nvidia-tegra-modules.git/drivers/video/tegra/nvmap/nvmap_cache.c, branch gpu-paging NVIDIA's kernel modules to support tegra chips (used in Jetson boards) tegra: nvmap: Address few inappropriate mixes of integer types 2021-07-09T23:54:44+00:00 Martin Radev mradev@nvidia.com 2021-06-01T12:16:44+00:00 1b1628709790f71ebb4bcf024164f5ff3da54201 There are possible value truncations when mixing types of different width, e.g. s32 (int), u32, u64. This patch attempts to address such issues in two ways: 1) Manually find and fix error-prone mixing. 2) Prevent creating a handle from an exuberantly large size. The maximum selected size is set to maximum of system memory. This is expected to be small enough that the number of pages fits even in s32. This should offer some future protection in case nvmap starts mixing int and u64 again. Bug 3315168 Change-Id: Icb83d745a7b1955ec473bec46f12a3ae25ad73af Signed-off-by: Martin Radev <mradev@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/c/linux-nvidia/+/2537851 (cherry picked from commit 5fa42e9d5f73a937995f87ba28b99d3b891d8f3a) Reviewed-on: https://git-master.nvidia.com/r/c/linux-nvidia/+/2547360 Tested-by: mobile promotions <svcmobile_promotions@nvidia.com> Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> 
There are possible value truncations when mixing types of different
width, e.g. s32 (int), u32, u64. This patch attempts to address
such issues in two ways:
1) Manually find and fix error-prone mixing.
2) Prevent creating a handle from an exuberantly large size.

The maximum selected size is set to maximum of system memory. This
is expected to be small enough that the number of pages fits even
in s32. This should offer some future protection in case nvmap starts
mixing int and u64 again.

Bug 3315168

Change-Id: Icb83d745a7b1955ec473bec46f12a3ae25ad73af
Signed-off-by: Martin Radev <mradev@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/c/linux-nvidia/+/2537851
(cherry picked from commit 5fa42e9d5f73a937995f87ba28b99d3b891d8f3a)
Reviewed-on: https://git-master.nvidia.com/r/c/linux-nvidia/+/2547360
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
tegra: nvmap: replace BUG_ON by WARN_ON 2021-06-18T19:25:59+00:00 Puneet Saxena puneets@nvidia.com 2021-05-10T14:54:27+00:00 f1e237b01e6ea2b7039c0dc897f020780bea17be During per page cache_maint operation if Junk userspace VA passed which doesn't have page mapping created in kernel, __ioremap of the pages results NULL kernel VA. "nvmap_cache_maint_phys_range" returns -ENOMEM / No memory error for the page range. Per page heap cache-maint triggers BUG_ON when error is received. Here BUG_ON is unwarranted as it doesn't break system functionality. Rather only stale data will be received in user space as part of the faulty cache-maint operation. Replace it by WARN_ON to indicate cache-maint on page range is failed. Bug 3298659 Signed-off-by: Puneet Saxena <puneets@nvidia.com> Change-Id: Ia69015e6bd9b3ab0a2bf7b416282ae3f53a4393b Reviewed-on: https://git-master.nvidia.com/r/c/linux-nvidia/+/2527259 (cherry picked from commit 931227cd092f9948a2b86de22f8ee089d7128a97) Reviewed-on: https://git-master.nvidia.com/r/c/linux-nvidia/+/2545460 Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com> Reviewed-by: Bibek Basu <bbasu@nvidia.com> Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> GVS: Gerrit_Virtual_Submit Tested-by: Amulya Yarlagadda <ayarlagadda@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com> 
During per page cache_maint operation if Junk userspace VA passed
which doesn't have page mapping created in kernel, __ioremap
of the pages results NULL kernel VA. "nvmap_cache_maint_phys_range"
returns -ENOMEM / No memory error for the page range.
Per page heap cache-maint triggers BUG_ON when error is received.

Here BUG_ON is unwarranted as it doesn't break system functionality.
Rather only stale data will be received in user space as part
of the faulty cache-maint operation.

Replace it by WARN_ON to indicate cache-maint on page range is failed.

