Received-SPF: Pass (protection.outlook.com: domain of nvidia.com designates
 203.18.50.14 as permitted sender) receiver=protection.outlook.com;
 client-ip=203.18.50.14; 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 v2 03/11] mm/gup: migrate PIN_LONGTERM dev coherent pages to system
Date:   Wed, 8 Dec 2021 22:31:58 +1100
Message-ID: <2858338.J0npWUQLIM@nvdebian>
In-Reply-To: <20211206185251.20646-4-alex.sierra@amd.com>
References: <20211206185251.20646-1-alex.sierra@amd.com> <20211206185251.20646-4-alex.sierra@amd.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 7Bit
Content-Type: text/plain; charset="us-ascii"
X-MS-Exchange-CrossTenant-OriginalArrivalTime: 08 Dec 2021 11:32:11.5741
 (UTC)
X-MS-Exchange-CrossTenant-Network-Message-Id: ca4b1442-ca8a-499a-d6e2-08d9ba3e6094
X-MS-Exchange-CrossTenant-Id: 43083d15-7273-40c1-b7db-39efd9ccc17a
X-MS-Exchange-CrossTenant-OriginalAttributedTenantConnectingIp: TenantId=43083d15-7273-40c1-b7db-39efd9ccc17a;Ip=[203.18.50.14];Helo=[mail.nvidia.com]
X-MS-Exchange-CrossTenant-AuthSource: BN8NAM11FT033.eop-nam11.prod.protection.outlook.com
X-MS-Exchange-CrossTenant-AuthAs: Anonymous
X-MS-Exchange-CrossTenant-FromEntityHeader: HybridOnPrem
X-MS-Exchange-Transport-CrossTenantHeadersStamped: DM8PR12MB5495
Precedence: bulk
List-ID: <linux-ext4.vger.kernel.org>
X-Mailing-List: linux-ext4@vger.kernel.org

On Tuesday, 7 December 2021 5:52:43 AM AEDT Alex Sierra wrote:
> Avoid long term pinning for Coherent device type pages. This could
> interfere with their own device memory manager.
> If caller tries to get user device coherent pages with PIN_LONGTERM flag
> set, those pages will be migrated back to system memory.
> 
> Signed-off-by: Alex Sierra <alex.sierra@amd.com>
> ---
>  mm/gup.c | 32 ++++++++++++++++++++++++++++++--
>  1 file changed, 30 insertions(+), 2 deletions(-)
> 
> diff --git a/mm/gup.c b/mm/gup.c
> index 886d6148d3d0..1572eacf07f4 100644
> --- a/mm/gup.c
> +++ b/mm/gup.c
> @@ -1689,17 +1689,37 @@ struct page *get_dump_page(unsigned long addr)
>  #endif /* CONFIG_ELF_CORE */
>  
>  #ifdef CONFIG_MIGRATION
> +static int migrate_device_page(unsigned long address,
> +				struct page *page)
> +{
> +	struct vm_area_struct *vma = find_vma(current->mm, address);
> +	struct vm_fault vmf = {
> +		.vma = vma,
> +		.address = address & PAGE_MASK,
> +		.flags = FAULT_FLAG_USER,
> +		.pgoff = linear_page_index(vma, address),
> +		.gfp_mask = GFP_KERNEL,
> +		.page = page,
> +	};
> +	if (page->pgmap && page->pgmap->ops->migrate_to_ram)
> +		return page->pgmap->ops->migrate_to_ram(&vmf);

How does this synchronise against pgmap being released? As I understand things
at this point we're not holding a reference on either the page or pgmap, so
the page and therefore the pgmap may have been freed.

I think a similar problem exists for device private fault handling as well and
it has been on my list of things to fix for a while. I think the solution is to
call try_get_page(), except it doesn't work with device pages due to the whole
refcount thing. That issue is blocking a fair bit of work now so I've started
looking into it.

> +
> +	return -EBUSY;
> +}
> +
>  /*
>   * Check whether all pages are pinnable, if so return number of pages.  If some
>   * pages are not pinnable, migrate them, and unpin all pages. Return zero if
>   * pages were migrated, or if some pages were not successfully isolated.
>   * Return negative error if migration fails.
>   */
> -static long check_and_migrate_movable_pages(unsigned long nr_pages,
> +static long check_and_migrate_movable_pages(unsigned long start,
> +					    unsigned long nr_pages,
>  					    struct page **pages,
>  					    unsigned int gup_flags)
>  {
>  	unsigned long i;
> +	unsigned long page_index;
>  	unsigned long isolation_error_count = 0;
>  	bool drain_allow = true;
>  	LIST_HEAD(movable_page_list);
> @@ -1720,6 +1740,10 @@ static long check_and_migrate_movable_pages(unsigned long nr_pages,
>  		 * If we get a movable page, since we are going to be pinning
>  		 * these entries, try to move them out if possible.
>  		 */
> +		if (is_device_page(head)) {
> +			page_index = i;
> +			goto unpin_pages;
> +		}
>  		if (!is_pinnable_page(head)) {
>  			if (PageHuge(head)) {
>  				if (!isolate_huge_page(head, &movable_page_list))
> @@ -1750,12 +1774,16 @@ static long check_and_migrate_movable_pages(unsigned long nr_pages,
>  	if (list_empty(&movable_page_list) && !isolation_error_count)
>  		return nr_pages;
>  
> +unpin_pages:
>  	if (gup_flags & FOLL_PIN) {
>  		unpin_user_pages(pages, nr_pages);
>  	} else {
>  		for (i = 0; i < nr_pages; i++)
>  			put_page(pages[i]);
>  	}
> +	if (is_device_page(head))
> +		return migrate_device_page(start + page_index * PAGE_SIZE, head);

This isn't very optimal - if a range contains more than one device page (which
seems likely) we will have to go around the whole gup/check_and_migrate loop
once for each device page which seems unnecessary. You should be able to either
build a list or migrate them as you go through the loop. I'm also currently
looking into how to extend migrate_pages() to support device pages which might
be useful here too.

> +
>  	if (!list_empty(&movable_page_list)) {
>  		ret = migrate_pages(&movable_page_list, alloc_migration_target,
>  				    NULL, (unsigned long)&mtc, MIGRATE_SYNC,
> @@ -1798,7 +1826,7 @@ static long __gup_longterm_locked(struct mm_struct *mm,
>  					     NULL, gup_flags);
>  		if (rc <= 0)
>  			break;
> -		rc = check_and_migrate_movable_pages(rc, pages, gup_flags);
> +		rc = check_and_migrate_movable_pages(start, rc, pages, gup_flags);
>  	} while (!rc);
>  	memalloc_pin_restore(flags);
>  
>