All of lore.kernel.org
 help / color / mirror / Atom feed
* [PATCH 01/11] drm/amdgpu: Comply with implicit fencing rules
@ 2021-05-21  9:09 ` Daniel Vetter
  0 siblings, 0 replies; 175+ messages in thread
From: Daniel Vetter @ 2021-05-21  9:09 UTC (permalink / raw)
  To: DRI Development
  Cc: Rob Clark, Daniel Stone, Christian König, Daniel Vetter,
	Daniel Vetter, Intel Graphics Development, Kevin Wang,
	linaro-mm-sig, Luben Tuikov, Kristian H . Kristensen, Chen Li,
	Alex Deucher, mesa-dev, Michel Dänzer, Dennis Li,
	Deepak R Varma

Docs for struct dma_resv are fairly clear:

"A reservation object can have attached one exclusive fence (normally
associated with write operations) or N shared fences (read
operations)."

https://dri.freedesktop.org/docs/drm/driver-api/dma-buf.html#reservation-objects

Furthermore a review across all of upstream.

First of render drivers and how they set implicit fences:

- nouveau follows this contract, see in validate_fini_no_ticket()

			nouveau_bo_fence(nvbo, fence, !!b->write_domains);

  and that last boolean controls whether the exclusive or shared fence
  slot is used.

- radeon follows this contract by setting

		p->relocs[i].tv.num_shared = !r->write_domain;

  in radeon_cs_parser_relocs(), which ensures that the call to
  ttm_eu_fence_buffer_objects() in radeon_cs_parser_fini() will do the
  right thing.

- vmwgfx seems to follow this contract with the shotgun approach of
  always setting ttm_val_buf->num_shared = 0, which means
  ttm_eu_fence_buffer_objects() will only use the exclusive slot.

- etnaviv follows this contract, as can be trivially seen by looking
  at submit_attach_object_fences()

- i915 is a bit a convoluted maze with multiple paths leading to
  i915_vma_move_to_active(). Which sets the exclusive flag if
  EXEC_OBJECT_WRITE is set. This can either come as a buffer flag for
  softpin mode, or through the write_domain when using relocations. It
  follows this contract.

- lima follows this contract, see lima_gem_submit() which sets the
  exclusive fence when the LIMA_SUBMIT_BO_WRITE flag is set for that
  bo

- msm follows this contract, see msm_gpu_submit() which sets the
  exclusive flag when the MSM_SUBMIT_BO_WRITE is set for that buffer

- panfrost follows this contract with the shotgun approach of just
  always setting the exclusive fence, see
  panfrost_attach_object_fences(). Benefits of a single engine I guess

- v3d follows this contract with the same shotgun approach in
  v3d_attach_fences_and_unlock_reservation(), but it has at least an
  XXX comment that maybe this should be improved

- v4c uses the same shotgun approach of always setting an exclusive
  fence, see vc4_update_bo_seqnos()

- vgem also follows this contract, see vgem_fence_attach_ioctl() and
  the VGEM_FENCE_WRITE. This is used in some igts to validate prime
  sharing with i915.ko without the need of a 2nd gpu

- vritio follows this contract again with the shotgun approach of
  always setting an exclusive fence, see virtio_gpu_array_add_fence()

This covers the setting of the exclusive fences when writing.

Synchronizing against the exclusive fence is a lot more tricky, and I
only spot checked a few:

- i915 does it, with the optional EXEC_OBJECT_ASYNC to skip all
  implicit dependencies (which is used by vulkan)

- etnaviv does this. Implicit dependencies are collected in
  submit_fence_sync(), again with an opt-out flag
  ETNA_SUBMIT_NO_IMPLICIT. These are then picked up in
  etnaviv_sched_dependency which is the
  drm_sched_backend_ops->dependency callback.

- v4c seems to not do much here, maybe gets away with it by not having
  a scheduler and only a single engine. Since all newer broadcom chips than
  the OG vc4 use v3d for rendering, which follows this contract, the
  impact of this issue is fairly small.

