[Why]
This was added in the past to solve the issue of not knowing when
to stall for medium and full updates in DM.
Since DC is ultimately decides what requires bandwidth changes we
wanted to make use of it directly to determine this.
The problem is that we can't actually pass any of the stream or surface
updates into DC global validation, so we don't actually check if the new
configuration is valid - we just validate the old existing config
instead and stall for outstanding commits to finish.
There's also the problem of grabbing the DRM private object for
pageflips which can lead to page faults in the case where commits
execute out of order and free a DRM private object state that was
still required for commit tail.
[How]
Now that we reset the plane in DM with the same conditions DC checks
we can have planes go through DC validation and we know when we need
to check and stall based on whether the stream or planes changed.
We mark lock_and_validation_needed whenever we've done this, so just
go back to using that instead of dm_determine_update_type_for_commit.
Since we'll skip resetting the plane for a pageflip we will no longer
grab the DRM private object for pageflips as well, avoiding the
page fault issued caused by pageflipping under load with commits
executing out of order.
Signed-off-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Reviewed-by: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
[Why]
MEDIUM or FULL updates can require global validation or affect
bandwidth. By treating these all simply as surface updates we aren't
actually passing this through DC global validation.
[How]
There's currently no way to pass surface updates through DC global
validation, nor do I think it's a good idea to change the interface
to accept these.
DC global validation itself is currently stateless, and we can move
our update type checking to be stateless as well by duplicating DC
surface checks in DM based on DRM properties.
We wanted to rely on DC automatically determining this since DC knows
best, but DM is ultimately what fills in everything into DC plane
state so it does need to know as well.
There are basically only three paths that we exercise in DM today:
1) Cursor (async update)
2) Pageflip (fast update)
3) Full pipe programming (medium/full updates)
Which means that anything that's more than a pageflip really needs to
go down path #3.
So this change duplicates all the surface update checks based on DRM
state instead inside of should_reset_plane().
Next step is dropping dm_determine_update_type_for_commit and we no
longer require the old DC state at all for global validation.
Optimization can come later so we don't reset DC planes at all for
MEDIUM udpates and avoid validation, but we might require some extra
checks in DM to achieve this.
Signed-off-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Reviewed-by: Hersen Wu <hersenxs.wu@amd.com>
Reviewed-by: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
[Why]
So we're not racing with userspace or deadlocking DM.
[How]
These flags are now stored on dm_plane_state itself and acquried and
validated during commit_check, so just use those instead.
Signed-off-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Reviewed-by: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
[Why]
We're racing with userspace as the flags could potentially change
from when we acquired and validated them in commit_check.
[How]
We unfortunately can't drop this function in its entirety from
prepare_planes since we don't know the afb->address at commit_check
time yet.
So instead of querying new tiling_flags and tmz_surface use the ones
from the plane_state directly.
While we're at it, also update the force_disable_dcc option based
on the state from atomic check.
Signed-off-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Reviewed-by: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
[Why]
Enabling or disable DCC or switching between tiled and linear formats
can require bandwidth updates.
They're currently skipping all DC validation by being treated as purely
surface updates.
[How]
Treat tiling_flag changes (which encode DCC state) as a condition for
resetting the plane.
Signed-off-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Reviewed-by: Hersen Wu <hersenxs.wu@amd.com>
Reviewed-by: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
[Why]
Store these in advance so we can reuse them later in commit_tail without
having to reserve the fbo again.
These will also be used for checking for tiling changes when deciding
to reset the plane or not.
[How]
This change should mostly be a refactor. Only commit check is affected
for now and I'll drop the get_fb_info calls in prepare_planes and
commit_tail after.
This runs a prepass loop once we think that all planes have been added
to the context and replaces the get_fb_info calls with accessing the
dm_plane_state instead.
Signed-off-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Reviewed-by: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Allows UMD to know if TMZ is supported and enabled.
This commit also bumps KMS_DRIVER_MINOR because if we don't
UMD can't tell if "ids_flags & AMDGPU_IDS_FLAGS_TMZ == 0" means
"tmz is not enabled" or "tmz may be enabled but the kernel doesn't
report it".
v2: use amdgpu_is_tmz() and reworded commit message.
Signed-off-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
As for the gpu metric export, metrics cache makes no sense. It's up to
user to decide how often the metrics should be retrieved.
Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
As for the gpu metric export, metrics cache makes no sense. It's up to
user to decide how often the metrics should be retrieved.
Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
As for the gpu metric export, metrics cache makes no sense. It's up to
user to decide how often the metrics should be retrieved.
Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
As for the gpu metric export, metrics cache makes no sense. It's up to
user to decide how often the metrics should be retrieved.
Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
As for the gpu metric export, metrics cache makes no sense. It's up to
user to decide how often the metrics should be retrieved.
Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
As for the gpu metric export, metrics cache makes no sense. It's up to
user to decide how often the metrics should be retrieved.
Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Although it does not bring any problem for now, the coming gpu
metrics interface needs to handle them differently based on the
asic type.
Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Thus we can provide an interface for UMD to retrieve gpu metrics data.
V2: better naming and comments
V3: two structures created for dGPU and APU separately
V4: add driver attached timestamp
Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
For Arcturus, the softmin/max settings from driver are permitted on the
latest(54.26 later) SMU firmware. Thus enabling them in driver.
Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Kenneth Feng <kenneth.feng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
If multiple process share system memory through /dev/shm, KFD allocate
memory should not fail if it reaches the system memory limit because
one copy of physical system memory are shared by multiple process.
Add module parameter no_system_mem_limit to provide user option to
disable system memory limit check at runtime using sysfs or during
driver module init using kernel boot argument. By default the system
memory limit is on.
Print out debug message to warn user if KFD allocate memory failed
because system memory reaches limit.
Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
The only usage of dcn30_res_pool_funcs is to assign its address to a
const pointer. Make it const to allow the compiler to put it in
read-only memory.
Signed-off-by: Rikard Falkeborn <rikard.falkeborn@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
The only usage of dcn21_res_pool_funcs is to assign its address to a
const pointer. Make it const to allow the compiler to put it in
read-only memory.
Signed-off-by: Rikard Falkeborn <rikard.falkeborn@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
The only usage of dcn20_res_pool_funcs is to assign its address to a
const pointer. Make it const to allow the compiler to put it in
read-only memory.
Signed-off-by: Rikard Falkeborn <rikard.falkeborn@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
I suspect the only reason this was set was to avoid touching
the display related registers on arcturus. Someone should
double check this on arcturus with S3.
Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This adds a new gmc callback to get the size reserved by the pre-OS
console and provides a helper function for use by gmc IP drivers.
Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This will allow us to split the allocation for systems
where we have to keep the stolen memory around to avoid
S3 issues. This way we don't waste as much memory and
still avoid any screen artifacts during the bios to
driver transition.
Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
