drm/nouveau: Add DRM_IOCTL_NOUVEAU_GET_ZCULL_INFO

Add kernel-side support for using the zcull hardware in nvidia gpus.
zcull aims to improve memory bandwidth by using an early approximate
depth test, similar to hierarchical Z on an AMD card.

Add a new ioctl that exposes zcull information that has been read
from the hardware. Userspace uses each of these parameters either
in a heuristic for determining zcull region parameters or in the
calculation of a buffer size.

It appears the hardware hasn't changed its structure for these
values since FERMI_C (circa 2011), so the assumption is that it
won't change on us too quickly, and is therefore reasonable to
include in UAPI.

This bypasses the nvif layer and instead accesses nvkm_gr directly,
which mirrors existing usage of nvkm_gr_units(). There is no nvif
object for nvkm_gr yet, and adding one is not trivial.

Signed-off-by: Mel Henning <mhenning@darkrefraction.com>
Link: https://patch.msgid.link/20260219-zcull3-v3-2-dbe6a716f104@darkrefraction.com
Signed-off-by: Danilo Krummrich <dakr@kernel.org>

diff --git a/drivers/gpu/drm/nouveau/nouveau_abi16.c b/drivers/gpu/drm/nouveau/nouveau_abi16.c
index f9201f2e73a339a10baca7083147053b12d3709a..7860877d909b038fc49713b98489388a3b2658e2 100644 (file)
--- a/drivers/gpu/drm/nouveau/nouveau_abi16.c
+++ b/drivers/gpu/drm/nouveau/nouveau_abi16.c
@@ -333,6 +333,35 @@ nouveau_abi16_ioctl_getparam(ABI16_IOCTL_ARGS)
        return 0;
 }
 
+int
+nouveau_abi16_ioctl_get_zcull_info(ABI16_IOCTL_ARGS)
+{
+       struct nouveau_drm *drm = nouveau_drm(dev);
+       struct nvkm_gr *gr = nvxx_gr(drm);
+       struct drm_nouveau_get_zcull_info *out = data;
+
+       if (gr->has_zcull_info) {
+               const struct nvkm_gr_zcull_info *i = &gr->zcull_info;
+
+               out->width_align_pixels = i->width_align_pixels;
+               out->height_align_pixels = i->height_align_pixels;
+               out->pixel_squares_by_aliquots = i->pixel_squares_by_aliquots;
+               out->aliquot_total = i->aliquot_total;
+               out->zcull_region_byte_multiplier = i->zcull_region_byte_multiplier;
+               out->zcull_region_header_size = i->zcull_region_header_size;
+               out->zcull_subregion_header_size = i->zcull_subregion_header_size;
+               out->subregion_count = i->subregion_count;
+               out->subregion_width_align_pixels = i->subregion_width_align_pixels;
+               out->subregion_height_align_pixels = i->subregion_height_align_pixels;
+               out->ctxsw_size = i->ctxsw_size;
+               out->ctxsw_align = i->ctxsw_align;
+
+               return 0;
+       } else {
+               return -ENOTTY;
+       }
+}
+
 int
 nouveau_abi16_ioctl_channel_alloc(ABI16_IOCTL_ARGS)
 {

diff --git a/drivers/gpu/drm/nouveau/nouveau_abi16.h b/drivers/gpu/drm/nouveau/nouveau_abi16.h
index af6b4e1cefd23074db7882abc6211cb0ff0b7643..134b3ab58719b32a018a1769b9104b4546afa8f0 100644 (file)
--- a/drivers/gpu/drm/nouveau/nouveau_abi16.h
+++ b/drivers/gpu/drm/nouveau/nouveau_abi16.h
@@ -6,6 +6,7 @@
        struct drm_device *dev, void *data, struct drm_file *file_priv
 
 int nouveau_abi16_ioctl_getparam(ABI16_IOCTL_ARGS);
+int nouveau_abi16_ioctl_get_zcull_info(ABI16_IOCTL_ARGS);
 int nouveau_abi16_ioctl_channel_alloc(ABI16_IOCTL_ARGS);
 int nouveau_abi16_ioctl_channel_free(ABI16_IOCTL_ARGS);
 int nouveau_abi16_ioctl_grobj_alloc(ABI16_IOCTL_ARGS);

diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c
index 17c114645d9f9f75124766532e0de475be8ed060..5d8475e4895e42fc2f94230265150f93b0a4904a 100644 (file)
--- a/drivers/gpu/drm/nouveau/nouveau_drm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_drm.c
@@ -1304,6 +1304,7 @@ nouveau_ioctls[] = {
        DRM_IOCTL_DEF_DRV(NOUVEAU_GROBJ_ALLOC, nouveau_abi16_ioctl_grobj_alloc, DRM_RENDER_ALLOW),
        DRM_IOCTL_DEF_DRV(NOUVEAU_NOTIFIEROBJ_ALLOC, nouveau_abi16_ioctl_notifierobj_alloc, DRM_RENDER_ALLOW),
        DRM_IOCTL_DEF_DRV(NOUVEAU_GPUOBJ_FREE, nouveau_abi16_ioctl_gpuobj_free, DRM_RENDER_ALLOW),
+       DRM_IOCTL_DEF_DRV(NOUVEAU_GET_ZCULL_INFO, nouveau_abi16_ioctl_get_zcull_info, DRM_RENDER_ALLOW),
        DRM_IOCTL_DEF_DRV(NOUVEAU_SVM_INIT, nouveau_svmm_init, DRM_RENDER_ALLOW),
        DRM_IOCTL_DEF_DRV(NOUVEAU_SVM_BIND, nouveau_svmm_bind, DRM_RENDER_ALLOW),
        DRM_IOCTL_DEF_DRV(NOUVEAU_GEM_NEW, nouveau_gem_ioctl_new, DRM_RENDER_ALLOW),

diff --git a/include/uapi/drm/nouveau_drm.h b/include/uapi/drm/nouveau_drm.h
index dd87f8f30793d9df698c92f78bdb37d78f0dcafd..1fa82fa6af386a040ce7e36f74f4c5f992258aa5 100644 (file)
--- a/include/uapi/drm/nouveau_drm.h
+++ b/include/uapi/drm/nouveau_drm.h
@@ -432,6 +432,69 @@ struct drm_nouveau_exec {
        __u64 push_ptr;
 };
 
+struct drm_nouveau_get_zcull_info {
+       /**
+        * @width_align_pixels: required alignment for region widths, in pixels
+        * (typically #TPC's * 16).
+        */
+       __u32 width_align_pixels;
+       /**
+        * @height_align_pixels: required alignment for region heights, in
+        * pixels (typically 32).
+        */
+       __u32 height_align_pixels;
+       /**
+        * @pixel_squares_by_aliquots: the pixel area covered by an aliquot
+        * (typically #Zcull_banks * 16 * 16).
+        */
+       __u32 pixel_squares_by_aliquots;
+       /**
+        * @aliquot_total: the total aliquot pool available in hardware
+        */
+       __u32 aliquot_total;
+       /**
+        * @zcull_region_byte_multiplier: the size of an aliquot in bytes, which
+        * is used for save/restore operations on a region
+        */
+       __u32 zcull_region_byte_multiplier;
+       /**
+        * @zcull_region_header_size: the region header size in bytes, which is
+        * used for save/restore operations on a region
+        */
+       __u32 zcull_region_header_size;
+       /**
+        * @zcull_subregion_header_size: the subregion header size in bytes,
+        * which is used for save/restore operations on a region
+        */
+       __u32 zcull_subregion_header_size;
+       /**
+        * @subregion_count: the total number of subregions the hardware
+        * supports
+        */
+       __u32 subregion_count;
+       /**
+        * @subregion_width_align_pixels: required alignment for subregion
+        * widths, in pixels (typically #TPC's * 16).
+        */
+       __u32 subregion_width_align_pixels;
+       /**
+        * @subregion_height_align_pixels: required alignment for subregion
+        * heights, in pixels
+        */
+       __u32 subregion_height_align_pixels;
+
+       /**
+        * @ctxsw_size: the size, in bytes, of a zcull context switching region.
+        * Will be zero if the kernel does not support zcull context switching.
+        */
+       __u32 ctxsw_size;
+       /**
+        * @ctxsw_align: the alignment, in bytes, of a zcull context switching
+        * region
+        */
+       __u32 ctxsw_align;
+};
+
 #define DRM_NOUVEAU_GETPARAM           0x00
 #define DRM_NOUVEAU_SETPARAM           0x01 /* deprecated */
 #define DRM_NOUVEAU_CHANNEL_ALLOC      0x02
@@ -445,6 +508,7 @@ struct drm_nouveau_exec {
 #define DRM_NOUVEAU_VM_INIT            0x10
 #define DRM_NOUVEAU_VM_BIND            0x11
 #define DRM_NOUVEAU_EXEC               0x12
+#define DRM_NOUVEAU_GET_ZCULL_INFO     0x13
 #define DRM_NOUVEAU_GEM_NEW            0x40
 #define DRM_NOUVEAU_GEM_PUSHBUF        0x41
 #define DRM_NOUVEAU_GEM_CPU_PREP       0x42
@@ -513,6 +577,8 @@ struct drm_nouveau_svm_bind {
 #define DRM_IOCTL_NOUVEAU_VM_INIT            DRM_IOWR(DRM_COMMAND_BASE + DRM_NOUVEAU_VM_INIT, struct drm_nouveau_vm_init)
 #define DRM_IOCTL_NOUVEAU_VM_BIND            DRM_IOWR(DRM_COMMAND_BASE + DRM_NOUVEAU_VM_BIND, struct drm_nouveau_vm_bind)
 #define DRM_IOCTL_NOUVEAU_EXEC               DRM_IOWR(DRM_COMMAND_BASE + DRM_NOUVEAU_EXEC, struct drm_nouveau_exec)
+
+#define DRM_IOCTL_NOUVEAU_GET_ZCULL_INFO     DRM_IOR (DRM_COMMAND_BASE + DRM_NOUVEAU_GET_ZCULL_INFO, struct drm_nouveau_get_zcull_info)
 #if defined(__cplusplus)
 }
 #endif