For saving switch state, check if the GPU is having SWUS/DS
architecture. Otherwise, skip saving.
Reported-by: Roman Elshin <roman.elshin@gmail.com>
Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/4602
Fixes: 1dd2fa0e00 ("drm/amdgpu: Save and restore switch state")
Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Queue read and write pointers are "to KFD", not "from KFD".
Suggested-by: Robert Liu <robert.liu@amd.com>
Signed-off-by: Felix Kuehling <felix.kuehling@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Robert Liu <robert.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
PMFW interface version is not used by some IP implementations like SMU
v13.0.6/12, instead rely on PMFW version checks. Avoid the log if
interface version is not used.
Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Asad Kamal <asad.kamal@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
As KFD no longer uses a separate PASID, the global amdgpu_vm_set_pasid()function is no longer necessary.
Merge its functionality directly intoamdgpu_vm_init() to simplify code flow and eliminate redundant locking.
v2: remove superflous check
adjust amdgpu_vm_fin and remove amdgpu_vm_set_pasid (Chritian)
v3: drop amdgpu_vm_assert_locked (Chritian)
Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/4614
Fixes: 59e4405e9e ("drm/amdgpu: revert to old status lock handling v3")
Reviewed-by: Christian König <christian.koenig@amd.com>
Suggested-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Jesse Zhang <Jesse.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
MES version 0x83 is not stable to use the inv_tlbs API. Defer it to 0x84 vertsion.
Fixes: 85442bac84 ("drm/amd/amdgpu: Fix the mes version that support inv_tlbs")
Signed-off-by: Shaoyun Liu <shaoyun.liu@amd.com>
Reviewed-by: Michael Chen <michael.chen@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
[Why]
Not all renoir hardware supports secure display. If the TA is present
but the feature isn't supported it will fail to load or send commands.
This shows ERR messages to the user that make it seems like there is
a problem.
[How]
Check the resp_status of the context to see if there was an error
before trying to send any secure display commands.
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/1415
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
If mmap write lock is taken while draining retry fault, mmap write lock
is not released because svm_range_restore_pages calls mmap_read_unlock
then returns. This causes deadlock and system hangs later because mmap
read or write lock cannot be taken.
Downgrade mmap write lock to read lock if draining retry fault fix this
bug.
Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Reviewed-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
kfd_lookup_process_by_pid hold the kfd process reference to ensure it
doesn't get destroyed while sending the segfault event to user space.
Calling kfd_lookup_process_by_pid as function parameter leaks the kfd
process refcount and miss the NULL pointer check if app process is
already destroyed.
Fixes: 2d274bf709 ("amd/amdkfd: Trigger segfault for early userptr unmmapping")
Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Reviewed-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
There is some probability that reset workqueue is blocked by KIQ I/O for 10+ seconds after gpu hangs.
So we need to add a in_reset check during each KIQ register poll.
Signed-off-by: Heng Zhou <Heng.Zhou@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Scaling doesn't work on DCE6 at the moment, the current
register programming produces incorrect output when using
fractional scaling (between 100-200%) on resolutions higher
than 1080p.
Disable it until we figure out how to program it properly.
Fixes: 7c15fd86aa ("drm/amd/display: dc/dce: add initial DCE6 support (v10)")
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
SCL_SCALER_ENABLE can be used to enable/disable the scaler
on DCE6. Program it to 0 when scaling isn't used, 1 when used.
Additionally, clear some other registers when scaling is
disabled and program the SCL_UPDATE register as recommended.
This fixes visible glitches for users whose BIOS sets up a
mode with scaling at boot, which DC was unable to clean up.
Fixes: b70aaf5586 ("drm/amd/display: dce_transform: add DCE6 specific macros,functions")
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Previously, the code would set a bit field which didn't exist
on DCE6 so it would be effectively a no-op.
Fixes: b70aaf5586 ("drm/amd/display: dce_transform: add DCE6 specific macros,functions")
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Without these, it's impossible to program these registers.
Fixes: 102b2f587a ("drm/amd/display: dce_transform: DCE6 Scaling Horizontal Filter Init (v2)")
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This tag contains habanalabs driver changes for v6.18.
It continues the previous upstream work from tags/drm-habanalabs-next-2024-06-23,
Including improvements in debug and visibility, alongside general code cleanups,
and new features such as vmalloc-backed coherent mmap, HLDIO infrastructure, etc.
Signed-off-by: Dave Airlie <airlied@redhat.com>
From: "Elbaz, Koby" <koby.elbaz@intel.com>
Link: https://lore.kernel.org/r/da02d370-9967-49d2-9eef-7aeaa40c987c@intel.com
[Why]
When DC adds common modes it adds modes with a string to match what
they are. Non-DC doesn't. This can be inconsistent when turning on/off
DC support.
[How]
Add a name member to common_modes[] and copy it into the drm display
mode.
Cc: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Link: https://lore.kernel.org/r/20250924161624.1975819-6-mario.limonciello@amd.com
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
[Why]
DC and non-DC codepaths have different sets of common modes that are
added for eDP and LVDS cases. This can cause different behaviors for
turning on DC on hardware that can support both.
[How]
Drop extra modes from amdgpu_connector_add_common_modes() not present
in amdgpu_dm_connector_add_common_modes().
Cc: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Link: https://lore.kernel.org/r/20250924161624.1975819-5-mario.limonciello@amd.com
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
[Why]
Adding or removing a mode from common_modes[] can be fragile if a user
forgot to update the for loop boundaries.
[How]
Use ARRAY_SIZE() to detect size of the array and use that instead.
Cc: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Link: https://lore.kernel.org/r/20250924161624.1975819-4-mario.limonciello@amd.com
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
The dce100_validate_global function was verbatim exactly the
same as dce60_validate_global and dce80_validate_global.
Share dce100_validate_global between DCE6-10 to save code size.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
DCE6-8 have very similar capabilities to DCE10, they support the
same DP and HDMI versions and work similarly.
Share dce100_validate_bandwidth between DCE6-10 to reduce code
duplication in the DC driver.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit fixes a potential race condition in the userqueue fence
signaling mechanism by replacing dma_fence_is_signaled_locked() with
dma_fence_is_signaled().
The issue occurred because:
1. dma_fence_is_signaled_locked() should only be used when holding
the fence's individual lock, not just the fence list lock
2. Using the locked variant without the proper fence lock could lead
to double-signaling scenarios:
- Hardware completion signals the fence
- Software path also tries to signal the same fence
By using dma_fence_is_signaled() instead, we properly handle the
locking hierarchy and avoid the race condition while still maintaining
the necessary synchronization through the fence_list_lock.
v2: drop the comment (Christian)
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Jesse Zhang <Jesse.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Reject modes with a pixel clock higher than the maximum display
clock. Use 400 MHz as a fallback value when the maximum display
clock is not known. Pixel clocks that are higher than the display
clock just won't work and are not supported.
With the addition of the YUV422 fallback, DC can now accidentally
select a mode requiring higher pixel clock than actually supported
when the DP version supports the required bandwidth but the clock
is otherwise too high for the display engine. DCE 6-10 don't
support these modes but they don't have a bandwidth calculation
to reject them properly.
Fixes: db291ed173 ("drm/amd/display: Add fallback path for YCBCR422")
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
[Why]
amdgpu_connector_add_common_modes() has a check for the width and height
of common modes being too small, but the array of common_modes[] has fixed
values. The check is dead code.
[How]
Drop unnecessary check.
Cc: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Link: https://lore.kernel.org/r/20250924161624.1975819-3-mario.limonciello@amd.com
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
[Why]
The main reason common modes are added is for compatibility with
clone mode when a laptop is connected to a projector or external
monitor. Since commit 978fa2f6d0 ("drm/amd/display: Use scaling
for non-native resolutions on eDP") when non-native modes are picked
for eDP the GPU scalar will be used. This is because it is inconsistent
whether eDP panels have the capability to actually drive non-native
resolutions. With panels connected to other connectors this limitation
generally doesn't exist as we the EDID will advertise support for a
number of resolutions and monitors will use built in scaling hardware.
Comparing DC and non-DC code paths the non-DC code path only adds
common modes for LVDS and eDP whereas the DC codepath does it for
all connector types.
In the past there was an experiment done to disable common mode adding
for eDP and LVDS from commit 6d396e7ac1 ("drm/amd/display: Disable
common modes for LVDS") and commit 7948afb46a ("drm/amd/display:
Disable common modes for eDP") but this was reverted in
commit a8b79b0918 ("drm/amd: Re-enable common modes for eDP and
LVDS") because it caused problems with Xorg.
[How]
Only add common modes for eDP and LVDS for DC, matching the behavior
of non-DC.
Suggested-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Link: https://lore.kernel.org/r/20250924161624.1975819-2-mario.limonciello@amd.com
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Variable "i" has been redeclared as integer later in the function
which is wrong and not serving any purpose.
Fixes: 899fbde146 ("drm/amdgpu: replace get_user_pages with HMM mirror helpers")
Signed-off-by: Sunil Khatri <sunil.khatri@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
It should return an error code if userq VA validation fails.
Fixes: 9e46b8bb05 ("drm/amdgpu: validate userq buffer virtual address and size")
Signed-off-by: Prike Liang <Prike.Liang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This reverts commit e44a0fe630.
Initially we used VMID reservation to enforce isolation between
processes. That has now been replaced by proper fence handling.
Both OpenGL, RADV and ROCm developers requested a way to reserve a VMID
for SPM, so restore that approach by reverting back to only allowing a
single process to use the reserved VMID.
Only compile tested for now.
v2: use -ENOENT instead of -EINVAL if VMID is not available
Signed-off-by: Christian König <christian.koenig@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Initially we enforced isolation by reserving a VMID, but that practice
was now removed.
Signed-off-by: Christian König <christian.koenig@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Add a fallback mechanism to attempt pipe reset when KCQ reset
fails to recover the ring. After performing the KCQ reset and
queue remapping, test the ring functionality. If the ring test
fails, initiate a pipe reset as an additional recovery step.
v2: fix the typo (Lijo)
v3: try pipeline reset when kiq mapping fails (Lijo)
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Jesse Zhang <Jesse.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
On HL338 ASICs, the Infineon first‑stage firmware is not present and
the reported version is 0. In this case printing a version number is
misleading, as it suggests valid firmware when it does not exist.
Fix this by printing the first‑stage Infineon firmware version only
if the reported value is non‑zero. This avoids confusing or incorrect
log messages on devices where the first stage is not applicable.
Signed-off-by: Pavan S <pavan.sreenivas@intel.com>
Reviewed-by: Koby Elbaz <koby.elbaz@intel.com>
Signed-off-by: Koby Elbaz <koby.elbaz@intel.com>
Dirty state can occur when the host VM undergoes a reset while the
device does not. In such a case, the driver must reset the device before
it can be used again. As part of this reset, the device capabilities
are zeroed. Therefore, the driver must read the Preboot status again to
learn the Preboot state, capabilities, and security configuration.
Signed-off-by: Konstantin Sinyuk <konstantin.sinyuk@intel.com>
Reviewed-by: Koby Elbaz <koby.elbaz@intel.com>
Signed-off-by: Koby Elbaz <koby.elbaz@intel.com>
Add a new passthrough type HL_GET_P_STATE to the cpucp generic ioctl
to allow userspace to read the device performance state via firmware.
Signed-off-by: Ariel Aviad <ariel.aviad@intel.com>
Reviewed-by: Koby Elbaz <koby.elbaz@intel.com>
Signed-off-by: Koby Elbaz <koby.elbaz@intel.com>
Introduce NVMe Direct I/O (HLDIO) infrastructure to support
peer‑to‑peer DMA in the habanalabs driver. This adds internal helpers
and data structures to enable direct transfers between NVMe storage
and device memory.
The feature is built only when CONFIG_HL_HLDIO is enabled. A debugfs
interface is also provided for functional validation.
Signed-off-by: Konstantin Sinyuk <konstantin.sinyuk@intel.com>
Reviewed-by: Farah Kassabri <farah.kassabri@intel.com>
Reviewed-by: Koby Elbaz <koby.elbaz@intel.com>
Signed-off-by: Koby Elbaz <koby.elbaz@intel.com>
When IOMMU is enabled, dma_alloc_coherent() with GFP_USER may return
addresses from the vmalloc range. If such an address is mapped without
VM_MIXEDMAP, vm_insert_page() will trigger a BUG_ON due to the
VM_PFNMAP restriction.