- v3d does this using the drm_gem_fence_array_add_implicit() helper,
  which then it's drm_sched_backend_ops->dependency callback
  v3d_job_dependency() picks up.

- panfrost is nice here and tracks the implicit fences in
  panfrost_job->implicit_fences, which again the
  drm_sched_backend_ops->dependency callback panfrost_job_dependency()
  picks up. It is mildly questionable though since it only picks up
  exclusive fences in panfrost_acquire_object_fences(), but not buggy
  in practice because it also always sets the exclusive fence. It
  should pick up both sets of fences, just in case there's ever going
  to be a 2nd gpu in a SoC with a mali gpu. Or maybe a mali SoC with a
  pcie port and a real gpu, which might actually happen eventually. A
  bug, but easy to fix. Should probably use the
  drm_gem_fence_array_add_implicit() helper.

- lima is nice an easy, uses drm_gem_fence_array_add_implicit() and
  the same schema as v3d.

- msm is mildly entertaining. It also supports MSM_SUBMIT_NO_IMPLICIT,
  but because it doesn't use the drm/scheduler it handles fences from
  the wrong context with a synchronous dma_fence_wait. See
  submit_fence_sync() leading to msm_gem_sync_object(). Investing into
  a scheduler might be a good idea.

- all the remaining drivers are ttm based, where I hope they do
  appropriately obey implicit fences already. I didn't do the full
  audit there because a) not follow the contract would confuse ttm
  quite well and b) reading non-standard scheduler and submit code
  which isn't based on drm/scheduler is a pain.

Onwards to the display side.

- Any driver using the drm_gem_plane_helper_prepare_fb() helper will
  correctly. Overwhelmingly most drivers get this right, except a few
  totally dont. I'll follow up with a patch to make this the default
  and avoid a bunch of bugs.

- I didn't audit the ttm drivers, but given that dma_resv started
  there I hope they get this right.

In conclusion this IS the contract, both as documented and
overwhelmingly implemented, specically as implemented by all render
drivers except amdgpu.

Amdgpu tried to fix this already in

commit 049aca4363d8af87cab8d53de5401602db3b9999
Author: Christian König <christian.koenig@amd.com>
Date:   Wed Sep 19 16:54:35 2018 +0200

    drm/amdgpu: fix using shared fence for exported BOs v2

but this fix falls short on a number of areas:

- It's racy, by the time the buffer is shared it might be too late. To
  make sure there's definitely never a problem we need to set the
  fences correctly for any buffer that's potentially exportable.

- It's breaking uapi, dma-buf fds support poll() and differentitiate
  between, which was introduced in

	commit 9b495a5887994a6d74d5c261d012083a92b94738
	Author: Maarten Lankhorst <maarten.lankhorst@canonical.com>
	Date:   Tue Jul 1 12:57:43 2014 +0200

	    dma-buf: add poll support, v3

- Christian König wants to nack new uapi building further on this
  dma_resv contract because it breaks amdgpu, quoting

  "Yeah, and that is exactly the reason why I will NAK this uAPI change.

  "This doesn't works for amdgpu at all for the reasons outlined above."

  https://lore.kernel.org/dri-devel/f2eb6751-2f82-9b23-f57e-548de5b729de@gmail.com/

  Rejecting new development because your own driver is broken and
  violates established cross driver contracts and uapi is really not
  how upstream works.

Now this patch will have a severe performance impact on anything that
runs on multiple engines. So we can't just merge it outright, but need
a bit a plan:

- amdgpu needs a proper uapi for handling implicit fencing. The funny
  thing is that to do it correctly, implicit fencing must be treated
  as a very strange IPC mechanism for transporting fences, where both
  setting the fence and dependency intercepts must be handled
  explicitly. Current best practices is a per-bo flag to indicate
  writes, and a per-bo flag to to skip implicit fencing in the CS
  ioctl as a new chunk.

