linux-kernel - [PATCH 4.8 025/125] drm/i915/gen9: minimum scanlines for Y tile is not always 4

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20161029134948.262651731@linuxfoundation.org>
Date:   Sat, 29 Oct 2016 09:49:03 -0400
From:   Greg Kroah-Hartman <gregkh@...uxfoundation.org>
To:     linux-kernel@...r.kernel.org
Cc:     Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
        stable@...r.kernel.org,
        Maarten Lankhorst <maarten.lankhorst@...ux.intel.com>,
        Paulo Zanoni <paulo.r.zanoni@...el.com>,
        Jani Nikula <jani.nikula@...el.com>
Subject: [PATCH 4.8 025/125] drm/i915/gen9: minimum scanlines for Y tile is not always 4

4.8-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Paulo Zanoni <paulo.r.zanoni@...el.com>

commit ccc1057477bc99678896b51adce6b6ee4019dc37 upstream.

During watermarks calculations, this value is used in 3 different
places. Only one of them was not using a hardcoded 4. Move the code up
so everybody can benefit from the actual value.

This should only help on situations with Y tiling + 90/270 rotation +
1 or 2 bpp or NV12.

Reviewed-by: Maarten Lankhorst <maarten.lankhorst@...ux.intel.com>
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@...el.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1474578035-424-6-git-send-email-paulo.r.zanoni@intel.com
(cherry picked from commit 1186fa85eb9b3cc0589990fbc39617e50e38759a)
Signed-off-by: Jani Nikula <jani.nikula@...el.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@...uxfoundation.org>

---
 drivers/gpu/drm/i915/intel_pm.c |   56 ++++++++++++++++++++++------------------
 1 file changed, 32 insertions(+), 24 deletions(-)

--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -3476,7 +3476,8 @@ static uint32_t skl_wm_method1(uint32_t
 
 static uint32_t skl_wm_method2(uint32_t pixel_rate, uint32_t pipe_htotal,
 			       uint32_t horiz_pixels, uint8_t cpp,
-			       uint64_t tiling, uint32_t latency)
+			       uint64_t tiling, uint32_t latency,
+			       uint32_t y_min_scanlines)
 {
 	uint32_t ret;
 	uint32_t plane_bytes_per_line, plane_blocks_per_line;
@@ -3489,9 +3490,9 @@ static uint32_t skl_wm_method2(uint32_t
 
 	if (tiling == I915_FORMAT_MOD_Y_TILED ||
 	    tiling == I915_FORMAT_MOD_Yf_TILED) {
-		plane_bytes_per_line *= 4;
+		plane_bytes_per_line *= y_min_scanlines;
 		plane_blocks_per_line = DIV_ROUND_UP(plane_bytes_per_line, 512);
-		plane_blocks_per_line /= 4;
+		plane_blocks_per_line /= y_min_scanlines;
 	} else if (tiling == DRM_FORMAT_MOD_NONE) {
 		plane_blocks_per_line = DIV_ROUND_UP(plane_bytes_per_line, 512) + 1;
 	} else {
@@ -3548,6 +3549,7 @@ static int skl_compute_plane_wm(const st
 	uint8_t cpp;
 	uint32_t width = 0, height = 0;
 	uint32_t plane_pixel_rate;
+	uint32_t y_min_scanlines;
 
 	if (latency == 0 || !cstate->base.active || !intel_pstate->visible) {
 		*enabled = false;
@@ -3563,38 +3565,44 @@ static int skl_compute_plane_wm(const st
 	cpp = drm_format_plane_cpp(fb->pixel_format, 0);
 	plane_pixel_rate = skl_adjusted_plane_pixel_rate(cstate, intel_pstate);
 
+	if (intel_rotation_90_or_270(pstate->rotation)) {
+		int cpp = (fb->pixel_format == DRM_FORMAT_NV12) ?
+			drm_format_plane_cpp(fb->pixel_format, 1) :
+			drm_format_plane_cpp(fb->pixel_format, 0);
+
+		switch (cpp) {
+		case 1:
+			y_min_scanlines = 16;
+			break;
+		case 2:
+			y_min_scanlines = 8;
+			break;
+		default:
+			WARN(1, "Unsupported pixel depth for rotation");
+		case 4:
+			y_min_scanlines = 4;
+			break;
+		}
+	} else {
+		y_min_scanlines = 4;
+	}
+
 	method1 = skl_wm_method1(plane_pixel_rate, cpp, latency);
 	method2 = skl_wm_method2(plane_pixel_rate,
 				 cstate->base.adjusted_mode.crtc_htotal,
 				 width,
 				 cpp,
 				 fb->modifier[0],
-				 latency);
+				 latency,
+				 y_min_scanlines);
 
 	plane_bytes_per_line = width * cpp;
 	plane_blocks_per_line = DIV_ROUND_UP(plane_bytes_per_line, 512);
 
 	if (fb->modifier[0] == I915_FORMAT_MOD_Y_TILED ||
 	    fb->modifier[0] == I915_FORMAT_MOD_Yf_TILED) {
-		uint32_t min_scanlines = 4;
-		uint32_t y_tile_minimum;
-		if (intel_rotation_90_or_270(pstate->rotation)) {
-			int cpp = (fb->pixel_format == DRM_FORMAT_NV12) ?
-				drm_format_plane_cpp(fb->pixel_format, 1) :
-				drm_format_plane_cpp(fb->pixel_format, 0);
-
-			switch (cpp) {
-			case 1:
-				min_scanlines = 16;
-				break;
-			case 2:
-				min_scanlines = 8;
-				break;
-			case 8:
-				WARN(1, "Unsupported pixel depth for rotation");
-			}
-		}
-		y_tile_minimum = plane_blocks_per_line * min_scanlines;
+		uint32_t y_tile_minimum = plane_blocks_per_line *
+					  y_min_scanlines;
 		selected_result = max(method2, y_tile_minimum);
 	} else {
 		if ((ddb_allocation / plane_blocks_per_line) >= 1)
@@ -3609,7 +3617,7 @@ static int skl_compute_plane_wm(const st
 	if (level >= 1 && level <= 7) {
 		if (fb->modifier[0] == I915_FORMAT_MOD_Y_TILED ||
 		    fb->modifier[0] == I915_FORMAT_MOD_Yf_TILED)
-			res_lines += 4;
+			res_lines += y_min_scanlines;
 		else
 			res_blocks++;
 	}