From patchwork Thu Jun 1 12:19:17 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: "Govindapillai, Vinod" X-Patchwork-Id: 13263636 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from gabe.freedesktop.org (gabe.freedesktop.org [131.252.210.177]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.lore.kernel.org (Postfix) with ESMTPS id C8512C77B7A for ; Thu, 1 Jun 2023 12:19:44 +0000 (UTC) Received: from gabe.freedesktop.org (localhost [127.0.0.1]) by gabe.freedesktop.org (Postfix) with ESMTP id 4BF7B10E240; Thu, 1 Jun 2023 12:19:44 +0000 (UTC) Received: from mga06.intel.com (mga06b.intel.com [134.134.136.31]) by gabe.freedesktop.org (Postfix) with ESMTPS id 4BB1110E240 for ; Thu, 1 Jun 2023 12:19:42 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1685621982; x=1717157982; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=RFlNjFT/kR+wU2SDb7bJFfNcSGMLfuxHva0MBtyTvzc=; b=bTR95kPvmhqEuxorawWov026d5vRAkcDj1WSO0/qhDP0FkgoW5+knAry nARaz9omGq313sNI74kZjs4CU6oPYvBjDZJyqIH2DMqPrqPsFEJBzphBS ygeuMTNQgX7Tu006O0B0NywPHx9tmYaQhw+qbueXliiHLb/M2US510ZJZ 0ZU431qwLz0uZre1NgqMFOfRR7HiiGVEKdAjsDf2O57Ne3YN5qOAe/ENN PGZF1Ag88YstUwJOrOEu5i14jlEa7b2N+RhqEnKs92IGJ1Ngvn5Bj8VWA 2cBO0q0eYwIsZtCkgppM8X2ButI1OKFK3zpS+UaFbVkVpWGq9/AegjUst g==; X-IronPort-AV: E=McAfee;i="6600,9927,10727"; a="419040017" X-IronPort-AV: E=Sophos;i="6.00,210,1681196400"; d="scan'208";a="419040017" Received: from orsmga001.jf.intel.com ([10.7.209.18]) by orsmga104.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 01 Jun 2023 05:19:42 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=McAfee;i="6600,9927,10727"; a="740336137" X-IronPort-AV: E=Sophos;i="6.00,210,1681196400"; d="scan'208";a="740336137" Received: from unknown (HELO vgovind2-mobl3.fi.intel.com) ([10.237.66.43]) by orsmga001-auth.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 01 Jun 2023 05:19:39 -0700 From: Vinod Govindapillai To: intel-gfx@lists.freedesktop.org Date: Thu, 1 Jun 2023 15:19:17 +0300 Message-Id: <20230601121923.19775-2-vinod.govindapillai@intel.com> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20230601121923.19775-1-vinod.govindapillai@intel.com> References: <20230601121923.19775-1-vinod.govindapillai@intel.com> MIME-Version: 1.0 Organization: Intel Finland Oy - BIC 0357606-4 - Westendinkatu 7, 02160 Espoo Subject: [Intel-gfx] [PATCH v11 1/7] drm/i915: fix the derating percentage for MTL X-BeenThere: intel-gfx@lists.freedesktop.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Intel graphics driver community testing & development List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: ville.syrjala@intel.com Errors-To: intel-gfx-bounces@lists.freedesktop.org Sender: "Intel-gfx" Follow the values from bspec for the percentage overhead for efficiency in MTL BW calculations. Bspec: 64631 Signed-off-by: Vinod Govindapillai Reviewed-by: Matt Roper --- drivers/gpu/drm/i915/display/intel_bw.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/display/intel_bw.c b/drivers/gpu/drm/i915/display/intel_bw.c index 597d5816ad1b..ab405c48ca3a 100644 --- a/drivers/gpu/drm/i915/display/intel_bw.c +++ b/drivers/gpu/drm/i915/display/intel_bw.c @@ -379,7 +379,7 @@ static const struct intel_sa_info mtl_sa_info = { .deburst = 32, .deprogbwlimit = 38, /* GB/s */ .displayrtids = 256, - .derating = 20, + .derating = 10, }; static int icl_get_bw_info(struct drm_i915_private *dev_priv, const struct intel_sa_info *sa) From patchwork Thu Jun 1 12:19:18 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: "Govindapillai, Vinod" X-Patchwork-Id: 13263637 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from gabe.freedesktop.org (gabe.freedesktop.org [131.252.210.177]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.lore.kernel.org (Postfix) with ESMTPS id 32F81C77B7E for ; Thu, 1 Jun 2023 12:19:50 +0000 (UTC) Received: from gabe.freedesktop.org (localhost [127.0.0.1]) by gabe.freedesktop.org (Postfix) with ESMTP id AF76110E551; Thu, 1 Jun 2023 12:19:49 +0000 (UTC) Received: from mga06.intel.com (mga06b.intel.com [134.134.136.31]) by gabe.freedesktop.org (Postfix) with ESMTPS id AA90310E24B for ; Thu, 1 Jun 2023 12:19:47 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1685621987; x=1717157987; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=hyfATA09M4kDbLsYonI0B8aDA1XKZzvWiKBrlGzM7qc=; b=JgYu+iKFxxokceNnXuYUlGWBNC1cRODvPHnsyFKS6kMVwPlaBoTv/9M8 7+MQtSn6sloGTLIo6y0spoqE3YMgOlWYGJ45n3noqIpG3lWQJJDdGeks1 S6V2yHPY+tbOfUBN6GfAykzT4qCBmhEQ5mn9Smi47uSA/kiCvmpXr4WPU iGfwObSRuNuuYhHzQQhD28Mf8ItiMz+taTRqYcLQCUqChSe70GybR4+pE +sh/S6vGaEgyPfG+cTxyXIRgKpL1IIqHT6VLVHFXb6+4aET2R/GEWrI/v 9VSkUggCWSn5QSxpA7Cvf+bNHXJAkEHrXFU9nC9gogO6eldIg+rOMdsI2 Q==; X-IronPort-AV: E=McAfee;i="6600,9927,10727"; a="419040027" X-IronPort-AV: E=Sophos;i="6.00,210,1681196400"; d="scan'208,223";a="419040027" Received: from orsmga001.jf.intel.com ([10.7.209.18]) by orsmga104.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 01 Jun 2023 05:19:47 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=McAfee;i="6600,9927,10727"; a="740336148" X-IronPort-AV: E=Sophos;i="6.00,210,1681196400"; d="scan'208,223";a="740336148" Received: from unknown (HELO vgovind2-mobl3.fi.intel.com) ([10.237.66.43]) by orsmga001-auth.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 01 Jun 2023 05:19:44 -0700 From: Vinod Govindapillai To: intel-gfx@lists.freedesktop.org Date: Thu, 1 Jun 2023 15:19:18 +0300 Message-Id: <20230601121923.19775-3-vinod.govindapillai@intel.com> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20230601121923.19775-1-vinod.govindapillai@intel.com> References: <20230601121923.19775-1-vinod.govindapillai@intel.com> MIME-Version: 1.0 Organization: Intel Finland Oy - BIC 0357606-4 - Westendinkatu 7, 02160 Espoo Subject: [Intel-gfx] [PATCH v11 2/7] drm/i915: update the QGV point frequency calculations X-BeenThere: intel-gfx@lists.freedesktop.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Intel graphics driver community testing & development List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: ville.syrjala@intel.com Errors-To: intel-gfx-bounces@lists.freedesktop.org Sender: "Intel-gfx" From MTL onwwards, pcode locks the QGV point based on peak BW of the intended QGV point passed by the driver. So the peak BW calculation must match the value expected by the pcode. Update the calculations as per the Bspec. v2: use DIV_ROUND_* macro for the calculations (Ville) v3: Use only DIV_ROUN_CLOSEST and remove divisor / 2 again Bspec: 64636 Signed-off-by: Vinod Govindapillai Reviewed-by: Stanislav Lisovskiy --- drivers/gpu/drm/i915/display/intel_bw.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/display/intel_bw.c b/drivers/gpu/drm/i915/display/intel_bw.c index ab405c48ca3a..61b3babf2d83 100644 --- a/drivers/gpu/drm/i915/display/intel_bw.c +++ b/drivers/gpu/drm/i915/display/intel_bw.c @@ -182,7 +182,7 @@ static int mtl_read_qgv_point_info(struct drm_i915_private *dev_priv, val2 = intel_uncore_read(&dev_priv->uncore, MTL_MEM_SS_INFO_QGV_POINT_HIGH(point)); dclk = REG_FIELD_GET(MTL_DCLK_MASK, val); - sp->dclk = DIV_ROUND_UP((16667 * dclk), 1000); + sp->dclk = DIV_ROUND_CLOSEST(16667 * dclk, 1000); sp->t_rp = REG_FIELD_GET(MTL_TRP_MASK, val); sp->t_rcd = REG_FIELD_GET(MTL_TRCD_MASK, val); From patchwork Thu Jun 1 12:19:19 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: "Govindapillai, Vinod" X-Patchwork-Id: 13263638 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from gabe.freedesktop.org (gabe.freedesktop.org [131.252.210.177]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.lore.kernel.org (Postfix) with ESMTPS id 49D1DC77B7A for ; Thu, 1 Jun 2023 12:19:53 +0000 (UTC) Received: from gabe.freedesktop.org (localhost [127.0.0.1]) by gabe.freedesktop.org (Postfix) with ESMTP id C236710E24B; Thu, 1 Jun 2023 12:19:52 +0000 (UTC) Received: from mga06.intel.com (mga06b.intel.com [134.134.136.31]) by gabe.freedesktop.org (Postfix) with ESMTPS id CEE4D10E555 for ; Thu, 1 Jun 2023 12:19:51 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1685621991; x=1717157991; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=p8Diu7wJvA1Zw8sv4HsHEvjH8ejD5ov2eUbJduRJN4A=; b=N8KF3opbZgCIK2HTfqpbzytpT2zx9tuc8VYLwC/0BzIoE3NfkG4wqL1b lgUoLujCXe6a8nbgtYn0RxgluHWMgxYrTEb75Z+mn//I6lFkXBUE51H9l ygNx87hcY34M+9pCZnKKeK+vzXlk/ndTIDDas+7zggF92Ch83S27KCnZU iNa5R64wjMqV2Kxf6BtPEoa0MSjyWyFzH1k85phhKwu6QeIFXW5iux04O GxQOQeb9OeJi/7rA2gd7h7Blh47R3AKl2S7uEpINsrX7lHCZ+G6hvyZr9 dixQLAfPNS4LOC3xqWEZY1PowewoTI1KGIZpcedr/KXPtnABf6mv6QDJO w==; X-IronPort-AV: E=McAfee;i="6600,9927,10727"; a="419040038" X-IronPort-AV: E=Sophos;i="6.00,210,1681196400"; d="scan'208";a="419040038" Received: from orsmga001.jf.intel.com ([10.7.209.18]) by orsmga104.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 01 Jun 2023 05:19:51 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=McAfee;i="6600,9927,10727"; a="740336154" X-IronPort-AV: E=Sophos;i="6.00,210,1681196400"; d="scan'208";a="740336154" Received: from unknown (HELO vgovind2-mobl3.fi.intel.com) ([10.237.66.43]) by orsmga001-auth.