#include <linux/string.h>
#include <linux/buffer_head.h>
#include <linux/writeback.h>
+#include <linux/pagevec.h>
#include <linux/mpage.h>
#include <linux/uio.h>
#include <linux/bio.h>
#include "ext4_jbd2.h"
#include "xattr.h"
#include "acl.h"
+#include "ext4_extents.h"
static inline int ext4_begin_ordered_truncate(struct inode *inode,
loff_t new_size)
new_size);
}
+static void ext4_invalidatepage(struct page *page, unsigned long offset);
+
/*
* Test whether an inode is a fast symlink.
*/
void ext4_delete_inode (struct inode * inode)
{
handle_t *handle;
+ int err;
if (ext4_should_order_data(inode))
ext4_begin_ordered_truncate(inode, 0);
if (is_bad_inode(inode))
goto no_delete;
- handle = start_transaction(inode);
+ handle = ext4_journal_start(inode, blocks_for_truncate(inode)+3);
if (IS_ERR(handle)) {
+ ext4_std_error(inode->i_sb, PTR_ERR(handle));
/*
* If we're going to skip the normal cleanup, we still need to
* make sure that the in-core orphan linked list is properly
if (IS_SYNC(inode))
handle->h_sync = 1;
inode->i_size = 0;
+ err = ext4_mark_inode_dirty(handle, inode);
+ if (err) {
+ ext4_warning(inode->i_sb, __func__,
+ "couldn't mark inode dirty (err %d)", err);
+ goto stop_handle;
+ }
if (inode->i_blocks)
ext4_truncate(inode);
+
+ /*
+ * ext4_ext_truncate() doesn't reserve any slop when it
+ * restarts journal transactions; therefore there may not be
+ * enough credits left in the handle to remove the inode from
+ * the orphan list and set the dtime field.
+ */
+ if (handle->h_buffer_credits < 3) {
+ err = ext4_journal_extend(handle, 3);
+ if (err > 0)
+ err = ext4_journal_restart(handle, 3);
+ if (err != 0) {
+ ext4_warning(inode->i_sb, __func__,
+ "couldn't extend journal (err %d)", err);
+ stop_handle:
+ ext4_journal_stop(handle);
+ goto no_delete;
+ }
+ }
+
/*
* Kill off the orphan record which ext4_truncate created.
* AKPM: I think this can be inside the above `if'.
struct ext4_inode_info *ei = EXT4_I(inode);
int count = 0;
ext4_fsblk_t first_block = 0;
+ loff_t disksize;
J_ASSERT(!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL));
* protect it if you're about to implement concurrent
* ext4_get_block() -bzzz
*/
- if (!err && extend_disksize && inode->i_size > ei->i_disksize)
- ei->i_disksize = inode->i_size;
+ if (!err && extend_disksize) {
+ disksize = ((loff_t) iblock + count) << inode->i_blkbits;
+ if (disksize > i_size_read(inode))
+ disksize = i_size_read(inode);
+ if (disksize > ei->i_disksize)
+ ei->i_disksize = disksize;
+ }
if (err)
goto cleanup;
return err;
}
+/*
+ * Calculate the number of metadata blocks need to reserve
+ * to allocate @blocks for non extent file based file
+ */
+static int ext4_indirect_calc_metadata_amount(struct inode *inode, int blocks)
+{
+ int icap = EXT4_ADDR_PER_BLOCK(inode->i_sb);
+ int ind_blks, dind_blks, tind_blks;
+
+ /* number of new indirect blocks needed */
+ ind_blks = (blocks + icap - 1) / icap;
+
+ dind_blks = (ind_blks + icap - 1) / icap;
+
+ tind_blks = 1;
+
+ return ind_blks + dind_blks + tind_blks;
+}
+
+/*
+ * Calculate the number of metadata blocks need to reserve
+ * to allocate given number of blocks
+ */
+static int ext4_calc_metadata_amount(struct inode *inode, int blocks)
+{
+ if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL)
+ return ext4_ext_calc_metadata_amount(inode, blocks);
+
+ return ext4_indirect_calc_metadata_amount(inode, blocks);
+}
+
+static void ext4_da_update_reserve_space(struct inode *inode, int used)
+{
+ struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+ int total, mdb, mdb_free;
+
+ spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
+ /* recalculate the number of metablocks still need to be reserved */
+ total = EXT4_I(inode)->i_reserved_data_blocks - used;
+ mdb = ext4_calc_metadata_amount(inode, total);
+
+ /* figure out how many metablocks to release */
+ BUG_ON(mdb > EXT4_I(inode)->i_reserved_meta_blocks);
+ mdb_free = EXT4_I(inode)->i_reserved_meta_blocks - mdb;
+
+ /* Account for allocated meta_blocks */
+ mdb_free -= EXT4_I(inode)->i_allocated_meta_blocks;
+
+ /* update fs free blocks counter for truncate case */
+ percpu_counter_add(&sbi->s_freeblocks_counter, mdb_free);
+
+ /* update per-inode reservations */
+ BUG_ON(used > EXT4_I(inode)->i_reserved_data_blocks);
+ EXT4_I(inode)->i_reserved_data_blocks -= used;
+
+ BUG_ON(mdb > EXT4_I(inode)->i_reserved_meta_blocks);
+ EXT4_I(inode)->i_reserved_meta_blocks = mdb;
+ EXT4_I(inode)->i_allocated_meta_blocks = 0;
+ spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
+}
+
/* Maximum number of blocks we map for direct IO at once. */
#define DIO_MAX_BLOCKS 4096
/*
/*
+ * The ext4_get_blocks_wrap() function try to look up the requested blocks,
+ * and returns if the blocks are already mapped.
