From nobody Tue Feb 10 23:01:27 2026 Received: from BL2PR02CU003.outbound.protection.outlook.com (mail-eastusazon11011057.outbound.protection.outlook.com [52.101.52.57]) (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 8028926ED48; Mon, 9 Feb 2026 21:43:09 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=fail smtp.client-ip=52.101.52.57 ARC-Seal: i=2; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1770673391; cv=fail; b=IRztt/j+uPZ/ZbkGi4YUqbbw//l5ni4u2pl21/wVReYip25HRKKOJu+Ap66yMxHiK35fZtc6afuGw0A1LZNVylogg9vxyP55et4x3TMPtyy5zL0A0jHV/X1Ghgt5kCPN0qayCxEIbRRx8WFjGBiVl4PHUHJd4gGQXOqQ00OIzeI= ARC-Message-Signature: i=2; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1770673391; c=relaxed/simple; bh=PQTsbUT7plG0wUVrGnrjr48gEbTYrvubPlz9iIm+HdY=; h=From:To:Cc:Subject:Date:Message-Id:In-Reply-To:References: Content-Type:MIME-Version; b=UbtDDDj0wlCJc1vxndHgqgkSgNBm/69ocl3/cM6RV5Wr1iMx6s63ceja5FGiuQg5s+bN8WzSsWVeDhX4eAYuqvBJ6hj2iIkKOKoNN7/3LJ4V8Nstfhf57JxcvM7rpYfDm78TzbqvhTJ1frnnrCNG+ZFSJ61MIkl4ehdO9UyK6Io= ARC-Authentication-Results: i=2; smtp.subspace.kernel.org; dmarc=pass (p=reject dis=none) header.from=nvidia.com; spf=fail smtp.mailfrom=nvidia.com; dkim=pass (2048-bit key) header.d=Nvidia.com header.i=@Nvidia.com header.b=MojgspjM; arc=fail smtp.client-ip=52.101.52.57 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=reject dis=none) header.from=nvidia.com Authentication-Results: smtp.subspace.kernel.org; spf=fail smtp.mailfrom=nvidia.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=Nvidia.com header.i=@Nvidia.com header.b="MojgspjM" ARC-Seal: i=1; a=rsa-sha256; s=arcselector10001; d=microsoft.com; cv=none; b=Tf0x/P6TXnQuwUp/THPS24LEIEyYUqZ8C9r2NyvTjNrUXcgma5A8AWBnbipo7gLySnzBNC2N10klIz4zSqZn9o/pR2JZdGl8wDeFH9dqoSXdVnMLexUuFgaCGOTWfPheWljbJeDFvpDZf+kOkydKTN33s+cWeMg7tagQsEO55uF/tbyP/w+C+nuWQnm6IM6qX9AcKPcOQun5seHBET8Zikj23MlUI7/If8dVdUTbFTZud3dF/SvVAQbZtwHyU56csSKbDP1MVR2XuQ1YZrU2/bbPynktCPBr+O+S4PGwNMJzb28MgbpyBBAFUVaEnHCHfZm1w3TcuHFKcP1wPQCx/g== 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=etkSDa6lu5kXrrUuZnzh7GkzN5919YLao+lGLA9tXZE=; b=Dw3PFT8GOldF3eSTUQd6mCeGU9Ih4rTaYTlP3GwWzWZNvYIzRyWf+2BTBYnRQMYFsBygOfzmvLC5t3O1Cz8+C6CI22GTElu7YVW7Ce1kN3ZEHNneGkpsklRYBdR51pfTQiGSjQzO/xXz21TrnaQcfVjmsNT4yuyj1B4HqgWt/kKQI5B6tQNaXFg2VgXtThsLsgyOjugc5MMm2/b57R0P7sKME+gF/gwYWzkLmQJnEsqO97RFmjR+Ghib+kDuNvTVBbSErAU8jG39JQ9t9byts4J6FM74mjZPPxuAZ+8aLlCURtojy1bV+vYvgWXkomEm9VqpzHzlgH/kxc+OwAa1SA== ARC-Authentication-Results: i=1; mx.microsoft.com 1; spf=pass smtp.mailfrom=nvidia.com; dmarc=pass action=none header.from=nvidia.com; dkim=pass header.d=nvidia.com; arc=none DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=Nvidia.com; s=selector2; h=From:Date:Subject:Message-ID:Content-Type:MIME-Version:X-MS-Exchange-SenderADCheck; bh=etkSDa6lu5kXrrUuZnzh7GkzN5919YLao+lGLA9tXZE=; b=MojgspjM6iWt/Z9uCJjOGsHEaRq2v1HksTOKgvnUZqGig5yiAf6VbQDbxYP6j1zq8jFCkHXw2Y05dZcC+Crxdo3tyQAewmON9SE3jFtkXgu9qhP5bIBTOlpK707w9hQorJAZUNnLlRUCkonZOzCjRt2d13i6KDi1CICE6rIhmuVMyhKjFQfv0E9AaLf9ebNvORKzXwyctadxnWS9uA+YyL+XhZmPwySdtcwWc+DeVr/2lkPqPkMkMjhQQQbiY9TOvYsAJuXYWdQwLYsLNlIhuVelhmB3hcQvsWEgwRUhY0x3Jx24z1kBHPnI8b4/1pEPTXTwQwC9TA6BXQiakOCcKw== Authentication-Results: dkim=none (message not signed) header.d=none;dmarc=none action=none header.from=nvidia.com; Received: from DS0PR12MB6486.namprd12.prod.outlook.com (2603:10b6:8:c5::21) by CY5PR12MB6108.namprd12.prod.outlook.com (2603:10b6:930:27::15) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id 15.20.9587.19; Mon, 9 Feb 2026 21:42:57 +0000 Received: from DS0PR12MB6486.namprd12.prod.outlook.com ([fe80::88a9:f314:c95f:8b33]) by DS0PR12MB6486.namprd12.prod.outlook.com ([fe80::88a9:f314:c95f:8b33%4]) with mapi id 15.20.9587.017; Mon, 9 Feb 2026 21:42:57 +0000 From: Joel Fernandes To: linux-kernel@vger.kernel.org Cc: Maarten Lankhorst , Maxime Ripard , Thomas Zimmermann , David Airlie , Simona Vetter , Jonathan Corbet , Alex Deucher , =?UTF-8?q?Christian=20K=C3=B6nig?