Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   jhubbard.send.patches@gmail.com
To:     Jens Axboe <axboe@kernel.dk>, Jan Kara <jack@suse.cz>,
        Christoph Hellwig <hch@infradead.org>,
        Dave Chinner <dchinner@redhat.com>,
        "Darrick J . Wong" <djwong@kernel.org>,
        Theodore Ts'o <tytso@mit.edu>,
        Alexander Viro <viro@zeniv.linux.org.uk>,
        Miklos Szeredi <miklos@szeredi.hu>,
        Andrew Morton <akpm@linux-foundation.org>,
        Chaitanya Kulkarni <kch@nvidia.com>
Cc:     linux-block@vger.kernel.org, linux-fsdevel@vger.kernel.org,
        linux-xfs@vger.kernel.org, linux-mm@kvack.org,
        LKML <linux-kernel@vger.kernel.org>,
        John Hubbard <jhubbard@nvidia.com>
Subject: [PATCH 2/6] iov_iter: new iov_iter_pin_pages*(), for FOLL_PIN pages
Date:   Sun, 27 Feb 2022 01:34:30 -0800
Message-Id: <20220227093434.2889464-3-jhubbard@nvidia.com>
In-Reply-To: <20220227093434.2889464-1-jhubbard@nvidia.com>
References: <20220227093434.2889464-1-jhubbard@nvidia.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

From: John Hubbard <jhubbard@nvidia.com>

Provide two new specialized routines that only handle user space pages,
and invoke pin_user_pages_fast() on them: iov_iter_pin_pages() and
iov_iter_pin_pages_alloc().

This allows subsequent patches to convert various callers of
iov_iter_get_pages*(), to the new calls, without having to attempt a
mass conversion all at once.

Signed-off-by: John Hubbard <jhubbard@nvidia.com>
---
 include/linux/uio.h |  4 +++
 lib/iov_iter.c      | 78 +++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 82 insertions(+)

diff --git a/include/linux/uio.h b/include/linux/uio.h
index 739285fe5a2f..208020c2b75a 100644
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -236,6 +236,10 @@ ssize_t iov_iter_get_pages(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);
+ssize_t iov_iter_pin_pages(struct iov_iter *i, struct page **pages,
+			size_t maxsize, unsigned int maxpages, size_t *start);
+ssize_t iov_iter_pin_pages_alloc(struct iov_iter *i, struct page ***pages,
+			size_t maxsize, size_t *start);
 int iov_iter_npages(const struct iov_iter *i, int maxpages);
 void iov_iter_restore(struct iov_iter *i, struct iov_iter_state *state);
 
diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index 6dd5330f7a99..e64e8e4edd0c 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -1560,6 +1560,41 @@ ssize_t iov_iter_get_pages(struct iov_iter *i,
 }
 EXPORT_SYMBOL(iov_iter_get_pages);
 
+ssize_t iov_iter_pin_pages(struct iov_iter *i,
+		   struct page **pages, size_t maxsize, unsigned int maxpages,
+		   size_t *start)
+{
+	size_t len;
+	int n, res;
+
+	if (maxsize > i->count)
+		maxsize = i->count;
+	if (!maxsize)
+		return 0;
+
+	WARN_ON_ONCE(!iter_is_iovec(i));
+
+	if (likely(iter_is_iovec(i))) {
+		unsigned int gup_flags = 0;
+		unsigned long addr;
+
+		if (iov_iter_rw(i) != WRITE)
+			gup_flags |= FOLL_WRITE;
+		if (i->nofault)
+			gup_flags |= FOLL_NOFAULT;
+
+		addr = first_iovec_segment(i, &len, start, maxsize, maxpages);
+		n = DIV_ROUND_UP(len, PAGE_SIZE);
+		res = pin_user_pages_fast(addr, n, gup_flags, pages);
+		if (unlikely(res <= 0))
+			return res;
+		return (res == n ? len : res * PAGE_SIZE) - *start;
+	}
+
+	return -EFAULT;
+}
+EXPORT_SYMBOL(iov_iter_pin_pages);
+
 static struct page **get_pages_array(size_t n)
 {
 	return kvmalloc_array(n, sizeof(struct page *), GFP_KERNEL);
@@ -1696,6 +1731,49 @@ ssize_t iov_iter_get_pages_alloc(struct iov_iter *i,
 }
 EXPORT_SYMBOL(iov_iter_get_pages_alloc);
 
+ssize_t iov_iter_pin_pages_alloc(struct iov_iter *i,
+		   struct page ***pages, size_t maxsize,
+		   size_t *start)
+{
+	struct page **p;
+	size_t len;
+	int n, res;
+
+	if (maxsize > i->count)
+		maxsize = i->count;
+	if (!maxsize)
+		return 0;
+
+	WARN_ON_ONCE(!iter_is_iovec(i));
+
+	if (likely(iter_is_iovec(i))) {
+		unsigned int gup_flags = 0;
+		unsigned long addr;
+
+		if (iov_iter_rw(i) != WRITE)
+			gup_flags |= FOLL_WRITE;
+		if (i->nofault)
+			gup_flags |= FOLL_NOFAULT;
+
+		addr = first_iovec_segment(i, &len, start, maxsize, ~0U);
+		n = DIV_ROUND_UP(len, PAGE_SIZE);
+		p = get_pages_array(n);
+		if (!p)
+			return -ENOMEM;
+		res = pin_user_pages_fast(addr, n, gup_flags, p);
+		if (unlikely(res <= 0)) {
+			kvfree(p);
+			*pages = NULL;
+			return res;
+		}
+		*pages = p;
+		return (res == n ? len : res * PAGE_SIZE) - *start;
+	}
+
+	return -EFAULT;
+}
+EXPORT_SYMBOL(iov_iter_pin_pages_alloc);
+
 size_t csum_and_copy_from_iter(void *addr, size_t bytes, __wsum *csum,
 			       struct iov_iter *i)
 {
-- 
2.35.1