Commit 5f1b5664 authored by David Sterba's avatar David Sterba

Merge branch 'chandan/prep-subpage-blocksize' into for-chris-4.6

# Conflicts:
#	fs/btrfs/file.c
parents 388f7b1d 65bfa658
......@@ -311,7 +311,7 @@ struct tree_mod_root {
struct tree_mod_elem {
struct rb_node node;
u64 index; /* shifted logical */
u64 logical;
u64 seq;
enum mod_log_op op;
......@@ -435,11 +435,11 @@ void btrfs_put_tree_mod_seq(struct btrfs_fs_info *fs_info,
/*
* key order of the log:
* index -> sequence
* node/leaf start address -> sequence
*
* the index is the shifted logical of the *new* root node for root replace
* operations, or the shifted logical of the affected block for all other
* operations.
* The 'start address' is the logical address of the *new* root node
* for root replace operations, or the logical address of the affected
* block for all other operations.
*
* Note: must be called with write lock (tree_mod_log_write_lock).
*/
......@@ -460,9 +460,9 @@ __tree_mod_log_insert(struct btrfs_fs_info *fs_info, struct tree_mod_elem *tm)
while (*new) {
cur = container_of(*new, struct tree_mod_elem, node);
parent = *new;
if (cur->index < tm->index)
if (cur->logical < tm->logical)
new = &((*new)->rb_left);
else if (cur->index > tm->index)
else if (cur->logical > tm->logical)
new = &((*new)->rb_right);
else if (cur->seq < tm->seq)
new = &((*new)->rb_left);
......@@ -523,7 +523,7 @@ alloc_tree_mod_elem(struct extent_buffer *eb, int slot,
if (!tm)
return NULL;
tm->index = eb->start >> PAGE_CACHE_SHIFT;
tm->logical = eb->start;
if (op != MOD_LOG_KEY_ADD) {
btrfs_node_key(eb, &tm->key, slot);
tm->blockptr = btrfs_node_blockptr(eb, slot);
......@@ -588,7 +588,7 @@ tree_mod_log_insert_move(struct btrfs_fs_info *fs_info,
goto free_tms;
}
tm->index = eb->start >> PAGE_CACHE_SHIFT;
tm->logical = eb->start;
tm->slot = src_slot;
tm->move.dst_slot = dst_slot;
tm->move.nr_items = nr_items;
......@@ -699,7 +699,7 @@ tree_mod_log_insert_root(struct btrfs_fs_info *fs_info,
goto free_tms;
}
tm->index = new_root->start >> PAGE_CACHE_SHIFT;
tm->logical = new_root->start;
tm->old_root.logical = old_root->start;
tm->old_root.level = btrfs_header_level(old_root);
tm->generation = btrfs_header_generation(old_root);
......@@ -739,16 +739,15 @@ __tree_mod_log_search(struct btrfs_fs_info *fs_info, u64 start, u64 min_seq,
struct rb_node *node;
struct tree_mod_elem *cur = NULL;
struct tree_mod_elem *found = NULL;
u64 index = start >> PAGE_CACHE_SHIFT;
tree_mod_log_read_lock(fs_info);
tm_root = &fs_info->tree_mod_log;
node = tm_root->rb_node;
while (node) {
cur = container_of(node, struct tree_mod_elem, node);
if (cur->index < index) {
if (cur->logical < start) {
node = node->rb_left;
} else if (cur->index > index) {
} else if (cur->logical > start) {
node = node->rb_right;
} else if (cur->seq < min_seq) {
node = node->rb_left;
......@@ -1230,9 +1229,10 @@ __tree_mod_log_oldest_root(struct btrfs_fs_info *fs_info,
return NULL;
/*
* the very last operation that's logged for a root is the replacement
* operation (if it is replaced at all). this has the index of the *new*
* root, making it the very first operation that's logged for this root.
* the very last operation that's logged for a root is the
* replacement operation (if it is replaced at all). this has
* the logical address of the *new* root, making it the very
* first operation that's logged for this root.