= , Jani Nikula , Joonas Lahtinen , Rodrigo Vivi , Tvrtko Ursulin , Huang Rui , Matthew Auld , Matthew Brost , Lucas De Marchi , =?UTF-8?q?Thomas=20Hellstr=C3=B6m?= , Helge Deller , Danilo Krummrich , Alice Ryhl , Miguel Ojeda , Alex Gaynor , Boqun Feng , Gary Guo , =?UTF-8?q?Bj=C3=B6rn=20Roy=20Baron?= , Benno Lossin , Andreas Hindborg , Trevor Gross , John Hubbard , Alistair Popple , Timur Tabi , Edwin Peer , Alexandre Courbot , Andrea Righi , Andy Ritger , Zhi Wang , Balbir Singh , Philipp Stanner , Elle Rhumsaa , Daniel Almeida , joel@joelfernandes.org, nouveau@lists.freedesktop.org, dri-devel@lists.freedesktop.org, rust-for-linux@vger.kernel.org, linux-doc@vger.kernel.org, amd-gfx@lists.freedesktop.org, intel-gfx@lists.freedesktop.org, intel-xe@lists.freedesktop.org, linux-fbdev@vger.kernel.org, Joel Fernandes Subject: [PATCH -next v8 2/3] rust: gpu: Add GPU buddy allocator bindings Date: Mon, 9 Feb 2026 16:42:45 -0500 Message-Id: <20260209214246.2783990-3-joelagnelf@nvidia.com> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20260209214246.2783990-1-joelagnelf@nvidia.com> References: <20260209214246.2783990-1-joelagnelf@nvidia.com> Content-Transfer-Encoding: quoted-printable X-ClientProxiedBy: IA4P220CA0011.NAMP220.PROD.OUTLOOK.COM (2603:10b6:208:558::11) To DS0PR12MB6486.namprd12.prod.outlook.com (2603:10b6:8:c5::21) Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 X-MS-PublicTrafficType: Email X-MS-TrafficTypeDiagnostic: DS0PR12MB6486:EE_|CY5PR12MB6108:EE_ X-MS-Office365-Filtering-Correlation-Id: 9210bdc7-8398-48fa-1a0d-08de6824306e X-MS-Exchange-SenderADCheck: 1 X-MS-Exchange-AntiSpam-Relay: 0 X-Microsoft-Antispam: BCL:0;ARA:13230040|7416014|376014|366016|1800799024; X-Microsoft-Antispam-Message-Info: =?us-ascii?Q?7c8UBbaNT2uRrl8MC6aJGg9Mg/cA3HR+MIxrxzaBcki3jFOF8nYPHwkWY5g6?= =?us-ascii?Q?mALh73fX1y+DdsgbWpVnvPRM1NzzOxT9irXLmt1PVdCXr1/YTDwOCmFgAia+?= =?us-ascii?Q?Z8QXtGlzrI6lnwDm6z8mZphjTsKOdMjAxltoCAtxSMZFY7nb9/HOzjaf/FW3?= =?us-ascii?Q?2h22ttDdqB67EJV1Ex5ZNbTgj2UwDtG0I7VsK8Ow14fBlTt4GzimQYcayfRV?= =?us-ascii?Q?1NQdM2ByZKzQnyGlyPRKT1U6x4wmkOlHgXHvOPMLXBggce7WSlu6RmDJkClb?= =?us-ascii?Q?LyaQa5+wiF2sM2hF42ZMiqbDq9DyqaZEJw9cXmB1hUVgg9HuQbOJTDq20gOJ?= =?us-ascii?Q?CL1lD14dTbeH/hpPEHWfdDZD017QFCqacFc9uv1YESHitkKYX5rT4S13iVQp?= =?us-ascii?Q?ZxjKK4uvsM74m/y0QAI2w9ODuG4qswI7WAfpXED081Guaet14Nc53qqNVTn2?= =?us-ascii?Q?vNFbEwwh8aRrnG5/FE9zZR+gkUH+wA7PQq4Ul9wKtiq7BLT5SlPbWyvtEtoo?= =?us-ascii?Q?hwa0eOr1d55SITLJTEPPVEbX+Z0kh9u0BzumQemCRb90PtMy7ghgPdez4cST?= =?us-ascii?Q?ckoYkwiuG4xw4RAK/L1tEpwNvGANku7DHWovyqVRG0Bx8fcmz/O/4NLBWrIK?= =?us-ascii?Q?c0mBI3EmO/MvfN1S65ohLDXCbpN2xvx7efGJpr4GXMRD0VEVsqbRR6LDx0b6?= =?us-ascii?Q?ZqcsJ6Cwv1+N5CSZvK17mnFGLyU6zFQFnqmmSTRMKFh5X/SZ38iI/IpdcR9X?= =?us-ascii?Q?EWtCvcDtbjWmqmuoqbhQUVWo/vbv3Vb6RK8t6rpQCeVLzm+1Loc/4mFc5foP?= =?us-ascii?Q?NGTNTLAmybOoe4XJ961/edyqgFFrfdMFoO7mUd0UonYiFm6G2bp/kVxvn+J4?= =?us-ascii?Q?kdfK+n0uCosZ+DM2oQpSKzy70K4GAO7jLAjyAOuTl+gXY1775iY33Tbrts8g?= =?us-ascii?Q?bpsx6/Nc06YXwOVUiTODNreWhjlGKJeQFfVUWZSdxVTTa/uCxjVbFTVOMjEJ?= =?us-ascii?Q?6OOQGEnxXibvyVgc6TS59QvJNjXKb+J83bBsfbMbX79DFB0TlboHiMRec5bw?= =?us-ascii?Q?npc1NY44+H99fELhK04N6tZLUNM+D9zLK+6x2+AMVldUcFH9nYTC6sotQYOa?= =?us-ascii?Q?Btl8Ippri+ub8PmQs0sjWQVA7tcOdCyQTx1Cr6nkDGn4xadQ6x4KYwIsyOyc?= =?us-ascii?Q?wpROKtICLyEjqB+loe516RngENFqNQU+BV9bvuXcBSkp2LyGqnyim+vzCDBZ?= =?us-ascii?Q?g1PLX1YkgKQ0xTClxbNhdeUOavzMxGnlp+DXGP/MlT8gfG4UFc/ZWvODptDm?= =?us-ascii?Q?6FdqwR04LUb/Nx5xWgCPoHEyHwvpRysALehTO0G05RS+I1RYLF8jS/1O6gVa?= =?us-ascii?Q?3v+keOuKZf2RfR6E1Jh+xGbEOqgeCgNnOtKRsDbxlDOMT8SwAR8p9NYj5Yp6?= =?us-ascii?Q?4cLX9+o/1bvicYWozHfOze6mO9FgKKEHZ3YgQ9SsKKnNG0ezrI3k/56/jNn0?= =?us-ascii?Q?tImjFuOzp+w4WmGgvAk0oUUwjiSV0gHUg8rnQPKCDfAWQYKxM2/9rvWfxKjN?= =?us-ascii?Q?NCjkpozv699a0zetPMk=3D?= X-Forefront-Antispam-Report: CIP:255.255.255.255;CTRY:;LANG:en;SCL:1;SRV:;IPV:NLI;SFV:NSPM;H:DS0PR12MB6486.namprd12.prod.outlook.com;PTR:;CAT:NONE;SFS:(13230040)(7416014)(376014)(366016)(1800799024);DIR:OUT;SFP:1101; X-MS-Exchange-AntiSpam-MessageData-ChunkCount: 1 X-MS-Exchange-AntiSpam-MessageData-0: =?us-ascii?Q?L4exT8iJ3d4y1csajQWtKlkyxih6+qw98b6XvYnIKtBn+/y6MIfib13LHRQU?