[PATCH v4 1/5] drm/nouveau/gsp/r535: Add support for INTERNAL_GCX_ENTRY_PREREQUISITE

[Lyude Paul <lyude@redhat.com>]

OpenRM's runtime PM handling looks a bit different then nouveau's, one part
in particular that differs from us: OpenRM actually consults GSP to ask
whether the GPU should be allowed to enter Gc6 and/or GcOff before runtime
suspending the GPU. In the event the card isn't ready, runtime suspend is
simply delayed for a few seconds before retrying.

Implement the command used for querying GSP about this,
NV2080_CTRL_CMD_INTERNAL_GCX_ENTRY_PREREQUISITE, and check to ensure that
the GPU is ready for runtime suspend in nouveau_pmops_runtime_suspend()
using this query. If the GPU can't be runtime suspended, update the last
busy counter of the device and then return -EBUSY from
nouveau_pmops_runtime_suspend() - essentially delaying the runtime suspend
process by whatever autosuspend_delay_ms is set to.

Signed-off-by: Lyude Paul <lyude@redhat.com>

---
V2:
* Remove accidental return of bitmask from nvkm_udevice_gcx_ready()
* Use gsp variable in nvkm_udevice_gcx_ready() more.
* Remove unused GSP_GCX_ENTRY defines
V3:
* Fix error checking
V4:
* Fix layering violation
* Remove structs from r535, this hadn't been added yet!

 drivers/gpu/drm/nouveau/include/nvif/cl0080.h | 10 ++++++
 drivers/gpu/drm/nouveau/include/nvif/device.h |  1 +
 .../gpu/drm/nouveau/include/nvkm/subdev/gsp.h |  2 ++
 drivers/gpu/drm/nouveau/nouveau_drm.c         | 13 +++++++
 drivers/gpu/drm/nouveau/nvif/device.c         | 13 +++++++
 .../gpu/drm/nouveau/nvkm/engine/device/user.c | 35 +++++++++++++++++++
 .../gpu/drm/nouveau/nvkm/subdev/gsp/base.c    | 10 ++++++
 .../gpu/drm/nouveau/nvkm/subdev/gsp/priv.h    |  1 +
 .../nvkm/subdev/gsp/rm/r535/nvrm/gsp.h        |  7 ++++
 .../drm/nouveau/nvkm/subdev/gsp/rm/r570/gsp.c | 28 +++++++++++++++
 .../nvkm/subdev/gsp/rm/r570/nvrm/gsp.h        |  7 ++++
 .../gpu/drm/nouveau/nvkm/subdev/gsp/rm/rm.h   |  2 ++
 12 files changed, 129 insertions(+)

diff --git a/drivers/gpu/drm/nouveau/include/nvif/cl0080.h b/drivers/gpu/drm/nouveau/include/nvif/cl0080.h
index ea8267e0d8da2..9e639df1da467 100644
--- a/drivers/gpu/drm/nouveau/include/nvif/cl0080.h
+++ b/drivers/gpu/drm/nouveau/include/nvif/cl0080.h
@@ -4,6 +4,7 @@
 
 #define NV_DEVICE_V0_INFO                                                  0x00
 #define NV_DEVICE_V0_TIME                                                  0x01
+#define NV_DEVICE_V0_GCX_READY						   0x02
 
 struct nv_device_info_v0 {
 	__u8  version;
@@ -55,6 +56,15 @@ struct nv_device_time_v0 {
 	__u64 time;
 };
 
+#define NV_DEVICE_GC6_READY	BIT(0)
+#define NV_DEVICE_GCOFF_READY	BIT(1)
+
+struct nv_device_gcx_ready_v0 {
+	__u8 version;
+	__u8 pad01[6];
+	__u8 ready;
+};
+
 #define NV_DEVICE_INFO_UNIT                               (0xffffffffULL << 32)
 #define NV_DEVICE_INFO(n)                          ((n) | (0x00000000ULL << 32))
 #define NV_DEVICE_HOST(n)                          ((n) | (0x00000001ULL << 32))
diff --git a/drivers/gpu/drm/nouveau/include/nvif/device.h b/drivers/gpu/drm/nouveau/include/nvif/device.h
index 7877a2a79da9b..ce2fadcb05d9e 100644
--- a/drivers/gpu/drm/nouveau/include/nvif/device.h
+++ b/drivers/gpu/drm/nouveau/include/nvif/device.h
@@ -22,4 +22,5 @@ int  nvif_device_ctor(struct nvif_client *, const char *name, struct nvif_device
 void nvif_device_dtor(struct nvif_device *);
 int  nvif_device_map(struct nvif_device *);
 u64  nvif_device_time(struct nvif_device *);
+int  nvif_device_gcx_ready(struct nvif_device *);
 #endif
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h
index 64fed208e4cf8..cd10c37053695 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h
@@ -495,6 +495,8 @@ nvkm_gsp_event_dtor(struct nvkm_gsp_event *event)
 int nvkm_gsp_intr_stall(struct nvkm_gsp *, enum nvkm_subdev_type, int);
 int nvkm_gsp_intr_nonstall(struct nvkm_gsp *, enum nvkm_subdev_type, int);
 
