/*
* file.c - NTFS kernel file operations. Part of the Linux-NTFS project.
*
- * Copyright (c) 2001-2006 Anton Altaparmakov
+ * Copyright (c) 2001-2007 Anton Altaparmakov
*
* This program/include file is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License as published
*/
#include <linux/buffer_head.h>
+#include <linux/gfp.h>
#include <linux/pagemap.h>
#include <linux/pagevec.h>
#include <linux/sched.h>
{
if (sizeof(unsigned long) < 8) {
if (i_size_read(vi) > MAX_LFS_FILESIZE)
- return -EFBIG;
+ return -EOVERFLOW;
}
return generic_file_open(vi, filp);
}
* the page at all. For a more detailed explanation see ntfs_truncate() in
* fs/ntfs/inode.c.
*
- * @cached_page and @lru_pvec are just optimizations for dealing with multiple
- * pages.
- *
* Return 0 on success and -errno on error. In the case that an error is
* encountered it is possible that the initialized size will already have been
* incremented some way towards @new_init_size but it is guaranteed that if
* Locking: i_mutex on the vfs inode corrseponsind to the ntfs inode @ni must be
* held by the caller.
*/
-static int ntfs_attr_extend_initialized(ntfs_inode *ni, const s64 new_init_size,
- struct page **cached_page, struct pagevec *lru_pvec)
+static int ntfs_attr_extend_initialized(ntfs_inode *ni, const s64 new_init_size)
{
s64 old_init_size;
loff_t old_i_size;
err = PTR_ERR(page);
goto init_err_out;
}
- wait_on_page_locked(page);
- if (unlikely(!PageUptodate(page) || PageError(page))) {
+ if (unlikely(PageError(page))) {
page_cache_release(page);
err = -EIO;
goto init_err_out;
volatile char c;
/* Set @end to the first byte outside the last page we care about. */
- end = (const char __user*)PAGE_ALIGN((ptrdiff_t __user)uaddr + bytes);
+ end = (const char __user*)PAGE_ALIGN((unsigned long)uaddr + bytes);
while (!__get_user(c, uaddr) && (uaddr += PAGE_SIZE, uaddr < end))
;
* @cached_page: allocated but as yet unused page
* @lru_pvec: lru-buffering pagevec of caller
*
- * Obtain @nr_pages locked page cache pages from the mapping @maping and
+ * Obtain @nr_pages locked page cache pages from the mapping @mapping and
* starting at index @index.
*
- * If a page is newly created, increment its refcount and add it to the
- * caller's lru-buffering pagevec @lru_pvec.
- *
- * This is the same as mm/filemap.c::__grab_cache_page(), except that @nr_pages
- * are obtained at once instead of just one page and that 0 is returned on
- * success and -errno on error.
+ * If a page is newly created, add it to lru list
*
* Note, the page locks are obtained in ascending page index order.
*/
static inline int __ntfs_grab_cache_pages(struct address_space *mapping,
pgoff_t index, const unsigned nr_pages, struct page **pages,
- struct page **cached_page, struct pagevec *lru_pvec)
+ struct page **cached_page)
{
int err, nr;
goto err_out;
}
}
- err = add_to_page_cache(*cached_page, mapping, index,
+ err = add_to_page_cache_lru(*cached_page, mapping, index,
GFP_KERNEL);
if (unlikely(err)) {
if (err == -EEXIST)
goto err_out;
}
pages[nr] = *cached_page;
- page_cache_get(*cached_page);
- if (unlikely(!pagevec_add(lru_pvec, *cached_page)))
- __pagevec_lru_add(lru_pvec);
*cached_page = NULL;
}
index++;
blocksize_bits = vol->sb->s_blocksize_bits;
u = 0;
do {
- struct page *page = pages[u];
+ page = pages[u];
+ BUG_ON(!page);
/*
* create_empty_buffers() will create uptodate/dirty buffers if
* the page is uptodate/dirty.