- Since amdgpu has been shipping with broken behaviour we need an
  opt-out flag from the butchered implicit fencing model to enable the
  proper explicit implicit fencing model.

- for kernel memory fences due to bo moves at least the i915 idea is
  to use ttm_bo->moving. amdgpu probably needs the same.

- since the current p2p dma-buf interface assumes the kernel memory
  fence is in the exclusive dma_resv fence slot we need to add a new
  fence slot for kernel fences, which must never be ignored. Since
  currently only amdgpu supports this there's no real problem here
  yet, until amdgpu gains a NO_IMPLICIT CS flag.

- New userspace needs to ship in enough desktop distros so that users
  wont notice the perf impact. I think we can ignore LTS distros who
  upgrade their kernels but not their mesa3d snapshot.

- Then when this is all in place we can merge this patch here.

What is not a solution to this problem here is trying to make the
dma_resv rules in the kernel more clever. The fundamental issue here
is that the amdgpu CS uapi is the least expressive one across all
drivers (only equalled by panfrost, which has an actual excuse) by not
allowing any userspace control over how implicit sync is conducted.

Until this is fixed it's completely pointless to make the kernel more
clever to improve amdgpu, because all we're doing is papering over
this uapi design issue. amdgpu needs to attain the status quo
established by other drivers first, once that's achieved we can tackle
the remaining issues in a consistent way across drivers.

Cc: mesa-dev@lists.freedesktop.org
Cc: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Cc: Dave Airlie <airlied@gmail.com>
Cc: Rob Clark <robdclark@chromium.org>
Cc: Kristian H. Kristensen <hoegsberg@google.com>
Cc: Michel Dänzer <michel@daenzer.net>
Cc: Daniel Stone <daniels@collabora.com>
Cc: Sumit Semwal <sumit.semwal@linaro.org>
Cc: "Christian König" <christian.koenig@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Deepak R Varma <mh12gx2825@gmail.com>
Cc: Chen Li <chenli@uniontech.com>
Cc: Kevin Wang <kevin1.wang@amd.com>
Cc: Dennis Li <Dennis.Li@amd.com>
Cc: Luben Tuikov <luben.tuikov@amd.com>
Cc: linaro-mm-sig@lists.linaro.org
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 88a24a0b5691..cc8426e1e8a8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -617,8 +617,8 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
 	amdgpu_bo_list_for_each_entry(e, p->bo_list) {
 		struct amdgpu_bo *bo = ttm_to_amdgpu_bo(e->tv.bo);
 
-		/* Make sure we use the exclusive slot for shared BOs */
-		if (bo->prime_shared_count)
+		/* Make sure we use the exclusive slot for all potentially shared BOs */
+		if (!(bo->flags & AMDGPU_GEM_CREATE_VM_ALWAYS_VALID))
 			e->tv.num_shared = 0;
 		e->bo_va = amdgpu_vm_bo_find(vm, bo);
 	}
-- 
2.31.0


^ permalink raw reply related	[flat|nested] 175+ messages in thread

end of thread, other threads:[~2021-06-03  7:48 UTC | newest]

Thread overview: 175+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2021-05-21  9:09 [PATCH 01/11] drm/amdgpu: Comply with implicit fencing rules Daniel Vetter
2021-05-21  9:09 ` [Intel-gfx] " Daniel Vetter
2021-05-21  9:09 ` [PATCH 02/11] drm/panfrost: Remove sched_lock Daniel Vetter
2021-05-21  9:09   ` [Intel-gfx] " Daniel Vetter
2021-05-21  9:32   ` Lucas Stach
2021-05-21  9:32     ` [Intel-gfx] " Lucas Stach
2021-05-21 14:49     ` Daniel Vetter
2021-05-21 14:49       ` [Intel-gfx] " Daniel Vetter
2021-05-21  9:09 ` [PATCH 03/11] drm/panfrost: Use xarray and helpers for depedency tracking Daniel Vetter
2021-05-21  9:09   ` [Intel-gfx] " Daniel Vetter
2021-05-21  9:09   ` Daniel Vetter
2021-06-02 14:06   ` Steven Price
2021-06-02 14:06     ` [Intel-gfx] " Steven Price
2021-06-02 14:06     ` Steven Price
2021-06-02 18:51     ` Daniel Vetter
2021-06-02 18:51       ` [Intel-gfx] " Daniel Vetter
2021-06-02 18:51       ` Daniel Vetter
2021-06-03  7:48       ` Steven Price
2021-06-03  7:48         ` [Intel-gfx] " Steven Price
2021-06-03  7:48         ` Steven Price
2021-05-21  9:09 ` [PATCH 04/11] drm/panfrost: Fix implicit sync Daniel Vetter
2021-05-21  9:09   ` [Intel-gfx] " Daniel Vetter
2021-05-21  9:09   ` Daniel Vetter
2021-05-21 12:22   ` Daniel Stone
2021-05-21 12:22     ` [Intel-gfx] " Daniel Stone
2021-05-21 12:22     ` Daniel Stone
2021-05-21 12:28     ` [Linaro-mm-sig] " Christian König
2021-05-21 12:28       ` [Intel-gfx] " Christian König
2021-05-21 12:54       ` Daniel Stone
2021-05-21 12:54         ` [Intel-gfx] " Daniel Stone
2021-05-21 12:54         ` Daniel Stone
2021-05-21 13:09         ` Christian König
2021-05-21 13:09           ` [Intel-gfx] " Christian König
2021-05-21 13:09           ` Christian König
2021-05-21 13:23           ` Daniel Stone
2021-05-21 13:23             ` [Intel-gfx] " Daniel Stone
2021-05-21 13:23             ` Daniel Stone
2021-05-21  9:09 ` [PATCH 05/11] drm/atomic-helper: make drm_gem_plane_helper_prepare_fb the default Daniel Vetter
2021-05-21  9:09   ` [Intel-gfx] " Daniel Vetter
2021-05-21  9:09 ` [PATCH 06/11] drm/<driver>: drm_gem_plane_helper_prepare_fb is now " Daniel Vetter
2021-05-21  9:09   ` Daniel Vetter
2021-05-21  9:09   ` [Intel-gfx] " Daniel Vetter
2021-05-21  9:09   ` Daniel Vetter
2021-05-21  9:09   ` Daniel Vetter
2021-05-21  9:09   ` Daniel Vetter
2021-05-21  9:09   ` Daniel Vetter
2021-05-21  9:38   ` Lucas Stach
2021-05-21  9:38     ` Lucas Stach
2021-05-21  9:38     ` [Intel-gfx] " Lucas Stach
2021-05-21  9:38     ` Lucas Stach
2021-05-21  9:38     ` Lucas Stach
2021-05-21  9:38     ` Lucas Stach
2021-05-21  9:38     ` Lucas Stach
2021-05-21 12:20   ` Heiko Stübner
2021-05-21 12:20     ` Heiko Stübner
2021-05-21 12:20     ` [Intel-gfx] " Heiko Stübner
2021-05-21 12:20     ` Heiko Stübner
2021-05-21 12:20     ` Heiko Stübner
2021-05-21 12:20     ` Heiko Stübner
2021-05-21 12:20     ` Heiko Stübner
2021-05-21 12:22   ` Paul Cercueil
2021-05-21 12:22     ` Paul Cercueil
2021-05-21 12:22     ` [Intel-gfx] " Paul Cercueil
2021-05-21 12:22     ` Paul Cercueil
2021-05-21 12:22     ` Paul Cercueil
2021-05-21 12:22     ` Paul Cercueil
2021-05-21 12:22     ` Paul Cercueil
2021-05-21 15:53   ` Jernej Škrabec
2021-05-21 15:53     ` Jernej Škrabec
2021-05-21 15:53     ` [Intel-gfx] " Jernej Škrabec
2021-05-21 15:53     ` Jernej Škrabec
2021-05-21 15:53     ` Jernej Škrabec
2021-05-21 15:53     ` Jernej Škrabec
2021-05-21 15:53     ` Jernej Škrabec
2021-05-21 23:18   ` Chun-Kuang Hu
2021-05-21 23:18     ` Chun-Kuang Hu
2021-05-21 23:18     ` [Intel-gfx] " Chun-Kuang Hu
2021-05-21 23:18     ` Chun-Kuang Hu
2021-05-21 23:18     ` Chun-Kuang Hu
2021-05-21 23:18     ` Chun-Kuang Hu
2021-05-21 23:18     ` Chun-Kuang Hu
2021-05-23 12:17   ` Martin Blumenstingl
2021-05-23 12:17     ` Martin Blumenstingl
2021-05-23 12:17     ` [Intel-gfx] " Martin Blumenstingl
2021-05-23 12:17     ` Martin Blumenstingl
2021-05-23 12:17     ` Martin Blumenstingl
2021-05-23 12:17     ` Martin Blumenstingl
2021-05-23 12:17     ` Martin Blumenstingl
2021-05-24  7:54   ` Tomi Valkeinen
2021-05-24  7:54     ` Tomi Valkeinen
2021-05-24  7:54     ` [Intel-gfx] " Tomi Valkeinen
2021-05-24  7:54     ` Tomi Valkeinen
2021-05-24  7:54     ` Tomi Valkeinen
2021-05-24  7:54     ` Tomi Valkeinen
2021-05-24  7:54     ` Tomi Valkeinen
2021-05-28  9:55   ` Philippe CORNU
2021-05-28  9:55     ` Philippe CORNU
2021-05-28  9:55     ` [Intel-gfx] " Philippe CORNU
2021-05-28  9:55     ` Philippe CORNU
2021-05-28  9:55     ` Philippe CORNU
2021-05-28  9:55     ` Philippe CORNU
2021-05-28  9:55     ` Philippe CORNU
2021-05-21  9:09 ` [PATCH 07/11] drm/armada: Remove prepare/cleanup_fb hooks Daniel Vetter
2021-05-21  9:09   ` [Intel-gfx] " Daniel Vetter
2021-05-21  9:09 ` [PATCH 08/11] drm/vram-helpers: Create DRM_GEM_VRAM_PLANE_HELPER_FUNCS Daniel Vetter
2021-05-21  9:09   ` [Intel-gfx] " Daniel Vetter
2021-05-21  9:33   ` tiantao (H)
2021-05-21  9:33     ` [Intel-gfx] " tiantao (H)
2021-05-21  9:09 ` [PATCH 09/11] drm/omap: Follow implicit fencing in prepare_fb Daniel Vetter
2021-05-21  9:09   ` [Intel-gfx] " Daniel Vetter
2021-05-24  7:53   ` Tomi Valkeinen
2021-05-24  7:53     ` [Intel-gfx] " Tomi Valkeinen
2021-05-21  9:09 ` [PATCH 10/11] drm/simple-helper: drm_gem_simple_display_pipe_prepare_fb as default Daniel Vetter
2021-05-21  9:09   ` [Intel-gfx] " Daniel Vetter
2021-05-25 17:48   ` Noralf Trønnes
2021-05-25 17:48     ` [Intel-gfx] " Noralf Trønnes
2021-05-25 17:53     ` Daniel Vetter
2021-05-25 17:53       ` [Intel-gfx] " Daniel Vetter
2021-05-21  9:09 ` [PATCH 11/11] drm/tiny: drm_gem_simple_display_pipe_prepare_fb is the default Daniel Vetter
2021-05-21  9:09   ` Daniel Vetter
2021-05-21  9:09   ` [Intel-gfx] " Daniel Vetter
2021-05-21  9:09   ` Daniel Vetter
2021-05-21 13:41   ` David Lechner
2021-05-21 13:41     ` David Lechner
2021-05-21 13:41     ` [Intel-gfx] " David Lechner
2021-05-21 13:41     ` David Lechner
2021-05-21 14:09   ` Noralf Trønnes
2021-05-21 14:09     ` Noralf Trønnes
2021-05-21 14:09     ` [Intel-gfx] " Noralf Trønnes
2021-05-21 14:09     ` Noralf Trønnes
2021-05-25 16:05     ` Daniel Vetter
2021-05-25 16:05       ` Daniel Vetter
2021-05-25 16:05       ` [Intel-gfx] " Daniel Vetter
2021-05-25 16:05       ` Daniel Vetter
2021-05-21 14:13   ` Oleksandr Andrushchenko
2021-05-21 14:13     ` Oleksandr Andrushchenko
2021-05-21 14:13     ` [Intel-gfx] " Oleksandr Andrushchenko
2021-05-21 14:13     ` Oleksandr Andrushchenko
2021-05-28  0:38   ` Linus Walleij
2021-05-28  0:38     ` Linus Walleij
2021-05-28  0:38     ` [Intel-gfx] " Linus Walleij
2021-05-28  0:38     ` Linus Walleij
2021-05-21  9:18 ` [Intel-gfx] ✗ Fi.CI.CHECKPATCH: warning for series starting with [01/11] drm/amdgpu: Comply with implicit fencing rules Patchwork
2021-05-21  9:20 ` [Intel-gfx] ✗ Fi.CI.SPARSE: " Patchwork
2021-05-21  9:45 ` [Intel-gfx] ✓ Fi.CI.BAT: success " Patchwork
2021-05-21  9:46 ` [PATCH 01/11] " Bas Nieuwenhuizen
2021-05-21  9:46   ` [Intel-gfx] " Bas Nieuwenhuizen
2021-05-21 14:37   ` Daniel Vetter
2021-05-21 14:37     ` [Intel-gfx] " Daniel Vetter
2021-05-21 15:00     ` Bas Nieuwenhuizen
2021-05-21 15:00       ` [Intel-gfx] " Bas Nieuwenhuizen
2021-05-21 15:16       ` Daniel Vetter
2021-05-21 15:16         ` [Intel-gfx] " Daniel Vetter
2021-05-21 18:08         ` [Mesa-dev] " Christian König
2021-05-21 18:08           ` [Intel-gfx] " Christian König
2021-05-21 18:31           ` Daniel Vetter
2021-05-21 18:31             ` [Intel-gfx] " Daniel Vetter
2021-05-22  8:30             ` Christian König
2021-05-22  8:30               ` [Intel-gfx] " Christian König
2021-05-25 13:05               ` Daniel Vetter
2021-05-25 13:05                 ` [Intel-gfx] " Daniel Vetter
2021-05-25 15:05                 ` Christian König
2021-05-25 15:23                   ` Daniel Vetter
2021-05-25 15:23                     ` [Intel-gfx] " Daniel Vetter
2021-05-26 13:32                     ` Christian König
2021-05-26 13:32                       ` [Intel-gfx] " Christian König
2021-05-26 13:51                       ` Daniel Vetter
2021-05-26 13:51                         ` [Intel-gfx] " Daniel Vetter
2021-05-21 11:22 ` Christian König
2021-05-21 11:22   ` [Intel-gfx] " Christian König
2021-05-21 14:58 ` [Mesa-dev] " Rob Clark
2021-05-21 14:58   ` [Intel-gfx] " Rob Clark
2021-05-21 14:58   ` Daniel Vetter
2021-05-21 14:58     ` [Intel-gfx] " Daniel Vetter
2021-05-23  5:00 ` [Intel-gfx] ✗ Fi.CI.IGT: failure for series starting with [01/11] " Patchwork

This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.