*/
while (1) {
tm = tree_mod_log_search_oldest(fs_info, root_logical,
......@@ -1336,7 +1336,7 @@ __tree_mod_log_rewind(struct btrfs_fs_info *fs_info, struct extent_buffer *eb,
if (!next)
break;
tm = container_of(next, struct tree_mod_elem, node);
if (tm->index != first_tm->index)
if (tm->logical != first_tm->logical)
break;
}
tree_mod_log_read_unlock(fs_info);
......
......@@ -2353,6 +2353,9 @@ struct btrfs_map_token {
unsigned long offset;
};
#define BTRFS_BYTES_TO_BLKS(fs_info, bytes) \
((bytes) >> (fs_info)->sb->s_blocksize_bits)
static inline void btrfs_init_map_token (struct btrfs_map_token *token)
{
token->kaddr = NULL;
......@@ -4027,7 +4030,7 @@ int btrfs_unlink_subvol(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct inode *dir, u64 objectid,
const char *name, int name_len);
int btrfs_truncate_page(struct inode *inode, loff_t from, loff_t len,
int btrfs_truncate_block(struct inode *inode, loff_t from, loff_t len,
int front);
int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
......
......@@ -3186,7 +3186,8 @@ static int __extent_read_full_page(struct extent_io_tree *tree,
while (1) {
lock_extent(tree, start, end);
ordered = btrfs_lookup_ordered_extent(inode, start);
ordered = btrfs_lookup_ordered_range(inode, start,
PAGE_CACHE_SIZE);
if (!ordered)
break;
unlock_extent(tree, start, end);
......
......@@ -172,6 +172,7 @@ static int __btrfs_lookup_bio_sums(struct btrfs_root *root,
u64 item_start_offset = 0;
u64 item_last_offset = 0;
u64 disk_bytenr;
u64 page_bytes_left;
u32 diff;
int nblocks;
int bio_index = 0;
......@@ -220,6 +221,8 @@ static int __btrfs_lookup_bio_sums(struct btrfs_root *root,
disk_bytenr = (u64)bio->bi_iter.bi_sector << 9;
if (dio)
offset = logical_offset;
page_bytes_left = bvec->bv_len;
while (bio_index < bio->bi_vcnt) {
if (!dio)
offset = page_offset(bvec->bv_page) + bvec->bv_offset;
......@@ -243,7 +246,7 @@ static int __btrfs_lookup_bio_sums(struct btrfs_root *root,
if (BTRFS_I(inode)->root->root_key.objectid ==
BTRFS_DATA_RELOC_TREE_OBJECTID) {
set_extent_bits(io_tree, offset,
offset + bvec->bv_len - 1,
offset + root->sectorsize - 1,
EXTENT_NODATASUM, GFP_NOFS);
} else {
btrfs_info(BTRFS_I(inode)->root->fs_info,
......@@ -281,11 +284,17 @@ static int __btrfs_lookup_bio_sums(struct btrfs_root *root,
found:
csum += count * csum_size;
nblocks -= count;
bio_index += count;
while (count--) {
disk_bytenr += bvec->bv_len;
offset += bvec->bv_len;
bvec++;
disk_bytenr += root->sectorsize;
offset += root->sectorsize;
page_bytes_left -= root->sectorsize;
if (!page_bytes_left) {
bio_index++;
bvec++;
page_bytes_left = bvec->bv_len;
}
}
}
btrfs_free_path(path);
......@@ -432,6 +441,8 @@ int btrfs_csum_one_bio(struct btrfs_root *root, struct inode *inode,
struct bio_vec *bvec = bio->bi_io_vec;
int bio_index = 0;
int index;
int nr_sectors;
int i;
unsigned long total_bytes = 0;
unsigned long this_sum_bytes = 0;
u64 offset;
......@@ -459,41 +470,56 @@ int btrfs_csum_one_bio(struct btrfs_root *root, struct inode *inode,
if (!contig)
offset = page_offset(bvec->bv_page) + bvec->bv_offset;
if (offset >= ordered->file_offset + ordered->len ||
offset < ordered->file_offset) {
unsigned long bytes_left;
sums->len = this_sum_bytes;
this_sum_bytes = 0;
btrfs_add_ordered_sum(inode, ordered, sums);
btrfs_put_ordered_extent(ordered);
data = kmap_atomic(bvec->bv_page);
bytes_left = bio->bi_iter.bi_size - total_bytes;
nr_sectors = BTRFS_BYTES_TO_BLKS(root->fs_info,
bvec->bv_len + root->sectorsize
- 1);
for (i = 0; i < nr_sectors; i++) {
