path: root/fs/nfs/direct.c

/*
 * linux/fs/nfs/direct.c
 *
 * Copyright (C) 2003 by Chuck Lever <cel@netapp.com>
 *
 * High-performance uncached I/O for the Linux NFS client
 *
 * There are important applications whose performance or correctness
 * depends on uncached access to file data.  Database clusters
 * (multiple copies of the same instance running on separate hosts)
 * implement their own cache coherency protocol that subsumes file
 * system cache protocols.  Applications that process datasets
 * considerably larger than the client's memory do not always benefit
 * from a local cache.  A streaming video server, for instance, has no
 * need to cache the contents of a file.
 *
 * When an application requests uncached I/O, all read and write requests
 * are made directly to the server; data stored or fetched via these
 * requests is not cached in the Linux page cache.  The client does not
 * correct unaligned requests from applications.  All requested bytes are
 * held on permanent storage before a direct write system call returns to
 * an application.
 *
 * Solaris implements an uncached I/O facility called directio() that
 * is used for backups and sequential I/O to very large files.  Solaris
 * also supports uncaching whole NFS partitions with "-o forcedirectio,"
 * an undocumented mount option.
 *
 * Designed by Jeff Kimmel, Chuck Lever, and Trond Myklebust, with
 * help from Andrew Morton.
 *
 * 18 Dec 2001	Initial implementation for 2.4  --cel
 * 08 Jul 2002	Version for 2.4.19, with bug fixes --trondmy
 * 08 Jun 2003	Port to 2.5 APIs  --cel
 * 31 Mar 2004	Handle direct I/O without VFS support  --cel
 * 15 Sep 2004	Parallel async reads  --cel
 * 04 May 2005	support O_DIRECT with aio  --cel
 *
 */

#include <linux/errno.h>
#include <linux/sched.h>
#include <linux/kernel.h>
#include <linux/file.h>
#include <linux/pagemap.h>
#include <linux/kref.h>
#include <linux/slab.h>
#include <linux/task_io_accounting_ops.h>

#include <linux/nfs_fs.h>
#include <linux/nfs_page.h>
#include <linux/sunrpc/clnt.h>

#include <asm/uaccess.h>
#include <linux/atomic.h>

#include "internal.h"
#include "iostat.h"

#define NFSDBG_FACILITY		NFSDBG_VFS

static struct kmem_cache *nfs_direct_cachep;

/*
 * This represents a set of asynchronous requests that we're waiting on
 */
struct nfs_direct_req {
	struct kref		kref;		/* release manager */

	/* I/O parameters */
	struct nfs_open_context	*ctx;		/* file open context info */
	struct nfs_lock_context *l_ctx;		/* Lock context info */
	struct kiocb *		iocb;		/* controlling i/o request */
	struct inode *		inode;		/* target file of i/o */

	/* completion state */
	atomic_t		io_count;	/* i/os we're waiting for */
	spinlock_t		lock;		/* protect completion state */
	ssize_t			count,		/* bytes actually processed */
				error;		/* any reported error */
	struct completion	completion;	/* wait for i/o completion */

	/* commit state */
	struct list_head	rewrite_list;	/* saved nfs_write_data structs */
	struct nfs_commit_data *commit_data;	/* special write_data for commits */
	int			flags;
#define NFS_ODIRECT_DO_COMMIT		(1)	/* an unstable reply was received */
#define NFS_ODIRECT_RESCHED_WRITES	(2)	/* write verification failed */
	struct nfs_writeverf	verf;		/* unstable write verifier */
};

static void nfs_direct_write_complete(struct nfs_direct_req *dreq, struct inode *inode);
static const struct rpc_call_ops nfs_write_direct_ops;

static inline void get_dreq(struct nfs_direct_req *dreq)
{
	atomic_inc(&dreq->io_count);
}

static inline int put_dreq(struct nfs_direct_req *dreq)
{
	return atomic_dec_and_test(&dreq->io_count);
}

/**
 * nfs_direct_IO - NFS address space operation for direct I/O
 * @rw: direction (read or write)
 * @iocb: target I/O control block
 * @iov: array of vectors that define I/O buffer
 * @pos: offset in file to begin the operation
 * @nr_segs: size of iovec array
 *
 * The presence of this routine in the address space ops vector means
 * the NFS client supports direct I/O.  However, we shunt off direct
 * read and write requests before the VFS gets them, so this method
 * should never be called.
 */
ssize_t nfs_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, loff_t pos, unsigned long nr_segs)
{
	dprintk("NFS: nfs_direct_IO (%s) off/no(%Ld/%lu) EINVAL\n",
			iocb->ki_filp->f_path.dentry->d_name.name,
			(long long) pos, nr_segs);

	return -EINVAL;
}

static void nfs_direct_dirty_pages(struct page **pages, unsigned int pgbase, size_t count)
{
	unsigned int npages;
	unsigned int i;

	if (count == 0)
		return;
	pages += (pgbase >> PAGE_SHIFT);
	npages = (count + (pgbase & ~PAGE_MASK) + PAGE_SIZE - 1) >> PAGE_SHIFT;
	for (i = 0; i < npages; i++) {
		struct page *page = pages[i];
		if (!PageCompound(page))
			set_page_dirty(page);
	}
}

static void nfs_direct_release_pages(struct page **pages, unsigned int npages)
{
	unsigned int i;
	for (i = 0; i < npages; i++)
		page_cache_release(pages[i]);
}

static inline struct nfs_direct_req *nfs_direct_req_alloc(void)
{
	struct nfs_direct_req *dreq;

	dreq = kmem_cache_alloc(nfs_direct_cachep, GFP_KERNEL);
	if (!dreq)
		return NULL;

	kref_init(&dreq->kref);
	kref_get(&dreq->kref<