drm/nouveau/fifo: add new channel classes

Exposes a bunch of the new features that became possible as a result
of the earlier commits.  DRM will build on this in the future to add
support for features such as SCG ("async compute") and multi-device
rendering, as part of the work necessary to be able to write a half-
decent vulkan driver - finally.

For the moment, this just crudely ports DRM to the API changes.

- channel class interfaces now the same for all HW classes
- channel group class exposed (SCG)
- channel runqueue selector exposed (SCG)
- channel sub-device id control exposed (multi-device rendering)
- channel names in logging will reflect creating process, not fd owner
- explicit USERD allocation required by VOLTA_CHANNEL_GPFIFO_A and newer
- drm is smarter about determining the appropriate channel class to use

Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Reviewed-by: Lyude Paul <lyude@redhat.com>

1 files changed, 4 insertions, 4 deletions

diff --git a/drivers/gpu/drm/nouveau/nouveau_dma.c b/drivers/gpu/drm/nouveau/nouveau_dma.c
index ddb75d80bc53..b90cac6d5772 100644
--- a/drivers/gpu/drm/nouveau/nouveau_dma.c
+++ b/drivers/gpu/drm/nouveau/nouveau_dma.c
@@ -42,9 +42,9 @@ READ_GET(struct nouveau_channel *chan, uint64_t *prev_get, int *timeout)
 {
 	uint64_t val;
 
-	val = nvif_rd32(&chan->user, chan->user_get);
+	val = nvif_rd32(chan->userd, chan->user_get);
         if (chan->user_get_hi)
-                val |= (uint64_t)nvif_rd32(&chan->user, chan->user_get_hi) << 32;
+		val |= (uint64_t)nvif_rd32(chan->userd, chan->user_get_hi) << 32;
 
 	/* reset counter as long as GET is still advancing, this is
 	 * to avoid misdetecting a GPU lockup if the GPU happens to
@@ -86,7 +86,7 @@ nv50_dma_push(struct nouveau_channel *chan, u64 offset, int length)
 	/* Flush writes. */
 	nouveau_bo_rd32(pb, 0);
 
-	nvif_wr32(&chan->user, 0x8c, chan->dma.ib_put);
+	nvif_wr32(chan->userd, 0x8c, chan->dma.ib_put);
 	if (user->func && user->func->doorbell)
 		user->func->doorbell(user, chan->token);
 	chan->dma.ib_free--;
@@ -98,7 +98,7 @@ nv50_dma_push_wait(struct nouveau_channel *chan, int count)
 	uint32_t cnt = 0, prev_get = 0;
 
 	while (chan->dma.ib_free < count) {
-		uint32_t get = nvif_rd32(&chan->user, 0x88);
+		uint32_t get = nvif_rd32(chan->userd, 0x88);
 		if (get != prev_get) {
 			prev_get = get;
 			cnt = 0;