file.c

linux 内核源代码

/*
 *  linux/fs/nfs/file.c
 *
 *  Copyright (C) 1992  Rick Sladkey
 *
 *  Changes Copyright (C) 1994 by Florian La Roche
 *   - Do not copy data too often around in the kernel.
 *   - In nfs_file_read the return value of kmalloc wasn't checked.
 *   - Put in a better version of read look-ahead buffering. Original idea
 *     and implementation by Wai S Kok [e-mail].
 *
 *  Expire cache on write to a file by Wai S Kok (Oct 1994).
 *
 *  Total rewrite of read side for new NFS buffer cache.. Linus.
 *
 *  nfs regular file handling functions
 */

#include <linux/time.h>
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/fcntl.h>
#include <linux/stat.h>
#include <linux/nfs_fs.h>
#include <linux/nfs_mount.h>
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/pagemap.h>
#include <linux/smp_lock.h>
#include <linux/aio.h>

#include <asm/uaccess.h>
#include <asm/system.h>

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

#define NFSDBG_FACILITY		NFSDBG_FILE

static int nfs_file_open(struct inode *, struct file *);
static int nfs_file_release(struct inode *, struct file *);
static loff_t nfs_file_llseek(struct file *file, loff_t offset, int origin);
static int  nfs_file_mmap(struct file *, struct vm_area_struct *);
static ssize_t nfs_file_splice_read(struct file *filp, loff_t *ppos,
					struct pipe_inode_info *pipe,
					size_t count, unsigned int flags);
static ssize_t nfs_file_read(struct kiocb *, const struct iovec *iov,
				unsigned long nr_segs, loff_t pos);
static ssize_t nfs_file_write(struct kiocb *, const struct iovec *iov,
				unsigned long nr_segs, loff_t pos);
static int  nfs_file_flush(struct file *, fl_owner_t id);
static int  nfs_fsync(struct file *, struct dentry *dentry, int datasync);
static int nfs_check_flags(int flags);
static int nfs_lock(struct file *filp, int cmd, struct file_lock *fl);
static int nfs_flock(struct file *filp, int cmd, struct file_lock *fl);
static int nfs_setlease(struct file *file, long arg, struct file_lock **fl);

static struct vm_operations_struct nfs_file_vm_ops;

const struct file_operations nfs_file_operations = {
	.llseek		= nfs_file_llseek,
	.read		= do_sync_read,
	.write		= do_sync_write,
	.aio_read	= nfs_file_read,
	.aio_write	= nfs_file_write,
	.mmap		= nfs_file_mmap,
	.open		= nfs_file_open,
	.flush		= nfs_file_flush,
	.release	= nfs_file_release,
	.fsync		= nfs_fsync,
	.lock		= nfs_lock,
	.flock		= nfs_flock,
	.splice_read	= nfs_file_splice_read,
	.check_flags	= nfs_check_flags,
	.setlease	= nfs_setlease,
};

const struct inode_operations nfs_file_inode_operations = {
	.permission	= nfs_permission,
	.getattr	= nfs_getattr,
	.setattr	= nfs_setattr,
};

#ifdef CONFIG_NFS_V3
const struct inode_operations nfs3_file_inode_operations = {
	.permission	= nfs_permission,
	.getattr	= nfs_getattr,
	.setattr	= nfs_setattr,
	.listxattr	= nfs3_listxattr,
	.getxattr	= nfs3_getxattr,
	.setxattr	= nfs3_setxattr,
	.removexattr	= nfs3_removexattr,
};
#endif  /* CONFIG_NFS_v3 */

/* Hack for future NFS swap support */
#ifndef IS_SWAPFILE
# define IS_SWAPFILE(inode)	(0)
#endif

static int nfs_check_flags(int flags)
{
	if ((flags & (O_APPEND | O_DIRECT)) == (O_APPEND | O_DIRECT))
		return -EINVAL;

	return 0;
}

/*
 * Open file
 */
static int
nfs_file_open(struct inode *inode, struct file *filp)
{
	int res;

	res = nfs_check_flags(filp->f_flags);
	if (res)
		return res;

	nfs_inc_stats(inode, NFSIOS_VFSOPEN);
	lock_kernel();
	res = NFS_PROTO(inode)->file_open(inode, filp);
	unlock_kernel();
	return res;
}

static int
nfs_file_release(struct inode *inode, struct file *filp)
{
	/* Ensure that dirty pages are flushed out with the right creds */
	if (filp->f_mode & FMODE_WRITE)
		nfs_wb_all(filp->f_path.dentry->d_inode);
	nfs_inc_stats(inode, NFSIOS_VFSRELEASE);
	return NFS_PROTO(inode)->file_release(inode, filp);
}

/**
 * nfs_revalidate_size - Revalidate the file size
 * @inode - pointer to inode struct
 * @file - pointer to struct file
 *
 * Revalidates the file length. This is basically a wrapper around
 * nfs_revalidate_inode() that takes into account the fact that we may
 * have cached writes (in which case we don't care about the server's
 * idea of what the file length is), or O_DIRECT (in which case we
 * shouldn't trust the cache).
 */
static int nfs_revalidate_file_size(struct inode *inode, struct file *filp)
{
	struct nfs_server *server = NFS_SERVER(inode);
	struct nfs_inode *nfsi = NFS_I(inode);

	if (server->flags & NFS_MOUNT_NOAC)
		goto force_reval;
	if (filp->f_flags & O_DIRECT)
		goto force_reval;
	if (nfsi->npages != 0)
		return 0;
	if (!(nfsi->cache_validity & NFS_INO_REVAL_PAGECACHE) && !nfs_attribute_timeout(inode))
		return 0;
force_reval:
	return __nfs_revalidate_inode(server, inode);
}

static loff_t nfs_file_llseek(struct file *filp, loff_t offset, int origin)
{
	/* origin == SEEK_END => we must revalidate the cached file length */
	if (origin == SEEK_END) {
		struct inode *inode = filp->f_mapping->host;
		int retval = nfs_revalidate_file_size(inode, filp);
		if (retval < 0)
			return (loff_t)retval;
	}
	return remote_llseek(filp, offset, origin);
}

/*
 * Helper for nfs_file_flush() and nfs_fsync()
 *
 * Notice that it clears the NFS_CONTEXT_ERROR_WRITE before synching to
 * disk, but it retrieves and clears ctx->error after synching, despite
 * the two being set at the same time in nfs_context_set_write_error().
 * This is because the former is used to notify the _next_ call to
 * nfs_file_write() that a write error occured, and hence cause it to
 * fall back to doing a synchronous write.
 */
static int nfs_do_fsync(struct nfs_open_context *ctx, struct inode *inode)
{
	int have_error, status;
	int ret = 0;

	have_error = test_and_clear_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags);
	status = nfs_wb_all(inode);
	have_error |= test_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags);
	if (have_error)
		ret = xchg(&ctx->error, 0);
	if (!ret)
		ret = status;
	return ret;
}

/*
 * Flush all dirty pages, and check for write errors.
 *
 */
static int
nfs_file_flush(struct file *file, fl_owner_t id)
{
	struct nfs_open_context *ctx = nfs_file_open_context(file);
	struct inode	*inode = file->f_path.dentry->d_inode;
	int		status;

	dfprintk(VFS, "nfs: flush(%s/%ld)\n", inode->i_sb->s_id, inode->i_ino);

	if ((file->f_mode & FMODE_WRITE) == 0)
		return 0;
	nfs_inc_stats(inode, NFSIOS_VFSFLUSH);

