drm/nouveau/kms/nvd9-: Add CRC support

This introduces support for CRC readback on gf119+, using the
documentation generously provided to us by Nvidia:

https://github.com/NVIDIA/open-gpu-doc/blob/master/Display-CRC/display-crc.txt

We expose all available CRC sources. SF, SOR, PIOR, and DAC are exposed
through a single set of "outp" sources: outp-active/auto for a CRC of
the scanout region, outp-complete for a CRC of both the scanout and
blanking/sync region combined, and outp-inactive for a CRC of only the
blanking/sync region. For each source, nouveau selects the appropriate
tap point based on the output path in use. We also expose an "rg"
source, which allows for capturing CRCs of the scanout raster before
it's encoded into a video signal in the output path. This tap point is
referred to as the raster generator.

Note that while there's some other neat features that can be used with
CRC capture on nvidia hardware, like capturing from two CRC sources
simultaneously, I couldn't see any usecase for them and did not
implement them.

Nvidia only allows for accessing CRCs through a shared DMA region that
we program through the core EVO/NvDisplay channel which is referred to
as the notifier context. The notifier context is limited to either 255
(for Fermi-Pascal) or 2047 (Volta+) entries to store CRCs in, and
unfortunately the hardware simply drops CRCs and reports an overflow
once all available entries in the notifier context are filled.

Since the DRM CRC API and igt-gpu-tools don't expect there to be a limit
on how many CRCs can be captured, we work around this in nouveau by
allocating two separate notifier contexts for each head instead of one.
We schedule a vblank worker ahead of time so that once we start getting
close to filling up all of the available entries in the notifier
context, we can swap the currently used notifier context out with
another pre-prepared notifier context in a manner similar to page
flipping.

Unfortunately, the hardware only allows us to this by flushing two
separate updates on the core channel: one to release the current
notifier context handle, and one to program the next notifier context's
handle. When the hardware processes the first update, the CRC for the
current frame is lost. However, the second update can be flushed
immediately without waiting for the first to complete so that CRC
generation resumes on the next frame. According to Nvidia's hardware
engineers, there isn't any cleaner way of flipping notifier contexts
that would avoid this.

Since using vblank workers to swap out the notifier context will ensure
we can usually flush both updates to hardware within the timespan of a
single frame, we can also ensure that there will only be exactly one
frame lost between the first and second update being executed by the
hardware. This gives us the guarantee that we're always correctly
matching each CRC entry with it's respective frame even after a context
flip. And since IGT will retrieve the CRC entry for a frame by waiting
until it receives a CRC for any subsequent frames, this doesn't cause an
issue with any tests and is much simpler than trying to change the
current DRM API to accommodate.

In order to facilitate testing of correct handling of this limitation,
we also expose a debugfs interface to manually control the threshold for
when we start trying to flip the notifier context. We will use this in
igt to trigger a context flip for testing purposes without needing to
wait for the notifier to completely fill up. This threshold is reset
to the default value set by nouveau after each capture, and is exposed
in a separate folder within each CRTC's debugfs directory labelled
"nv_crc".

Changes since v1:
* Forgot to finish saving crc.h before saving, whoops. This just adds
  some corrections to the empty function declarations that we use if
  CONFIG_DEBUG_FS isn't enabled.
Changes since v2:
* Don't check return code from debugfs_create_dir() or
  debugfs_create_file() - Greg K-H
Changes since v3:
  (no functional changes)
* Fix SPDX license identifiers (checkpatch)
* s/uint32_t/u32/ (checkpatch)
* Fix indenting in switch cases (checkpatch)
Changes since v4:
* Remove unneeded param changes with nv50_head_flush_clr/set
* Rebase
Changes since v5:
* Remove set but unused variable (outp) in nv50_crc_atomic_check() -
  Kbuild bot

Signed-off-by: Lyude Paul <lyude@redhat.com>
Reviewed-by: Ben Skeggs <bskeggs@redhat.com>
Acked-by: Dave Airlie <airlied@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200627194657.156514-10-lyude@redhat.com

drivers/gpu/drm/nouveau/dispnv04/crtc.c

@@ -44,6 +44,9 @@
 #include <subdev/bios/pll.h>
 #include <subdev/clk.h>
 
+#include <nvif/event.h>
+#include <nvif/cl0046.h>
+
 static int
 nv04_crtc_mode_set_base(struct drm_crtc *crtc, int x, int y,
 			struct drm_framebuffer *old_fb);
@@ -756,6 +759,7 @@ static void nv_crtc_destroy(struct drm_crtc *crtc)
 	nouveau_bo_unmap(nv_crtc->cursor.nvbo);
 	nouveau_bo_unpin(nv_crtc->cursor.nvbo);
 	nouveau_bo_ref(NULL, &nv_crtc->cursor.nvbo);
+	nvif_notify_fini(&nv_crtc->vblank);
 	kfree(nv_crtc);
 }
 
@@ -1297,9 +1301,19 @@ create_primary_plane(struct drm_device *dev)
         return primary;
 }
 
+static int nv04_crtc_vblank_handler(struct nvif_notify *notify)
+{
+	struct nouveau_crtc *nv_crtc =
+		container_of(notify, struct nouveau_crtc, vblank);
+
+	drm_crtc_handle_vblank(&nv_crtc->base);
+	return NVIF_NOTIFY_KEEP;
+}
+
 int
 nv04_crtc_create(struct drm_device *dev, int crtc_num)
 {
+	struct nouveau_display *disp = nouveau_display(dev);
 	struct nouveau_crtc *nv_crtc;
 	int ret;
 
@@ -1337,5 +1351,14 @@ nv04_crtc_create(struct drm_device *dev, int crtc_num)
 
 	nv04_cursor_init(nv_crtc);
 
-	return 0;
+	ret = nvif_notify_init(&disp->disp.object, nv04_crtc_vblank_handler,
+			       false, NV04_DISP_NTFY_VBLANK,
+			       &(struct nvif_notify_head_req_v0) {
+				    .head = nv_crtc->index,
+			       },
+			       sizeof(struct nvif_notify_head_req_v0),
+			       sizeof(struct nvif_notify_head_rep_v0),
+			       &nv_crtc->vblank);
+
+	return ret;
 }

drivers/gpu/drm/nouveau/dispnv50/Kbuild

@@ -10,6 +10,10 @@ nouveau-y += dispnv50/core917d.o
 nouveau-y += dispnv50/corec37d.o
 nouveau-y += dispnv50/corec57d.o
 
+nouveau-$(CONFIG_DEBUG_FS) += dispnv50/crc.o
+nouveau-$(CONFIG_DEBUG_FS) += dispnv50/crc907d.o
+nouveau-$(CONFIG_DEBUG_FS) += dispnv50/crcc37d.o
+
 nouveau-y += dispnv50/dac507d.o
 nouveau-y += dispnv50/dac907d.o
 

drivers/gpu/drm/nouveau/dispnv50/atom.h

@@ -2,6 +2,9 @@
 #define __NV50_KMS_ATOM_H__
 #define nv50_atom(p) container_of((p), struct nv50_atom, state)
 #include <drm/drm_atomic.h>
+#include "crc.h"
+
+struct nouveau_encoder;
 
 struct nv50_atom {
 	struct drm_atomic_state state;
@@ -115,9 +118,12 @@ struct nv50_head_atom {
 		u8 nhsync:1;
 		u8 nvsync:1;
 		u8 depth:4;
+		u8 crc_raster:2;
 		u8 bpc;
 	} or;
 
+	struct nv50_crc_atom crc;
+
 	/* Currently only used for MST */
 	struct {
 		int pbn;
@@ -135,6 +141,7 @@ struct nv50_head_atom {
 			bool ovly:1;
 			bool dither:1;
 			bool procamp:1;
+			bool crc:1;
 			bool or:1;
 		};
 		u16 mask;
@@ -150,6 +157,19 @@ nv50_head_atom_get(struct drm_atomic_state *state, struct drm_crtc *crtc)
 	return nv50_head_atom(statec);
 }
 
+static inline struct drm_encoder *
+nv50_head_atom_get_encoder(struct nv50_head_atom *atom)
+{
+	struct drm_encoder *encoder = NULL;
+
+	/* We only ever have a single encoder */
+	drm_for_each_encoder_mask(encoder, atom->state.crtc->dev,
+				  atom->state.encoder_mask)
+		break;
+
+	return encoder;
+}
+
 #define nv50_wndw_atom(p) container_of((p), struct nv50_wndw_atom, state)
 
 struct nv50_wndw_atom {

drivers/gpu/drm/nouveau/dispnv50/core.h

@@ -2,6 +2,7 @@
 #define __NV50_KMS_CORE_H__
 #include "disp.h"
 #include "atom.h"
+#include "crc.h"
 #include <nouveau_encoder.h>
 
 struct nv50_core {
@@ -26,6 +27,9 @@ struct nv50_core_func {
 	} wndw;
 
 	const struct nv50_head_func *head;
+#if IS_ENABLED(CONFIG_DEBUG_FS)
+	const struct nv50_crc_func *crc;
+#endif
 	const struct nv50_outp_func {
 		void (*ctrl)(struct nv50_core *, int or, u32 ctrl,
 			     struct nv50_head_atom *);

drivers/gpu/drm/nouveau/dispnv50/core907d.c

@@ -30,6 +30,9 @@ core907d = {
 	.ntfy_wait_done = core507d_ntfy_wait_done,
 	.update = core507d_update,
 	.head = &head907d,
+#if IS_ENABLED(CONFIG_DEBUG_FS)
+	.crc = &crc907d,
+#endif
 	.dac = &dac907d,
 	.sor = &sor907d,
 };

drivers/gpu/drm/nouveau/dispnv50/core917d.c

@@ -30,6 +30,9 @@ core917d = {
 	.ntfy_wait_done = core507d_ntfy_wait_done,
 	.update = core507d_update,
 	.head = &head917d,
+#if IS_ENABLED(CONFIG_DEBUG_FS)
+	.crc = &crc907d,
+#endif
 	.dac = &dac907d,
 	.sor = &sor907d,
 };

drivers/gpu/drm/nouveau/dispnv50/corec37d.c

@@ -142,6 +142,9 @@ corec37d = {
 	.wndw.owner = corec37d_wndw_owner,
 	.head = &headc37d,
 	.sor = &sorc37d,
+#if IS_ENABLED(CONFIG_DEBUG_FS)
+	.crc = &crcc37d,
+#endif
 };
 
 int

drivers/gpu/drm/nouveau/dispnv50/corec57d.c

@@ -52,6 +52,9 @@ corec57d = {
 	.wndw.owner = corec37d_wndw_owner,
 	.head = &headc57d,
 	.sor = &sorc37d,
+#if IS_ENABLED(CONFIG_DEBUG_FS)
+	.crc = &crcc37d,
+#endif
 };
 
 int

drivers/gpu/drm/nouveau/dispnv50/crc.h

@@ -0,0 +1,125 @@
+/* SPDX-License-Identifier: MIT */
+#ifndef __NV50_CRC_H__
+#define __NV50_CRC_H__
+
+#include <linux/mutex.h>
+#include <drm/drm_crtc.h>
+#include <drm/drm_vblank_work.h>
+
+#include <nvif/mem.h>
+#include <nvkm/subdev/bios.h>
+#include "nouveau_encoder.h"
+
+struct nv50_disp;
+struct nv50_head;
+
+#if IS_ENABLED(CONFIG_DEBUG_FS)
+enum nv50_crc_source {
+	NV50_CRC_SOURCE_NONE = 0,
+	NV50_CRC_SOURCE_AUTO,
+	NV50_CRC_SOURCE_RG,
+	NV50_CRC_SOURCE_OUTP_ACTIVE,
+	NV50_CRC_SOURCE_OUTP_COMPLETE,
+	NV50_CRC_SOURCE_OUTP_INACTIVE,
+};
+
+/* RG -> SF (DP only)
+ *    -> SOR
+ *    -> PIOR
+ *    -> DAC
+ */
+enum nv50_crc_source_type {
+	NV50_CRC_SOURCE_TYPE_NONE = 0,
+	NV50_CRC_SOURCE_TYPE_SOR,
+	NV50_CRC_SOURCE_TYPE_PIOR,
+	NV50_CRC_SOURCE_TYPE_DAC,
+	NV50_CRC_SOURCE_TYPE_RG,
+	NV50_CRC_SOURCE_TYPE_SF,
+};
+
+struct nv50_crc_notifier_ctx {
+	struct nvif_mem mem;
+	struct nvif_object ntfy;
+};
+
+struct nv50_crc_atom {
+	enum nv50_crc_source src;
+	/* Only used for gv100+ */
+	u8 wndw : 4;
+};
+
+struct nv50_crc_func {
+	void (*set_src)(struct nv50_head *, int or, enum nv50_crc_source_type,
+			struct nv50_crc_notifier_ctx *, u32 wndw);
+	void (*set_ctx)(struct nv50_head *, struct nv50_crc_notifier_ctx *);
+	u32 (*get_entry)(struct nv50_head *, struct nv50_crc_notifier_ctx *,
+			 enum nv50_crc_source, int idx);
+	bool (*ctx_finished)(struct nv50_head *,
+			     struct nv50_crc_notifier_ctx *);
+	short flip_threshold;
+	short num_entries;
+	size_t notifier_len;
+};
+
+struct nv50_crc {
+	spinlock_t lock;
+	struct nv50_crc_notifier_ctx ctx[2];
+	struct drm_vblank_work flip_work;
+	enum nv50_crc_source src;
+
+	u64 frame;
+	short entry_idx;
+	short flip_threshold;
+	u8 ctx_idx : 1;
+	bool ctx_changed : 1;
+};
+
+void nv50_crc_init(struct drm_device *dev);
+int nv50_head_crc_late_register(struct nv50_head *);
+void nv50_crc_handle_vblank(struct nv50_head *head);
+
+int nv50_crc_verify_source(struct drm_crtc *, const char *, size_t *);
+const char *const *nv50_crc_get_sources(struct drm_crtc *, size_t *);
+int nv50_crc_set_source(struct drm_crtc *, const char *);
+
+int nv50_crc_atomic_check(struct nv50_head *, struct nv50_head_atom *,
+			  struct nv50_head_atom *);
+void nv50_crc_atomic_stop_reporting(struct drm_atomic_state *);
+void nv50_crc_atomic_prepare_notifier_contexts(struct drm_atomic_state *);
+void nv50_crc_atomic_start_reporting(struct drm_atomic_state *);
+void nv50_crc_atomic_set(struct nv50_head *, struct nv50_head_atom *);
+void nv50_crc_atomic_clr(struct nv50_head *);
+
+extern const struct nv50_crc_func crc907d;
+extern const struct nv50_crc_func crcc37d;
+
+#else /* IS_ENABLED(CONFIG_DEBUG_FS) */
+struct nv50_crc {};
+struct nv50_crc_func {};
+struct nv50_crc_atom {};
+
+#define nv50_crc_verify_source NULL
+#define nv50_crc_get_sources NULL
+#define nv50_crc_set_source NULL
+
+static inline void nv50_crc_init(struct drm_device *dev) {}
+static inline int nv50_head_crc_late_register(struct nv50_head *) {}
+static inline void
+nv50_crc_handle_vblank(struct nv50_head *head) { return 0; }
+
+static inline int
+nv50_crc_atomic_check(struct nv50_head *, struct nv50_head_atom *,
+		      struct nv50_head_atom *) {}
+static inline void
+nv50_crc_atomic_stop_reporting(struct drm_atomic_state *) {}
+static inline void
+nv50_crc_atomic_prepare_notifier_contexts(struct drm_atomic_state *) {}
+static inline void
+nv50_crc_atomic_start_reporting(struct drm_atomic_state *) {}
+static inline void
+nv50_crc_atomic_set(struct nv50_head *, struct nv50_head_atom *) {}
+static inline void
+nv50_crc_atomic_clr(struct nv50_head *) {}
+
+#endif /* IS_ENABLED(CONFIG_DEBUG_FS) */
+#endif /* !__NV50_CRC_H__ */

