cgroup resource allocation has to be handled in TTM, so -EAGAIN from
cgroups can be converted into -ENOSPC, and the limitcg can be properly
evicted in ttm code.
When hitting a resource limit through -EAGAIN, the cgroup for which the
limit is hit is also returned. This allows eviction to delete only from
cgroups which are a subgroup of the current cgroup.
The returned CSS is used to determine if eviction is valuable for a
given resource, and allows TTM to only target specific resources to
lower memory usage.
Co-developed-by: Friedrich Vock <friedrich.vock@gmx.de>
Signed-off-by: Friedrich Vock <friedrich.vock@gmx.de>
Co-developed-by: Maxime Ripard <mripard@kernel.org>
Signed-off-by: Maarten Lankhorst <dev@lankhorst.se>
Acked-by: Tejun Heo <tj@kernel.org>
Link: https://lore.kernel.org/r/20241204134410.1161769-4-dev@lankhorst.se
Signed-off-by: Maxime Ripard <mripard@kernel.org>
Driver Changes:
- Some DG2 refactor to fix DG2 bugs when operating with certain CPUs (Raag)
- Use hw support for min/interim ddb allocation for async flip (Vinod)
- More general code refactor to allow full display separation (Jani)
- Expose dsc sink max slice count via debugfs (Swati)
- Fix C10 pll programming sequence (Suraj)
- Fix DG1 power gate sequence (Rodrigo)
- Use preemption timeout on selftest cleanup (Janusz)
- DP DSC related fixes (Ankit)
- Fix HDCP compliance test (Suraj)
- Clean and Optimise mtl_ddi_prepare_link_retrain (Suraj)
- Adjust Added Wake Time with PKG_C_LATENCY (Animesh)
- Enabling uncompressed 128b/132b UHBR SST (Jani)
- Handle hdmi connector init failures, and no HDMI/DP cases (Jani)
Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/Z31_WPbBoHkwgEA9@intel.com
Enable basic 128b/132b SST functionality without compression. Reuse
intel_dp_mtp_tu_compute_config() to figure out the TU after we've
determined we need to use an UHBR rate.
It's slightly complicated as the M/N computation is done in different
places in MST and SST paths, so we need to avoid trashing the values
later for UHBR.
If uncompressed UHBR fails, we drop to compressed non-UHBR, which is
quite likely to fail as well. We still lack 128b/132b SST+DSC.
We need mst_master_transcoder also for 128b/132b SST. Use cpu_transcoder
directly. Enhanced framing is "don't care" for 128b/132b link.
v2: mst_master_transcoder, enhanced framing (Imre)
Reviewed-by: Imre Deak <imre.deak@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/084e4e05bf25a5dd396dd391014943d42b11c88d.1735912293.git.jani.nikula@intel.com
We'll want to distinguish 128b/132b SST and MST modes at state
readout. There's a catch, though. From the hardware perspective,
128b/132b SST and MST programming are pretty much the same. And we can't
really ask the sink at this point.
If we have more than one transcoder in 128b/132b mode associated with
the port, we can safely assume it's MST. But for MST with only a single
stream enabled, we are pretty much out of luck. Let's fall back to
looking at the software state, i.e. intel_dp->is_mst. It should be fine
for the state checker, but for hardware takeover at probe, we'll have to
trust the GOP has only enabled SST.
TODO: Not sure how this *or* our current code handles 128b/132b enabled
by GOP.
Cc: Imre Deak <imre.deak@intel.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Imre Deak <imre.deak@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/119a773a0d4d74ad204435e462f8d12cb0ea4128.1735912293.git.jani.nikula@intel.com
Write the payload allocation table for 128b/132b SST. Use VCPID 1 and
start from slot 0, with dp_m_n.tu slots.
This is preparation for enabling 128b/132b SST. This path is not
reachable yet. Indeed, we don't yet compute TU for 128b/132b SST.
v2: Handle drm_dp_dpcd_write_payload() failures (Imre)
v3: Include drm_dp_helper.h (kernel test robot)
Reviewed-by: Imre Deak <imre.deak@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250107095414.1244286-1-jani.nikula@intel.com
The struct drm_dp_mst_topology_mgr *mgr parameter is only used for debug
logging in case the passed in link rate or lane count are zero. There's
no further error checking as such, and the function returns 0.
There should be no case where the parameters are zero. The returned
value is generally used as a divisor, and if we were hitting this, we'd
be seeing division by zero.