= =?us-ascii?Q?0ugQRLRXXkdnJ8gFhEAHB4MLDsOWNszZdKN8AesBaWA5aHUlydKI8+FMlyfE?= =?us-ascii?Q?ZRzRwM8bD9PidFSfhQv5XNRUL+qcaFeVJh5UfwIyCmmNZVAw+Fmz4OeBKVOx?= =?us-ascii?Q?WLJwC93w0UgZijS7ZhYzLZyDW4MSUafZcTF1FJG5mg9+Q8QoIKobw6rA/pey?= =?us-ascii?Q?eSIkswmmF6/JvOqkEgBWfrxzxsx9bQwCSFMynP6vWBOBy8cASRO2xubSBo3A?= =?us-ascii?Q?8GC1zBwkQh22+hIkDoLSTXItKV1is5LxmxS3eclRrHRPuvMCDgxoGt25HSVB?= =?us-ascii?Q?dZ+n8eVAWDaQDUa94jFEwkc7R+6b2mPGs379eN6UzLj6vzBiBz00crDpfVAH?= =?us-ascii?Q?EuwDTLpTnV3Ma3YSkkbKk4FHgXNvUiAeQO7E5AbPlxvdWpgBE78vIkKcrWIi?= =?us-ascii?Q?1QYrPyIOWFgbBsWYCoDiyeoT96cC425Zp8iEbL2pSgSyxqw7y+5WI+LhGiT7?= =?us-ascii?Q?ifWSHK4yoHQArQ6siSer+spG5WvT0qI16zGZ5pTxPykZcnD/Hqcu2fne3jB6?= =?us-ascii?Q?qY2ZVoaok0Z1YAeYXVGUJvFgqumxfL3BhtHL8EDw0lDIBQ9IxhydSp0IrvDh?= =?us-ascii?Q?XZQ0u+pvuA4YawjiYkcS6qrk2rH27X1HBS0sZCV5zuXMCtRjHmwxBqLfB0rc?= =?us-ascii?Q?FqHmCvP5C9vjWzUAm7r78IfldzMMTPlBJOm0Uc08BzHzYYEzePmoPhVUTDBA?= =?us-ascii?Q?1O/Pt9oE9M26Bl/q4wIYx18K3dhHK/xTHz5cNEt9J0Gj6tPiA9CdwLgFgK/5?= =?us-ascii?Q?mDz9ufpVlul4lo5/DIsu6FOfYN6fx87Yol5Am3+KlOzQVoW2g7LaB5xNyX1M?= =?us-ascii?Q?zw03UTxoCxG8nbrocUXc4Ao7jca5BubJvb9pYjWtEP90pMAukmcwGpxUjbam?= =?us-ascii?Q?zX6u8l8LqCnBI8QtpU5kt+O07T4negn7HFfcuEikZngVSTv9+SQudWd7Ramx?= =?us-ascii?Q?BuHXaWwiov4nL5XDc+xrALZKY+dBql+IeTGtckey4Mce2tmW5KUs1P/xq8NC?= =?us-ascii?Q?bQQqwtEpYP9sPC/3q/7IIw/KpsUzcOG0fnfbHQZETinl6QHOHzip9h6Zm13l?= =?us-ascii?Q?VxWmmqXIn91ENhVMs5vdsw4y5DRDNxM5dzBBWfhukHBmUGELadM8Iq/Apl/i?= =?us-ascii?Q?W2xSyrM62jUuxCHr5HCs9qeNqMgJvyuL2y05JKr/fjS5hZjkuhbqCCF/QTr1?= =?us-ascii?Q?IdHHcquqQjoMrIHuzjISwjwjNWze/LWpCk5xrQUfb4w3B4smV5UaODVM9ioe?= =?us-ascii?Q?c1JIMUm/di0+h8j3EjDtyiCvr1hFfqV2ZGzxZ+fdKMctHg4qh2x36L66zuyF?= =?us-ascii?Q?Up0fS8aCxFjp7cUAbfU9AGBoxo+qFNgmmgr5KtLQ0qmXhBfmYJ0PidXL6TTL?= =?us-ascii?Q?eWAob0P/WjAv4YPclIN5k6q7UkpV0pRMp1Y2FYpIHL6yzIVhYrceSisrok9m?= =?us-ascii?Q?0EaHl70pdrNbHhFHUWj6DM7biuZi44TUGrMKpZjvgeVVFMf9Q/QdC2e0E0b4?= =?us-ascii?Q?vittD2Mwe+FvqEy3JAISxp2EP9if2meSIliPBAqTe+6kC6oBpJjBNhHgt52Q?= =?us-ascii?Q?7hApjRWjHzcDXvgAP7ehTe4wbdtg457bHA5T3nD3GYIjRTBuCL6Eu8ErTv89?= =?us-ascii?Q?mWpfiLVEnV95g7AZVm7PgdwFR5/2ATSHsUSp6mNnEhcrHGCv/ZFi/Rdg9q8G?= =?us-ascii?Q?g4W1ES9qjA=3D=3D?= X-OriginatorOrg: Nvidia.com X-MS-Exchange-CrossTenant-Network-Message-Id: 9210bdc7-8398-48fa-1a0d-08de6824306e X-MS-Exchange-CrossTenant-AuthSource: DS0PR12MB6486.namprd12.prod.outlook.com X-MS-Exchange-CrossTenant-AuthAs: Internal X-MS-Exchange-CrossTenant-OriginalArrivalTime: 09 Feb 2026 21:42:57.6462 (UTC) X-MS-Exchange-CrossTenant-FromEntityHeader: Hosted X-MS-Exchange-CrossTenant-Id: 43083d15-7273-40c1-b7db-39efd9ccc17a X-MS-Exchange-CrossTenant-MailboxType: HOSTED X-MS-Exchange-CrossTenant-UserPrincipalName: RS9IgiI73grSYc00PDOCRcxsistFLXHbPkXneSDiVsLZoXjqm+u1UH0P5LeBdLqnXGvm0aCT57F7ouOIpQAGQA== X-MS-Exchange-Transport-CrossTenantHeadersStamped: CY5PR12MB6108 Content-Type: text/plain; charset="utf-8" Add safe Rust abstractions over the Linux kernel's GPU buddy allocator for physical memory management. The GPU buddy allocator implements a binary buddy system useful for GPU physical memory allocation. nova-core will use it for physical memory allocation. Signed-off-by: Joel Fernandes --- rust/bindings/bindings_helper.h | 11 + rust/helpers/gpu.c | 23 ++ rust/helpers/helpers.c | 1 + rust/kernel/gpu/buddy.rs | 530 ++++++++++++++++++++++++++++++++ rust/kernel/gpu/mod.rs | 5 + rust/kernel/lib.rs | 2 + 6 files changed, 572 insertions(+) create mode 100644 rust/helpers/gpu.c create mode 100644 rust/kernel/gpu/buddy.rs create mode 100644 rust/kernel/gpu/mod.rs diff --git a/rust/bindings/bindings_helper.h b/rust/bindings/bindings_helpe= r.h index 083cc44aa952..dbb765a9fdbd 100644 --- a/rust/bindings/bindings_helper.h +++ b/rust/bindings/bindings_helper.h @@ -29,6 +29,7 @@ #include =20 #include +#include #include #include #include @@ -146,6 +147,16 @@ const