aboutsummaryrefslogtreecommitdiffstats
path: root/CREDITS
Commit message (Expand)AuthorAge
* remove the OSS trident driverAdrian Bunk2008-07-24
* Don't list my old OSDL mailing address in CREDITS fileLinus Torvalds2008-07-21
* Miguel Ojeda has movedMiguel Ojeda2008-07-04
* pcsp - Don't build pcspkr when snd-pcsp is enabledStas Sergeev2008-04-24
* MAINTAINERS: remove Adam Fritzler, remove his email address in other sourcesJoe Perches2008-02-03
* remove obsolete contact information from CREDITSAdrian Bunk2008-02-03
* [CAN]: Add maintainer entriesOliver Hartkopp2008-01-28
* Convert files to UTF-8 and some cleanupsJan Engelhardt2007-10-19
* Merge git://git.kernel.org/pub/scm/linux/kernel/git/sam/kbuildLinus Torvalds2007-10-16
|\
| * kbuild: move Kai Germaschewski to CREDITSSam Ravnborg2007-10-12
* | Merge branch 'linus' of master.kernel.org:/pub/scm/linux/kernel/git/perex/alsaLinus Torvalds2007-10-16
|\ \
| * | [ALSA] Changed Jaroslav Kysela's e-mail from perex@suse.cz to perex@perex.czJaroslav Kysela2007-10-16
| |/
* / CREDITS: correct Mikael Pettersson's URLMikael Pettersson2007-10-16
|/
* [RT2x00]: add driver for Ralink wireless hardwareIvo van Doorn2007-10-10
* Slab maintainer & Credits updateChristoph Lameter2007-07-26
* [ALSA] Update Claudio's CREDITS informationClaudio Matsuoka2007-07-20
* Fix up CREDIT entry orderingLi Yang2007-06-20
* further UTF-8 fixes and name correctionDavid Woodhouse2007-05-11
* Convert the toplevel files CREDITS and MAINTAINERS to UTF-8.John Anthony Kazos Jr2007-05-09
* Add webpages' URL and summarize 3 lines.Miguel Ojeda2007-05-08
* proc: maps protectionKees Cook2007-05-08
* [PATCH] x86-64: Change my email addressAndi Kleen2007-05-02
* USB: update MAINAINERS and CREDITS for Freescale USB driverLi Yang2007-04-27
* [WIRELESS] cfg80211: New wireless config infrastructure.Johannes Berg2007-04-26
* [CREDITS]: Update Arnaldo entryArnaldo Carvalho de Melo2007-04-26
* [PATCH] CREDITS: update my email addressMikael Pettersson2007-02-26
* [PATCH] drivers: add LCD supportMiguel Ojeda Sandonis2007-02-11
* Change Linus' email address tooLinus Torvalds2007-01-23
* [PATCH] Update CREDITS and MAINTAINERS entries for Lennert BuytenhekLennert Buytenhek2006-12-30
* [PATCH] Generic HID layer - buildJiri Kosina2006-12-08
* [TCP]: MD5 Signature Option (RFC2385) support.YOSHIFUJI Hideaki2006-12-03
* [PATCH] Update my CREDITS entryDavid Weinehall2006-11-17
* [PATCH] Tigran has movedTigran Aivazian2006-11-08
* Merge git://git.kernel.org/pub/scm/linux/kernel/git/steve/gfs2-2.6Linus Torvalds2006-10-04
|\
| * Merge branch 'master' into gfs2Steven Whitehouse2006-10-02
| |\
| * \ [GFS2] Fix up merge of Linus' kernel into GFS2Steven Whitehouse2006-09-25
| |\ \
| * \ \ Merge branch 'master' into gfs2Steven Whitehouse2006-08-29
| |\ \ \
| * \ \ \ Merge branch 'master'Steven Whitehouse2006-07-17
| |\ \ \ \
| * \ \ \ \ Merge rsync://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6Steven Whitehouse2006-07-03
| |\ \ \ \ \
| * \ \ \ \ \ Merge branch 'master'Steven Whitehouse2006-05-25
| |\ \ \ \ \ \
| * \ \ \ \ \ \ Merge branch 'master'Steven Whitehouse2006-05-12
| |\ \ \ \ \ \ \
| * | | | | | | | [GFS2] Update my Credits file entrySteven Whitehouse2006-04-28
* | | | | | | | | [PATCH] RCU: CREDITS and MAINTAINERSJosh Triplett2006-10-04
* | | | | | | | | Add missing maintainer countries in CREDITSSamuel Tardieu2006-10-03
* | | | | | | | | Michal Wronski: update contact infoMichal Wronski2006-10-03
* | | | | | | | | [PATCH] Add Pekka to CREDITSPekka Enberg2006-10-03
| |_|_|_|_|_|_|/ |/| | | | | | |
* | | | | | | | [PATCH] /sys/modules: allow full length section namesIan S. Nelson2006-09-29
* | | | | | | | [PATCH] Small update to CREDITSJesper Juhl2006-09-29
| |_|_|_|_|_|/ |/| | | | | |
* | | | | | | [NetLabel]: documentationPaul Moore2006-09-22
| |_|_|_|_|/ |/| | | | |
* | | | | | [DCCP]: Update contact details and copyrightIan McDonald2006-08-26
| |_|_|_|/ |/| | | |
n712'>712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890
/*
 *  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 elekokws@ee.nus.sg.
 *
 *  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/pagemap.h>
#include <linux/aio.h>
#include <linux/gfp.h>
#include <linux/swap.h>

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

#include "delegation.h"
#include "internal.h"
#include "iostat.h"
#include "fscache.h"
#include "pnfs.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_splice_write(struct pipe_inode_info *pipe,
					struct file *filp, loff_t *ppos,
					size_t count, unsigned int flags);
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_file_fsync(struct file *, 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 const 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_file_fsync,
	.lock		= nfs_lock,
	.flock		= nfs_flock,
	.splice_read	= nfs_file_splice_read,
	.splice_write	= nfs_file_splice_write,
	.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;

	dprintk("NFS: open file(%s/%s)\n",
			filp->f_path.dentry->d_parent->d_name.name,
			filp->f_path.dentry->d_name.name);

	nfs_inc_stats(inode, NFSIOS_VFSOPEN);
	res = nfs_check_flags(filp->f_flags);
	if (res)
		return res;

	res = nfs_open(inode, filp);
	return res;
}

static int
nfs_file_release(struct inode *inode, struct file *filp)
{
	struct dentry *dentry = filp->f_path.dentry;

	dprintk("NFS: release(%s/%s)\n",
			dentry->d_parent->d_name.name,
			dentry->d_name.name);

	nfs_inc_stats(inode, NFSIOS_VFSRELEASE);
	return nfs_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 (nfs_have_delegated_attributes(inode))
		goto out_noreval;

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

static loff_t nfs_file_llseek(struct file *filp, loff_t offset, int origin)
{
	loff_t loff;

	dprintk("NFS: llseek file(%s/%s, %lld, %d)\n",
			filp->f_path.dentry->d_parent->d_name.name,
			filp->f_path.dentry->d_name.name,
			offset, 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;

		spin_lock(&inode->i_lock);
		loff = generic_file_llseek_unlocked(filp, offset, origin);
		spin_unlock(&inode->i_lock);
	} else
		loff = generic_file_llseek_unlocked(filp, offset, origin);
	return loff;
}

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

	dprintk("NFS: flush(%s/%s)\n",
			dentry->d_parent->d_name.name,
			dentry->d_name.name);

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

	/* Flush writes to the server and return any errors */
	return vfs_fsync(file, 0);
}

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);

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

	dprintk("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);
	if (!result) {
		result = generic_file_aio_read(iocb, iov, nr_segs, pos);
		if (result > 0)
			nfs_add_stats(inode, NFSIOS_NORMALREADBYTES, result);
	}
	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;

	dprintk("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);
		if (res > 0)
			nfs_add_stats(inode, NFSIOS_NORMALREADBYTES, res);
	}
	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;

	dprintk("NFS: mmap(%s/%s)\n",
		dentry->d_parent->d_name.name, dentry->d_name.name);

	/* Note: generic_file_mmap() returns ENOSYS on nommu systems
	 *       so we call that before revalidating the mapping
	 */
	status = generic_file_mmap(file, vma);
	if (!status) {
		vma->vm_ops = &nfs_file_vm_ops;
		status = nfs_revalidate_mapping(inode, file->f_mapping);
	}
	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.
 *
 * 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_file_fsync(struct file *file, int datasync)
{
	struct dentry *dentry = file->f_path.dentry;
	struct nfs_open_context *ctx = nfs_file_open_context(file);
	struct inode *inode = dentry->d_inode;
	int have_error, status;
	int ret = 0;


	dprintk("NFS: fsync file(%s/%s) datasync %d\n",
			dentry->d_parent->d_name.name, dentry->d_name.name,
			datasync);