+int nvkm_gsp_gcx_ready(struct nvkm_gsp *gsp);
+
 int gv100_gsp_new(struct nvkm_device *, enum nvkm_subdev_type, int, struct nvkm_gsp **);
 int tu102_gsp_new(struct nvkm_device *, enum nvkm_subdev_type, int, struct nvkm_gsp **);
 int tu116_gsp_new(struct nvkm_device *, enum nvkm_subdev_type, int, struct nvkm_gsp **);
diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c
index b0f9fb10a74dd..c2e2f430deded 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_drm.c
@@ -1157,6 +1157,7 @@ nouveau_pmops_runtime_suspend(struct device *dev)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct nouveau_drm *drm = pci_get_drvdata(pdev);
+	struct nvif_device *nvif = &drm->client.device;
 	int ret;
 
 	if (!nouveau_pmops_runtime()) {
@@ -1164,6 +1165,18 @@ nouveau_pmops_runtime_suspend(struct device *dev)
 		return -EBUSY;
 	}
 
+	// Check if the GPU itself is ready for runtime suspend, otherwise mark as busy and check
+	// again in a bit.
+	ret = nvif_device_gcx_ready(nvif);
+	if (ret < 0) {
+		NV_ERROR(drm, "Failed to query GCX readiness (returned %d)\n", ret);
+		return -EBUSY;
+	} else if (!(ret & NV_DEVICE_GCOFF_READY)) {
+		NV_DEBUG(drm, "GPU isn't ready for suspend yet, delaying...\n");
+		pm_runtime_mark_last_busy(dev);
+		return -EBUSY;
+	}
+
 	nouveau_switcheroo_optimus_dsm();
 	ret = nouveau_do_suspend(drm, true);
 	pci_save_state(pdev);
diff --git a/drivers/gpu/drm/nouveau/nvif/device.c b/drivers/gpu/drm/nouveau/nvif/device.c
index 24880931039f6..1be9fbe6cb703 100644
--- a/drivers/gpu/drm/nouveau/nvif/device.c
+++ b/drivers/gpu/drm/nouveau/nvif/device.c
@@ -38,6 +38,19 @@ nvif_device_time(struct nvif_device *device)
 	return device->user.func->time(&device->user);
 }
 
+int
+nvif_device_gcx_ready(struct nvif_device *device)
+{
+	struct nv_device_gcx_ready_v0 args = {};
+	int ret;
+
+	ret = nvif_object_mthd(&device->object, NV_DEVICE_V0_GCX_READY, &args, sizeof(args));
+	if (ret)
+		return ret;
+
+	return args.ready;
+}
+
 int
 nvif_device_map(struct nvif_device *device)
 {
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/user.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/user.c
index 23d11d8221cb6..f78e6b9b42923 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/device/user.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/user.c
@@ -27,6 +27,7 @@
 
 #include <core/client.h>
 #include <subdev/fb.h>
+#include <subdev/gsp.h>
 #include <subdev/instmem.h>
 #include <subdev/timer.h>
 
@@ -189,6 +190,38 @@ nvkm_udevice_time(struct nvkm_udevice *udev, void *data, u32 size)
 	return ret;
 }
 