if (offset >= ordered->file_offset + ordered->len ||
offset < ordered->file_offset) {
unsigned long bytes_left;
kunmap_atomic(data);
sums->len = this_sum_bytes;
this_sum_bytes = 0;
btrfs_add_ordered_sum(inode, ordered, sums);
btrfs_put_ordered_extent(ordered);
bytes_left = bio->bi_iter.bi_size - total_bytes;
sums = kzalloc(btrfs_ordered_sum_size(root, bytes_left),
GFP_NOFS);
BUG_ON(!sums); /* -ENOMEM */
sums->len = bytes_left;
ordered = btrfs_lookup_ordered_extent(inode,
offset);
ASSERT(ordered); /* Logic error */
sums->bytenr = ((u64)bio->bi_iter.bi_sector << 9)
+ total_bytes;
index = 0;
data = kmap_atomic(bvec->bv_page);
}
sums = kzalloc(btrfs_ordered_sum_size(root, bytes_left),
GFP_NOFS);
BUG_ON(!sums); /* -ENOMEM */
sums->len = bytes_left;
ordered = btrfs_lookup_ordered_extent(inode, offset);
BUG_ON(!ordered); /* Logic error */
sums->bytenr = ((u64)bio->bi_iter.bi_sector << 9) +
total_bytes;
index = 0;
sums->sums[index] = ~(u32)0;
sums->sums[index]
= btrfs_csum_data(data + bvec->bv_offset
+ (i * root->sectorsize),
sums->sums[index],
root->sectorsize);
btrfs_csum_final(sums->sums[index],
(char *)(sums->sums + index));
index++;
offset += root->sectorsize;
this_sum_bytes += root->sectorsize;
total_bytes += root->sectorsize;
}
data = kmap_atomic(bvec->bv_page);
sums->sums[index] = ~(u32)0;
sums->sums[index] = btrfs_csum_data(data + bvec->bv_offset,
sums->sums[index],
bvec->bv_len);
kunmap_atomic(data);
btrfs_csum_final(sums->sums[index],
(char *)(sums->sums + index));
bio_index++;
index++;
total_bytes += bvec->bv_len;
this_sum_bytes += bvec->bv_len;
offset += bvec->bv_len;
bvec++;
}
this_sum_bytes = 0;
......
......@@ -498,7 +498,7 @@ int btrfs_dirty_pages(struct btrfs_root *root, struct inode *inode,
loff_t isize = i_size_read(inode);
start_pos = pos & ~((u64)root->sectorsize - 1);
num_bytes = ALIGN(write_bytes + pos - start_pos, root->sectorsize);
num_bytes = round_up(write_bytes + pos - start_pos, root->sectorsize);
end_of_last_block = start_pos + num_bytes - 1;
err = btrfs_set_extent_delalloc(inode, start_pos, end_of_last_block,
......@@ -1379,16 +1379,19 @@ static noinline int prepare_pages(struct inode *inode, struct page **pages,
static noinline int
lock_and_cleanup_extent_if_need(struct inode *inode, struct page **pages,
size_t num_pages, loff_t pos,
size_t write_bytes,
u64 *lockstart, u64 *lockend,
struct extent_state **cached_state)
{
struct btrfs_root *root = BTRFS_I(inode)->root;
u64 start_pos;
u64 last_pos;
int i;
int ret = 0;
start_pos = pos & ~((u64)PAGE_CACHE_SIZE - 1);
last_pos = start_pos + ((u64)num_pages << PAGE_CACHE_SHIFT) - 1;
start_pos = round_down(pos, root->sectorsize);
last_pos = start_pos
+ round_up(pos + write_bytes - start_pos, root->sectorsize) - 1;
if (start_pos < inode->i_size) {
struct btrfs_ordered_extent *ordered;
......@@ -1503,6 +1506,7 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
while (iov_iter_count(i) > 0) {
size_t offset = pos & (PAGE_CACHE_SIZE - 1);
size_t sector_offset;
size_t write_bytes = min(iov_iter_count(i),
nrptrs * (size_t)PAGE_CACHE_SIZE -
offset);
......@@ -1511,6 +1515,8 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
size_t reserve_bytes;
size_t dirty_pages;
size_t copied;
size_t dirty_sectors;
size_t num_sectors;
WARN_ON(num_pages > nrptrs);
......@@ -1523,7 +1529,9 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
break;
}
reserve_bytes = num_pages << PAGE_CACHE_SHIFT;
sector_offset = pos & (root->sectorsize - 1);
reserve_bytes = round_up(write_bytes + sector_offset,
root->sectorsize);
if (BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW |
BTRFS_INODE_PREALLOC)) {
......@@ -1542,7 +1550,9 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
*/
num_pages = DIV_ROUND_UP(write_bytes + offset,
PAGE_CACHE_SIZE);
reserve_bytes = num_pages << PAGE_CACHE_SHIFT;
reserve_bytes = round_up(write_bytes
+ sector_offset,
root->sectorsize);
goto reserve_metadata;
}
}
......@@ -1576,8 +1586,8 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
break;
ret = lock_and_cleanup_extent_if_need(inode, pages, num_pages,
pos, &lockstart, &lockend,
&cached_state);
pos, write_bytes, &lockstart,
&lockend, &cached_state);
if (ret < 0) {
if (ret == -EAGAIN)
goto again;
......@@ -1612,9 +1622,16 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
* we still have an outstanding extent for the chunk we actually
* managed to copy.
*/
if (num_pages > dirty_pages) {
release_bytes = (num_pages - dirty_pages) <<
PAGE_CACHE_SHIFT;
num_sectors = BTRFS_BYTES_TO_BLKS(root->fs_info,
reserve_bytes);
dirty_sectors = round_up(copied + sector_offset,
root->sectorsize);
dirty_sectors = BTRFS_BYTES_TO_BLKS(root->fs_info,
dirty_sectors);
if (num_sectors > dirty_sectors) {
release_bytes = (write_bytes - copied)
& ~((u64)root->sectorsize - 1);
if (copied > 0) {
spin_lock(&BTRFS_I(inode)->lock);
BTRFS_I(inode)->outstanding_extents++;
......@@ -1633,7 +1650,8 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
}
}
release_bytes = dirty_pages << PAGE_CACHE_SHIFT;
release_bytes = round_up(copied + sector_offset,
root->sectorsize);
if (copied > 0)
ret = btrfs_dirty_pages(root, inode, pages,
......@@ -1654,8 +1672,7 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
if (only_release_metadata && copied > 0) {
lockstart = round_down(pos, root->sectorsize);
lockend = lockstart +
(dirty_pages << PAGE_CACHE_SHIFT) - 1;
lockend = round_up(pos + copied, root->sectorsize) - 1;
set_extent_bit(&BTRFS_I(inode)->io_tree, lockstart,
lockend, EXTENT_NORESERVE, NULL,
......@@ -1761,6 +1778,8 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
ssize_t err;
loff_t pos;
size_t count;
loff_t oldsize;
int clean_page = 0;
inode_lock(inode);
err = generic_write_checks(iocb, from);
......@@ -1799,14 +1818,17 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
pos = iocb->ki_pos;
count = iov_iter_count(from);
start_pos = round_down(pos, root->sectorsize);
if (start_pos > i_size_read(inode)) {
oldsize = i_size_read(inode);
if (start_pos > oldsize) {
/* Expand hole size to cover write data, preventing empty gap */
end_pos = round_up(pos + count, root->sectorsize);
err = btrfs_cont_expand(inode, i_size_read(inode), end_pos);
err = btrfs_cont_expand(inode, oldsize, end_pos);
if (err) {
inode_unlock(inode);
goto out;
}
if (start_pos > round_up(oldsize, root->sectorsize))
clean_page = 1;
}
if (sync)
......@@ -1818,6 +1840,9 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
num_written = __btrfs_buffered_write(file, from, pos);
if (num_written > 0)
iocb->ki_pos = pos + num_written;
if (clean_page)
pagecache_isize_extended(inode, oldsize,
i_size_read(inode));
}
inode_unlock(inode);
......@@ -2293,10 +2318,10 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
int ret = 0;
int err = 0;
unsigned int rsv_count;
bool same_page;
bool same_block;
bool no_holes = btrfs_fs_incompat(root->fs_info, NO_HOLES);
u64 ino_size;
bool truncated_page = false;
bool truncated_block = false;
bool updated_inode = false;
ret = btrfs_wait_ordered_range(inode, offset, len);
......@@ -2304,7 +2329,7 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
return ret;
inode_lock(inode);
ino_size = round_up(inode->i_size, PAGE_CACHE_SIZE);
ino_size = round_up(inode->i_size, root->sectorsize);
ret = find_first_non_hole(inode, &offset, &len);
if (ret < 0)
goto out_only_mutex;
......@@ -2317,31 +2342,30 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
lockstart = round_up(offset, BTRFS_I(inode)->root->sectorsize);
lockend = round_down(offset + len,
BTRFS_I(inode)->root->sectorsize) - 1;
same_page = ((offset >> PAGE_CACHE_SHIFT) ==
((offset + len - 1) >> PAGE_CACHE_SHIFT));
same_block = (BTRFS_BYTES_TO_BLKS(root->fs_info, offset))
== (BTRFS_BYTES_TO_BLKS(root->fs_info, offset + len - 1));
/*
* We needn't truncate any page which is beyond the end of the file
* We needn't truncate any block which is beyond the end of the file
* because we are sure there is no data there.
*/
/*
* Only do this if we are in the same page and we aren't doing the
* entire page.
* Only do this if we are in the same block and we aren't doing the
* entire block.
*/
if (same_page && len < PAGE_CACHE_SIZE) {
if (same_block && len < root->sectorsize) {
if (offset < ino_size) {
truncated_page = true;
ret = btrfs_truncate_page(inode, offset, len, 0);
truncated_block = true;
ret = btrfs_truncate_block(inode, offset, len, 0);
} else {
ret = 0;
}
goto out_only_mutex;
}
/* zero back part of the first page */
/* zero back part of the first block */
if (offset < ino_size) {
truncated_page = true;
ret = btrfs_truncate_page(inode, offset, 0, 0);
truncated_block = true;
ret = btrfs_truncate_block(inode, offset, 0, 0);
if (ret) {
inode_unlock(inode);
return ret;
......@@ -2376,9 +2400,10 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
if (!ret) {
/* zero the front end of the last page */
if (tail_start + tail_len < ino_size) {
truncated_page = true;
ret = btrfs_truncate_page(inode,
tail_start + tail_len, 0, 1);
truncated_block = true;
ret = btrfs_truncate_block(inode,
tail_start + tail_len,
0, 1);
if (ret)
goto out_only_mutex;
}
......@@ -2558,7 +2583,7 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
unlock_extent_cached(&BTRFS_I(inode)->io_tree, lockstart, lockend,
&cached_state, GFP_NOFS);
out_only_mutex:
if (!updated_inode && truncated_page && !ret && !err) {
if (!updated_inode && truncated_block && !ret && !err) {
/*
* If we only end up zeroing part of a page, we still need to
* update the inode item, so that all the time fields are
......@@ -2678,10 +2703,10 @@ static long btrfs_fallocate(struct file *file, int mode,
} else if (offset + len > inode->i_size) {
/*
* If we are fallocating from the end of the file onward we
* need to zero out the end of the page if i_size lands in the
* middle of a page.
* need to zero out the end of the block if i_size lands in the
* middle of a block.
*/
ret = btrfs_truncate_page(inode, inode->i_size, 0, 0);
ret = btrfs_truncate_block(inode, inode->i_size, 0, 0);
if (ret)
goto out;
}
......
This diff is collapsed.
......@@ -3814,8 +3814,9 @@ static noinline int btrfs_clone_files(struct file *file, struct file *file_src,
* Truncate page cache pages so that future reads will see the cloned
* data immediately and not the previous data.
*/
truncate_inode_pages_range(&inode->i_data, destoff,
PAGE_CACHE_ALIGN(destoff + len) - 1);
truncate_inode_pages_range(&inode->i_data,
round_down(destoff, PAGE_CACHE_SIZE),
round_up(destoff + len, PAGE_CACHE_SIZE) - 1);
out_unlock:
if (!same_inode)
btrfs_double_inode_unlock(src, inode);
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment