* aops.c - NTFS kernel address space operations and page cache handling.
* Part of the Linux-NTFS project.
*
- * Copyright (c) 2001-2005 Anton Altaparmakov
+ * Copyright (c) 2001-2006 Anton Altaparmakov
* Copyright (c) 2002 Richard Russon
*
* This program/include file is free software; you can redistribute it and/or
*/
#include <linux/errno.h>
+#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/pagemap.h>
#include <linux/swap.h>
unsigned long flags;
struct buffer_head *first, *tmp;
struct page *page;
+ struct inode *vi;
ntfs_inode *ni;
int page_uptodate = 1;
page = bh->b_page;
- ni = NTFS_I(page->mapping->host);
+ vi = page->mapping->host;
+ ni = NTFS_I(vi);
if (likely(uptodate)) {
- s64 file_ofs, initialized_size;
+ loff_t i_size;
+ s64 file_ofs, init_size;
set_buffer_uptodate(bh);
file_ofs = ((s64)page->index << PAGE_CACHE_SHIFT) +
bh_offset(bh);
read_lock_irqsave(&ni->size_lock, flags);
- initialized_size = ni->initialized_size;
+ init_size = ni->initialized_size;
+ i_size = i_size_read(vi);
read_unlock_irqrestore(&ni->size_lock, flags);
+ if (unlikely(init_size > i_size)) {
+ /* Race with shrinking truncate. */
+ init_size = i_size;
+ }
/* Check for the current buffer head overflowing. */
- if (file_ofs + bh->b_size > initialized_size) {
- char *addr;
- int ofs = 0;
-
- if (file_ofs < initialized_size)
- ofs = initialized_size - file_ofs;
- addr = kmap_atomic(page, KM_BIO_SRC_IRQ);
- memset(addr + bh_offset(bh) + ofs, 0, bh->b_size - ofs);
+ if (unlikely(file_ofs + bh->b_size > init_size)) {
+ u8 *kaddr;
+ int ofs;
+
+ ofs = 0;
+ if (file_ofs < init_size)
+ ofs = init_size - file_ofs;
+ kaddr = kmap_atomic(page, KM_BIO_SRC_IRQ);
+ memset(kaddr + bh_offset(bh) + ofs, 0,
+ bh->b_size - ofs);
+ kunmap_atomic(kaddr, KM_BIO_SRC_IRQ);
flush_dcache_page(page);
- kunmap_atomic(addr, KM_BIO_SRC_IRQ);
}
} else {
clear_buffer_uptodate(bh);
SetPageError(page);
- ntfs_error(ni->vol->sb, "Buffer I/O error, logical block %llu.",
- (unsigned long long)bh->b_blocknr);
+ ntfs_error(ni->vol->sb, "Buffer I/O error, logical block "
+ "0x%llx.", (unsigned long long)bh->b_blocknr);
}
first = page_buffers(page);
local_irq_save(flags);
if (likely(page_uptodate && !PageError(page)))
SetPageUptodate(page);
} else {
- char *addr;
+ u8 *kaddr;
unsigned int i, recs;
u32 rec_size;
recs = PAGE_CACHE_SIZE / rec_size;
/* Should have been verified before we got here... */
BUG_ON(!recs);
- addr = kmap_atomic(page, KM_BIO_SRC_IRQ);
+ kaddr = kmap_atomic(page, KM_BIO_SRC_IRQ);
for (i = 0; i < recs; i++)
- post_read_mst_fixup((NTFS_RECORD*)(addr +
+ post_read_mst_fixup((NTFS_RECORD*)(kaddr +
i * rec_size), rec_size);
+ kunmap_atomic(kaddr, KM_BIO_SRC_IRQ);
flush_dcache_page(page);
- kunmap_atomic(addr, KM_BIO_SRC_IRQ);
if (likely(page_uptodate && !PageError(page)))
SetPageUptodate(page);
}
*/
static int ntfs_read_block(struct page *page)
{
+ loff_t i_size;
VCN vcn;
LCN lcn;
+ s64 init_size;
+ struct inode *vi;
ntfs_inode *ni;
ntfs_volume *vol;
runlist_element *rl;
int i, nr;
unsigned char blocksize_bits;
- ni = NTFS_I(page->mapping->host);
+ vi = page->mapping->host;
+ ni = NTFS_I(vi);
vol = ni->vol;
/* $MFT/$DATA must have its complete runlist in memory at all times. */
BUG_ON(!ni->runlist.rl && !ni->mft_no && !NInoAttr(ni));
- blocksize_bits = VFS_I(ni)->i_blkbits;
- blocksize = 1 << blocksize_bits;
+ blocksize = vol->sb->s_blocksize;
+ blocksize_bits = vol->sb->s_blocksize_bits;
if (!page_has_buffers(page)) {
create_empty_buffers(page, blocksize, 0);
bh = head = page_buffers(page);
BUG_ON(!bh);
+ /*
+ * We may be racing with truncate. To avoid some of the problems we
+ * now take a snapshot of the various sizes and use those for the whole
+ * of the function. In case of an extending truncate it just means we
+ * may leave some buffers unmapped which are now allocated. This is
+ * not a problem since these buffers will just get mapped when a write
+ * occurs. In case of a shrinking truncate, we will detect this later
+ * on due to the runlist being incomplete and if the page is being
+ * fully truncated, truncate will throw it away as soon as we unlock
+ * it so no need to worry what we do with it.
+ */
iblock = (s64)page->index << (PAGE_CACHE_SHIFT - blocksize_bits);
read_lock_irqsave(&ni->size_lock, flags);
lblock = (ni->allocated_size + blocksize - 1) >> blocksize_bits;
- zblock = (ni->initialized_size + blocksize - 1) >> blocksize_bits;
+ init_size = ni->initialized_size;
+ i_size = i_size_read(vi);
read_unlock_irqrestore(&ni->size_lock, flags);
+ if (unlikely(init_size > i_size)) {
+ /* Race with shrinking truncate. */
+ init_size = i_size;
+ }
+ zblock = (init_size + blocksize - 1) >> blocksize_bits;
/* Loop through all the buffers in the page. */
rl = NULL;
*/
static int ntfs_readpage(struct file *file, struct page *page)
{
+ loff_t i_size;
+ struct inode *vi;
ntfs_inode *ni, *base_ni;
u8 *kaddr;
ntfs_attr_search_ctx *ctx;
unlock_page(page);
return 0;
}
- ni = NTFS_I(page->mapping->host);
+ vi = page->mapping->host;
+ ni = NTFS_I(vi);
/*
* Only $DATA attributes can be encrypted and only unnamed $DATA
* attributes can be compressed. Index root can have the flags set but
* this means to create compressed/encrypted files, not that the
- * attribute is compressed/encrypted.
+ * attribute is compressed/encrypted. Note we need to check for
+ * AT_INDEX_ALLOCATION since this is the type of both directory and
+ * index inodes.
*/
- if (ni->type != AT_INDEX_ROOT) {
+ if (ni->type != AT_INDEX_ALLOCATION) {
/* If attribute is encrypted, deny access, just like NT4. */
if (NInoEncrypted(ni)) {
BUG_ON(ni->type != AT_DATA);
read_lock_irqsave(&ni->size_lock, flags);
if (unlikely(attr_len > ni->initialized_size))
attr_len = ni->initialized_size;
+ i_size = i_size_read(vi);
read_unlock_irqrestore(&ni->size_lock, flags);
+ if (unlikely(attr_len > i_size)) {
+ /* Race with shrinking truncate. */
+ attr_len = i_size;
+ }
kaddr = kmap_atomic(page, KM_USER0);
/* Copy the data to the page. */
memcpy(kaddr, (u8*)ctx->attr +
BUG_ON(!NInoNonResident(ni));
BUG_ON(NInoMstProtected(ni));
-
- blocksize_bits = vi->i_blkbits;
- blocksize = 1 << blocksize_bits;
-
+ blocksize = vol->sb->s_blocksize;
+ blocksize_bits = vol->sb->s_blocksize_bits;
if (!page_has_buffers(page)) {
BUG_ON(!PageUptodate(page));
create_empty_buffers(page, blocksize,
*/
BUG_ON(!(is_mft || S_ISDIR(vi->i_mode) ||
(NInoAttr(ni) && ni->type == AT_INDEX_ALLOCATION)));
- bh_size_bits = vi->i_blkbits;
- bh_size = 1 << bh_size_bits;
+ bh_size = vol->sb->s_blocksize;
+ bh_size_bits = vol->sb->s_blocksize_bits;
max_bhs = PAGE_CACHE_SIZE / bh_size;
BUG_ON(!max_bhs);
BUG_ON(max_bhs > MAX_BUF_PER_PAGE);
tni = locked_nis[nr_locked_nis];
/* Get the base inode. */
- down(&tni->extent_lock);
+ mutex_lock(&tni->extent_lock);
if (tni->nr_extents >= 0)
base_tni = tni;
else {
base_tni = tni->ext.base_ntfs_ino;
BUG_ON(!base_tni);
}
- up(&tni->extent_lock);
+ mutex_unlock(&tni->extent_lock);
ntfs_debug("Unlocking %s inode 0x%lx.",
tni == base_tni ? "base" : "extent",
tni->mft_no);
- up(&tni->mrec_lock);
+ mutex_unlock(&tni->mrec_lock);
atomic_dec(&tni->count);
iput(VFS_I(base_tni));
}
* Only $DATA attributes can be encrypted and only unnamed $DATA
* attributes can be compressed. Index root can have the flags set but
* this means to create compressed/encrypted files, not that the
- * attribute is compressed/encrypted.
+ * attribute is compressed/encrypted. Note we need to check for
+ * AT_INDEX_ALLOCATION since this is the type of both directory and
+ * index inodes.
*/
- if (ni->type != AT_INDEX_ROOT) {
+ if (ni->type != AT_INDEX_ALLOCATION) {
/* If file is encrypted, deny access, just like NT4. */
if (NInoEncrypted(ni)) {
unlock_page(page);
BUG_ON(ni->type != AT_DATA);
- ntfs_debug("Denying write access to encrypted "
- "file.");
+ ntfs_debug("Denying write access to encrypted file.");
return -EACCES;
}
/* Compressed data streams are handled in compress.c. */
unsigned int ofs = i_size & ~PAGE_CACHE_MASK;
kaddr = kmap_atomic(page, KM_USER0);
memset(kaddr + ofs, 0, PAGE_CACHE_SIZE - ofs);
- flush_dcache_page(page);
kunmap_atomic(kaddr, KM_USER0);
+ flush_dcache_page(page);
}
/* Handle mst protected attributes. */
if (NInoMstProtected(ni))
BUG_ON(PageWriteback(page));
set_page_writeback(page);
unlock_page(page);
- /*
- * Here, we do not need to zero the out of bounds area everytime
- * because the below memcpy() already takes care of the
- * mmap-at-end-of-file requirements. If the file is converted to a
- * non-resident one, then the code path use is switched to the
- * non-resident one where the zeroing happens on each ntfs_writepage()
- * invocation.
- */
attr_len = le32_to_cpu(ctx->attr->data.resident.value_length);
i_size = i_size_read(vi);
if (unlikely(attr_len > i_size)) {
+ /* Race with shrinking truncate or a failed truncate. */
attr_len = i_size;
- ctx->attr->data.resident.value_length = cpu_to_le32(attr_len);
+ /*
+ * If the truncate failed, fix it up now. If a concurrent
+ * truncate, we do its job, so it does not have to do anything.
+ */
+ err = ntfs_resident_attr_value_resize(ctx->mrec, ctx->attr,
+ attr_len);
+ /* Shrinking cannot fail. */
+ BUG_ON(err);
}
kaddr = kmap_atomic(page, KM_USER0);
/* Copy the data from the page to the mft record. */
memcpy((u8*)ctx->attr +
le16_to_cpu(ctx->attr->data.resident.value_offset),
kaddr, attr_len);
- flush_dcache_mft_record_page(ctx->ntfs_ino);
/* Zero out of bounds area in the page cache page. */
memset(kaddr + attr_len, 0, PAGE_CACHE_SIZE - attr_len);
- flush_dcache_page(page);
kunmap_atomic(kaddr, KM_USER0);
-
+ flush_dcache_page(page);
+ flush_dcache_mft_record_page(ctx->ntfs_ino);
+ /* We are done with the page. */
end_page_writeback(page);
-
- /* Mark the mft record dirty, so it gets written back. */
+ /* Finally, mark the mft record dirty, so it gets written back. */
mark_mft_record_dirty(ctx->ntfs_ino);
ntfs_attr_put_search_ctx(ctx);
unmap_mft_record(base_ni);
"error %i.", err);
SetPageError(page);
NVolSetErrors(ni->vol);
- make_bad_inode(vi);
}
unlock_page(page);
if (ctx)
return err;
}
-/**
- * ntfs_prepare_nonresident_write -
- *
- */
-static int ntfs_prepare_nonresident_write(struct page *page,
- unsigned from, unsigned to)
-{
- VCN vcn;
- LCN lcn;
- s64 initialized_size;
- loff_t i_size;
- sector_t block, ablock, iblock;
- struct inode *vi;
- ntfs_inode *ni;
- ntfs_volume *vol;
- runlist_element *rl;
- struct buffer_head *bh, *head, *wait[2], **wait_bh = wait;
- unsigned long flags;
- unsigned int vcn_ofs, block_start, block_end, blocksize;
- int err;
- BOOL is_retry;
- unsigned char blocksize_bits;
-
- vi = page->mapping->host;
- ni = NTFS_I(vi);
- vol = ni->vol;
-
- ntfs_debug("Entering for inode 0x%lx, attribute type 0x%x, page index "
- "0x%lx, from = %u, to = %u.", ni->mft_no, ni->type,
- page->index, from, to);
-
- BUG_ON(!NInoNonResident(ni));
-
- blocksize_bits = vi->i_blkbits;
- blocksize = 1 << blocksize_bits;
-
- /*
- * create_empty_buffers() will create uptodate/dirty buffers if the
- * page is uptodate/dirty.
- */
- if (!page_has_buffers(page))
- create_empty_buffers(page, blocksize, 0);
- bh = head = page_buffers(page);
- if (unlikely(!bh))
- return -ENOMEM;
-
- /* The first block in the page. */
- block = (s64)page->index << (PAGE_CACHE_SHIFT - blocksize_bits);
-
- read_lock_irqsave(&ni->size_lock, flags);
- /*
- * The first out of bounds block for the allocated size. No need to
- * round up as allocated_size is in multiples of cluster size and the
- * minimum cluster size is 512 bytes, which is equal to the smallest
- * blocksize.
- */
- ablock = ni->allocated_size >> blocksize_bits;
- i_size = i_size_read(vi);
- initialized_size = ni->initialized_size;
- read_unlock_irqrestore(&ni->size_lock, flags);
-
- /* The last (fully or partially) initialized block. */
- iblock = initialized_size >> blocksize_bits;
-
- /* Loop through all the buffers in the page. */
- block_start = 0;
- rl = NULL;
- err = 0;
- do {
- block_end = block_start + blocksize;
- /*
- * If buffer @bh is outside the write, just mark it uptodate
- * if the page is uptodate and continue with the next buffer.
- */
- if (block_end <= from || block_start >= to) {
- if (PageUptodate(page)) {
- if (!buffer_uptodate(bh))
- set_buffer_uptodate(bh);
- }
- continue;
- }
- /*
- * @bh is at least partially being written to.
- * Make sure it is not marked as new.
- */
- //if (buffer_new(bh))
- // clear_buffer_new(bh);
-
- if (block >= ablock) {
- // TODO: block is above allocated_size, need to
- // allocate it. Best done in one go to accommodate not
- // only block but all above blocks up to and including:
- // ((page->index << PAGE_CACHE_SHIFT) + to + blocksize
- // - 1) >> blobksize_bits. Obviously will need to round
- // up to next cluster boundary, too. This should be
- // done with a helper function, so it can be reused.