vm_flags_t RUST_CONST_HELPER_VM_MIXEDMAP =3D VM_= MIXEDMAP; const vm_flags_t RUST_CONST_HELPER_VM_HUGEPAGE =3D VM_HUGEPAGE; const vm_flags_t RUST_CONST_HELPER_VM_NOHUGEPAGE =3D VM_NOHUGEPAGE; =20 +#if IS_ENABLED(CONFIG_GPU_BUDDY) +const unsigned long RUST_CONST_HELPER_GPU_BUDDY_RANGE_ALLOCATION =3D GPU_B= UDDY_RANGE_ALLOCATION; +const unsigned long RUST_CONST_HELPER_GPU_BUDDY_TOPDOWN_ALLOCATION =3D GPU= _BUDDY_TOPDOWN_ALLOCATION; +const unsigned long RUST_CONST_HELPER_GPU_BUDDY_CONTIGUOUS_ALLOCATION =3D + GPU_BUDDY_CONTIGUOUS_ALLOCATION; +const unsigned long RUST_CONST_HELPER_GPU_BUDDY_CLEAR_ALLOCATION =3D GPU_B= UDDY_CLEAR_ALLOCATION; +const unsigned long RUST_CONST_HELPER_GPU_BUDDY_CLEARED =3D GPU_BUDDY_CLEA= RED; +const unsigned long RUST_CONST_HELPER_GPU_BUDDY_TRIM_DISABLE =3D GPU_BUDDY= _TRIM_DISABLE; +#endif + #if IS_ENABLED(CONFIG_ANDROID_BINDER_IPC_RUST) #include "../../drivers/android/binder/rust_binder.h" #include "../../drivers/android/binder/rust_binder_events.h" diff --git a/rust/helpers/gpu.c b/rust/helpers/gpu.c new file mode 100644 index 000000000000..38b1a4e6bef8 --- /dev/null +++ b/rust/helpers/gpu.c @@ -0,0 +1,23 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include + +#ifdef CONFIG_GPU_BUDDY + +__rust_helper u64 rust_helper_gpu_buddy_block_offset(const struct gpu_budd= y_block *block) +{ + return gpu_buddy_block_offset(block); +} + +__rust_helper unsigned int rust_helper_gpu_buddy_block_order(struct gpu_bu= ddy_block *block) +{ + return gpu_buddy_block_order(block); +} + +__rust_helper u64 rust_helper_gpu_buddy_block_size(struct gpu_buddy *mm, + struct gpu_buddy_block *block) +{ + return gpu_buddy_block_size(mm, block); +} + +#endif /* CONFIG_GPU_BUDDY */ diff --git a/rust/helpers/helpers.c b/rust/helpers/helpers.c index 724fcb8240ac..a53929ce52a3 100644 --- a/rust/helpers/helpers.c +++ b/rust/helpers/helpers.c @@ -32,6 +32,7 @@ #include "err.c" #include "irq.c" #include "fs.c" +#include "gpu.c" #include "io.c" #include "jump_label.c" #include "kunit.c" diff --git a/rust/kernel/gpu/buddy.rs b/rust/kernel/gpu/buddy.rs new file mode 100644 index 000000000000..00290ce53aeb --- /dev/null +++ b/rust/kernel/gpu/buddy.rs @@ -0,0 +1,530 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! GPU buddy allocator bindings. +//! +//! C header: [`include/linux/gpu_buddy.h`](srctree/include/linux/gpu_budd= y.h) +//! +//! This module provides Rust abstractions over the Linux kernel's GPU bud= dy +//! allocator, which implements a binary buddy memory allocator. +//! +//! The buddy allocator manages a contiguous address space and allocates b= locks +//! in power-of-two sizes, useful for GPU physical memory management. +//! +//! # Examples +//! +//! ``` +//! use kernel::{ +//! gpu::buddy::{BuddyFlags, GpuBuddy, GpuBuddyAllocParams, GpuBuddyPa= rams}, +//! prelude::*, +//! sizes::*, // +//! }; +//! +//! // Create a 1GB buddy allocator with 4KB minimum chunk size. +//! let buddy =3D GpuBuddy::new(&GpuBuddyParams { +//! base_offset_bytes: 0, +//! physical_memory_size_bytes: SZ_1G as u64, +//! chunk_size_bytes: SZ_4K as u64, +//! })?; +//! +//! // Verify initial state. +//! assert_eq!(buddy.size(), SZ_1G as u64); +//! assert_eq!(buddy.chunk_size(), SZ_4K as u64); +//! let initial_free =3D buddy.free_memory_bytes(); +//! +//! // Base allocation params - mutated between calls for field overrides. +//! let mut params =3D GpuBuddyAllocParams { +//! start_range_address: 0, +//! end_range_address: 0, // Entire range. +//! size_bytes: SZ_16M as u64, +//! min_block_size_bytes: SZ_16M as u64, +//! buddy_flags: BuddyFlags::try_new(BuddyFlags::RANGE_ALLOCATION)?, +//! }; +//! +//! // Test top-down allocation (allocates from highest addresses). +//! params.buddy_flags =3D BuddyFlags::try_new(BuddyFlags::TOPDOWN_ALLOCAT= ION)?; +//! let topdown =3D buddy.alloc_blocks(¶ms)?; +//! assert_eq!(buddy.free_memory_bytes(), initial_free - SZ_16M as u64); +//! +//! for block in topdown.iter() { +//! assert_eq!