Received-SPF: pass (google.com: domain of linux-ext4-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
Received-SPF: Pass (protection.outlook.com: domain of nvidia.com designates
 12.22.5.236 as permitted sender) receiver=protection.outlook.com;
 client-ip=12.22.5.236; helo=mail.nvidia.com;
From:   Alistair Popple <apopple@nvidia.com>
To:     <akpm@linux-foundation.org>, <Felix.Kuehling@amd.com>,
        <linux-mm@kvack.org>, <rcampbell@nvidia.com>,
        <linux-ext4@vger.kernel.org>, <linux-xfs@vger.kernel.org>,
        Alex Sierra <alex.sierra@amd.com>
CC:     <amd-gfx@lists.freedesktop.org>, <dri-devel@lists.freedesktop.org>,
        <hch@lst.de>, <jgg@nvidia.com>, <jglisse@redhat.com>,
        <willy@infradead.org>
Subject: Re: [PATCH v4 07/10] lib: test_hmm add module param for zone device type
Date:   Fri, 28 Jan 2022 15:22:46 +1100
Message-ID: <1953720.XltcCvqqDp@nvdebian>
In-Reply-To: <20220127030949.19396-8-alex.sierra@amd.com>
References: <20220127030949.19396-1-alex.sierra@amd.com> <20220127030949.19396-8-alex.sierra@amd.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 7Bit
Content-Type: text/plain; charset="us-ascii"
X-MS-Exchange-CrossTenant-OriginalArrivalTime: 28 Jan 2022 04:22:52.3096
 (UTC)
X-MS-Exchange-CrossTenant-Network-Message-Id: 289a033c-2dad-4f9f-0712-08d9e215d9b5
X-MS-Exchange-CrossTenant-Id: 43083d15-7273-40c1-b7db-39efd9ccc17a
X-MS-Exchange-CrossTenant-OriginalAttributedTenantConnectingIp: TenantId=43083d15-7273-40c1-b7db-39efd9ccc17a;Ip=[12.22.5.236];Helo=[mail.nvidia.com]
X-MS-Exchange-CrossTenant-AuthSource: CO1NAM11FT020.eop-nam11.prod.protection.outlook.com
X-MS-Exchange-CrossTenant-AuthAs: Anonymous
X-MS-Exchange-CrossTenant-FromEntityHeader: HybridOnPrem
X-MS-Exchange-Transport-CrossTenantHeadersStamped: MN2PR12MB3247
Precedence: bulk
List-ID: <linux-ext4.vger.kernel.org>
X-Mailing-List: linux-ext4@vger.kernel.org

Thanks for the updates, looks good now.

Reviewed-by: Alistair Popple <apopple@nvidia.com>

On Thursday, 27 January 2022 2:09:46 PM AEDT Alex Sierra wrote:
> 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>
> ---
>  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 fb1fa7c6fa98..6f068f7c4ee3 100644
> --- a/lib/test_hmm.c
> +++ b/lib/test_hmm.c
> @@ -34,6 +34,16 @@
>  #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;
> @@ -452,28 +462,44 @@ 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;
> @@ -494,10 +520,14 @@ 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;
> @@ -526,15 +556,17 @@ 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)
> @@ -559,7 +591,7 @@ 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;
>  	}
>  
> @@ -1219,10 +1251,8 @@ 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)
> @@ -1235,8 +1265,9 @@ 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 17f842f1aa02..625f3690d086 100644
> --- a/lib/test_hmm_uapi.h
> +++ b/lib/test_hmm_uapi.h
> @@ -68,6 +68,7 @@ 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 */
>