All of lore.kernel.org
 help / color / mirror / Atom feed
From: Vidya Srinivas <vidya.srinivas@intel.com>
To: intel-gfx@lists.freedesktop.org
Cc: ville.syrjala@intel.com,
	Vidya Srinivas <vidya.srinivas@intel.com>,
	maarten.lankhorst@intel.com
Subject: [PATCH v15 02/18] drm/i915/skl+: refactor WM calculation for NV12
Date: Mon, 26 Mar 2018 09:28:09 +0530	[thread overview]
Message-ID: <1522036705-10536-3-git-send-email-vidya.srinivas@intel.com> (raw)
In-Reply-To: <1522036705-10536-1-git-send-email-vidya.srinivas@intel.com>

From: Mahesh Kumar <mahesh1.kumar@intel.com>

Current code calculates DDB for planar formats in such a way that we
store DDB of plane-0 in plane 1 & vice-versa.
In order to make this clean this patch refactors WM/DDB calculation for
NV12 planar formats.

v2: Addressed review comments by Maarten

v3: Rebased and addressed review comments by Maarten

v4: Fixed a compilation issue of string replacement is_nv12 to
is_planar

v5: Added reviewed by from Juha-Pekka Heikkila

Reviewed-by: Juha-Pekka Heikkila <juhapekka.heikkila@gmail.com>
Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Signed-off-by: Mahesh Kumar <mahesh1.kumar@intel.com>
Signed-off-by: Vidya Srinivas <vidya.srinivas@intel.com>
---
 drivers/gpu/drm/i915/i915_drv.h  |   5 +-
 drivers/gpu/drm/i915/intel_drv.h |   1 +
 drivers/gpu/drm/i915/intel_pm.c  | 121 ++++++++++++++++++++-------------------
 3 files changed, 66 insertions(+), 61 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index fbea1c2..a99cf24 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1181,8 +1181,9 @@ static inline bool skl_ddb_entry_equal(const struct skl_ddb_entry *e1,
 }
 
 struct skl_ddb_allocation {
-	struct skl_ddb_entry plane[I915_MAX_PIPES][I915_MAX_PLANES]; /* packed/uv */
-	struct skl_ddb_entry y_plane[I915_MAX_PIPES][I915_MAX_PLANES];
+	/* packed/y */
+	struct skl_ddb_entry plane[I915_MAX_PIPES][I915_MAX_PLANES];
+	struct skl_ddb_entry uv_plane[I915_MAX_PIPES][I915_MAX_PLANES];
 };
 
 struct skl_ddb_values {
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 1dfb323..62493ff 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -599,6 +599,7 @@ struct intel_pipe_wm {
 struct skl_plane_wm {
 	struct skl_wm_level wm[8];
 	struct skl_wm_level trans_wm;
+	bool is_planar;
 };
 
 struct skl_pipe_wm {
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index c8bd899..37caa18 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -4009,9 +4009,9 @@ int skl_check_pipe_max_pixel_rate(struct intel_crtc *intel_crtc,
 static unsigned int
 skl_plane_relative_data_rate(const struct intel_crtc_state *cstate,
 			     const struct drm_plane_state *pstate,
-			     int y)
+			     const int plane)
 {
-	struct intel_plane *plane = to_intel_plane(pstate->plane);
+	struct intel_plane *intel_plane = to_intel_plane(pstate->plane);
 	struct intel_plane_state *intel_pstate = to_intel_plane_state(pstate);
 	uint32_t data_rate;
 	uint32_t width = 0, height = 0;
@@ -4025,9 +4025,9 @@ skl_plane_relative_data_rate(const struct intel_crtc_state *cstate,
 	fb = pstate->fb;
 	format = fb->format->format;
 
-	if (plane->id == PLANE_CURSOR)
+	if (intel_plane->id == PLANE_CURSOR)
 		return 0;
-	if (y && format != DRM_FORMAT_NV12)
+	if (plane == 1 && format != DRM_FORMAT_NV12)
 		return 0;
 