(block.offset(), (SZ_1G - SZ_16M) as u64); +//! assert_eq!(block.order(), 12); // 2^12 pages +//! assert_eq!(block.size(), SZ_16M as u64); +//! } +//! drop(topdown); +//! assert_eq!(buddy.free_memory_bytes(), initial_free); +//! +//! // Allocate 16MB - should result in a single 16MB block at offset 0. +//! params.buddy_flags =3D BuddyFlags::try_new(BuddyFlags::RANGE_ALLOCATIO= N)?; +//! let allocated =3D buddy.alloc_blocks(¶ms)?; +//! assert_eq!(buddy.free_memory_bytes(), initial_free - SZ_16M as u64); +//! +//! for block in allocated.iter() { +//! assert_eq!(block.offset(), 0); +//! assert_eq!(block.order(), 12); // 2^12 pages +//! assert_eq!(block.size(), SZ_16M as u64); +//! } +//! drop(allocated); +//! assert_eq!(buddy.free_memory_bytes(), initial_free); +//! +//! // Test non-contiguous allocation with fragmented memory. +//! // Create fragmentation by allocating 4MB blocks at [0,4M) and [8M,12M= ). +//! params.end_range_address =3D SZ_4M as u64; +//! params.size_bytes =3D SZ_4M as u64; +//! params.min_block_size_bytes =3D SZ_4M as u64; +//! let frag1 =3D buddy.alloc_blocks(¶ms)?; +//! assert_eq!(buddy.free_memory_bytes(), initial_free - SZ_4M as u64); +//! +//! params.start_range_address =3D SZ_8M as u64; +//! params.end_range_address =3D (SZ_8M + SZ_4M) as u64; +//! let frag2 =3D buddy.alloc_blocks(¶ms)?; +//! assert_eq!(buddy.free_memory_bytes(), initial_free - SZ_8M as u64); +//! +//! // Allocate 8MB without CONTIGUOUS - should return 2 blocks from the h= oles. +//! params.start_range_address =3D 0; +//! params.end_range_address =3D SZ_16M as u64; +//! params.size_bytes =3D SZ_8M as u64; +//! let fragmented =3D buddy.alloc_blocks(¶ms)?; +//! assert_eq!(buddy.free_memory_bytes(), initial_free - (SZ_16M) as u64); +//! +//! let (mut count, mut total) =3D (0u32, 0u64); +//! for block in fragmented.iter() { +//! // The 8MB allocation should return 2 blocks, each 4MB. +//! assert_eq!(block.size(), SZ_4M as u64); +//! total +=3D block.size(); +//! count +=3D 1; +//! } +//! assert_eq!(total, SZ_8M as u64); +//! assert_eq!(count, 2); +//! drop(fragmented); +//! drop(frag2); +//! drop(frag1); +//! assert_eq!(buddy.free_memory_bytes(), initial_free); +//! +//! // Test CONTIGUOUS failure when only fragmented space available. +//! // Create a small buddy allocator with only 16MB of memory. +//! let small =3D GpuBuddy::new(&GpuBuddyParams { +//! base_offset_bytes: 0, +//! physical_memory_size_bytes: SZ_16M as u64, +//! chunk_size_bytes: SZ_4K as u64, +//! })?; +//! +//! // Allocate 4MB blocks at [0,4M) and [8M,12M) to create fragmented mem= ory. +//! params.start_range_address =3D 0; +//! params.end_range_address =3D SZ_4M as u64; +//! params.size_bytes =3D SZ_4M as u64; +//! let hole1 =3D small.alloc_blocks(¶ms)?; +//! +//! params.start_range_address =3D SZ_8M as u64; +//! params.end_range_address =3D (SZ_8M + SZ_4M) as u64; +//! let hole2 =3D small.alloc_blocks(¶ms)?; +//! +//! // 8MB contiguous should fail - only two non-contiguous 4MB holes exis= t. +//! params.start_range_address =3D 0; +//! params.end_range_address =3D 0; +//! params.size_bytes =3D SZ_8M as u64; +//! params.buddy_flags =3D BuddyFlags::try_new(BuddyFlags::CONTIGUOUS_ALLO= CATION)?; +//! let result =3D small.alloc_blocks(¶ms); +//! assert!(result.is_err()); +//! drop(hole2); +//! drop(hole1); +//! +//! # Ok::<(), Error>(()) +//! ``` + +use crate::{ + bindings, + clist::CListHead, + clist_create, + error::to_result, + new_mutex, + prelude::*, + sync::{ + lock::mutex::MutexGuard, + Arc, + Mutex, // + }, + types::Opaque, +}; + +/// Flags for GPU buddy allocator operations. +/// +/// These flags control the allocation behavior of the buddy allocator. +#[derive(Clone, Copy, Default, PartialEq, Eq)] +pub struct BuddyFlags(usize); + +impl BuddyFlags { + /// Range-based allocation from start to end addresses. + pub const RANGE_ALLOCATION: usize =3D bindings::GPU_BUDDY_RANGE_ALLOCA= TION; + + /// Allocate from top of address space downward. + pub const TOPDOWN_ALLOCATION: usize =3D bindings::GPU_BUDDY_TOPDOWN_AL= LOCATION; + + /// Allocate physically contiguous blocks. + pub const CONTIGUOUS_ALLOCATION: usize =3D bindings::GPU_BUDDY_CONTIGU= OUS_ALLOCATION; + + /// Request allocation from the cleared (zeroed) memory. The zero'ing = is not + /// done by the allocator, but by the caller before freeing old blocks. + pub const CLEAR_ALLOCATION: usize =3D bindings::GPU_BUDDY_CLEAR_ALLOCA= TION; + + /// Disable trimming of partially used blocks. + pub const TRIM_DISABLE: usize =3D bindings::GPU_BUDDY_TRIM_DISABLE; + + /// Mark blocks as cleared (zeroed) when freeing. When set during free, + /// indicates that the caller has already zeroed the memory. + pub const CLEARED: usize =3D bindings::GPU_BUDDY_CLEARED; + + /// Create [`BuddyFlags`] from a raw value with validation. + /// + /// Use `|` operator to combine flags if needed, before calling this m= ethod. + pub fn try_new(flags: usize) -> Result { + // Flags must not exceed u32::MAX to satisfy the GPU buddy allocat= or C API. + if flags > u32::MAX as usize { + return Err(EINVAL); + } + + // `TOPDOWN_ALLOCATION` only works without `RANGE_ALLOCATION`. Whe= n both are + // set, `TOPDOWN_ALLOCATION` is silently ignored by the allocator.= Reject this. + if (flags & Self::RANGE_ALLOCATION) !=3D 0 && (flags & Self::TOPDO= WN_ALLOCATION) !=3D 0 { + return Err(EINVAL); + } + + Ok(Self(flags)) + } + + /// Get raw value of the flags. + pub(crate) fn as_raw(self) -> usize { + self.0 + } +} + +/// Parameters for creating a GPU buddy allocator. +pub struct GpuBuddyParams { + /// Base offset in bytes where the managed memory region starts. + /// Allocations will be offset by this value. + pub base_offset_bytes: u64, + /// Total physical memory size managed by the allocator in bytes. + pub physical_memory_size_bytes: u64, + /// Minimum allocation unit / chunk size in bytes, must be >=3D 4KB. + pub chunk_size_bytes: u64, +} + +/// Parameters for allocating blocks from a GPU buddy allocator. +pub struct GpuBuddyAllocParams { + /// Start of allocation range in bytes. Use 0 for beginning. + pub start_range_address: u64, + /// End of allocation range in bytes. Use 0 for entire range. + pub end_range_address: u64, + /// Total size to allocate in bytes. + pub size_bytes: u64, + /// Minimum block size for fragmented allocations in bytes. + pub min_block_size_bytes: u64, + /// Buddy allocator behavior flags. + pub buddy_flags: BuddyFlags, +} + +/// Inner structure holding the actual buddy allocator. +/// +/// # Synchronization +/// +/// The C `gpu_buddy` API requires synchronization (see `include/linux/gpu= _buddy.h`). +/// The internal [`GpuBuddyGuard`] ensures that the lock is held for all +/// allocator and free operations, preventing races between concurrent all= ocations +/// and the freeing that occurs when [`AllocatedBlocks`] is dropped. +/// +/// # Invariants +/// +/// The inner [`Opaque`] contains a valid, initialized buddy allocator. +#[pin_data(PinnedDrop)] +struct GpuBuddyInner { + #[pin] + inner: Opaque, + #[pin] + lock: Mutex<()>, + /// Base offset for all allocations (does not change after init). + base_offset: u64, + /// Cached chunk size (does not change after init). + chunk_size: u64, + /// Cached total size (does not change after init). + size: u64, +} + +impl GpuBuddyInner { + /// Create a pin-initializer for the buddy allocator. + fn new(params: &GpuBuddyParams) -> impl PinInit { + let base_offset =3D params.base_offset_bytes; + let size =3D params.physical_memory_size_bytes; + let chunk_size =3D params.chunk_size_bytes; + + try_pin_init!(Self { + inner <- Opaque::try_ffi_init(|ptr| { + // SAFETY: ptr points to valid uninitialized memory from t= he pin-init + // infrastructure. gpu_buddy_init will initialize the stru= cture. + to_result(unsafe { bindings::gpu_buddy_init(ptr, size, chu= nk_size) }) + }), + lock <- new_mutex!(()), + base_offset: base_offset, + chunk_size: chunk_size, + size: size, + }) + } + + /// Lock the mutex and return a guard for accessing the allocator. + fn lock(&self) -> GpuBuddyGuard<'_> { + GpuBuddyGuard { + inner: self, + _guard: self.lock.lock(), + } + } +} + +#[pinned_drop] +impl PinnedDrop for GpuBuddyInner { + fn drop(self: Pin<&mut Self>) { + let guard =3D self.lock(); + + // SAFETY: guard provides exclusive access to the allocator. + unsafe { + bindings::gpu_buddy_fini(guard.as_raw()); + } + } +} + +// SAFETY: [`GpuBuddyInner`] can be sent between threads. +unsafe impl Send for GpuBuddyInner {} + +// SAFETY: [`GpuBuddyInner`] is `Sync` because the internal [`GpuBuddyGuar= d`] +// serializes all access to the C allocator, preventing data races. +unsafe impl Sync for GpuBuddyInner {} + +/// Guard that proves the lock is held, enabling access to the allocator. +/// +/// # Invariants +/// +/// The inner `_guard` holds the lock for the duration of this guard's lif= etime. +pub(crate) struct GpuBuddyGuard<'a> { + inner: &'a GpuBuddyInner, + _guard: MutexGuard<'a, ()>, +} + +impl GpuBuddyGuard<'_> { + /// Get a raw pointer to the underlying C `gpu_buddy` structure. + fn as_raw(&self) -> *mut bindings::gpu_buddy { + self.inner.inner.get() + } +} + +/// GPU buddy allocator instance. +/// +/// This structure wraps the C `gpu_buddy` allocator using reference count= ing. +/// The allocator is automatically cleaned up when all references are drop= ped. +/// +/// # Invariants +/// +/// The inner [`Arc`] points to a valid, initialized GPU buddy allocator. +pub struct GpuBuddy(Arc); + +impl GpuBuddy { + /// Create a new buddy allocator. + /// + /// Creates a buddy allocator that manages a contiguous address space = of the given + /// size, with the specified minimum allocation unit (chunk_size must = be at least 4KB). + pub fn new(params: &GpuBuddyParams) -> Result { + Ok(Self(Arc::pin_init( + GpuBuddyInner::new(params), + GFP_KERNEL, + )?)) + } + + /// Get the base offset for allocations. + pub fn base_offset(&self) -> u64 { + self.0.base_offset + } + + /// Get the chunk size (minimum allocation unit). + pub fn chunk_size(&self) -> u64 { + self.0.chunk_size + } + + /// Get the total managed size. + pub fn size(&self) -> u64 { + self.0.size + } + + /// Get the available (free) memory in bytes. + pub fn free_memory_bytes(&self) -> u64 { + let guard =3D self.0.lock(); + // SAFETY: guard provides exclusive access to the allocator. + unsafe { (*guard.as_raw()).avail } + } + + /// Allocate blocks from the buddy allocator. + /// + /// Returns an [`Arc`] structure that owns the alloca= ted blocks + /// and automatically frees them when all references are dropped. + /// + /// Takes `&self` instead of `&mut self` because the internal [`Mutex`= ] provides + /// synchronization - no external `&mut` exclusivity needed. + pub fn alloc_blocks(&self, params: &GpuBuddyAllocParams) -> Result> { + let buddy_arc =3D Arc::clone(&self.0); + + // Create pin-initializer that initializes list and allocates bloc= ks. + let init =3D try_pin_init!(AllocatedBlocks { + buddy: Arc::clone(&buddy_arc), + list <- CListHead::new(), + flags: params.buddy_flags, + _: { + // Lock while allocating to serialize with concurrent free= s. + let guard =3D buddy.lock(); + + // SAFETY: `guard` provides exclusive access to the buddy = allocator. + to_result(unsafe { + bindings::gpu_buddy_alloc_blocks( + guard.as_raw(), + params.start_range_address, + params.end_range_address, + params.size_bytes, + params.min_block_size_bytes, + list.as_raw(), + params.buddy_flags.as_raw(), + ) + })? + } + }); + + Arc::pin_init(init, GFP_KERNEL) + } +} + +/// Allocated blocks from the buddy allocator with automatic cleanup. +/// +/// This structure owns a list of allocated blocks and ensures they are +/// automatically freed when dropped. Use `iter()` to iterate over all +/// allocated [`Block`] structures. +/// +/// # Invariants +/// +/// - `list` is an initialized, valid list head containing allocated block= s. +/// - `buddy` references a valid [`GpuBuddyInner`]. +#[pin_data(PinnedDrop)] +pub struct AllocatedBlocks { + #[pin] + list: CListHead, + buddy: Arc, + flags: BuddyFlags, +} + +impl AllocatedBlocks { + /// Check if the block list is empty. + pub fn is_empty(&self) -> bool { + // An empty list head points to itself. + !self.list.is_linked() + } + + /// Iterate over allocated blocks. + /// + /// Returns an iterator yielding [`AllocatedBlock`] references. The bl= ocks + /// are only valid for the duration of the borrow of `self`. + pub fn iter(&self) -> impl Iterator> + '_ { + // SAFETY: list contains gpu_buddy_block items linked via __bindge= n_anon_1.link. + let clist =3D unsafe { + clist_create!( + self.list.as_raw(), + Block, + bindings::gpu_buddy_block, + __bindgen_anon_1.link + ) + }; + + clist + .iter() + .map(|block| AllocatedBlock { block, alloc: self }) + } +} + +#[pinned_drop] +impl PinnedDrop for AllocatedBlocks { + fn drop(self: Pin<&mut Self>) { + let guard =3D self.buddy.lock(); + + // SAFETY: + // - list is valid per the type's invariants. + // - guard provides exclusive access to the allocator. + // CAST: BuddyFlags were validated to fit in u32 at construction. + unsafe { + bindings::gpu_buddy_free_list( + guard.as_raw(), + self.list.as_raw(), + self.flags.as_raw() as u32, + ); + } + } +} + +/// A GPU buddy block. +/// +/// Transparent wrapper over C `gpu_buddy_block` structure. This type is r= eturned +/// as references from [`CListIter`] during iteration over [`AllocatedBloc= ks`]. +/// +/// # Invariants +/// +/// The inner [`Opaque`] contains a valid, allocated `gpu_buddy_block`. +#[repr(transparent)] +pub struct Block(Opaque); + +impl Block { + /// Get a raw pointer to the underlying C block. + fn as_raw(&self) -> *mut bindings::gpu_buddy_block { + self.0.get() + } + + /// Get the block's offset in the address space. + pub(crate) fn offset(&self) -> u64 { + // SAFETY: self.as_raw() is valid per the type's invariants. + unsafe { bindings::gpu_buddy_block_offset(self.as_raw()) } + } + + /// Get the block order. + pub(crate) fn order(&self) -> u32 { + // SAFETY: self.as_raw() is valid per the type's invariants. + unsafe { bindings::gpu_buddy_block_order(self.as_raw()) } + } +} + +// SAFETY: `Block` is a transparent wrapper over `gpu_buddy_block` which i= s not +// modified after allocation. It can be safely sent between threads. +unsafe impl Send for Block {} + +// SAFETY: `Block` is a transparent wrapper over `gpu_buddy_block` which i= s not +// modified after allocation. It can be safely shared among threads. +unsafe impl Sync for Block {} + +/// An allocated block with access to the allocation list. +/// +/// # Invariants +/// +/// - `block` is a valid reference to an allocated [`Block`]. +/// - `alloc` is a valid reference to the [`AllocatedBlocks`] that owns th= is block. +pub struct AllocatedBlock<'a> { + block: &'a Block, + alloc: &'a AllocatedBlocks, +} + +impl AllocatedBlock<'_> { + /// Get the block's offset in the address space. + /// + /// Returns the absolute offset including the allocator's base offset. + /// This is the actual address to use for accessing the allocated memo= ry. + pub fn offset(&self) -> u64 { + self.alloc.buddy.base_offset + self.block.offset() + } + + /// Get the block order (size =3D chunk_size << order). + pub fn order(&self) -> u32 { + self.block.order() + } + + /// Get the block's size in bytes. + pub fn size(&self) -> u64 { + self.alloc.buddy.chunk_size << self.block.order() + } +} diff --git a/rust/kernel/gpu/mod.rs b/rust/kernel/gpu/mod.rs new file mode 100644 index 000000000000..8f25e6367edc --- /dev/null +++ b/rust/kernel/gpu/mod.rs @@ -0,0 +1,5 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! GPU subsystem abstractions. + +pub mod buddy; diff --git a/rust/kernel/lib.rs b/rust/kernel/lib.rs index fe711d34ca1e..02ec5b9b22c8 100644 --- a/rust/kernel/lib.rs +++ b/rust/kernel/lib.rs @@ -98,6 +98,8 @@ pub mod firmware; pub mod fmt; pub mod fs; +#[cfg(CONFIG_GPU_BUDDY)] +pub mod gpu; #[cfg(CONFIG_I2C =3D "y")] pub mod i2c; pub mod id_pool; --=20 2.34.1