#include <linux/writeback.h>
#include <linux/statfs.h>
#include <linux/compat.h>
+#include <linux/slab.h>
#include "ctree.h"
#include "disk-io.h"
#include "transaction.h"
static noinline int btrfs_copy_from_user(loff_t pos, int num_pages,
int write_bytes,
struct page **prepared_pages,
- const char __user *buf)
+ struct iov_iter *i)
{
- long page_fault = 0;
- int i;
+ size_t copied;
+ int pg = 0;
int offset = pos & (PAGE_CACHE_SIZE - 1);
- for (i = 0; i < num_pages && write_bytes > 0; i++, offset = 0) {
+ while (write_bytes > 0) {
size_t count = min_t(size_t,
PAGE_CACHE_SIZE - offset, write_bytes);
- struct page *page = prepared_pages[i];
- fault_in_pages_readable(buf, count);
+ struct page *page = prepared_pages[pg];
+again:
+ if (unlikely(iov_iter_fault_in_readable(i, count)))
+ return -EFAULT;
/* Copy data from userspace to the current page */
- kmap(page);
- page_fault = __copy_from_user(page_address(page) + offset,
- buf, count);
+ copied = iov_iter_copy_from_user(page, i, offset, count);
+
/* Flush processor's dcache for this page */
flush_dcache_page(page);
- kunmap(page);
- buf += count;
- write_bytes -= count;
+ iov_iter_advance(i, copied);
+ write_bytes -= copied;
- if (page_fault)
- break;
+ if (unlikely(copied == 0)) {
+ count = min_t(size_t, PAGE_CACHE_SIZE - offset,
+ iov_iter_single_seg_count(i));
+ goto again;
+ }
+
+ if (unlikely(copied < PAGE_CACHE_SIZE - offset)) {
+ offset += copied;
+ } else {
+ pg++;
+ offset = 0;
+ }
}
- return page_fault ? -EFAULT : 0;
+ return 0;
}
/*
root->sectorsize - 1) & ~((u64)root->sectorsize - 1);
end_of_last_block = start_pos + num_bytes - 1;
- err = btrfs_set_extent_delalloc(inode, start_pos, end_of_last_block);
- if (err)
- return err;
+ err = btrfs_set_extent_delalloc(inode, start_pos, end_of_last_block,
+ NULL);
+ BUG_ON(err);
for (i = 0; i < num_pages; i++) {
struct page *p = pages[i];
* at this time.
*/
}
- return err;
+ return 0;
}
/*
}
flags = em->flags;
if (skip_pinned && test_bit(EXTENT_FLAG_PINNED, &em->flags)) {
- if (em->start <= start &&
- (!testend || em->start + em->len >= start + len)) {
+ if (testend && em->start + em->len >= start + len) {
free_extent_map(em);
write_unlock(&em_tree->lock);
break;
}
- if (start < em->start) {
- len = em->start - start;
- } else {
+ start = em->start + em->len;
+ if (testend)
len = start + len - (em->start + em->len);
- start = em->start + em->len;
- }
free_extent_map(em);
write_unlock(&em_tree->lock);
continue;
}
static int extent_mergeable(struct extent_buffer *leaf, int slot,
- u64 objectid, u64 bytenr, u64 *start, u64 *end)
+ u64 objectid, u64 bytenr, u64 orig_offset,
+ u64 *start, u64 *end)
{
struct btrfs_file_extent_item *fi;
struct btrfs_key key;
fi = btrfs_item_ptr(leaf, slot, struct btrfs_file_extent_item);
if (btrfs_file_extent_type(leaf, fi) != BTRFS_FILE_EXTENT_REG ||
btrfs_file_extent_disk_bytenr(leaf, fi) != bytenr ||
+ btrfs_file_extent_offset(leaf, fi) != key.offset - orig_offset ||
btrfs_file_extent_compression(leaf, fi) ||
btrfs_file_extent_encryption(leaf, fi) ||
btrfs_file_extent_other_encoding(leaf, fi))
u64 split;
int del_nr = 0;
int del_slot = 0;
+ int recow;
int ret;
btrfs_drop_extent_cache(inode, start, end - 1, 0);
path = btrfs_alloc_path();
BUG_ON(!path);
again:
+ recow = 0;
split = start;
key.objectid = inode->i_ino;
key.type = BTRFS_EXTENT_DATA_KEY;
bytenr = btrfs_file_extent_disk_bytenr(leaf, fi);
num_bytes = btrfs_file_extent_disk_num_bytes(leaf, fi);
orig_offset = key.offset - btrfs_file_extent_offset(leaf, fi);
+ memcpy(&new_key, &key, sizeof(new_key));
+
+ if (start == key.offset && end < extent_end) {
+ other_start = 0;
+ other_end = start;
+ if (extent_mergeable(leaf, path->slots[0] - 1,
+ inode->i_ino, bytenr, orig_offset,
+ &other_start, &other_end)) {
+ new_key.offset = end;
+ btrfs_set_item_key_safe(trans, root, path, &new_key);
+ fi = btrfs_item_ptr(leaf, path->slots[0],
+ struct btrfs_file_extent_item);
+ btrfs_set_file_extent_num_bytes(leaf, fi,
+ extent_end - end);
+ btrfs_set_file_extent_offset(leaf, fi,
+ end - orig_offset);
+ fi = btrfs_item_ptr(leaf, path->slots[0] - 1,
+ struct btrfs_file_extent_item);
+ btrfs_set_file_extent_num_bytes(leaf, fi,
+ end - other_start);
+ btrfs_mark_buffer_dirty(leaf);
+ goto out;
+ }
+ }
+
+ if (start > key.offset && end == extent_end) {
+ other_start = end;
+ other_end = 0;
+ if (extent_mergeable(leaf, path->slots[0] + 1,
+ inode->i_ino, bytenr, orig_offset,
+ &other_start, &other_end)) {
+ fi = btrfs_item_ptr(leaf, path->slots[0],
+ struct btrfs_file_extent_item);
+ btrfs_set_file_extent_num_bytes(leaf, fi,
+ start - key.offset);
+ path->slots[0]++;
+ new_key.offset = start;
+ btrfs_set_item_key_safe(trans, root, path, &new_key);
+
+ fi = btrfs_item_ptr(leaf, path->slots[0],
+ struct btrfs_file_extent_item);
+ btrfs_set_file_extent_num_bytes(leaf, fi,
+ other_end - start);
+ btrfs_set_file_extent_offset(leaf, fi,
+ start - orig_offset);
+ btrfs_mark_buffer_dirty(leaf);
+ goto out;
+ }
+ }
while (start > key.offset || end < extent_end) {
if (key.offset == start)
split = end;
- memcpy(&new_key, &key, sizeof(new_key));
new_key.offset = split;
ret = btrfs_duplicate_item(trans, root, path, &new_key);
if (ret == -EAGAIN) {
path->slots[0]--;
extent_end = end;
}
+ recow = 1;
}
- fi = btrfs_item_ptr(leaf, path->slots[0],
- struct btrfs_file_extent_item);
-
other_start = end;
other_end = 0;
- if (extent_mergeable(leaf, path->slots[0] + 1, inode->i_ino,
- bytenr, &other_start, &other_end)) {
+ if (extent_mergeable(leaf, path->slots[0] + 1,
+ inode->i_ino, bytenr, orig_offset,
+ &other_start, &other_end)) {
+ if (recow) {
+ btrfs_release_path(root, path);
+ goto again;
+ }
extent_end = other_end;
del_slot = path->slots[0] + 1;
del_nr++;
}
other_start = 0;
other_end = start;
- if (extent_mergeable(leaf, path->slots[0] - 1, inode->i_ino,
- bytenr, &other_start, &other_end)) {
+ if (extent_mergeable(leaf, path->slots[0] - 1,
+ inode->i_ino, bytenr, orig_offset,
+ &other_start, &other_end)) {
+ if (recow) {
+ btrfs_release_path(root, path);
+ goto again;
+ }
key.offset = other_start;
del_slot = path->slots[0];
del_nr++;
BUG_ON(ret);
}
if (del_nr == 0) {
+ fi = btrfs_item_ptr(leaf, path->slots[0],
+ struct btrfs_file_extent_item);
btrfs_set_file_extent_type(leaf, fi,
BTRFS_FILE_EXTENT_REG);
btrfs_mark_buffer_dirty(leaf);
- goto out;
- }
-
- fi = btrfs_item_ptr(leaf, del_slot - 1,
- struct btrfs_file_extent_item);
- btrfs_set_file_extent_type(leaf, fi, BTRFS_FILE_EXTENT_REG);
- btrfs_set_file_extent_num_bytes(leaf, fi,
- extent_end - key.offset);
- btrfs_mark_buffer_dirty(leaf);
+ } else {