- ntfs_error(vol->sb, "Writing beyond allocated size "
- "is not supported yet. Sorry.");
- err = -EOPNOTSUPP;
- goto err_out;
- // Need to update ablock.
- // Need to set_buffer_new() on all block bhs that are
- // newly allocated.
- }
- /*
- * Now we have enough allocated size to fulfill the whole
- * request, i.e. block < ablock is true.
- */
- if (unlikely((block >= iblock) &&
- (initialized_size < i_size))) {
- /*
- * If this page is fully outside initialized size, zero
- * out all pages between the current initialized size
- * and the current page. Just use ntfs_readpage() to do
- * the zeroing transparently.
- */
- if (block > iblock) {
- // TODO:
- // For each page do:
- // - read_cache_page()
- // Again for each page do:
- // - wait_on_page_locked()
- // - Check (PageUptodate(page) &&
- // !PageError(page))
- // Update initialized size in the attribute and
- // in the inode.
- // Again, for each page do:
- // __set_page_dirty_buffers();
- // page_cache_release()
- // We don't need to wait on the writes.
- // Update iblock.
- }
- /*
- * The current page straddles initialized size. Zero
- * all non-uptodate buffers and set them uptodate (and
- * dirty?). Note, there aren't any non-uptodate buffers
- * if the page is uptodate.
- * FIXME: For an uptodate page, the buffers may need to
- * be written out because they were not initialized on
- * disk before.
- */
- if (!PageUptodate(page)) {
- // TODO:
- // Zero any non-uptodate buffers up to i_size.
- // Set them uptodate and dirty.
- }
- // TODO:
- // Update initialized size in the attribute and in the
- // inode (up to i_size).
- // Update iblock.
- // FIXME: This is inefficient. Try to batch the two
- // size changes to happen in one go.
- ntfs_error(vol->sb, "Writing beyond initialized size "
- "is not supported yet. Sorry.");
- err = -EOPNOTSUPP;
- goto err_out;
- // Do NOT set_buffer_new() BUT DO clear buffer range
- // outside write request range.
- // set_buffer_uptodate() on complete buffers as well as
- // set_buffer_dirty().
- }
-
- /* Need to map unmapped buffers. */
- if (!buffer_mapped(bh)) {
- /* Unmapped buffer. Need to map it. */
- bh->b_bdev = vol->sb->s_bdev;
-
- /* Convert block into corresponding vcn and offset. */
- vcn = (VCN)block << blocksize_bits >>
- vol->cluster_size_bits;
- vcn_ofs = ((VCN)block << blocksize_bits) &
- vol->cluster_size_mask;
-
- is_retry = FALSE;
- if (!rl) {
-lock_retry_remap:
- down_read(&ni->runlist.lock);
- rl = ni->runlist.rl;
- }
- if (likely(rl != NULL)) {
- /* Seek to element containing target vcn. */
- while (rl->length && rl[1].vcn <= vcn)
- rl++;
- lcn = ntfs_rl_vcn_to_lcn(rl, vcn);
- } else
- lcn = LCN_RL_NOT_MAPPED;
- if (unlikely(lcn < 0)) {
- /*
- * We extended the attribute allocation above.
- * If we hit an ENOENT here it means that the
- * allocation was insufficient which is a bug.
- */
- BUG_ON(lcn == LCN_ENOENT);
-
- /* It is a hole, need to instantiate it. */
- if (lcn == LCN_HOLE) {
- // TODO: Instantiate the hole.
- // clear_buffer_new(bh);
- // unmap_underlying_metadata(bh->b_bdev,
- // bh->b_blocknr);
- // For non-uptodate buffers, need to
- // zero out the region outside the
- // request in this bh or all bhs,
- // depending on what we implemented
- // above.
- // Need to flush_dcache_page().
- // Or could use set_buffer_new()
- // instead?
- ntfs_error(vol->sb, "Writing into "
- "sparse regions is "
- "not supported yet. "
- "Sorry.");
- err = -EOPNOTSUPP;
- if (!rl)
- up_read(&ni->runlist.lock);
- goto err_out;
- } else if (!is_retry &&
- lcn == LCN_RL_NOT_MAPPED) {
- is_retry = TRUE;
- /*
- * Attempt to map runlist, dropping
- * lock for the duration.
- */
- up_read(&ni->runlist.lock);
- err = ntfs_map_runlist(ni, vcn);
- if (likely(!err))
- goto lock_retry_remap;
- rl = NULL;
- } else if (!rl)
- up_read(&ni->runlist.lock);
- /*
- * Failed to map the buffer, even after
- * retrying.
- */
- if (!err)
- err = -EIO;
- bh->b_blocknr = -1;
- ntfs_error(vol->sb, "Failed to write to inode "
- "0x%lx, attribute type 0x%x, "
- "vcn 0x%llx, offset 0x%x "
- "because its location on disk "
- "could not be determined%s "
- "(error code %i).",
- ni->mft_no, ni->type,
- (unsigned long long)vcn,
- vcn_ofs, is_retry ? " even "
- "after retrying" : "", err);
- goto err_out;
- }
- /* We now have a successful remap, i.e. lcn >= 0. */
-
- /* Setup buffer head to correct block. */
- bh->b_blocknr = ((lcn << vol->cluster_size_bits)
- + vcn_ofs) >> blocksize_bits;
- set_buffer_mapped(bh);
-
- // FIXME: Something analogous to this is needed for
- // each newly allocated block, i.e. BH_New.
