diff options
author | David Sterba <dsterba@suse.com> | 2016-02-26 15:38:28 +0100 |
---|---|---|
committer | David Sterba <dsterba@suse.com> | 2016-02-26 15:38:28 +0100 |
commit | 5f1b5664d97842bc5dba40c2053bf95270b6ff7a (patch) | |
tree | 28d6a3aaf9c095ab2703634693615559329ee3b2 /fs/btrfs | |
parent | 388f7b1d6e8ca06762e2454d28d6c3c55ad0fe95 (diff) | |
parent | 65bfa6580791f8c01fbc9cd8bd73d92aea53723f (diff) | |
download | linux-5f1b5664d97842bc5dba40c2053bf95270b6ff7a.tar.bz2 |
Merge branch 'chandan/prep-subpage-blocksize' into for-chris-4.6
# Conflicts:
# fs/btrfs/file.c
Diffstat (limited to 'fs/btrfs')
-rw-r--r-- | fs/btrfs/ctree.c | 34 | ||||
-rw-r--r-- | fs/btrfs/ctree.h | 5 | ||||
-rw-r--r-- | fs/btrfs/extent_io.c | 3 | ||||
-rw-r--r-- | fs/btrfs/file-item.c | 92 | ||||
-rw-r--r-- | fs/btrfs/file.c | 99 | ||||
-rw-r--r-- | fs/btrfs/inode.c | 248 | ||||
-rw-r--r-- | fs/btrfs/ioctl.c | 5 |
7 files changed, 321 insertions, 165 deletions
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 769e0ff1b4ce..f5ef7d171bb8 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -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); diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index bfe4a337fb4d..5f5c4fbd7a3c 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -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, diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 2e7c97a3f344..1b2073389dc2 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -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); diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c index a67e1c828d0f..1c50a7b09b4e 100644 --- a/fs/btrfs/file-item.c +++ b/fs/btrfs/file-item.c @@ -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; diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 098bb8f690c9..5a58e292bdad 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -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 @@ fail: 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 @@ again: 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 @@ again: * 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 @@ again: } } - 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 @@ again: 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 @@ out: 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; } diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 5f06eb1f4384..3e0d41511517 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -263,7 +263,7 @@ static noinline int cow_file_range_inline(struct btrfs_root *root, data_len = compressed_size; if (start > 0 || - actual_end > PAGE_CACHE_SIZE || + actual_end > root->sectorsize || data_len > BTRFS_MAX_INLINE_DATA_SIZE(root) || (!compressed_size && (actual_end & (root->sectorsize - 1)) == 0) || @@ -2002,7 +2002,8 @@ again: if (PagePrivate2(page)) goto out; - ordered = btrfs_lookup_ordered_extent(inode, page_start); + ordered = btrfs_lookup_ordered_range(inode, page_start, + PAGE_CACHE_SIZE); if (ordered) { unlock_extent_cached(&BTRFS_I(inode)->io_tree, page_start, page_end, &cached_state, GFP_NOFS); @@ -4248,7 +4249,8 @@ static int truncate_inline_extent(struct inode *inode, * read the extent item from disk (data not in the page cache). */ btrfs_release_path(path); - return btrfs_truncate_page(inode, offset, page_end - offset, 0); + return btrfs_truncate_block(inode, offset, page_end - offset, + 