#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>
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_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;
+static const struct vm_operations_struct nfs_file_vm_ops;
const struct file_operations nfs_file_operations = {
.llseek = nfs_file_llseek,
.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,
};
}
/*
+ * 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.
struct page **pagep, void **fsdata)
{
int ret;
- pgoff_t index;
+ pgoff_t index = pos >> PAGE_CACHE_SHIFT;
struct page *page;
- index = pos >> PAGE_CACHE_SHIFT;
+ 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);
+start:
/*
* Prevent starvation issues if someone is doing a consistency
* sync-to-disk
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;
}
.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,
};
/*
return VM_FAULT_SIGBUS;
}
-static struct vm_operations_struct nfs_file_vm_ops = {
+static const struct vm_operations_struct nfs_file_vm_ops = {
.fault = filemap_fault,
.page_mkwrite = nfs_vm_page_mkwrite,
};
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;
+ 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.
+ */
+
+ nfs_add_stats(inode, NFSIOS_NORMALWRITTENBYTES, count);
+
+ ret = generic_file_splice_write(pipe, filp, ppos, count, flags);
+ if (ret >= 0 && nfs_need_sync_write(filp, inode)) {
+ int err = nfs_do_fsync(nfs_file_open_context(filp), inode);
+ if (err < 0)
+ ret = err;
+ }
+ return ret;
+}
+
static int do_getlk(struct file *filp, int cmd, struct file_lock *fl)
{
struct inode *inode = filp->f_mapping->host;
int status = 0;
- lock_kernel();
/* Try local locking first */
posix_test_lock(filp, fl);
if (fl->fl_type != F_UNLCK) {
status = NFS_PROTO(inode)->lock(filp, cmd, fl);
out:
- unlock_kernel();
return status;
out_noconflict:
fl->fl_type = F_UNLCK;
* If we're signalled while cleaning up locks on process exit, we
* still need to complete the unlock.
*/
- lock_kernel();
/* Use local locking if mounted with "-onolock" */
if (!(NFS_SERVER(inode)->flags & NFS_MOUNT_NONLM))
status = NFS_PROTO(inode)->lock(filp, cmd, fl);
else
status = do_vfs_lock(filp, fl);
- unlock_kernel();
return status;
}
if (status != 0)
goto out;
- lock_kernel();
/* Use local locking if mounted with "-onolock" */
if (!(NFS_SERVER(inode)->flags & NFS_MOUNT_NONLM))
status = NFS_PROTO(inode)->lock(filp, cmd, fl);
else
status = do_vfs_lock(filp, fl);
- unlock_kernel();
if (status < 0)
goto out;
/*
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff