Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.37 as permitted sender) client-ip=23.128.96.37;
From:   David Howells <dhowells@redhat.com>
To:     Jeff Layton <jlayton@kernel.org>, Steve French <smfrench@gmail.com>
Cc:     David Howells <dhowells@redhat.com>,
        Matthew Wilcox <willy@infradead.org>,
        Marc Dionne <marc.dionne@auristor.com>,
        Paulo Alcantara <pc@manguebit.com>,
        Shyam Prasad N <sprasad@microsoft.com>,
        Tom Talpey <tom@talpey.com>,
        Dominique Martinet <asmadeus@codewreck.org>,
        Ilya Dryomov <idryomov@gmail.com>,
        Christian Brauner <christian@brauner.io>,
        linux-cachefs@redhat.com, linux-afs@lists.infradead.org,
        linux-cifs@vger.kernel.org, linux-nfs@vger.kernel.org,
        ceph-devel@vger.kernel.org, v9fs@lists.linux.dev,
        linux-fsdevel@vger.kernel.org, linux-mm@kvack.org,
        netdev@vger.kernel.org, linux-kernel@vger.kernel.org
Subject: [PATCH v2 07/51] netfs: Implement unbuffered/DIO vs buffered I/O locking
Date:   Fri, 17 Nov 2023 21:14:59 +0000
Message-ID: <20231117211544.1740466-8-dhowells@redhat.com>
In-Reply-To: <20231117211544.1740466-1-dhowells@redhat.com>
References: <20231117211544.1740466-1-dhowells@redhat.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

Borrow NFS's direct-vs-buffered I/O locking into netfslib.  Similar code is
also used in ceph.

Modify it to have the correct checker annotations for i_rwsem lock
acquisition/release and to return -ERESTARTSYS if waits are interrupted.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 fs/netfs/Makefile     |   1 +
 fs/netfs/locking.c    | 215 ++++++++++++++++++++++++++++++++++++++++++
 include/linux/netfs.h |  10 ++
 3 files changed, 226 insertions(+)
 create mode 100644 fs/netfs/locking.c