	/* Ensure that data+attribute caches are up to date after close() */
	status = nfs_do_fsync(ctx, inode);
	if (!status)
		nfs_revalidate_inode(NFS_SERVER(inode), inode);
	return status;
}

static ssize_t
nfs_file_read(struct kiocb *iocb, const struct iovec *iov,
		unsigned long nr_segs, loff_t pos)
{
	struct dentry * dentry = iocb->ki_filp->f_path.dentry;
	struct inode * inode = dentry->d_inode;
	ssize_t result;
	size_t count = iov_length(iov, nr_segs);

#ifdef CONFIG_NFS_DIRECTIO
	if (iocb->ki_filp->f_flags & O_DIRECT)
		return nfs_file_direct_read(iocb, iov, nr_segs, pos);
#endif

	dfprintk(VFS, "nfs: read(%s/%s, %lu@%lu)\n",
		dentry->d_parent->d_name.name, dentry->d_name.name,
		(unsigned long) count, (unsigned long) pos);

	result = nfs_revalidate_mapping(inode, iocb->ki_filp->f_mapping);
	nfs_add_stats(inode, NFSIOS_NORMALREADBYTES, count);
	if (!result)
		result = generic_file_aio_read(iocb, iov, nr_segs, pos);
	return result;
}

static ssize_t
nfs_file_splice_read(struct file *filp, loff_t *ppos,
		     struct pipe_inode_info *pipe, size_t count,
		     unsigned int flags)
{
	struct dentry *dentry = filp->f_path.dentry;
	struct inode *inode = dentry->d_inode;
	ssize_t res;

	dfprintk(VFS, "nfs: splice_read(%s/%s, %lu@%Lu)\n",
		dentry->d_parent->d_name.name, dentry->d_name.name,
		(unsigned long) count, (unsigned long long) *ppos);

	res = nfs_revalidate_mapping(inode, filp->f_mapping);
	if (!res)
		res = generic_file_splice_read(filp, ppos, pipe, count, flags);
	return res;
}

static int
nfs_file_mmap(struct file * file, struct vm_area_struct * vma)
{
	struct dentry *dentry = file->f_path.dentry;
	struct inode *inode = dentry->d_inode;
	int	status;

	dfprintk(VFS, "nfs: mmap(%s/%s)\n",
		dentry->d_parent->d_name.name, dentry->d_name.name);

	status = nfs_revalidate_mapping(inode, file->f_mapping);
	if (!status) {
		vma->vm_ops = &nfs_file_vm_ops;
		vma->vm_flags |= VM_CAN_NONLINEAR;
		file_accessed(file);
	}
	return status;
}

/*
 * Flush any dirty pages for this process, and check for write errors.
 * The return status from this call provides a reliable indication of
 * whether any write errors occurred for this process.
 */
static int
nfs_fsync(struct file *file, struct dentry *dentry, int datasync)
{
	struct nfs_open_context *ctx = nfs_file_open_context(file);
	struct inode *inode = dentry->d_inode;

	dfprintk(VFS, "nfs: fsync(%s/%ld)\n", inode->i_sb->s_id, inode->i_ino);

	nfs_inc_stats(inode, NFSIOS_VFSFSYNC);
	return nfs_do_fsync(ctx, inode);
}

/*
 * This does the "real" work of the write. We must allocate and lock the
 * page to be sent back to the generic routine, which then copies the
 * data from user space.
 *
 * If the writer ends up delaying the write, the writer needs to
 * increment the page use counts until he is done with the page.
 */
static int nfs_write_begin(struct file *file, struct address_space *mapping,
			loff_t pos, unsigned len, unsigned flags,
			struct page **pagep, void **fsdata)
{
	int ret;
	pgoff_t index;
	struct page *page;
	index = pos >> PAGE_CACHE_SHIFT;

	page = __grab_cache_page(mapping, index);
	if (!page)
		return -ENOMEM;
	*pagep = page;

	ret = nfs_flush_incompatible(file, page);
	if (ret) {
		unlock_page(page);
		page_cache_release(page);
	}
	return ret;