drivers/gpu/drm/nouveau/dispnv50/crc907d.c

@@ -0,0 +1,139 @@
+// SPDX-License-Identifier: MIT
+#include <drm/drm_crtc.h>
+
+#include "crc.h"
+#include "core.h"
+#include "disp.h"
+#include "head.h"
+
+#define CRC907D_MAX_ENTRIES 255
+
+struct crc907d_notifier {
+	u32 status;
+	u32 :32; /* reserved */
+	struct crc907d_entry {
+		u32 status;
+		u32 compositor_crc;
+		u32 output_crc[2];
+	} entries[CRC907D_MAX_ENTRIES];
+} __packed;
+
+static void
+crc907d_set_src(struct nv50_head *head, int or,
+		enum nv50_crc_source_type source,
+		struct nv50_crc_notifier_ctx *ctx, u32 wndw)
+{
+	struct drm_crtc *crtc = &head->base.base;
+	struct nv50_dmac *core = &nv50_disp(head->base.base.dev)->core->chan;
+	const u32 hoff = head->base.index * 0x300;
+	u32 *push;
+	u32 crc_args = 0xfff00000;
+
+	switch (source) {
+	case NV50_CRC_SOURCE_TYPE_SOR:
+		crc_args |= (0x00000f0f + or * 16) << 8;
+		break;
+	case NV50_CRC_SOURCE_TYPE_PIOR:
+		crc_args |= (0x000000ff + or * 256) << 8;
+		break;
+	case NV50_CRC_SOURCE_TYPE_DAC:
+		crc_args |= (0x00000ff0 + or) << 8;
+		break;
+	case NV50_CRC_SOURCE_TYPE_RG:
+		crc_args |= (0x00000ff8 + drm_crtc_index(crtc)) << 8;
+		break;
+	case NV50_CRC_SOURCE_TYPE_SF:
+		crc_args |= (0x00000f8f + drm_crtc_index(crtc) * 16) << 8;
+		break;
+	case NV50_CRC_SOURCE_NONE:
+		crc_args |= 0x000fff00;
+		break;
+	}
+
+	push = evo_wait(core, 4);
+	if (!push)
+		return;
+
+	if (source) {
+		evo_mthd(push, 0x0438 + hoff, 1);
+		evo_data(push, ctx->ntfy.handle);
+		evo_mthd(push, 0x0430 + hoff, 1);
+		evo_data(push, crc_args);
+	} else {
+		evo_mthd(push, 0x0430 + hoff, 1);
+		evo_data(push, crc_args);
+		evo_mthd(push, 0x0438 + hoff, 1);
+		evo_data(push, 0);
+	}
+	evo_kick(push, core);
+}
+
+static void crc907d_set_ctx(struct nv50_head *head,
+			    struct nv50_crc_notifier_ctx *ctx)
+{
+	struct nv50_dmac *core = &nv50_disp(head->base.base.dev)->core->chan;
+	u32 *push = evo_wait(core, 2);
+
+	if (!push)
+		return;
+
+	evo_mthd(push, 0x0438 + (head->base.index * 0x300), 1);
+	evo_data(push, ctx ? ctx->ntfy.handle : 0);
+	evo_kick(push, core);
+}
+
+static u32 crc907d_get_entry(struct nv50_head *head,
+			     struct nv50_crc_notifier_ctx *ctx,
+			     enum nv50_crc_source source, int idx)
+{
+	struct crc907d_notifier __iomem *notifier = ctx->mem.object.map.ptr;
+
+	return ioread32_native(&notifier->entries[idx].output_crc[0]);
+}
+
+static bool crc907d_ctx_finished(struct nv50_head *head,
+				 struct nv50_crc_notifier_ctx *ctx)
+{
+	struct nouveau_drm *drm = nouveau_drm(head->base.base.dev);
+	struct crc907d_notifier __iomem *notifier = ctx->mem.object.map.ptr;
+	const u32 status = ioread32_native(&notifier->status);
+	const u32 overflow = status & 0x0000003e;
+
+	if (!(status & 0x00000001))
+		return false;
+
+	if (overflow) {
+		const char *engine = NULL;
+
+		switch (overflow) {
+		case 0x00000004: engine = "DSI"; break;
+		case 0x00000008: engine = "Compositor"; break;
+		case 0x00000010: engine = "CRC output 1"; break;
+		case 0x00000020: engine = "CRC output 2"; break;
+		}
+
+		if (engine)
+			NV_ERROR(drm,
+				 "CRC notifier context for head %d overflowed on %s: %x\n",
+				 head->base.index, engine, status);
+		else
+			NV_ERROR(drm,
+				 "CRC notifier context for head %d overflowed: %x\n",
+				 head->base.index, status);
+	}
+
+	NV_DEBUG(drm, "Head %d CRC context status: %x\n",
+		 head->base.index, status);
+
+	return true;
+}
+
+const struct nv50_crc_func crc907d = {
+	.set_src = crc907d_set_src,
+	.set_ctx = crc907d_set_ctx,
+	.get_entry = crc907d_get_entry,
+	.ctx_finished = crc907d_ctx_finished,
+	.flip_threshold = CRC907D_MAX_ENTRIES - 10,
+	.num_entries = CRC907D_MAX_ENTRIES,
+	.notifier_len = sizeof(struct crc907d_notifier),
+};

drivers/gpu/drm/nouveau/dispnv50/crcc37d.c

@@ -0,0 +1,153 @@
+// SPDX-License-Identifier: MIT
+#include <drm/drm_crtc.h>
+
+#include "crc.h"
+#include "core.h"
+#include "disp.h"
+#include "head.h"
+
+#define CRCC37D_MAX_ENTRIES 2047
+
+struct crcc37d_notifier {
+	u32 status;
+
+	/* reserved */
+	u32 :32;
+	u32 :32;
+	u32 :32;
+	u32 :32;
+	u32 :32;
+	u32 :32;
+	u32 :32;
+
+	struct crcc37d_entry {
+		u32 status[2];
+		u32 :32; /* reserved */
+		u32 compositor_crc;
+		u32 rg_crc;
+		u32 output_crc[2];
+		u32 :32; /* reserved */
+	} entries[CRCC37D_MAX_ENTRIES];
+} __packed;
+
+static void
+crcc37d_set_src(struct nv50_head *head, int or,
+		enum nv50_crc_source_type source,
+		struct nv50_crc_notifier_ctx *ctx, u32 wndw)
+{
+	struct nv50_dmac *core = &nv50_disp(head->base.base.dev)->core->chan;
+	const u32 hoff = head->base.index * 0x400;
+	u32 *push;
+	u32 crc_args;
+
+	switch (source) {
+	case NV50_CRC_SOURCE_TYPE_SOR:
+		crc_args = (0x00000050 + or) << 12;
+		break;
+	case NV50_CRC_SOURCE_TYPE_PIOR:
+		crc_args = (0x00000060 + or) << 12;
+		break;
+	case NV50_CRC_SOURCE_TYPE_SF:
+		crc_args = 0x00000030 << 12;
+		break;
+	default:
+		crc_args = 0;
+		break;
+	}
+
+	push = evo_wait(core, 4);
+	if (!push)
+		return;
+
+	if (source) {
+		evo_mthd(push, 0x2180 + hoff, 1);
+		evo_data(push, ctx->ntfy.handle);
+		evo_mthd(push, 0x2184 + hoff, 1);
+		evo_data(push, crc_args | wndw);
+	} else {
+		evo_mthd(push, 0x2184 + hoff, 1);
+		evo_data(push, 0);
+		evo_mthd(push, 0x2180 + hoff, 1);
+		evo_data(push, 0);
+	}
+
+	evo_kick(push, core);
+}
+
+static void crcc37d_set_ctx(struct nv50_head *head,
+			    struct nv50_crc_notifier_ctx *ctx)
+{
+	struct nv50_dmac *core = &nv50_disp(head->base.base.dev)->core->chan;
+	u32 *push = evo_wait(core, 2);
+
+	if (!push)
+		return;
+
+	evo_mthd(push, 0x2180 + (head->base.index * 0x400), 1);
+	evo_data(push, ctx ? ctx->ntfy.handle : 0);
+	evo_kick(push, core);
+}
+
+static u32 crcc37d_get_entry(struct nv50_head *head,
+			     struct nv50_crc_notifier_ctx *ctx,
+			     enum nv50_crc_source source, int idx)
+{
+	struct crcc37d_notifier __iomem *notifier = ctx->mem.object.map.ptr;
+	struct crcc37d_entry __iomem *entry = &notifier->entries[idx];
+	u32 __iomem *crc_addr;
+
+	if (source == NV50_CRC_SOURCE_RG)
+		crc_addr = &entry->rg_crc;
+	else
+		crc_addr = &entry->output_crc[0];
+
+	return ioread32_native(crc_addr);
+}
+
+static bool crcc37d_ctx_finished(struct nv50_head *head,
+				 struct nv50_crc_notifier_ctx *ctx)
+{
+	struct nouveau_drm *drm = nouveau_drm(head->base.base.dev);
+	struct crcc37d_notifier __iomem *notifier = ctx->mem.object.map.ptr;
+	const u32 status = ioread32_native(&notifier->status);
+	const u32 overflow = status & 0x0000007e;
+
+	if (!(status & 0x00000001))
+		return false;
+
+	if (overflow) {
+		const char *engine = NULL;
+
+		switch (overflow) {
+		case 0x00000004: engine = "Front End"; break;
+		case 0x00000008: engine = "Compositor"; break;
+		case 0x00000010: engine = "RG"; break;
+		case 0x00000020: engine = "CRC output 1"; break;
+		case 0x00000040: engine = "CRC output 2"; break;
+		}
+
+		if (engine)
+			NV_ERROR(drm,
+				 "CRC notifier context for head %d overflowed on %s: %x\n",
+				 head->base.index, engine, status);
+		else
+			NV_ERROR(drm,
+				 "CRC notifier context for head %d overflowed: %x\n",
+				 head->base.index, status);
+	}
+
+	NV_DEBUG(drm, "Head %d CRC context status: %x\n",
+		 head->base.index, status);
+
+	return true;
+}
+
+const struct nv50_crc_func crcc37d = {
+	.set_src = crcc37d_set_src,
+	.set_ctx = crcc37d_set_ctx,
+	.get_entry = crcc37d_get_entry,
+	.ctx_finished = crcc37d_ctx_finished,
+	.flip_threshold = CRCC37D_MAX_ENTRIES - 30,
+	.num_entries = CRCC37D_MAX_ENTRIES,
+	.notifier_len = sizeof(struct crcc37d_notifier),
+};

drivers/gpu/drm/nouveau/dispnv50/disp.c

@@ -783,6 +783,19 @@ struct nv50_msto {
 	bool disabled;
 };
 
+struct nouveau_encoder *nv50_real_outp(struct drm_encoder *encoder)
+{
+	struct nv50_msto *msto;
+
+	if (encoder->encoder_type != DRM_MODE_ENCODER_DPMST)
+		return nouveau_encoder(encoder);
+
+	msto = nv50_msto(encoder);
+	if (!msto->mstc)
+		return NULL;
+	return msto->mstc->mstm->outp;
+}
+
 static struct drm_dp_payload *
 nv50_msto_payload(struct nv50_msto *msto)
 {
@@ -1932,6 +1945,7 @@ nv50_disp_atomic_commit_tail(struct drm_atomic_state *state)
 	int i;
 
 	NV_ATOMIC(drm, "commit %d %d\n", atom->lock_core, atom->flush_disable);
+	nv50_crc_atomic_stop_reporting(state);
 	drm_atomic_helper_wait_for_fences(dev, state, false);
 	drm_atomic_helper_wait_for_dependencies(state);
 	drm_atomic_helper_update_legacy_modeset_state(dev, state);
@@ -2002,6 +2016,8 @@ nv50_disp_atomic_commit_tail(struct drm_atomic_state *state)
 		}
 	}
 
+	nv50_crc_atomic_prepare_notifier_contexts(state);
+
 	/* Update output path(s). */
 	list_for_each_entry_safe(outp, outt, &atom->outp, head) {
 		const struct drm_encoder_helper_funcs *help;
@@ -2115,6 +2131,7 @@ nv50_disp_atomic_commit_tail(struct drm_atomic_state *state)
 		}
 	}
 
+	nv50_crc_atomic_start_reporting(state);
 	drm_atomic_helper_commit_hw_done(state);
 	drm_atomic_helper_cleanup_planes(dev, state);
 	drm_atomic_helper_commit_cleanup_done(state);

drivers/gpu/drm/nouveau/dispnv50/disp.h

@@ -1,10 +1,12 @@
 #ifndef __NV50_KMS_H__
 #define __NV50_KMS_H__
+#include <linux/workqueue.h>
 #include <nvif/mem.h>
 
 #include "nouveau_display.h"
 
 struct nv50_msto;
+struct nouveau_encoder;
 
 struct nv50_disp {
 	struct nvif_disp *disp;
@@ -90,6 +92,14 @@ int nv50_dmac_create(struct nvif_device *device, struct nvif_object *disp,
 		     u64 syncbuf, struct nv50_dmac *dmac);
 void nv50_dmac_destroy(struct nv50_dmac *);
 
+/*
+ * For normal encoders this just returns the encoder. For active MST encoders,
+ * this returns the real outp that's driving displays on the topology.
+ * Inactive MST encoders return NULL, since they would have no real outp to
+ * return anyway.
+ */
+struct nouveau_encoder *nv50_real_outp(struct drm_encoder *encoder);
+
 u32 *evo_wait(struct nv50_dmac *, int nr);
 void evo_kick(u32 *, struct nv50_dmac *);
 

drivers/gpu/drm/nouveau/dispnv50/handles.h

@@ -11,5 +11,6 @@
 #define NV50_DISP_HANDLE_VRAM                                           0xf0000001
 
 #define NV50_DISP_HANDLE_WNDW_CTX(kind)                        (0xfb000000 | kind)
+#define NV50_DISP_HANDLE_CRC_CTX(head, i) (0xfc000000 | head->base.index << 1 | i)
 
 #endif /* !__NV50_KMS_HANDLES_H__ */

drivers/gpu/drm/nouveau/dispnv50/head.c

@@ -24,13 +24,17 @@
 #include "core.h"
 #include "curs.h"
 #include "ovly.h"
+#include "crc.h"
 
 #include <nvif/class.h>
+#include <nvif/event.h>
+#include <nvif/cl0046.h>
 
 #include <drm/drm_atomic_helper.h>
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_vblank.h>
 #include "nouveau_connector.h"
+
 void
 nv50_head_flush_clr(struct nv50_head *head,
 		    struct nv50_head_atom *asyh, bool flush)
@@ -38,6 +42,7 @@ nv50_head_flush_clr(struct nv50_head *head,
 	union nv50_head_atom_mask clr = {
 		.mask = asyh->clr.mask & ~(flush ? 0 : asyh->set.mask),
 	};
+	if (clr.crc)  nv50_crc_atomic_clr(head);
 	if (clr.olut) head->func->olut_clr(head);
 	if (clr.core) head->func->core_clr(head);
 	if (clr.curs) head->func->curs_clr(head);
@@ -61,6 +66,7 @@ nv50_head_flush_set(struct nv50_head *head, struct nv50_head_atom *asyh)
 	if (asyh->set.ovly   ) head->func->ovly    (head, asyh);
 	if (asyh->set.dither ) head->func->dither  (head, asyh);
 	if (asyh->set.procamp) head->func->procamp (head, asyh);
+	if (asyh->set.crc    ) nv50_crc_atomic_set (head, asyh);
 	if (asyh->set.or     ) head->func->or      (head, asyh);
 }
 
@@ -313,7 +319,7 @@ nv50_head_atomic_check(struct drm_crtc *crtc, struct drm_crtc_state *state)
 	struct nouveau_conn_atom *asyc = NULL;
 	struct drm_connector_state *conns;
 	struct drm_connector *conn;
-	int i;
+	int i, ret;
 
 	NV_ATOMIC(drm, "%s atomic_check %d\n", crtc->name, asyh->state.active);
 	if (asyh->state.active) {
@@ -408,6 +414,10 @@ nv50_head_atomic_check(struct drm_crtc *crtc, struct drm_crtc_state *state)
 		asyh->set.curs = asyh->curs.visible;
 	}
 
+	ret = nv50_crc_atomic_check(head, asyh, armh);
+	if (ret)
+		return ret;
+
 	if (asyh->clr.mask || asyh->set.mask)
 		nv50_atom(asyh->state.state)->lock_core = true;
 	return 0;
@@ -446,6 +456,7 @@ nv50_head_atomic_duplicate_state(struct drm_crtc *crtc)
 	asyh->ovly = armh->ovly;
 	asyh->dither = armh->dither;
 	asyh->procamp = armh->procamp;
+	asyh->crc = armh->crc;
 	asyh->or = armh->or;
 	asyh->dp = armh->dp;
 	asyh->clr.mask = 0;
@@ -467,10 +478,18 @@ nv50_head_reset(struct drm_crtc *crtc)
 	__drm_atomic_helper_crtc_reset(crtc, &asyh->state);
 }
 
+static int
+nv50_head_late_register(struct drm_crtc *crtc)
+{
+	return nv50_head_crc_late_register(nv50_head(crtc));
+}
+
 static void
 nv50_head_destroy(struct drm_crtc *crtc)
 {
 	struct nv50_head *head = nv50_head(crtc);
+
+	nvif_notify_fini(&head->base.vblank);
 	nv50_lut_fini(&head->olut);
 	drm_crtc_cleanup(crtc);
 	kfree(head);
@@ -488,8 +507,38 @@ nv50_head_func = {
 	.enable_vblank = nouveau_display_vblank_enable,
 	.disable_vblank = nouveau_display_vblank_disable,
 	.get_vblank_timestamp = drm_crtc_vblank_helper_get_vblank_timestamp,
+	.late_register = nv50_head_late_register,
 };
 
+static const struct drm_crtc_funcs
+nvd9_head_func = {
+	.reset = nv50_head_reset,
+	.gamma_set = drm_atomic_helper_legacy_gamma_set,
+	.destroy = nv50_head_destroy,
+	.set_config = drm_atomic_helper_set_config,
+	.page_flip = drm_atomic_helper_page_flip,
+	.atomic_duplicate_state = nv50_head_atomic_duplicate_state,
+	.atomic_destroy_state = nv50_head_atomic_destroy_state,
+	.enable_vblank = nouveau_display_vblank_enable,
+	.disable_vblank = nouveau_display_vblank_disable,
+	.get_vblank_timestamp = drm_crtc_vblank_helper_get_vblank_timestamp,
+	.verify_crc_source = nv50_crc_verify_source,
+	.get_crc_sources = nv50_crc_get_sources,
+	.set_crc_source = nv50_crc_set_source,
+	.late_register = nv50_head_late_register,
+};
+
+static int nv50_head_vblank_handler(struct nvif_notify *notify)
+{
+	struct nouveau_crtc *nv_crtc =
+		container_of(notify, struct nouveau_crtc, vblank);
+
+	if (drm_crtc_handle_vblank(&nv_crtc->base))
+		nv50_crc_handle_vblank(nv50_head(&nv_crtc->base));
+
+	return NVIF_NOTIFY_KEEP;
+}
+
 struct nv50_head *
 nv50_head_create(struct drm_device *dev, int index)
 {
@@ -497,7 +546,9 @@ nv50_head_create(struct drm_device *dev, int index)
 	struct nv50_disp *disp = nv50_disp(dev);
 	struct nv50_head *head;
 	struct nv50_wndw *base, *ovly, *curs;
+	struct nouveau_crtc *nv_crtc;
 	struct drm_crtc *crtc;
+	const struct drm_crtc_funcs *funcs;
 	int ret;
 
 	head = kzalloc(sizeof(*head), GFP_KERNEL);
@@ -507,6 +558,11 @@ nv50_head_create(struct drm_device *dev, int index)
 	head->func = disp->core->func->head;
 	head->base.index = index;
 
+	if (disp->disp->object.oclass < GF110_DISP)
+		funcs = &nv50_head_func;
+	else
+		funcs = &nvd9_head_func;
+
 	if (disp->disp->object.oclass < GV100_DISP) {
 		ret = nv50_base_new(drm, head->base.index, &base);
 		ret = nv50_ovly_new(drm, head->base.index, &ovly);
@@ -523,9 +579,10 @@ nv50_head_create(struct drm_device *dev, int index)
 		return ERR_PTR(ret);
 	}
 
-	crtc = &head->base.base;
+	nv_crtc = &head->base;
+	crtc = &nv_crtc->base;
 	drm_crtc_init_with_planes(dev, crtc, &base->plane, &curs->plane,
-				  &nv50_head_func, "head-%d", head->base.index);
+				  funcs, "head-%d", head->base.index);
 	drm_crtc_helper_add(crtc, &nv50_head_help);
 	/* Keep the legacy gamma size at 256 to avoid compatibility issues */
 	drm_mode_crtc_set_gamma_size(crtc, 256);
@@ -541,5 +598,16 @@ nv50_head_create(struct drm_device *dev, int index)
 		}
 	}
 
+	ret = nvif_notify_init(&disp->disp->object, nv50_head_vblank_handler,
+			       false, NV04_DISP_NTFY_VBLANK,
+			       &(struct nvif_notify_head_req_v0) {
+				    .head = nv_crtc->index,
+			       },
+			       sizeof(struct nvif_notify_head_req_v0),
+			       sizeof(struct nvif_notify_head_rep_v0),
+			       &nv_crtc->vblank);
+	if (ret)
+		return ERR_PTR(ret);
+
 	return head;
 }

drivers/gpu/drm/nouveau/dispnv50/head.h

@@ -1,22 +1,28 @@
 #ifndef __NV50_KMS_HEAD_H__
 #define __NV50_KMS_HEAD_H__
 #define nv50_head(c) container_of((c), struct nv50_head, base.base)
+#include <linux/workqueue.h>
+
 #include "disp.h"
 #include "atom.h"
+#include "crc.h"
 #include "lut.h"
 
 #include "nouveau_crtc.h"
+#include "nouveau_encoder.h"
 
 struct nv50_head {
 	const struct nv50_head_func *func;
 	struct nouveau_crtc base;
+	struct nv50_crc crc;
 	struct nv50_lut olut;
 	struct nv50_msto *msto;
 };
 
 struct nv50_head *nv50_head_create(struct drm_device *, int index);
-void nv50_head_flush_set(struct nv50_head *, struct nv50_head_atom *);
-void nv50_head_flush_clr(struct nv50_head *, struct nv50_head_atom *, bool y);
+void nv50_head_flush_set(struct nv50_head *head, struct nv50_head_atom *asyh);
+void nv50_head_flush_clr(struct nv50_head *head,
+			 struct nv50_head_atom *asyh, bool flush);
 
 struct nv50_head_func {
 	void (*view)(struct nv50_head *, struct nv50_head_atom *);

drivers/gpu/drm/nouveau/dispnv50/head907d.c

@@ -19,8 +19,15 @@
  * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
  * OTHER DEALINGS IN THE SOFTWARE.
  */
+#include <drm/drm_connector.h>
+#include <drm/drm_mode_config.h>
+#include <drm/drm_vblank.h>
+#include "nouveau_drv.h"
+#include "nouveau_bios.h"
+#include "nouveau_connector.h"
 #include "head.h"
 #include "core.h"
+#include "crc.h"
 
 void
 head907d_or(struct nv50_head *head, struct nv50_head_atom *asyh)
@@ -29,9 +36,10 @@ head907d_or(struct nv50_head *head, struct nv50_head_atom *asyh)
 	u32 *push;
 	if ((push = evo_wait(core, 3))) {
 		evo_mthd(push, 0x0404 + (head->base.index * 0x300), 2);
-		evo_data(push, 0x00000001 | asyh->or.depth  << 6 |
-					    asyh->or.nvsync << 4 |
-					    asyh->or.nhsync << 3);
+		evo_data(push, asyh->or.depth  << 6 |
+			       asyh->or.nvsync << 4 |
+			       asyh->or.nhsync << 3 |
+			       asyh->or.crc_raster);
 		evo_data(push, 0x31ec6000 | head->base.index << 25 |
 					    asyh->mode.interlace);
 		evo_kick(push, core);

drivers/gpu/drm/nouveau/dispnv50/headc37d.c

@@ -46,10 +46,10 @@ headc37d_or(struct nv50_head *head, struct nv50_head_atom *asyh)
 		}
 
 		evo_mthd(push, 0x2004 + (head->base.index * 0x400), 1);
-		evo_data(push, 0x00000001 |
-			       asyh->or.depth << 4 |
+		evo_data(push, depth << 4 |
 			       asyh->or.nvsync << 3 |
-			       asyh->or.nhsync << 2);
+			       asyh->or.nhsync << 2 |
+			       asyh->or.crc_raster);
 		evo_kick(push, core);
 	}
 }

drivers/gpu/drm/nouveau/dispnv50/headc57d.c

@@ -46,10 +46,11 @@ headc57d_or(struct nv50_head *head, struct nv50_head_atom *asyh)
 		}
 
 		evo_mthd(push, 0x2004 + (head->base.index * 0x400), 1);
-		evo_data(push, 0xfc000001 |
-			       asyh->or.depth << 4 |
+		evo_data(push, 0xfc000000 |
+			       depth << 4 |
 			       asyh->or.nvsync << 3 |
-			       asyh->or.nhsync << 2);
+			       asyh->or.nhsync << 2 |
+			       asyh->or.crc_raster);
 		evo_kick(push, core);
 	}
 }