From nobody Thu Apr 2 17:16:01 2026 Received: from MW6PR02CU001.outbound.protection.outlook.com (mail-westus2azon11012022.outbound.protection.outlook.com [52.101.48.22]) (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 BC1CB3A63FD for ; Mon, 9 Mar 2026 12:12:00 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=fail smtp.client-ip=52.101.48.22 ARC-Seal: i=2; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1773058322; cv=fail; b=i7UJTU4fwhZqG6oOwy5RwCTGzWlUaUHqt926DvTFqW4njotW/jy7//XtcmbRL5FfISd4g599hXg84TnhioejTC7s0aahBP7WCrFKSagg//RJyoEgzDK1SeO3YSHDCO6vimQDMc9eT0Pw+XFvcvVli20/bnDeLHWKxoiSEGHu2eE= ARC-Message-Signature: i=2; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1773058322; c=relaxed/simple; bh=YQQTereXG3UfBtjQ+yRqAcMlLA8Bmpbxu9mdAvGcYVA=; h=From:To:CC:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version:Content-Type; b=KjaVgwaM1XqAPLPGSAN44eaQ+HPd51/67DST37teqaTGQgwfdj1NZqYmHWSgvsyTKJNX9V51udpliafJxrTZy8lDrVDlMn6g+gxAa/HXndk9C9LiXbtiEsBsVSX7b2BkBV/njSKWtt1eXmMYF3IiFralpv9HMq0suwjOlEMEdiY= 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=eyVneOux; arc=fail smtp.client-ip=52.101.48.22 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="eyVneOux" ARC-Seal: i=1; a=rsa-sha256; s=arcselector10001; d=microsoft.com; cv=none; b=ZHDH+WkgPz9bC7zjQirkLqnIQnR3AuYLYpQMYLCcKouYo77PEP3anaMG3gBuf/JY+DXsa5Svs4X48Cn+biMqwsfSJBNhA5ydgiDlSWiRGEYCZV/EjXqSIZBr/2QFw1VYYyQUa3D8hUI9RbfrQ3yU9kkb1v3k/q1AzZdNk+Vh02qowYhyEYYVFDkYTzdkznuaXWMl4qh1rRFTTI/+bIFGg7aefrdk2W6cEaqA5X4gfFbmf/4u2nrT+qAhdMjJwVW2hdBC46+Juwc/Iug01h7eyyNSWPERjWDBPq4kfvuX2CbQDveaxGWvy48icz8yim/xbQo6CNtxYRpSUdr85pn4iQ== 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=anzeTeLieTQNE724hLeCdyNgyUWdCBnBwzbDi1FBssI=; b=C+xX69SnXoGSM0gCo/YrPIQ38ibNAQNqBA7mIgUBRTJwVdtnlDVX01YgcNEIKJ/7vhOJpjCeDezHx7o7AcON1MsGYU4butH13ggbkRnwMA04N8kIS1fscx2TxpLEOgm21uUjdHT505GJ17gfzzf5ON9rMFQq8uA6PulxdA+0mESUm+Xv/8lsxjgegBdtwLPoLf0n+PXrTwyOVdvi07pBJpINDiZ98L/fA1zFyxL+Kb5nXf/93qlAnZEFcaoaOPz5AjbUwyTHAiy7mnhyMZRebmsXnGyN97W5/XRu+yvf3IP/26BuD2B0AtuCalQ0/Ojgflyqw3GRlxZ7ox4+GwbXsQ== ARC-Authentication-Results: i=1; mx.microsoft.com 1; spf=pass (sender ip is 165.204.84.17) smtp.rcpttodomain=linux-foundation.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=anzeTeLieTQNE724hLeCdyNgyUWdCBnBwzbDi1FBssI=; b=eyVneOux+A+OJJOONRu/ym2sP7K3zStgs7gNLj77i7LTSo/mg29UqwQY+8IH2gnl9a33ZBqONLJN6uJ2GAFICkZp7UHAfI7Ljs69lmasHeJoeVDSmmKgJPx02UcdLqytIy2p7G8QMMxgQZiJ/pmqiNxyilTBh0B+6XLKzfHiQbU= Received: from CH0PR03CA0320.namprd03.prod.outlook.com (2603:10b6:610:118::25) by DM4PR12MB7744.namprd12.prod.outlook.com (2603:10b6:8:100::14) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id 15.20.9700.11; Mon, 9 Mar 2026 12:11:54 +0000 Received: from CH3PEPF0000000B.namprd04.prod.outlook.com (2603:10b6:610:118:cafe::d5) by CH0PR03CA0320.outlook.office365.com (2603:10b6:610:118::25) with Microsoft SMTP Server (version=TLS1_3, cipher=TLS_AES_256_GCM_SHA384) id 15.20.9678.25 via Frontend Transport; Mon, 9 Mar 2026 12:11:54 +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=satlexmb07.amd.com; pr=C Received: from satlexmb07.amd.com (165.204.84.17) by CH3PEPF0000000B.mail.protection.outlook.com (10.167.244.38) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id 15.20.9678.18 via Frontend Transport; Mon, 9 Mar 2026 12:11:54 +0000 Received: from satlexmb10.amd.com (10.181.42.219) by satlexmb07.amd.com (10.181.42.216) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id 15.2.2562.17; Mon, 9 Mar 2026 07:11:54 -0500 Received: from kaveri.amd.com (10.180.168.240) by satlexmb10.amd.com (10.181.42.219) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id 15.2.2562.17; Mon, 9 Mar 2026 07:11:43 -0500 From: Shivank Garg To: , CC: , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , Shivank Garg Subject: [RFC PATCH v4 5/6] drivers/migrate_offload: add DMA batch copy driver (dcbm) Date: Mon, 9 Mar 2026 12:07:31 +0000 Message-ID: <20260309120725.308854-14-shivankg@amd.com> X-Mailer: git-send-email 2.43.0 In-Reply-To: <20260309120725.308854-3-shivankg@amd.com> References: <20260309120725.308854-3-shivankg@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-ClientProxiedBy: satlexmb07.amd.com (10.181.42.216) To satlexmb10.amd.com (10.181.42.219) X-EOPAttributedMessage: 0 X-MS-PublicTrafficType: Email X-MS-TrafficTypeDiagnostic: CH3PEPF0000000B:EE_|DM4PR12MB7744:EE_ X-MS-Office365-Filtering-Correlation-Id: 644dac95-d683-4618-bf05-08de7dd50dcd X-MS-Exchange-SenderADCheck: 1 X-MS-Exchange-AntiSpam-Relay: 0 X-Microsoft-Antispam: BCL:0;ARA:13230040|36860700016|1800799024|7416014|376014|82310400026; X-Microsoft-Antispam-Message-Info: 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 X-Forefront-Antispam-Report: CIP:165.204.84.17;CTRY:US;LANG:en;SCL:1;SRV:;IPV:NLI;SFV:NSPM;H:satlexmb07.amd.com;PTR:InfoDomainNonexistent;CAT:NONE;SFS:(13230040)(36860700016)(1800799024)(7416014)(376014)(82310400026);DIR:OUT;SFP:1101; X-MS-Exchange-AntiSpam-MessageData-ChunkCount: 1 X-MS-Exchange-AntiSpam-MessageData-0: rZN+7itx5mdCyLfki9kYUkMqalAkpwYOhWyEBVq3I+w4fnBso8vPLW0EYujz0S1ws2VtAfk/xIezrb1WphXQImPUtWyDTeVrbPEs1Tu2JRP7T2I3FyfPlI+qg2+K9oZvDFWf64t7ZlcTseO5oFCQVV+vT3PCqZMWwUXEEhUXjGPPV+dVhVBHCNMgc3xNdhAVOs9v31Lm5YbxrzDJOsSC0Sec4qzg8QgVj0EHzUTA2Cx6xp2zdSowL8cK17iluib26SdoOQmVp5XQNQPjHbiNM4B9CMmLVxZvm3pCvvfGFe6GiaSOtub5BZrsowP2zmQEbdQRcDufG/F/yI1lYsCFNzrB/o0Ki9qopUCAA/fCN3EpeoZZqtt1w77gjT9HO/TXV9oPNOaiZQYsyzEivjSxIhu322eJv7CAGqLB0tNZz/dIL0qqe5bY9dG7ur041hHy X-OriginatorOrg: amd.com X-MS-Exchange-CrossTenant-OriginalArrivalTime: 09 Mar 2026 12:11:54.5757 (UTC) X-MS-Exchange-CrossTenant-Network-Message-Id: 644dac95-d683-4618-bf05-08de7dd50dcd 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=[satlexmb07.amd.com] X-MS-Exchange-CrossTenant-AuthSource: CH3PEPF0000000B.namprd04.prod.outlook.com X-MS-Exchange-CrossTenant-AuthAs: Anonymous X-MS-Exchange-CrossTenant-FromEntityHeader: HybridOnPrem X-MS-Exchange-Transport-CrossTenantHeadersStamped: DM4PR12MB7744 Content-Type: text/plain; charset="utf-8" Simple DMAEngine based driver that uses memcpy channels to batch-copy folios during page migration. Primarily for testing the copy offload infrastructure. When DMA fails the callback returns an error and the migration path falls back to per-folio CPU copy. Sysfs interface under /sys/kernel/dcbm/: offloading - enable/disable DMA offload nr_dma_chan - max number of DMA channels to use folios_migrated - folios copied via DMA folios_failures - fallback count Signed-off-by: Shivank Garg --- drivers/Kconfig | 2 + drivers/Makefile | 2 + drivers/migrate_offload/Kconfig | 8 + drivers/migrate_offload/Makefile | 1 + drivers/migrate_offload/dcbm/Makefile | 1 + drivers/migrate_offload/dcbm/dcbm.c | 457 ++++++++++++++++++++++++++ 6 files changed, 471 insertions(+) create mode 100644 drivers/migrate_offload/Kconfig create mode 100644 drivers/migrate_offload/Makefile create mode 100644 drivers/migrate_offload/dcbm/Makefile create mode 100644 drivers/migrate_offload/dcbm/dcbm.c diff --git a/drivers/Kconfig b/drivers/Kconfig index c0f1fb893ec0..3dbea1380603 100644 --- a/drivers/Kconfig +++ b/drivers/Kconfig @@ -255,4 +255,6 @@ source "drivers/cdx/Kconfig" =20 source "drivers/resctrl/Kconfig" =20 +source "drivers/migrate_offload/Kconfig" + endmenu diff --git a/drivers/Makefile b/drivers/Makefile index 53fbd2e0acdd..f55bddf490cc 100644 --- a/drivers/Makefile +++ b/drivers/Makefile @@ -42,6 +42,8 @@ obj-y +=3D clk/ # really early. obj-$(CONFIG_DMADEVICES) +=3D dma/ =20 +obj-$(CONFIG_MIGRATION_COPY_OFFLOAD) +=3D migrate_offload/ + # SOC specific infrastructure drivers. obj-y +=3D soc/ obj-$(CONFIG_PM_GENERIC_DOMAINS) +=3D pmdomain/ diff --git a/drivers/migrate_offload/Kconfig b/drivers/migrate_offload/Kcon= fig new file mode 100644 index 000000000000..0bbaedbae4ad --- /dev/null +++ b/drivers/migrate_offload/Kconfig @@ -0,0 +1,8 @@ +config DCBM_DMA + bool "DMA Core Batch Migrator" + depends on MIGRATION_COPY_OFFLOAD && DMA_ENGINE + help + DMA-based batch copy engine for page migration. Uses + DMAEngine memcpy channels to offload folio data copies + during migration. Primarily intended for testing the copy + offload infrastructure. diff --git a/drivers/migrate_offload/Makefile b/drivers/migrate_offload/Mak= efile new file mode 100644 index 000000000000..9e16018beb15 --- /dev/null +++ b/drivers/migrate_offload/Makefile @@ -0,0 +1 @@ +obj-$(CONFIG_DCBM_DMA) +=3D dcbm/ diff --git a/drivers/migrate_offload/dcbm/Makefile b/drivers/migrate_offloa= d/dcbm/Makefile new file mode 100644 index 000000000000..56ba47cce0f1 --- /dev/null +++ b/drivers/migrate_offload/dcbm/Makefile @@ -0,0 +1 @@ +obj-$(CONFIG_DCBM_DMA) +=3D dcbm.o diff --git a/drivers/migrate_offload/dcbm/dcbm.c b/drivers/migrate_offload/= dcbm/dcbm.c new file mode 100644 index 000000000000..89751d03101e --- /dev/null +++ b/drivers/migrate_offload/dcbm/dcbm.c @@ -0,0 +1,457 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * DMA Core Batch Migrator (DCBM) + * + * Uses DMAEngine memcpy channels to offload batch folio copies during + * page migration. Reference driver meant for testing the offload + * infrastructure. + * + * Copyright (C) 2024-26 Advanced Micro Devices, Inc. + */ + +#include +#include +#include +#include +#include + +#define MAX_DMA_CHANNELS 16 + +static unsigned long long folios_migrated; +static unsigned long long folios_failures; + +static bool offloading_enabled; +static unsigned int nr_dma_channels =3D 1; +static DEFINE_MUTEX(dcbm_mutex); + +struct dma_work { + struct dma_chan *chan; + struct completion done; + atomic_t pending; + struct sg_table *src_sgt; + struct sg_table *dst_sgt; + bool mapped; +}; + +static void dma_completion_callback(void *data) +{ + struct dma_work *work =3D data; + + if (atomic_dec_and_test(&work->pending)) + complete(&work->done); +} + +static int setup_sg_tables(struct dma_work *work, struct list_head **src_p= os, + struct list_head **dst_pos, int nr) +{ + struct scatterlist *sg_src, *sg_dst; + struct