0); } btrfs_set_file_extent_ram_bytes(leaf, fi, size); @@ -4601,17 +4603,17 @@ error: } /* - * btrfs_truncate_page - read, zero a chunk and write a page + * btrfs_truncate_block - read, zero a chunk and write a block * @inode - inode that we're zeroing * @from - the offset to start zeroing * @len - the length to zero, 0 to zero the entire range respective to the * offset * @front - zero up to the offset instead of from the offset on * - * This will find the page for the "from" offset and cow the page and zero the + * This will find the block for the "from" offset and cow the block and zero the * part we want to zero. This is used with truncate and hole punching. */ -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) { struct address_space *mapping = inode->i_mapping; @@ -4622,18 +4624,19 @@ int btrfs_truncate_page(struct inode *inode, loff_t from, loff_t len, char *kaddr; u32 blocksize = root->sectorsize; pgoff_t index = from >> PAGE_CACHE_SHIFT; - unsigned offset = from & (PAGE_CACHE_SIZE-1); + unsigned offset = from & (blocksize - 1); struct page *page; gfp_t mask = btrfs_alloc_write_mask(mapping); int ret = 0; - u64 page_start; - u64 page_end; + u64 block_start; + u64 block_end; if ((offset & (blocksize - 1)) == 0 && (!len || ((len & (blocksize - 1)) == 0))) goto out; + ret = btrfs_delalloc_reserve_space(inode, - round_down(from, PAGE_CACHE_SIZE), PAGE_CACHE_SIZE); + round_down(from, blocksize), blocksize); if (ret) goto out; @@ -4641,14 +4644,14 @@ again: page = find_or_create_page(mapping, index, mask); if (!page) { btrfs_delalloc_release_space(inode, - round_down(from, PAGE_CACHE_SIZE), - PAGE_CACHE_SIZE); + round_down(from, blocksize), + blocksize); ret = -ENOMEM; goto out; } - page_start = page_offset(page); - page_end = page_start + PAGE_CACHE_SIZE - 1; + block_start = round_down(from, blocksize); + block_end = block_start + blocksize - 1; if (!PageUptodate(page)) { ret = btrfs_readpage(NULL, page); @@ -4665,12 +4668,12 @@ again: } wait_on_page_writeback(page); - lock_extent_bits(io_tree, page_start, page_end, &cached_state); + lock_extent_bits(io_tree, block_start, block_end, &cached_state); set_page_extent_mapped(page); - ordered = btrfs_lookup_ordered_extent(inode, page_start); + ordered = btrfs_lookup_ordered_extent(inode, block_start); if (ordered) { - unlock_extent_cached(io_tree, page_start, page_end, + unlock_extent_cached(io_tree, block_start, block_end, &cached_state, GFP_NOFS); unlock_page(page); page_cache_release(page); @@ -4679,39 +4682,41 @@ again: goto again; } - clear_extent_bit(&BTRFS_I(inode)->io_tree, page_start, page_end, + clear_extent_bit(&BTRFS_I(inode)->io_tree, block_start, block_end, EXTENT_DIRTY | EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG, 0, 0, &cached_state, GFP_NOFS); - ret = btrfs_set_extent_delalloc(inode, page_start, page_end, + ret = btrfs_set_extent_delalloc(inode, block_start, block_end, &cached_state); if (ret) { - unlock_extent_cached(io_tree, page_start, page_end, + unlock_extent_cached(io_tree, block_start, block_end, &cached_state, GFP_NOFS); goto out_unlock; } - if (offset != PAGE_CACHE_SIZE) { + if (offset != blocksize) { if (!len) - len = PAGE_CACHE_SIZE - offset; + len = blocksize - offset; kaddr = kmap(page); if (front) - memset(kaddr, 0, offset); + memset(kaddr + (block_start - page_offset(page)), + 0, offset); else - memset(kaddr + offset, 0, len); + memset(kaddr + (block_start - page_offset(page)) + offset, + 0, len); flush_dcache_page(page); kunmap(page); } ClearPageChecked(page); set_page_dirty(page); - unlock_extent_cached(io_tree, page_start, page_end, &cached_state, + unlock_extent_cached(io_tree, block_start, block_end, &cached_state, GFP_NOFS); out_unlock: if (ret) - btrfs_delalloc_release_space(inode, page_start, - PAGE_CACHE_SIZE); + btrfs_delalloc_release_space(inode, block_start, + blocksize); unlock_page(page); page_cache_release(page); out: @@ -4782,11 +4787,11 @@ int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size) int err = 0; /* - * If our size started in the middle of a page we need to zero out the - * rest of the page before we expand the i_size, otherwise we could + * If our size started in the middle of a block we need to zero out the + * rest of the block before we expand the i_size, otherwise we could * expose stale data. */ - err = btrfs_truncate_page(inode, oldsize, 0, 0); + err = btrfs_truncate_block(inode, oldsize, 0, 0); if (err) return err; @@ -4895,7 +4900,6 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr) } if (newsize > oldsize) { - truncate_pagecache(inode, newsize); /* * Don't do an expanding truncate while snapshoting is ongoing. * This is to ensure the snapshot captures a fully consistent @@ -4918,6 +4922,7 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr) i_size_write(inode, newsize); btrfs_ordered_update_i_size(inode, i_size_read(inode), NULL); + pagecache_isize_extended(inode, oldsize, newsize); ret = btrfs_update_inode(trans, root, inode); btrfs_end_write_no_snapshoting(root); btrfs_end_transaction(trans, root); @@ -7752,9 +7757,9 @@ static int btrfs_check_dio_repairable(struct inode *inode, } static int dio_read_error(struct inode *inode, struct bio *failed_bio, - struct page *page, u64 start, u64 end, - int failed_mirror, bio_end_io_t *repair_endio, - void *repair_arg) + struct page *page, unsigned int pgoff, + u64 start, u64 end, int failed_mirror, + bio_end_io_t *repair_endio, void *repair_arg) { struct io_failure_record *failrec; struct bio *bio; @@ -7775,7 +7780,9 @@ static int dio_read_error(struct inode *inode, struct bio *failed_bio, return -EIO; } - if (failed_bio->bi_vcnt > 1) + if ((failed_bio->bi_vcnt > 1) + || (failed_bio->bi_io_vec->bv_len + > BTRFS_I(inode)->root->sectorsize)) read_mode = READ_SYNC | REQ_FAILFAST_DEV; else read_mode = READ_SYNC; @@ -7783,7 +7790,7 @@ static int dio_read_error(struct inode *inode, struct bio *failed_bio, isector = start - btrfs_io_bio(failed_bio)->logical; isector >>= inode->i_sb->s_blocksize_bits; bio = btrfs_create_repair_bio(inode, failed_bio, failrec, page, - 0, isector, repair_endio, repair_arg); + pgoff, isector, repair_endio, repair_arg); if (!bio) { free_io_failure(inode, failrec); return -EIO; @@ -7813,12 +7820,17 @@ struct btrfs_retry_complete { static void btrfs_retry_endio_nocsum(struct bio *bio) { struct btrfs_retry_complete *done = bio->bi_private; + struct inode *inode; struct bio_vec *bvec; int i; if (bio->bi_error) goto end; + ASSERT(bio->bi_vcnt == 1); + inode = bio->bi_io_vec->bv_page->mapping->host; + ASSERT(bio->bi_io_vec->bv_len == BTRFS_I(inode)->root->sectorsize); + done->uptodate = 1; bio_for_each_segment_all(bvec, bio, i) clean_io_failure(done->inode, done->start, bvec->bv_page, 0); @@ -7830,25 +7842,35 @@ end: static int __btrfs_correct_data_nocsum(struct inode *inode, struct btrfs_io_bio *io_bio) { + struct