Received-SPF: Pass (protection.outlook.com: domain of nvidia.com designates
 216.228.117.160 as permitted sender) receiver=protection.outlook.com;
 client-ip=216.228.117.160; helo=mail.nvidia.com; pr=C
Message-ID: <0b649477-8e61-b330-aba5-eba4761a56d5@nvidia.com>
Date:   Tue, 24 Jan 2023 11:23:45 -0800
MIME-Version: 1.0
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:102.0) Gecko/20100101
 Thunderbird/102.6.1
Subject: Re: [PATCH v9 1/8] iov_iter: Define flags to qualify page extraction.
Content-Language: en-US
To:     David Howells <dhowells@redhat.com>,
        Al Viro <viro@zeniv.linux.org.uk>,
        Christoph Hellwig <hch@infradead.org>
CC:     Matthew Wilcox <willy@infradead.org>, Jens Axboe <axboe@kernel.dk>,
        "Jan Kara" <jack@suse.cz>, Jeff Layton <jlayton@kernel.org>,
        David Hildenbrand <david@redhat.com>,
        Jason Gunthorpe <jgg@nvidia.com>,
        Logan Gunthorpe <logang@deltatee.com>,
        <linux-fsdevel@vger.kernel.org>, <linux-block@vger.kernel.org>,
        <linux-kernel@vger.kernel.org>
References: <20230124170108.1070389-1-dhowells@redhat.com>
 <20230124170108.1070389-2-dhowells@redhat.com>
From:   John Hubbard <jhubbard@nvidia.com>
In-Reply-To: <20230124170108.1070389-2-dhowells@redhat.com>
Content-Type: text/plain; charset="UTF-8"; format=flowed
Content-Transfer-Encoding: 7bit
X-MS-Exchange-CrossTenant-OriginalArrivalTime: 24 Jan 2023 19:24:00.9771
 (UTC)
X-MS-Exchange-CrossTenant-Network-Message-Id: 9a7559f2-725f-43c3-9e1d-08dafe408c50
X-MS-Exchange-CrossTenant-Id: 43083d15-7273-40c1-b7db-39efd9ccc17a
X-MS-Exchange-CrossTenant-OriginalAttributedTenantConnectingIp: TenantId=43083d15-7273-40c1-b7db-39efd9ccc17a;Ip=[216.228.117.160];Helo=[mail.nvidia.com]
X-MS-Exchange-CrossTenant-AuthSource: BN8NAM11FT099.eop-nam11.prod.protection.outlook.com
X-MS-Exchange-CrossTenant-AuthAs: Anonymous
X-MS-Exchange-CrossTenant-FromEntityHeader: HybridOnPrem
X-MS-Exchange-Transport-CrossTenantHeadersStamped: DS7PR12MB6007
Precedence: bulk
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

On 1/24/23 09:01, David Howells wrote:
> Define flags to qualify page extraction to pass into iov_iter_*_pages*()
> rather than passing in FOLL_* flags.
> 
> For now only a flag to allow peer-to-peer DMA is supported.
> 
> Signed-off-by: David Howells <dhowells@redhat.com>
> cc: Al Viro <viro@zeniv.linux.org.uk>
> cc: Christoph Hellwig <hch@infradead.org>
> cc: Jens Axboe <axboe@kernel.dk>
> cc: Logan Gunthorpe <logang@deltatee.com>
> cc: linux-fsdevel@vger.kernel.org
> cc: linux-block@vger.kernel.org
> ---
> 
> Notes:
>      ver #9)
>       - Change extract_flags to extraction_flags.

Reviewed-by: John Hubbard <jhubbard@nvidia.com>

thanks,
-- 
John Hubbard
NVIDIA

>      
>      ver #7)
>       - Don't use FOLL_* as a parameter, but rather define constants
>         specifically to use with iov_iter_*_pages*().
>       - Drop the I/O direction constants for now.
> 
>   block/bio.c         |  6 +++---
>   block/blk-map.c     |  8 ++++----
>   include/linux/uio.h |  7 +++++--
>   lib/iov_iter.c      | 14 ++++++++------
>   4 files changed, 20 insertions(+), 15 deletions(-)
> 
> diff --git a/block/bio.c b/block/bio.c
> index ab59a491a883..683444e6b711 100644
> --- a/block/bio.c
> +++ b/block/bio.c
> @@ -1249,7 +1249,7 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
>   	unsigned short entries_left = bio->bi_max_vecs - bio->bi_vcnt;
>   	struct bio_vec *bv = bio->bi_io_vec + bio->bi_vcnt;
>   	struct page **pages = (struct page **)bv;
> -	unsigned int gup_flags = 0;
> +	unsigned int extraction_flags = 0;
>   	ssize_t size, left;
>   	unsigned len, i = 0;
>   	size_t offset, trim;
> @@ -1264,7 +1264,7 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
>   	pages += entries_left * (PAGE_PTRS_PER_BVEC - 1);
>   
>   	if (bio->bi_bdev && blk_queue_pci_p2pdma(bio->bi_bdev->bd_disk->queue))
> -		gup_flags |= FOLL_PCI_P2PDMA;
> +		extraction_flags |= ITER_ALLOW_P2PDMA;
>   
>   	/*
>   	 * Each segment in the iov is required to be a block size multiple.
> @@ -1275,7 +1275,7 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
>   	 */
>   	size = iov_iter_get_pages(iter, pages,
>   				  UINT_MAX - bio->bi_iter.bi_size,
> -				  nr_pages, &offset, gup_flags);
> +				  nr_pages, &offset, extraction_flags);
>   	if (unlikely(size <= 0))
>   		return size ? size : -EFAULT;
>   
> diff --git a/block/blk-map.c b/block/blk-map.c
> index 19940c978c73..7db52ad5b2d0 100644
> --- a/block/blk-map.c
> +++ b/block/blk-map.c
> @@ -267,7 +267,7 @@ static int bio_map_user_iov(struct request *rq, struct iov_iter *iter,
>   {
>   	unsigned int max_sectors = queue_max_hw_sectors(rq->q);
>   	unsigned int nr_vecs = iov_iter_npages(iter, BIO_MAX_VECS);
> -	unsigned int gup_flags = 0;
> +	unsigned int extraction_flags = 0;
>   	struct bio *bio;
>   	int ret;
>   	int j;
> @@ -280,7 +280,7 @@ static int bio_map_user_iov(struct request *rq, struct iov_iter *iter,
>   		return -ENOMEM;
>   
>   	if (blk_queue_pci_p2pdma(rq->q))
> -		gup_flags |= FOLL_PCI_P2PDMA;
> +		extraction_flags |= ITER_ALLOW_P2PDMA;
>   
>   	while (iov_iter_count(iter)) {
>   		struct page **pages, *stack_pages[UIO_FASTIOV];
> @@ -291,10 +291,10 @@ static int bio_map_user_iov(struct request *rq, struct iov_iter *iter,
>   		if (nr_vecs <= ARRAY_SIZE(stack_pages)) {
>   			pages = stack_pages;
>   			bytes = iov_iter_get_pages(iter, pages, LONG_MAX,
> -						   nr_vecs, &offs, gup_flags);
> +						   nr_vecs, &offs, extraction_flags);
>   		} else {
>   			bytes = iov_iter_get_pages_alloc(iter, &pages,
> -						LONG_MAX, &offs, gup_flags);
> +						LONG_MAX, &offs, extraction_flags);
>   		}
>   		if (unlikely(bytes <= 0)) {
>   			ret = bytes ? bytes : -EFAULT;
> diff --git a/include/linux/uio.h b/include/linux/uio.h
> index 9f158238edba..58fda77f6847 100644
> --- a/include/linux/uio.h
> +++ b/include/linux/uio.h