+static int
+nvkm_udevice_gcx_ready(struct nvkm_udevice *udev, void *data, u32 size)
+{
+	struct nvkm_object *object = &udev->object;
+	struct nvkm_device *device = udev->device;
+	struct nvkm_gsp *gsp = device->gsp;
+	union {
+		struct nv_device_gcx_ready_v0 v0;
+	} *args = data;
+	int ret = -ENOSYS;
+
+	if (!gsp) {
+		args->v0.ready = NV_DEVICE_GC6_READY | NV_DEVICE_GCOFF_READY;
+		return 0;
+	}
+
+	nvif_ioctl(object, "device gcx ready size %d\n", size);
+	ret = nvif_unpack(ret, &data, &size, args->v0, 0, 0, false);
+	if (!ret) {
+		nvif_ioctl(object, "device gcx ready vers %d\n", args->v0.version);
+
+		ret = nvkm_gsp_gcx_ready(gsp);
+		if (ret < 0)
+			return ret;
+
+		args->v0.ready = ret;
+		ret = 0;
+	}
+
+	return ret;
+}
+
 static int
 nvkm_udevice_mthd(struct nvkm_object *object, u32 mthd, void *data, u32 size)
 {
@@ -199,6 +232,8 @@ nvkm_udevice_mthd(struct nvkm_object *object, u32 mthd, void *data, u32 size)
 		return nvkm_udevice_info(udev, data, size);
 	case NV_DEVICE_V0_TIME:
 		return nvkm_udevice_time(udev, data, size);
+	case NV_DEVICE_V0_GCX_READY:
+		return nvkm_udevice_gcx_ready(udev, data, size);
 	default:
 		break;
 	}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/base.c
index 9ba1316831e7e..e475d0e8fa7bf 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/base.c
@@ -20,6 +20,7 @@
  * OTHER DEALINGS IN THE SOFTWARE.
  */
 #include "priv.h"
+#include <nvif/cl0080.h>
 
 int
 nvkm_gsp_intr_nonstall(struct nvkm_gsp *gsp, enum nvkm_subdev_type type, int inst)
@@ -47,6 +48,15 @@ nvkm_gsp_intr_stall(struct nvkm_gsp *gsp, enum nvkm_subdev_type type, int inst)
 	return -ENOENT;
 }
 
+int
+nvkm_gsp_gcx_ready(struct nvkm_gsp *gsp)
+{
+	if (!gsp->rm->api->gsp->gcx_ready)
+		return NV_DEVICE_GC6_READY | NV_DEVICE_GCOFF_READY;
+
+	return gsp->rm->api->gsp->gcx_ready(gsp);
+}
+
 static int
 nvkm_gsp_fini(struct nvkm_subdev *subdev, enum nvkm_suspend_state suspend)
 {
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/priv.h b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/priv.h
index 71b7203bef507..b07797813b049 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/priv.h
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/priv.h
@@ -93,6 +93,7 @@ void r535_gsp_dtor(struct nvkm_gsp *);
 int r535_gsp_oneinit(struct nvkm_gsp *);
 int r535_gsp_init(struct nvkm_gsp *);
 int r535_gsp_fini(struct nvkm_gsp *, enum nvkm_suspend_state suspend);
+int r535_gsp_gcx_ready(struct nvkm_gsp *gsp);
 
 int nvkm_gsp_new_(const struct nvkm_gsp_fwif *, struct nvkm_device *, enum nvkm_subdev_type, int,
 		  struct nvkm_gsp **);
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/nvrm/gsp.h b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/nvrm/gsp.h
index b6683a5bf870c..fd1170037c030 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/nvrm/gsp.h
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/nvrm/gsp.h
@@ -782,6 +782,13 @@ typedef struct NV2080_CTRL_INTERNAL_INTR_GET_KERNEL_TABLE_PARAMS {
 
 #define GSP_FW_HEAP_PARAM_CLIENT_ALLOC_SIZE      ((48 << 10) * 2048)   // Support 2048 channels
 
+#define NV2080_CTRL_CMD_INTERNAL_GCX_ENTRY_PREREQUISITE (0x2080a7d7)
+
+typedef struct NV2080_CTRL_INTERNAL_GCX_ENTRY_PREREQUISITE_PARAMS {
+    NvBool bIsGC6Satisfied;
+    NvBool bIsGCOFFSatisfied;
+} NV2080_CTRL_INTERNAL_GCX_ENTRY_PREREQUISITE_PARAMS;
+
 typedef union rpc_message_rpc_union_field_v03_00
 {
     NvU32      spare;
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r570/gsp.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r570/gsp.c
index b45781cd0dfdc..dfda6b0b910a2 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r570/gsp.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r570/gsp.c
@@ -10,6 +10,7 @@
 #include "nvrm/gsp.h"
 #include "nvrm/rpcfn.h"
 #include "nvrm/msgfn.h"
+#include "nvif/cl0080.h"
 
 #include <core/pci.h>
 #include <subdev/pci/priv.h>
@@ -215,6 +216,32 @@ r570_gsp_set_rmargs(struct nvkm_gsp *gsp, bool resume)
 	args->bDmemStack = 1;
 }
 
+int
+r570_gsp_gcx_ready(struct nvkm_gsp *gsp)
+{
+	NV2080_CTRL_INTERNAL_GCX_ENTRY_PREREQUISITE_PARAMS *ctrl;
+	int ret = 0;
+
+	ctrl = nvkm_gsp_rm_ctrl_rd(&gsp->internal.device.subdevice,
+				   NV2080_CTRL_CMD_INTERNAL_GCX_ENTRY_PREREQUISITE,
+				   sizeof(*ctrl));
+	if (IS_ERR(ctrl))
+		return PTR_ERR(ctrl);
+
+	if (ctrl->bIsGC6Satisfied)
+		ret |= NV_DEVICE_GC6_READY;
+	if (ctrl->bIsGCOFFSatisfied)
+		ret |= NV_DEVICE_GCOFF_READY;
+
+	nvkm_debug(&gsp->subdev,
+		   "GCX ready status: GC6=%s GCOFF=%s\n",
+		   str_yes_no(ctrl->bIsGC6Satisfied), str_yes_no(ctrl->bIsGCOFFSatisfied));
+
+	nvkm_gsp_rm_ctrl_done(&gsp->internal.client.object, ctrl);
+	return ret;
+}
+
+
 const struct nvkm_rm_api_gsp
 r570_gsp = {
 	.set_rmargs = r570_gsp_set_rmargs,
@@ -223,4 +250,5 @@ r570_gsp = {
 	.xlat_mc_engine_idx = r570_gsp_xlat_mc_engine_idx,
 	.drop_post_nocat_record = r570_gsp_drop_post_nocat_record,
 	.sr_data_size = r570_gsp_sr_data_size,
+	.gcx_ready = r570_gsp_gcx_ready,
 };
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r570/nvrm/gsp.h b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r570/nvrm/gsp.h
index c458569af9d72..2814629fddd22 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r570/nvrm/gsp.h
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r570/nvrm/gsp.h
@@ -639,4 +639,11 @@ typedef struct GSP_FMC_BOOT_PARAMS
 } GSP_FMC_BOOT_PARAMS;
 
 #define GSP_FW_HEAP_PARAM_BASE_RM_SIZE_GH100              (14 << 20)   // Hopper+
+
+#define NV2080_CTRL_CMD_INTERNAL_GCX_ENTRY_PREREQUISITE (0x2080a7d7)
+
+typedef struct NV2080_CTRL_INTERNAL_GCX_ENTRY_PREREQUISITE_PARAMS {
+    NvBool bIsGC6Satisfied;
+    NvBool bIsGCOFFSatisfied;
+} NV2080_CTRL_INTERNAL_GCX_ENTRY_PREREQUISITE_PARAMS;
 #endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/rm.h b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/rm.h
index e9ac47d86b69a..86970129ad96a 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/rm.h
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/rm.h
@@ -40,6 +40,7 @@ struct nvkm_rm_api {
 		void (*drop_send_user_shared_data)(struct nvkm_gsp *);
 		void (*drop_post_nocat_record)(struct nvkm_gsp *);
 		u32 (*sr_data_size)(struct nvkm_gsp *);
+		int (*gcx_ready)(struct nvkm_gsp *gsp);
 	} *gsp;
 
 	const struct nvkm_rm_api_rpc {
@@ -174,6 +175,7 @@ int r535_gr_chan_new(struct nvkm_gr *, struct nvkm_chan *, const struct nvkm_ocl
 int r535_gr_promote_ctx(struct r535_gr *, bool golden, struct nvkm_vmm *,
 			struct nvkm_memory **pctxbuf_mem, struct nvkm_vma **pctxbuf_vma,
 			struct nvkm_gsp_object *chan);
+int r570_gsp_gcx_ready(struct nvkm_gsp *gsp);
 extern const struct nvkm_rm_api_engine r535_nvdec;
 extern const struct nvkm_rm_api_engine r535_nvenc;
 extern const struct nvkm_rm_api_engine r535_nvjpg;
-- 
2.55.0