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

/*
 * Decide whether a read/modify/write cycle may be more efficient
 * then a modify/write/read cycle when writing to a page in the
 * page cache.
 *
 * The modify/write/read cycle may occur if a page is read before
 * being completely filled by the writer.  In this situation, the
 * page must be completely written to stable storage on the server
 * before it can be refilled by reading in the page from the server.
 * This can lead to expensive, small, FILE_SYNC mode writes being
 * done.
 *
 * It may be more efficient to read the page first if the file is
 * open for reading in addition to writing, the page is not marked
 * as Uptodate, it is not dirty or waiting to be committed,
 * indicating that it was previously allocated and then modified,
 * that there were valid bytes of data in that range of the file,
 * and that the new data won't completely replace the old data in
 * that range of the file.
 */
static int nfs_want_read_modify_write(struct file *file, struct page *page,
			loff_t pos, unsigned len)
{
	unsigned int pglen = nfs_page_length(page);
	unsigned int offset = pos & (PAGE_CACHE_SIZE - 1);
	unsigned int end = offset + len;

	if ((file->f_mode & FMODE_READ) &&	/* open for read? */
	    !PageUptodate(page) &&		/* Uptodate? */
	    !PagePrivate(page) &&		/* i/o request already? */
	    pglen &&				/* valid bytes of file? */
	    (end < pglen || offset))		/* replace all valid bytes? */
		return 1;
	return 0;
}

/*
 * 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 = pos >> PAGE_CACHE_SHIFT;
	struct page *page;
	int once_thru = 0;

	dfprintk(PAGECACHE, "NFS: write_begin(%s/%s(%ld), %u@%lld)\n",
		file->f_path.dentry->d_parent->d_name.name,
		file->f_path.dentry->d_name.name,
		mapping->host->i_ino, len, (long long) pos);

	pnfs_update_layout(mapping->host,
			   nfs_file_open_context(file),
			   IOMODE_RW);

start:
	/*
	 * Prevent starvation issues if someone is doing a consistency
	 * sync-to-disk
	 */
	ret = wait_on_bit(&NFS_I(mapping->host)->flags, NFS_INO_FLUSHING,
			nfs_wait_bit_killable, TASK_KILLABLE);
	if (ret)
		return ret;

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

	ret = nfs_flush_incompatible(file, page);
	if (ret) {
		unlock_page(page);
		page_cache_release(page);
	} else if (!once_thru &&
		   nfs_want_read_modify_write(file, page, pos, len)) {
		once_thru = 1;
		ret = nfs_readpage(file, page);
		page_cache_release(page);
		if (!ret)
			goto start;
	}
	return ret;
}

static int nfs_write_end(struct file *file, struct address_space *mapping,
			loff_t pos, unsigned len, unsigned copied,
			struct page *page, void *fsdata)
{
	unsigned offset = pos & (PAGE_CACHE_SIZE - 1);
	int status;

	dfprintk(PAGECACHE, "NFS: write_end(%s/%s(%ld), %u@%lld)\n",
		file->f_path.dentry->d_parent->d_name.name,
		file->f_path.dentry->d_name.name,
		mapping->host->i_ino, len, (long long) pos);

	/*
	 * Zero any uninitialised parts of the page, and then mark the page
	 * as up to date if it turns out that we're extending the file.
	 */
	if (!PageUptodate(page)) {
		unsigned pglen = nfs_page_length(page);
		unsigned end = offset + len;

		if (pglen == 0) {
			zero_user_segments(page, 0, offset,
					end, PAGE_CACHE_SIZE);
			SetPageUptodate(page);
		} else if (end >= pglen) {
			zero_user_segment(page, end, PAGE_CACHE_SIZE);
			if (offset == 0)
				SetPageUptodate(page);
		} else
			zero_user_segment(page, pglen, PAGE_CACHE_SIZE);
	}

	status = nfs_updatepage(file, page, offset, copied);

	unlock_page(page);
	page_cache_release(page);

	if (status < 0)
		return status;
	return copied;
}

/*
 * Partially or wholly invalidate a page
 * - Release the private state associated with a page if undergoing complete
 *   page invalidation
 * - Called if either PG_private or PG_fscache is set on the page
 * - Caller holds page lock
 */
static void nfs_invalidate_page(struct page *page, unsigned long offset)
{
	dfprintk(PAGECACHE, "NFS: invalidate_page(%p, %lu)\n", page, offset);