Bug 3298659

Signed-off-by: Puneet Saxena <puneets@nvidia.com>
Change-Id: Ia69015e6bd9b3ab0a2bf7b416282ae3f53a4393b
Reviewed-on: https://git-master.nvidia.com/r/c/linux-nvidia/+/2527259
(cherry picked from commit 931227cd092f9948a2b86de22f8ee089d7128a97)
Reviewed-on: https://git-master.nvidia.com/r/c/linux-nvidia/+/2545460
Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com>
Reviewed-by: Bibek Basu <bbasu@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
GVS: Gerrit_Virtual_Submit
Tested-by: Amulya Yarlagadda <ayarlagadda@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
video: tegra: nvmap: use chip specific cache ability 2020-10-30T12:39:41+00:00 Ken Chang kenc@nvidia.com 2020-10-29T00:46:42+00:00 f077a20e0e6515ee73229e9b2f1952f7971b979a Add nvmap_get_cacheability function pointer in struct nvmap_chip_cache_op and select the correct chip specific get_cacheability callback in nvmap_select_cache_ops() during probing. Bug 3164495 Change-Id: I3dad39db98500cb1b45f9741eb3e3548e596feb7 Signed-off-by: Ken Chang <kenc@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/c/linux-nvidia/+/2438139 Tested-by: Puneet Saxena <puneets@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com> Reviewed-by: automaticguardword <automaticguardword@nvidia.com> Reviewed-by: Puneet Saxena <puneets@nvidia.com> Reviewed-by: Bibek Basu <bbasu@nvidia.com> Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> GVS: Gerrit_Virtual_Submit 
Add nvmap_get_cacheability function pointer in struct nvmap_chip_cache_op
and select the correct chip specific get_cacheability callback in
nvmap_select_cache_ops() during probing.

Bug 3164495

Change-Id: I3dad39db98500cb1b45f9741eb3e3548e596feb7
Signed-off-by: Ken Chang <kenc@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/c/linux-nvidia/+/2438139
Tested-by: Puneet Saxena <puneets@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Reviewed-by: automaticguardword <automaticguardword@nvidia.com>
Reviewed-by: Puneet Saxena <puneets@nvidia.com>
Reviewed-by: Bibek Basu <bbasu@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
GVS: Gerrit_Virtual_Submit
video: tegra: nvmap: fix reserve page op for huge allocs 2018-06-12T00:23:54+00:00 Navneet Kumar navneetk@nvidia.com 2018-06-05T22:15:03+00:00 67b081a4749c903a71250eb82903f1435be6c010 Fix a logic bug in reserve_pages operation that did not pass element size information (32bit vs 64bit) correctly in all cases. While at it - * Simplify passing of this info down the stack. * Add some error logging in case the ioctl flow fails in between. Bug 200377221 Change-Id: I6c20915ca0d81a5842879545ca0a44e82809664a Signed-off-by: Navneet Kumar <navneetk@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1740728 Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: Krishna Reddy <vdumpa@nvidia.com> Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com> 
Fix a logic bug in reserve_pages operation that did not pass
element size information (32bit vs 64bit) correctly in all cases.

While at it -
* Simplify passing of this info down the stack.
* Add some error logging in case the ioctl flow fails in between.

Bug 200377221

Change-Id: I6c20915ca0d81a5842879545ca0a44e82809664a
Signed-off-by: Navneet Kumar <navneetk@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1740728
Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Krishna Reddy <vdumpa@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Revert "video: tegra: nvmap: remove nvmap_flush_dcache_all" 2018-05-06T18:12:00+00:00 Juha Tukkinen jtukkinen@nvidia.com 2018-05-05T17:49:39+00:00 346ccc0c5d03a23687d8df836f8e30af26be6894 This reverts commit 018d9063061a0b2d0f92cdac616fe696965f666f. Bug 2113399 Change-Id: I3a5b4a64071fe7659211a1ca3df60d70bcd3c6d9 Signed-off-by: Juha Tukkinen <jtukkinen@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1708933 
This reverts commit 018d9063061a0b2d0f92cdac616fe696965f666f.