*
- *
- * ext4_ext4 get_block() wrapper function
- * It will do a look up first, and returns if the blocks already mapped.
* Otherwise it takes the write lock of the i_data_sem and allocate blocks
* and store the allocated blocks in the result buffer head and mark it
* mapped.
*/
int ext4_get_blocks_wrap(handle_t *handle, struct inode *inode, sector_t block,
unsigned long max_blocks, struct buffer_head *bh,
- int create, int extend_disksize)
+ int create, int extend_disksize, int flag)
{
int retval;
* with create == 1 flag.
*/
down_write((&EXT4_I(inode)->i_data_sem));
+
+ /*
+ * if the caller is from delayed allocation writeout path
+ * we have already reserved fs blocks for allocation
+ * let the underlying get_block() function know to
+ * avoid double accounting
+ */
+ if (flag)
+ EXT4_I(inode)->i_delalloc_reserved_flag = 1;
/*
* We need to check for EXT4 here because migrate
* could have changed the inode type in between
~EXT4_EXT_MIGRATE;
}
}
+
+ if (flag) {
+ EXT4_I(inode)->i_delalloc_reserved_flag = 0;
+ /*
+ * Update reserved blocks/metadata blocks
+ * after successful block allocation
+ * which were deferred till now
+ */
+ if ((retval > 0) && buffer_delay(bh))
+ ext4_da_update_reserve_space(inode, retval);
+ }
+
up_write((&EXT4_I(inode)->i_data_sem));
return retval;
}
}
ret = ext4_get_blocks_wrap(handle, inode, iblock,
- max_blocks, bh_result, create, 0);
+ max_blocks, bh_result, create, 0, 0);
if (ret > 0) {
bh_result->b_size = (ret << inode->i_blkbits);
ret = 0;
dummy.b_blocknr = -1000;
buffer_trace_init(&dummy.b_history);
err = ext4_get_blocks_wrap(handle, inode, block, 1,
- &dummy, create, 1);
+ &dummy, create, 1, 0);
/*
* ext4_get_blocks_handle() returns number of blocks
* mapped. 0 in case of a HOLE.
{
handle_t *handle = ext4_journal_current_handle();
struct inode *inode = mapping->host;
- unsigned from, to;
int ret = 0, ret2;
- from = pos & (PAGE_CACHE_SIZE - 1);
- to = from + len;
-
ret = ext4_jbd2_file_inode(handle, inode);
if (ret == 0) {
return ret ? ret : copied;
}
+static int ext4_da_reserve_space(struct inode *inode, int nrblocks)
+{
+ struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+ unsigned long md_needed, mdblocks, total = 0;
+
+ /*
+ * recalculate the amount of metadata blocks to reserve
+ * in order to allocate nrblocks
+ * worse case is one extent per block
+ */
+ spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
+ total = EXT4_I(inode)->i_reserved_data_blocks + nrblocks;
+ mdblocks = ext4_calc_metadata_amount(inode, total);
+ BUG_ON(mdblocks < EXT4_I(inode)->i_reserved_meta_blocks);
+
+ md_needed = mdblocks - EXT4_I(inode)->i_reserved_meta_blocks;
+ total = md_needed + nrblocks;
+
+ if (ext4_has_free_blocks(sbi, total) < total) {
+ spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
+ return -ENOSPC;
+ }
+ /* reduce fs free blocks counter */
+ percpu_counter_sub(&sbi->s_freeblocks_counter, total);
+
+ EXT4_I(inode)->i_reserved_data_blocks += nrblocks;
+ EXT4_I(inode)->i_reserved_meta_blocks = mdblocks;
+
+ spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
+ return 0; /* success */
+}
+
+static void ext4_da_release_space(struct inode *inode, int to_free)
+{
+ struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+ int total, mdb, mdb_free, release;
+
+ spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
+ /* recalculate the number of metablocks still need to be reserved */
+ total = EXT4_I(inode)->i_reserved_data_blocks - to_free;
+ mdb = ext4_calc_metadata_amount(inode, total);
+
+ /* figure out how many metablocks to release */
+ BUG_ON(mdb > EXT4_I(inode)->i_reserved_meta_blocks);
+ mdb_free = EXT4_I(inode)->i_reserved_meta_blocks - mdb;
+
+ release = to_free + mdb_free;
+
+ /* update fs free blocks counter for truncate case */
+ percpu_counter_add(&sbi->s_freeblocks_counter, release);
+
+ /* update per-inode reservations */
+ BUG_ON(to_free > EXT4_I(inode)->i_reserved_data_blocks);
+ EXT4_I(inode)->i_reserved_data_blocks -= to_free;
+
+ BUG_ON(mdb > EXT4_I(inode)->i_reserved_meta_blocks);
+ EXT4_I(inode)->i_reserved_meta_blocks = mdb;
+ spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
+}
+
+static void ext4_da_page_release_reservation(struct page *page,
+ unsigned long offset)
+{
+ int to_release = 0;
+ struct buffer_head *head, *bh;
+ unsigned int curr_off = 0;
+
+ head = page_buffers(page);
+ bh = head;
+ do {
+ unsigned int next_off = curr_off + bh->b_size;
+
+ if ((offset <= curr_off) && (buffer_delay(bh))) {
+ to_release++;
+ clear_buffer_delay(bh);
+ }
+ curr_off = next_off;
+ } while ((bh = bh->b_this_page) != head);
+ ext4_da_release_space(page->mapping->host, to_release);
+}
+
+/*
+ * Delayed allocation stuff
+ */
+
+struct mpage_da_data {
+ struct inode *inode;
+ struct buffer_head lbh; /* extent of blocks */
+ unsigned long first_page, next_page; /* extent of pages */
+ get_block_t *get_block;
+ struct writeback_control *wbc;
+};
+
+/*
+ * mpage_da_submit_io - walks through extent of pages and try to write
+ * them with __mpage_writepage()
+ *
+ * @mpd->inode: inode
+ * @mpd->first_page: first page of the extent
+ * @mpd->next_page: page after the last page of the extent
+ * @mpd->get_block: the filesystem's block mapper function
+ *
+ * By the time mpage_da_submit_io() is called we expect all blocks
+ * to be allocated. this may be wrong if allocation failed.
+ *
+ * As pages are already locked by write_cache_pages(), we can't use it
+ */
+static int mpage_da_submit_io(struct mpage_da_data *mpd)
+{
+ struct address_space *mapping = mpd->inode->i_mapping;
+ struct mpage_data mpd_pp = {
+ .bio = NULL,
+ .last_block_in_bio = 0,
+ .get_block = mpd->get_block,
+ .use_writepage = 1,
+ };
+ int ret = 0, err, nr_pages, i;
+ unsigned long index, end;
+ struct pagevec pvec;
+
+ BUG_ON(mpd->next_page <= mpd->first_page);
+
+ pagevec_init(&pvec, 0);
+ index = mpd->first_page;
+ end = mpd->next_page - 1;
+
+ while (index <= end) {
+ /* XXX: optimize tail */
+ nr_pages = pagevec_lookup(&pvec, mapping, index, PAGEVEC_SIZE);
+ if (nr_pages == 0)
+ break;
+ for (i = 0; i < nr_pages; i++) {
+ struct page *page = pvec.pages[i];
+
+ index = page->index;
+ if (index > end)
+ break;
+ index++;
+
+ err = __mpage_writepage(page, mpd->wbc, &mpd_pp);
+
+ /*
+ * In error case, we have to continue because
+ * remaining pages are still locked
+ * XXX: unlock and re-dirty them?
