[PULL] drm-intel-gt-next

Joonas Lahtinen <joonas.lahtinen@xxxxxxxxxxxxxxx> · Fri, 6 Aug 2021 13:06:17 +0300

Hi Dave & Daniel,

Sorry for the big PR in advance. Had the summer vacations and did not
notice until tool late how many patches were in already before leaving.

As requested, there is a lot of refactoring to increase the use of TTM
allocator and prep for DRM scheduler. Note that at times the patches trade
simplicity for performance and revert optimizations not seen as critical.
So some performance regressions are expected.

As an example is dropping of faster GPU relocation path for older platforms,
which should be mitigated by updating to the latest UMD versions to regain
the perf.

This PR drops various bits of uAPI where userspace has dropped the ball after reviews
have been completed on both sides (Thanks Jason for doing the due-diligence!). [1]
Due to the complexity of tracing back who used what, I think we could do better in the
future to avoid such situations to begin with. See below for my suggestion [2].

In addition to the refactoring and uAPI cleanup there is preliminay code for
ADL-P/XeHP and DG2 platforms. Fixes for ADL-S and removal of CNL code.
A couple of fixes that have been Cc: stable already. Removing unnecessary
workarounds per stepping and adding missing for Gen12 iGFX.

I915_MMAP_OFFSET_FIXED is also added to to align with the static/fixed caching
mode per BO instead of per-mapping mode (for dGFX only). There is GuC firmware
interface update and backend code major rework that unblock enabling GuC on Gen11
(not on by default). Then there is the addition of the GuCRC power management
feature which can be enabled for Gen12+ when submission is enabled.

Then there is finally the drm-next backmerge and 3 topic branch merges.

I think that is mostly all. I tried to summarize much in the tag description so
it should hopefully not be horribly long...

Regards, Joonas

[1] Given that Jason is only human and there is no way to automate this analysis, we
may have to bring something back as fixes if we find breakage (like with the MMAP IOCTL).

[2] As we first require to merge the kernel code, should we introduce some further rules
that the userspace has to land their code before the final kernel version release? If
that is not followed through, we would neuter the new uAPI with as small patch as possible
in the final release candidate and then remove it in next release. Thoughts?

***

drm-intel-gt-next-2021-08-06-1:

UAPI Changes:

- Add I915_MMAP_OFFSET_FIXED

  On devices with local memory `I915_MMAP_OFFSET_FIXED` is the only valid
  type. On devices without local memory, this caching mode is invalid.

  As caching mode when specifying `I915_MMAP_OFFSET_FIXED`, WC or WB will
  be used, depending on the object placement on creation. WB will be used
  when the object can only exist in system memory, WC otherwise.

  Userspace: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11888

- Reinstate the mmap ioctl for (already released) integrated Gen12 platforms

  Rationale: Otherwise media driver breaks eg. for ADL-P. Long term goal is
  still to sunset the IOCTL even for integrated and require using mmap_offset.

- Reject caching/set_domain IOCTLs on discrete

  Expected to become immutable property of the BO

- Disallow changing context parameters after first use on Gen12 and earlier
- Require setting context parameters at creation on platforms after Gen12

  Rationale (for both): Allow less dynamic changes to the context to simplify
  the implementation and avoid user shooting theirselves in the foot.

- Drop I915_CONTEXT_PARAM_RINGSIZE

  Userspace PR for compute-driver has not been merged

- Drop I915_CONTEXT_PARAM_NO_ZEROMAP

  Userspace PR for libdrm / Beignet was never landed

- Drop CONTEXT_CLONE API

  Userspace PR for Mesa was never landed

- Drop getparam support for I915_CONTEXT_PARAM_ENGINES

  Only existed for symmetry wrt. setparam, never used.

- Disallow bonding of virtual engines

  Drop the prep work, no hardware has been released needing it.

- (Implicit) Disable gpu relocations

  Media userspace was the last userspace to still use them. They
  have converted so performance can be regained with an update.