btrfs_fs_info *fs_info; struct bio_vec *bvec; struct btrfs_retry_complete done; u64 start; + unsigned int pgoff; + u32 sectorsize; + int nr_sectors; int i; int ret; + fs_info = BTRFS_I(inode)->root->fs_info; + sectorsize = BTRFS_I(inode)->root->sectorsize; + start = io_bio->logical; done.inode = inode; bio_for_each_segment_all(bvec, &io_bio->bio, i) { -try_again: + nr_sectors = BTRFS_BYTES_TO_BLKS(fs_info, bvec->bv_len); + pgoff = bvec->bv_offset; + +next_block_or_try_again: done.uptodate = 0; done.start = start; init_completion(&done.done); - ret = dio_read_error(inode, &io_bio->bio, bvec->bv_page, start, - start + bvec->bv_len - 1, - io_bio->mirror_num, - btrfs_retry_endio_nocsum, &done); + ret = dio_read_error(inode, &io_bio->bio, bvec->bv_page, + pgoff, start, start + sectorsize - 1, + io_bio->mirror_num, + btrfs_retry_endio_nocsum, &done); if (ret) return ret; @@ -7856,10 +7878,15 @@ try_again: if (!done.uptodate) { /* We might have another mirror, so try again */ - goto try_again; + goto next_block_or_try_again; } - start += bvec->bv_len; + start += sectorsize; + + if (nr_sectors--) { + pgoff += sectorsize; + goto next_block_or_try_again; + } } return 0; @@ -7869,7 +7896,9 @@ static void btrfs_retry_endio(struct bio *bio) { struct btrfs_retry_complete *done = bio->bi_private; struct btrfs_io_bio *io_bio = btrfs_io_bio(bio); + struct inode *inode; struct bio_vec *bvec; + u64 start; int uptodate; int ret; int i; @@ -7878,13 +7907,20 @@ static void btrfs_retry_endio(struct bio *bio) goto end; uptodate = 1; + + start = done->start; + + ASSERT(bio->bi_vcnt == 1); + inode = bio->bi_io_vec->bv_page->mapping->host; + ASSERT(bio->bi_io_vec->bv_len == BTRFS_I(inode)->root->sectorsize); + bio_for_each_segment_all(bvec, bio, i) { ret = __readpage_endio_check(done->inode, io_bio, i, - bvec->bv_page, 0, - done->start, bvec->bv_len); + bvec->bv_page, bvec->bv_offset, + done->start, bvec->bv_len); if (!ret) clean_io_failure(done->inode, done->start, - bvec->bv_page, 0); + bvec->bv_page, bvec->bv_offset); else uptodate = 0; } @@ -7898,20 +7934,34 @@ end: static int __btrfs_subio_endio_read(struct inode *inode, struct btrfs_io_bio *io_bio, int err) { + struct btrfs_fs_info *fs_info; struct bio_vec *bvec; struct btrfs_retry_complete done; u64 start; u64 offset = 0; + u32 sectorsize; + int nr_sectors; + unsigned int pgoff; + int csum_pos; int i; int ret; + fs_info = BTRFS_I(inode)->root->fs_info; + sectorsize = BTRFS_I(inode)->root->sectorsize; + err = 0; start = io_bio->logical; done.inode = inode; bio_for_each_segment_all(bvec, &io_bio->bio, i) { - ret = __readpage_endio_check(inode, io_bio, i, bvec->bv_page, - 0, start, bvec->bv_len); + nr_sectors = BTRFS_BYTES_TO_BLKS(fs_info, bvec->bv_len); + + pgoff = bvec->bv_offset; +next_block: + csum_pos = BTRFS_BYTES_TO_BLKS(fs_info, offset); + ret = __readpage_endio_check(inode, io_bio, csum_pos, + bvec->bv_page, pgoff, start, + sectorsize); if (likely(!ret)) goto next; try_again: @@ -7919,10 +7969,10 @@ try_again: done.start = start; init_completion(&done.done); - ret = dio_read_error(inode, &io_bio->bio, bvec->bv_page, start, - start + bvec->bv_len - 1, - io_bio->mirror_num, - btrfs_retry_endio, &done); + ret = dio_read_error(inode, &io_bio->bio, bvec->bv_page, + pgoff, start, start + sectorsize - 1, + io_bio->mirror_num, + btrfs_retry_endio, &done); if (ret) { err = ret; goto next; @@ -7935,8 +7985,15 @@ try_again: goto try_again; } next: - offset += bvec->bv_len; - start += bvec->bv_len; + offset += sectorsize; + start += sectorsize; + + ASSERT(nr_sectors); + + if (--nr_sectors) { + pgoff += sectorsize; + goto next_block; + } } return err; @@ -8188,9 +8245,11 @@ static int btrfs_submit_direct_hook(int rw, struct btrfs_dio_private *dip, u64 file_offset = dip->logical_offset; u64 submit_len = 0; u64 map_length; - int nr_pages = 0; - int ret; + u32 blocksize = root->sectorsize; int async_submit = 0; + int nr_sectors; + int ret; + int i; map_length = orig_bio->bi_iter.bi_size; ret = btrfs_map_block(root->fs_info, rw, start_sector << 9, @@ -8220,9 +8279,12 @@ static int btrfs_submit_direct_hook(int rw, struct btrfs_dio_private *dip, atomic_inc(&dip->pending_bios); while (bvec <= (orig_bio->bi_io_vec + orig_bio->bi_vcnt - 1)) { - if (map_length < submit_len + bvec->bv_len || - bio_add_page(bio, bvec->bv_page, bvec->bv_len, - bvec->bv_offset) < bvec->bv_len) { + nr_sectors = BTRFS_BYTES_TO_BLKS(root->fs_info, bvec->bv_len); + i = 0; +next_block: + if (unlikely(map_length < submit_len + blocksize || + bio_add_page(bio, bvec->bv_page, blocksize, + bvec->bv_offset + (i * blocksize)) < blocksize)) { /* * inc the count before we submit the bio so * we know the end IO handler won't happen before @@ -8243,7 +8305,6 @@ static int btrfs_submit_direct_hook(int rw, struct btrfs_dio_private *dip, file_offset += submit_len; submit_len = 0; - nr_pages = 0; bio = btrfs_dio_bio_alloc(orig_bio->bi_bdev, start_sector, GFP_NOFS); @@ -8261,9 +8322,14 @@ static int btrfs_submit_direct_hook(int rw, struct btrfs_dio_private *dip, bio_put(bio); goto out_err; } + + goto next_block; } else { - submit_len += bvec->bv_len; - nr_pages++; + submit_len += blocksize; + if (--nr_sectors) { + i++; + goto next_block; + } bvec++; } } @@ -8628,6 +8694,8 @@ static void btrfs_invalidatepage(struct page *page, unsigned int offset, struct extent_state *cached_state = NULL; u64 page_start = page_offset(page); u64 page_end = page_start + PAGE_CACHE_SIZE - 1; + u64 start; + u64 end; int inode_evicting = inode->i_state & I_FREEING; /* @@ -8647,14 +8715,18 @@ static void btrfs_invalidatepage(struct page *page, unsigned int offset, if (!inode_evicting) lock_extent_bits(tree, page_start, page_end, &cached_state); - ordered = btrfs_lookup_ordered_extent(inode, page_start); +again: + start = page_start; + ordered = btrfs_lookup_ordered_range(inode, start, + page_end - start + 1); if (ordered) { + end = min(page_end, ordered->file_offset + ordered->len - 1); /* * IO on this page will never be started, so we need * to account for any ordered extents now */ if (!inode_evicting) - clear_extent_bit(tree, page_start, page_end, + clear_extent_bit(tree, start, end, EXTENT_DIRTY | EXTENT_DELALLOC | EXTENT_LOCKED | EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG, 1, 0, &cached_state, @@ -8671,22 +8743,26 @@ static void btrfs_invalidatepage(struct page *page, unsigned int offset, spin_lock_irq(&tree->lock); set_bit(BTRFS_ORDERED_TRUNCATED, &ordered->flags); - new_len = page_start - ordered->file_offset; + new_len = start - ordered->file_offset; if (new_len < ordered->truncated_len) ordered->truncated_len = new_len; spin_unlock_irq(&tree->lock); if (btrfs_dec_test_ordered_pending(inode, &ordered, - page_start, - PAGE_CACHE_SIZE, 1)) + start, + end - start + 1, 1)) btrfs_finish_ordered_io(ordered); } btrfs_put_ordered_extent(ordered); if (!inode_evicting) { cached_state = NULL; - lock_extent_bits(tree, page_start, page_end, + lock_extent_bits(tree, start, end, &cached_state); } + + start = end + 1; + if (start < page_end) + goto again; } /* @@ -8747,15 +8823,28 @@ int btrfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) loff_t size; int ret; int reserved = 0; + u64 reserved_space; u64 page_start; u64 page_end; + u64 end; + + reserved_space = PAGE_CACHE_SIZE; sb_start_pagefault(inode->i_sb); page_start = page_offset(page); page_end = page_start + PAGE_CACHE_SIZE - 1; + end = page_end; + /* + * Reserving delalloc space after obtaining the page lock can lead to + * deadlock. For example, if a dirty page is locked by this function + * and the call to btrfs_delalloc_reserve_space() ends up triggering + * dirty page write out, then the btrfs_writepage() function could + * end up waiting indefinitely to get a lock on the page currently + * being processed by btrfs_page_mkwrite() function. + */ ret = btrfs_delalloc_reserve_space(inode, page_start, - PAGE_CACHE_SIZE); + reserved_space); if (!ret) { ret = file_update_time(vma->vm_file); reserved = 1; @@ -8789,7 +8878,7 @@ again: * we can't set the delalloc bits if there are pending ordered * extents. Drop our locks and wait for them to finish */ - ordered = btrfs_lookup_ordered_extent(inode, page_start); + ordered = btrfs_lookup_ordered_range(inode, page_start, page_end); if (ordered) { unlock_extent_cached(io_tree, page_start, page_end, &cached_state, GFP_NOFS); @@ -8799,6 +8888,18 @@ again: goto again; } + if (page->index == ((size - 1) >> PAGE_CACHE_SHIFT)) { + reserved_space = round_up(size - page_start, root->sectorsize); + if (reserved_space < PAGE_CACHE_SIZE) { + end = page_start + reserved_space - 1; + spin_lock(&BTRFS_I(inode)->lock); + BTRFS_I(inode)->outstanding_extents++; + spin_unlock(&BTRFS_I(inode)->lock); + btrfs_delalloc_release_space(inode, page_start, + PAGE_CACHE_SIZE - reserved_space); + } + } + /* * XXX - page_mkwrite gets called every time the page is dirtied, even * if it was already dirty, so for space accounting reasons we need to @@ -8806,12 +8907,12 @@ again: * is probably a better way to do this, but for now keep consistent with * prepare_pages in the normal write path. */ - clear_extent_bit(&BTRFS_I(inode)->io_tree, page_start, page_end, + clear_extent_bit(&BTRFS_I(inode)->io_tree, page_start, end, EXTENT_DIRTY | EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG, 0, 0, &cached_state, GFP_NOFS); - ret = btrfs_set_extent_delalloc(inode, page_start, page_end, + ret = btrfs_set_extent_delalloc(inode, page_start, end, &cached_state); if (ret) { unlock_extent_cached(io_tree, page_start, page_end, @@ -8850,7 +8951,7 @@ out_unlock: } unlock_page(page); out: - btrfs_delalloc_release_space(inode, page_start, PAGE_CACHE_SIZE); + btrfs_delalloc_release_space(inode, page_start, reserved_space); out_noreserve: sb_end_pagefault(inode->i_sb); return ret; @@ -9236,7 +9337,6 @@ static int btrfs_getattr(struct vfsmount *mnt, generic_fillattr(inode, stat); stat->dev = BTRFS_I(inode)->root->anon_dev; - stat->blksize = PAGE_CACHE_SIZE; spin_lock(&BTRFS_I(inode)->lock); delalloc_bytes = BTRFS_I(inode)->delalloc_bytes; diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 952172ca7e45..93e7832d1d1b 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -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); |