Just remove the debug logging altogether, along with the mgr parameter,
so that the function can be used in non-MST contexts without the
topology manager.
v2: Also remove drm_dp_mst_helper_tests_init as unnecessary (Imre)
Cc: Imre Deak <imre.deak@intel.com>
Cc: Lyude Paul <lyude@redhat.com>
Reviewed-by: Imre Deak <imre.deak@intel.com>
Acked-by: Maxime Ripard <mripard@kernel.org>
Acked-by: Thomas Zimmermann <tzimmermann@suse.de>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/72d77e7a7fe69c784e9df048b7e6f250fd7599e4.1735912293.git.jani.nikula@intel.com
Core Changes:
- drm/print: add drm_print_hex_dump()
Driver Changes:
- HDCP fixes and updates for Xe3lpd and for HDCP 1.4 (Suraj)
- Add dedicated lock for each sideband (Jani)
- New GSC FW for ARL-H and ARL-U (Daniele)
- Add support for 3 VDSC engines 12 slices (Ankit)
- Sanitize MBUS joining (Ville)
- Fixes in DP MST (Imre)
- Stop using pixel_format_from_register_bits() to parse VBT (Ville)
- Declutter CDCLK code (Ville)
- PSR clean up and fixes (Jouni, Jani, Animesh)
- DMC wakelock - Fixes and enablement for Xe3_LPD (Gustavo)
- Demote source OUI read/write failure logging to debug (Jani)
- Potential boot oops fix and some general cleanups (Ville)
- Scaler code cleanups (Ville)
- More conversion towards struct intel_display and general cleanups (Jani)
- Limit max compressed bpp to 18 when forcing DSC (Ankit)
- Start to reconcile i915's and xe's display power mgt sequences (Rodrigo)
- Some correction in the DP Link Training sequence (Arun)
- Avoid setting YUV420_MODE in PIPE_MISC on Xe3lpd (Ankit)
- MST and DDI cleanups and refactoring (Jani)
- Fixed an typo in i915_gem_gtt.c (Zhang)
- Try to make DPT shrinkable again (Ville)
- Try to fix CPU MMIO fails during legacy LUT updates (Ville)
- Some PPS cleanups (Ville, Jani)
- Use seq buf for printing rates (Jani)
- Flush DMC wakelock release work at the end of runtime suspend (Gustavo)
- Fix NULL pointer dereference in capture_engine (Eugene)
- Fix memory leak by correcting cache object name in error handler (Jiasheng)
- Small refactor in WM/DPKGC for modifying latency programmed into PKG_C_LATENCY (Suraj)
- Add drm_printer based hex dumper and use it (Jani)
- Move g4x code to specific g4x functions (Jani)
Signed-off-by: Simona Vetter <simona.vetter@ffwll.ch>
From: Rodrigo Vivi <rodrigo.vivi@intel.com>
[sima: conflict in intel_dp_mst.c due to conversion to
drm_connector_dynamic_init that landed through drm-misc]
Link: https://patchwork.freedesktop.org/patch/msgid/Z1n4VhatZpvT5xKs@intel.com
Currently, when bandwidth is insufficient for a given mode, we attempt
to use DSC. This is indicated by a debug print, followed by a check for
DSC support.
The debug message states that we are trying DSC, but DSC might not be
supported, which can give an incorrect picture in the logs if we bail
out later.
Correct the order for both DP and DP MST to:
- Check if DSC is required and supported, and return early if DSC is
not supported.
- Print a debug message to indicate that DSC will be tried next.
Suggested-by: Jani Nikula <jani.nikula@linux.intel.com>
Signed-off-by: Ankit Nautiyal <ankit.k.nautiyal@intel.com>
Reviewed-by: Suraj Kandpal <suraj.kandpal@intel.com>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250103031424.1732774-1-ankit.k.nautiyal@intel.com
This code is based on the RDMA and misc cgroup initially, but now
uses page_counter. It uses the same min/low/max semantics as the memory
cgroup as a result.
There's a small mismatch as TTM uses u64, and page_counter long pages.
In practice it's not a problem. 32-bits systems don't really come with
>=4GB cards and as long as we're consistently wrong with units, it's
fine. The device page size may not be in the same units as kernel page
size, and each region might also have a different page size (VRAM vs GART
for example).
The interface is simple:
- Call dmem_cgroup_register_region()
- Use dmem_cgroup_try_charge to check if you can allocate a chunk of memory,
use dmem_cgroup__uncharge when freeing it. This may return an error code,
or -EAGAIN when the cgroup limit is reached. In that case a reference
to the limiting pool is returned.
- The limiting cs can be used as compare function for
dmem_cgroup_state_evict_valuable.
- After having evicted enough, drop reference to limiting cs with
dmem_cgroup_pool_state_put.
This API allows you to limit device resources with cgroups.
You can see the supported cards in /sys/fs/cgroup/dmem.capacity
You need to echo +dmem to cgroup.subtree_control, and then you can
partition device memory.
Co-developed-by: Friedrich Vock <friedrich.vock@gmx.de>
Signed-off-by: Friedrich Vock <friedrich.vock@gmx.de>
Co-developed-by: Maxime Ripard <mripard@kernel.org>
Signed-off-by: Maarten Lankhorst <dev@lankhorst.se>
Acked-by: Tejun Heo <tj@kernel.org>
Link: https://lore.kernel.org/r/20241204143112.1250983-1-dev@lankhorst.se
Signed-off-by: Maxime Ripard <mripard@kernel.org>