Core Changes:

- Merge topic branch 'topic/i915-ttm-2021-06-11' (from Maarten)
- Merge topic branch 'topic/revid_steppings' (from Matt R)
- Merge topic branch 'topic/xehp-dg2-definitions-2021-07-21' (from Matt R)
- Backmerges drm-next (Rodrigo)

Driver Changes:

- Initial workarounds for ADL-P (Clint)
- Preliminary code for XeHP/DG2 (Stuart, Umesh, Matt R, Prathap, Ram,
  Venkata, Akeem, Tvrtko, John, Lucas)
- Fix ADL-S DMA mask size to 39 bits (Tejas)
- Remove code for CNL (Lucas)
- Add ADL-P GuC/HuC firmwares (John)
- Update HuC to 7.9.3 for TGL/ADL-S/RKL (John)
- Fix -EDEADLK handling regression (Ville)
- Implement Wa_1508744258 for DG1 and Gen12 iGFX (Jose)
- Extend Wa_1406941453 to ADL-S (Jose)
- Drop unnecessary workarounds per stepping for SKL/BXT/ICL (Matt R)
- Use fuse info to enable SFC on Gen12 (Venkata)
- Unconditionally flush the pages on acquire on EHL/JSL (Matt A)
- Probe existence of backing struct pages upon userptr creation (Chris, Matt A)

- Add an intermediate GEM proto-context to delay real context creation (Jason)
- Implement SINGLE_TIMELINE with a syncobj (Jason)
- Set the watchdog timeout directly in intel_context_set_gem (Jason)
- Disallow userspace from creating contexts with too many engines (Jason)
- Revert "drm/i915/gem: Asynchronous cmdparser" (Jason)
- Revert "drm/i915: Propagate errors on awaiting already signaled fences" (Jason)
- Revert "drm/i915: Skip over MI_NOOP when parsing" (Jason)
- Revert "drm/i915: Shrink the GEM kmem_caches upon idling" (Daniel)
- Always let TTM handle object migration (Jason)
- Correct the locking and pin pattern for dma-buf (Thomas H, Michael R, Jason)
- Migrate to system at dma-buf attach time (Thomas, Michael R)

- MAJOR refactoring of the GuC backend code to allow for enabling on Gen11+
  (Matt B, John, Michal Wa., Fernando, Daniele, Vinay)
- Update GuC firmware interface to v62.0.0 (John, Michal Wa., Matt B)
- Add GuCRC feature to hand over the control of HW RC6 to the GuC on
  Gen12+ when GuC submission is enabled (Vinay, Sujaritha, Daniele,
  John, Tvrtko)
- Use the correct IRQ during resume and eliminate DRM IRQ midlayer (Thomas Z)
- Add pipelined page migration and clearing (Chris, Thomas H)
- Use TTM for system memory on discrete (Thomas H)
- Implement object migration for display vs. dma-buf (Thomas H)
- Perform execbuffer object locking as a separate step (Thomas H)
- Add support for explicit L3BANK steering (Matt, Daniele)
- Remove duplicated call to ops->pread (Daniel)
- Fix pagefault disabling in the first execbuf slowpath (Daniel)
- Simplify userptr locking (Thomas H)
- Improvements to the GuC CTB code (Matt B, John)
- Make GT workaround upper bounds exclusive (Matt R)
- Check for nomodeset in i915_init() first (Daniel)
- Delete now unused gpu reloc code (Daniel)

- Document RFC plans for GuC submission, DRM scheduler and new parallel
  submit uAPI (Matt B)
- Reintroduce buddy allocator this time with TTM (Matt A)
- Support forcing page size with LMEM (Matt A)
- Add i915_sched_engine to abstract a submission queue between backends (Matt B)
- Use accelerated move in TTM (Ram)
- Fix memory leaks from TTM backend (Thomas H)
- Introduce WW transaction helper (Thomas H)
- Improve debug Kconfig texts a bit (Daniel)
- Unify user object creation code (Jason)
- Use a table for i915_init/exit (Jason)
- Move slabs to module init/exit (Daniel)
- Remove now unused i915_globals (Daniel)
- Extract i915_module.c (Daniel)

- Consistently use adl-p/adl-s in WA comments (Jose)
- Finish INTEL_GEN and friends conversion (Lucas)
- Correct variable/function namings (Lucas)
- Code checker fixes (Wan, Matt A)
- Tracepoint improvements (Matt B)
- Kerneldoc improvements (Tvrtko, Jason, Matt A, Maarten)
- Selftest improvements (Chris, Matt A, Tejas, Thomas H, John, Matt B,
  Rahul, Vinay)
The following changes since commit e73f0f0ee7541171d89f2e2491130c7771ba58d3:

  Linux 5.14-rc1 (2021-07-11 15:07:40 -0700)

are available in the Git repository at:

  git://anongit.freedesktop.org/drm/drm-intel tags/drm-intel-gt-next-2021-08-06-1

for you to fetch changes up to 927dfdd09d8c03ba100ed0c8c3915f8e1d1f5556:

  drm/i915/dg2: Add SQIDI steering (2021-08-05 08:07:25 -0700)

----------------------------------------------------------------
UAPI Changes:

- Add I915_MMAP_OFFSET_FIXED