	if (offset != 0)
		return;
	/* Cancel any unstarted writes on this page */
	nfs_wb_page_cancel(page->mapping->host, page);

	nfs_fscache_invalidate_page(page, page->mapping->host);
}

/*
 * Attempt to release the private state associated with a page
 * - Called if either PG_private or PG_fscache is set on the page
 * - Caller holds page lock
 * - Return true (may release page) or false (may not)
 */
static int nfs_release_page(struct page *page, gfp_t gfp)
{
	struct address_space *mapping = page->mapping;

	dfprintk(PAGECACHE, "NFS: release_page(%p)\n", page);

	/* Only do I/O if gfp is a superset of GFP_KERNEL */
	if (mapping && (gfp & GFP_KERNEL) == GFP_KERNEL) {
		int how = FLUSH_SYNC;

		/* Don't let kswapd deadlock waiting for OOM RPC calls */
		if (current_is_kswapd())
			how = 0;
		nfs_commit_inode(mapping->host, how);
	}
	/* If PagePrivate() is set, then the page is not freeable */
	if (PagePrivate(page))
		return 0;
	return nfs_fscache_release_page(page, gfp);
}

/*
 * Attempt to clear the private state associated with a page when an error
 * occurs that requires the cached contents of an inode to be written back or
 * destroyed
 * - Called if either PG_private or fscache is set on the page
 * - Caller holds page lock
 * - Return 0 if successful, -error otherwise
 */
static int nfs_launder_page(struct page *page)
{
	struct inode *inode = page->mapping->host;
	struct nfs_inode *nfsi = NFS_I(inode);

	dfprintk(PAGECACHE, "NFS: launder_page(%ld, %llu)\n",
		inode->i_ino, (long long)page_offset(page));

	nfs_fscache_wait_on_page_write(nfsi, page);
	return nfs_wb_page(inode, page);
}

const struct address_space_operations nfs_file_aops = {
	.readpage = nfs_readpage,
	.readpages = nfs_readpages,
	.set_page_dirty = __set_page_dirty_nobuffers,
	.writepage = nfs_writepage,
	.writepages = nfs_writepages,
	.write_begin = nfs_write_begin,
	.write_end = nfs_write_end,
	.invalidatepage = nfs_invalidate_page,
	.releasepage = nfs_release_page,
	.direct_IO = nfs_direct_IO,
	.migratepage = nfs_migrate_page,
	.launder_page = nfs_launder_page,
	.error_remove_page = generic_error_remove_page,
};

/*
 * Notification that a PTE pointing to an NFS page is about to be made
 * writable, implying that someone is about to modify the page through a
 * shared-writable mapping
 */
static int nfs_vm_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
{
	struct page *page = vmf->page;
	struct file *filp = vma->vm_file;
	struct dentry *dentry = filp->f_path.dentry;
	unsigned pagelen;
	int ret = VM_FAULT_NOPAGE;
	struct address_space *mapping;

	dfprintk(PAGECACHE, "NFS: vm_page_mkwrite(%s/%s(%ld), offset %lld)\n",
		dentry->d_parent->d_name.name, dentry->d_name.name,
		filp->f_mapping->host->i_ino,
		(long long)page_offset(page));

	/* make sure the cache has finished storing the page */
	nfs_fscache_wait_on_page_write(NFS_I(dentry->d_inode), page);

	lock_page(page);
	mapping = page->mapping;
	if (mapping != dentry->d_inode->i_mapping)
		goto out_unlock;

	pagelen = nfs_page_length(page);
	if (pagelen == 0)
		goto out_unlock;

	ret = VM_FAULT_LOCKED;
	if (nfs_flush_incompatible(filp, page) == 0 &&
	    nfs_updatepage(filp, page, 0, pagelen) == 0)
		goto out;

	ret = VM_FAULT_SIGBUS;
out_unlock:
	unlock_page(page);
out:
	return ret;
}

static const struct vm_operations_struct nfs_file_vm_ops = {
	.fault = filemap_fault,
	.page_mkwrite = nfs_vm_page_mkwrite,
};

static int nfs_need_sync_write(struct file *filp, struct inode *inode)
{
	struct nfs_open_context *ctx;

	if (IS_SYNC(inode) || (filp->f_flags & O_DSYNC))
		return 1;
	ctx = nfs_file_open_context(filp);
	if (test_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags))
		return 1;
	return 0;
}

