If IH primary ring and KFD ih fifo overflows, we may miss CP, SDMA
interrupts and cause application soft hang. Show warning message with
ring name if overflow happens.
Add function to get ih ring name to avoid duplicating it. To keep
warning message consistent between GPU generations, change all
*_ih.c except ASICs older than Vega which has only one ih ring.
Signed-off-by: Philip Yang <Philip.Yang@amd.com>
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>
If event slot is not signaled, kfd_signal_event_interrupt goes to slow
path to scan all event slots to find the signaled event, this is needed
for old ASICs that don't have the event ID or the event IDs are
incorrect in the IH payload.
There is case that GPU signal the same event twice, then driver process
the first event interrupt, set_event and event slot is auto-reset, then
for the second event interrupt, KFD goes to slow path as event is not
signaled, just drop the second event interrupt because the application
only need wakeup once.
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>
For CPX mode, each KFD node has interrupt worker to process ih_fifo to
send events to user space. Currently all interrupt workers of same adev
queue to same CPU, all workers execution are actually serialized and
this cause KFD ih_fifo overflow when CPU usage is high.
Use per-GPU unbounded highpri queue with number of workers equals to
number of partitions, let queue_work select the next CPU round robin
among the local CPUs of same NUMA.
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>
After GPU page fault, there are lots of page fault interrupts generated
at short period even with CAM filter enabled because the fault address
is different. Each page fault copy to KFD ih fifo to send event to user
space by KFD interrupt worker, this could cause KFD ih fifo overflow
while other processes generate events at same time.
KFD process is aborted after GPU page fault, we only need one GPU page
fault interrupt sent to KFD ih fifo to send memory exception event to
user space.
Incease KFD ih fifo size to 2 times of IH primary ring size, to handle
the burst events case.
This patch handle the gfx v9 path, cover retry on/off and CAM filter
on/off cases.
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>
To handle 40000 to 80000 interrupts per second running CPX mode with 4
streams/queues per KFD node, KFD interrupt handler becomes the
performance bottleneck.
Remove the kfifo_out memcpy overhead by accessing ih_fifo data in-place
and updating rptr with kfifo_skip_count.
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>
This partially reverts commit 194eb174cb.
This commit introduced a new state variable into adev without even
remotely worrying about CPU barriers.
Since we already have the amdgpu_in_reset() function exactly for this
use case partially revert that.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
The sdma context empty interrupt is dropped in amdgpu_irq_dispatch
as unregistered interrupt src_id 243, this interrupt accounts to 1/3 of
total interrupts and causes IH primary ring overflow when running
stressful benchmark application. Disable this interrupt has no side
effect found.
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 use of 1 << i in scheduler mask calculations can result in an
unintentional integer overflow due to the expression being
evaluated as a 32-bit signed integer.
This patch replaces 1 << i with 1ULL << i to ensure the operation
is performed as a 64-bit unsigned integer, preventing overflow
Discovered in coverity scan, CID 1636393, 1636175, 1636007, 1635853
Fixes: c5c63d9cb5 ("drm/amdgpu: add amdgpu_gfx_sched_mask and amdgpu_compute_sched_mask debugfs")
Signed-off-by: Karol Przybylski <karprzy7@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
[Why]
Seamless boot skips MPC init for the active pipe, resulting in stale MPC
rate control state being retained. This will cause issues since other
logic assumes it is disabled (as DCN30 and newer does not need it).
[How]
Disable MPC rate control on ODM pipe update to cover the seamless boot
case.
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Reviewed-by: Alvin Lee <alvin.lee2@amd.com>
Signed-off-by: George Shen <george.shen@amd.com>
Signed-off-by: Rodrigo Siqueira <rodrigo.siqueira@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This reverts commit 87b7ebc2e1.
A long time ago, we had an issue with the Raven system when it was
connected to two displays: one with DP and another with HDMI. After the
system woke up from suspension, we saw a solid green screen caused by an
underflow generated by bad DCC metadata. To workaround this issue, the
'commit 87b7ebc2e1 ("drm/amd/display: Fix green screen issue after
suspend")' was introduced to disable the DCC for a few frames after in
the resume phase. However, in hindsight, this solution was probably a
workaround at the kernel level for some issues from another part
(probably other driver components or user space). After applying this
patch and trying to reproduce the green issue in a similar hardware
system but using the latest kernel and userspace, we cannot see the
issue, which makes this workaround obsolete and creates extra
unnecessary complexity to the code; for all of this reason, this commit
reverts the original change.
Cc: Mario Limonciello <mario.limonciello@amd.com>
Cc: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Reviewed-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Signed-off-by: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
[WHAT]
Some fields in struct dc_link_settings and link_training_settings are
not initialized and using them can cause unexpected results.
[HOW]
Initialize struct dc_link_settings and link_training_settings to zero.
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Reviewed-by: Rodrigo Siqueira <rodrigo.siqueira@amd.com>
Signed-off-by: Alex Hung <alex.hung@amd.com>
Signed-off-by: Rodrigo Siqueira <rodrigo.siqueira@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
[Why]
Dropping the entirety of dml2_policy_build_synthetic_soc_states exposes
an issue for states that cannot be filled via bbox_overrides and rely on
the default parameters that may or may not be present depending on the
DM.
For amdgpu_dm this results in missing parameters for most of the struct
in higher states:
- sr_exit_time_us
- sr_enter_plus_exit_time_us
- sr_exit_z8_time_us
- sr_enter_plus_exit_z8_time_us
- urgent_latency_pixel_data_only_us
- urgent_latency_pixel_mixed_with_vm_data_us
- urgent_latency_vm_data_only_us
- dram_clock_change_latency_us
- fclk_change_latency_us
- usr_retraining_latency_us
- writeback_latency_us
- urgent_latency_adjustment_fabric_clock_component_us
- urgent_latency_adjustment_fabric_clock_reference_mhz
- dscclk_mhz
- phyclk_mhz
- phyclk_d18_mhz
- phyclk_d32_mhz
- use_ideal_dram_bw_strobe
[How]
Copy from the first state, applying a minimal policy to set max clocks
for SOC independent values.
Then copy the SOC dependent ones from the states modified by
bbox_overrides.
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Reviewed-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Signed-off-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Signed-off-by: Rodrigo Siqueira <rodrigo.siqueira@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
[WHY]
When effective bandwidth from the SoC is enough to perform SubVP
prefetchs, then DF throttling is not required.
[HOW]
Provide SMU the required clocks for which DF throttling is not required.
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Reviewed-by: Alvin Lee <alvin.lee2@amd.com>
Signed-off-by: Dillon Varone <dillon.varone@amd.com>
Signed-off-by: Rodrigo Siqueira <rodrigo.siqueira@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Source --> DP2.1 MST hub --> DP1.4/2.1 monitor
When change from DP1.4 to DP2.1 from monitor manual, modes higher than
4k120 are all cutoff by mode validation. Switch back to DP1.4 gets all
the modes up to 4k240 available to be enabled by dsc passthrough.
[why]
Compared to DP1.4 link from hub to monitor, DP2.1 link has larger
full_pbn value that causes overflow in the process of doing conversion
from pbn to kbps.
[how]
Change the data type accordingly to fit into the data limit during
conversion calculation.
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Reviewed-by: Wayne Lin <wayne.lin@amd.com>
Signed-off-by: Fangzhi Zuo <Jerry.Zuo@amd.com>
Signed-off-by: Rodrigo Siqueira <rodrigo.siqueira@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Current driver interface does not allow for flexibility in coexistence
of multiple interface versions, so add support for checking minor
interface revisions and providing appropriate programming.
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Reviewed-by: Alvin Lee <alvin.lee2@amd.com>
Signed-off-by: Dillon Varone <dillon.varone@amd.com>
Signed-off-by: Rodrigo Siqueira <rodrigo.siqueira@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Driver has different ways to fetch VBIOS. If one of the methods doesn't
find an authentic one, it will show misleading info messages eventhough
a subsequent method finds a valid VBIOS. Keep the message level at debug
and add device context.
Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Since 2320c9e6a7 ("drm/sched: memset() 'job' in drm_sched_job_init()")
accessing job->base.sched can produce unexpected results as the initialisation
of (*job)->base.sched done in amdgpu_job_alloc is overwritten by the
memset.
This commit fixes an issue when a CS would fail validation and would
be rejected after job->num_ibs is incremented. In this case,
amdgpu_ib_free(ring->adev, ...) will be called, which would crash the
machine because the ring value is bogus.
To fix this, pass a NULL pointer to amdgpu_ib_free(): we can do this
because the device is actually not used in this function.
The next commit will remove the ring argument completely.
Fixes: 2320c9e6a7 ("drm/sched: memset() 'job' in drm_sched_job_init()")
Signed-off-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Add support for the drm_panic module, which displays a pretty user
friendly message on the screen when a Linux kernel panic occurs.
Adapt Lu Yao's code to use common helpers derived from
Jocelyn's patch. This extends the non-DC code to enable
access to non-CPU accessible VRAM and adds support for
other DCE versions.
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: Lu Yao <yaolu@kylinos.cn>
Cc: Jocelyn Falempe <jfalempe@redhat.com>
Cc: Harry Wentland <harry.wentland@amd.com>
Add support for the drm_panic module, which displays a pretty user
friendly message on the screen when a Linux kernel panic occurs.
It doesn't work yet on laptop panels, maybe due to PSR.
Adapted from Jocelyn's original patch to add DC drm_panic
support.
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Jocelyn Falempe <jfalempe@redhat.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: Lu Yao <yaolu@kylinos.cn>
Cc: Jocelyn Falempe <jfalempe@redhat.com>
Cc: Harry Wentland <harry.wentland@amd.com>
- The previous patch only considered the case for baremetal
and is not applicable for SRIOV code path. We also need to
init fw_share for SRIOV VF
Fixes: 928cd772e1 ("drm/amdgpu/vcn: reset fw_shared when VCPU buffers corrupted on vcn v4.0.3")
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Bokun Zhang <bokun.zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
