.530615]  ? xas_clear_mark+0x34/0xd0
[ 1337.530623]  bnxt_qplib_free_mrw+0x104/0x1a0 [bnxt_re]
[ 1337.530631]  ? bnxt_qplib_destroy_ah+0x110/0x110 [bnxt_re]
[ 1337.530633]  ? bit_wait_io_timeout+0xc0/0xc0
[ 1337.530641]  bnxt_re_dealloc_mw+0x2c/0x60 [bnxt_re]
[ 1337.530648]  bnxt_re_destroy_fence_mr+0x77/0x1d0 [bnxt_re]
[ 1337.530655]  bnxt_re_dealloc_pd+0x25/0x60 [bnxt_re]
[ 1337.530677]  ib_dealloc_pd_user+0xbe/0xe0 [ib_core]
[ 1337.530683]  srpt_remove_one+0x5de/0x690 [ib_srpt]
[ 1337.530689]  ? __srpt_close_all_ch+0xc0/0xc0 [ib_srpt]
[ 1337.530692]  ? xa_load+0x87/0xe0
...
[ 1337.530840]  do_syscall_64+0x6d/0x1f0
[ 1337.530843]  entry_SYSCALL_64_after_hwframe+0x44/0xa9
[ 1337.530845] RIP: 0033:0x7ff5b389035b
[ 1337.530848] Code: 73 01 c3 48 8b 0d 2d 0b 2c 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa b8 b0 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d fd 0a 2c 00 f7 d8 64 89 01 48
[ 1337.530849] RSP: 002b:00007fff83425c28 EFLAGS: 00000206 ORIG_RAX: 00000000000000b0
[ 1337.530852] RAX: ffffffffffffffda RBX: 00005596443e6750 RCX: 00007ff5b389035b
[ 1337.530853] RDX: 000000000000000a RSI: 0000000000000800 RDI: 00005596443e67b8
[ 1337.530854] RBP: 0000000000000000 R08: 00007fff83424ba1 R09: 0000000000000000
[ 1337.530856] R10: 00007ff5b3902960 R11: 0000000000000206 R12: 00007fff83425e50
[ 1337.530857] R13: 00007fff8342673c R14: 00005596443e6260 R15: 00005596443e6750

[ 1337.530885] The buggy address belongs to the page:
[ 1337.530962] page:ffffea001c951dc0 refcount:0 mapcount:0 mapping:0000000000000000 index:0x0
[ 1337.530964] flags: 0x57ffffc0000000()
[ 1337.530967] raw: 0057ffffc0000000 0000000000000000 ffffffff1c950101 0000000000000000
[ 1337.530970] raw: 0000000000000000 0000000000000000 00000000ffffffff 0000000000000000
[ 1337.530970] page dumped because: kasan: bad access detected

[ 1337.530996] Memory state around the buggy address:
[ 1337.531072]  ffff888725477900: 00 00 00 00 f1 f1 f1 f1 00 00 00 00 00 f2 f2 f2
[ 1337.531180]  ffff888725477980: 00 00 00 00 00 00 00 00 00 00 00 f1 f1 f1 f1 00
[ 1337.531288] >ffff888725477a00: 00 f2 f2 f2 f2 f2 f2 00 00 00 f2 00 00 00 00 00
[ 1337.531393]                                                  ^
[ 1337.531478]  ffff888725477a80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
[ 1337.531585]  ffff888725477b00: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
[ 1337.531691] ==================================================================

Fix this by passing the exact size of each FW command to
bnxt_qplib_rcfw_send_message as req->cmd_size. Before sending
the command to HW, modify the req->cmd_size to number of 16 byte units.

Fixes: 1ac5a4047975 ("RDMA/bnxt_re: Add bnxt_re RoCE driver")
Signed-off-by: Selvin Xavier 
Link: https://lore.kernel.org/r/1566468170-489-1-git-send-email-selvin.xavier@broadcom.com
Signed-off-by: Doug Ledford 
Signed-off-by: Sasha Levin

drm/amdgpu: prevent memory leaks in AMDGPU_CS ioctl

2019-09-10T09:35:23+00:00

[ Upstream commit 1a701ea924815b0518733aa8d5d05c1f6fa87062 ]

Error out if the AMDGPU_CS ioctl is called with multiple SYNCOBJ_OUT and/or
TIMELINE_SIGNAL chunks, since otherwise the last chunk wins while the
allocated array as well as the reference counts of sync objects are leaked.

Signed-off-by: Nicolai Hähnle 
Reviewed-by: Christian König 
Signed-off-by: Alex Deucher 
Signed-off-by: Sasha Levin

infiniband: hfi1: fix memory leaks

2019-09-10T09:35:22+00:00

[ Upstream commit 2323d7baab2b18d87d9bc267452e387aa9f0060a ]

In fault_opcodes_write(), 'data' is allocated through kcalloc(). However,
it is not deallocated in the following execution if an error occurs,
leading to memory leaks. To fix this issue, introduce the 'free_data' label
to free 'data' before returning the error.

