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>,
	<linux-xfs@vger.kernel.org>, <linux-fsdevel@vger.kernel.org>,
	<linux-block@vger.kernel.org>, <linux-mm@kvack.org>,
	LKML <linux-kernel@vger.kernel.org>,
	John Hubbard <jhubbard@nvidia.com>
Subject: [PATCH v2 2/3] iov_iter: introduce iov_iter_pin_user_pages*() routines
Date: Sat, 29 Aug 2020 01:08:52 -0700	[thread overview]
Message-ID: <20200829080853.20337-3-jhubbard@nvidia.com> (raw)
In-Reply-To: <20200829080853.20337-1-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()

Also, pipe_get_pages() and related are changed so as to pass
down a "use_pup" (use pin_user_page() instead of get_page()) bool
argument.

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

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      | 110 ++++++++++++++++++++++++++++++++++++++++----
 2 files changed, 107 insertions(+), 8 deletions(-)

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..f25555eb3279 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -1269,7 +1269,8 @@ static inline ssize_t __pipe_get_pages(struct iov_iter *i,
 				size_t maxsize,
 				struct page **pages,
 				int iter_head,
-				size_t *start)
+				size_t *start,
+				bool use_pup)
 {
 	struct pipe_inode_info *pipe = i->pipe;
 	unsigned int p_mask = pipe->ring_size - 1;
@@ -1280,7 +1281,11 @@ static inline ssize_t __pipe_get_pages(struct iov_iter *i,
 	maxsize = n;
 	n += *start;
 	while (n > 0) {
-		get_page(*pages++ = pipe->bufs[iter_head & p_mask].page);
+		if (use_pup)
+			pin_user_page(*pages++ = pipe->bufs[iter_head & p_mask].page);
+		else
+			get_page(*pages++ = pipe->bufs[iter_head & p_mask].page);
+
 		iter_head++;
 		n -= PAGE_SIZE;
 	}
@@ -1290,7 +1295,7 @@ static inline ssize_t __pipe_get_pages(struct iov_iter *i,
 
 static ssize_t pipe_get_pages(struct iov_iter *i,
 		   struct page **pages, size_t maxsize, unsigned maxpages,
-		   size_t *start)
+		   size_t *start, bool use_pup)
 {
 	unsigned int iter_head, npages;
 	size_t capacity;
@@ -1306,8 +1311,51 @@ static ssize_t pipe_get_pages(struct iov_iter *i,
 	npages = pipe_space_for_user(iter_head, i->pipe->tail, i->pipe);
 	capacity = min(npages, maxpages) * PAGE_SIZE - *start;
 
-	return __pipe_get_pages(i, min(maxsize, capacity), pages, iter_head, start);
+	return __pipe_get_pages(i, min(maxsize, capacity), pages, iter_head,
+				start, use_pup);
+}
+
+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 (unlikely(iov_iter_is_pipe(i)))
+		return pipe_get_pages(i, pages, maxsize, maxpages, start, true);
+	if (unlikely(iov_iter_is_discard(i)))
+		return -EFAULT;
+	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,
@@ -1317,7 +1365,7 @@ ssize_t iov_iter_get_pages(struct iov_iter *i,
 		maxsize = i->count;
 
 	if (unlikely(iov_iter_is_pipe(i)))
-		return pipe_get_pages(i, pages, maxsize, maxpages, start);
+		return pipe_get_pages(i, pages, maxsize, maxpages, start, false);
 	if (unlikely(iov_iter_is_discard(i)))
 		return -EFAULT;
 
@@ -1357,7 +1405,7 @@ static struct page **get_pages_array(size_t n)
 
 static ssize_t pipe_get_pages_alloc(struct iov_iter *i,
 		   struct page ***pages, size_t maxsize,
-		   size_t *start)
+		   size_t *start, bool use_pup)
 {
 	struct page **p;
 	unsigned int iter_head, npages;
@@ -1380,7 +1428,7 @@ static ssize_t pipe_get_pages_alloc(struct iov_iter *i,
 	p = get_pages_array(npages);
 	if (!p)
 		return -ENOMEM;
-	n = __pipe_get_pages(i, maxsize, p, iter_head, start);
+	n = __pipe_get_pages(i, maxsize, p, iter_head, start, use_pup);
 	if (n > 0)
 		*pages = p;
 	else
@@ -1388,6 +1436,52 @@ 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 (unlikely(iov_iter_is_pipe(i)))
+		return pipe_get_pages_alloc(i, pages, maxsize, start, true);
+	if (unlikely(iov_iter_is_discard(i)))
+		return -EFAULT;
+	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)
@@ -1398,7 +1492,7 @@ ssize_t iov_iter_get_pages_alloc(struct iov_iter *i,
 		maxsize = i->count;
 
 	if (unlikely(iov_iter_is_pipe(i)))
-		return pipe_get_pages_alloc(i, pages, maxsize, start);
+		return pipe_get_pages_alloc(i, pages, maxsize, start, false);
 	if (unlikely(iov_iter_is_discard(i)))
 		return -EFAULT;
 
-- 
2.28.0


  parent reply	other threads:[~2020-08-29  8:09 UTC|newest]

Thread overview: 12+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-08-29  8:08 [PATCH v2 0/3] bio: Direct IO: convert to pin_user_pages_fast() John Hubbard
2020-08-29  8:08 ` [PATCH v2 1/3] mm/gup: introduce pin_user_page() John Hubbard
2020-08-29 14:54   ` Christoph Hellwig
2020-08-29 21:57     ` John Hubbard
2020-08-29  8:08 ` John Hubbard [this message]
2020-08-29 14:58   ` [PATCH v2 2/3] iov_iter: introduce iov_iter_pin_user_pages*() routines Christoph Hellwig
2020-08-29 21:58     ` John Hubbard
2020-08-30 20:17   ` Al Viro
2020-08-30 20:44     ` John Hubbard
2020-08-29  8:08 ` [PATCH v2 3/3] bio: convert get_user_pages_fast() --> pin_user_pages_fast() John Hubbard
2020-08-29 15:02   ` Christoph Hellwig
2020-08-29 22:08     ` 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=20200829080853.20337-3-jhubbard@nvidia.com \
    --to=jhubbard@nvidia.com \
    --cc=akpm@linux-foundation.org \
    --cc=axboe@kernel.dk \
    --cc=hch@infradead.org \
    --cc=idryomov@gmail.com \
    --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 v2 2/3] 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).