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 6/6] fuse: convert direct IO paths to use FOLL_PIN
Date:   Sun, 27 Feb 2022 01:34:34 -0800
Message-Id: <20220227093434.2889464-7-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>

Convert the fuse filesystem to support the new iov_iter_get_pages()
behavior. That routine now invokes pin_user_pages_fast(), which means
that such pages must be released via unpin_user_page(), rather than via
put_page().

This commit also removes any possibility of kernel pages being handled,
in the fuse_get_user_pages() call. Although this may seem like a steep
price to pay, Christoph Hellwig actually recommended it a few years ago
for nearly the same situation [1].

[1] https://lore.kernel.org/kvm/20190724061750.GA19397@infradead.org/

Signed-off-by: John Hubbard <jhubbard@nvidia.com>
---
 fs/fuse/dev.c  |  7 +++++--
 fs/fuse/file.c | 38 +++++++++-----------------------------
 2 files changed, 14 insertions(+), 31 deletions(-)

diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index e1b4a846c90d..9db85c4d549a 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -675,7 +675,10 @@ static void fuse_copy_finish(struct fuse_copy_state *cs)
 			flush_dcache_page(cs->pg);
 			set_page_dirty_lock(cs->pg);
 		}
-		put_page(cs->pg);
+		if (cs->pipebufs)
+			put_page(cs->pg);
+		else
+			unpin_user_page(cs->pg);
 	}
 	cs->pg = NULL;
 }
@@ -730,7 +733,7 @@ static int fuse_copy_fill(struct fuse_copy_state *cs)
 		}
 	} else {
 		size_t off;
-		err = iov_iter_get_pages(cs->iter, &page, PAGE_SIZE, 1, &off);
+		err = iov_iter_pin_pages(cs->iter, &page, PAGE_SIZE, 1, &off);
 		if (err < 0)
 			return err;
 		BUG_ON(!err);
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 94747bac3489..ecfa5bdde919 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -611,18 +611,6 @@ void fuse_read_args_fill(struct fuse_io_args *ia, struct file *file, loff_t pos,
 	args->out_args[0].size = count;
 }
 
-static void fuse_release_user_pages(struct fuse_args_pages *ap,
-				    bool should_dirty)
-{
-	unsigned int i;
-
-	for (i = 0; i < ap->num_pages; i++) {
-		if (should_dirty)
-			set_page_dirty_lock(ap->pages[i]);
-		put_page(ap->pages[i]);
-	}
-}
-
 static void fuse_io_release(struct kref *kref)
 {
 	kfree(container_of(kref, struct fuse_io_priv, refcnt));
@@ -720,7 +708,8 @@ static void fuse_aio_complete_req(struct fuse_mount *fm, struct fuse_args *args,
 	struct fuse_io_priv *io = ia->io;
 	ssize_t pos = -1;
 
-	fuse_release_user_pages(&ia->ap, io->should_dirty);
+	unpin_user_pages_dirty_lock(ia->ap.pages, ia->ap.num_pages,
+				    io->should_dirty);
 
 	if (err) {
 		/* Nothing */
@@ -1382,25 +1371,14 @@ static int fuse_get_user_pages(struct fuse_args_pages *ap, struct iov_iter *ii,
 	size_t nbytes = 0;  /* # bytes already packed in req */
 	ssize_t ret = 0;
 
-	/* Special case for kernel I/O: can copy directly into the buffer */
-	if (iov_iter_is_kvec(ii)) {
-		unsigned long user_addr = fuse_get_user_addr(ii);
-		size_t frag_size = fuse_get_frag_size(ii, *nbytesp);
-
-		if (write)
-			ap->args.in_args[1].value = (void *) user_addr;
-		else
-			ap->args.out_args[0].value = (void *) user_addr;
-
-		iov_iter_advance(ii, frag_size);
-		*nbytesp = frag_size;
-		return 0;
-	}
+	/* Only user space buffers are allowed with fuse Direct IO. */
+	if (WARN_ON_ONCE(!iter_is_iovec(ii)))
+		return -EOPNOTSUPP;
 
 	while (nbytes < *nbytesp && ap->num_pages < max_pages) {
 		unsigned npages;
 		size_t start;
-		ret = iov_iter_get_pages(ii, &ap->pages[ap->num_pages],
+		ret = iov_iter_pin_pages(ii, &ap->pages[ap->num_pages],
 					*nbytesp - nbytes,
 					max_pages - ap->num_pages,
 					&start);
@@ -1484,7 +1462,9 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter,
 		}
 
 		if (!io->async || nres < 0) {
-			fuse_release_user_pages(&ia->ap, io->should_dirty);
+			unpin_user_pages_dirty_lock(ia->ap.pages,
+						    ia->ap.num_pages,
+						    io->should_dirty);
 			fuse_io_free(ia);
 		}
 		ia = NULL;
-- 
2.35.1