 	/*
@@ -4038,19 +4038,14 @@ skl_plane_relative_data_rate(const struct intel_crtc_state *cstate,
 	width = drm_rect_width(&intel_pstate->base.src) >> 16;
 	height = drm_rect_height(&intel_pstate->base.src) >> 16;
 
-	/* for planar format */
-	if (format == DRM_FORMAT_NV12) {
-		if (y)  /* y-plane data rate */
-			data_rate = width * height *
-				fb->format->cpp[0];
-		else    /* uv-plane data rate */
-			data_rate = (width / 2) * (height / 2) *
-				fb->format->cpp[1];
-	} else {
-		/* for packed formats */
-		data_rate = width * height * fb->format->cpp[0];
+	/* UV plane does 1/2 pixel sub-sampling */
+	if (plane == 1 && format == DRM_FORMAT_NV12) {
+		width /= 2;
+		height /= 2;
 	}
 
+	data_rate = width * height * fb->format->cpp[plane];
+
 	down_scale_amount = skl_plane_downscale_amount(cstate, intel_pstate);
 
 	return mul_round_up_u32_fixed16(data_rate, down_scale_amount);
@@ -4063,8 +4058,8 @@ skl_plane_relative_data_rate(const struct intel_crtc_state *cstate,
  */
 static unsigned int
 skl_get_total_relative_data_rate(struct intel_crtc_state *intel_cstate,
-				 unsigned *plane_data_rate,
-				 unsigned *plane_y_data_rate)
+				 unsigned int *plane_data_rate,
+				 unsigned int *uv_plane_data_rate)
 {
 	struct drm_crtc_state *cstate = &intel_cstate->base;
 	struct drm_atomic_state *state = cstate->state;
@@ -4080,17 +4075,17 @@ skl_get_total_relative_data_rate(struct intel_crtc_state *intel_cstate,
 		enum plane_id plane_id = to_intel_plane(plane)->id;
 		unsigned int rate;
 
-		/* packed/uv */
+		/* packed/y */
 		rate = skl_plane_relative_data_rate(intel_cstate,
 						    pstate, 0);
 		plane_data_rate[plane_id] = rate;
 
 		total_data_rate += rate;
 
-		/* y-plane */
+		/* uv-plane */
 		rate = skl_plane_relative_data_rate(intel_cstate,
 						    pstate, 1);
-		plane_y_data_rate[plane_id] = rate;
+		uv_plane_data_rate[plane_id] = rate;
 
 		total_data_rate += rate;
 	}
@@ -4099,8 +4094,7 @@ skl_get_total_relative_data_rate(struct intel_crtc_state *intel_cstate,
 }
 
 static uint16_t
-skl_ddb_min_alloc(const struct drm_plane_state *pstate,
-		  const int y)
+skl_ddb_min_alloc(const struct drm_plane_state *pstate, const int plane)
 {
 	struct drm_framebuffer *fb = pstate->fb;
 	struct intel_plane_state *intel_pstate = to_intel_plane_state(pstate);
@@ -4111,8 +4105,8 @@ skl_ddb_min_alloc(const struct drm_plane_state *pstate,
 	if (WARN_ON(!fb))
 		return 0;
 
-	/* For packed formats, no y-plane, return 0 */
-	if (y && fb->format->format != DRM_FORMAT_NV12)
+	/* For packed formats, and uv-plane, return 0 */
+	if (plane == 1 && fb->format->format != DRM_FORMAT_NV12)
 		return 0;
 
 	/* For Non Y-tile return 8-blocks */
@@ -4131,15 +4125,12 @@ skl_ddb_min_alloc(const struct drm_plane_state *pstate,
 	src_h = drm_rect_height(&intel_pstate->base.src) >> 16;
 
 	/* Halve UV plane width and height for NV12 */
-	if (fb->format->format == DRM_FORMAT_NV12 && !y) {
+	if (plane == 1) {
 		src_w /= 2;
 		src_h /= 2;
 	}
 
-	if (fb->format->format == DRM_FORMAT_NV12 && !y)
-		plane_bpp = fb->format->cpp[1];
-	else
-		plane_bpp = fb->format->cpp[0];
+	plane_bpp = fb->format->cpp[plane];
 
 	if (drm_rotation_90_or_270(pstate->rotation)) {
 		switch (plane_bpp) {
@@ -4167,7 +4158,7 @@ skl_ddb_min_alloc(const struct drm_plane_state *pstate,
 
 static void
 skl_ddb_calc_min(const struct intel_crtc_state *cstate, int num_active,
-		 uint16_t *minimum, uint16_t *y_minimum)
+		 uint16_t *minimum, uint16_t *uv_minimum)
 {
 	const struct drm_plane_state *pstate;
 	struct drm_plane *plane;
@@ -4182,7 +4173,7 @@ skl_ddb_calc_min(const struct intel_crtc_state *cstate, int num_active,
 			continue;
 
 		minimum[plane_id] = skl_ddb_min_alloc(pstate, 0);
-		y_minimum[plane_id] = skl_ddb_min_alloc(pstate, 1);
+		uv_minimum[plane_id] = skl_ddb_min_alloc(pstate, 1);
 	}
 
 	minimum[PLANE_CURSOR] = skl_cursor_allocation(num_active);
@@ -4200,17 +4191,17 @@ skl_allocate_pipe_ddb(struct intel_crtc_state *cstate,
 	struct skl_ddb_entry *alloc = &cstate->wm.skl.ddb;
 	uint16_t alloc_size, start;
 	uint16_t minimum[I915_MAX_PLANES] = {};
-	uint16_t y_minimum[I915_MAX_PLANES] = {};
+	uint16_t uv_minimum[I915_MAX_PLANES] = {};
 	unsigned int total_data_rate;
 	enum plane_id plane_id;
 	int num_active;
-	unsigned plane_data_rate[I915_MAX_PLANES] = {};
-	unsigned plane_y_data_rate[I915_MAX_PLANES] = {};
+	unsigned int plane_data_rate[I915_MAX_PLANES] = {};
+	unsigned int uv_plane_data_rate[I915_MAX_PLANES] = {};
 	uint16_t total_min_blocks = 0;
 
 	/* Clear the partitioning for disabled planes. */
 	memset(ddb->plane[pipe], 0, sizeof(ddb->plane[pipe]));
-	memset(ddb->y_plane[pipe], 0, sizeof(ddb->y_plane[pipe]));
+	memset(ddb->uv_plane[pipe], 0, sizeof(ddb->uv_plane[pipe]));
 
 	if (WARN_ON(!state))
 		return 0;
@@ -4225,7 +4216,7 @@ skl_allocate_pipe_ddb(struct intel_crtc_state *cstate,
 	if (alloc_size == 0)
 		return 0;
 
-	skl_ddb_calc_min(cstate, num_active, minimum, y_minimum);
+	skl_ddb_calc_min(cstate, num_active, minimum, uv_minimum);
 
 	/*
 	 * 1. Allocate the mininum required blocks for each active plane
@@ -4235,7 +4226,7 @@ skl_allocate_pipe_ddb(struct intel_crtc_state *cstate,
 
 	for_each_plane_id_on_crtc(intel_crtc, plane_id) {
 		total_min_blocks += minimum[plane_id];
-		total_min_blocks += y_minimum[plane_id];
+		total_min_blocks += uv_minimum[plane_id];
 	}
 
 	if (total_min_blocks > alloc_size) {
@@ -4257,14 +4248,14 @@ skl_allocate_pipe_ddb(struct intel_crtc_state *cstate,
 	 */
 	total_data_rate = skl_get_total_relative_data_rate(cstate,
 							   plane_data_rate,
-							   plane_y_data_rate);
+							   uv_plane_data_rate);
 	if (total_data_rate == 0)
 		return 0;
 
 	start = alloc->start;
 	for_each_plane_id_on_crtc(intel_crtc, plane_id) {
-		unsigned int data_rate, y_data_rate;
-		uint16_t plane_blocks, y_plane_blocks = 0;
+		unsigned int data_rate, uv_data_rate;
+		uint16_t plane_blocks, uv_plane_blocks;
 
 		if (plane_id == PLANE_CURSOR)
 			continue;
@@ -4288,21 +4279,20 @@ skl_allocate_pipe_ddb(struct intel_crtc_state *cstate,
 
 		start += plane_blocks;
 
-		/*
-		 * allocation for y_plane part of planar format:
-		 */
-		y_data_rate = plane_y_data_rate[plane_id];
+		/* Allocate DDB for UV plane for planar format/NV12 */
+		uv_data_rate = uv_plane_data_rate[plane_id];
 
-		y_plane_blocks = y_minimum[plane_id];
-		y_plane_blocks += div_u64((uint64_t)alloc_size * y_data_rate,
-					total_data_rate);
+		uv_plane_blocks = uv_minimum[plane_id];
+		uv_plane_blocks += div_u64((uint64_t)alloc_size * uv_data_rate,
+					   total_data_rate);
 
-		if (y_data_rate) {
-			ddb->y_plane[pipe][plane_id].start = start;
-			ddb->y_plane[pipe][plane_id].end = start + y_plane_blocks;
+		if (uv_data_rate) {
+			ddb->uv_plane[pipe][plane_id].start = start;
+			ddb->uv_plane[pipe][plane_id].end =
+				start + uv_plane_blocks;
 		}
 
-		start += y_plane_blocks;
+		start += uv_plane_blocks;
 	}
 
 	return 0;
@@ -4430,8 +4420,7 @@ skl_compute_plane_wm_params(const struct drm_i915_private *dev_priv,
 		wp->width = drm_rect_width(&intel_pstate->base.src) >> 16;
 	}
 
-	wp->cpp = (fb->format->format == DRM_FORMAT_NV12) ? fb->format->cpp[1] :
-							    fb->format->cpp[0];
+	wp->cpp = fb->format->cpp[0];
 	wp->plane_pixel_rate = skl_adjusted_plane_pixel_rate(cstate,
 							     intel_pstate);
 
@@ -4660,6 +4649,9 @@ skl_compute_wm_levels(const struct drm_i915_private *dev_priv,
 			return ret;
 	}
 
+	if (intel_pstate->base.fb->format->format == DRM_FORMAT_NV12)
+		wm->is_planar = true;
+
 	return 0;
 }
 
@@ -4833,10 +4825,21 @@ static void skl_write_plane_wm(struct intel_crtc *intel_crtc,
 
 	skl_ddb_entry_write(dev_priv, PLANE_BUF_CFG(pipe, plane_id),
 			    &ddb->plane[pipe][plane_id]);
-	if (INTEL_GEN(dev_priv) < 11)
+	if (INTEL_GEN(dev_priv) >= 11)
+		return skl_ddb_entry_write(dev_priv,
+					   PLANE_BUF_CFG(pipe, plane_id),
+					   &ddb->plane[pipe][plane_id]);
+	if (wm->is_planar) {
+		skl_ddb_entry_write(dev_priv, PLANE_BUF_CFG(pipe, plane_id),
+				    &ddb->uv_plane[pipe][plane_id]);
 		skl_ddb_entry_write(dev_priv,
 				    PLANE_NV12_BUF_CFG(pipe, plane_id),
-				    &ddb->y_plane[pipe][plane_id]);
+				    &ddb->plane[pipe][plane_id]);
+	} else {
+		skl_ddb_entry_write(dev_priv, PLANE_BUF_CFG(pipe, plane_id),
+				    &ddb->plane[pipe][plane_id]);
+		I915_WRITE(PLANE_NV12_BUF_CFG(pipe, plane_id), 0x0);
+	}
 }
 
 static void skl_write_cursor_wm(struct intel_crtc *intel_crtc,
@@ -4951,8 +4954,8 @@ skl_ddb_add_affected_planes(struct intel_crtc_state *cstate)
 
 		if (skl_ddb_entry_equal(&cur_ddb->plane[pipe][plane_id],
 					&new_ddb->plane[pipe][plane_id]) &&
-		    skl_ddb_entry_equal(&cur_ddb->y_plane[pipe][plane_id],
-					&new_ddb->y_plane[pipe][plane_id]))
+		    skl_ddb_entry_equal(&cur_ddb->uv_plane[pipe][plane_id],
+					&new_ddb->uv_plane[pipe][plane_id]))
 			continue;
 
