From nobody Sat Nov 23 22:56:02 2024 Received: from NAM11-BN8-obe.outbound.protection.outlook.com (mail-bn8nam11on2060.outbound.protection.outlook.com [40.107.236.60]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 2AB191AB522 for ; Mon, 11 Nov 2024 17:32:44 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=fail smtp.client-ip=40.107.236.60 ARC-Seal: i=2; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1731346367; cv=fail; b=NFaltjiqx4VcX9eoY9TithD0FeSsyCVrXBXoUbbru5R1LqAC7WKCDzeC1PnUDY6aXEjCFfuNK1cHdwkB3SW0EUODs4GJrk+32mMdWg+Nnwc8r1iPKhRL6WpOzf+jhIkeJ6yRY2hrG6eCYb7gNicpTw6ug3aexGMzgPGTCd43iOo= ARC-Message-Signature: i=2; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1731346367; c=relaxed/simple; bh=A3/WWMjwD9c/nDRsFrRxGGCgYISUAmHhpoKW4wUJSK8=; h=From:To:CC:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version:Content-Type; b=Cqrc0ZcLSi0YU1xpsisi8QfPhIlEQrS3yBPKc/1FmhO8HIvtrPyQQq/2spRnCCeot/U31VSyLYqK242YoPLuEm6hBhdP9RKnH1Fn9UpKlGU4CH36Vx5n6H0hbZTnFcFHt2/3Sq6cVLvo9wrfGfruXwfWdspZ+lh3z4J0AJAaOkQ= ARC-Authentication-Results: i=2; smtp.subspace.kernel.org; dmarc=pass (p=quarantine dis=none) header.from=amd.com; spf=fail smtp.mailfrom=amd.com; dkim=pass (1024-bit key) header.d=amd.com header.i=@amd.com header.b=sk4hj7Vh; arc=fail smtp.client-ip=40.107.236.60 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=quarantine dis=none) header.from=amd.com Authentication-Results: smtp.subspace.kernel.org; spf=fail smtp.mailfrom=amd.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=amd.com header.i=@amd.com header.b="sk4hj7Vh" ARC-Seal: i=1; a=rsa-sha256; s=arcselector10001; d=microsoft.com; cv=none; b=U52h2vr/dgDnECFqqTFZlMTwF3d2CJendkWa9rRsdBgDfV7QCips75bDiLI8PJkL3lc4ZEDviVz3Z44nUEO2DO5T+/3Zi3qP1BzB0K/yPvXh4FnnYLq8Gkg+kQfeez1gpeKd6d6VmdeqWM0dYwjbP0P3S0m8cnb7Z4xRYAKkNbMVm3/oMHSkScKXnnYfCLMVlAq9uZusxwIhw0l7D0zP8FMU3OdoJ6vElg9KY82an60LE3Ek3zOZgbo9BBjEcIDsAOJ+0GnGL9oWM7H+d5h9FLUaMn9fT605Bp7WkdtUdqCll2iw4ZfEUogmvb4Zf5Zg05JVYavHzogDEJRUbhAxug== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=microsoft.com; s=arcselector10001; h=From:Date:Subject:Message-ID:Content-Type:MIME-Version:X-MS-Exchange-AntiSpam-MessageData-ChunkCount:X-MS-Exchange-AntiSpam-MessageData-0:X-MS-Exchange-AntiSpam-MessageData-1; bh=asyFZaLo6mPu+KtbRIx8dlBchQlf9hDlqpDU1EIf3jU=; b=IhS8XC6tmSAeu7SmtNu9DEVRAt6A0peB/JaSN+hfsYaXvAvg1rshcgAomrJ+IMoN0peSfdCsfdODtg/GjtdZaiHwxyh7J0AS+w/q1PmF8+1j83oWoTyzVlGvXdqPjFBM3kGqwHjYEAGm6hdpBUCY3iyYrcLI0RhK1sTOr8GAmU66zcj8fA4WhTmy4OSGVc+r765tVwgd/24XjQn7pJpvd5neRGz80JTIaK/kLLB454mgZMqcAORZc6mse10XawlfEQEqYog+UAtR740PeIHl/pAE5qFsBh/irOFBL6a0z9rFE12kky/5gmiJBGkGle1Rfv90ZH4uwRyLPhVhVvDevw== ARC-Authentication-Results: i=1; mx.microsoft.com 1; spf=pass (sender ip is 165.204.84.17) smtp.rcpttodomain=kernel.org smtp.mailfrom=amd.com; dmarc=pass (p=quarantine sp=quarantine pct=100) action=none header.from=amd.com; dkim=none (message not signed); arc=none (0) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=amd.com; s=selector1; h=From:Date:Subject:Message-ID:Content-Type:MIME-Version:X-MS-Exchange-SenderADCheck; bh=asyFZaLo6mPu+KtbRIx8dlBchQlf9hDlqpDU1EIf3jU=; b=sk4hj7VhAe8fDjQYfOdCEgmHwrB+rNbsGn0P1LNE9rJ1kUIIIJ7v6Rox6ySMLmLsxZ8hQQNcp3Ygv1Zrh+JTFgFGehohbPsYSjn6FRie+xqmI5w12t4qx7KeZhHSQdCxHOYgnozpjfqku//8E794BIMO434Kf0KkGEXZPCgVpPA= Received: from PH7PR02CA0013.namprd02.prod.outlook.com (2603:10b6:510:33d::21) by CH3PR12MB8404.namprd12.prod.outlook.com (2603:10b6:610:12d::17) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id 15.20.8137.26; Mon, 11 Nov 2024 17:32:38 +0000 Received: from CY4PEPF0000E9CF.namprd03.prod.outlook.com (2603:10b6:510:33d:cafe::a) by PH7PR02CA0013.outlook.office365.com (2603:10b6:510:33d::21) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id 15.20.8137.28 via Frontend Transport; Mon, 11 Nov 2024 17:32:38 +0000 X-MS-Exchange-Authentication-Results: spf=pass (sender IP is 165.204.84.17) smtp.mailfrom=amd.com; dkim=none (message not signed) header.d=none;dmarc=pass action=none header.from=amd.com; Received-SPF: Pass (protection.outlook.com: domain of amd.com designates 165.204.84.17 as permitted sender) receiver=protection.outlook.com; client-ip=165.204.84.17; helo=SATLEXMB03.amd.com; pr=C Received: from SATLEXMB03.amd.com (165.204.84.17) by CY4PEPF0000E9CF.mail.protection.outlook.com (10.167.241.134) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256) id 15.20.8158.14 via Frontend Transport; Mon, 11 Nov 2024 17:32:37 +0000 Received: from SATLEXMB06.amd.com (10.181.40.147) by SATLEXMB03.amd.com (10.181.40.144) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256) id 15.1.2507.39; Mon, 11 Nov 2024 11:32:37 -0600 Received: from SATLEXMB04.amd.com (10.181.40.145) by SATLEXMB06.amd.com (10.181.40.147) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256) id 15.1.2507.39; Mon, 11 Nov 2024 11:32:36 -0600 Received: from xsjlizhih51.xilinx.com (10.180.168.240) by SATLEXMB04.amd.com (10.181.40.145) with Microsoft SMTP Server id 15.1.2507.39 via Frontend Transport; Mon, 11 Nov 2024 11:32:36 -0600 From: Lizhi Hou To: , , CC: Lizhi Hou , , , , , Subject: [PATCH V8 04/10] accel/amdxdna: Add hardware resource solver Date: Mon, 11 Nov 2024 09:32:24 -0800 Message-ID: <20241111173230.655325-5-lizhi.hou@amd.com> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20241111173230.655325-1-lizhi.hou@amd.com> References: <20241111173230.655325-1-lizhi.hou@amd.com> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable X-EOPAttributedMessage: 0 X-MS-PublicTrafficType: Email X-MS-TrafficTypeDiagnostic: CY4PEPF0000E9CF:EE_|CH3PR12MB8404:EE_ X-MS-Office365-Filtering-Correlation-Id: 33f39db3-baec-43cd-f702-08dd0276d643 X-MS-Exchange-SenderADCheck: 1 X-MS-Exchange-AntiSpam-Relay: 0 X-Microsoft-Antispam: BCL:0;ARA:13230040|1800799024|36860700013|82310400026|376014; X-Microsoft-Antispam-Message-Info: =?us-ascii?Q?Rh2MLNXkn4YvwsVaKs11a8RUdWaA4hMJ3nl7DqcfLt/EjE9Cj3iE3mHr6WDp?= =?us-ascii?Q?o4ha7vUk+mmjp/jZzCioXYNXNypn0lZ4HBRd/y6B9F9DSChSM9mnH/E7SCnv?= =?us-ascii?Q?8EtfgPvyN6rfXQPnFfaN9l/M0FYhfWqfuSdxxPPD2djnQjO2PvqDGG3CXZn/?= =?us-ascii?Q?zOjgCzUKs/VG9uQbnct5//9uIa/Brd4FVzudKGY7TqKWmzmdHC81s+1U/qW2?= =?us-ascii?Q?54N+AKyPJkakmHVsCV1/d6nGZ8QcFzX2zWIl7Qn8dw/ngMCuYu6lIav3qIVh?= =?us-ascii?Q?ISib8LeIN2muY0elqKxsuZino1PsLLXNnzsxnwKMq2Ck/mXpluxKa3T/ysLW?= =?us-ascii?Q?Wkw+PjEm45AYE5oWyNu98mJKkv3KA3LXAAGWjXcyQquzeryqYXyUYchjzZho?= =?us-ascii?Q?VBzU+JBcH3kc57xydqA/d8iKhWRZCWNMfOMBtLmLMDSJCrjaG6OD5el2ZZ3d?= =?us-ascii?Q?rgsP8TWllOE7YiPZDbeFpXThfD0spO8UzEYHHSvfEG1gsVMhgC4PfYrma+0s?= =?us-ascii?Q?PbqPsHoX9E4nhQIMmmUpsvkrkQbWjujgOvHC7QJVgfCztjRIbA4zEd383CgK?= =?us-ascii?Q?1U8mo/3pOXbkEs54/2i5qywjISD3VjQxVnu5E0ZVMJqXJYtAB3GLRDTapu3S?= =?us-ascii?Q?UKNqyFmRhLQzhk5y7xrFLcQAyvzfUcmolIqzy0AJFuWjNalsALflUZyRFGxy?= =?us-ascii?Q?e5Ab4XbbifKZAhBJrkipuWC3yWd05a+N6Rk+mMGUUk2mmQ/MK+3QijpY9Y++?= =?us-ascii?Q?PBN637mM/MTZznetMUbavHo0ptig6A+498e5HSk1UndLvnRKa4rMr0B8FDHv?= =?us-ascii?Q?3pnhDmxaXp0JG/QLWjM9RvbBwMTqoDR1EaVu24pYEg7PN3D40i9afxk2COA4?= =?us-ascii?Q?a993Brq/uQ2aMWGndOHbAq4Y52YpavxvyMl/0V6L4NzbNLcd8t9LMxN1I/sq?= =?us-ascii?Q?PWecmXhk6XNJ+BbVDWs5aINSDI0+ruE82r2g0G8RmfuVYe7bcvtDrNl4Kf4i?= =?us-ascii?Q?fOqYaP0rSbaBCz1R3dv5+D57i1V2psO9l4xMOH/ses9/dzBYnuYdiVCEyYxm?= =?us-ascii?Q?cmMg9PUgoPqYoYAqR0g5b0t7VndbZX7GjhevwIrfiGv4Tu9eJCT3ZfTlfTW5?= =?us-ascii?Q?F8qwhuZJ+cBnP5d37wdd2kQkzB/tZJbL5b4PpQ1CL2m5cp2zcv8Nm5gagx81?= =?us-ascii?Q?B3XByUXVuowgBwPUXzoSlUPKJzUGpLRDLCgxSR4zvBiDfPt3qoBxND2qthZA?= =?us-ascii?Q?ntuk19efxZPW5/6u16in4vGe/OemkeW2NdsUXhX8fcii7GA/qnyQt+cB8bSO?= =?us-ascii?Q?cb+/XzgPhX3tmo2gEEJMCZsfSZzvKnS/NGTQ+P606yQtStYffu291rOg28af?= =?us-ascii?Q?uM1HftlUX1a+mvlXNtiGwb+DaOc0wasTPgcSM66G7uUVkCEU1Q=3D=3D?= X-Forefront-Antispam-Report: CIP:165.204.84.17;CTRY:US;LANG:en;SCL:1;SRV:;IPV:CAL;SFV:NSPM;H:SATLEXMB03.amd.com;PTR:InfoDomainNonexistent;CAT:NONE;SFS:(13230040)(1800799024)(36860700013)(82310400026)(376014);DIR:OUT;SFP:1101; X-OriginatorOrg: amd.com X-MS-Exchange-CrossTenant-OriginalArrivalTime: 11 Nov 2024 17:32:37.8934 (UTC) X-MS-Exchange-CrossTenant-Network-Message-Id: 33f39db3-baec-43cd-f702-08dd0276d643 X-MS-Exchange-CrossTenant-Id: 3dd8961f-e488-4e60-8e11-a82d994e183d X-MS-Exchange-CrossTenant-OriginalAttributedTenantConnectingIp: TenantId=3dd8961f-e488-4e60-8e11-a82d994e183d;Ip=[165.204.84.17];Helo=[SATLEXMB03.amd.com] X-MS-Exchange-CrossTenant-AuthSource: CY4PEPF0000E9CF.namprd03.prod.outlook.com X-MS-Exchange-CrossTenant-AuthAs: Anonymous X-MS-Exchange-CrossTenant-FromEntityHeader: HybridOnPrem X-MS-Exchange-Transport-CrossTenantHeadersStamped: CH3PR12MB8404 Content-Type: text/plain; charset="utf-8" The AI Engine consists of 2D array of tiles arranged as columns. Provides the basic column allocation and release functions for the tile columns. Co-developed-by: Min Ma Signed-off-by: Min Ma Reviewed-by: Jeffrey Hugo Signed-off-by: Lizhi Hou --- drivers/accel/amdxdna/Makefile | 1 + drivers/accel/amdxdna/aie2_pci.c | 23 +- drivers/accel/amdxdna/aie2_solver.c | 330 ++++++++++++++++++++++++ drivers/accel/amdxdna/aie2_solver.h | 154 +++++++++++ drivers/accel/amdxdna/amdxdna_pci_drv.h | 1 + 5 files changed, 508 insertions(+), 1 deletion(-) create mode 100644 drivers/accel/amdxdna/aie2_solver.c create mode 100644 drivers/accel/amdxdna/aie2_solver.h diff --git a/drivers/accel/amdxdna/Makefile b/drivers/accel/amdxdna/Makefile index 1b4e78b43b44..39d3404fbc8f 100644 --- a/drivers/accel/amdxdna/Makefile +++ b/drivers/accel/amdxdna/Makefile @@ -5,6 +5,7 @@ amdxdna-y :=3D \ aie2_pci.o \ aie2_psp.o \ aie2_smu.o \ + aie2_solver.o \ amdxdna_mailbox.o \ amdxdna_mailbox_helper.o \ amdxdna_pci_drv.o \ diff --git a/drivers/accel/amdxdna/aie2_pci.c b/drivers/accel/amdxdna/aie2_= pci.c index d4acee1cee31..ce0822238b11 100644 --- a/drivers/accel/amdxdna/aie2_pci.c +++ b/drivers/accel/amdxdna/aie2_pci.c @@ -14,9 +14,14 @@ =20 #include "aie2_msg_priv.h" #include "aie2_pci.h" +#include "aie2_solver.h" #include "amdxdna_mailbox.h" #include "amdxdna_pci_drv.h" =20 +int aie2_max_col =3D XRS_MAX_COL; +module_param(aie2_max_col, uint, 0600); +MODULE_PARM_DESC(aie2_max_col, "Maximum column could be used"); + /* * The management mailbox channel is allocated by firmware. * The related register and ring buffer information is on SRAM BAR. @@ -307,6 +312,7 @@ static int aie2_init(struct amdxdna_dev *xdna) { struct pci_dev *pdev =3D to_pci_dev(xdna->ddev.dev); void __iomem *tbl[PCI_NUM_RESOURCES] =3D {0}; + struct init_config xrs_cfg =3D { 0 }; struct amdxdna_dev_hdl *ndev; struct psp_config psp_conf; const struct firmware *fw; @@ -403,7 +409,22 @@ static int aie2_init(struct amdxdna_dev *xdna) XDNA_ERR(xdna, "Query firmware failed, ret %d", ret); goto stop_hw; } - ndev->total_col =3D ndev->metadata.cols; + ndev->total_col =3D min(aie2_max_col, ndev->metadata.cols); + + xrs_cfg.clk_list.num_levels =3D 3; + xrs_cfg.clk_list.cu_clk_list[0] =3D 0; + xrs_cfg.clk_list.cu_clk_list[1] =3D 800; + xrs_cfg.clk_list.cu_clk_list[2] =3D 1000; + xrs_cfg.sys_eff_factor =3D 1; + xrs_cfg.ddev =3D &xdna->ddev; + xrs_cfg.total_col =3D ndev->total_col; + + xdna->xrs_hdl =3D xrsm_init(&xrs_cfg); + if (!xdna->xrs_hdl) { + XDNA_ERR(xdna, "Initialize resolver failed"); + ret =3D -EINVAL; + goto stop_hw; + } =20 release_firmware(fw); return 0; diff --git a/drivers/accel/amdxdna/aie2_solver.c b/drivers/accel/amdxdna/ai= e2_solver.c new file mode 100644 index 000000000000..a537c66589a4 --- /dev/null +++ b/drivers/accel/amdxdna/aie2_solver.c @@ -0,0 +1,330 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2022-2024, Advanced Micro Devices, Inc. + */ + +#include +#include +#include +#include +#include + +#include "aie2_solver.h" + +struct partition_node { + struct list_head list; + u32 nshared; /* # shared requests */ + u32 start_col; /* start column */ + u32 ncols; /* # columns */ + bool exclusive; /* can not be shared if set */ +}; + +struct solver_node { + struct list_head list; + u64 rid; /* Request ID from consumer */ + + struct partition_node *pt_node; + void *cb_arg; + u32 cols_len; + u32 start_cols[] __counted_by(cols_len); +}; + +struct solver_rgroup { + u32 rgid; + u32 nnode; + u32 npartition_node; + + DECLARE_BITMAP(resbit, XRS_MAX_COL); + struct list_head node_list; + struct list_head pt_node_list; +}; + +struct solver_state { + struct solver_rgroup rgp; + struct init_config cfg; + struct xrs_action_ops *actions; +}; + +static u32 calculate_gops(struct aie_qos *rqos) +{ + u32 service_rate =3D 0; + + if (rqos->latency) + service_rate =3D (1000 / rqos->latency); + + if (rqos->fps > service_rate) + return rqos->fps * rqos->gops; + + return service_rate * rqos->gops; +} + +/* + * qos_meet() - Check the QOS request can be met. + */ +static int qos_meet(struct solver_state *xrs, struct aie_qos *rqos, u32 cg= ops) +{ + u32 request_gops =3D calculate_gops(rqos) * xrs->cfg.sys_eff_factor; + + if (request_gops <=3D cgops) + return 0; + + return -EINVAL; +} + +/* + * sanity_check() - Do a basic sanity check on allocation request. + */ +static int sanity_check(struct solver_state *xrs, struct alloc_requests *r= eq) +{ + struct cdo_parts *cdop =3D &req->cdo; + struct aie_qos *rqos =3D &req->rqos; + u32 cu_clk_freq; + + if (cdop->ncols > xrs->cfg.total_col) + return -EINVAL; + + /* + * We can find at least one CDOs groups that meet the + * GOPs requirement. + */ + cu_clk_freq =3D xrs->cfg.clk_list.cu_clk_list[xrs->cfg.clk_list.num_level= s - 1]; + + if (qos_meet(xrs, rqos, cdop->qos_cap.opc * cu_clk_freq / 1000)) + return -EINVAL; + + return 0; +} + +static struct solver_node *rg_search_node(struct solver_rgroup *rgp, u64 r= id) +{ + struct solver_node *node; + + list_for_each_entry(node, &rgp->node_list, list) { + if (node->rid =3D=3D rid) + return node; + } + + return NULL; +} + +static void remove_partition_node(struct solver_rgroup *rgp, + struct partition_node *pt_node) +{ + pt_node->nshared--; + if (pt_node->nshared > 0) + return; + + list_del(&pt_node->list); + rgp->npartition_node--; + + bitmap_clear(rgp->resbit, pt_node->start_col, pt_node->ncols); + kfree(pt_node); +} + +static void remove_solver_node(struct solver_rgroup *rgp, + struct solver_node *node) +{ + list_del(&node->list); + rgp->nnode--; + + if (node->pt_node) + remove_partition_node(rgp, node->pt_node); + + kfree(node); +} + +static int get_free_partition(struct solver_state *xrs, + struct solver_node *snode, + struct alloc_requests *req) +{ + struct partition_node *pt_node; + u32 ncols =3D req->cdo.ncols; + u32 col, i; + + for (i =3D 0; i < snode->cols_len; i++) { + col =3D snode->start_cols[i]; + if (find_next_bit(xrs->rgp.resbit, XRS_MAX_COL, col) >=3D col + ncols) + break; + } + + if (i =3D=3D snode->cols_len) + return -ENODEV; + + pt_node =3D kzalloc(sizeof(*pt_node), GFP_KERNEL); + if (!pt_node) + return -ENOMEM; + + pt_node->nshared =3D 1; + pt_node->start_col =3D col; + pt_node->ncols =3D ncols; + + /* + * Before fully support latency in QoS, if a request + * specifies a non-zero latency value, it will not share + * the partition with other requests. + */ + if (req->rqos.latency) + pt_node->exclusive =3D true; + + list_add_tail(&pt_node->list, &xrs->rgp.pt_node_list); + xrs->rgp.npartition_node++; + bitmap_set(xrs->rgp.resbit, pt_node->start_col, pt_node->ncols); + + snode->pt_node =3D pt_node; + + return 0; +} + +static int allocate_partition(struct solver_state *xrs, + struct solver_node *snode, + struct alloc_requests *req) +{ + struct partition_node *pt_node, *rpt_node =3D NULL; + int idx, ret; + + ret =3D get_free_partition(xrs, snode, req); + if (!ret) + return ret; + + /* try to get a share-able partition */ + list_for_each_entry(pt_node, &xrs->rgp.pt_node_list, list) { + if (pt_node->exclusive) + continue; + + if (rpt_node && pt_node->nshared >=3D rpt_node->nshared) + continue; + + for (idx =3D 0; idx < snode->cols_len; idx++) { + if (snode->start_cols[idx] !=3D pt_node->start_col) + continue; + + if (req->cdo.ncols !=3D pt_node->ncols) + continue; + + rpt_node =3D pt_node; + break; + } + } + + if (!rpt_node) + return -ENODEV; + + rpt_node->nshared++; + snode->pt_node =3D rpt_node; + + return 0; +} + +static struct solver_node *create_solver_node(struct solver_state *xrs, + struct alloc_requests *req) +{ + struct cdo_parts *cdop =3D &req->cdo; + struct solver_node *node; + int ret; + + node =3D kzalloc(struct_size(node, start_cols, cdop->cols_len), GFP_KERNE= L); + if (!node) + return ERR_PTR(-ENOMEM); + + node->rid =3D req->rid; + node->cols_len =3D cdop->cols_len; + memcpy(node->start_cols, cdop->start_cols, cdop->cols_len * sizeof(u32)); + + ret =3D allocate_partition(xrs, node, req); + if (ret) + goto free_node; + + list_add_tail(&node->list, &xrs->rgp.node_list); + xrs->rgp.nnode++; + return node; + +free_node: + kfree(node); + return ERR_PTR(ret); +} + +static void fill_load_action(struct solver_state *xrs, + struct solver_node *snode, + struct xrs_action_load *action) +{ + action->rid =3D snode->rid; + action->part.start_col =3D snode->pt_node->start_col; + action->part.ncols =3D snode->pt_node->ncols; +} + +int xrs_allocate_resource(void *hdl, struct alloc_requests *req, void *cb_= arg) +{ + struct xrs_action_load load_act; + struct solver_node *snode; + struct solver_state *xrs; + int ret; + + xrs =3D (struct solver_state *)hdl; + + ret =3D sanity_check(xrs, req); + if (ret) { + drm_err(xrs->cfg.ddev, "invalid request"); + return ret; + } + + if (rg_search_node(&xrs->rgp, req->rid)) { + drm_err(xrs->cfg.ddev, "rid %lld is in-use", req->rid); + return -EEXIST; + } + + snode =3D create_solver_node(xrs, req); + if (IS_ERR(snode)) + return PTR_ERR(snode); + + fill_load_action(xrs, snode, &load_act); + ret =3D xrs->cfg.actions->load(cb_arg, &load_act); + if (ret) + goto free_node; + + snode->cb_arg =3D cb_arg; + + drm_dbg(xrs->cfg.ddev, "start col %d ncols %d\n", + snode->pt_node->start_col, snode->pt_node->ncols); + + return 0; + +free_node: + remove_solver_node(&xrs->rgp, snode); + + return ret; +} + +int xrs_release_resource(void *hdl, u64 rid) +{ + struct solver_state *xrs =3D hdl; + struct solver_node *node; + + node =3D rg_search_node(&xrs->rgp, rid); + if (!node) { + drm_err(xrs->cfg.ddev, "node not exist"); + return -ENODEV; + } + + xrs->cfg.actions->unload(node->cb_arg); + remove_solver_node(&xrs->rgp, node); + + return 0; +} + +void *xrsm_init(struct init_config *cfg) +{ + struct solver_rgroup *rgp; + struct solver_state *xrs; + + xrs =3D drmm_kzalloc(cfg->ddev, sizeof(*xrs), GFP_KERNEL); + if (!xrs) + return NULL; + + memcpy(&xrs->cfg, cfg, sizeof(*cfg)); + + rgp =3D &xrs->rgp; + INIT_LIST_HEAD(&rgp->node_list); + INIT_LIST_HEAD(&rgp->pt_node_list); + + return xrs; +} diff --git a/drivers/accel/amdxdna/aie2_solver.h b/drivers/accel/amdxdna/ai= e2_solver.h new file mode 100644 index 000000000000..9b1847bb46a6 --- /dev/null +++ b/drivers/accel/amdxdna/aie2_solver.h @@ -0,0 +1,154 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2023-2024, Advanced Micro Devices, Inc. + */ + +#ifndef _AIE2_SOLVER_H +#define _AIE2_SOLVER_H + +#define XRS_MAX_COL 128 + +/* + * Structure used to describe a partition. A partition is column based + * allocation unit described by its start column and number of columns. + */ +struct aie_part { + u32 start_col; + u32 ncols; +}; + +/* + * The QoS capabilities of a given AIE partition. + */ +struct aie_qos_cap { + u32 opc; /* operations per cycle */ + u32 dma_bw; /* DMA bandwidth */ +}; + +/* + * QoS requirement of a resource allocation. + */ +struct aie_qos { + u32 gops; /* Giga operations */ + u32 fps; /* Frames per second */ + u32 dma_bw; /* DMA bandwidth */ + u32 latency; /* Frame response latency */ + u32 exec_time; /* Frame execution time */ + u32 priority; /* Request priority */ +}; + +/* + * Structure used to describe a relocatable CDO (Configuration Data Object= ). + */ +struct cdo_parts { + u32 *start_cols; /* Start column array */ + u32 cols_len; /* Length of start column array */ + u32 ncols; /* # of column */ + struct aie_qos_cap qos_cap; /* CDO QoS capabilities */ +}; + +/* + * Structure used to describe a request to allocate. + */ +struct alloc_requests { + u64 rid; + struct cdo_parts cdo; + struct aie_qos rqos; /* Requested QoS */ +}; + +/* + * Load callback argument + */ +struct xrs_action_load { + u32 rid; + struct aie_part part; +}; + +/* + * Define the power level available + * + * POWER_LEVEL_MIN: + * Lowest power level. Usually set when all actions are unloaded. + * + * POWER_LEVEL_n + * Power levels 0 - n, is a step increase in system frequencies + */ +enum power_level { + POWER_LEVEL_MIN =3D 0x0, + POWER_LEVEL_0 =3D 0x1, + POWER_LEVEL_1 =3D 0x2, + POWER_LEVEL_2 =3D 0x3, + POWER_LEVEL_3 =3D 0x4, + POWER_LEVEL_4 =3D 0x5, + POWER_LEVEL_5 =3D 0x6, + POWER_LEVEL_6 =3D 0x7, + POWER_LEVEL_7 =3D 0x8, + POWER_LEVEL_NUM, +}; + +/* + * Structure used to describe the frequency table. + * Resource solver chooses the frequency from the table + * to meet the QOS requirements. + */ +struct clk_list_info { + u32 num_levels; /* available power levels */ + u32 cu_clk_list[POWER_LEVEL_NUM]; /* available aie clock frequen= cies in Mhz*/ +}; + +struct xrs_action_ops { + int (*load)(void *cb_arg, struct xrs_action_load *action); + int (*unload)(void *cb_arg); +}; + +/* + * Structure used to describe information for solver during initialization. + */ +struct init_config { + u32 total_col; + u32 sys_eff_factor; /* system efficiency factor */ + u32 latency_adj; /* latency adjustment in ms */ + struct clk_list_info clk_list; /* List of frequencies available in = system */ + struct drm_device *ddev; + struct xrs_action_ops *actions; +}; + +/* + * xrsm_init() - Register resource solver. Resource solver client needs + * to call this function to register itself. + * + * @cfg: The system metrics for resource solver to use + * + * Return: A resource solver handle + * + * Note: We should only create one handle per AIE array to be managed. + */ +void *xrsm_init(struct init_config *cfg); + +/* + * xrs_allocate_resource() - Request to allocate resources for a given con= text + * and a partition metadata. (See struct part_me= ta) + * + * @hdl: Resource solver handle obtained from xrs_init() + * @req: Input to the Resource solver including request id + * and partition metadata. + * @cb_arg: callback argument pointer + * + * Return: 0 when successful. + * Or standard error number when failing + * + * Note: + * There is no lock mechanism inside resource solver. So it is + * the caller's responsibility to lock down XCLBINs and grab + * necessary lock. + */ +int xrs_allocate_resource(void *hdl, struct alloc_requests *req, void *cb_= arg); + +/* + * xrs_release_resource() - Request to free resources for a given context. + * + * @hdl: Resource solver handle obtained from xrs_init() + * @rid: The Request ID to identify the requesting context + */ +int xrs_release_resource(void *hdl, u64 rid); +#endif /* _AIE2_SOLVER_H */ diff --git a/drivers/accel/amdxdna/amdxdna_pci_drv.h b/drivers/accel/amdxdn= a/amdxdna_pci_drv.h index 64bce970514b..c0710d3130fd 100644 --- a/drivers/accel/amdxdna/amdxdna_pci_drv.h +++ b/drivers/accel/amdxdna/amdxdna_pci_drv.h @@ -58,6 +58,7 @@ struct amdxdna_dev { struct drm_device ddev; struct amdxdna_dev_hdl *dev_handle; const struct amdxdna_dev_info *dev_info; + void *xrs_hdl; =20 struct mutex dev_lock; /* per device lock */ struct amdxdna_fw_ver fw_ver; --=20 2.34.1