Bug 2113399

Change-Id: I3a5b4a64071fe7659211a1ca3df60d70bcd3c6d9
Signed-off-by: Juha Tukkinen <jtukkinen@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1708933
video: tegra: nvmap: remove nvmap_flush_dcache_all 2018-05-04T04:44:55+00:00 Krishna Reddy vdumpa@nvidia.com 2018-04-30T21:34:04+00:00 018d9063061a0b2d0f92cdac616fe696965f666f Move the Denver specific dcache flush instruction to MCE code, which is handling the cache maint now. Remove the function nvmap_flush_dcache_all that would no longer be used. Bug 2110982 Change-Id: Ib62133c48b3e7c2980301e205a47cefa47622f23 Signed-off-by: Krishna Reddy <vdumpa@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1705739 Reviewed-by: Navneet Kumar <navneetk@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com> 
Move the Denver specific dcache flush instruction to
MCE code, which is handling the cache maint now.
Remove the function nvmap_flush_dcache_all that would
no longer be used.

Bug 2110982

Change-Id: Ib62133c48b3e7c2980301e205a47cefa47622f23
Signed-off-by: Krishna Reddy <vdumpa@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1705739
Reviewed-by: Navneet Kumar <navneetk@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
video: tegra: nvmap: no cache maint from T194 onwards 2018-04-16T08:26:36+00:00 Puneet Saxena puneets@nvidia.com 2018-04-06T11:38:11+00:00 698f7ad70d2699d9a741ea843a3a267a8e72c156 From T194 onwards, cpu side io-coherency is enabled by default. Therefore don't do cache maint from cpu side explicitly. Its done by SCF. Bug 200393748 Change-Id: Ia04a476fcd5c1511f4bfe4ed2dbfbf393625d9b9 Signed-off-by: Puneet Saxena <puneets@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1690031 Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com> Reviewed-by: Pritesh Raithatha <praithatha@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: Sachin Nikam <snikam@nvidia.com> Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com> 
From T194 onwards, cpu side io-coherency is enabled
by default. Therefore don't do cache maint from
cpu side explicitly. Its done by SCF.

Bug 200393748

Change-Id: Ia04a476fcd5c1511f4bfe4ed2dbfbf393625d9b9
Signed-off-by: Puneet Saxena <puneets@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1690031
Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com>
Reviewed-by: Pritesh Raithatha <praithatha@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Sachin Nikam <snikam@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
video: tegra: nvmap: remove obsolete cache maint code 2018-02-22T13:34:04+00:00 Krishna Reddy vdumpa@nvidia.com 2018-02-08T01:22:21+00:00 9646af481a59ce751a2ee2eeb511be692905f8ae Outer cache doesn't exist on current active SOC's t21x, t18x and t19x. Clean up all the obsolete and broken code. Bug 200386771 Change-Id: I3dc80ac7c84ecc3c0f9e0d81776a9422d10e21fc Signed-off-by: Krishna Reddy <vdumpa@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1653906 Reviewed-by: Sachin Nikam <snikam@nvidia.com> Tested-by: Sachin Nikam <snikam@nvidia.com> Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com> Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com> 
Outer cache doesn't exist on current active SOC's t21x, t18x and t19x.
Clean up all the obsolete and broken code.

Bug 200386771

Change-Id: I3dc80ac7c84ecc3c0f9e0d81776a9422d10e21fc
Signed-off-by: Krishna Reddy <vdumpa@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1653906
Reviewed-by: Sachin Nikam <snikam@nvidia.com>
Tested-by: Sachin Nikam <snikam@nvidia.com>
Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
video: tegra: nvmap: search in only valid nodes 2018-01-08T06:15:00+00:00 Prateek Patel prpatel@nvidia.com 2018-01-04T12:14:12+00:00 529a1583d0fbf24cd12026bb6739a2195e669782 using of_device_is_compatible() in loop to search for non-zero score to find the correct match earlier for_each_matching_node_and_match() was used which invokes of_find_matching_node_and_match() which invokes __of_match_node() which uses all the nodes in table for searching (including invalid ones) This will reduce time in nvmap_init_driver Also, change: https://git-master.nvidia.com/r/#/c/1593376/ is no longer required which was a temporary check provided to check for nvidia,carveout* bug 200341139 bug 200360206 bug 2019790 Change-Id: Iacec105c80bf601fa5ce025a2236f43821288001 Signed-off-by: Prateek Patel <prpatel@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1631651 Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: Sachin Nikam <snikam@nvidia.com> Reviewed-by: Puneet Saxena <puneets@nvidia.com> Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com> 
using of_device_is_compatible() in loop to search for
non-zero score to find the correct match

earlier for_each_matching_node_and_match() was used which  invokes
of_find_matching_node_and_match() which invokes __of_match_node()
which uses all the nodes in table for searching (including
invalid ones)

This will reduce time in nvmap_init_driver

Also, change: https://git-master.nvidia.com/r/#/c/1593376/ is no
longer required which was a temporary check provided to check for
nvidia,carveout*

bug 200341139
bug 200360206
bug 2019790

Change-Id: Iacec105c80bf601fa5ce025a2236f43821288001
Signed-off-by: Prateek Patel <prpatel@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1631651
Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Sachin Nikam <snikam@nvidia.com>
Reviewed-by: Puneet Saxena <puneets@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Revert "video: tegra: nvmap: avoid unnecessaray DT node search" 2017-12-29T08:33:51+00:00 Alex Waterman alexw@nvidia.com 2017-12-28T23:00:03+00:00 e583df95e5008dc7e8a89d0244333e75032de4db This reverts commit f6e8747f2892390353b90c43d607ecfbd8a1316e. Appears this may be causing a regression in some L4T builds - boot failure like so: [ 2.405162] PC is at 0x6563697665645f [ 2.409009] LR is at nvmap_select_cache_ops+0x4c/0xf8 [ 2.414308] pc : [<006563697665645f>] lr : [<ffffff8008519f5c>] pstate: 60400045 [ 2.422064] sp : ffffffc1eab73b40 [ 2.425545] x29: ffffffc1eab73b40 x28: 0000000000000000 [ 2.431124] x27: ffffffc1eafa4c00 x26: 00000000710af800 [ 2.436702] x25: ffffffc1eafa4c10 x24: ffffff8008e65000 [ 2.442277] x23: ffffff8009286000 x22: ffffff8009d54138 [ 2.447853] x21: ffffff800a013000 x20: ffffffc1eafa4c10 [ 2.453428] x19: ffffffc1ea5f7000 x18: 0000000000000001 [ 2.459004] x17: 000000000015bcca x16: 0000000000000000 [ 2.464579] x15: ffffffffffffffff x14: ffffffc1ea5f568a [ 2.470158] x13: ffffffc1ea5f5689 x12: 0000000000000030 [ 2.475734] x11: 0101010101010101 x10: 7f7f7f7f7f7f7f7f [ 2.481310] x9 : 0000000000000001 x8 : 0000000000000010 [ 2.486886] x7 : ffffff8008e359d0 x6 : 00000000000000e8 [ 2.492463] x5 : 000000000000005c x4 : 0000000000000008 [ 2.498038] x3 : 0000000000000002 x2 : 0000000000000000 [ 2.503614] x1 : 006563697665645f x0 : ffffffc1eab73b80 [ 2.509195] [ 2.510755] Process kworker/u12:5 (pid: 572, stack limit = 0xffffffc1eab70028) [ 2.515223] Freeing initrd memory: 6100K [ 2.522436] Call trace: [ 2.524998] [<006563697665645f>] 0x6563697665645f [ 2.529965] [<ffffff800851a198>] nvmap_override_cache_ops+0x20/0x28 [ 2.541312] [<ffffff8009470c7c>] nvmap_probe+0x11c/0x6b4 [ 2.546908] [<ffffff8008740fb0>] platform_drv_probe+0x60/0xc8 [ 2.552958] [<ffffff800873e73c>] driver_probe_device+0x26c/0x420 [ 2.559280] [<ffffff800873ea14>] __driver_attach+0x124/0x128 [ 2.565239] [<ffffff800873c0ac>] bus_for_each_dev+0x74/0xb0 [ 2.571086] [<ffffff800873dd98>] driver_attach+0x30/0x40 [ 2.576661] [<ffffff800873c670>] driver_attach_async+0x20/0x60 [ 2.582783] [<ffffff80080d7b88>] async_run_entry_fn+0x48/0x160 [ 2.588906] [<ffffff80080cd1b0>] process_one_work+0x1e0/0x478 [ 2.594940] [<ffffff80080cd4a0>] worker_thread+0x58/0x4d0 [ 2.600605] [<ffffff80080d3dd0>] kthread+0xe8/0x100 [ 2.605733] [<ffffff8008082ad0>] ret_from_fork+0x10/0x40 Change-Id: Ia0b932c307871ffc4e6206948ea732f03599218e Signed-off-by: Alex Waterman <alexw@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1628108 Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: Sachin Nikam <snikam@nvidia.com> Tested-by: Sachin Nikam <snikam@nvidia.com> 
This reverts commit f6e8747f2892390353b90c43d607ecfbd8a1316e.

Appears this may be causing a regression in some L4T builds - boot failure
like so:

[    2.405162] PC is at 0x6563697665645f
[    2.409009] LR is at nvmap_select_cache_ops+0x4c/0xf8
[    2.414308] pc : [<006563697665645f>] lr : [<ffffff8008519f5c>] pstate: 60400045
[    2.422064] sp : ffffffc1eab73b40
[    2.425545] x29: ffffffc1eab73b40 x28: 0000000000000000
[    2.431124] x27: ffffffc1eafa4c00 x26: 00000000710af800
[    2.436702] x25: ffffffc1eafa4c10 x24: ffffff8008e65000
[    2.442277] x23: ffffff8009286000 x22: ffffff8009d54138
[    2.447853] x21: ffffff800a013000 x20: ffffffc1eafa4c10
[    2.453428] x19: ffffffc1ea5f7000 x18: 0000000000000001
[    2.459004] x17: 000000000015bcca x16: 0000000000000000
[    2.464579] x15: ffffffffffffffff x14: ffffffc1ea5f568a
[    2.470158] x13: ffffffc1ea5f5689 x12: 0000000000000030
[    2.475734] x11: 0101010101010101 x10: 7f7f7f7f7f7f7f7f
[    2.481310] x9 : 0000000000000001 x8 : 0000000000000010
[    2.486886] x7 : ffffff8008e359d0 x6 : 00000000000000e8
[    2.492463] x5 : 000000000000005c x4 : 0000000000000008
[    2.498038] x3 : 0000000000000002 x2 : 0000000000000000
[    2.503614] x1 : 006563697665645f x0 : ffffffc1eab73b80
[    2.509195]
[    2.510755] Process kworker/u12:5 (pid: 572, stack limit = 0xffffffc1eab70028)
[    2.515223] Freeing initrd memory: 6100K
[    2.522436] Call trace:
[    2.524998] [<006563697665645f>] 0x6563697665645f
[    2.529965] [<ffffff800851a198>] nvmap_override_cache_ops+0x20/0x28
[    2.541312] [<ffffff8009470c7c>] nvmap_probe+0x11c/0x6b4
[    2.546908] [<ffffff8008740fb0>] platform_drv_probe+0x60/0xc8
[    2.552958] [<ffffff800873e73c>] driver_probe_device+0x26c/0x420
[    2.559280] [<ffffff800873ea14>] __driver_attach+0x124/0x128
[    2.565239] [<ffffff800873c0ac>] bus_for_each_dev+0x74/0xb0
[    2.571086] [<ffffff800873dd98>] driver_attach+0x30/0x40
[    2.576661] [<ffffff800873c670>] driver_attach_async+0x20/0x60
[    2.582783] [<ffffff80080d7b88>] async_run_entry_fn+0x48/0x160
[    2.588906] [<ffffff80080cd1b0>] process_one_work+0x1e0/0x478
[    2.594940] [<ffffff80080cd4a0>] worker_thread+0x58/0x4d0
[    2.600605] [<ffffff80080d3dd0>] kthread+0xe8/0x100
[    2.605733] [<ffffff8008082ad0>] ret_from_fork+0x10/0x40

Change-Id: Ia0b932c307871ffc4e6206948ea732f03599218e
Signed-off-by: Alex Waterman <alexw@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1628108
Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Sachin Nikam <snikam@nvidia.com>
Tested-by: Sachin Nikam <snikam@nvidia.com>