Received-SPF: pass (google.com: domain of linux-kernel+bounces-215521-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:45e3:2400::1 as permitted sender) client-ip=2604:1380:45e3:2400::1;
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=SATLEXMB04.amd.com; pr=C
From: Shivank Garg <shivankg@amd.com>
To: <akpm@linux-foundation.org>, <linux-kernel@vger.kernel.org>,
	<linux-mm@kvack.org>
CC: <bharata@amd.com>, <raghavendra.kodsarathimmappa@amd.com>,
	<Michael.Day@amd.com>, <dmaengine@vger.kernel.org>, <vkoul@kernel.org>,
	<shivankg@amd.com>
Subject: [RFC PATCH 5/5] dcbm: add dma core batch migrator for batch page offloading
Date: Sat, 15 Jun 2024 03:45:25 +0530
Message-ID: <20240614221525.19170-6-shivankg@amd.com>
In-Reply-To: <20240614221525.19170-1-shivankg@amd.com>
References: <20240614221525.19170-1-shivankg@amd.com>
Precedence: bulk
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Content-Type: text/plain
X-MS-Exchange-CrossTenant-OriginalArrivalTime: 14 Jun 2024 22:16:45.0967
 (UTC)
X-MS-Exchange-CrossTenant-Network-Message-Id: 6909e38f-cf95-487c-0505-08dc8cbfad5e
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=[SATLEXMB04.amd.com]
X-MS-Exchange-CrossTenant-AuthSource:
	DS1PEPF0001708E.namprd03.prod.outlook.com
X-MS-Exchange-CrossTenant-AuthAs: Anonymous
X-MS-Exchange-CrossTenant-FromEntityHeader: HybridOnPrem
X-MS-Exchange-Transport-CrossTenantHeadersStamped: MW4PR12MB5644

This commit is example code on how to leverage mm's migrate offload support
for offloading batch page migration. The dcbm (DMA core batch migrator)
provides a generic interface using DMAEngine for end-to-end testing of
the batch page migration offload feature. This facilitates testing and
validation of the functionality.

Enable DCBM offload: echo 1 > /sys/kernel/dcbm/offloading
Disable DCBM offload: echo 0 > /sys/kernel/dcbm/offloading

Signed-off-by: Shivank Garg <shivankg@amd.com>
---
 drivers/dma/Kconfig       |   2 +
 drivers/dma/Makefile      |   1 +
 drivers/dma/dcbm/Kconfig  |   7 ++
 drivers/dma/dcbm/Makefile |   1 +
 drivers/dma/dcbm/dcbm.c   | 229 ++++++++++++++++++++++++++++++++++++++
 5 files changed, 240 insertions(+)
 create mode 100644 drivers/dma/dcbm/Kconfig
 create mode 100644 drivers/dma/dcbm/Makefile
 create mode 100644 drivers/dma/dcbm/dcbm.c

diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index e928f2ca0f1e..376bd13d46f8 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -750,6 +750,8 @@ config XILINX_ZYNQMP_DPDMA
 # driver files
 source "drivers/dma/bestcomm/Kconfig"
 
+source "drivers/dma/dcbm/Kconfig"
+
 source "drivers/dma/mediatek/Kconfig"
 