device *dev; + int i, ret; + + work->src_sgt =3D kmalloc_obj(*work->src_sgt, GFP_KERNEL); + if (!work->src_sgt) + return -ENOMEM; + work->dst_sgt =3D kmalloc_obj(*work->dst_sgt, GFP_KERNEL); + if (!work->dst_sgt) + goto err_free_src; + + ret =3D sg_alloc_table(work->src_sgt, nr, GFP_KERNEL); + if (ret) + goto err_free_dst; + ret =3D sg_alloc_table(work->dst_sgt, nr, GFP_KERNEL); + if (ret) + goto err_free_src_table; + + sg_src =3D work->src_sgt->sgl; + sg_dst =3D work->dst_sgt->sgl; + for (i =3D 0; i < nr; i++) { + struct folio *src =3D list_entry(*src_pos, struct folio, lru); + struct folio *dst =3D list_entry(*dst_pos, struct folio, lru); + + sg_set_folio(sg_src, src, folio_size(src), 0); + sg_set_folio(sg_dst, dst, folio_size(dst), 0); + + *src_pos =3D (*src_pos)->next; + *dst_pos =3D (*dst_pos)->next; + + if (i < nr - 1) { + sg_src =3D sg_next(sg_src); + sg_dst =3D sg_next(sg_dst); + } + } + + dev =3D dmaengine_get_dma_device(work->chan); + if (!dev) { + ret =3D -ENODEV; + goto err_free_dst_table; + } + ret =3D dma_map_sgtable(dev, work->src_sgt, DMA_TO_DEVICE, + DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_NO_KERNEL_MAPPING); + if (ret) + goto err_free_dst_table; + ret =3D dma_map_sgtable(dev, work->dst_sgt, DMA_FROM_DEVICE, + DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_NO_KERNEL_MAPPING); + if (ret) + goto err_unmap_src; + + if (work->src_sgt->nents !=3D work->dst_sgt->nents) { + ret =3D -EINVAL; + goto err_unmap_dst; + } + work->mapped =3D true; + return 0; + +err_unmap_dst: + dma_unmap_sgtable(dev, work->dst_sgt, DMA_FROM_DEVICE, + DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_NO_KERNEL_MAPPING); +err_unmap_src: + dma_unmap_sgtable(dev, work->src_sgt, DMA_TO_DEVICE, + DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_NO_KERNEL_MAPPING); +err_free_dst_table: + sg_free_table(work->dst_sgt); +err_free_src_table: + sg_free_table(work->src_sgt); +err_free_dst: + kfree(work->dst_sgt); + work->dst_sgt =3D NULL; +err_free_src: + kfree(work->src_sgt); + work->src_sgt =3D NULL; + return ret; +} + +static void cleanup_dma_work(struct dma_work *works, int actual_channels) +{ + struct device *dev; + int i; + + if (!works) + return; + + for (i =3D 0; i < actual_channels; i++) { + if (!works[i].chan) + continue; + + dev =3D dmaengine_get_dma_device(works[i].chan); + + if (works[i].mapped) + dmaengine_terminate_sync(works[i].chan); + + if (dev && works[i].mapped) { + if (works[i].src_sgt) { + dma_unmap_sgtable(dev, works[i].src_sgt, + DMA_TO_DEVICE, + DMA_ATTR_SKIP_CPU_SYNC | + DMA_ATTR_NO_KERNEL_MAPPING); + sg_free_table(works[i].src_sgt); + kfree(works[i].src_sgt); + } + if (works[i].dst_sgt) { + dma_unmap_sgtable(dev, works[i].dst_sgt, + DMA_FROM_DEVICE, + DMA_ATTR_SKIP_CPU_SYNC | + DMA_ATTR_NO_KERNEL_MAPPING); + sg_free_table(works[i].dst_sgt); + kfree(works[i].dst_sgt); + } + } + dma_release_channel(works[i].chan); + } + kfree(works); +} + +static int submit_dma_transfers(struct dma_work *work) +{ + struct scatterlist *sg_src, *sg_dst; + struct dma_async_tx_descriptor *tx; + unsigned long flags =3D DMA_CTRL_ACK; + dma_cookie_t cookie; + int i; + + atomic_set(&work->pending, 1); + + sg_src =3D work->src_sgt->sgl; + sg_dst =3D work->dst_sgt->sgl; + for_each_sgtable_dma_sg(work->src_sgt, sg_src, i) { + if (i =3D=3D work->src_sgt->nents - 1) + flags |=3D DMA_PREP_INTERRUPT; + + tx =3D dmaengine_prep_dma_memcpy(work->chan, + sg_dma_address(sg_dst), + sg_dma_address(sg_src), + sg_dma_len(sg_src), flags); + if (!tx) { + atomic_set(&work->pending, 0); + return -EIO; + } + + if (i =3D=3D work->src_sgt->nents - 1) { + tx->callback =3D dma_completion_callback; + tx->callback_param =3D work; + } + + cookie =3D dmaengine_submit(tx); + if (dma_submit_error(cookie)) { + atomic_set(&work->pending, 0); + return -EIO; + } + sg_dst =3D sg_next(sg_dst); + } + return 0; +} + +/** + * folios_copy_dma - copy a batch of folios via DMA memcpy + * @dst_list: destination folio list + * @src_list: source folio list + * @nr_folios: number of folios in each list + * + * Return: 0 on success, negative errno on failure. + */ +static int folios_copy_dma(struct list_head *dst_list, + struct list_head *src_list, unsigned int nr_folios) +{ + struct dma_work *works; + struct list_head *src_pos =3D src_list->next; + struct list_head *dst_pos =3D dst_list->next; + int i, folios_per_chan, ret; + dma_cap_mask_t mask; + int actual_channels =3D 0; + unsigned int max_channels; + + max_channels =3D min3(nr_dma_channels, nr_folios, + (unsigned int)MAX_DMA_CHANNELS); + + works =3D kcalloc(max_channels, sizeof(*works), GFP_KERNEL); + if (!works) + return -ENOMEM; + + dma_cap_zero(mask); + dma_cap_set(DMA_MEMCPY, mask); + + for (i =3D 0; i < max_channels; i++) { + works[actual_channels].chan =3D dma_request_chan_by_mask(&mask); + if (IS_ERR(works[actual_channels].chan)) + break; + init_completion(&works[actual_channels].done); + actual_channels++; + } + + if (actual_channels =3D=3D 0) { + kfree(works); + return -ENODEV; + } + + for (i =3D 0; i < actual_channels; i++) { + folios_per_chan =3D nr_folios * (i + 1) / actual_channels - + (nr_folios * i) / actual_channels; + if (folios_per_chan =3D=3D 0) + continue; + + ret =3D setup_sg_tables(&works[i], &src_pos, &dst_pos, + folios_per_chan); + if (ret) + goto err_cleanup; + } + + for (i =3D 0; i < actual_channels; i++) { + ret =3D submit_dma_transfers(&works[i]); + if (ret) + goto err_cleanup; + } + + for (i =3D 0; i < actual_channels; i++) { + if (atomic_read(&works[i].pending) > 0) + dma_async_issue_pending(works[i].chan); + } + + for (i =3D 0; i < actual_channels; i++) { + if (atomic_read(&works[i].pending) =3D=3D 0) + continue; + if (!wait_for_completion_timeout(&works[i].done, + msecs_to_jiffies(10000))) { + ret =3D -ETIMEDOUT; + goto err_cleanup; + } + } + + cleanup_dma_work(works, actual_channels); + + mutex_lock(&dcbm_mutex); + folios_migrated +=3D nr_folios; + mutex_unlock(&dcbm_mutex); + return 0; + +err_cleanup: + pr_warn_ratelimited("dcbm: DMA copy failed (%d), falling back to CPU\n", + ret); + cleanup_dma_work(works, actual_channels); + + mutex_lock(&dcbm_mutex); + folios_failures +=3D nr_folios; + mutex_unlock(&dcbm_mutex); + return ret; +} + +/* TODO: tune based on usecase */ +static bool dma_should_batch(int reason) +{ + if (reason =3D=3D MR_SYSCALL || reason =3D=3D MR_COMPACTION || reason =3D= =3D MR_DEMOTION || + reason =3D=3D MR_NUMA_MISPLACED) + return true; + return false; +} + +static struct migrator dma_migrator =3D { + .name =3D "DCBM", + .offload_copy =3D folios_copy_dma, + .should_batch =3D dma_should_batch, + .owner =3D THIS_MODULE, +}; + +static ssize_t