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 01 Jun 2023 05:19:48 -0700 From: Vinod Govindapillai To: intel-gfx@lists.freedesktop.org Date: Thu, 1 Jun 2023 15:19:19 +0300 Message-Id: <20230601121923.19775-4-vinod.govindapillai@intel.com> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20230601121923.19775-1-vinod.govindapillai@intel.com> References: <20230601121923.19775-1-vinod.govindapillai@intel.com> MIME-Version: 1.0 Organization: Intel Finland Oy - BIC 0357606-4 - Westendinkatu 7, 02160 Espoo Subject: [Intel-gfx] [PATCH v11 3/7] drm/i915: store the peak bw per QGV point X-BeenThere: intel-gfx@lists.freedesktop.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Intel graphics driver community testing & development List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: ville.syrjala@intel.com Errors-To: intel-gfx-bounces@lists.freedesktop.org Sender: "Intel-gfx" In MTL onwards, pcode locks the GV point based on the peak BW of a QGV point. So store the peak BW of all the QGV points. v2: use DIV_ROUND_CLOSEST() for the peakBW calculation Bspec: 64636 Signed-off-by: Vinod Govindapillai Reviewed-by: Stanislav Lisovskiy --- drivers/gpu/drm/i915/display/intel_bw.c | 8 ++++++-- drivers/gpu/drm/i915/display/intel_display_core.h | 2 ++ 2 files changed, 8 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/i915/display/intel_bw.c b/drivers/gpu/drm/i915/display/intel_bw.c index 61b3babf2d83..b792d307e9d5 100644 --- a/drivers/gpu/drm/i915/display/intel_bw.c +++ b/drivers/gpu/drm/i915/display/intel_bw.c @@ -534,10 +534,14 @@ static int tgl_get_bw_info(struct drm_i915_private *dev_priv, const struct intel bi->deratedbw[j] = min(maxdebw, bw * (100 - sa->derating) / 100); + bi->peakbw[j] = DIV_ROUND_CLOSEST(sp->dclk * + num_channels * + qi.channel_width, 8); drm_dbg_kms(&dev_priv->drm, - "BW%d / QGV %d: num_planes=%d deratedbw=%u\n", - i, j, bi->num_planes, bi->deratedbw[j]); + "BW%d / QGV %d: num_planes=%d deratedbw=%u peakbw: %u\n", + i, j, bi->num_planes, bi->deratedbw[j], + bi->peakbw[j]); } for (j = 0; j < qi.num_psf_points; j++) { diff --git a/drivers/gpu/drm/i915/display/intel_display_core.h b/drivers/gpu/drm/i915/display/intel_display_core.h index 2209811eb29e..dd8e08c8598f 100644 --- a/drivers/gpu/drm/i915/display/intel_display_core.h +++ b/drivers/gpu/drm/i915/display/intel_display_core.h @@ -314,6 +314,8 @@ struct intel_display { unsigned int deratedbw[I915_NUM_QGV_POINTS]; /* for each PSF GV point */ unsigned int psf_bw[I915_NUM_PSF_GV_POINTS]; + /* Peak BW for each QGV point */ + unsigned int peakbw[I915_NUM_QGV_POINTS]; u8 num_qgv_points; u8 num_psf_gv_points; u8 num_planes; From patchwork Thu Jun 1 12:19:20 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: "Govindapillai, Vinod" X-Patchwork-Id: 13263639 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from gabe.freedesktop.org (gabe.freedesktop.org [131.252.210.177]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.lore.kernel.org (Postfix) with ESMTPS id 84A8FC7EE29 for ; Thu, 1 Jun 2023 12:19:58 +0000 (UTC) Received: from gabe.freedesktop.org (localhost [127.0.0.1]) by gabe.freedesktop.org (Postfix) with ESMTP id 160A610E02B; Thu, 1 Jun 2023 12:19:58 +0000 (UTC) Received: from mga06.intel.com (mga06b.intel.com [134.134.136.31]) by gabe.freedesktop.org (Postfix) with ESMTPS id 8739F10E02B for ; Thu, 1 Jun 2023 12:19:56 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1685621996; x=1717157996; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=XPDwWIaXS7gitexGHnVtMNj92widGCCHY6N2HeSBtrA=; b=BkPf0VKWXR3/2ts/1uEZVr+vlj4FvS/NGMZRlio5rU8J5+CgPVWuLuBT qXGVBy2GltoW3gsmPl+TzLjNckIyMnLvrSUmHms6nkrUAkab5iGDnwuQc XkHnyVcX8ai2lJs+yCFfDogWtw2E/ZRHNXQeY5u52aANYAOaowasEciZd gBRc7v9RN9rMVixb7bUtgzG+HFyUQCXEFF4Bqjhr19OPDDqPPoCzyJfLt /EHN+2cvnc43JtGLwRMRwS9L0cYMP1AOSrZpfo53oDdljOSbX42ohJXka XN3j33FX/0ZkkMu4lc9uydO/pg7MdE8be4HXnxlwlYdtEwdfner4d7Ge5 A==; X-IronPort-AV: E=McAfee;i="6600,9927,10727"; a="419040053" X-IronPort-AV: E=Sophos;i="6.00,210,1681196400"; d="scan'208";a="419040053" Received: from orsmga001.jf.intel.com ([10.7.209.18]) by orsmga104.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 01 Jun 2023 05:19:56 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=McAfee;i="6600,9927,10727"; a="740336169" X-IronPort-AV: E=Sophos;i="6.00,210,1681196400"; d="scan'208";a="740336169" Received: from unknown (HELO vgovind2-mobl3.fi.intel.com) ([10.237.66.43]) by orsmga001-auth.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 01 Jun 2023 05:19:52 -0700 From: Vinod Govindapillai To: intel-gfx@lists.freedesktop.org Date: Thu, 1 Jun 2023 15:19:20 +0300 Message-Id: <20230601121923.19775-5-vinod.govindapillai@intel.com> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20230601121923.19775-1-vinod.govindapillai@intel.com> References: <20230601121923.19775-1-vinod.govindapillai@intel.com> MIME-Version: 1.0 Organization: Intel Finland Oy - BIC 0357606-4 - Westendinkatu 7, 02160 Espoo Subject: [Intel-gfx] [PATCH v11 4/7] drm/i915: extract intel_bw_check_qgv_points() X-BeenThere: intel-gfx@lists.freedesktop.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Intel graphics driver community testing & development List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: ville.syrjala@intel.com Errors-To: intel-gfx-bounces@lists.freedesktop.org Sender: "Intel-gfx" Extract intel_bw_check_qgv_points() from intel_bw_atomic_check to facilitate future platform variations in handling SAGV configurations. Signed-off-by: Vinod Govindapillai Reviewed-by: Stanislav Lisovskiy --- drivers/gpu/drm/i915/display/intel_bw.c | 235 +++++++++++++----------- 1 file changed, 130 insertions(+), 105 deletions(-) diff --git a/drivers/gpu/drm/i915/display/intel_bw.c b/drivers/gpu/drm/i915/display/intel_bw.c index b792d307e9d5..56b3975f3ccb 100644 --- a/drivers/gpu/drm/i915/display/intel_bw.c +++ b/drivers/gpu/drm/i915/display/intel_bw.c @@ -803,6 +803,128 @@ intel_atomic_get_bw_state(struct intel_atomic_state *state) return to_intel_bw_state(bw_state); } +static int icl_find_qgv_points(struct drm_i915_private *i915, + unsigned int data_rate, + unsigned int num_active_planes, + const struct intel_bw_state *old_bw_state, + struct intel_bw_state *new_bw_state) +{ + unsigned int max_bw_point = 0; + unsigned int max_bw = 0; + unsigned int num_psf_gv_points = i915->display.bw.max[0].num_psf_gv_points; + unsigned int num_qgv_points = i915->display.bw.max[0].num_qgv_points; + u16 psf_points = 0; + u16 qgv_points = 0; + int i; + int ret; + + ret = intel_atomic_lock_global_state(&new_bw_state->base); + if (ret) + return ret; + + for (i = 0; i < num_qgv_points; i++) { + unsigned int max_data_rate; + + if (DISPLAY_VER(i915) > 11) + max_data_rate = tgl_max_bw(i915, num_active_planes, i); + else + max_data_rate = icl_max_bw(i915, num_active_planes, i); + /* + * We need to know which qgv point gives us + * maximum bandwidth in order to disable SAGV + * if we find that we exceed SAGV block time + * with watermarks. By that moment we already + * have those, as it is calculated earlier in + * intel_atomic_check, + */ + if (max_data_rate > max_bw) { + max_bw_point = i; + max_bw = max_data_rate; + } + if (max_data_rate >= data_rate) + qgv_points |= BIT(i); + + drm_dbg_kms(&i915->drm, "QGV point %d: max bw %d required %d\n", + i, max_data_rate, data_rate); + } + + for (i = 0; i < num_psf_gv_points; i++) { + unsigned int max_data_rate = adl_psf_bw(i915, i); + + if (max_data_rate >= data_rate) + psf_points |= BIT(i); + + drm_dbg_kms(&i915->drm, "PSF GV point %d: max bw %d" + " required %d\n", + i, max_data_rate, data_rate); + } + + /* + * BSpec states that we always should have at least one allowed point + * left, so if we couldn't - simply reject the configuration for obvious + * reasons. + */ + if (qgv_points == 0) { + drm_dbg_kms(&i915->drm, "No QGV points provide sufficient memory" + " bandwidth %d for display configuration(%d active planes).\n", + data_rate, num_active_planes); + return -EINVAL; + } + + if (num_psf_gv_points > 0 && psf_points == 0) { + drm_dbg_kms(&i915->drm, "No PSF GV points provide sufficient memory" + " bandwidth %d for display configuration(%d active planes).\n", + data_rate, num_active_planes); + return -EINVAL; + } + + /* + * Leave only single point with highest bandwidth, if + * we can't enable SAGV due to the increased memory latency it may + * cause. + */ + if (!intel_can_enable_sagv(i915, new_bw_state)) { + qgv_points = BIT(max_bw_point); + drm_dbg_kms(&i915->drm, "No SAGV, using single QGV point %d\n", + max_bw_point); + } + + /* + * We store the ones which need to be masked as that is what PCode + * actually accepts as a parameter. + */ + new_bw_state->qgv_points_mask = + ~(ICL_PCODE_REQ_QGV_PT(qgv_points) | + ADLS_PCODE_REQ_PSF_PT(psf_points)) & + icl_qgv_points_mask(i915); + + /* + * If the actual mask had changed we need to make sure that + * the commits are serialized(in case this is a nomodeset, nonblocking) + */ + if (new_bw_state->qgv_points_mask != old_bw_state->qgv_points_mask) { + ret = intel_atomic_serialize_global_state(&new_bw_state->base); + if (ret) + return ret; + } + + return 0; +} + +static int intel_bw_check_qgv_points(struct drm_i915_private *i915, + const struct intel_bw_state *old_bw_state, + struct intel_bw_state *new_bw_state) +{ + unsigned int data_rate = intel_bw_data_rate(i915, new_bw_state); + unsigned int num_active_planes = + intel_bw_num_active_planes(i915, new_bw_state); + + data_rate = DIV_ROUND_UP(data_rate, 1000); + + return icl_find_qgv_points(i915, data_rate, num_active_planes, + old_bw_state, new_bw_state); +} + static bool intel_bw_state_changed(struct drm_i915_private *i915, const struct intel_bw_state *old_bw_state, const struct intel_bw_state *new_bw_state) @@ -1049,20 +1171,14 @@ static int intel_bw_check_data_rate(struct intel_atomic_state *state, bool *chan int intel_bw_atomic_check(struct intel_atomic_state *state) { - struct drm_i915_private *dev_priv = to_i915(state->base.dev); - const struct intel_bw_state *old_bw_state; - struct intel_bw_state *new_bw_state; - unsigned int data_rate; - unsigned int num_active_planes; - int i, ret; - u16 qgv_points = 0, psf_points = 0; - unsigned int max_bw_point = 0, max_bw = 0; - unsigned int num_qgv_points = dev_priv->display.bw.max[0].num_qgv_points; - unsigned int num_psf_gv_points = dev_priv->display.bw.max[0].num_psf_gv_points; bool changed = false; + struct drm_i915_private *i915 = to_i915(state->base.dev); + struct intel_bw_state *new_bw_state; + const struct intel_bw_state *old_bw_state; + int ret; /* FIXME earlier gens need some checks too */ - if (DISPLAY_VER(dev_priv) < 11) + if (DISPLAY_VER(i915) < 11) return 0; ret = intel_bw_check_data_rate(state, &changed); @@ -1073,8 +1189,8 @@ int intel_bw_atomic_check(struct intel_atomic_state *state) new_bw_state = intel_atomic_get_new_bw_state(state); if (new_bw_state && - intel_can_enable_sagv(dev_priv, old_bw_state) != - intel_can_enable_sagv(dev_priv, new_bw_state)) + intel_can_enable_sagv(i915, old_bw_state) != + intel_can_enable_sagv(i915, new_bw_state)) changed = true; /* @@ -1084,101 +1200,10 @@ int intel_bw_atomic_check(struct intel_atomic_state *state) if (!changed) return 0; - ret = intel_atomic_lock_global_state(&new_bw_state->base); + ret = intel_bw_check_qgv_points(i915, old_bw_state, new_bw_state); if (ret) return ret; - data_rate = intel_bw_data_rate(dev_priv, new_bw_state); - data_rate = DIV_ROUND_UP(data_rate, 1000); - - num_active_planes = intel_bw_num_active_planes(dev_priv, new_bw_state); - - for (i = 0; i < num_qgv_points; i++) { - unsigned int max_data_rate; - - if (DISPLAY_VER(dev_priv) > 11) - max_data_rate = tgl_max_bw(dev_priv, num_active_planes, i); - else - max_data_rate = icl_max_bw(dev_priv, num_active_planes, i); - /* - * We need to know which qgv point gives us - * maximum bandwidth in order to disable SAGV - * if we find that we exceed SAGV block time - * with watermarks. By that moment we already - * have those, as it is calculated earlier in - * intel_atomic_check, - */ - if (max_data_rate > max_bw) { - max_bw_point = i; - max_bw = max_data_rate; - } - if (max_data_rate >= data_rate) - qgv_points |= BIT(i); - - drm_dbg_kms(&dev_priv->drm, "QGV point %d: max bw %d required %d\n", - i, max_data_rate, data_rate); - } - - for (i = 0; i < num_psf_gv_points; i++) { - unsigned int max_data_rate = adl_psf_bw(dev_priv, i); - - if (max_data_rate >= data_rate) - psf_points |= BIT(i); - - drm_dbg_kms(&dev_priv->drm, "PSF GV point %d: max bw %d" - " required %d\n", - i, max_data_rate, data_rate); - } - - /* - * BSpec states that we always should have at least one allowed point - * left, so if we couldn't - simply reject the configuration for obvious - * reasons. - */ - if (qgv_points == 0) { - drm_dbg_kms(&dev_priv->drm, "No QGV points provide sufficient memory" - " bandwidth %d for display configuration(%d active planes).\n", - data_rate, num_active_planes); - return -EINVAL; - } - - if (num_psf_gv_points > 0 && psf_points == 0) { - drm_dbg_kms(&dev_priv->drm, "No PSF GV points provide sufficient memory" - " bandwidth %d for display configuration(%d active planes).\n", - data_rate, num_active_planes); - return -EINVAL; - } - - /* - * Leave only single point with highest bandwidth, if - * we can't enable SAGV due to the increased memory latency it may - * cause. - */ - if (!intel_can_enable_sagv(dev_priv, new_bw_state)) { - qgv_points = BIT(max_bw_point); - drm_dbg_kms(&dev_priv->drm, "No SAGV, using single QGV point %d\n", - max_bw_point); - } - - /* - * We store the ones which need to be masked as that is what PCode - * actually accepts as a parameter. - */ - new_bw_state->qgv_points_mask = - ~(ICL_PCODE_REQ_QGV_PT(qgv_points) | - ADLS_PCODE_REQ_PSF_PT(psf_points)) & - icl_qgv_points_mask(dev_priv); - - /* - * If the actual mask had changed we need to make sure that - * the commits are serialized(in case this is a nomodeset, nonblocking) - */ - if (new_bw_state->qgv_points_mask != old_bw_state->qgv_points_mask) { - ret = intel_atomic_serialize_global_state(&new_bw_state->base); - if (ret) - return ret; - } - return 0; } From patchwork Thu Jun 1 12:19:21 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: "Govindapillai, Vinod" X-Patchwork-Id: 13263640 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from gabe.freedesktop.org (gabe.freedesktop.org [131.252.210.177]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.lore.kernel.org (Postfix) with ESMTPS id D7AD7C77B7E for ; Thu, 1 Jun 2023 12:20:02 +0000 (UTC) Received: from gabe.freedesktop.org (localhost [127.0.0.1]) by gabe.freedesktop.org (Postfix) with ESMTP id 6E40E10E555; Thu, 1 Jun 2023 12:20:02 +0000 (UTC) Received: from mga06.intel.com (mga06b.intel.com [134.134.136.31]) by gabe.freedesktop.org (Postfix) with ESMTPS id E0BCA10E555 for ; Thu, 1 Jun 2023 12:20:00 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1685622000; x=1717158000; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=6YL/oJGHickUiahL4FdNBLu7zUkFf867Tq4brz/OQBM=; b=mvyq3vUwajzktjdbYgfu4gx0LP1yiqwhdy8HaHjRdsqbavUxkwh9syEV 9knJHvW0f7A4qoeZWnVfCjrywEI9nBcm8HwCkVS98tp3eOwrb7NQOz08O +W7NfCn9j6zRPR1qTnQULe2wkr4NneHp28pB+ypWm+UZG4iYf9D45gdq2 z6lMs8hGu/fNwZ/XmEXUdKAFq0/G759QdZnHXka/k/n5vYzsZVvAFzk94 pa1UwLghJ8/7t3w3vOpsT7bmz0TAgeevzaInpFiZlyGVznltvdB/oMqt0 HTP+ptwLBYBCC2Nrkt33KuTwtS0G5dOoFfexaPCIPUICGZ2AakSazGEC2 A==; X-IronPort-AV: E=McAfee;i="6600,9927,10727"; a="419040061" X-IronPort-AV: E=Sophos;i="6.00,210,1681196400"; d="scan'208";a="419040061" Received: from orsmga001.jf.intel.com ([10.7.209.18]) by orsmga104.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 01 Jun 2023 05:20:00 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=McAfee;i="6600,9927,10727"; a="740336184" X-IronPort-AV: E=Sophos;i="6.00,210,1681196400"; d="scan'208";a="740336184" Received: from unknown (HELO vgovind2-mobl3.fi.intel.com) ([10.237.66.43]) by orsmga001-auth.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 01 Jun 2023 05:19:57 -0700 From: Vinod Govindapillai To: intel-gfx@lists.freedesktop.org Date: Thu, 1 Jun 2023 15:19:21 +0300 Message-Id: <20230601121923.19775-6-vinod.govindapillai@intel.com> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20230601121923.19775-1-vinod.govindapillai@intel.com> References: <20230601121923.19775-1-vinod.govindapillai@intel.com> MIME-Version: 1.0 Organization: Intel Finland Oy - BIC 0357606-4 - Westendinkatu 7, 02160 Espoo Subject: [Intel-gfx] [PATCH v11 5/7] drm/i915: modify max_bw to return index to intel_bw_info X-BeenThere: intel-gfx@lists.freedesktop.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Intel graphics driver community testing & development List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: ville.syrjala@intel.com Errors-To: intel-gfx-bounces@lists.freedesktop.org Sender: "Intel-gfx" MTL uses the peak BW of a QGV point to lock the required QGV point instead of the QGV index. Instead of passing the deratedbw of the selected bw_info, return the index to the selected bw_info so that either deratedbw or peakbw can be used based on the platform. v2: use idx to store index returned by max_bw_index functions v3: return UINT_MAX in icl_max_bw_index in case no match found v3: check idx >= ARRAY_SIZE Signed-off-by: Vinod Govindapillai Reviewed-by: Stanislav Lisovskiy --- drivers/gpu/drm/i915/display/intel_bw.c | 27 ++++++++++++++++--------- 1 file changed, 17 insertions(+), 10 deletions(-) diff --git a/drivers/gpu/drm/i915/display/intel_bw.c b/drivers/gpu/drm/i915/display/intel_bw.c index 56b3975f3ccb..b1cbeda0b2e3 100644 --- a/drivers/gpu/drm/i915/display/intel_bw.c +++ b/drivers/gpu/drm/i915/display/intel_bw.c @@ -593,8 +593,8 @@ static void dg2_get_bw_info(struct drm_i915_private *i915) i915->display.sagv.status = I915_SAGV_NOT_CONTROLLED; } -static unsigned int icl_max_bw(struct drm_i915_private *dev_priv, - int num_planes, int qgv_point) +static unsigned int icl_max_bw_index(struct drm_i915_private *dev_priv, + int num_planes, int qgv_point) { int i; @@ -615,14 +615,14 @@ static unsigned int icl_max_bw(struct drm_i915_private *dev_priv, return UINT_MAX; if (num_planes >= bi->num_planes) - return bi->deratedbw[qgv_point]; + return i; } - return 0; + return UINT_MAX; } -static unsigned int tgl_max_bw(struct drm_i915_private *dev_priv, - int num_planes, int qgv_point) +static unsigned int tgl_max_bw_index(struct drm_i915_private *dev_priv, + int num_planes, int qgv_point) { int i; @@ -643,10 +643,10 @@ static unsigned int tgl_max_bw(struct drm_i915_private *dev_priv, return UINT_MAX; if (num_planes <= bi->num_planes) - return bi->deratedbw[qgv_point]; + return i; } - return dev_priv->display.bw.max[0].deratedbw[qgv_point]; + return 0; } static unsigned int adl_psf_bw(struct drm_i915_private *dev_priv, @@ -823,12 +823,19 @@ static int icl_find_qgv_points(struct drm_i915_private *i915, return ret; for (i = 0; i < num_qgv_points; i++) { + unsigned int idx; unsigned int max_data_rate; if (DISPLAY_VER(i915) > 11) - max_data_rate = tgl_max_bw(i915, num_active_planes, i); + idx = tgl_max_bw_index(i915, num_active_planes, i); else - max_data_rate = icl_max_bw(i915, num_active_planes, i); + idx = icl_max_bw_index(i915, num_active_planes, i); + + if (idx >= ARRAY_SIZE(i915->display.bw.max)) + continue; + + max_data_rate = i915->display.bw.max[idx].deratedbw[i]; + /* * We need to know which qgv point gives us * maximum bandwidth in order to disable SAGV From patchwork Thu Jun 1 12:19:22 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: "Govindapillai, Vinod" X-Patchwork-Id: 13263641 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from gabe.freedesktop.org (gabe.freedesktop.org [131.252.210.177]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.lore.kernel.org (Postfix) with ESMTPS id AFE94C77B7E for ; Thu, 1 Jun 2023 12:20:09 +0000 (UTC) Received: from gabe.freedesktop.org (localhost [127.0.0.1]) by gabe.freedesktop.org (Postfix) with ESMTP id 4F76110E55A; Thu, 1 Jun 2023 12:20:09 +0000 (UTC) Received: from mga06.intel.com (mga06b.intel.com [134.134.136.31]) by gabe.freedesktop.org (Postfix) with ESMTPS id 8A29C10E55A for ; Thu, 1 Jun 2023 12:20:07 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1685622007; x=1717158007; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=i56j+AsLzARKA9u4bHAP9ta4xLf7fG6gYXB4gP9+8hs=; b=Elw6aYMQ+7HLrMVb7JEwPd66yfndEUurQm7XL2gvgUbfJLEuO5osHuJ8 I8U9nL+FBpoEPZHE1/XDUe6HazfeAr13ieYpbFVd2CdLnSaFdPl6zz5UF XyYkkAJX0Bo05pdDEEorxu1auFSkR++67U/HVH4P6heaIwktlREgrMPo6 D7yOMZPirHDfMK10zyB48XIiDKxawMMWIvQ7WOkkh7sJAUzKimznAi0+0 Q0lLsEUtIRcLu037zYBgR/jazY2RHRZfdjuwE5CUykhI2fI2DSnG4r5go hRrLSlPnH9BxiatTS/nfsOEyiv4nh/778iPxvHqZTn/925oQY7bic9MSf A==; X-IronPort-AV: E=McAfee;i="6600,9927,10727"; a="419040088" X-IronPort-AV: E=Sophos;i="6.00,210,1681196400"; d="scan'208,223";a="419040088" Received: from orsmga001.jf.intel.com ([10.7.209.18]) by orsmga104.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 01 Jun 2023 05:20:07 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=McAfee;i="6600,9927,10727"; a="740336240" X-IronPort-AV: E=Sophos;i="6.00,210,1681196400"; d="scan'208,223";a="740336240" Received: from unknown (HELO vgovind2-mobl3.fi.intel.com) ([10.237.66.43]) by orsmga001-auth.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 01 Jun 2023 05:20:04 -0700 From: Vinod Govindapillai To: intel-gfx@lists.freedesktop.org Date: Thu, 1 Jun 2023 15:19:22 +0300 Message-Id: <20230601121923.19775-7-vinod.govindapillai@intel.com> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20230601121923.19775-1-vinod.govindapillai@intel.com> References: <20230601121923.19775-1-vinod.govindapillai@intel.com> MIME-Version: 1.0 Organization: Intel Finland Oy - BIC 0357606-4 - Westendinkatu 7, 02160 Espoo Subject: [Intel-gfx] [PATCH v11 6/7] drm/i915/mtl: find the best QGV point for the SAGV configuration X-BeenThere: intel-gfx@lists.freedesktop.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Intel graphics driver community testing & development List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: ville.syrjala@intel.com Errors-To: intel-gfx-bounces@lists.freedesktop.org Sender: "Intel-gfx" From MTL onwards, we need to find the best QGV point based on the required data rate and pass the peak BW of that point to the punit to lock the corresponding QGV point. v1: Fix for warning from kernel test robot Bspec: 64636 Reported-by: kernel test robot Closes: https://lore.kernel.org/r/202305280253.Ab8bRV2w-lkp@intel.com/ Reported-by: Dan Carpenter Closes: https://lore.kernel.org/r/202305280253.Ab8bRV2w-lkp@intel.com/ Signed-off-by: Vinod Govindapillai Reviewed-by: Stanislav Lisovskiy --- drivers/gpu/drm/i915/display/intel_bw.c | 87 ++++++++++++++++++++++++- drivers/gpu/drm/i915/display/intel_bw.h | 6 ++ 2 files changed, 91 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/i915/display/intel_bw.c b/drivers/gpu/drm/i915/display/intel_bw.c index b1cbeda0b2e3..7672963dc49c 100644 --- a/drivers/gpu/drm/i915/display/intel_bw.c +++ b/drivers/gpu/drm/i915/display/intel_bw.c @@ -803,6 +803,85 @@ intel_atomic_get_bw_state(struct intel_atomic_state *state) return to_intel_bw_state(bw_state); } +static int mtl_find_qgv_points(struct drm_i915_private *i915, + unsigned int data_rate, + unsigned int num_active_planes, + const struct intel_bw_state *old_bw_state, + struct intel_bw_state *new_bw_state) +{ + unsigned int best_rate = UINT_MAX; + unsigned int num_qgv_points = i915->display.bw.max[0].num_qgv_points; + unsigned int qgv_peak_bw = 0; + int i; + int ret; + + ret = intel_atomic_lock_global_state(&new_bw_state->base); + if (ret) + return ret; + + /* + * If SAGV cannot be enabled, disable the pcode SAGV by passing all 1's + * for qgv peak bw in PM Demand request. So assign UINT_MAX if SAGV is + * not enabled. PM Demand code will clamp the value for the register + */ + if (!intel_can_enable_sagv(i915, new_bw_state)) { + new_bw_state->qgv_point_peakbw = UINT_MAX; + drm_dbg_kms(&i915->drm, "No SAGV, use UINT_MAX as peak bw."); + goto out; + } + + /* + * Find the best QGV point by comparing the data_rate with max data rate + * offered per plane group + */ + for (i = 0; i < num_qgv_points; i++) { + unsigned int bw_index = + tgl_max_bw_index(i915, num_active_planes, i); + unsigned int max_data_rate; + + if (bw_index >= ARRAY_SIZE(i915->display.bw.max)) + continue; + + max_data_rate = i915->display.bw.max[bw_index].deratedbw[i]; + + if (max_data_rate < data_rate) + continue; + + if (max_data_rate - data_rate < best_rate) { + best_rate = max_data_rate - data_rate; + qgv_peak_bw = i915->display.bw.max[bw_index].peakbw[i]; + } + + drm_dbg_kms(&i915->drm, "QGV point %d: max bw %d required %d qgv_peak_bw: %d\n", + i, max_data_rate, data_rate, qgv_peak_bw); + } + + drm_dbg_kms(&i915->drm, "Matching peaks QGV bw: %d for required data rate: %d\n", + qgv_peak_bw, data_rate); + + /* + * The display configuration cannot be supported if no QGV point + * satisfying the required data rate is found + */ + if (qgv_peak_bw == 0) { + drm_dbg_kms(&i915->drm, "No QGV points for bw %d for display configuration(%d active planes).\n", + data_rate, num_active_planes); + return -EINVAL; + } + + /* MTL PM DEMAND expects QGV BW parameter in multiples of 100 mbps */ + new_bw_state->qgv_point_peakbw = DIV_ROUND_CLOSEST(qgv_peak_bw, 100); + +out: + if (new_bw_state->qgv_point_peakbw != old_bw_state->qgv_point_peakbw) { + ret = intel_atomic_serialize_global_state(&new_bw_state->base); + if (ret) + return ret; + } + + return 0; +} + static int icl_find_qgv_points(struct drm_i915_private *i915, unsigned int data_rate, unsigned int num_active_planes, @@ -928,8 +1007,12 @@ static int intel_bw_check_qgv_points(struct drm_i915_private *i915, data_rate = DIV_ROUND_UP(data_rate, 1000); - return icl_find_qgv_points(i915, data_rate, num_active_planes, - old_bw_state, new_bw_state); + if (DISPLAY_VER(i915) >= 14) + return mtl_find_qgv_points(i915, data_rate, num_active_planes, + old_bw_state, new_bw_state); + else + return icl_find_qgv_points(i915, data_rate, num_active_planes, + old_bw_state, new_bw_state); } static bool intel_bw_state_changed(struct drm_i915_private *i915, diff --git a/drivers/gpu/drm/i915/display/intel_bw.h b/drivers/gpu/drm/i915/display/intel_bw.h index f20292143745..67ae66a3fcdd 100644 --- a/drivers/gpu/drm/i915/display/intel_bw.h +++ b/drivers/gpu/drm/i915/display/intel_bw.h @@ -34,6 +34,12 @@ struct intel_bw_state { /* bitmask of active pipes */ u8 active_pipes; + /* + * From MTL onwards, to lock a QGV point, punit expects the peak BW of + * the selected QGV point as the parameter in multiples of 100MB/s + */ + unsigned int qgv_point_peakbw; + /* * Current QGV points mask, which restricts * some particular SAGV states, not to confuse From patchwork Thu Jun 1 12:19:23 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-Patchwork-Submitter: "Govindapillai, Vinod" X-Patchwork-Id: 13263642 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from gabe.freedesktop.org (gabe.freedesktop.org [131.252.210.177]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.lore.kernel.org (Postfix) with ESMTPS id 407E0C77B7E for ; Thu, 1 Jun 2023 12:20:16 +0000 (UTC) Received: from gabe.freedesktop.org (localhost [127.0.0.1]) by gabe.freedesktop.org (Postfix) with ESMTP id BC85710E55E; Thu, 1 Jun 2023 12:20:15 +0000 (UTC) Received: from mga06.intel.com (mga06b.intel.com [134.134.136.31]) by gabe.freedesktop.org (Postfix) with ESMTPS id 4F56510E237 for ; Thu, 1 Jun 2023 12:20:13 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1685622013; x=1717158013; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=hvhkfG//ZECMLs1frAWJdIGd85yKQiux7IGJAMYSm+8=; b=fJ3EHE3MdUa2SW4F/k+wtsP19Rqt/WuFjFY5k5t9k6KTNbdWuEY17pwH Rv3hnTYCk//9KDmjEHol4FxD35ZW2U9MI6YlxOdKgM4UBR/GwfMB2abNI Ei7z7+Cc7hs8g+pi4E8UG/AXxla9ZJWrrQdmohhPLDQrzHX/VNdjKsDEz EkCGHJp4oR1QxEidHTZzbLfG4/TOhHzBu9PJ0LPqJ1eNUEpwm2nwBxrvt jEWYXzycmv7lfkCZEwwOGsQiSshJUxC1BTkr2cNyi51ZWfEWzdoft49J4 DwppkHkw26l7oSA76g+CVWnjRTGuVTpRaOMz7tryyKV1F2kRkXk4r2ij3 g==; X-IronPort-AV: E=McAfee;i="6600,9927,10727"; a="419040111" X-IronPort-AV: E=Sophos;i="6.00,210,1681196400"; d="scan'208";a="419040111" Received: from orsmga001.jf.intel.com ([10.7.209.18]) by orsmga104.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 01 Jun 2023 05:20:12 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=McAfee;i="6600,9927,10727"; a="740336269" X-IronPort-AV: E=Sophos;i="6.00,210,1681196400"; d="scan'208";a="740336269" Received: from unknown (HELO vgovind2-mobl3.fi.intel.com) ([10.237.66.43]) by orsmga001-auth.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 01 Jun 2023 05:20:09 -0700 From: Vinod Govindapillai To: intel-gfx@lists.freedesktop.org Date: Thu, 1 Jun 2023 15:19:23 +0300 Message-Id: <20230601121923.19775-8-vinod.govindapillai@intel.com> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20230601121923.19775-1-vinod.govindapillai@intel.com> References: <20230601121923.19775-1-vinod.govindapillai@intel.com> MIME-Version: 1.0 Organization: Intel Finland Oy - BIC 0357606-4 - Westendinkatu 7, 02160 Espoo Subject: [Intel-gfx] [PATCH v11 7/7] drm/i915/mtl: Add support for PM DEMAND X-BeenThere: intel-gfx@lists.freedesktop.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Intel graphics driver community testing & development List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: ville.syrjala@intel.com Errors-To: intel-gfx-bounces@lists.freedesktop.org Sender: "Intel-gfx" From: Mika Kahola MTL introduces a new way to instruct the PUnit with power and bandwidth requirements of DE. Add the functionality to program the registers and handle waits using interrupts. The current wait time for timeouts is programmed for 10 msecs to factor in the worst case scenarios. Changes made to use REG_BIT for a register that we touched(GEN8_DE_MISC_IER _MMIO). Wa_14016740474 is added which applies to Xe_LPD+ display v2: checkpatch warning fixes, simplify program pmdemand part v3: update to dbufs and pipes values to pmdemand register(stan) Removed the macro usage in update_pmdemand_values() v4: move the pmdemand_pre_plane_update before cdclk update pmdemand_needs_update included cdclk params comparisons pmdemand_state NULL check (Gustavo) pmdemand.o in sorted order in the makefile (Jani) update pmdemand misc irq handler loop (Gustavo) active phys bitmask and programming correction (Gustavo) v5: simplify pmdemand_state structure simplify methods to find active phys and max port clock Timeout in case of previou pmdemand task pending (Gustavo) v6: rebasing updates to max_ddiclk calculations (Gustavo) updates to active_phys count method (Gustavo) v7: use two separate loop to iterate throug old and new crtc states to calculate the active phys (Gustavo) v8: use uniform function names (Gustavo) v9: For phys change iterate through connectors (Imre) Look for change in phys for pmdemand update (Gustavo, Imre) Some more stlying changes (Imre) Update pmdemand state during HW readout/sanitize (Imre) v10: Fix CI checkpatch warnings Bspec: 66451, 64636, 64602, 64603 Cc: Matt Atwood Cc: Matt Roper Cc: Lucas De Marchi Cc: Gustavo Sousa Signed-off-by: José Roberto de Souza Signed-off-by: Radhakrishna Sripada Signed-off-by: Gustavo Sousa Signed-off-by: Mika Kahola Signed-off-by: Vinod Govindapillai Reviewed-by: Stanislav Lisovskiy Acked-by: Gustavo Sousa --- drivers/gpu/drm/i915/Makefile | 1 + drivers/gpu/drm/i915/display/intel_display.c | 14 + .../gpu/drm/i915/display/intel_display_core.h | 9 + .../drm/i915/display/intel_display_driver.c | 7 + .../gpu/drm/i915/display/intel_display_irq.c | 23 +- .../drm/i915/display/intel_display_power.c | 14 +- .../drm/i915/display/intel_modeset_setup.c | 18 + drivers/gpu/drm/i915/display/intel_pmdemand.c | 555 ++++++++++++++++++ drivers/gpu/drm/i915/display/intel_pmdemand.h | 56 ++ drivers/gpu/drm/i915/i915_reg.h | 36 +- 10 files changed, 727 insertions(+), 6 deletions(-) create mode 100644 drivers/gpu/drm/i915/display/intel_pmdemand.c create mode 100644 drivers/gpu/drm/i915/display/intel_pmdemand.h diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile index 1c9ed4c52760..2cd8de174bf6 100644 --- a/drivers/gpu/drm/i915/Makefile +++ b/drivers/gpu/drm/i915/Makefile @@ -269,6 +269,7 @@ i915-y += \ display/intel_pch_display.o \ display/intel_pch_refclk.o \ display/intel_plane_initial.o \ + display/intel_pmdemand.o \ display/intel_psr.o \ display/intel_quirks.o \ display/intel_sprite.o \ diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index f51a55f4e9d0..5cbf5eae2414 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -99,6 +99,7 @@ #include "intel_pcode.h" #include "intel_pipe_crc.h" #include "intel_plane_initial.h" +#include "intel_pmdemand.h" #include "intel_pps.h" #include "intel_psr.h" #include "intel_sdvo.h" @@ -6352,6 +6353,10 @@ int intel_atomic_check(struct drm_device *dev, return ret; } + ret = intel_pmdemand_atomic_check(state); + if (ret) + goto fail; + ret = intel_atomic_check_crtcs(state); if (ret) goto fail; @@ -6997,6 +7002,14 @@ static void intel_atomic_commit_tail(struct intel_atomic_state *state) for_each_new_intel_crtc_in_state(state, crtc, new_crtc_state, i) crtc->config = new_crtc_state; + /* + * In XE_LPD+ Pmdemand combines many parameters such as voltage index, + * plls, cdclk frequency, QGV point selection parameter etc. Voltage + * index, cdclk/ddiclk frequencies are supposed to be configured before + * the cdclk config is set. + */ + intel_pmdemand_pre_plane_update(state); + if (state->modeset) { drm_atomic_helper_update_legacy_modeset_state(dev, &state->base); @@ -7116,6 +7129,7 @@ static void intel_atomic_commit_tail(struct intel_atomic_state *state) intel_verify_planes(state); intel_sagv_post_plane_update(state); + intel_pmdemand_post_plane_update(state); drm_atomic_helper_commit_hw_done(&state->base); diff --git a/drivers/gpu/drm/i915/display/intel_display_core.h b/drivers/gpu/drm/i915/display/intel_display_core.h index dd8e08c8598f..8d2243c71dd8 100644 --- a/drivers/gpu/drm/i915/display/intel_display_core.h +++ b/drivers/gpu/drm/i915/display/intel_display_core.h @@ -345,6 +345,15 @@ struct intel_display { struct intel_global_obj obj; } dbuf; + struct { + wait_queue_head_t waitqueue; + + /* mutex to protect pmdemand programming sequence */ + struct mutex lock; + + struct intel_global_obj obj; + } pmdemand; + struct { /* * dkl.phy_lock protects against concurrent access of the diff --git a/drivers/gpu/drm/i915/display/intel_display_driver.c b/drivers/gpu/drm/i915/display/intel_display_driver.c index 60ce10fc7205..dc8de861339d 100644 --- a/drivers/gpu/drm/i915/display/intel_display_driver.c +++ b/drivers/gpu/drm/i915/display/intel_display_driver.c @@ -47,6 +47,7 @@ #include "intel_opregion.h" #include "intel_overlay.h" #include "intel_plane_initial.h" +#include "intel_pmdemand.h" #include "intel_pps.h" #include "intel_quirks.h" #include "intel_vga.h" @@ -211,6 +212,8 @@ int intel_display_driver_probe_noirq(struct drm_i915_private *i915) if (ret < 0) goto cleanup_vga; + intel_pmdemand_init_early(i915); + intel_power_domains_init_hw(i915, false); if (!HAS_DISPLAY(i915)) @@ -240,6 +243,10 @@ int intel_display_driver_probe_noirq(struct drm_i915_private *i915) if (ret) goto cleanup_vga_client_pw_domain_dmc; + ret = intel_pmdemand_init(i915); + if (ret) + goto cleanup_vga_client_pw_domain_dmc; + init_llist_head(&i915->display.atomic_helper.free_list); INIT_WORK(&i915->display.atomic_helper.free_work, intel_atomic_helper_free_state_worker); diff --git a/drivers/gpu/drm/i915/display/intel_display_irq.c b/drivers/gpu/drm/i915/display/intel_display_irq.c index 3b2a287d2041..0b3739310f81 100644 --- a/drivers/gpu/drm/i915/display/intel_display_irq.c +++ b/drivers/gpu/drm/i915/display/intel_display_irq.c @@ -18,6 +18,7 @@ #include "intel_fifo_underrun.h" #include "intel_gmbus.h" #include "intel_hotplug_irq.h" +#include "intel_pmdemand.h" #include "intel_psr.h" #include "intel_psr_regs.h" @@ -827,12 +828,27 @@ static u32 gen8_de_pipe_fault_mask(struct drm_i915_private *dev_priv) return GEN8_DE_PIPE_IRQ_FAULT_ERRORS; } +static void intel_pmdemand_irq_handler(struct drm_i915_private *dev_priv) +{ + wake_up_all(&dev_priv->display.pmdemand.waitqueue); +} + static void gen8_de_misc_irq_handler(struct drm_i915_private *dev_priv, u32 iir) { bool found = false; - if (iir & GEN8_DE_MISC_GSE) { + if (DISPLAY_VER(dev_priv) >= 14) { + if (iir & (XELPDP_PMDEMAND_RSP | + XELPDP_PMDEMAND_RSPTOUT_ERR)) { + if (iir & XELPDP_PMDEMAND_RSPTOUT_ERR) + drm_dbg(&dev_priv->drm, + "Error waiting for Punit PM Demand Response\n"); + + intel_pmdemand_irq_handler(dev_priv); + found = true; + } + } else if (iir & GEN8_DE_MISC_GSE) { intel_opregion_asle_intr(dev_priv); found = true; } @@ -1576,7 +1592,10 @@ void gen8_de_irq_postinstall(struct drm_i915_private *dev_priv) if (IS_GEMINILAKE(dev_priv) || IS_BROXTON(dev_priv)) de_port_masked |= BXT_DE_PORT_GMBUS; - if (DISPLAY_VER(dev_priv) >= 11) { + if (DISPLAY_VER(dev_priv) >= 14) { + de_misc_masked |= XELPDP_PMDEMAND_RSPTOUT_ERR | + XELPDP_PMDEMAND_RSP; + } else if (DISPLAY_VER(dev_priv) >= 11) { enum port port; if (intel_bios_is_dsi_present(dev_priv, &port)) diff --git a/drivers/gpu/drm/i915/display/intel_display_power.c b/drivers/gpu/drm/i915/display/intel_display_power.c index 9c9a809c71f1..db827cf3c9ca 100644 --- a/drivers/gpu/drm/i915/display/intel_display_power.c +++ b/drivers/gpu/drm/i915/display/intel_display_power.c @@ -20,6 +20,7 @@ #include "intel_mchbar_regs.h" #include "intel_pch_refclk.h" #include "intel_pcode.h" +#include "intel_pmdemand.h" #include "intel_pps_regs.h" #include "intel_snps_phy.h" #include "skl_watermark.h" @@ -1082,20 +1083,29 @@ void gen9_dbuf_slices_update(struct drm_i915_private *dev_priv, static void gen9_dbuf_enable(struct drm_i915_private *dev_priv) { + u8 slices_mask; + dev_priv->display.dbuf.enabled_slices = intel_enabled_dbuf_slices_mask(dev_priv); + slices_mask = BIT(DBUF_S1) | dev_priv->display.dbuf.enabled_slices; + + if (DISPLAY_VER(dev_priv) >= 14) + intel_pmdemand_program_dbuf(dev_priv, slices_mask); + /* * Just power up at least 1 slice, we will * figure out later which slices we have and what we need. */ - gen9_dbuf_slices_update(dev_priv, BIT(DBUF_S1) | - dev_priv->display.dbuf.enabled_slices); + gen9_dbuf_slices_update(dev_priv, slices_mask); } static void gen9_dbuf_disable(struct drm_i915_private *dev_priv) { gen9_dbuf_slices_update(dev_priv, 0); + + if (DISPLAY_VER(dev_priv) >= 14) + intel_pmdemand_program_dbuf(dev_priv, 0); } static void gen12_dbuf_slices_config(struct drm_i915_private *dev_priv) diff --git a/drivers/gpu/drm/i915/display/intel_modeset_setup.c b/drivers/gpu/drm/i915/display/intel_modeset_setup.c index 5ff99ca7f1de..87f41040916b 100644 --- a/drivers/gpu/drm/i915/display/intel_modeset_setup.c +++ b/drivers/gpu/drm/i915/display/intel_modeset_setup.c @@ -26,6 +26,7 @@ #include "intel_fifo_underrun.h" #include "intel_modeset_setup.h" #include "intel_pch_display.h" +#include "intel_pmdemand.h" #include "intel_tc.h" #include "intel_vblank.h" #include "intel_wm.h" @@ -153,6 +154,8 @@ static void intel_crtc_disable_noatomic_complete(struct intel_crtc *crtc) to_intel_dbuf_state(i915->display.dbuf.obj.state); struct intel_crtc_state *crtc_state = to_intel_crtc_state(crtc->base.state); + struct intel_pmdemand_state *pmdemand_state = + to_intel_pmdemand_state(i915->display.dbuf.obj.state); enum pipe pipe = crtc->pipe; __drm_atomic_helper_crtc_destroy_state(&crtc_state->uapi); @@ -174,6 +177,8 @@ static void intel_crtc_disable_noatomic_complete(struct intel_crtc *crtc) bw_state->data_rate[pipe] = 0; bw_state->num_active_planes[pipe] = 0; + + pmdemand_state->ddi_clocks[pipe] = 0; } /* @@ -661,6 +666,9 @@ static void intel_modeset_readout_hw_state(struct drm_i915_private *i915) to_intel_cdclk_state(i915->display.cdclk.obj.state); struct intel_dbuf_state *dbuf_state = to_intel_dbuf_state(i915->display.dbuf.obj.state); + struct intel_pmdemand_state *pmdemand_state = + to_intel_pmdemand_state(i915->display.dbuf.obj.state); + u16 active_phys = 0; enum pipe pipe; struct intel_crtc *crtc; struct intel_encoder *encoder; @@ -742,6 +750,8 @@ static void intel_modeset_readout_hw_state(struct drm_i915_private *i915) drm_connector_list_iter_begin(&i915->drm, &conn_iter); for_each_intel_connector_iter(connector, &conn_iter) { + enum phy phy; + if (connector->get_hw_state(connector)) { struct intel_crtc_state *crtc_state; struct intel_crtc *crtc; @@ -764,6 +774,10 @@ static void intel_modeset_readout_hw_state(struct drm_i915_private *i915) drm_connector_mask(&connector->base); crtc_state->uapi.encoder_mask |= drm_encoder_mask(&encoder->base); + + phy = intel_port_to_phy(i915, encoder->port); + if (!intel_phy_is_tc(i915, phy)) + active_phys |= BIT(phy); } } else { connector->base.dpms = DRM_MODE_DPMS_OFF; @@ -776,6 +790,8 @@ static void intel_modeset_readout_hw_state(struct drm_i915_private *i915) } drm_connector_list_iter_end(&conn_iter); + pmdemand_state->active_phys_mask = active_phys; + for_each_intel_crtc(&i915->drm, crtc) { struct intel_bw_state *bw_state = to_intel_bw_state(i915->display.bw.obj.state); @@ -840,6 +856,8 @@ static void intel_modeset_readout_hw_state(struct drm_i915_private *i915) cdclk_state->min_cdclk[crtc->pipe] = min_cdclk; cdclk_state->min_voltage_level[crtc->pipe] = crtc_state->min_voltage_level; + pmdemand_state->ddi_clocks[crtc->pipe] = + crtc_state->port_clock; intel_bw_crtc_update(bw_state, crtc_state); } diff --git a/drivers/gpu/drm/i915/display/intel_pmdemand.c b/drivers/gpu/drm/i915/display/intel_pmdemand.c new file mode 100644 index 000000000000..fca99b84c835 --- /dev/null +++ b/drivers/gpu/drm/i915/display/intel_pmdemand.c @@ -0,0 +1,555 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright © 2023 Intel Corporation + */ + +#include + +#include "i915_drv.h" +#include "i915_reg.h" +#include "intel_atomic.h" +#include "intel_bw.h" +#include "intel_cdclk.h" +#include "intel_de.h" +#include "intel_display_trace.h" +#include "intel_pmdemand.h" +#include "skl_watermark.h" + +static struct intel_global_state * +intel_pmdemand_duplicate_state(struct intel_global_obj *obj) +{ + struct intel_pmdemand_state *pmdemand_state; + + pmdemand_state = kmemdup(obj->state, sizeof(*pmdemand_state), GFP_KERNEL); + if (!pmdemand_state) + return NULL; + + return &pmdemand_state->base; +} + +static void intel_pmdemand_destroy_state(struct intel_global_obj *obj, + struct intel_global_state *state) +{ + kfree(state); +} + +static const struct intel_global_state_funcs intel_pmdemand_funcs = { + .atomic_duplicate_state = intel_pmdemand_duplicate_state, + .atomic_destroy_state = intel_pmdemand_destroy_state, +}; + +static struct intel_pmdemand_state * +intel_atomic_get_pmdemand_state(struct intel_atomic_state *state) +{ + struct drm_i915_private *i915 = to_i915(state->base.dev); + struct intel_global_state *pmdemand_state = + intel_atomic_get_global_obj_state(state, + &i915->display.pmdemand.obj); + + if (IS_ERR(pmdemand_state)) + return ERR_CAST(pmdemand_state); + + return to_intel_pmdemand_state(pmdemand_state); +} + +static struct intel_pmdemand_state * +intel_atomic_get_old_pmdemand_state(struct intel_atomic_state *state) +{ + struct drm_i915_private *i915 = to_i915(state->base.dev); + struct intel_global_state *pmdemand_state = + intel_atomic_get_old_global_obj_state(state, + &i915->display.pmdemand.obj); + + if (!pmdemand_state) + return NULL; + + return to_intel_pmdemand_state(pmdemand_state); +} + +static struct intel_pmdemand_state * +intel_atomic_get_new_pmdemand_state(struct intel_atomic_state *state) +{ + struct drm_i915_private *i915 = to_i915(state->base.dev); + struct intel_global_state *pmdemand_state = + intel_atomic_get_new_global_obj_state(state, + &i915->display.pmdemand.obj); + + if (!pmdemand_state) + return NULL; + + return to_intel_pmdemand_state(pmdemand_state); +} + +int intel_pmdemand_init(struct drm_i915_private *i915) +{ + struct intel_pmdemand_state *pmdemand_state; + + pmdemand_state = kzalloc(sizeof(*pmdemand_state), GFP_KERNEL); + if (!pmdemand_state) + return -ENOMEM; + + intel_atomic_global_obj_init(i915, &i915->display.pmdemand.obj, + &pmdemand_state->base, + &intel_pmdemand_funcs); + + if (IS_MTL_DISPLAY_STEP(i915, STEP_A0, STEP_C0)) + /* Wa_14016740474 */ + intel_de_rmw(i915, XELPD_CHICKEN_DCPR_3, 0, DMD_RSP_TIMEOUT_DISABLE); + + return 0; +} + +void intel_pmdemand_init_early(struct drm_i915_private *i915) +{ + mutex_init(&i915->display.pmdemand.lock); + init_waitqueue_head(&i915->display.pmdemand.waitqueue); +} + +static void +intel_pmdemand_update_max_ddiclk(struct intel_atomic_state *state, + struct intel_pmdemand_state *pmdemand_state) +{ + int max_ddiclk = 0; + struct intel_crtc *crtc; + int i; + const struct intel_crtc_state *new_crtc_state; + + for_each_new_intel_crtc_in_state(state, crtc, new_crtc_state, i) + pmdemand_state->ddi_clocks[crtc->pipe] = + new_crtc_state->port_clock; + + for (i = 0; i < ARRAY_SIZE(pmdemand_state->ddi_clocks); i++) + max_ddiclk = max(pmdemand_state->ddi_clocks[i], max_ddiclk); + + pmdemand_state->params.ddiclk_max = DIV_ROUND_UP(max_ddiclk, 1000); +} + +static void +intel_pmdemand_update_phys_mask(struct drm_i915_private *i915, + struct intel_atomic_state *state, + struct drm_connector_state *conn_state, + bool for_old_state, u16 *phys_mask) +{ + struct intel_crtc *crtc = to_intel_crtc(conn_state->crtc); + struct intel_encoder *encoder = to_intel_encoder(conn_state->best_encoder); + struct intel_crtc_state *crtc_state; + enum phy phy; + + if (!crtc || !encoder) + return; + + phy = intel_port_to_phy(i915, encoder->port); + if (intel_phy_is_tc(i915, phy)) + return; + + if (for_old_state) + crtc_state = intel_atomic_get_old_crtc_state(state, crtc); + else + crtc_state = intel_atomic_get_new_crtc_state(state, crtc); + + if (!crtc_state->hw.active) + return; + + if (for_old_state) + *phys_mask &= ~BIT(phy); + else + *phys_mask |= BIT(phy); +} + +static void +intel_pmdemand_update_active_non_tc_phys(struct drm_i915_private *i915, + struct intel_atomic_state *state, + struct intel_pmdemand_state *pmdemand_state) +{ + u16 *phys_mask = &pmdemand_state->active_phys_mask; + struct drm_connector *connector; + int i; + struct drm_connector_state *old_conn_state, *new_conn_state; + + for_each_oldnew_connector_in_state(&state->base, connector, + old_conn_state, new_conn_state, i) { + if (!intel_connector_needs_modeset(state, connector)) + continue; + + /* First clear the active phys in the old connector state */ + intel_pmdemand_update_phys_mask(i915, state, old_conn_state, + true, phys_mask); + + /* First set the active phys in new connector state */ + intel_pmdemand_update_phys_mask(i915, state, new_conn_state, + false, phys_mask); + } + + pmdemand_state->params.active_phys = hweight16(*phys_mask); +} + +static bool intel_pmdemand_phys_needs_update(struct intel_atomic_state *state) +{ + struct drm_connector *connector; + int i; + struct drm_connector_state *old_conn_state, *new_conn_state; + + for_each_oldnew_connector_in_state(&state->base, connector, + old_conn_state, new_conn_state, i) { + struct intel_crtc *old_crtc = + to_intel_crtc(old_conn_state->crtc); + struct intel_crtc *new_crtc = + to_intel_crtc(new_conn_state->crtc); + struct intel_crtc_state *new_crtc_state, *old_crtc_state; + + /* If the connector do not need modeset, no phys change */ + if (!intel_connector_needs_modeset(state, connector)) + continue; + + /* If crtcs are different, update phys */ + if (old_crtc != new_crtc) + return true; + + if (!new_crtc) + continue; + + /* If crtc state's active status changed, update the phys */ + old_crtc_state = intel_atomic_get_old_crtc_state(state, + new_crtc); + new_crtc_state = intel_atomic_get_old_crtc_state(state, + new_crtc); + if (old_crtc_state->hw.active != new_crtc_state->hw.active) + return true; + } + + return false; +} + +static bool intel_pmdemand_needs_update(struct intel_atomic_state *state) +{ + struct intel_crtc *crtc; + int i; + const struct intel_bw_state *new_bw_state, *old_bw_state; + const struct intel_cdclk_state *new_cdclk_state, *old_cdclk_state; + const struct intel_crtc_state *new_crtc_state, *old_crtc_state; + const struct intel_dbuf_state *new_dbuf_state, *old_dbuf_state; + + new_bw_state = intel_atomic_get_new_bw_state(state); + old_bw_state = intel_atomic_get_old_bw_state(state); + if (new_bw_state && new_bw_state->qgv_point_peakbw != + old_bw_state->qgv_point_peakbw) + return true; + + new_dbuf_state = intel_atomic_get_new_dbuf_state(state); + old_dbuf_state = intel_atomic_get_old_dbuf_state(state); + if (new_dbuf_state && + (new_dbuf_state->active_pipes != + old_dbuf_state->active_pipes || + new_dbuf_state->enabled_slices != + old_dbuf_state->enabled_slices)) + return true; + + new_cdclk_state = intel_atomic_get_new_cdclk_state(state); + old_cdclk_state = intel_atomic_get_old_cdclk_state(state); + if (new_cdclk_state && + (new_cdclk_state->actual.cdclk != + old_cdclk_state->actual.cdclk || + new_cdclk_state->actual.voltage_level != + old_cdclk_state->actual.voltage_level)) + return true; + + for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state, + new_crtc_state, i) + if (new_crtc_state->port_clock != old_crtc_state->port_clock) + return true; + + return intel_pmdemand_phys_needs_update(state); +} + +int intel_pmdemand_atomic_check(struct intel_atomic_state *state) +{ + struct drm_i915_private *i915 = to_i915(state->base.dev); + const struct intel_bw_state *new_bw_state; + const struct intel_cdclk_state *new_cdclk_state; + const struct intel_dbuf_state *new_dbuf_state; + struct intel_pmdemand_state *new_pmdemand_state; + int ret; + + if (DISPLAY_VER(i915) < 14) + return 0; + + if (!intel_pmdemand_needs_update(state)) + return 0; + + new_pmdemand_state = intel_atomic_get_pmdemand_state(state); + if (IS_ERR(new_pmdemand_state)) + return PTR_ERR(new_pmdemand_state); + + ret = intel_atomic_lock_global_state(&new_pmdemand_state->base); + if (ret) + return ret; + + new_bw_state = intel_atomic_get_bw_state(state); + if (IS_ERR(new_bw_state)) + return PTR_ERR(new_bw_state); + + /* firmware will calculate the qclck_gc_index, requirement is set to 0 */ + new_pmdemand_state->params.qclk_gv_index = 0; + new_pmdemand_state->params.qclk_gv_bw = + min_t(u16, new_bw_state->qgv_point_peakbw, 0xffff); + + new_dbuf_state = intel_atomic_get_dbuf_state(state); + if (IS_ERR(new_dbuf_state)) + return PTR_ERR(new_dbuf_state); + + new_pmdemand_state->params.active_pipes = + min_t(u8, hweight8(new_dbuf_state->active_pipes), 3); + new_pmdemand_state->params.active_dbufs = + min_t(u8, + hweight8(BIT(DBUF_S1) | new_dbuf_state->enabled_slices), + 3); + + new_cdclk_state = intel_atomic_get_cdclk_state(state); + if (IS_ERR(new_cdclk_state)) + return PTR_ERR(new_cdclk_state); + + new_pmdemand_state->params.voltage_index = + new_cdclk_state->actual.voltage_level; + new_pmdemand_state->params.cdclk_freq_mhz = + DIV_ROUND_UP(new_cdclk_state->actual.cdclk, 1000); + + intel_pmdemand_update_max_ddiclk(state, new_pmdemand_state); + + intel_pmdemand_update_active_non_tc_phys(i915, state, new_pmdemand_state); + + /* + * Setting scalers to max as it can not be calculated during flips and + * fastsets without taking global states locks. + */ + new_pmdemand_state->params.scalers = 7; + + ret = intel_atomic_serialize_global_state(&new_pmdemand_state->base); + if (ret) + return ret; + + return 0; +} + +static bool intel_pmdemand_check_prev_transaction(struct drm_i915_private *i915) +{ + return !(intel_de_wait_for_clear(i915, + XELPDP_INITIATE_PMDEMAND_REQUEST(1), + XELPDP_PMDEMAND_REQ_ENABLE, 10) || + intel_de_wait_for_clear(i915, + GEN12_DCPR_STATUS_1, + XELPDP_PMDEMAND_INFLIGHT_STATUS, 10)); +} + +static bool intel_pmdemand_req_complete(struct drm_i915_private *i915) +{ + return !(intel_de_read(i915, XELPDP_INITIATE_PMDEMAND_REQUEST(1)) & + XELPDP_PMDEMAND_REQ_ENABLE); +} + +static void intel_pmdemand_wait(struct drm_i915_private *i915) +{ + const unsigned int timeout_ms = 10; + + if (!wait_event_timeout(i915->display.pmdemand.waitqueue, + intel_pmdemand_req_complete(i915), + msecs_to_jiffies_timeout(timeout_ms))) + drm_err(&i915->drm, + "timed out waiting for Punit PM Demand Response\n"); +} + +/* Required to be programmed during Display Init Sequences. */ +void intel_pmdemand_program_dbuf(struct drm_i915_private *i915, + u8 dbuf_slices) +{ + u32 dbufs = min_t(u32, hweight8(dbuf_slices), 3); + + mutex_lock(&i915->display.pmdemand.lock); + if (drm_WARN_ON(&i915->drm, + !intel_pmdemand_check_prev_transaction(i915))) + goto unlock; + + intel_de_rmw(i915, XELPDP_INITIATE_PMDEMAND_REQUEST(0), + XELPDP_PMDEMAND_DBUFS_MASK, XELPDP_PMDEMAND_DBUFS(dbufs)); + intel_de_rmw(i915, XELPDP_INITIATE_PMDEMAND_REQUEST(1), 0, + XELPDP_PMDEMAND_REQ_ENABLE); + + intel_pmdemand_wait(i915); + +unlock: + mutex_unlock(&i915->display.pmdemand.lock); +} + +static void +intel_pmdemand_update_params(const struct intel_pmdemand_state *new, + const struct intel_pmdemand_state *old, + u32 *reg1, u32 *reg2) +{ + u32 plls, tmp; + + /* + * The pmdemand parameter updates happens in two steps. Pre plane and + * post plane updates. During the pre plane, as DE might still be + * handling with some old operations, to avoid unwanted performance + * issues, program the pmdemand parameters with higher of old and new + * values. And then after once settled, use the new parameter values + * as part of the post plane update. + */ + + /* Set 1*/ + *reg1 &= ~XELPDP_PMDEMAND_QCLK_GV_BW_MASK; + tmp = old ? max(old->params.qclk_gv_bw, new->params.qclk_gv_bw) : + new->params.qclk_gv_bw; + *reg1 |= XELPDP_PMDEMAND_QCLK_GV_BW(tmp); + + *reg1 &= ~XELPDP_PMDEMAND_VOLTAGE_INDEX_MASK; + tmp = old ? max(old->params.voltage_index, new->params.voltage_index) : + new->params.voltage_index; + *reg1 |= XELPDP_PMDEMAND_VOLTAGE_INDEX(tmp); + + *reg1 &= ~XELPDP_PMDEMAND_QCLK_GV_INDEX_MASK; + tmp = old ? max(old->params.qclk_gv_index, new->params.qclk_gv_index) : + new->params.qclk_gv_index; + *reg1 |= XELPDP_PMDEMAND_QCLK_GV_INDEX(tmp); + + *reg1 &= ~XELPDP_PMDEMAND_PIPES_MASK; + tmp = old ? max(old->params.active_pipes, new->params.active_pipes) : + new->params.active_pipes; + *reg1 |= XELPDP_PMDEMAND_PIPES(tmp); + + *reg1 &= ~XELPDP_PMDEMAND_DBUFS_MASK; + tmp = old ? max(old->params.active_dbufs, new->params.active_dbufs) : + new->params.active_dbufs; + *reg1 |= XELPDP_PMDEMAND_DBUFS(tmp); + + *reg1 &= ~XELPDP_PMDEMAND_PHYS_MASK; + plls = old ? max(old->params.active_phys, new->params.active_phys) : + new->params.active_phys; + plls = min_t(u32, plls, 7); + *reg1 |= XELPDP_PMDEMAND_PHYS(plls); + + /* Set 2*/ + *reg2 &= ~XELPDP_PMDEMAND_CDCLK_FREQ_MASK; + tmp = old ? max(old->params.cdclk_freq_mhz, + new->params.cdclk_freq_mhz) : + new->params.cdclk_freq_mhz; + *reg2 |= XELPDP_PMDEMAND_CDCLK_FREQ(tmp); + + *reg2 &= ~XELPDP_PMDEMAND_DDICLK_FREQ_MASK; + tmp = old ? max(old->params.ddiclk_max, new->params.ddiclk_max) : + new->params.ddiclk_max; + *reg2 |= XELPDP_PMDEMAND_DDICLK_FREQ(tmp); + + *reg2 &= ~XELPDP_PMDEMAND_SCALERS_MASK; + tmp = old ? max(old->params.scalers, new->params.scalers) : + new->params.scalers; + *reg2 |= XELPDP_PMDEMAND_SCALERS(tmp); + + /* + * Active_PLLs starts with 1 because of CDCLK PLL. + * TODO: Missing to account genlock filter when it gets used. + */ + plls = min_t(u32, plls + 1, 7); + *reg2 &= ~XELPDP_PMDEMAND_PLLS_MASK; + *reg2 |= XELPDP_PMDEMAND_PLLS(plls); +} + +static void +intel_pmdemand_program_params(struct drm_i915_private *i915, + const struct intel_pmdemand_state *new, + const struct intel_pmdemand_state *old) +{ + bool changed = false; + u32 reg1, mod_reg1; + u32 reg2, mod_reg2; + + mutex_lock(&i915->display.pmdemand.lock); + if (drm_WARN_ON(&i915->drm, + !intel_pmdemand_check_prev_transaction(i915))) + goto unlock; + + reg1 = intel_de_read(i915, XELPDP_INITIATE_PMDEMAND_REQUEST(0)); + mod_reg1 = reg1; + + reg2 = intel_de_read(i915, XELPDP_INITIATE_PMDEMAND_REQUEST(1)); + mod_reg2 = reg2; + + intel_pmdemand_update_params(new, old, &mod_reg1, &mod_reg2); + + if (reg1 != mod_reg1) { + intel_de_write(i915, XELPDP_INITIATE_PMDEMAND_REQUEST(0), + mod_reg1); + changed = true; + } + + if (reg2 != mod_reg2) { + intel_de_write(i915, XELPDP_INITIATE_PMDEMAND_REQUEST(1), + mod_reg2); + changed = true; + } + + /* Initiate pm demand request only if register values are changed */ + if (!changed) + goto unlock; + + drm_dbg_kms(&i915->drm, + "initate pmdemand request values: (0x%x 0x%x)\n", + mod_reg1, mod_reg2); + + intel_de_rmw(i915, XELPDP_INITIATE_PMDEMAND_REQUEST(1), 0, + XELPDP_PMDEMAND_REQ_ENABLE); + + intel_pmdemand_wait(i915); + +unlock: + mutex_unlock(&i915->display.pmdemand.lock); +} + +static bool +intel_pmdemand_state_changed(const struct intel_pmdemand_state *new, + const struct intel_pmdemand_state *old) +{ + return memcmp(&new->params, &old->params, sizeof(new->params)) != 0; +} + +void intel_pmdemand_pre_plane_update(struct intel_atomic_state *state) +{ + struct drm_i915_private *i915 = to_i915(state->base.dev); + const struct intel_pmdemand_state *new_pmdemand_state = + intel_atomic_get_new_pmdemand_state(state); + const struct intel_pmdemand_state *old_pmdemand_state = + intel_atomic_get_old_pmdemand_state(state); + + if (DISPLAY_VER(i915) < 14) + return; + + if (!new_pmdemand_state || + !intel_pmdemand_state_changed(new_pmdemand_state, + old_pmdemand_state)) + return; + + WARN_ON(!new_pmdemand_state->base.changed); + + intel_pmdemand_program_params(i915, new_pmdemand_state, + old_pmdemand_state); +} + +void intel_pmdemand_post_plane_update(struct intel_atomic_state *state) +{ + struct drm_i915_private *i915 = to_i915(state->base.dev); + const struct intel_pmdemand_state *new_pmdemand_state = + intel_atomic_get_new_pmdemand_state(state); + const struct intel_pmdemand_state *old_pmdemand_state = + intel_atomic_get_old_pmdemand_state(state); + + if (DISPLAY_VER(i915) < 14) + return; + + if (!new_pmdemand_state || + !intel_pmdemand_state_changed(new_pmdemand_state, + old_pmdemand_state)) + return; + + WARN_ON(!new_pmdemand_state->base.changed); + + intel_pmdemand_program_params(i915, new_pmdemand_state, NULL); +} diff --git a/drivers/gpu/drm/i915/display/intel_pmdemand.h b/drivers/gpu/drm/i915/display/intel_pmdemand.h new file mode 100644 index 000000000000..c1c9b93934bb --- /dev/null +++ b/drivers/gpu/drm/i915/display/intel_pmdemand.h @@ -0,0 +1,56 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2023 Intel Corporation + */ + +#ifndef __INTEL_PMDEMAND_H__ +#define __INTEL_PMDEMAND_H__ + +#include "intel_display_limits.h" +#include "intel_global_state.h" + +struct drm_i915_private; +struct intel_atomic_state; +struct intel_crtc_state; +struct intel_plane_state; + +struct pmdemand_params { + u16 qclk_gv_bw; + u8 voltage_index; + u8 qclk_gv_index; + u8 active_pipes; + u8 active_dbufs; + /* Total number of non type C active phys from active_phys_mask */ + u8 active_phys; + u16 cdclk_freq_mhz; + /* max from ddi_clocks[] */ + u16 ddiclk_max; + u8 scalers; +}; + +struct intel_pmdemand_state { + struct intel_global_state base; + + /* Maintain a persistent list of port clocks across all crtcs */ + int ddi_clocks[I915_MAX_PIPES]; + + /* Maintain a persistent list of non type C phys mask */ + u16 active_phys_mask; + + /* Parameters to be configured in the pmdemand registers */ + struct pmdemand_params params; +}; + +#define to_intel_pmdemand_state(x) container_of((x), \ + struct intel_pmdemand_state, \ + base) + +void intel_pmdemand_init_early(struct drm_i915_private *i915); +int intel_pmdemand_init(struct drm_i915_private *i915); +void intel_pmdemand_program_dbuf(struct drm_i915_private *i915, + u8 dbuf_slices); +void intel_pmdemand_pre_plane_update(struct intel_atomic_state *state); +void intel_pmdemand_post_plane_update(struct intel_atomic_state *state); +int intel_pmdemand_atomic_check(struct intel_atomic_state *state); + +#endif /* __INTEL_PMDEMAND_H__ */ diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 0523418129c5..6d34d9f59b1c 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -4418,8 +4418,10 @@ #define GEN8_DE_MISC_IMR _MMIO(0x44464) #define GEN8_DE_MISC_IIR _MMIO(0x44468) #define GEN8_DE_MISC_IER _MMIO(0x4446c) -#define GEN8_DE_MISC_GSE (1 << 27) -#define GEN8_DE_EDP_PSR (1 << 19) +#define XELPDP_PMDEMAND_RSPTOUT_ERR REG_BIT(27) +#define GEN8_DE_MISC_GSE REG_BIT(27) +#define GEN8_DE_EDP_PSR REG_BIT(19) +#define XELPDP_PMDEMAND_RSP REG_BIT(3) #define GEN8_PCU_ISR _MMIO(0x444e0) #define GEN8_PCU_IMR _MMIO(0x444e4) @@ -4504,6 +4506,33 @@ #define XELPDP_DP_ALT_HPD_LONG_DETECT REG_BIT(1) #define XELPDP_DP_ALT_HPD_SHORT_DETECT REG_BIT(0) +#define XELPDP_INITIATE_PMDEMAND_REQUEST(dword) _MMIO(0x45230 + 4 * (dword)) +#define XELPDP_PMDEMAND_QCLK_GV_BW_MASK REG_GENMASK(31, 16) +#define XELPDP_PMDEMAND_QCLK_GV_BW(x) REG_FIELD_PREP(XELPDP_PMDEMAND_QCLK_GV_BW_MASK, x) +#define XELPDP_PMDEMAND_VOLTAGE_INDEX_MASK REG_GENMASK(14, 12) +#define XELPDP_PMDEMAND_VOLTAGE_INDEX(x) REG_FIELD_PREP(XELPDP_PMDEMAND_VOLTAGE_INDEX_MASK, x) +#define XELPDP_PMDEMAND_QCLK_GV_INDEX_MASK REG_GENMASK(11, 8) +#define XELPDP_PMDEMAND_QCLK_GV_INDEX(x) REG_FIELD_PREP(XELPDP_PMDEMAND_QCLK_GV_INDEX_MASK, x) +#define XELPDP_PMDEMAND_PIPES_MASK REG_GENMASK(7, 6) +#define XELPDP_PMDEMAND_PIPES(x) REG_FIELD_PREP(XELPDP_PMDEMAND_PIPES_MASK, x) +#define XELPDP_PMDEMAND_DBUFS_MASK REG_GENMASK(5, 4) +#define XELPDP_PMDEMAND_DBUFS(x) REG_FIELD_PREP(XELPDP_PMDEMAND_DBUFS_MASK, x) +#define XELPDP_PMDEMAND_PHYS_MASK REG_GENMASK(2, 0) +#define XELPDP_PMDEMAND_PHYS(x) REG_FIELD_PREP(XELPDP_PMDEMAND_PHYS_MASK, x) + +#define XELPDP_PMDEMAND_REQ_ENABLE REG_BIT(31) +#define XELPDP_PMDEMAND_CDCLK_FREQ_MASK REG_GENMASK(30, 20) +#define XELPDP_PMDEMAND_CDCLK_FREQ(x) REG_FIELD_PREP(XELPDP_PMDEMAND_CDCLK_FREQ_MASK, x) +#define XELPDP_PMDEMAND_DDICLK_FREQ_MASK REG_GENMASK(18, 8) +#define XELPDP_PMDEMAND_DDICLK_FREQ(x) REG_FIELD_PREP(XELPDP_PMDEMAND_DDICLK_FREQ_MASK, x) +#define XELPDP_PMDEMAND_SCALERS_MASK REG_GENMASK(6, 4) +#define XELPDP_PMDEMAND_SCALERS(x) REG_FIELD_PREP(XELPDP_PMDEMAND_SCALERS_MASK, x) +#define XELPDP_PMDEMAND_PLLS_MASK REG_GENMASK(2, 0) +#define XELPDP_PMDEMAND_PLLS(x) REG_FIELD_PREP(XELPDP_PMDEMAND_PLLS_MASK, x) + +#define GEN12_DCPR_STATUS_1 _MMIO(0x46440) +#define XELPDP_PMDEMAND_INFLIGHT_STATUS REG_BIT(26) + #define ILK_DISPLAY_CHICKEN2 _MMIO(0x42004) /* Required on all Ironlake and Sandybridge according to the B-Spec. */ #define ILK_ELPIN_409_SELECT REG_BIT(25) @@ -4663,6 +4692,9 @@ #define DCPR_SEND_RESP_IMM REG_BIT(25) #define DCPR_CLEAR_MEMSTAT_DIS REG_BIT(24) +#define XELPD_CHICKEN_DCPR_3 _MMIO(0x46438) +#define DMD_RSP_TIMEOUT_DISABLE REG_BIT(19) + #define SKL_DFSM _MMIO(0x51000) #define SKL_DFSM_DISPLAY_PM_DISABLE (1 << 27) #define SKL_DFSM_DISPLAY_HDCP_DISABLE (1 << 25)