+ fi = btrfs_item_ptr(leaf, del_slot - 1,
+ struct btrfs_file_extent_item);
+ btrfs_set_file_extent_type(leaf, fi,
+ BTRFS_FILE_EXTENT_REG);
+ btrfs_set_file_extent_num_bytes(leaf, fi,
+ extent_end - key.offset);
+ btrfs_mark_buffer_dirty(leaf);
- ret = btrfs_del_items(trans, root, path, del_slot, del_nr);
- BUG_ON(ret);
+ ret = btrfs_del_items(trans, root, path, del_slot, del_nr);
+ BUG_ON(ret);
+ }
out:
btrfs_free_path(path);
return 0;
loff_t pos, unsigned long first_index,
unsigned long last_index, size_t write_bytes)
{
+ struct extent_state *cached_state = NULL;
int i;
unsigned long index = pos >> PAGE_CACHE_SHIFT;
struct inode *inode = fdentry(file)->d_inode;
}
if (start_pos < inode->i_size) {
struct btrfs_ordered_extent *ordered;
- lock_extent(&BTRFS_I(inode)->io_tree,
- start_pos, last_pos - 1, GFP_NOFS);
+ lock_extent_bits(&BTRFS_I(inode)->io_tree,
+ start_pos, last_pos - 1, 0, &cached_state,
+ GFP_NOFS);
ordered = btrfs_lookup_first_ordered_extent(inode,
last_pos - 1);
if (ordered &&
ordered->file_offset + ordered->len > start_pos &&
ordered->file_offset < last_pos) {
btrfs_put_ordered_extent(ordered);
- unlock_extent(&BTRFS_I(inode)->io_tree,
- start_pos, last_pos - 1, GFP_NOFS);
+ unlock_extent_cached(&BTRFS_I(inode)->io_tree,
+ start_pos, last_pos - 1,
+ &cached_state, GFP_NOFS);
for (i = 0; i < num_pages; i++) {
unlock_page(pages[i]);
page_cache_release(pages[i]);
if (ordered)
btrfs_put_ordered_extent(ordered);
- clear_extent_bits(&BTRFS_I(inode)->io_tree, start_pos,
+ clear_extent_bit(&BTRFS_I(inode)->io_tree, start_pos,
last_pos - 1, EXTENT_DIRTY | EXTENT_DELALLOC |
- EXTENT_DO_ACCOUNTING,
+ EXTENT_DO_ACCOUNTING, 0, 0, &cached_state,
GFP_NOFS);
- unlock_extent(&BTRFS_I(inode)->io_tree,
- start_pos, last_pos - 1, GFP_NOFS);
+ unlock_extent_cached(&BTRFS_I(inode)->io_tree,
+ start_pos, last_pos - 1, &cached_state,
+ GFP_NOFS);
}
for (i = 0; i < num_pages; i++) {
clear_page_dirty_for_io(pages[i]);
return 0;
}
-static ssize_t btrfs_file_write(struct file *file, const char __user *buf,
- size_t count, loff_t *ppos)
+static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
+ const struct iovec *iov,
+ unsigned long nr_segs, loff_t pos)
{
- loff_t pos;
+ struct file *file = iocb->ki_filp;
+ struct inode *inode = fdentry(file)->d_inode;
+ struct btrfs_root *root = BTRFS_I(inode)->root;
+ struct page *pinned[2];
+ struct page **pages = NULL;
+ struct iov_iter i;
+ loff_t *ppos = &iocb->ki_pos;
loff_t start_pos;
ssize_t num_written = 0;
ssize_t err = 0;
+ size_t count;
+ size_t ocount;
int ret = 0;
- struct inode *inode = fdentry(file)->d_inode;
- struct btrfs_root *root = BTRFS_I(inode)->root;
- struct page **pages = NULL;
int nrptrs;
- struct page *pinned[2];
unsigned long first_index;
unsigned long last_index;
int will_write;
+ int buffered = 0;
- will_write = ((file->f_flags & O_SYNC) || IS_SYNC(inode) ||
+ will_write = ((file->f_flags & O_DSYNC) || IS_SYNC(inode) ||
(file->f_flags & O_DIRECT));
- nrptrs = min((count + PAGE_CACHE_SIZE - 1) / PAGE_CACHE_SIZE,
- PAGE_CACHE_SIZE / (sizeof(struct page *)));
pinned[0] = NULL;
pinned[1] = NULL;
- pos = *ppos;
start_pos = pos;
vfs_check_frozen(inode->i_sb, SB_FREEZE_WRITE);
- /* do the reserve before the mutex lock in case we have to do some
- * flushing. We wouldn't deadlock, but this is more polite.