Fix this by checking for vmalloc addresses and setting VM_MIXEDMAP
in the VMA before mapping. This ensures safe mapping and avoids kernel
crashes. The memory is still driver-allocated and cannot be accessed
directly by userspace.
Signed-off-by: Moti Haimovski <moti.haimovski@intel.com>
Reviewed-by: Koby Elbaz <koby.elbaz@intel.com>
Signed-off-by: Koby Elbaz <koby.elbaz@intel.com>
The access_ok() API no longer requires the VERIFY_WRITE argument,
and the use of the old interface with VERIFY_WRITE is deprecated.
Clean up the habanalabs memory manager to use the modern access_ok()
interface consistently. This removes old #ifdef guards and aligns the
driver with current upstream kernel APIs.
Signed-off-by: Ilia Levi <ilia.levi@intel.com>
Reviewed-by: Koby Elbaz <koby.elbaz@intel.com>
Signed-off-by: Koby Elbaz <koby.elbaz@intel.com>
After CPLD shutdown event the device is not usable anymore. The common
CPLD_SHUTDOWN event handler disables any subsequent device access.
Signed-off-by: Konstantin Sinyuk <konstantin.sinyuk@intel.com>
Reviewed-by: Koby Elbaz <koby.elbaz@intel.com>
Signed-off-by: Koby Elbaz <koby.elbaz@intel.com>
After a CPLD shutdown event the device becomes unusable. Prevent further
device access once this event is received.
Signed-off-by: Konstantin Sinyuk <konstantin.sinyuk@intel.com>
Reviewed-by: Koby Elbaz <koby.elbaz@intel.com>
Signed-off-by: Koby Elbaz <koby.elbaz@intel.com>
In hl_release_dmabuf(), ctx is dereferenced after calling hl_ctx_put()
to obtain the compute device file.
This is safe because the dma-buf object holds a file reference taken in
export_dmabuf(), and the file release (which drops another ctx reference)
can only happen after we drop that file reference via fput(). Thus, this
hl_ctx_put() call cannot be the last one at this point.
Add a comment explaining this to avoid confusion.
Signed-off-by: Tomer Tayar <tomer.tayar@intel.com>
Reviewed-by: Koby Elbaz <koby.elbaz@intel.com>
Signed-off-by: Koby Elbaz <koby.elbaz@intel.com>
Add infrastructure for logging the last configuration register accesses
that occur via debugfs read/write operations. At interrupt time, these
log entries can be dumped to dmesg, which helps in diagnosing the cause
of RAZWI and ADDR_DEC interrupts.
The logging is implemented as a ring buffer of access entries, with each
entry recording timestamp and access details. To ensure correctness
under concurrent access, operations are now protected using spinlocks.
Entries are copied under lock and then printed after releasing it, which
minimizes time spent in the critical section.
Signed-off-by: Sharley Calzolari <sharley.calzolari@intel.com>
Reviewed-by: Koby Elbaz <koby.elbaz@intel.com>
Signed-off-by: Koby Elbaz <koby.elbaz@intel.com>
Add a new CPUCP generic message type to retrieve HBM, SRAM and critical
error counters from the device.
Signed-off-by: Vitaly Margolin <vitaly.margolin@intel.com>
Reviewed-by: Koby Elbaz <koby.elbaz@intel.com>
Signed-off-by: Koby Elbaz <koby.elbaz@intel.com>
Change the BMON_CR register value back to its original state before
enabling, so that BMON does not continue to collect information
after being disabled.
Signed-off-by: Vered Yavniely <vered.yavniely@intel.com>
Reviewed-by: Koby Elbaz <koby.elbaz@intel.com>
Signed-off-by: Koby Elbaz <koby.elbaz@intel.com>
EFAULT is currently returned if less than requested user pages are
pinned. This value means a "bad address" which might be confusing to
the user, as the address of the given user memory is not necessarily
"bad".
Modify the return value to ENOMEM, as "out of memory" is more suitable
in this case.
Signed-off-by: Tomer Tayar <tomer.tayar@intel.com>
Reviewed-by: Koby Elbaz <koby.elbaz@intel.com>
Signed-off-by: Koby Elbaz <koby.elbaz@intel.com>
