- 29 Aug, 2017 40 commits
-
-
Christian König authored
Instead of using the vm_state use a separate flag to note that the BO was moved. v2: reorder patches to avoid temporary lockless access Signed-off-by:
Christian König <christian.koenig@amd.com> Reviewed-by:
Chunming Zhou <david1.zhou@amd.com> Signed-off-by:
Alex Deucher <alexander.deucher@amd.com>
-
Tom St Denis authored
Allows writing data to vram via debugfs. Signed-off-by:
Tom St Denis <tom.stdenis@amd.com> Reviewed-by:
-
Rex Zhu authored
when User turn off display or screen idle timeout, smu need this message to start S0i2 entry. Signed-off-by:
Rex Zhu <Rex.Zhu@amd.com> Reviewed-by:
-
Rex Zhu authored
As there is no PPTable in RV, it is difficult to cleanly decouple PPTABLE functionality in existing codes. v2: agd: squash in clean build fix Signed-off-by:
-
Rex Zhu authored
delete useless code. Signed-off-by:
-
Alex Deucher authored
To allocate additional space for the dynamic cu masks. Confirmed with the hw team that we only need 1 dword for the mask. The mask is the same for each SE so you only need 1 dword. Reviewed-by:
Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by:
-
Alex Deucher authored
Necessary for proper operation with KIQ. Reviewed-by:
-
Alex Deucher authored
It was unused and according to hw team, it's the same for all asics in a gfx family so remove it. Reviewed-by:
-
Alex Deucher authored
Confirmed with the hw team. It's the same for all asics. Reviewed-by:
-
Alex Deucher authored
Probably a copy pasta. No functional difference, both have the same value. Reviewed-by:
Michael von Khurja <mvonkhurja@techpowerup.com> Signed-off-by:
-
Christian König authored
Those are certainly not kernel allocations, instead set the NO_CPU_ACCESS flag. Signed-off-by:
-
Christian König authored
Stop checking the mapped BO itself, cause that one is certainly not a page table. Additional to that move the code into amdgpu_vm.c Signed-off-by:
-
Christian König authored
That somehow got lost. Signed-off-by:
-
Kent Russell authored
sysfs is more stable, and doesn't require root to access Signed-off-by:
Kent Russell <kent.russell@amd.com> Reviewed-by:
-
Kent Russell authored
Add 2 debugfs files, one that contains the VBIOS version, and one that contains the VBIOS itself. These won't change after initialization, so we can add the VBIOS version when we parse the atombios information. This ensures that we can find out the VBIOS version, even when the dmesg buffer fills up, and makes it easier to associate which VBIOS version is for which GPU on mGPU configurations. Set the size to 20 characters in case of some weird VBIOS version that exceeds the expected 17 character format (3-8-3\0). The VBIOS dump also allows for easy debugging v2: Move to debugfs, clarify commit message, add VBIOS dump file Signed-off-by: -
Tom St Denis authored
Minor tidy up. Signed-off-by:
-
Tom St Denis authored
Signed-off-by:
-
Tom St Denis authored
Signed-off-by:
-
Tom St Denis authored
These functions replace a section of common code found in radeon/amdgpu drivers (and possibly others) as part of the ttm_tt_*populate() callbacks. v2: squash in fix for sw iommu from Tom Signed-off-by:
-
Harry Wentland authored
We'll need this for a some upcoming display changes Signed-off-by:
Harry Wentland <harry.wentland@amd.com> Reviewed-by:
-
Tom St Denis authored
Switches the AMDGPU driver over to the TTM tracepoint and removes our old one. Now you can enable traces before loading the module and trace all mappings. Signed-off-by:
-
Tom St Denis authored
Also exports two functions that vendor drivers can call to trace DMA mappings. This is meant to help translate IOMMU mappings of bus addresses back to physical pages. Used by the umr amdgpu debugger for instance. Signed-off-by:
-
Evan Quan authored
Newer versions of the CP firmware require changes in how the driver initializes the hw block. Change the firmware name for new firmware to maintain compatibility with older kernels. Acked-by:
Evan Quan <evan.quan@amd.com> Reviewed-by:
-
Colin Ian King authored
Remove a redundant identical return statement, it has no use. Detected by CoverityScan, CID#1454586 ("Structurally dead code") Reviewed-by:Colin Ian King <colin.king@canonical.com> Signed-off-by:
-
Christophe JAILLET authored
Check memory allocation failure and return -ENOMEM in such a case. 'num_post_dep_syncobjs' still has to be set to 0 before the test in order to have it initialized if 'amdgpu_cs_parser_fini()' is called to free resources. The calling graph would be, in such a case! failure in amdgpu_cs_process_syncobj_out_dep() ---> error code returned by amdgpu_cs_dependencies() --> amdgpu_cs_parser_fini() is called Reviewed-by:Christophe JAILLET <christophe.jaillet@wanadoo.fr> Signed-off-by:
-
Roger He authored
BANK_SELECT should always be FRAGMENT_SIZE + 3 due to 8-entry (2^3) per cache line in L2 TLB for Vega10. v2: agd: fix warning Reviewed-by:
Roger He <Hongbo.He@amd.com> Signed-off-by:
-
Christian König authored
The function is called only once and doesn't do anything special. Signed-off-by:
-
Christian König authored
Use ttm_bo_mem_space instead of manually allocating GART space. This allows us to evict BOs when there isn't enought GART space any more. Signed-off-by:
-
Christian König authored
This isn't used since we don't map evicted BOs to GART any more. Signed-off-by:
-
Monk Liu authored
we observe abnormal number from: /sys/devices/virtual/drm/amdttm/buffer_objects/bo_count bo_count is atomic_inc which is "int" type, shouldn't explicitly turn it to unsigned long. Signed-off-by:
Monk Liu <monk.liu@amd.com> Reviewed-by:
-
Monk Liu authored
Signed-off-by:
-
Alex Deucher authored
KIQ doesn't really use the GPU scheduler. The base drivers generally use the KIQ ring directly rather than submitting IBs. However, amdgpu_sched_hw_submission (which defaults to 2) limits the number of outstanding fences to 2. KFD uses the KIQ for TLB flushes and the 2 fence limit hurts performance when there are several KFD processes running. v2: move some expressions to one line change KIQ sched_hw_submission to at least 16 v3: bump to 256 Reviewed-by: -
Alex Deucher authored
Move the asic specific code into the IP modules. Reviewed-by:
-
Alex Deucher authored
Be more explicit and add comments explaining each case. Also s/gart/GART/ in the parameter string as per Felix' suggestion. Reviewed-by:
-
Evan Quan authored
Signed-off-by:
-
Christian König authored
When a process is killed we shouldn't submit all waiting jobs, but instead clean up as fast as possible. Signed-off-by:
-
Christian König authored
Set the shadow flag on the shadow and not the parent, always bind shadow BOs during allocation instead of manually, use the reservation_object wrappers to grab the lock. This fixes a couple of issues with binding the shadow BOs as well as correctly evicting them when memory becomes tight. Signed-off-by:
-
Alex Deucher authored
We need a larger gart for asics that do not support GPUVM on all engines (e.g., MM) to make sure we have enough space for all gtt buffers in physical mode. Change the default size based on the asic type. Reviewed-by:
-
Alex Deucher authored
Acked-by:
-
Evan Quan authored
Signed-off-by:
-