 		plane_state = drm_atomic_get_plane_state(state, plane);
@@ -5046,8 +5049,8 @@ skl_copy_ddb_for_pipe(struct skl_ddb_values *dst,
 		      struct skl_ddb_values *src,
 		      enum pipe pipe)
 {
-	memcpy(dst->ddb.y_plane[pipe], src->ddb.y_plane[pipe],
-	       sizeof(dst->ddb.y_plane[pipe]));
+	memcpy(dst->ddb.uv_plane[pipe], src->ddb.uv_plane[pipe],
+	       sizeof(dst->ddb.uv_plane[pipe]));
 	memcpy(dst->ddb.plane[pipe], src->ddb.plane[pipe],
 	       sizeof(dst->ddb.plane[pipe]));
 }
-- 
2.7.4

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

  parent reply	other threads:[~2018-03-26  4:01 UTC|newest]

Thread overview: 20+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-03-26  3:58 [PATCH v15 00/18] Add NV12 support Vidya Srinivas
2018-03-26  3:58 ` [PATCH v15 01/18] drm/i915/skl+: rename skl_wm_values struct to skl_ddb_values Vidya Srinivas
2018-03-26  3:58 ` Vidya Srinivas [this message]
2018-03-26  3:58 ` [PATCH v15 03/18] drm/i915/skl+: add NV12 in skl_format_to_fourcc Vidya Srinivas
2018-03-26  3:58 ` [PATCH v15 04/18] drm/i915/skl+: support verification of DDB HW state for NV12 Vidya Srinivas
2018-03-26  3:58 ` [PATCH v15 05/18] drm/i915/skl+: NV12 related changes for WM Vidya Srinivas
2018-03-26  3:58 ` [PATCH v15 06/18] drm/i915/skl+: pass skl_wm_level struct to wm compute func Vidya Srinivas
2018-03-26  3:58 ` [PATCH v15 07/18] drm/i915/skl+: make sure higher latency level has higher wm value Vidya Srinivas
2018-03-26  3:58 ` [PATCH v15 08/18] drm/i915/skl+: nv12 workaround disable WM level 1-7 Vidya Srinivas
2018-03-26  3:58 ` [PATCH v15 09/18] drm/i915/skl: split skl_compute_ddb function Vidya Srinivas
2018-03-26  3:58 ` [PATCH v15 10/18] drm/i915: Set scaler mode for NV12 Vidya Srinivas
2018-03-26  3:58 ` [PATCH v15 11/18] drm/i915: Update format_is_yuv() to include NV12 Vidya Srinivas
2018-03-26  3:58 ` [PATCH v15 12/18] drm/i915: Upscale scaler max scale for NV12 Vidya Srinivas
2018-03-26  3:58 ` [PATCH v15 13/18] drm/i915: Add NV12 as supported format for primary plane Vidya Srinivas
2018-03-26  3:58 ` [PATCH v15 14/18] drm/i915: Add NV12 as supported format for sprite plane Vidya Srinivas
2018-03-26  3:58 ` [PATCH v15 15/18] drm/i915: Add NV12 support to intel_framebuffer_init Vidya Srinivas
2018-03-26  3:58 ` [PATCH v15 16/18] drm/i915: Enable YUV to RGB for Gen10 in Plane Ctrl Reg Vidya Srinivas
2018-03-26  3:58 ` [PATCH v15 17/18] drm/i915: Display WA 827 Vidya Srinivas
2018-03-26  3:58 ` [PATCH v15 18/18] drm/i915: Add checks to primary plane Vidya Srinivas
2018-03-26  4:05 ` ✗ Fi.CI.BAT: failure for Add NV12 support (rev3) Patchwork

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1522036705-10536-3-git-send-email-vidya.srinivas@intel.com \
    --to=vidya.srinivas@intel.com \
    --cc=intel-gfx@lists.freedesktop.org \
    --cc=maarten.lankhorst@intel.com \
    --cc=ville.syrjala@intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.