Received-SPF: pass (google.com: domain of linux-ext4-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
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:   Alex Sierra <alex.sierra@amd.com>
To:     <jgg@nvidia.com>
CC:     <david@redhat.com>, <Felix.Kuehling@amd.com>, <linux-mm@kvack.org>,
        <rcampbell@nvidia.com>, <linux-ext4@vger.kernel.org>,
        <linux-xfs@vger.kernel.org>, <amd-gfx@lists.freedesktop.org>,
        <dri-devel@lists.freedesktop.org>, <hch@lst.de>,
        <jglisse@redhat.com>, <apopple@nvidia.com>, <willy@infradead.org>,
        <akpm@linux-foundation.org>
Subject: [PATCH v8 10/15] lib: test_hmm add module param for zone device type
Date:   Thu, 7 Jul 2022 14:03:44 -0500
Message-ID: <20220707190349.9778-11-alex.sierra@amd.com>
In-Reply-To: <20220707190349.9778-1-alex.sierra@amd.com>
References: <20220707190349.9778-1-alex.sierra@amd.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Content-Type: text/plain
X-MS-Exchange-CrossTenant-OriginalArrivalTime: 07 Jul 2022 19:04:17.9964
 (UTC)
X-MS-Exchange-CrossTenant-Network-Message-Id: 4a65340c-4aa1-4fb9-a64d-08da604b7e1b
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: BN8NAM11FT012.eop-nam11.prod.protection.outlook.com
X-MS-Exchange-CrossTenant-AuthAs: Anonymous
X-MS-Exchange-CrossTenant-FromEntityHeader: HybridOnPrem
X-MS-Exchange-Transport-CrossTenantHeadersStamped: MWHPR12MB1694
X-Spam-Status: No, score=-2.1 required=5.0 tests=BAYES_00,DKIM_SIGNED,
        DKIM_VALID,DKIM_VALID_AU,DKIM_VALID_EF,RCVD_IN_DNSWL_NONE,
        RCVD_IN_MSPIKE_H2,SPF_HELO_PASS,SPF_PASS,T_SCC_BODY_TEXT_LINE
        autolearn=ham autolearn_force=no version=3.4.6
X-Spam-Checker-Version: SpamAssassin 3.4.6 (2021-04-09) on
        lindbergh.monkeyblade.net
Precedence: bulk
List-ID: <linux-ext4.vger.kernel.org>
X-Mailing-List: linux-ext4@vger.kernel.org

In order to configure device coherent in test_hmm, two module parameters
should be passed, which correspond to the SP start address of each
device (2) spm_addr_dev0 & spm_addr_dev1. If no parameters are passed,
private device type is configured.

Signed-off-by: Alex Sierra <alex.sierra@amd.com>
Acked-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Alistair Poppple <apopple@nvidia.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 lib/test_hmm.c      | 73 ++++++++++++++++++++++++++++++++-------------
 lib/test_hmm_uapi.h |  1 +
 2 files changed, 53 insertions(+), 21 deletions(-)

diff --git a/lib/test_hmm.c b/lib/test_hmm.c
index 915ef6b5b0d4..afb30af9f3ff 100644
--- a/lib/test_hmm.c
+++ b/lib/test_hmm.c
@@ -37,6 +37,16 @@
 #define DEVMEM_CHUNK_SIZE		(256 * 1024 * 1024U)
 #define DEVMEM_CHUNKS_RESERVE		16
 
+static unsigned long spm_addr_dev0;
+module_param(spm_addr_dev0, long, 0644);
+MODULE_PARM_DESC(spm_addr_dev0,
+		"Specify start address for SPM (special purpose memory) used for device 0. By setting this Coherent device type will be used. Make sure spm_addr_dev1 is set too. Minimum SPM size should be DEVMEM_CHUNK_SIZE.");
+
+static unsigned long spm_addr_dev1;
+module_param(spm_addr_dev1, long, 0644);
+MODULE_PARM_DESC(spm_addr_dev1,
+		"Specify start address for SPM (special purpose memory) used for device 1. By setting this Coherent device type will be used. Make sure spm_addr_dev0 is set too. Minimum SPM size should be DEVMEM_CHUNK_SIZE.");
+
 static const struct dev_pagemap_ops dmirror_devmem_ops;
 static const struct mmu_interval_notifier_ops dmirror_min_ops;
 static dev_t dmirror_dev;
@@ -455,28 +465,44 @@ static int dmirror_write(struct dmirror *dmirror, struct hmm_dmirror_cmd *cmd)
 	return ret;
 }
 
-static bool dmirror_allocate_chunk(struct dmirror_device *mdevice,
+static int dmirror_allocate_chunk(struct dmirror_device *mdevice,
 				   struct page **ppage)
 {
 	struct dmirror_chunk *devmem;
-	struct resource *res;
+	struct resource *res = NULL;
 	unsigned long pfn;
 	unsigned long pfn_first;
 	unsigned long pfn_last;
 	void *ptr;
+	int ret = -ENOMEM;
 
 	devmem = kzalloc(sizeof(*devmem), GFP_KERNEL);
 	if (!devmem)
-		return false;
+		return ret;
 