diff --git a/fs/netfs/Makefile b/fs/netfs/Makefile
index cd22554d9048..647ce1935674 100644
--- a/fs/netfs/Makefile
+++ b/fs/netfs/Makefile
@@ -4,6 +4,7 @@ netfs-y := \
 	buffered_read.o \
 	io.o \
 	iterator.o \
+	locking.o \
 	main.o \
 	misc.o \
 	objects.o
diff --git a/fs/netfs/locking.c b/fs/netfs/locking.c
new file mode 100644
index 000000000000..58e0f48394c5
--- /dev/null
+++ b/fs/netfs/locking.c
@@ -0,0 +1,215 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * I/O and data path helper functionality.
+ *
+ * Borrowed from NFS Copyright (c) 2016 Trond Myklebust
+ */
+
+#include <linux/kernel.h>
+#include <linux/netfs.h>
+
+/*
+ * inode_dio_wait_interruptible - wait for outstanding DIO requests to finish
+ * @inode: inode to wait for
+ *
+ * Waits for all pending direct I/O requests to finish so that we can
+ * proceed with a truncate or equivalent operation.
+ *
+ * Must be called under a lock that serializes taking new references
+ * to i_dio_count, usually by inode->i_mutex.
+ */
+static int inode_dio_wait_interruptible(struct inode *inode)
+{
+	if (!atomic_read(&inode->i_dio_count))
+		return 0;
+
+	wait_queue_head_t *wq = bit_waitqueue(&inode->i_state, __I_DIO_WAKEUP);
+	DEFINE_WAIT_BIT(q, &inode->i_state, __I_DIO_WAKEUP);
+
+	for (;;) {
+		prepare_to_wait(wq, &q.wq_entry, TASK_INTERRUPTIBLE);
+		if (!atomic_read(&inode->i_dio_count))
+			break;
+		if (signal_pending(current))
+			break;
+		schedule();
+	}
+	finish_wait(wq, &q.wq_entry);
+
+	return atomic_read(&inode->i_dio_count) ? -ERESTARTSYS : 0;
+}
+
+/* Call with exclusively locked inode->i_rwsem */
+static int netfs_block_o_direct(struct netfs_inode *ictx)
+{
+	if (!test_bit(NETFS_ICTX_ODIRECT, &ictx->flags))
+		return 0;
+	clear_bit(NETFS_ICTX_ODIRECT, &ictx->flags);
+	return inode_dio_wait_interruptible(&ictx->inode);
+}
+
+/**
+ * netfs_start_io_read - declare the file is being used for buffered reads
+ * @inode: file inode
+ *
+ * Declare that a buffered read operation is about to start, and ensure
+ * that we block all direct I/O.
+ * On exit, the function ensures that the NETFS_ICTX_ODIRECT flag is unset,
+ * and holds a shared lock on inode->i_rwsem to ensure that the flag
+ * cannot be changed.
+ * In practice, this means that buffered read operations are allowed to
+ * execute in parallel, thanks to the shared lock, whereas direct I/O
+ * operations need to wait to grab an exclusive lock in order to set
+ * NETFS_ICTX_ODIRECT.
+ * Note that buffered writes and truncates both take a write lock on
+ * inode->i_rwsem, meaning that those are serialised w.r.t. the reads.
+ */
+int netfs_start_io_read(struct inode *inode)
+	__acquires(inode->i_rwsem)
+{
+	struct netfs_inode *ictx = netfs_inode(inode);
+
+	/* Be an optimist! */
+	if (down_read_interruptible(&inode->i_rwsem) < 0)
+		return -ERESTARTSYS;
+	if (test_bit(NETFS_ICTX_ODIRECT, &ictx->flags) == 0)
+		return 0;
+	up_read(&inode->i_rwsem);
+
+	/* Slow path.... */
+	if (down_write_killable(&inode->i_rwsem) < 0)
+		return -ERESTARTSYS;
+	if (netfs_block_o_direct(ictx) < 0) {
+		up_write(&inode->i_rwsem);
+		return -ERESTARTSYS;
+	}
+	downgrade_write(&inode->i_rwsem);
+	return 0;
+}
+EXPORT_SYMBOL(netfs_start_io_read);
+
+/**
+ * netfs_end_io_read - declare that the buffered read operation is done
+ * @inode: file inode
+ *
+ * Declare that a buffered read operation is done, and release the shared
+ * lock on inode->i_rwsem.
+ */
+void netfs_end_io_read(struct inode *inode)
+	__releases(inode->i_rwsem)
+{
+	up_read(&inode->i_rwsem);
+}
+EXPORT_SYMBOL(netfs_end_io_read);
+
+/**
+ * netfs_start_io_write - declare the file is being used for buffered writes
+ * @inode: file inode
+ *
+ * Declare that a buffered read operation is about to start, and ensure
+ * that we block all direct I/O.
+ */
+int netfs_start_io_write(struct inode *inode)
+	__acquires(inode->i_rwsem)
+{
+	struct netfs_inode *ictx = netfs_inode(inode);
+
+	if (down_write_killable(&inode->i_rwsem) < 0)
+		return -ERESTARTSYS;
+	if (netfs_block_o_direct(ictx) < 0) {