+ */
+ if (ret == 0)
+ ret = err;
+ }
+ pagevec_release(&pvec);
+ }
+ if (mpd_pp.bio)
+ mpage_bio_submit(WRITE, mpd_pp.bio);
+
+ return ret;
+}
+
+/*
+ * mpage_put_bnr_to_bhs - walk blocks and assign them actual numbers
+ *
+ * @mpd->inode - inode to walk through
+ * @exbh->b_blocknr - first block on a disk
+ * @exbh->b_size - amount of space in bytes
+ * @logical - first logical block to start assignment with
+ *
+ * the function goes through all passed space and put actual disk
+ * block numbers into buffer heads, dropping BH_Delay
+ */
+static void mpage_put_bnr_to_bhs(struct mpage_da_data *mpd, sector_t logical,
+ struct buffer_head *exbh)
+{
+ struct inode *inode = mpd->inode;
+ struct address_space *mapping = inode->i_mapping;
+ int blocks = exbh->b_size >> inode->i_blkbits;
+ sector_t pblock = exbh->b_blocknr, cur_logical;
+ struct buffer_head *head, *bh;
+ unsigned long index, end;
+ struct pagevec pvec;
+ int nr_pages, i;
+
+ index = logical >> (PAGE_CACHE_SHIFT - inode->i_blkbits);
+ end = (logical + blocks - 1) >> (PAGE_CACHE_SHIFT - inode->i_blkbits);
+ cur_logical = index << (PAGE_CACHE_SHIFT - inode->i_blkbits);
+
+ pagevec_init(&pvec, 0);
+
+ while (index <= end) {
+ /* XXX: optimize tail */
+ nr_pages = pagevec_lookup(&pvec, mapping, index, PAGEVEC_SIZE);
+ if (nr_pages == 0)
+ break;
+ for (i = 0; i < nr_pages; i++) {
+ struct page *page = pvec.pages[i];
+
+ index = page->index;
+ if (index > end)
+ break;
+ index++;
+
+ BUG_ON(!PageLocked(page));
+ BUG_ON(PageWriteback(page));
+ BUG_ON(!page_has_buffers(page));
+
+ bh = page_buffers(page);
+ head = bh;
+
+ /* skip blocks out of the range */
+ do {
+ if (cur_logical >= logical)
+ break;
+ cur_logical++;
+ } while ((bh = bh->b_this_page) != head);
+
+ do {
+ if (cur_logical >= logical + blocks)
+ break;
+ if (buffer_delay(bh)) {
+ bh->b_blocknr = pblock;
+ clear_buffer_delay(bh);
+ } else if (buffer_mapped(bh))
+ BUG_ON(bh->b_blocknr != pblock);
+
+ cur_logical++;
+ pblock++;
+ } while ((bh = bh->b_this_page) != head);
+ }
+ pagevec_release(&pvec);
+ }
+}
+
+
+/*
+ * __unmap_underlying_blocks - just a helper function to unmap
+ * set of blocks described by @bh
+ */
+static inline void __unmap_underlying_blocks(struct inode *inode,
+ struct buffer_head *bh)
+{
+ struct block_device *bdev = inode->i_sb->s_bdev;
+ int blocks, i;
+
+ blocks = bh->b_size >> inode->i_blkbits;
+ for (i = 0; i < blocks; i++)
+ unmap_underlying_metadata(bdev, bh->b_blocknr + i);
+}
+
+/*
+ * mpage_da_map_blocks - go through given space
+ *
+ * @mpd->lbh - bh describing space
+ * @mpd->get_block - the filesystem's block mapper function
+ *
+ * The function skips space we know is already mapped to disk blocks.
+ *
+ * The function ignores errors ->get_block() returns, thus real
+ * error handling is postponed to __mpage_writepage()
+ */
+static void mpage_da_map_blocks(struct mpage_da_data *mpd)
+{
+ struct buffer_head *lbh = &mpd->lbh;
+ int err = 0, remain = lbh->b_size;
+ sector_t next = lbh->b_blocknr;
+ struct buffer_head new;
+
+ /*
+ * We consider only non-mapped and non-allocated blocks
+ */
+ if (buffer_mapped(lbh) && !buffer_delay(lbh))
+ return;
+
+ while (remain) {
+ new.b_state = lbh->b_state;
+ new.b_blocknr = 0;
+ new.b_size = remain;
+ err = mpd->get_block(mpd->inode, next, &new, 1);
+ if (err) {
+ /*
+ * Rather than implement own error handling
+ * here, we just leave remaining blocks
+ * unallocated and try again with ->writepage()
+ */
+ break;
+ }
+ BUG_ON(new.b_size == 0);
+
+ if (buffer_new(&new))
+ __unmap_underlying_blocks(mpd->inode, &new);
+
+ /*
+ * If blocks are delayed marked, we need to
+ * put actual blocknr and drop delayed bit
+ */
+ if (buffer_delay(lbh))
+ mpage_put_bnr_to_bhs(mpd, next, &new);
+
+ /* go for the remaining blocks */
+ next += new.b_size >> mpd->inode->i_blkbits;
+ remain -= new.b_size;
+ }
+}
+
+#define BH_FLAGS ((1 << BH_Uptodate) | (1 << BH_Mapped) | (1 << BH_Delay))
+
+/*
+ * mpage_add_bh_to_extent - try to add one more block to extent of blocks
+ *
+ * @mpd->lbh - extent of blocks
+ * @logical - logical number of the block in the file
+ * @bh - bh of the block (used to access block's state)
+ *
+ * the function is used to collect contig. blocks in same state
+ */
+static void mpage_add_bh_to_extent(struct mpage_da_data *mpd,
+ sector_t logical, struct buffer_head *bh)
+{
+ struct buffer_head *lbh = &mpd->lbh;
+ sector_t next;
+
+ next = lbh->b_blocknr + (lbh->b_size >> mpd->inode->i_blkbits);
+
+ /*
+ * First block in the extent
+ */
+ if (lbh->b_size == 0) {
+ lbh->b_blocknr = logical;
+ lbh->b_size = bh->b_size;
+ lbh->b_state = bh->b_state & BH_FLAGS;
+ return;
+ }
+
+ /*
+ * Can we merge the block to our big extent?
