[Intel-gfx] [PATCH] drm/i915/dg2: Tile 4 plane format support
Nanley Chery
nanleychery at gmail.com
Mon Nov 22 22:08:31 UTC 2021
Hi Stanislav,
Are there IGT tests for this modifier?
On Mon, Nov 22, 2021 at 4:14 PM Stanislav Lisovskiy
<stanislav.lisovskiy at intel.com> wrote:
>
> TileF(Tile4 in bspec) format is 4K tile organized into
> 64B subtiles with same basic shape as for legacy TileY
> which will be supported by Display13.
>
> v2: - Fixed wrong case condition(Jani Nikula)
> - Increased I915_FORMAT_MOD_F_TILED up to 12(Imre Deak)
>
> v3: - s/I915_TILING_F/TILING_4/g
> - s/I915_FORMAT_MOD_F_TILED/I915_FORMAT_MOD_4_TILED/g
> - Removed unneeded fencing code
>
> v4: - Rebased, fixed merge conflict with new table-oriented
> format modifier checking(Stan)
> - Replaced the rest of "Tile F" mentions to "Tile 4"(Stan)
>
> v5: - Still had to remove some Tile F mentionings
> - Moved has_4tile from adlp to DG2(Ramalingam C)
> - Check specifically for DG2, but not the Display13(Imre)
>
> v6: - Moved Tile4 assocating struct for modifier/display to
> the beginning(Imre Deak)
> - Removed unneeded case I915_FORMAT_MOD_4_TILED modifier
> checks(Imre Deak)
> - Fixed I915_FORMAT_MOD_4_TILED to be 9 instead of 12
> (Imre Deak)
>
> v7: - Fixed display_ver to { 13, 13 }(Imre Deak)
> - Removed redundant newline(Imre Deak)
>
> Reviewed-by: Imre Deak <imre.deak at intel.com>
> Cc: Imre Deak <imre.deak at intel.com>
> Cc: Matt Roper <matthew.d.roper at intel.com>
> Cc: Maarten Lankhorst <maarten.lankhorst at linux.intel.com>
> Signed-off-by: Stanislav Lisovskiy <stanislav.lisovskiy at intel.com>
> Signed-off-by: Matt Roper <matthew.d.roper at intel.com>
> Signed-off-by: Juha-Pekka Heikkilä <juha-pekka.heikkila at intel.com>
> ---
> drivers/gpu/drm/i915/display/intel_display.c | 1 +
> drivers/gpu/drm/i915/display/intel_fb.c | 9 +++++++++
> drivers/gpu/drm/i915/display/intel_fbc.c | 1 +
> .../drm/i915/display/intel_plane_initial.c | 1 +
> .../drm/i915/display/skl_universal_plane.c | 20 +++++++++++--------
> drivers/gpu/drm/i915/i915_drv.h | 1 +
> drivers/gpu/drm/i915/i915_pci.c | 1 +
> drivers/gpu/drm/i915/i915_reg.h | 1 +
> drivers/gpu/drm/i915/intel_device_info.h | 1 +
> drivers/gpu/drm/i915/intel_pm.c | 1 +
> include/uapi/drm/drm_fourcc.h | 8 ++++++++
> 11 files changed, 37 insertions(+), 8 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
> index f3c9208a30b1..7429965d3682 100644
> --- a/drivers/gpu/drm/i915/display/intel_display.c
> +++ b/drivers/gpu/drm/i915/display/intel_display.c
> @@ -7766,6 +7766,7 @@ static int intel_atomic_check_async(struct intel_atomic_state *state, struct int
> case I915_FORMAT_MOD_X_TILED:
> case I915_FORMAT_MOD_Y_TILED:
> case I915_FORMAT_MOD_Yf_TILED:
> + case I915_FORMAT_MOD_4_TILED:
> break;
> default:
> drm_dbg_kms(&i915->drm,
> diff --git a/drivers/gpu/drm/i915/display/intel_fb.c b/drivers/gpu/drm/i915/display/intel_fb.c
> index c4a743d0913f..b7f1ef62072c 100644
> --- a/drivers/gpu/drm/i915/display/intel_fb.c
> +++ b/drivers/gpu/drm/i915/display/intel_fb.c
> @@ -139,6 +139,9 @@ struct intel_modifier_desc {
>
> static const struct intel_modifier_desc intel_modifiers[] = {
> {
> + .modifier = I915_FORMAT_MOD_4_TILED,
> + .display_ver = { 13, 13 },
I see that every other modifier has the plane_cap field set. Why is it
okay for it to be zero here?