- // FIXME: Might need to take this out of the
- // if (!buffer_mapped(bh)) {}, depending on how we
- // implement things during the allocated_size and
- // initialized_size extension code above.
- if (buffer_new(bh)) {
- clear_buffer_new(bh);
- unmap_underlying_metadata(bh->b_bdev,
- bh->b_blocknr);
- if (PageUptodate(page)) {
- set_buffer_uptodate(bh);
- continue;
- }
- /*
- * Page is _not_ uptodate, zero surrounding
- * region. NOTE: This is how we decide if to
- * zero or not!
- */
- if (block_end > to || block_start < from) {
- void *kaddr;
-
- kaddr = kmap_atomic(page, KM_USER0);
- if (block_end > to)
- memset(kaddr + to, 0,
- block_end - to);
- if (block_start < from)
- memset(kaddr + block_start, 0,
- from -
- block_start);
- flush_dcache_page(page);
- kunmap_atomic(kaddr, KM_USER0);
- }
- continue;
- }
- }
- /* @bh is mapped, set it uptodate if the page is uptodate. */
- if (PageUptodate(page)) {
- if (!buffer_uptodate(bh))
- set_buffer_uptodate(bh);
- continue;
- }
- /*
- * The page is not uptodate. The buffer is mapped. If it is not
- * uptodate, and it is only partially being written to, we need
- * to read the buffer in before the write, i.e. right now.
- */
- if (!buffer_uptodate(bh) &&
- (block_start < from || block_end > to)) {
- ll_rw_block(READ, 1, &bh);
- *wait_bh++ = bh;
- }
- } while (block++, block_start = block_end,
- (bh = bh->b_this_page) != head);
-
- /* Release the lock if we took it. */
- if (rl) {
- up_read(&ni->runlist.lock);
- rl = NULL;
- }
-
- /* If we issued read requests, let them complete. */
- while (wait_bh > wait) {
- wait_on_buffer(*--wait_bh);
- if (!buffer_uptodate(*wait_bh))
- return -EIO;
- }
-
- ntfs_debug("Done.");
- return 0;
-err_out:
- /*
- * Zero out any newly allocated blocks to avoid exposing stale data.
- * If BH_New is set, we know that the block was newly allocated in the
- * above loop.
- * FIXME: What about initialized_size increments? Have we done all the
- * required zeroing above? If not this error handling is broken, and
- * in particular the if (block_end <= from) check is completely bogus.
- */
- bh = head;
- block_start = 0;
- is_retry = FALSE;
- do {
- block_end = block_start + blocksize;
- if (block_end <= from)
- continue;
- if (block_start >= to)
- break;
- if (buffer_new(bh)) {
- void *kaddr;
-
- clear_buffer_new(bh);
- kaddr = kmap_atomic(page, KM_USER0);
- memset(kaddr + block_start, 0, bh->b_size);
- kunmap_atomic(kaddr, KM_USER0);
- set_buffer_uptodate(bh);
- mark_buffer_dirty(bh);
- is_retry = TRUE;
- }
- } while (block_start = block_end, (bh = bh->b_this_page) != head);
- if (is_retry)
- flush_dcache_page(page);
- if (rl)
- up_read(&ni->runlist.lock);
- return err;
-}
-
-/**
- * ntfs_prepare_write - prepare a page for receiving data
- *
- * This is called from generic_file_write() with i_sem held on the inode
- * (@page->mapping->host). The @page is locked but not kmap()ped. The source
- * data has not yet been copied into the @page.
- *
- * Need to extend the attribute/fill in holes if necessary, create blocks and
- * make partially overwritten blocks uptodate,
- *
- * i_size is not to be modified yet.
- *
- * Return 0 on success or -errno on error.
- *
- * Should be using block_prepare_write() [support for sparse files] or
- * cont_prepare_write() [no support for sparse files]. Cannot do that due to
- * ntfs specifics but can look at them for implementation guidance.
- *
- * Note: In the range, @from is inclusive and @to is exclusive, i.e. @from is
- * the first byte in the page that will be written to and @to is the first byte
- * after the last byte that will be written to.
- */
-static int ntfs_prepare_write(struct file *file, struct page *page,
- unsigned from, unsigned to)
-{
- s64 new_size;
- loff_t i_size;
- struct inode *vi = page->mapping->host;
- ntfs_inode *base_ni = NULL, *ni = NTFS_I(vi);
- ntfs_volume *vol = ni->vol;
- ntfs_attr_search_ctx *ctx = NULL;
- MFT_RECORD *m = NULL;
- ATTR_RECORD *a;
- u8 *kaddr;
- u32 attr_len;
- int err;
-
- ntfs_debug("Entering for inode 0x%lx, attribute type 0x%x, page index "
- "0x%lx, from = %u, to = %u.", vi->i_ino, ni->type,
- page->index, from, to);
- BUG_ON(!PageLocked(page));
- BUG_ON(from > PAGE_CACHE_SIZE);
- BUG_ON(to > PAGE_CACHE_SIZE);
- BUG_ON(from > to);
- BUG_ON(NInoMstProtected(ni));
- /*
- * If a previous ntfs_truncate() failed, repeat it and abort if it
- * fails again.