+ */
+ if (logical == next && (bh->b_state & BH_FLAGS) == lbh->b_state) {
+ lbh->b_size += bh->b_size;
+ return;
+ }
+
+ /*
+ * We couldn't merge the block to our extent, so we
+ * need to flush current extent and start new one
+ */
+ mpage_da_map_blocks(mpd);
+
+ /*
+ * Now start a new extent
+ */
+ lbh->b_size = bh->b_size;
+ lbh->b_state = bh->b_state & BH_FLAGS;
+ lbh->b_blocknr = logical;
+}
+
+/*
+ * __mpage_da_writepage - finds extent of pages and blocks
+ *
+ * @page: page to consider
+ * @wbc: not used, we just follow rules
+ * @data: context
+ *
+ * The function finds extents of pages and scan them for all blocks.
+ */
+static int __mpage_da_writepage(struct page *page,
+ struct writeback_control *wbc, void *data)
+{
+ struct mpage_da_data *mpd = data;
+ struct inode *inode = mpd->inode;
+ struct buffer_head *bh, *head, fake;
+ sector_t logical;
+
+ /*
+ * Can we merge this page to current extent?
+ */
+ if (mpd->next_page != page->index) {
+ /*
+ * Nope, we can't. So, we map non-allocated blocks
+ * and start IO on them using __mpage_writepage()
+ */
+ if (mpd->next_page != mpd->first_page) {
+ mpage_da_map_blocks(mpd);
+ mpage_da_submit_io(mpd);
+ }
+
+ /*
+ * Start next extent of pages ...
+ */
+ mpd->first_page = page->index;
+
+ /*
+ * ... and blocks
+ */
+ mpd->lbh.b_size = 0;
+ mpd->lbh.b_state = 0;
+ mpd->lbh.b_blocknr = 0;
+ }
+
+ mpd->next_page = page->index + 1;
+ logical = (sector_t) page->index <<
+ (PAGE_CACHE_SHIFT - inode->i_blkbits);
+
+ if (!page_has_buffers(page)) {
+ /*
+ * There is no attached buffer heads yet (mmap?)
+ * we treat the page asfull of dirty blocks
+ */
+ bh = &fake;
+ bh->b_size = PAGE_CACHE_SIZE;
+ bh->b_state = 0;
+ set_buffer_dirty(bh);
+ set_buffer_uptodate(bh);
+ mpage_add_bh_to_extent(mpd, logical, bh);
+ } else {
+ /*
+ * Page with regular buffer heads, just add all dirty ones
+ */
+ head = page_buffers(page);
+ bh = head;
+ do {
+ BUG_ON(buffer_locked(bh));
+ if (buffer_dirty(bh))
+ mpage_add_bh_to_extent(mpd, logical, bh);
+ logical++;
+ } while ((bh = bh->b_this_page) != head);
+ }
+
+ return 0;
+}
+
+/*
+ * mpage_da_writepages - walk the list of dirty pages of the given
+ * address space, allocates non-allocated blocks, maps newly-allocated
+ * blocks to existing bhs and issue IO them
+ *
+ * @mapping: address space structure to write
+ * @wbc: subtract the number of written pages from *@wbc->nr_to_write
+ * @get_block: the filesystem's block mapper function.
+ *
+ * This is a library function, which implements the writepages()
+ * address_space_operation.
+ *
+ * In order to avoid duplication of logic that deals with partial pages,
+ * multiple bio per page, etc, we find non-allocated blocks, allocate
+ * them with minimal calls to ->get_block() and re-use __mpage_writepage()
+ *
+ * It's important that we call __mpage_writepage() only once for each
+ * involved page, otherwise we'd have to implement more complicated logic
+ * to deal with pages w/o PG_lock or w/ PG_writeback and so on.