> @@ -252,12 +252,12 @@ void iov_iter_xarray(struct iov_iter *i, unsigned int direction, struct xarray *
>   		     loff_t start, size_t count);
>   ssize_t iov_iter_get_pages(struct iov_iter *i, struct page **pages,
>   		size_t maxsize, unsigned maxpages, size_t *start,
> -		unsigned gup_flags);
> +		unsigned extraction_flags);
>   ssize_t iov_iter_get_pages2(struct iov_iter *i, struct page **pages,
>   			size_t maxsize, unsigned maxpages, size_t *start);
>   ssize_t iov_iter_get_pages_alloc(struct iov_iter *i,
>   		struct page ***pages, size_t maxsize, size_t *start,
> -		unsigned gup_flags);
> +		unsigned extraction_flags);
>   ssize_t iov_iter_get_pages_alloc2(struct iov_iter *i, struct page ***pages,
>   			size_t maxsize, size_t *start);
>   int iov_iter_npages(const struct iov_iter *i, int maxpages);
> @@ -360,4 +360,7 @@ static inline void iov_iter_ubuf(struct iov_iter *i, unsigned int direction,
>   	};
>   }
>   
> +/* Flags for iov_iter_get/extract_pages*() */
> +#define ITER_ALLOW_P2PDMA	0x01	/* Allow P2PDMA on the extracted pages */
> +
>   #endif
> diff --git a/lib/iov_iter.c b/lib/iov_iter.c
> index f9a3ff37ecd1..da7db39075c6 100644
> --- a/lib/iov_iter.c
> +++ b/lib/iov_iter.c
> @@ -1432,9 +1432,9 @@ static struct page *first_bvec_segment(const struct iov_iter *i,
>   static ssize_t __iov_iter_get_pages_alloc(struct iov_iter *i,
>   		   struct page ***pages, size_t maxsize,
>   		   unsigned int maxpages, size_t *start,
> -		   unsigned int gup_flags)
> +		   unsigned int extraction_flags)
>   {
> -	unsigned int n;
> +	unsigned int n, gup_flags = 0;
>   
>   	if (maxsize > i->count)
>   		maxsize = i->count;
> @@ -1442,6 +1442,8 @@ static ssize_t __iov_iter_get_pages_alloc(struct iov_iter *i,
>   		return 0;
>   	if (maxsize > MAX_RW_COUNT)
>   		maxsize = MAX_RW_COUNT;
> +	if (extraction_flags & ITER_ALLOW_P2PDMA)
> +		gup_flags |= FOLL_PCI_P2PDMA;
>   
>   	if (likely(user_backed_iter(i))) {
>   		unsigned long addr;
> @@ -1495,14 +1497,14 @@ static ssize_t __iov_iter_get_pages_alloc(struct iov_iter *i,
>   
>   ssize_t iov_iter_get_pages(struct iov_iter *i,
>   		   struct page **pages, size_t maxsize, unsigned maxpages,
> -		   size_t *start, unsigned gup_flags)
> +		   size_t *start, unsigned extraction_flags)
>   {
>   	if (!maxpages)
>   		return 0;
>   	BUG_ON(!pages);
>   
>   	return __iov_iter_get_pages_alloc(i, &pages, maxsize, maxpages,
> -					  start, gup_flags);
> +					  start, extraction_flags);
>   }
>   EXPORT_SYMBOL_GPL(iov_iter_get_pages);
>   
> @@ -1515,14 +1517,14 @@ EXPORT_SYMBOL(iov_iter_get_pages2);
>   
>   ssize_t iov_iter_get_pages_alloc(struct iov_iter *i,
>   		   struct page ***pages, size_t maxsize,
> -		   size_t *start, unsigned gup_flags)
> +		   size_t *start, unsigned extraction_flags)
>   {
>   	ssize_t len;
>   
>   	*pages = NULL;
>   
>   	len = __iov_iter_get_pages_alloc(i, pages, maxsize, ~0U, start,
> -					 gup_flags);
> +					 extraction_flags);
>   	if (len <= 0) {
>   		kvfree(*pages);
>   		*pages = NULL;
>