Signed-off-by: Wenwen Wang 
Reviewed-by: Leon Romanovsky 
Acked-by: Dennis Dalessandro 
Link: https://lore.kernel.org/r/1566154486-3713-1-git-send-email-wenwen@cs.uga.edu
Signed-off-by: Doug Ledford 
Signed-off-by: Sasha Levin

infiniband: hfi1: fix a memory leak bug

2019-09-10T09:35:22+00:00

[ Upstream commit b08afa064c320e5d85cdc27228426b696c4c8dae ]

In fault_opcodes_read(), 'data' is not deallocated if debugfs_file_get()
fails, leading to a memory leak. To fix this bug, introduce the 'free_data'
label to free 'data' before returning the error.

Signed-off-by: Wenwen Wang 
Reviewed-by: Leon Romanovsky 
Acked-by: Dennis Dalessandro 
Link: https://lore.kernel.org/r/1566156571-4335-1-git-send-email-wenwen@cs.uga.edu
Signed-off-by: Doug Ledford 
Signed-off-by: Sasha Levin

IB/mlx4: Fix memory leaks

2019-09-10T09:35:22+00:00

[ Upstream commit 5c1baaa82cea2c815a5180ded402a7cd455d1810 ]

In mlx4_ib_alloc_pv_bufs(), 'tun_qp->tx_ring' is allocated through
kcalloc(). However, it is not always deallocated in the following execution
if an error occurs, leading to memory leaks. To fix this issue, free
'tun_qp->tx_ring' whenever an error occurs.

Signed-off-by: Wenwen Wang 
Acked-by: Leon Romanovsky 
Link: https://lore.kernel.org/r/1566159781-4642-1-git-send-email-wenwen@cs.uga.edu
Signed-off-by: Doug Ledford 
Signed-off-by: Sasha Levin

RDMA/cma: fix null-ptr-deref Read in cma_cleanup

2019-09-10T09:35:21+00:00

[ Upstream commit a7bfb93f0211b4a2f1ffeeb259ed6206bac30460 ]

In cma_init, if cma_configfs_init fails, need to free the
previously memory and return fail, otherwise will trigger
null-ptr-deref Read in cma_cleanup.

cma_cleanup
  cma_configfs_exit
    configfs_unregister_subsystem

Fixes: 045959db65c6 ("IB/cma: Add configfs for rdma_cm")
Reported-by: Hulk Robot 
Signed-off-by: zhengbin 
Reviewed-by: Parav Pandit 
Link: https://lore.kernel.org/r/1566188859-103051-1-git-send-email-zhengbin13@huawei.com
Signed-off-by: Doug Ledford 
Signed-off-by: Sasha Levin

nvme: Fix cntlid validation when not using NVMEoF

2019-09-10T09:35:21+00:00

[ Upstream commit a89fcca8185633993018dc081d6b021d005e6d0b ]

Commit 1b1031ca63b2 ("nvme: validate cntlid during controller initialisation")
introduced a validation for controllers with duplicate cntlid that runs
on nvme_init_subsystem(). The problem is that the validation relies on
ctrl->cntlid, and this value is assigned (from id_ctrl value) after the
call for nvme_init_subsystem() in nvme_init_identify() for non-fabrics
scenario. That leads to ctrl->cntlid always being 0 in case we have a
physical set of controllers in the same subsystem.

This patch fixes that by loading the discovered cntlid id_ctrl value into
ctrl->cntlid before the subsystem initialization, only for the non-fabrics
case. The patch was tested with emulated nvme devices (qemu) having two
controllers in a single subsystem. Without the patch, we couldn't make
it work failing in the duplicate check; when running with the patch, we
could see the subsystem holding both controllers.

For the fabrics case we see ctrl->cntlid has a more intricate relation
with the admin connect, so we didn't change that.

Fixes: 1b1031ca63b2 ("nvme: validate cntlid during controller initialisation")
Signed-off-by: Guilherme G. Piccoli 
Reviewed-by: Sagi Grimberg 
Signed-off-by: Sagi Grimberg 
Signed-off-by: Jens Axboe 
Signed-off-by: Sasha Levin

nvme-multipath: fix possible I/O hang when paths are updated

2019-09-10T09:35:21+00:00

[ Upstream commit 504db087aaccdb32af61539916409f7dca31ceb5 ]

nvme_state_set_live() making a path available triggers requeue_work
in order to resubmit requests that ended up on requeue_list when no
paths were available.

This requeue_work may race with concurrent nvme_ns_head_make_request()
that do not observe the live path yet.
Such concurrent requests may by made by either:
- New IO submission.
- Requeue_work triggered by nvme_failover_req() or another ana_work.

A race may cause requeue_work capture the state of requeue_list before
more requests get onto the list. These requests will stay on the list
forever unless requeue_work is triggered again.

In order to prevent such race, nvme_state_set_live() should
synchronize_srcu(&head->srcu) before triggering the requeue_work and
prevent nvme_ns_head_make_request referencing an old snapshot of the
path list.

Reviewed-by: Christoph Hellwig 
Signed-off-by: Anton Eidelman 
Signed-off-by: Sagi Grimberg 
Signed-off-by: Jens Axboe 
Signed-off-by: Sasha Levin