+ *
+ * See comments to mpage_writepages()
+ */
+static int mpage_da_writepages(struct address_space *mapping,
+ struct writeback_control *wbc,
+ get_block_t get_block)
+{
+ struct mpage_da_data mpd;
+ int ret;
+
+ if (!get_block)
+ return generic_writepages(mapping, wbc);
+
+ mpd.wbc = wbc;
+ mpd.inode = mapping->host;
+ mpd.lbh.b_size = 0;
+ mpd.lbh.b_state = 0;
+ mpd.lbh.b_blocknr = 0;
+ mpd.first_page = 0;
+ mpd.next_page = 0;
+ mpd.get_block = get_block;
+
+ ret = write_cache_pages(mapping, wbc, __mpage_da_writepage, &mpd);
+
+ /*
+ * Handle last extent of pages
+ */
+ if (mpd.next_page != mpd.first_page) {
+ mpage_da_map_blocks(&mpd);
+ mpage_da_submit_io(&mpd);
+ }
+
+ return ret;
+}
+
+/*
+ * this is a special callback for ->write_begin() only
+ * it's intention is to return mapped block or reserve space
+ */
+static int ext4_da_get_block_prep(struct inode *inode, sector_t iblock,
+ struct buffer_head *bh_result, int create)
+{
+ int ret = 0;
+
+ BUG_ON(create == 0);
+ BUG_ON(bh_result->b_size != inode->i_sb->s_blocksize);
+
+ /*
+ * first, we need to know whether the block is allocated already
+ * preallocated blocks are unmapped but should treated
+ * the same as allocated blocks.
+ */
+ ret = ext4_get_blocks_wrap(NULL, inode, iblock, 1, bh_result, 0, 0, 0);
+ if ((ret == 0) && !buffer_delay(bh_result)) {
+ /* the block isn't (pre)allocated yet, let's reserve space */
+ /*
+ * XXX: __block_prepare_write() unmaps passed block,
+ * is it OK?
+ */
+ ret = ext4_da_reserve_space(inode, 1);
+ if (ret)
+ /* not enough space to reserve */
+ return ret;
+
+ map_bh(bh_result, inode->i_sb, 0);
+ set_buffer_new(bh_result);
+ set_buffer_delay(bh_result);
+ } else if (ret > 0) {
+ bh_result->b_size = (ret << inode->i_blkbits);
+ ret = 0;
+ }
+
+ return ret;
+}
+#define EXT4_DELALLOC_RSVED 1
+static int ext4_da_get_block_write(struct inode *inode, sector_t iblock,
+ struct buffer_head *bh_result, int create)
+{
+ int ret;
+ unsigned max_blocks = bh_result->b_size >> inode->i_blkbits;
+ loff_t disksize = EXT4_I(inode)->i_disksize;
+ handle_t *handle = NULL;
+
+ handle = ext4_journal_current_handle();
+ if (!handle) {
+ ret = ext4_get_blocks_wrap(handle, inode, iblock, max_blocks,
+ bh_result, 0, 0, 0);
+ BUG_ON(!ret);
+ } else {
+ ret = ext4_get_blocks_wrap(handle, inode, iblock, max_blocks,
+ bh_result, create, 0, EXT4_DELALLOC_RSVED);
+ }
+
+ if (ret > 0) {
+ bh_result->b_size = (ret << inode->i_blkbits);
+
+ /*
+ * Update on-disk size along with block allocation
+ * we don't use 'extend_disksize' as size may change
+ * within already allocated block -bzzz
+ */
+ disksize = ((loff_t) iblock + ret) << inode->i_blkbits;
+ if (disksize > i_size_read(inode))
+ disksize = i_size_read(inode);
+ if (disksize > EXT4_I(inode)->i_disksize) {
+ /*
+ * XXX: replace with spinlock if seen contended -bzzz
+ */
+ down_write(&EXT4_I(inode)->i_data_sem);
+ if (disksize > EXT4_I(inode)->i_disksize)
+ EXT4_I(inode)->i_disksize = disksize;
+ up_write(&EXT4_I(inode)->i_data_sem);
+
+ if (EXT4_I(inode)->i_disksize == disksize) {
+ ret = ext4_mark_inode_dirty(handle, inode);
+ return ret;
+ }
+ }
+ ret = 0;
+ }
+ return ret;
+}
+
+static int ext4_bh_unmapped_or_delay(handle_t *handle, struct buffer_head *bh)
+{
+ /*
+ * unmapped buffer is possible for holes.