ntfs_submit_bh_for_read(bh);
*wait_bh++ = bh;
} else {
- u8 *kaddr = kmap_atomic(page, KM_USER0);
- memset(kaddr + bh_offset(bh), 0,
+ zero_user(page, bh_offset(bh),
blocksize);
- kunmap_atomic(kaddr, KM_USER0);
- flush_dcache_page(page);
set_buffer_uptodate(bh);
}
}
ntfs_submit_bh_for_read(bh);
*wait_bh++ = bh;
} else {
- u8 *kaddr = kmap_atomic(page,
- KM_USER0);
- memset(kaddr + bh_offset(bh),
- 0, blocksize);
- kunmap_atomic(kaddr, KM_USER0);
- flush_dcache_page(page);
+ zero_user(page, bh_offset(bh),
+ blocksize);
set_buffer_uptodate(bh);
}
}
*/
if (bh_end <= pos || bh_pos >= end) {
if (!buffer_uptodate(bh)) {
- u8 *kaddr = kmap_atomic(page, KM_USER0);
- memset(kaddr + bh_offset(bh), 0,
+ zero_user(page, bh_offset(bh),
blocksize);
- kunmap_atomic(kaddr, KM_USER0);
- flush_dcache_page(page);
set_buffer_uptodate(bh);
}
mark_buffer_dirty(bh);
if (!buffer_uptodate(bh))
set_buffer_uptodate(bh);
} else if (!buffer_uptodate(bh)) {
- u8 *kaddr = kmap_atomic(page, KM_USER0);
- memset(kaddr + bh_offset(bh), 0, blocksize);
- kunmap_atomic(kaddr, KM_USER0);
- flush_dcache_page(page);
+ zero_user(page, bh_offset(bh), blocksize);
set_buffer_uptodate(bh);
}
continue;
if (!buffer_uptodate(bh))
set_buffer_uptodate(bh);
} else if (!buffer_uptodate(bh)) {
- u8 *kaddr = kmap_atomic(page, KM_USER0);
- memset(kaddr + bh_offset(bh), 0,
- blocksize);
- kunmap_atomic(kaddr, KM_USER0);
- flush_dcache_page(page);
+ zero_user(page, bh_offset(bh),
+ blocksize);
set_buffer_uptodate(bh);
}
continue;
* to zero the overflowing region.
*/
if (unlikely(bh_pos + blocksize > initialized_size)) {
- u8 *kaddr;
int ofs = 0;
if (likely(bh_pos < initialized_size))
ofs = initialized_size - bh_pos;
- kaddr = kmap_atomic(page, KM_USER0);
- memset(kaddr + bh_offset(bh) + ofs, 0,
- blocksize - ofs);
- kunmap_atomic(kaddr, KM_USER0);
- flush_dcache_page(page);
+ zero_user_segment(page, bh_offset(bh) + ofs,
+ blocksize);
}
} else /* if (unlikely(!buffer_uptodate(bh))) */
err = -EIO;
if (PageUptodate(page))
set_buffer_uptodate(bh);
else {
- u8 *kaddr = kmap_atomic(page, KM_USER0);
- memset(kaddr + bh_offset(bh), 0,
+ zero_user(page, bh_offset(bh),
blocksize);
- kunmap_atomic(kaddr, KM_USER0);
- flush_dcache_page(page);
set_buffer_uptodate(bh);
}
}
/*
* Copy as much as we can into the pages and return the number of bytes which
- * were sucessfully copied. If a fault is encountered then clear the pages
+ * were successfully copied. If a fault is encountered then clear the pages
* out to (ofs + bytes) and return the number of bytes which were copied.
*/
static inline size_t ntfs_copy_from_user(struct page **pages,
size_t bytes)
{
struct page **last_page = pages + nr_pages;
- char *kaddr;
+ char *addr;
size_t total = 0;
unsigned len;
int left;
len = PAGE_CACHE_SIZE - ofs;
if (len > bytes)
len = bytes;
- kaddr = kmap_atomic(*pages, KM_USER0);
- left = __copy_from_user_inatomic(kaddr + ofs, buf, len);
- kunmap_atomic(kaddr, KM_USER0);
+ addr = kmap_atomic(*pages, KM_USER0);
+ left = __copy_from_user_inatomic(addr + ofs, buf, len);
+ kunmap_atomic(addr, KM_USER0);
if (unlikely(left)) {
/* Do it the slow way. */
- kaddr = kmap(*pages);
- left = __copy_from_user(kaddr + ofs, buf, len);
+ addr = kmap(*pages);
+ left = __copy_from_user(addr + ofs, buf, len);
kunmap(*pages);
if (unlikely(left))
goto err_out;
len = PAGE_CACHE_SIZE;
if (len > bytes)
len = bytes;
- kaddr = kmap_atomic(*pages, KM_USER0);
- memset(kaddr, 0, len);
- kunmap_atomic(kaddr, KM_USER0);
+ zero_user(*pages, 0, len);
}
goto out;
}
size_t *iov_ofs, size_t bytes)
{
struct page **last_page = pages + nr_pages;
- char *kaddr;
+ char *addr;
size_t copied, len, total = 0;
do {
len = PAGE_CACHE_SIZE - ofs;
if (len > bytes)
len = bytes;
- kaddr = kmap_atomic(*pages, KM_USER0);
- copied = __ntfs_copy_from_user_iovec_inatomic(kaddr + ofs,
+ addr = kmap_atomic(*pages, KM_USER0);
+ copied = __ntfs_copy_from_user_iovec_inatomic(addr + ofs,
*iov, *iov_ofs, len);
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(addr, KM_USER0);
if (unlikely(copied != len)) {
/* Do it the slow way. */
- kaddr = kmap(*pages);
- copied = __ntfs_copy_from_user_iovec_inatomic(kaddr + ofs,
+ addr = kmap(*pages);
+ copied = __ntfs_copy_from_user_iovec_inatomic(addr + ofs,
*iov, *iov_ofs, len);
/*
* Zero the rest of the target like __copy_from_user().
*/
- memset(kaddr + ofs + copied, 0, len - copied);
+ memset(addr + ofs + copied, 0, len - copied);
kunmap(*pages);
if (unlikely(copied != len))
goto err_out;
len = PAGE_CACHE_SIZE;
if (len > bytes)
len = bytes;
- kaddr = kmap_atomic(*pages, KM_USER0);
- memset(kaddr, 0, len);
- kunmap_atomic(kaddr, KM_USER0);
+ zero_user(*pages, 0, len);
}
goto out;
}
read_unlock_irqrestore(&ni->size_lock, flags);
BUG_ON(initialized_size != i_size);
if (end > initialized_size) {
- unsigned long flags;
-
write_lock_irqsave(&ni->size_lock, flags);
ni->initialized_size = end;
i_size_write(vi, end);
ssize_t status, written;
unsigned nr_pages;
int err;
- struct pagevec lru_pvec;
ntfs_debug("Entering for i_ino 0x%lx, attribute type 0x%x, "
"pos 0x%llx, count 0x%lx.",
}
}
}
- pagevec_init(&lru_pvec, 0);
written = 0;
/*
* If the write starts beyond the initialized size, extend it up to the
ll = ni->initialized_size;
read_unlock_irqrestore(&ni->size_lock, flags);
if (pos > ll) {
- err = ntfs_attr_extend_initialized(ni, pos, &cached_page,
- &lru_pvec);
+ err = ntfs_attr_extend_initialized(ni, pos);
if (err < 0) {
ntfs_error(vol->sb, "Cannot perform write to inode "
"0x%lx, attribute type 0x%x, because "
ntfs_fault_in_pages_readable_iovec(iov, iov_ofs, bytes);
/* Get and lock @do_pages starting at index @start_idx. */
status = __ntfs_grab_cache_pages(mapping, start_idx, do_pages,
- pages, &cached_page, &lru_pvec);
+ pages, &cached_page);
if (unlikely(status))
break;
/*
*ppos = pos;
if (cached_page)
page_cache_release(cached_page);
- /* For now, when the user asks for O_SYNC, we actually give O_DSYNC. */
- if (likely(!status)) {
- if (unlikely((file->f_flags & O_SYNC) || IS_SYNC(vi))) {
- if (!mapping->a_ops->writepage || !is_sync_kiocb(iocb))
- status = generic_osync_inode(vi, mapping,
- OSYNC_METADATA|OSYNC_DATA);
- }
- }
- pagevec_lru_add(&lru_pvec);
ntfs_debug("Done. Returning %s (written 0x%lx, status %li).",
written ? "written" : "status", (unsigned long)written,
(long)status);
struct address_space *mapping = file->f_mapping;
struct inode *inode = mapping->host;
loff_t pos;
- unsigned long seg;
size_t count; /* after file limit checks */
ssize_t written, err;
count = 0;
- for (seg = 0; seg < nr_segs; seg++) {
- const struct iovec *iv = &iov[seg];
- /*
- * If any segment has a negative length, or the cumulative
- * length ever wraps negative then return -EINVAL.
- */
- count += iv->iov_len;
- if (unlikely((ssize_t)(count|iv->iov_len) < 0))
- return -EINVAL;
- if (access_ok(VERIFY_READ, iv->iov_base, iv->iov_len))
- continue;
- if (!seg)
- return -EFAULT;
- nr_segs = seg;
- count -= iv->iov_len; /* This segment is no good */
- break;
- }
+ err = generic_segment_checks(iov, &nr_segs, &count, VERIFY_READ);
+ if (err)
+ return err;
pos = *ppos;
vfs_check_frozen(inode->i_sb, SB_FREEZE_WRITE);
/* We can write back this queue in page reclaim. */
goto out;
if (!count)
goto out;
- err = remove_suid(file->f_path.dentry);
+ err = file_remove_suid(file);
if (err)
goto out;
file_update_time(file);
mutex_lock(&inode->i_mutex);
ret = ntfs_file_aio_write_nolock(iocb, iov, nr_segs, &iocb->ki_pos);
mutex_unlock(&inode->i_mutex);
- if (ret > 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) {
- int err = sync_page_range(inode, mapping, pos, ret);
+ if (ret > 0) {
+ int err = generic_write_sync(file, pos, ret);
if (err < 0)
ret = err;
}
}
/**
- * ntfs_file_writev -
- *
- * Basically the same as generic_file_writev() except that it ends up calling
- * ntfs_file_aio_write_nolock() instead of __generic_file_aio_write_nolock().
- */
-static ssize_t ntfs_file_writev(struct file *file, const struct iovec *iov,
- unsigned long nr_segs, loff_t *ppos)
-{
- struct address_space *mapping = file->f_mapping;
- struct inode *inode = mapping->host;
- struct kiocb kiocb;
- ssize_t ret;
-
- mutex_lock(&inode->i_mutex);
- init_sync_kiocb(&kiocb, file);
- ret = ntfs_file_aio_write_nolock(&kiocb, iov, nr_segs, ppos);
- if (ret == -EIOCBQUEUED)
- ret = wait_on_sync_kiocb(&kiocb);
- mutex_unlock(&inode->i_mutex);
- if (ret > 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) {
- int err = sync_page_range(inode, mapping, *ppos - ret, ret);
- if (err < 0)
- ret = err;
- }
- return ret;
-}
-
-/**
- * ntfs_file_write - simple wrapper for ntfs_file_writev()
- */
-static ssize_t ntfs_file_write(struct file *file, const char __user *buf,
- size_t count, loff_t *ppos)
-{
- struct iovec local_iov = { .iov_base = (void __user *)buf,
- .iov_len = count };
-
- return ntfs_file_writev(file, &local_iov, 1, ppos);
-}
-
-/**
* ntfs_file_fsync - sync a file to disk
* @filp: file to be synced
- * @dentry: dentry describing the file to sync
* @datasync: if non-zero only flush user data and not metadata
*
* Data integrity sync of a file to disk. Used for fsync, fdatasync, and msync
* Also, if @datasync is true, we do not wait on the inode to be written out
* but we always wait on the page cache pages to be written out.
*
- * Note: In the past @filp could be NULL so we ignore it as we don't need it
- * anyway.
- *
* Locking: Caller must hold i_mutex on the inode.
*
* TODO: We should probably also write all attribute/index inodes associated
* with this inode but since we have no simple way of getting to them we ignore
* this problem for now.
*/
-static int ntfs_file_fsync(struct file *filp, struct dentry *dentry,
- int datasync)
+static int ntfs_file_fsync(struct file *filp, int datasync)
{
- struct inode *vi = dentry->d_inode;
+ struct inode *vi = filp->f_mapping->host;
int err, ret = 0;
ntfs_debug("Entering for inode 0x%lx.", vi->i_ino);
BUG_ON(S_ISDIR(vi->i_mode));
if (!datasync || !NInoNonResident(NTFS_I(vi)))
- ret = ntfs_write_inode(vi, 1);
+ ret = __ntfs_write_inode(vi, 1);
write_inode_now(vi, !datasync);
/*
* NOTE: If we were to use mapping->private_list (see ext2 and
.read = do_sync_read, /* Read from file. */
.aio_read = generic_file_aio_read, /* Async read from file. */
#ifdef NTFS_RW
- .write = ntfs_file_write, /* Write to file. */
+ .write = do_sync_write, /* Write to file. */
.aio_write = ntfs_file_aio_write, /* Async write to file. */
/*.release = ,*/ /* Last file is closed. See
fs/ext2/file.c::
mounted filesystem. */
.mmap = generic_file_mmap, /* Mmap file. */
.open = ntfs_file_open, /* Open file. */
- .sendfile = generic_file_sendfile, /* Zero-copy data send with
+ .splice_read = generic_file_splice_read /* Zero-copy data send with
the data source being on
the ntfs partition. We do
not need to care about the