+		up_write(&inode->i_rwsem);
+		return -ERESTARTSYS;
+	}
+	return 0;
+}
+EXPORT_SYMBOL(netfs_start_io_write);
+
+/**
+ * netfs_end_io_write - declare that the buffered write operation is done
+ * @inode: file inode
+ *
+ * Declare that a buffered write operation is done, and release the
+ * lock on inode->i_rwsem.
+ */
+void netfs_end_io_write(struct inode *inode)
+	__releases(inode->i_rwsem)
+{
+	up_write(&inode->i_rwsem);
+}
+EXPORT_SYMBOL(netfs_end_io_write);
+
+/* Call with exclusively locked inode->i_rwsem */
+static int netfs_block_buffered(struct inode *inode)
+{
+	struct netfs_inode *ictx = netfs_inode(inode);
+	int ret;
+
+	if (!test_bit(NETFS_ICTX_ODIRECT, &ictx->flags)) {
+		set_bit(NETFS_ICTX_ODIRECT, &ictx->flags);
+		if (inode->i_mapping->nrpages != 0) {
+			unmap_mapping_range(inode->i_mapping, 0, 0, 0);
+			ret = filemap_fdatawait(inode->i_mapping);
+			if (ret < 0) {
+				clear_bit(NETFS_ICTX_ODIRECT, &ictx->flags);
+				return ret;
+			}
+		}
+	}
+	return 0;
+}
+
+/**
+ * netfs_start_io_direct - declare the file is being used for direct i/o
+ * @inode: file inode
+ *
+ * Declare that a direct I/O operation is about to start, and ensure
+ * that we block all buffered I/O.
+ * On exit, the function ensures that the NETFS_ICTX_ODIRECT flag is set,
+ * and holds a shared lock on inode->i_rwsem to ensure that the flag
+ * cannot be changed.
+ * In practice, this means that direct I/O operations are allowed to
+ * execute in parallel, thanks to the shared lock, whereas buffered I/O
+ * operations need to wait to grab an exclusive lock in order to clear
+ * NETFS_ICTX_ODIRECT.
+ * Note that buffered writes and truncates both take a write lock on
+ * inode->i_rwsem, meaning that those are serialised w.r.t. O_DIRECT.
+ */
+int netfs_start_io_direct(struct inode *inode)
+	__acquires(inode->i_rwsem)
+{
+	struct netfs_inode *ictx = netfs_inode(inode);
+	int ret;
+
+	/* Be an optimist! */
+	if (down_read_interruptible(&inode->i_rwsem) < 0)
+		return -ERESTARTSYS;
+	if (test_bit(NETFS_ICTX_ODIRECT, &ictx->flags) != 0)
+		return 0;
+	up_read(&inode->i_rwsem);
+
+	/* Slow path.... */
+	if (down_write_killable(&inode->i_rwsem) < 0)
+		return -ERESTARTSYS;
+	ret = netfs_block_buffered(inode);
+	if (ret < 0) {
+		up_write(&inode->i_rwsem);
+		return ret;
+	}
+	downgrade_write(&inode->i_rwsem);
+	return 0;
+}
+EXPORT_SYMBOL(netfs_start_io_direct);
+
+/**
+ * netfs_end_io_direct - declare that the direct i/o operation is done
+ * @inode: file inode
+ *
+ * Declare that a direct I/O operation is done, and release the shared
+ * lock on inode->i_rwsem.
+ */
+void netfs_end_io_direct(struct inode *inode)
+	__releases(inode->i_rwsem)
+{
+	up_read(&inode->i_rwsem);
+}
+EXPORT_SYMBOL(netfs_end_io_direct);
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index 6e662832c3ae..18e3d8b53646 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -131,6 +131,8 @@ struct netfs_inode {
 	loff_t			remote_i_size;	/* Size of the remote file */
 	loff_t			zero_point;	/* Size after which we assume there's no data
 						 * on the server */
+	unsigned long		flags;
+#define NETFS_ICTX_ODIRECT	0		/* The file has DIO in progress */
 };
 
 /*
@@ -312,6 +314,13 @@ ssize_t netfs_extract_user_iter(struct iov_iter *orig, size_t orig_len,
 				struct iov_iter *new,
 				iov_iter_extraction_t extraction_flags);
 
+int netfs_start_io_read(struct inode *inode);
+void netfs_end_io_read(struct inode *inode);
+int netfs_start_io_write(struct inode *inode);
+void netfs_end_io_write(struct inode *inode);
+int netfs_start_io_direct(struct inode *inode);
+void netfs_end_io_direct(struct inode *inode);
+
 /**
  * netfs_inode - Get the netfs inode context from the inode
  * @inode: The inode to query
@@ -338,6 +347,7 @@ static inline void netfs_inode_init(struct netfs_inode *ctx,
 	ctx->ops = ops;
 	ctx->remote_i_size = i_size_read(&ctx->inode);
 	ctx->zero_point = ctx->remote_i_size;
+	ctx->flags = 0;
 #if IS_ENABLED(CONFIG_FSCACHE)
 	ctx->cache = NULL;
 #endif