static ssize_t nfs_file_write(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;
	unsigned long written = 0;
	ssize_t result;
	size_t count = iov_length(iov, nr_segs);

	if (iocb->ki_filp->f_flags & O_DIRECT)
		return nfs_file_direct_write(iocb, iov, nr_segs, pos);

	dprintk("NFS: write(%s/%s, %lu@%Ld)\n",
		dentry->d_parent->d_name.name, dentry->d_name.name,
		(unsigned long) count, (long long) pos);

	result = -EBUSY;
	if (IS_SWAPFILE(inode))
		goto out_swapfile;
	/*
	 * O_APPEND implies that we must revalidate the file length.
	 */
	if (iocb->ki_filp->f_flags & O_APPEND) {
		result = nfs_revalidate_file_size(inode, iocb->ki_filp);
		if (result)
			goto out;
	}

	result = count;
	if (!count)
		goto out;

	result = generic_file_aio_write(iocb, iov, nr_segs, pos);
	if (result > 0)
		written = result;

	/* Return error values for O_DSYNC and IS_SYNC() */
	if (result >= 0 && nfs_need_sync_write(iocb->ki_filp, inode)) {
		int err = vfs_fsync(iocb->ki_filp, 0);
		if (err < 0)
			result = err;
	}
	if (result > 0)
		nfs_add_stats(inode, NFSIOS_NORMALWRITTENBYTES, written);
out:
	return result;

out_swapfile:
	printk(KERN_INFO "NFS: attempt to write to active swap file!\n");
	goto out;
}

static ssize_t nfs_file_splice_write(struct pipe_inode_info *pipe,
				     struct file *filp, loff_t *ppos,
				     size_t count, unsigned int flags)
{
	struct dentry *dentry = filp->f_path.dentry;
	struct inode *inode = dentry->d_inode;
	unsigned long written = 0;
	ssize_t ret;

	dprintk("NFS splice_write(%s/%s, %lu@%llu)\n",
		dentry->d_parent->d_name.name, dentry->d_name.name,
		(unsigned long) count, (unsigned long long) *ppos);

	/*
	 * The combination of splice and an O_APPEND destination is disallowed.
	 */

	ret = generic_file_splice_write(pipe, filp, ppos, count, flags);
	if (ret > 0)
		written = ret;

	if (ret >= 0 && nfs_need_sync_write(filp, inode)) {
		int err = vfs_fsync(filp, 0);
		if (err < 0)
			ret = err;
	}
	if (ret > 0)
		nfs_add_stats(inode, NFSIOS_NORMALWRITTENBYTES, written);
	return ret;
}

static int
do_getlk(struct file *filp, int cmd, struct file_lock *fl, int is_local)
{
	struct inode *inode = filp->f_mapping->host;
	int status = 0;
	unsigned int saved_type = fl->fl_type;

	/* Try local locking first */
	posix_test_lock(filp, fl);
	if (fl->fl_type != F_UNLCK) {
		/* found a conflict */
		goto out;
	}
	fl->fl_type = saved_type;

	if (nfs_have_delegation(inode, FMODE_READ))
		goto out_noconflict;

	if (is_local)
		goto out_noconflict;

	status = NFS_PROTO(inode)->lock(filp, cmd, fl);
out:
	return status;
out_noconflict:
	fl->fl_type = F_UNLCK;
	goto out;
}

static int do_vfs_lock(struct file *file, struct file_lock *fl)
{
	int res = 0;
	switch (fl->fl_flags & (FL_POSIX|FL_FLOCK)) {
		case FL_POSIX:
			res = posix_lock_file_wait(file, fl);
			break;
		case FL_FLOCK:
			res = flock_lock_file_wait(file, fl);
			break;
		default:
			BUG();
	}
	return res;
}

static int
do_unlk(struct file *filp, int cmd, struct file_lock *fl, int is_local)
{
	struct inode *inode = filp->f_mapping->host;
	int status;

	/*
	 * Flush all pending writes before doing anything
	 * with locks..
	 */
	nfs_sync_mapping(filp->f_mapping);

	/* NOTE: special case
	 * 	If we're signalled while cleaning up locks on process exit, we
	 * 	still need to complete the unlock.
	 */
	/*
	 * Use local locking if mounted with "-onolock" or with appropriate
	 * "-olocal_lock="
	 */
	if (!is_local)
		status = NFS_PROTO(inode)->lock(filp, cmd, fl);
	else
		status = do_vfs_lock(filp, fl);
	return status;
}

static int
is_time_granular(struct timespec *ts) {
	return ((ts->tv_sec == 0) && (ts->tv_nsec <= 1000));
}

static int
do_setlk(struct file *filp, int cmd, struct file_lock *fl, int is_local)
{
	struct inode *inode = filp->f_mapping->host;
	int status;

	/*
	 * Flush all pending writes before doing anything
	 * with locks..
	 */
	status = nfs_sync_mapping(filp->f_mapping);
	if (status != 0)
		goto out;

	/*
	 * Use local locking if mounted with "-onolock" or with appropriate
	 * "-olocal_lock="
	 */
	if (!is_local)
		status = NFS_PROTO(inode)->lock(filp, cmd, fl);
	else
		status = do_vfs_lock(filp, fl);
	if (status < 0)
		goto out;

	/*
	 * Revalidate the cache if the server has time stamps granular
	 * enough to detect subsecond changes.  Otherwise, clear the
	 * cache to prevent missing any changes.
	 *
	 * This makes locking act as a cache coherency point.
	 */
	nfs_sync_mapping(filp->f_mapping);
	if (!nfs_have_delegation(inode, FMODE_READ)) {
		if (is_time_granular(&NFS_SERVER(inode)->time_delta))
			__nfs_revalidate_inode(NFS_SERVER(inode), inode);
		else
			nfs_zap_caches(inode);
	}
out:
	return status;
}

/*
 * Lock a (portion of) a file
 */
static int nfs_lock(struct file *filp, int cmd, struct file_lock *fl)
{
	struct inode *inode = filp->f_mapping->host;
	int ret = -ENOLCK;
	int is_local = 0;

	dprintk("NFS: lock(%s/%s, t=%x, fl=%x, r=%lld:%lld)\n",
			filp->f_path.dentry->d_parent->d_name.name,
			filp->f_path.dentry->d_name.name,
			fl->fl_type, fl->fl_flags,
			(long long)fl->fl_start, (long long)fl->fl_end);

	nfs_inc_stats(inode, NFSIOS_VFSLOCK);

	/* No mandatory locks over NFS */
	if (__mandatory_lock(inode) && fl->fl_type != F_UNLCK)
		goto out_err;

	if (NFS_SERVER(inode)->flags & NFS_MOUNT_LOCAL_FCNTL)
		is_local = 1;

	if (NFS_PROTO(inode)->lock_check_bounds != NULL) {
		ret = NFS_PROTO(inode)->lock_check_bounds(fl);
		if (ret < 0)
			goto out_err;
	}

	if (IS_GETLK(cmd))
		ret = do_getlk(filp, cmd, fl, is_local);
	else if (fl->fl_type == F_UNLCK)
		ret = do_unlk(filp, cmd, fl, is_local);
	else
		ret = do_setlk(filp, cmd, fl, is_local);
out_err:
	return ret;
}

/*
 * Lock a (portion of) a file
 */
static int nfs_flock(struct file *filp, int cmd, struct file_lock *fl)
{
	struct inode *inode = filp->f_mapping->host;
	int is_local = 0;

	dprintk("NFS: flock(%s/%s, t=%x, fl=%x)\n",
			filp->f_path.dentry->d_parent->d_name.name,
			filp->f_path.dentry->d_name.name,
			fl->fl_type, fl->fl_flags);

	if (!(fl->fl_flags & FL_FLOCK))
		return -ENOLCK;

	if (NFS_SERVER(inode)->flags & NFS_MOUNT_LOCAL_FLOCK)
		is_local = 1;

	/* We're simulating flock() locks using posix locks on the server */
	fl->fl_owner = (fl_owner_t)filp;
	fl->fl_start = 0;
	fl->fl_end = OFFSET_MAX;

	if (fl->fl_type == F_UNLCK)
		return do_unlk(filp, cmd, fl, is_local);
	return do_setlk(filp, cmd, fl, is_local);
}

/*
 * There is no protocol support for leases, so we have no way to implement
 * them correctly in the face of opens by other clients.
 */
static int nfs_setlease(struct file *file, long arg, struct file_lock **fl)
{
	dprintk("NFS: setlease(%s/%s, arg=%ld)\n",
			file->f_path.dentry->d_parent->d_name.name,
			file->f_path.dentry->d_name.name, arg);
	return -EINVAL;
}