kernel/linux.git/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c, branch linux-4.13.y

drm/amdgpu: Remove unused field kgd2kfd_shared_resources.num_mec

2017-07-14T01:21:56+00:00

Dead code. Change-Id: I9575aa73b5741b80dc340f953cc773385c92b2be Signed-off-by: Jay Cornwall Reviewed-by: Alex Deucher Signed-off-by: Oded Gabbay

drm/amdgpu: Fix KFD oversubscription by tracking queues correctly

2017-07-14T01:21:53+00:00

The number of compute queues available to the KFD was erroneously calculated as 64. Only the first MEC can execute compute queues and it has 32 queue slots. This caused the oversubscription limit to be calculated incorrectly, leading to a missing chained runlist command at the end of an oversubscribed runlist. v2: Remove unused num_mec field to avoid duplicate logic v3: Separate num_mec removal into separate patches Change-Id: I9e7bba2cc1928b624e3eeb1edb06fdb602e5294f Signed-off-by: Jay Cornwall Reviewed-by: Alex Deucher Signed-off-by: Oded Gabbay

drm/amdgpu: move mec queue helpers to amdgpu_gfx.h

2017-06-07T22:02:06+00:00

They are gfx related, not general helpers. Reviewed-by: Alex Xie Signed-off-by: Alex Deucher

drm/amdgpu: avoid KIQ clashing with compute or KFD queues v2

2017-05-31T20:48:58+00:00

Instead of picking an arbitrary queue for KIQ, search for one according to policy. The queue must be unused. Also report the KIQ as an unavailable resource to KFD. In testing I ran into KCQ initialization issues when using pipes 2/3 of MEC2 for the KIQ. Therefore the policy disallows grabbing one of these. v2: fix (ring.me + 1) to (ring.me -1) in amdgpu_amdkfd_device_init Reviewed-by: Felix Kuehling Signed-off-by: Andres Rodriguez Signed-off-by: Alex Deucher

drm/amdkfd: allow split HQD on per-queue granularity v5

2017-05-31T20:48:54+00:00

Update the KGD to KFD interface to allow sharing pipes with queue granularity instead of pipe granularity. This allows for more interesting pipe/queue splits. v2: fix overflow check for res.queue_mask v3: fix shift overflow when setting res.queue_mask v4: fix comment in is_pipeline_enabled() v5: clamp res.queue_mask to the first MEC only Reviewed-by: Edward O'Callaghan Reviewed-by: Felix Kuehling Acked-by: Christian König Signed-off-by: Andres Rodriguez Signed-off-by: Alex Deucher

drm/amdgpu: rename rdev to adev

2017-05-31T20:48:50+00:00

Rename straggler instances of r(adeon)dev to a(mdgpu)dev Reviewed-by: Edward O'Callaghan Reviewed-by: Felix Kuehling Acked-by: Christian König Signed-off-by: Andres Rodriguez Signed-off-by: Alex Deucher

drm/amdgpu: remove unused functions

2016-09-22T14:24:16+00:00

We get 2 warnings when building kernel with W=1: drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c:146:5: warning: no previous prototype for 'pool_to_domain' [-Wmissing-prototypes] drivers/gpu/drm/amd/amdgpu/cz_smc.c:104:5: warning: no previous prototype for 'cz_send_msg_to_smc_with_parameter_async' [-Wmissing-prototypes] In fact, both functions are called by no one and not exported, so this patch removes them. Reviewed-by: Christian König Signed-off-by: Baoyou Xie Signed-off-by: Alex Deucher

drm/amdgpu: move get_gpu_clock_counter into the gfx struct

2016-07-07T19:01:42+00:00

It's gfx IP specific, not asic specific, so move to a gfx callback. Reviewed-by: Chunming Zhou Signed-off-by: Alex Deucher

drm/amdgpu: Return -EPROBE_DEFER when amdkfd not loaded

2016-02-27T20:52:40+00:00

amdgpu must load only after amdkfd's loading has been completed. If that is not enforced, then amdgpu's call into amdkfd's functions will cause a kernel BUG. When amdgpu and amdkfd are built as kernel modules, that rule is enforced by the kernel's modules loading mechanism. When amdgpu and amdkfd are built inside the kernel image, that rule is enforced by ordering in the drm Makefile (amdkfd before amdgpu). Instead of using drm Makefile ordering, we can now use deferred loading as amdkfd now returns -EPROBE_DEFER in kgd2kfd_init() when it is not yet loaded. This patch defers amdgpu loading by propagating -EPROBE_DEFER to the kernel's drivers loading infrastructure. That will put amdgpu into the pending drivers list (see description in dd.c). Once amdkfd is loaded, a call to kgd2kfd_init() will return successfully and amdgpu will be able to load. Signed-off-by: Oded Gabbay Reviewed-by: Alex Deucher

drm/amdkfd: Track when module's init is complete

2016-02-27T20:52:40+00:00

Current dependencies between amdkfd and radeon/amdgpu force the loading of amdkfd _before_ radeon and/or amdgpu are loaded. When all these kernel drivers are built as modules, this ordering is enforced by the kernel built-in mechanism of loading dependent modules. However, there is no such mechanism in case where all these drivers are compiled inside the kernel image (not as modules). The current way to enforce loading of amdkfd before radeon/amdgpu, is to put amdkfd before radeon/amdgpu in the drm Makefile, but that method is way too fragile. In addition, there is no kernel mechanism to check whether a kernel driver that is built inside the kernel image, has already been loaded. To solve this, this patch adds to kfd_module.c a new static variable, amdkfd_init_completed, that is set to 1 only when amdkfd's module initialization function has been completed (successfully). kgd2kfd_init(), which is the initialization function of the kgd-->kfd interface, and which is the first function in amdkfd called by radeon/amdgpu, will return successfully only if amdkfd_init_completed is equal 1. If amdkfd_init_completed is not equal to 1, kgd2kfd_init() will return -EPROBE_DEFER to signal radeon/amdgpu they need to defer their loading until amdkfd is loaded. Signed-off-by: Oded Gabbay Reviewed-by: Alex Deucher