Linux-Fsdevel Archive on lore.kernel.org
help / color / mirror / Atom feed
From: John Hubbard <jhubbard@nvidia.com>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>,
	Christoph Hellwig <hch@infradead.org>,
	Ilya Dryomov <idryomov@gmail.com>, Jens Axboe <axboe@kernel.dk>,
	Jeff Layton <jlayton@kernel.org>, <linux-xfs@vger.kernel.org>,
	<linux-fsdevel@vger.kernel.org>, <linux-block@vger.kernel.org>,
	<ceph-devel@vger.kernel.org>, <linux-mm@kvack.org>,
	LKML <linux-kernel@vger.kernel.org>,
	John Hubbard <jhubbard@nvidia.com>
Subject: [PATCH 1/5] iov_iter: introduce iov_iter_pin_user_pages*() routines
Date: Fri, 21 Aug 2020 21:20:55 -0700	[thread overview]
Message-ID: <20200822042059.1805541-2-jhubbard@nvidia.com> (raw)
In-Reply-To: <20200822042059.1805541-1-jhubbard@nvidia.com>

The new routines are:
    iov_iter_pin_user_pages()
    iov_iter_pin_user_pages_alloc()

and those correspond to these pre-existing routines:
    iov_iter_get_pages()
    iov_iter_get_pages_alloc()

Unlike the iov_iter_get_pages*() routines, the
iov_iter_pin_user_pages*() routines assert that only ITER_IOVEC items
are passed in. They then call pin_user_pages_fast(), instead of
get_user_pages_fast().

Why: In order to incrementally change Direct IO callers from calling
get_user_pages_fast() and put_page(), over to calling
pin_user_pages_fast() and unpin_user_page(), there need to be mid-level
routines that specifically call one or the other systems, for both page
acquisition and page release.

Signed-off-by: John Hubbard <jhubbard@nvidia.com>
---
 include/linux/uio.h |  5 +++
 lib/iov_iter.c      | 80 +++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 85 insertions(+)

diff --git a/include/linux/uio.h b/include/linux/uio.h
index 3835a8a8e9ea..29b0504a27cc 100644
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -229,6 +229,11 @@ int iov_iter_npages(const struct iov_iter *i, int maxpages);
 
 const void *dup_iter(struct iov_iter *new, struct iov_iter *old, gfp_t flags);
 
+ssize_t iov_iter_pin_user_pages(struct iov_iter *i, struct page **pages,
+			size_t maxsize, unsigned int maxpages, size_t *start);
+ssize_t iov_iter_pin_user_pages_alloc(struct iov_iter *i, struct page ***pages,
+			size_t maxsize, size_t *start);
+
 static inline size_t iov_iter_count(const struct iov_iter *i)
 {
 	return i->count;
diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index 5e40786c8f12..d818b16d136b 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -1309,6 +1309,44 @@ static ssize_t pipe_get_pages(struct iov_iter *i,
 	return __pipe_get_pages(i, min(maxsize, capacity), pages, iter_head, start);
 }
 
+ssize_t iov_iter_pin_user_pages(struct iov_iter *i,
+		   struct page **pages, size_t maxsize, unsigned int maxpages,
+		   size_t *start)
+{
+	size_t skip = i->iov_offset;
+	const struct iovec *iov;
+	struct iovec v;
+
+	if (WARN_ON_ONCE(!iter_is_iovec(i)))
+		return -EFAULT;
+
+	if (unlikely(!maxsize))
+		return 0;
+	maxsize = min(maxsize, i->count);
+
+	iterate_iovec(i, maxsize, v, iov, skip, ({
+		unsigned long addr = (unsigned long)v.iov_base;
+		size_t len = v.iov_len + (*start = addr & (PAGE_SIZE - 1));
+		int n;
+		int res;
+
+		if (len > maxpages * PAGE_SIZE)
+			len = maxpages * PAGE_SIZE;
+		addr &= ~(PAGE_SIZE - 1);
+		n = DIV_ROUND_UP(len, PAGE_SIZE);
+
+		res = pin_user_pages_fast(addr, n,
+				iov_iter_rw(i) != WRITE ?  FOLL_WRITE : 0,
+				pages);
+		if (unlikely(res < 0))
+			return res;
+		return (res == n ? len : res * PAGE_SIZE) - *start;
+		0;
+	}))
+	return 0;
+}
+EXPORT_SYMBOL(iov_iter_pin_user_pages);
+
 ssize_t iov_iter_get_pages(struct iov_iter *i,
 		   struct page **pages, size_t maxsize, unsigned maxpages,
 		   size_t *start)
@@ -1388,6 +1426,48 @@ static ssize_t pipe_get_pages_alloc(struct iov_iter *i,
 	return n;
 }
 
+ssize_t iov_iter_pin_user_pages_alloc(struct iov_iter *i,
+		   struct page ***pages, size_t maxsize,
+		   size_t *start)
+{
+	struct page **p;
+	size_t skip = i->iov_offset;
+	const struct iovec *iov;
+	struct iovec v;
+
+	if (WARN_ON_ONCE(!iter_is_iovec(i)))
+		return -EFAULT;
+
+	if (unlikely(!maxsize))
+		return 0;
+	maxsize = min(maxsize, i->count);
+
+	iterate_iovec(i, maxsize, v, iov, skip, ({
+		unsigned long addr = (unsigned long)v.iov_base;
+		size_t len = v.iov_len + (*start = addr & (PAGE_SIZE - 1));
+		int n;
+		int res;
+
+		addr &= ~(PAGE_SIZE - 1);
+		n = DIV_ROUND_UP(len, PAGE_SIZE);
+		p = get_pages_array(n);
+		if (!p)
+			return -ENOMEM;
+
+		res = pin_user_pages_fast(addr, n,
+				iov_iter_rw(i) != WRITE ?  FOLL_WRITE : 0, p);
+		if (unlikely(res < 0)) {
+			kvfree(p);
+			return res;
+		}
+		*pages = p;
+		return (res == n ? len : res * PAGE_SIZE) - *start;
+		0;
+	}))
+	return 0;
+}
+EXPORT_SYMBOL(iov_iter_pin_user_pages_alloc);
+
 ssize_t iov_iter_get_pages_alloc(struct iov_iter *i,
 		   struct page ***pages, size_t maxsize,
 		   size_t *start)
-- 
2.28.0


  reply	other threads:[~2020-08-22  4:21 UTC|newest]

Thread overview: 24+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-08-22  4:20 [PATCH 0/5] bio: Direct IO: convert to pin_user_pages_fast() John Hubbard
2020-08-22  4:20 ` John Hubbard [this message]
2020-08-22  4:20 ` [PATCH 2/5] mm/gup: introduce pin_user_page() John Hubbard
2020-08-22  4:20 ` [PATCH 3/5] bio: convert get_user_pages_fast() --> pin_user_pages_fast() John Hubbard
2020-08-22  4:20 ` [PATCH 4/5] bio: introduce BIO_FOLL_PIN flag John Hubbard
2020-08-23  6:25   ` Christoph Hellwig
2020-08-23  6:57     ` John Hubbard
2020-08-24  7:36       ` John Hubbard
2020-08-24  9:20     ` Jens Axboe
2020-08-24 14:42       ` Christoph Hellwig
2020-08-22  4:20 ` [PATCH 5/5] fs/ceph: use pipe_get_pages_alloc() for pipe John Hubbard
2020-08-24 10:53   ` Jeff Layton
2020-08-24 17:54     ` John Hubbard
2020-08-24 18:47       ` Jeff Layton
2020-08-24 18:54         ` Matthew Wilcox
2020-08-24 19:02           ` John Hubbard
2020-08-25  1:20           ` [PATCH v2] " John Hubbard
2020-08-25 16:22             ` Jeff Layton
2020-08-25  1:54 ` [PATCH 0/5] bio: Direct IO: convert to pin_user_pages_fast() Al Viro
2020-08-25  2:07   ` Al Viro
2020-08-25  2:13     ` John Hubbard
2020-08-25  2:07   ` John Hubbard
2020-08-25  2:22     ` Al Viro
2020-08-25  2:27       ` John Hubbard

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20200822042059.1805541-2-jhubbard@nvidia.com \
    --to=jhubbard@nvidia.com \
    --cc=akpm@linux-foundation.org \
    --cc=axboe@kernel.dk \
    --cc=ceph-devel@vger.kernel.org \
    --cc=hch@infradead.org \
    --cc=idryomov@gmail.com \
    --cc=jlayton@kernel.org \
    --cc=linux-block@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linux-xfs@vger.kernel.org \
    --cc=viro@zeniv.linux.org.uk \
    --subject='Re: [PATCH 1/5] iov_iter: introduce iov_iter_pin_user_pages*() routines' \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).