 source "drivers/dma/ptdma/Kconfig"
diff --git a/drivers/dma/Makefile b/drivers/dma/Makefile
index dfd40d14e408..7d67fc29bce2 100644
--- a/drivers/dma/Makefile
+++ b/drivers/dma/Makefile
@@ -22,6 +22,7 @@ obj-$(CONFIG_AT_HDMAC) += at_hdmac.o
 obj-$(CONFIG_AT_XDMAC) += at_xdmac.o
 obj-$(CONFIG_AXI_DMAC) += dma-axi-dmac.o
 obj-$(CONFIG_BCM_SBA_RAID) += bcm-sba-raid.o
+obj-$(CONFIG_DCBM_DMA) += dcbm/
 obj-$(CONFIG_DMA_BCM2835) += bcm2835-dma.o
 obj-$(CONFIG_DMA_JZ4780) += dma-jz4780.o
 obj-$(CONFIG_DMA_SA11X0) += sa11x0-dma.o
diff --git a/drivers/dma/dcbm/Kconfig b/drivers/dma/dcbm/Kconfig
new file mode 100644
index 000000000000..e58eca03fb52
--- /dev/null
+++ b/drivers/dma/dcbm/Kconfig
@@ -0,0 +1,7 @@
+config DCBM_DMA
+	bool "DMA Core Batch Migrator"
+	depends on DMA_ENGINE
+	default n
+	help
+	  Interface driver for batch page migration offloading. Say Y
+	  if you want to try offloading with DMAEngine APIs.
diff --git a/drivers/dma/dcbm/Makefile b/drivers/dma/dcbm/Makefile
new file mode 100644
index 000000000000..56ba47cce0f1
--- /dev/null
+++ b/drivers/dma/dcbm/Makefile
@@ -0,0 +1 @@
+obj-$(CONFIG_DCBM_DMA) += dcbm.o
diff --git a/drivers/dma/dcbm/dcbm.c b/drivers/dma/dcbm/dcbm.c
new file mode 100644
index 000000000000..dac87fa55327
--- /dev/null
+++ b/drivers/dma/dcbm/dcbm.c
@@ -0,0 +1,229 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ *
+ * DMA batch-offlading interface driver
+ *
+ * Copyright (C) 2024 Advanced Micro Devices, Inc.
+ */
+
+/*
+ * This code exemplifies how to leverage mm layer's migration offload support
+ * for batch page offloading using DMA Engine APIs.
+ * Developers can use this template to write interface for custom hardware
+ * accelerators with specialized capabilities for batch page migration.
+ * This interface driver is end-to-end working and can be used for testing the
+ * patch series without special hardware given DMAEngine support is available.
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/printk.h>
+#include <linux/init.h>
+#include <linux/fs.h>
+#include <linux/device.h>
+#include <linux/sysfs.h>
+#include <linux/dma-mapping.h>
+#include <linux/dmaengine.h>
+#include <linux/migrate.h>
+#include <linux/migrate_dma.h>
+#include <linux/printk.h>
+#include <linux/sysfs.h>
+
+static struct dma_chan *chan;
+static int is_dispatching;
+
+static void folios_copy_dma(struct list_head *dst_list, struct list_head *src_list);
+static bool can_migrate_dma(struct folio *dst, struct folio *src);
+
+static DEFINE_MUTEX(migratecfg_mutex);
+
+/* DMA Core Batch Migrator */
+struct migrator dmigrator = {
+	.name = "DCBM\0",
+	.migrate_dma = folios_copy_dma,
+	.can_migrate_dma = can_migrate_dma,
+	.owner = THIS_MODULE,
+};
+
+static ssize_t offloading_set(struct kobject *kobj, struct kobj_attribute *attr,
+		const char *buf, size_t count)
+{
+	int ccode;
+	int action;
+	dma_cap_mask_t mask;
+
+	ccode = kstrtoint(buf, 0, &action);
+	if (ccode) {
+		pr_debug("(%s:) error parsing input %s\n", __func__, buf);
+		return ccode;
+	}
+
+	/*
+	 * action is 0: User wants to disable DMA offloading.
+	 * action is 1: User wants to enable DMA offloading.
+	 */
+	switch (action) {
+	case 0:
+		mutex_lock(&migratecfg_mutex);
+		if (is_dispatching == 1) {
+			stop_offloading();
+			dma_release_channel(chan);
+			is_dispatching = 0;
+		} else
+			pr_debug("migration offloading is already OFF\n");
+		mutex_unlock(&migratecfg_mutex);
+		break;
+	case 1:
+		mutex_lock(&migratecfg_mutex);
+		if (is_dispatching == 0) {
+			dma_cap_zero(mask);
+			dma_cap_set(DMA_MEMCPY, mask);
+			chan = dma_request_channel(mask, NULL, NULL);
+			if (!chan) {
+				chan = ERR_PTR(-ENODEV);
+				pr_err("Error requesting DMA channel\n");
+				mutex_unlock(&migratecfg_mutex);
+				return -ENODEV;
+			}
+			start_offloading(&dmigrator);
+			is_dispatching = 1;
+		} else
+			pr_debug("migration offloading is already ON\n");
+		mutex_unlock(&migratecfg_mutex);
+		break;
+	default:
+		pr_debug("input should be zero or one, parsed as %d\n", action);
+	}
+	return sizeof(action);
+}
+
+static ssize_t offloading_show(struct kobject *kobj,
+		struct kobj_attribute *attr, char *buf)
+{
+	return sysfs_emit(buf, "%d\n", is_dispatching);
+}
+
+static bool can_migrate_dma(struct folio *dst, struct folio *src)
+{
+	if (folio_test_hugetlb(src) || folio_test_hugetlb(dst) ||
+			folio_has_private(src) || folio_has_private(dst) ||
+			(folio_nr_pages(src) != folio_nr_pages(dst)) ||
+			folio_nr_pages(src) != 1)
+		return false;
+	return true;
+}
+
+static void folios_copy_dma(struct list_head *dst_list,
+		struct list_head *src_list)
+{
+	int ret = 0;
+	struct folio *src, *dst;
+	struct dma_device *dev;
+	struct device *dma_dev;
+	static dma_cookie_t cookie;
+	struct dma_async_tx_descriptor *tx;
+	enum dma_status status;
+	enum dma_ctrl_flags flags = DMA_CTRL_ACK;
+	dma_addr_t srcdma_handle;
+	dma_addr_t dstdma_handle;
+
+
+	if (!chan) {
+		pr_err("error chan uninitialized\n");
+		goto fail;
+	}
+	dev = chan->device;
+	if (!dev) {
+		pr_err("error dev is NULL\n");
+		goto fail;
+	}
+	dma_dev = dmaengine_get_dma_device(chan);
+	if (!dma_dev) {
+		pr_err("error dma_dev is NULL\n");
+		goto fail;
+	}
+	dst = list_first_entry(dst_list, struct folio, lru);
+	list_for_each_entry(src, src_list, lru) {
+		srcdma_handle = dma_map_page(dma_dev, &src->page, 0, 4096, DMA_BIDIRECTIONAL);
+		ret = dma_mapping_error(dma_dev, srcdma_handle);
+		if (ret) {
+			pr_err("src mapping error\n");
+			goto fail1;
+		}
+		dstdma_handle = dma_map_page(dma_dev, &dst->page, 0, 4096, DMA_BIDIRECTIONAL);
+		ret = dma_mapping_error(dma_dev, dstdma_handle);
+		if (ret) {
+			pr_err("dst mapping error\n");
+			goto fail2;
+		}
+		tx = dev->device_prep_dma_memcpy(chan, dstdma_handle, srcdma_handle, 4096, flags);
+		if (!tx) {
+			ret = -EBUSY;
+			pr_err("prep_dma_error\n");
+			goto fail3;
+		}
+		cookie = tx->tx_submit(tx);
+		if (dma_submit_error(cookie)) {
+			ret = -EINVAL;
+			pr_err("dma_submit_error\n");
+			goto fail3;
+		}
+		status = dma_sync_wait(chan, cookie);
+		dmaengine_terminate_sync(chan);
+		if (status != DMA_COMPLETE) {
+			ret = -EINVAL;
+			pr_err("error while dma wait\n");
+			goto fail3;
+		}
+fail3:
+		dma_unmap_page(dma_dev, dstdma_handle, 4096, DMA_BIDIRECTIONAL);
+fail2:
+		dma_unmap_page(dma_dev, srcdma_handle, 4096, DMA_BIDIRECTIONAL);
+fail1:
+		if (ret)
+			folio_copy(dst, src);
+
+		dst = list_next_entry(dst, lru);
+	}
+fail:
+	folios_copy(dst_list, src_list);
+}
+
+static struct kobject *kobj_ref;
+static struct kobj_attribute offloading_attribute = __ATTR(offloading, 0664,
+		offloading_show, offloading_set);
+
+static int __init dma_module_init(void)
+{
+	int ret = 0;
+
+	kobj_ref = kobject_create_and_add("dcbm", kernel_kobj);
+	if (!kobj_ref)
+		return -ENOMEM;
+
+	ret = sysfs_create_file(kobj_ref, &offloading_attribute.attr);
+	if (ret)
+		goto out;
+
+	is_dispatching = 0;
+
+	return 0;
+out:
+	kobject_put(kobj_ref);
+	return ret;
+}
+
+static void __exit dma_module_exit(void)
+{
+	/* Stop the DMA offloading to unload the module */
+
+	//sysfs_remove_file(kobj, &offloading_show.attr);
+	kobject_put(kobj_ref);
+}
+
+module_init(dma_module_init);
+module_exit(dma_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Shivank Garg");
+MODULE_DESCRIPTION("DCBM"); /* DMA Core Batch Migrator */
-- 
2.34.1