- */
- if (unlikely(NInoTruncateFailed(ni))) {
- down_write(&vi->i_alloc_sem);
- err = ntfs_truncate(vi);
- up_write(&vi->i_alloc_sem);
- if (err || NInoTruncateFailed(ni)) {
- if (!err)
- err = -EIO;
- goto err_out;
- }
- }
- /* If the attribute is not resident, deal with it elsewhere. */
- if (NInoNonResident(ni)) {
- /*
- * Only unnamed $DATA attributes can be compressed, encrypted,
- * and/or sparse.
- */
- if (ni->type == AT_DATA && !ni->name_len) {
- /* If file is encrypted, deny access, just like NT4. */
- if (NInoEncrypted(ni)) {
- ntfs_debug("Denying write access to encrypted "
- "file.");
- return -EACCES;
- }
- /* Compressed data streams are handled in compress.c. */
- if (NInoCompressed(ni)) {
- // TODO: Implement and replace this check with
- // return ntfs_write_compressed_block(page);
- ntfs_error(vi->i_sb, "Writing to compressed "
- "files is not supported yet. "
- "Sorry.");
- return -EOPNOTSUPP;
- }
- // TODO: Implement and remove this check.
- if (NInoSparse(ni)) {
- ntfs_error(vi->i_sb, "Writing to sparse files "
- "is not supported yet. Sorry.");
- return -EOPNOTSUPP;
- }
- }
- /* Normal data stream. */
- return ntfs_prepare_nonresident_write(page, from, to);
- }
- /*
- * Attribute is resident, implying it is not compressed, encrypted, or
- * sparse.
- */
- BUG_ON(page_has_buffers(page));
- new_size = ((s64)page->index << PAGE_CACHE_SHIFT) + to;
- /* If we do not need to resize the attribute allocation we are done. */
- if (new_size <= i_size_read(vi))
- goto done;
- /* Map, pin, and lock the (base) mft record. */
- if (!NInoAttr(ni))
- base_ni = ni;
- else
- base_ni = ni->ext.base_ntfs_ino;
- m = map_mft_record(base_ni);
- if (IS_ERR(m)) {
- err = PTR_ERR(m);
- m = NULL;
- ctx = NULL;
- goto err_out;
- }
- ctx = ntfs_attr_get_search_ctx(base_ni, m);
- if (unlikely(!ctx)) {
- err = -ENOMEM;
- goto err_out;
- }
- err = ntfs_attr_lookup(ni->type, ni->name, ni->name_len,
- CASE_SENSITIVE, 0, NULL, 0, ctx);
- if (unlikely(err)) {
- if (err == -ENOENT)
- err = -EIO;
- goto err_out;
- }
- m = ctx->mrec;
- a = ctx->attr;
- /* The total length of the attribute value. */
- attr_len = le32_to_cpu(a->data.resident.value_length);
- /* Fix an eventual previous failure of ntfs_commit_write(). */
- i_size = i_size_read(vi);
- if (unlikely(attr_len > i_size)) {
- attr_len = i_size;
- a->data.resident.value_length = cpu_to_le32(attr_len);
- }
- /* If we do not need to resize the attribute allocation we are done. */
- if (new_size <= attr_len)
- goto done_unm;
- /* Check if new size is allowed in $AttrDef. */
- err = ntfs_attr_size_bounds_check(vol, ni->type, new_size);
- if (unlikely(err)) {
- if (err == -ERANGE) {
- ntfs_error(vol->sb, "Write would cause the inode "
- "0x%lx to exceed the maximum size for "
- "its attribute type (0x%x). Aborting "
- "write.", vi->i_ino,
- le32_to_cpu(ni->type));
- } else {
- ntfs_error(vol->sb, "Inode 0x%lx has unknown "
- "attribute type 0x%x. Aborting "
- "write.", vi->i_ino,
- le32_to_cpu(ni->type));
- err = -EIO;
- }
- goto err_out2;
- }
- /*
- * Extend the attribute record to be able to store the new attribute
- * size.
- */
- if (new_size >= vol->mft_record_size || ntfs_attr_record_resize(m, a,
- le16_to_cpu(a->data.resident.value_offset) +
- new_size)) {
- /* Not enough space in the mft record. */
- ntfs_error(vol->sb, "Not enough space in the mft record for "
- "the resized attribute value. This is not "
- "supported yet. Aborting write.");
- err = -EOPNOTSUPP;
- goto err_out2;
- }
- /*
- * We have enough space in the mft record to fit the write. This
- * implies the attribute is smaller than the mft record and hence the
- * attribute must be in a single page and hence page->index must be 0.
- */
- BUG_ON(page->index);
- /*
- * If the beginning of the write is past the old size, enlarge the
- * attribute value up to the beginning of the write and fill it with
- * zeroes.
- */
- if (from > attr_len) {
- memset((u8*)a + le16_to_cpu(a->data.resident.value_offset) +
- attr_len, 0, from - attr_len);
- a->data.resident.value_length = cpu_to_le32(from);
- /* Zero the corresponding area in the page as well. */
- if (PageUptodate(page)) {
- kaddr = kmap_atomic(page, KM_USER0);
- memset(kaddr + attr_len, 0, from - attr_len);
- kunmap_atomic(kaddr, KM_USER0);
- flush_dcache_page(page);
- }
- }
- flush_dcache_mft_record_page(ctx->ntfs_ino);
- mark_mft_record_dirty(ctx->ntfs_ino);
-done_unm:
- ntfs_attr_put_search_ctx(ctx);
- unmap_mft_record(base_ni);
- /*
- * Because resident attributes are handled by memcpy() to/from the
- * corresponding MFT record, and because this form of i/o is byte
- * aligned rather than block aligned, there is no need to bring the
- * page uptodate here as in the non-resident case where we need to
- * bring the buffers straddled by the write uptodate before
- * generic_file_write() does the copying from userspace.