-	res = request_free_mem_region(&iomem_resource, DEVMEM_CHUNK_SIZE,
-				      "hmm_dmirror");
-	if (IS_ERR(res))
+	switch (mdevice->zone_device_type) {
+	case HMM_DMIRROR_MEMORY_DEVICE_PRIVATE:
+		res = request_free_mem_region(&iomem_resource, DEVMEM_CHUNK_SIZE,
+					      "hmm_dmirror");
+		if (IS_ERR_OR_NULL(res))
+			goto err_devmem;
+		devmem->pagemap.range.start = res->start;
+		devmem->pagemap.range.end = res->end;
+		devmem->pagemap.type = MEMORY_DEVICE_PRIVATE;
+		break;
+	case HMM_DMIRROR_MEMORY_DEVICE_COHERENT:
+		devmem->pagemap.range.start = (MINOR(mdevice->cdevice.dev) - 2) ?
+							spm_addr_dev0 :
+							spm_addr_dev1;
+		devmem->pagemap.range.end = devmem->pagemap.range.start +
+					    DEVMEM_CHUNK_SIZE - 1;
+		devmem->pagemap.type = MEMORY_DEVICE_COHERENT;
+		break;
+	default:
+		ret = -EINVAL;
 		goto err_devmem;
+	}
 
-	devmem->pagemap.type = MEMORY_DEVICE_PRIVATE;
-	devmem->pagemap.range.start = res->start;
-	devmem->pagemap.range.end = res->end;
 	devmem->pagemap.nr_range = 1;
 	devmem->pagemap.ops = &dmirror_devmem_ops;
 	devmem->pagemap.owner = mdevice;
@@ -497,10 +523,14 @@ static bool dmirror_allocate_chunk(struct dmirror_device *mdevice,
 		mdevice->devmem_capacity = new_capacity;
 		mdevice->devmem_chunks = new_chunks;
 	}
-
 	ptr = memremap_pages(&devmem->pagemap, numa_node_id());
-	if (IS_ERR(ptr))
+	if (IS_ERR_OR_NULL(ptr)) {
+		if (ptr)
+			ret = PTR_ERR(ptr);
+		else
+			ret = -EFAULT;
 		goto err_release;
+	}
 
 	devmem->mdevice = mdevice;
 	pfn_first = devmem->pagemap.range.start >> PAGE_SHIFT;
@@ -529,15 +559,17 @@ static bool dmirror_allocate_chunk(struct dmirror_device *mdevice,
 	}
 	spin_unlock(&mdevice->lock);
 
-	return true;
+	return 0;
 
 err_release:
 	mutex_unlock(&mdevice->devmem_lock);
-	release_mem_region(devmem->pagemap.range.start, range_len(&devmem->pagemap.range));
+	if (res && devmem->pagemap.type == MEMORY_DEVICE_PRIVATE)
+		release_mem_region(devmem->pagemap.range.start,
+				   range_len(&devmem->pagemap.range));
 err_devmem:
 	kfree(devmem);
 
-	return false;
+	return ret;
 }
 
 static struct page *dmirror_devmem_alloc_page(struct dmirror_device *mdevice)
@@ -562,7 +594,7 @@ static struct page *dmirror_devmem_alloc_page(struct dmirror_device *mdevice)
 		spin_unlock(&mdevice->lock);
 	} else {
 		spin_unlock(&mdevice->lock);
-		if (!dmirror_allocate_chunk(mdevice, &dpage))
+		if (dmirror_allocate_chunk(mdevice, &dpage))
 			goto error;
 	}
 
@@ -1232,10 +1264,8 @@ static int dmirror_device_init(struct dmirror_device *mdevice, int id)
 	if (ret)
 		return ret;
 
-	/* Build a list of free ZONE_DEVICE private struct pages */
-	dmirror_allocate_chunk(mdevice, NULL);
-
-	return 0;
+	/* Build a list of free ZONE_DEVICE struct pages */
+	return dmirror_allocate_chunk(mdevice, NULL);
 }
 
 static void dmirror_device_remove(struct dmirror_device *mdevice)
@@ -1248,8 +1278,9 @@ static void dmirror_device_remove(struct dmirror_device *mdevice)
 				mdevice->devmem_chunks[i];
 
 			memunmap_pages(&devmem->pagemap);
-			release_mem_region(devmem->pagemap.range.start,
-					   range_len(&devmem->pagemap.range));
+			if (devmem->pagemap.type == MEMORY_DEVICE_PRIVATE)
+				release_mem_region(devmem->pagemap.range.start,
+						   range_len(&devmem->pagemap.range));
 			kfree(devmem);
 		}
 		kfree(mdevice->devmem_chunks);
diff --git a/lib/test_hmm_uapi.h b/lib/test_hmm_uapi.h
index 0511af7464ee..f700da7807c1 100644
--- a/lib/test_hmm_uapi.h
+++ b/lib/test_hmm_uapi.h
@@ -66,6 +66,7 @@ enum {
 enum {
 	/* 0 is reserved to catch uninitialized type fields */
 	HMM_DMIRROR_MEMORY_DEVICE_PRIVATE = 1,
+	HMM_DMIRROR_MEMORY_DEVICE_COHERENT,
 };
 
 #endif /* _LIB_TEST_HMM_UAPI_H */
-- 
2.32.0