+ * delay buffer is possible with delayed allocation
+ */
+ return ((!buffer_mapped(bh) || buffer_delay(bh)) && buffer_dirty(bh));
+}
+
+static int ext4_normal_get_block_write(struct inode *inode, sector_t iblock,
+ struct buffer_head *bh_result, int create)
+{
+ int ret = 0;
+ unsigned max_blocks = bh_result->b_size >> inode->i_blkbits;
+
+ /*
+ * we don't want to do block allocation in writepage
+ * so call get_block_wrap with create = 0
+ */
+ ret = ext4_get_blocks_wrap(NULL, inode, iblock, max_blocks,
+ bh_result, 0, 0, 0);
+ if (ret > 0) {
+ bh_result->b_size = (ret << inode->i_blkbits);
+ ret = 0;
+ }
+ return ret;
+}
+
+/*
+ * get called vi ext4_da_writepages after taking page lock (have journal handle)
+ * get called via journal_submit_inode_data_buffers (no journal handle)
+ * get called via shrink_page_list via pdflush (no journal handle)
+ * or grab_page_cache when doing write_begin (have journal handle)
+ */
+static int ext4_da_writepage(struct page *page,
+ struct writeback_control *wbc)
+{
+ int ret = 0;
+ loff_t size;
+ unsigned long len;
+ struct buffer_head *page_bufs;
+ struct inode *inode = page->mapping->host;
+
+ size = i_size_read(inode);
+ if (page->index == size >> PAGE_CACHE_SHIFT)
+ len = size & ~PAGE_CACHE_MASK;
+ else
+ len = PAGE_CACHE_SIZE;
+
+ if (page_has_buffers(page)) {
+ page_bufs = page_buffers(page);
+ if (walk_page_buffers(NULL, page_bufs, 0, len, NULL,
+ ext4_bh_unmapped_or_delay)) {
+ /*
+ * We don't want to do block allocation
+ * So redirty the page and return
+ * We may reach here when we do a journal commit
+ * via journal_submit_inode_data_buffers.
+ * If we don't have mapping block we just ignore
+ * them. We can also reach here via shrink_page_list
+ */
+ redirty_page_for_writepage(wbc, page);
+ unlock_page(page);
+ return 0;
+ }
+ } else {
+ /*
+ * The test for page_has_buffers() is subtle:
+ * We know the page is dirty but it lost buffers. That means
+ * that at some moment in time after write_begin()/write_end()
+ * has been called all buffers have been clean and thus they
+ * must have been written at least once. So they are all
+ * mapped and we can happily proceed with mapping them
+ * and writing the page.
+ *
+ * Try to initialize the buffer_heads and check whether
+ * all are mapped and non delay. We don't want to
+ * do block allocation here.
+ */
+ ret = block_prepare_write(page, 0, PAGE_CACHE_SIZE,
+ ext4_normal_get_block_write);
+ if (!ret) {
+ page_bufs = page_buffers(page);
+ /* check whether all are mapped and non delay */
+ if (walk_page_buffers(NULL, page_bufs, 0, len, NULL,
+ ext4_bh_unmapped_or_delay)) {
+ redirty_page_for_writepage(wbc, page);
+ unlock_page(page);
+ return 0;
+ }
+ } else {
+ /*
+ * We can't do block allocation here
+ * so just redity the page and unlock
+ * and return
+ */
+ redirty_page_for_writepage(wbc, page);
+ unlock_page(page);
+ return 0;
+ }
+ }
+
+ if (test_opt(inode->i_sb, NOBH) && ext4_should_writeback_data(inode))
+ ret = nobh_writepage(page, ext4_normal_get_block_write, wbc);
+ else
+ ret = block_write_full_page(page,
+ ext4_normal_get_block_write,
+ wbc);
+
+ return ret;
+}
+
+/*
+ * For now just follow the DIO way to estimate the max credits
+ * needed to write out EXT4_MAX_WRITEBACK_PAGES.
+ * todo: need to calculate the max credits need for
+ * extent based files, currently the DIO credits is based on
+ * indirect-blocks mapping way.
+ *
+ * Probably should have a generic way to calculate credits
+ * for DIO, writepages, and truncate
+ */
+#define EXT4_MAX_WRITEBACK_PAGES DIO_MAX_BLOCKS
+#define EXT4_MAX_WRITEBACK_CREDITS DIO_CREDITS
+
+static int ext4_da_writepages(struct address_space *mapping,
+ struct writeback_control *wbc)
+{
+ struct inode *inode = mapping->host;
+ handle_t *handle = NULL;
+ int needed_blocks;
+ int ret = 0;
+ long to_write;
+ loff_t range_start = 0;
+
+ /*
+ * No pages to write? This is mainly a kludge to avoid starting
+ * a transaction for special inodes like journal inode on last iput()
+ * because that could violate lock ordering on umount
+ */
+ if (!mapping->nrpages)
+ return 0;
+
+ /*
+ * Estimate the worse case needed credits to write out
+ * EXT4_MAX_BUF_BLOCKS pages
+ */
+ needed_blocks = EXT4_MAX_WRITEBACK_CREDITS;
+
+ to_write = wbc->nr_to_write;
+ if (!wbc->range_cyclic) {
+ /*
+ * If range_cyclic is not set force range_cont
+ * and save the old writeback_index
+ */
+ wbc->range_cont = 1;
+ range_start = wbc->range_start;
+ }
+
+ while (!ret && to_write) {
+ /* start a new transaction*/
+ handle = ext4_journal_start(inode, needed_blocks);
+ if (IS_ERR(handle)) {
+ ret = PTR_ERR(handle);
+ goto out_writepages;
+ }
+ if (ext4_should_order_data(inode)) {
+ /*
+ * With ordered mode we need to add
+ * the inode to the journal handle
+ * when we do block allocation.