> + }, {
> .modifier = I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS,
> .display_ver = { 12, 13 },
> .plane_caps = INTEL_PLANE_CAP_TILING_Y | INTEL_PLANE_CAP_CCS_MC,
> @@ -544,6 +547,12 @@ intel_tile_width_bytes(const struct drm_framebuffer *fb, int color_plane)
> return 128;
> else
> return 512;
> + case I915_FORMAT_MOD_4_TILED:
> + /*
> + * Each 4K tile consists of 64B(8*8) subtiles, with
> + * same shape as Y Tile(i.e 4*16B OWords)
> + */
> + return 128;
> case I915_FORMAT_MOD_Y_TILED_CCS:
> if (intel_fb_is_ccs_aux_plane(fb, color_plane))
> return 128;
> diff --git a/drivers/gpu/drm/i915/display/intel_fbc.c b/drivers/gpu/drm/i915/display/intel_fbc.c
> index d0c34bc3af6c..0ceabe40d8c9 100644
> --- a/drivers/gpu/drm/i915/display/intel_fbc.c
> +++ b/drivers/gpu/drm/i915/display/intel_fbc.c
> @@ -898,6 +898,7 @@ static bool tiling_is_valid(struct drm_i915_private *i915,
> case I915_FORMAT_MOD_Y_TILED:
> case I915_FORMAT_MOD_Yf_TILED:
> return DISPLAY_VER(i915) >= 9;
> + case I915_FORMAT_MOD_4_TILED:
The tile Y cases above check the display version. Should we do the same here?
> case I915_FORMAT_MOD_X_TILED:
> return true;
> default:
> diff --git a/drivers/gpu/drm/i915/display/intel_plane_initial.c b/drivers/gpu/drm/i915/display/intel_plane_initial.c
> index dcd698a02da2..d80855ee9b96 100644
> --- a/drivers/gpu/drm/i915/display/intel_plane_initial.c
> +++ b/drivers/gpu/drm/i915/display/intel_plane_initial.c
> @@ -125,6 +125,7 @@ intel_alloc_initial_plane_obj(struct intel_crtc *crtc,
> case DRM_FORMAT_MOD_LINEAR:
> case I915_FORMAT_MOD_X_TILED:
> case I915_FORMAT_MOD_Y_TILED:
> + case I915_FORMAT_MOD_4_TILED:
> break;
> default:
> drm_dbg(&dev_priv->drm,
> diff --git a/drivers/gpu/drm/i915/display/skl_universal_plane.c b/drivers/gpu/drm/i915/display/skl_universal_plane.c
> index 28890876bdeb..e5cda5bcbde4 100644
> --- a/drivers/gpu/drm/i915/display/skl_universal_plane.c
> +++ b/drivers/gpu/drm/i915/display/skl_universal_plane.c
> @@ -751,6 +751,8 @@ static u32 skl_plane_ctl_tiling(u64 fb_modifier)
> return PLANE_CTL_TILED_X;
> case I915_FORMAT_MOD_Y_TILED:
> return PLANE_CTL_TILED_Y;
> + case I915_FORMAT_MOD_4_TILED:
> + return PLANE_CTL_TILED_4;
> case I915_FORMAT_MOD_Y_TILED_CCS:
> case I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS_CC:
> return PLANE_CTL_TILED_Y | PLANE_CTL_RENDER_DECOMPRESSION_ENABLE;
> @@ -1971,9 +1973,7 @@ static bool gen12_plane_format_mod_supported(struct drm_plane *_plane,
> case DRM_FORMAT_Y216:
> case DRM_FORMAT_XVYU12_16161616:
> case DRM_FORMAT_XVYU16161616:
> - if (modifier == DRM_FORMAT_MOD_LINEAR ||
> - modifier == I915_FORMAT_MOD_X_TILED ||
> - modifier == I915_FORMAT_MOD_Y_TILED)
> + if (!intel_fb_is_ccs_modifier(modifier))
> return true;
> fallthrough;
> default:
> @@ -2299,11 +2299,15 @@ skl_get_initial_plane_config(struct intel_crtc *crtc,
> else
> fb->modifier = I915_FORMAT_MOD_Y_TILED;
> break;
> - case PLANE_CTL_TILED_YF:
> - if (val & PLANE_CTL_RENDER_DECOMPRESSION_ENABLE)
> - fb->modifier = I915_FORMAT_MOD_Yf_TILED_CCS;
> - else
> - fb->modifier = I915_FORMAT_MOD_Yf_TILED;
> + case PLANE_CTL_TILED_YF: /* aka PLANE_CTL_TILED_4 on XE_LPD+ */
To be safe, maybe add a static_assert(PLANE_CTL_TILED_YF ==
PLANE_CTL_TILED_4); ?
> + if (HAS_4TILE(dev_priv)) {
> + fb->modifier = I915_FORMAT_MOD_4_TILED;
> + } else {
> + if (val & PLANE_CTL_RENDER_DECOMPRESSION_ENABLE)
> + fb->modifier = I915_FORMAT_MOD_Yf_TILED_CCS;
> + else
> + fb->modifier = I915_FORMAT_MOD_Yf_TILED;
> + }
> break;
> default:
> MISSING_CASE(tiling);
> diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
> index 1bfadd9127fc..3d90bd732e91 100644
> --- a/drivers/gpu/drm/i915/i915_drv.h
> +++ b/drivers/gpu/drm/i915/i915_drv.h
> @@ -1627,6 +1627,7 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915,
> #define CMDPARSER_USES_GGTT(dev_priv) (GRAPHICS_VER(dev_priv) == 7)
>
> #define HAS_LLC(dev_priv) (INTEL_INFO(dev_priv)->has_llc)
> +#define HAS_4TILE(dev_priv) (INTEL_INFO(dev_priv)->has_4tile)
> #define HAS_SNOOP(dev_priv) (INTEL_INFO(dev_priv)->has_snoop)
> #define HAS_EDRAM(dev_priv) ((dev_priv)->edram_size_mb)
> #define HAS_SECURE_BATCHES(dev_priv) (GRAPHICS_VER(dev_priv) < 6)
> diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c
> index f01cba4ec283..403d3a581ce7 100644
> --- a/drivers/gpu/drm/i915/i915_pci.c
> +++ b/drivers/gpu/drm/i915/i915_pci.c
> @@ -1044,6 +1044,7 @@ static const struct intel_device_info dg2_info = {
> DGFX_FEATURES,
> .graphics.rel = 55,
> .media.rel = 55,
> + .has_4tile = 1,
> PLATFORM(INTEL_DG2),
> .platform_engine_mask =
> BIT(RCS0) | BIT(BCS0) |
> diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
> index 3450818802c2..22d18a292430 100644
> --- a/drivers/gpu/drm/i915/i915_reg.h
> +++ b/drivers/gpu/drm/i915/i915_reg.h
> @@ -7284,6 +7284,7 @@ enum {
> #define PLANE_CTL_TILED_X (1 << 10)
> #define PLANE_CTL_TILED_Y (4 << 10)
> #define PLANE_CTL_TILED_YF (5 << 10)
> +#define PLANE_CTL_TILED_4 (5 << 10)
> #define PLANE_CTL_ASYNC_FLIP (1 << 9)
> #define PLANE_CTL_FLIP_HORIZONTAL (1 << 8)
> #define PLANE_CTL_MEDIA_DECOMPRESSION_ENABLE (1 << 4) /* TGL+ */
> diff --git a/drivers/gpu/drm/i915/intel_device_info.h b/drivers/gpu/drm/i915/intel_device_info.h
> index 669f0d26c3c3..67177e18704a 100644
> --- a/drivers/gpu/drm/i915/intel_device_info.h
> +++ b/drivers/gpu/drm/i915/intel_device_info.h
> @@ -125,6 +125,7 @@ enum intel_ppgtt_type {
> func(has_64bit_reloc); \
> func(gpu_reset_clobbers_display); \
> func(has_reset_engine); \
> + func(has_4tile); \
> func(has_global_mocs); \
> func(has_gt_uc); \
> func(has_l3_dpf); \
> diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
> index 01fa3fac1b57..167704f0acf0 100644
> --- a/drivers/gpu/drm/i915/intel_pm.c
> +++ b/drivers/gpu/drm/i915/intel_pm.c
> @@ -5386,6 +5386,7 @@ skl_compute_wm_params(const struct intel_crtc_state *crtc_state,
> }
>
> wp->y_tiled = modifier == I915_FORMAT_MOD_Y_TILED ||
> + modifier == I915_FORMAT_MOD_4_TILED ||
> modifier == I915_FORMAT_MOD_Yf_TILED ||
> modifier == I915_FORMAT_MOD_Y_TILED_CCS ||
> modifier == I915_FORMAT_MOD_Yf_TILED_CCS;
> diff --git a/include/uapi/drm/drm_fourcc.h b/include/uapi/drm/drm_fourcc.h
> index 7f652c96845b..41184a94935d 100644
> --- a/include/uapi/drm/drm_fourcc.h
> +++ b/include/uapi/drm/drm_fourcc.h
> @@ -564,6 +564,14 @@ extern "C" {
> * pitch is required to be a multiple of 4 tile widths.
> */
> #define I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS_CC fourcc_mod_code(INTEL, 8)
> +/*
> + * Intel F-tiling(aka Tile4) layout
> + *
v4 and v5 attempted to get rid of the F-tile references, but this was
left behind.
> + * This is a tiled layout using 4Kb tiles in row-major layout.
> + * Within the tile pixels are laid out in 64 byte units / sub-tiles in OWORD
> + * (16 bytes) chunks column-major..
I can't picture how tile 4 is organized from this description. Could
we update it?
Here's a draft I came up with when wondering how I might do this myself:
* This is a tiled layout using 4KB tiles in a row-major layout. It has the same
* shape as Tile Y at two granularities: 4KB (128B x 32) and 64B (16B x 4). It
* only differs from Tile Y at the 256B granularity in between. At this
* granularity, Tile Y has a shape of 16B x 32 rows, but this tiling has a shape
* of 64B x 8 rows.
-Nanley
> + */
> +#define I915_FORMAT_MOD_4_TILED fourcc_mod_code(INTEL, 9)
>
> /*
> * Tiled, NV12MT, grouped in 64 (pixels) x 32 (lines) -sized macroblocks
> --
> 2.24.1.485.gad05a3d8e5
>
More information about the Intel-gfx
mailing list