- *
- * We thus defer the uptodate bringing of the page region outside the
- * region written to to ntfs_commit_write(), which makes the code
- * simpler and saves one atomic kmap which is good.
- */
-done:
- ntfs_debug("Done.");
- return 0;
-err_out:
- if (err == -ENOMEM)
- ntfs_warning(vi->i_sb, "Error allocating memory required to "
- "prepare the write.");
- else {
- ntfs_error(vi->i_sb, "Resident attribute prepare write failed "
- "with error %i.", err);
- NVolSetErrors(vol);
- make_bad_inode(vi);
- }
-err_out2:
- if (ctx)
- ntfs_attr_put_search_ctx(ctx);
- if (m)
- unmap_mft_record(base_ni);
- return err;
-}
-
-/**
- * ntfs_commit_nonresident_write -
- *
- */
-static int ntfs_commit_nonresident_write(struct page *page,
- unsigned from, unsigned to)
-{
- s64 pos = ((s64)page->index << PAGE_CACHE_SHIFT) + to;
- struct inode *vi = page->mapping->host;
- struct buffer_head *bh, *head;
- unsigned int block_start, block_end, blocksize;
- BOOL partial;
-
- ntfs_debug("Entering for inode 0x%lx, attribute type 0x%x, page index "
- "0x%lx, from = %u, to = %u.", vi->i_ino,
- NTFS_I(vi)->type, page->index, from, to);
- blocksize = 1 << vi->i_blkbits;
-
- // FIXME: We need a whole slew of special cases in here for compressed
- // files for example...
- // For now, we know ntfs_prepare_write() would have failed so we can't
- // get here in any of the cases which we have to special case, so we
- // are just a ripped off, unrolled generic_commit_write().
-
- bh = head = page_buffers(page);
- block_start = 0;
- partial = FALSE;
- do {
- block_end = block_start + blocksize;
- if (block_end <= from || block_start >= to) {
- if (!buffer_uptodate(bh))
- partial = TRUE;
- } else {
- set_buffer_uptodate(bh);
- mark_buffer_dirty(bh);
- }
- } while (block_start = block_end, (bh = bh->b_this_page) != head);
- /*
- * If this is a partial write which happened to make all buffers
- * uptodate then we can optimize away a bogus ->readpage() for the next
- * read(). Here we 'discover' whether the page went uptodate as a
- * result of this (potentially partial) write.
- */
- if (!partial)
- SetPageUptodate(page);
- /*
- * Not convinced about this at all. See disparity comment above. For
- * now we know ntfs_prepare_write() would have failed in the write
- * exceeds i_size case, so this will never trigger which is fine.
- */
- if (pos > i_size_read(vi)) {
- ntfs_error(vi->i_sb, "Writing beyond the existing file size is "
- "not supported yet. Sorry.");
- return -EOPNOTSUPP;
- // vi->i_size = pos;
- // mark_inode_dirty(vi);
- }
- ntfs_debug("Done.");
- return 0;
-}
-
-/**
- * ntfs_commit_write - commit the received data
- *
- * This is called from generic_file_write() with i_sem held on the inode
- * (@page->mapping->host). The @page is locked but not kmap()ped. The source
- * data has already been copied into the @page. ntfs_prepare_write() has been
- * called before the data copied and it returned success so we can take the
- * results of various BUG checks and some error handling for granted.
- *
- * Need to mark modified blocks dirty so they get written out later when
- * ntfs_writepage() is invoked by the VM.
- *
- * Return 0 on success or -errno on error.
- *
- * Should be using generic_commit_write(). This marks buffers uptodate and
- * dirty, sets the page uptodate if all buffers in the page are uptodate, and
- * updates i_size if the end of io is beyond i_size. In that case, it also
- * marks the inode dirty.
- *
- * Cannot use generic_commit_write() due to ntfs specialities but can look at
- * it for implementation guidance.
- *
- * If things have gone as outlined in ntfs_prepare_write(), then we do not
- * need to do any page content modifications here at all, except in the write
- * to resident attribute case, where we need to do the uptodate bringing here
- * which we combine with the copying into the mft record which means we save
- * one atomic kmap.
- */
-static int ntfs_commit_write(struct file *file, struct page *page,
- unsigned from, unsigned to)
-{
- struct inode *vi = page->mapping->host;
- ntfs_inode *base_ni, *ni = NTFS_I(vi);
- char *kaddr, *kattr;
- ntfs_attr_search_ctx *ctx;
- MFT_RECORD *m;
- ATTR_RECORD *a;
- u32 attr_len;
- int err;
-
- ntfs_debug("Entering for inode 0x%lx, attribute type 0x%x, page index "
- "0x%lx, from = %u, to = %u.", vi->i_ino, ni->type,
- page->index, from, to);
- /* If the attribute is not resident, deal with it elsewhere. */
- if (NInoNonResident(ni)) {
- /* Only unnamed $DATA attributes can be compressed/encrypted. */
- if (ni->type == AT_DATA && !ni->name_len) {
- /* Encrypted files need separate handling. */
- if (NInoEncrypted(ni)) {
- // We never get here at present!
- BUG();
- }
- /* Compressed data streams are handled in compress.c. */
- if (NInoCompressed(ni)) {
- // TODO: Implement this!
- // return ntfs_write_compressed_block(page);
- // We never get here at present!
- BUG();
- }
- }
- /* Normal data stream. */
- return ntfs_commit_nonresident_write(page, from, to);
- }
- /*
- * Attribute is resident, implying it is not compressed, encrypted, or
- * sparse.
- */
- if (!NInoAttr(ni))
- base_ni = ni;
- else
- base_ni = ni->ext.base_ntfs_ino;
- /* Map, pin, and lock the mft record. */
- m = map_mft_record(base_ni);
- if (IS_ERR(m)) {
- err = PTR_ERR(m);
- m = NULL;
- ctx = NULL;
- goto err_out;
- }
- ctx = ntfs_attr_get_search_ctx(base_ni, m);
- if (unlikely(!ctx)) {
- err = -ENOMEM;
- goto err_out;
- }
- err = ntfs_attr_lookup(ni->type, ni->name, ni->name_len,
- CASE_SENSITIVE, 0, NULL, 0, ctx);
- if (unlikely(err)) {
- if (err == -ENOENT)
- err = -EIO;
- goto err_out;
- }
- a = ctx->attr;
- /* The total length of the attribute value. */
- attr_len = le32_to_cpu(a->data.resident.value_length);
- BUG_ON(from > attr_len);
- kattr = (u8*)a + le16_to_cpu(a->data.resident.value_offset);
- kaddr = kmap_atomic(page, KM_USER0);
- /* Copy the received data from the page to the mft record. */
- memcpy(kattr + from, kaddr + from, to - from);
- /* Update the attribute length if necessary. */
- if (to > attr_len) {
- attr_len = to;
- a->data.resident.value_length = cpu_to_le32(attr_len);
- }
- /*
- * If the page is not uptodate, bring the out of bounds area(s)
- * uptodate by copying data from the mft record to the page.
- */
- if (!PageUptodate(page)) {
- if (from > 0)
- memcpy(kaddr, kattr, from);
- if (to < attr_len)
- memcpy(kaddr + to, kattr + to, attr_len - to);
- /* Zero the region outside the end of the attribute value. */
- if (attr_len < PAGE_CACHE_SIZE)
- memset(kaddr + attr_len, 0, PAGE_CACHE_SIZE - attr_len);
- /*
- * The probability of not having done any of the above is
- * extremely small, so we just flush unconditionally.
- */
- flush_dcache_page(page);
- SetPageUptodate(page);
- }
- kunmap_atomic(kaddr, KM_USER0);
- /* Update i_size if necessary. */
- if (i_size_read(vi) < attr_len) {
- unsigned long flags;
-
- write_lock_irqsave(&ni->size_lock, flags);
- ni->allocated_size = ni->initialized_size = attr_len;
- i_size_write(vi, attr_len);
- write_unlock_irqrestore(&ni->size_lock, flags);
- }
- /* Mark the mft record dirty, so it gets written back. */
- flush_dcache_mft_record_page(ctx->ntfs_ino);
- mark_mft_record_dirty(ctx->ntfs_ino);
- ntfs_attr_put_search_ctx(ctx);
- unmap_mft_record(base_ni);
- ntfs_debug("Done.");
- return 0;
-err_out:
- if (err == -ENOMEM) {
- ntfs_warning(vi->i_sb, "Error allocating memory required to "
- "commit the write.");
- if (PageUptodate(page)) {
- ntfs_warning(vi->i_sb, "Page is uptodate, setting "
- "dirty so the write will be retried "
- "later on by the VM.");
- /*
- * Put the page on mapping->dirty_pages, but leave its
- * buffers' dirty state as-is.
- */
- __set_page_dirty_nobuffers(page);
- err = 0;
- } else
- ntfs_error(vi->i_sb, "Page is not uptodate. Written "
- "data has been lost.");
- } else {
- ntfs_error(vi->i_sb, "Resident attribute commit write failed "
- "with error %i.", err);
- NVolSetErrors(ni->vol);
- make_bad_inode(vi);
- }
- if (ctx)
- ntfs_attr_put_search_ctx(ctx);
- if (m)
- unmap_mft_record(base_ni);
- return err;
-}
-
#endif /* NTFS_RW */
/**
disk request queue. */
#ifdef NTFS_RW
.writepage = ntfs_writepage, /* Write dirty page to disk. */
- .prepare_write = ntfs_prepare_write, /* Prepare page and buffers
- ready to receive data. */
- .commit_write = ntfs_commit_write, /* Commit received data. */
#endif /* NTFS_RW */
+ .migratepage = buffer_migrate_page, /* Move a page cache page from
+ one physical page to an
+ other. */
};
/**
without touching the buffers
belonging to the page. */
#endif /* NTFS_RW */
+ .migratepage = buffer_migrate_page, /* Move a page cache page from
+ one physical page to an
+ other. */
};
#ifdef NTFS_RW
BUG_ON(!PageUptodate(page));
end = ofs + ni->itype.index.block_size;
- bh_size = 1 << VFS_I(ni)->i_blkbits;
+ bh_size = VFS_I(ni)->i_sb->s_blocksize;
spin_lock(&mapping->private_lock);
if (unlikely(!page_has_buffers(page))) {
spin_unlock(&mapping->private_lock);