offloading_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sysfs_emit(buf, "%d\n", offloading_enabled); +} + +static ssize_t offloading_store(struct kobject *kobj, + struct kobj_attribute *attr, const char *buf, size_t count) +{ + bool enable; + int ret; + + ret =3D kstrtobool(buf, &enable); + if (ret) + return ret; + + mutex_lock(&dcbm_mutex); + + if (enable =3D=3D offloading_enabled) + goto out; + + if (enable) { + ret =3D migrate_offload_start(&dma_migrator); + if (ret) { + mutex_unlock(&dcbm_mutex); + return ret; + } + offloading_enabled =3D true; + } else { + migrate_offload_stop(&dma_migrator); + offloading_enabled =3D false; + } +out: + mutex_unlock(&dcbm_mutex); + return count; +} + +static ssize_t folios_migrated_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sysfs_emit(buf, "%llu\n", folios_migrated); +} + +static ssize_t folios_migrated_store(struct kobject *kobj, + struct kobj_attribute *attr, const char *buf, size_t count) +{ + mutex_lock(&dcbm_mutex); + folios_migrated =3D 0; + mutex_unlock(&dcbm_mutex); + return count; +} + +static ssize_t folios_failures_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sysfs_emit(buf, "%llu\n", folios_failures); +} + +static ssize_t folios_failures_store(struct kobject *kobj, + struct kobj_attribute *attr, const char *buf, size_t count) +{ + mutex_lock(&dcbm_mutex); + folios_failures =3D 0; + mutex_unlock(&dcbm_mutex); + return count; +} + +static ssize_t nr_dma_chan_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sysfs_emit(buf, "%u\n", nr_dma_channels); +} + +static ssize_t nr_dma_chan_store(struct kobject *kobj, + struct kobj_attribute *attr, const char *buf, size_t count) +{ + unsigned int val; + int ret; + + ret =3D kstrtouint(buf, 0, &val); + if (ret) + return ret; + + if (val < 1 || val > MAX_DMA_CHANNELS) + return -EINVAL; + + mutex_lock(&dcbm_mutex); + nr_dma_channels =3D val; + mutex_unlock(&dcbm_mutex); + return count; +} + +static struct kobj_attribute offloading_attr =3D __ATTR_RW(offloading); +static struct kobj_attribute nr_dma_chan_attr =3D __ATTR_RW(nr_dma_chan); +static struct kobj_attribute folios_migrated_attr =3D __ATTR_RW(folios_mig= rated); +static struct kobj_attribute folios_failures_attr =3D __ATTR_RW(folios_fai= lures); + +static struct attribute *dcbm_attrs[] =3D { + &offloading_attr.attr, + &nr_dma_chan_attr.attr, + &folios_migrated_attr.attr, + &folios_failures_attr.attr, + NULL +}; +ATTRIBUTE_GROUPS(dcbm); + +static struct kobject *dcbm_kobj; + +static int __init dcbm_init(void) +{ + int ret; + + dcbm_kobj =3D kobject_create_and_add("dcbm", kernel_kobj); + if (!dcbm_kobj) + return -ENOMEM; + + ret =3D sysfs_create_groups(dcbm_kobj, dcbm_groups); + if (ret) { + kobject_put(dcbm_kobj); + return ret; + } + + pr_info("dcbm: DMA Core Batch Migrator initialized\n"); + return 0; +} + +static void __exit dcbm_exit(void) +{ + mutex_lock(&dcbm_mutex); + if (offloading_enabled) { + migrate_offload_stop(&dma_migrator); + offloading_enabled =3D false; + } + mutex_unlock(&dcbm_mutex); + + sysfs_remove_groups(dcbm_kobj, dcbm_groups); + kobject_put(dcbm_kobj); + pr_info("dcbm: DMA Core Batch Migrator unloaded\n"); +} + +module_init(dcbm_init); +module_exit(dcbm_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Shivank Garg"); +MODULE_DESCRIPTION("DMA Core Batch Migrator"); --=20 2.43.0