- */
- err = btrfs_reserve_metadata_for_delalloc(root, inode, 1);
- if (err)
- goto out_nolock;
-
mutex_lock(&inode->i_mutex);
+ err = generic_segment_checks(iov, &nr_segs, &ocount, VERIFY_READ);
+ if (err)
+ goto out;
+ count = ocount;
+
current->backing_dev_info = inode->i_mapping->backing_dev_info;
err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode));
if (err)
goto out;
file_update_time(file);
+ BTRFS_I(inode)->sequence++;
+
+ if (unlikely(file->f_flags & O_DIRECT)) {
+ num_written = generic_file_direct_write(iocb, iov, &nr_segs,
+ pos, ppos, count,
+ ocount);
+ /*
+ * the generic O_DIRECT will update in-memory i_size after the
+ * DIOs are done. But our endio handlers that update the on
+ * disk i_size never update past the in memory i_size. So we
+ * need one more update here to catch any additions to the
+ * file
+ */
+ if (inode->i_size != BTRFS_I(inode)->disk_i_size) {
+ btrfs_ordered_update_i_size(inode, inode->i_size, NULL);
+ mark_inode_dirty(inode);
+ }
+
+ if (num_written < 0) {
+ ret = num_written;
+ num_written = 0;
+ goto out;
+ } else if (num_written == count) {
+ /* pick up pos changes done by the generic code */
+ pos = *ppos;
+ goto out;
+ }
+ /*
+ * We are going to do buffered for the rest of the range, so we
+ * need to make sure to invalidate the buffered pages when we're
+ * done.
+ */
+ buffered = 1;
+ pos += num_written;
+ }
+ iov_iter_init(&i, iov, nr_segs, count, num_written);
+ nrptrs = min((iov_iter_count(&i) + PAGE_CACHE_SIZE - 1) /
+ PAGE_CACHE_SIZE, PAGE_CACHE_SIZE /
+ (sizeof(struct page *)));
pages = kmalloc(nrptrs * sizeof(struct page *), GFP_KERNEL);
/* generic_write_checks can change our pos */
start_pos = pos;
- BTRFS_I(inode)->sequence++;
first_index = pos >> PAGE_CACHE_SHIFT;
- last_index = (pos + count) >> PAGE_CACHE_SHIFT;
+ last_index = (pos + iov_iter_count(&i)) >> PAGE_CACHE_SHIFT;
/*
* there are lots of better ways to do this, but this code
unlock_page(pinned[0]);
}
}
- if ((pos + count) & (PAGE_CACHE_SIZE - 1)) {
+ if ((pos + iov_iter_count(&i)) & (PAGE_CACHE_SIZE - 1)) {
pinned[1] = grab_cache_page(inode->i_mapping, last_index);
if (!PageUptodate(pinned[1])) {
ret = btrfs_readpage(NULL, pinned[1]);
}
}
- while (count > 0) {
+ while (iov_iter_count(&i) > 0) {
size_t offset = pos & (PAGE_CACHE_SIZE - 1);
- size_t write_bytes = min(count, nrptrs *
- (size_t)PAGE_CACHE_SIZE -
+ size_t write_bytes = min(iov_iter_count(&i),
+ nrptrs * (size_t)PAGE_CACHE_SIZE -
offset);
size_t num_pages = (write_bytes + PAGE_CACHE_SIZE - 1) >>
PAGE_CACHE_SHIFT;
WARN_ON(num_pages > nrptrs);
memset(pages, 0, sizeof(struct page *) * nrptrs);
- ret = btrfs_check_data_free_space(root, inode, write_bytes);
+ ret = btrfs_delalloc_reserve_space(inode, write_bytes);
if (ret)
goto out;
pos, first_index, last_index,
write_bytes);
if (ret) {
- btrfs_free_reserved_data_space(root, inode,
- write_bytes);
+ btrfs_delalloc_release_space(inode, write_bytes);
goto out;
}
ret = btrfs_copy_from_user(pos, num_pages,
- write_bytes, pages, buf);
- if (ret) {
- btrfs_free_reserved_data_space(root, inode,
- write_bytes);
- btrfs_drop_pages(pages, num_pages);
- goto out;
+ write_bytes, pages, &i);
+ if (ret == 0) {
+ dirty_and_release_pages(NULL, root, file, pages,
+ num_pages, pos, write_bytes);
}
- ret = dirty_and_release_pages(NULL, root, file, pages,
- num_pages, pos, write_bytes);
btrfs_drop_pages(pages, num_pages);
if (ret) {
- btrfs_free_reserved_data_space(root, inode,
- write_bytes);
+ btrfs_delalloc_release_space(inode, write_bytes);
goto out;
}
btrfs_throttle(root);
}
- buf += write_bytes;
- count -= write_bytes;
pos += write_bytes;
num_written += write_bytes;
mutex_unlock(&inode->i_mutex);
if (ret)
err = ret;
- btrfs_unreserve_metadata_for_delalloc(root, inode, 1);
-out_nolock:
kfree(pages);
if (pinned[0])
page_cache_release(pinned[0]);
if (err)
num_written = err;
- if ((file->f_flags & O_SYNC) || IS_SYNC(inode)) {
- trans = btrfs_start_transaction(root, 1);
+ if ((file->f_flags & O_DSYNC) || IS_SYNC(inode)) {
+ trans = btrfs_start_transaction(root, 0);
ret = btrfs_log_dentry_safe(trans, root,
file->f_dentry);
if (ret == 0) {
btrfs_end_transaction(trans, root);
}
}
- if (file->f_flags & O_DIRECT) {
+ if (file->f_flags & O_DIRECT && buffered) {
invalidate_mapping_pages(inode->i_mapping,
start_pos >> PAGE_CACHE_SHIFT,
(start_pos + num_written - 1) >> PAGE_CACHE_SHIFT);
* important optimization for directories because holding the mutex prevents
* new operations on the dir while we write to disk.
*/
-int btrfs_sync_file(struct file *file, struct dentry *dentry, int datasync)
+int btrfs_sync_file(struct file *file, int datasync)
{
+ struct dentry *dentry = file->f_path.dentry;
struct inode *inode = dentry->d_inode;
struct btrfs_root *root = BTRFS_I(inode)->root;
int ret = 0;
if (file && file->private_data)
btrfs_ioctl_trans_end(file);
- trans = btrfs_start_transaction(root, 1);
- if (!trans) {
- ret = -ENOMEM;
+ trans = btrfs_start_transaction(root, 0);
+ if (IS_ERR(trans)) {
+ ret = PTR_ERR(trans);
goto out;
}
}
mutex_lock(&dentry->d_inode->i_mutex);
out:
- return ret > 0 ? EIO : ret;
+ return ret > 0 ? -EIO : ret;
}
static const struct vm_operations_struct btrfs_file_vm_ops = {
.read = do_sync_read,
.aio_read = generic_file_aio_read,
.splice_read = generic_file_splice_read,
- .write = btrfs_file_write,
+ .aio_write = btrfs_file_aio_write,
.mmap = btrfs_file_mmap,
.open = generic_file_open,
.release = btrfs_release_file,
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff