linux-toradex.git/drivers/gpu/drm/amd/amdkfd, branch v4.4.93

drm/amdkfd: fix improper return value on error

2017-10-08T08:14:17+00:00

[ Upstream commit 8bf793883da213864efc50c274d2b38ec0ca58b2 ]

In function kfd_wait_on_events(), when the call to copy_from_user()
fails, the value of return variable ret is 0. 0 indicates success, which
is inconsistent with the execution status. This patch fixes the bug by
assigning "-EFAULT" to ret when copy_from_user() returns an unexpected
value.

Signed-off-by: Pan Bian 
Signed-off-by: Oded Gabbay 
Signed-off-by: Sasha Levin 
Signed-off-by: Greg Kroah-Hartman

drm/amdkfd: destroy dbgmgr in notifier release

2016-07-27T16:47:34+00:00

commit bc4755a4bd1845ef6e88ac8c62f12e05bb530256 upstream.

amdkfd need to destroy the debug manager in case amdkfd's notifier
function is called before the unbind function, because in that case,
the unbind function will exit without destroying debug manager.

Signed-off-by: Oded Gabbay 
Signed-off-by: Greg Kroah-Hartman

drm/amdkfd: unbind only existing processes

2016-07-27T16:47:33+00:00

commit 121b78e679ee3ffab780115e260b2775d0cc1f73 upstream.

When unbinding a process from a device (initiated by amd_iommu_v2), the
driver needs to make sure that process still exists in the process table.
There is a possibility that amdkfd's own notifier handler -
kfd_process_notifier_release() - was called before the unbind function
and it already removed the process from the process table.

v2:
Because there can be only one process with the specified pasid, and
because *p can't be NULL inside the hash_for_each_rcu macro, it is more
reasonable to just put the whole code inside the if statement that
compares the pasid value. That way, when we exit hash_for_each_rcu, we
simply exit the function as well.

Signed-off-by: Oded Gabbay 
Signed-off-by: Greg Kroah-Hartman

drm/amdkfd: uninitialized variable in dbgdev_wave_control_set_registers()

2016-05-04T21:48:47+00:00

commit 93fce954427effee89e44a976299b15dd75b4bbc upstream.

At the end of the function we expect "status" to be zero, but it's
either -EINVAL or uninitialized.

Fixes: 788bf83db301 ('drm/amdkfd: Add wave control operation to debugger')
Signed-off-by: Dan Carpenter 
Signed-off-by: Oded Gabbay 
Signed-off-by: Greg Kroah-Hartman

amdkfd: use instead of

2015-08-30T09:36:58+00:00

The latter is a default version of  and not for driver use.

Signed-off-by: Christoph Hellwig 
Signed-off-by: Oded Gabbay

drm/amdkfd: fix bug when initializing sdma vm

2015-07-30T06:26:15+00:00

A logical AND operation was used during mask and shift, instead of a
bitwise AND operation. This patch fixes this bug by changing the
operation to bitwise AND.

Signed-off-by: Oded Gabbay 
Reviewed-by: Alex Deucher

drm/amdkfd: Set correct doorbell packet type for Carrizo

2015-07-20T06:16:49+00:00

Signed-off-by: Ben Goz 
Reviewed-by: Yair Shachar 
Signed-off-by: Oded Gabbay

drm/amdkfd: Use generic defines in new amd headers

2015-07-20T06:16:49+00:00

This patch makes use of the new amd headers (that are part of the new
amdgpu driver), instead of private defines.

Signed-off-by: Oded Gabbay

drm/amdkfd: Implement create_map_queues() for Carrizo

2015-07-20T06:16:49+00:00

Signed-off-by: Ben Goz 
Signed-off-by: Oded Gabbay

drm/amdkfd: fix runlist length calculation

2015-07-20T06:16:49+00:00

The MAP_QUEUES packet length for Carrizo is different than for Kaveri.
Therefore, we now need to calculate the runlist length with regard to the
underlying H/W.

Signed-off-by: Ben Goz 
Signed-off-by: Oded Gabbay