+ */
+ ret = ext4_jbd2_file_inode(handle, inode);
+ if (ret) {
+ ext4_journal_stop(handle);
+ goto out_writepages;
+ }
+
+ }
+ /*
+ * set the max dirty pages could be write at a time
+ * to fit into the reserved transaction credits
+ */
+ if (wbc->nr_to_write > EXT4_MAX_WRITEBACK_PAGES)
+ wbc->nr_to_write = EXT4_MAX_WRITEBACK_PAGES;
+
+ to_write -= wbc->nr_to_write;
+ ret = mpage_da_writepages(mapping, wbc,
+ ext4_da_get_block_write);
+ ext4_journal_stop(handle);
+ if (wbc->nr_to_write) {
+ /*
+ * There is no more writeout needed
+ * or we requested for a noblocking writeout
+ * and we found the device congested
+ */
+ to_write += wbc->nr_to_write;
+ break;
+ }
+ wbc->nr_to_write = to_write;
+ }
+
+out_writepages:
+ wbc->nr_to_write = to_write;
+ if (range_start)
+ wbc->range_start = range_start;
+ return ret;
+}
+
+static int ext4_da_write_begin(struct file *file, struct address_space *mapping,
+ loff_t pos, unsigned len, unsigned flags,
+ struct page **pagep, void **fsdata)
+{
+ int ret, retries = 0;
+ struct page *page;
+ pgoff_t index;
+ unsigned from, to;
+ struct inode *inode = mapping->host;
+ handle_t *handle;
+
+ index = pos >> PAGE_CACHE_SHIFT;
+ from = pos & (PAGE_CACHE_SIZE - 1);
+ to = from + len;
+
+retry:
+ /*
+ * With delayed allocation, we don't log the i_disksize update
+ * if there is delayed block allocation. But we still need
+ * to journalling the i_disksize update if writes to the end
+ * of file which has an already mapped buffer.
+ */
+ handle = ext4_journal_start(inode, 1);
+ if (IS_ERR(handle)) {
+ ret = PTR_ERR(handle);
+ goto out;
+ }
+
+ page = __grab_cache_page(mapping, index);
+ if (!page) {
+ ext4_journal_stop(handle);
+ ret = -ENOMEM;
+ goto out;
+ }
+ *pagep = page;
+
+ ret = block_write_begin(file, mapping, pos, len, flags, pagep, fsdata,
+ ext4_da_get_block_prep);
+ if (ret < 0) {
+ unlock_page(page);
+ ext4_journal_stop(handle);
+ page_cache_release(page);
+ }
+
+ if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
+ goto retry;
+out:
+ return ret;
+}
+
+/*
+ * Check if we should update i_disksize
+ * when write to the end of file but not require block allocation
+ */
+static int ext4_da_should_update_i_disksize(struct page *page,
+ unsigned long offset)
+{
+ struct buffer_head *bh;
+ struct inode *inode = page->mapping->host;
+ unsigned int idx;
+ int i;
+
+ bh = page_buffers(page);
+ idx = offset >> inode->i_blkbits;
+
+ for (i=0; i < idx; i++)
+ bh = bh->b_this_page;
+
+ if (!buffer_mapped(bh) || (buffer_delay(bh)))
+ return 0;
+ return 1;
+}
+
+static int ext4_da_write_end(struct file *file,
+ struct address_space *mapping,
+ loff_t pos, unsigned len, unsigned copied,
+ struct page *page, void *fsdata)
+{
+ struct inode *inode = mapping->host;
+ int ret = 0, ret2;
+ handle_t *handle = ext4_journal_current_handle();
+ loff_t new_i_size;
+ unsigned long start, end;
+
+ start = pos & (PAGE_CACHE_SIZE - 1);
+ end = start + copied -1;
+
+ /*
+ * generic_write_end() will run mark_inode_dirty() if i_size
+ * changes. So let's piggyback the i_disksize mark_inode_dirty
+ * into that.
+ */
+
+ new_i_size = pos + copied;
+ if (new_i_size > EXT4_I(inode)->i_disksize) {
+ if (ext4_da_should_update_i_disksize(page, end)) {
+ down_write(&EXT4_I(inode)->i_data_sem);
+ if (new_i_size > EXT4_I(inode)->i_disksize) {
+ /*
+ * Updating i_disksize when extending file
+ * without needing block allocation
+ */
+ if (ext4_should_order_data(inode))
+ ret = ext4_jbd2_file_inode(handle,
+ inode);
+
+ EXT4_I(inode)->i_disksize = new_i_size;
+ }
+ up_write(&EXT4_I(inode)->i_data_sem);
+ }
+ }
+ ret2 = generic_write_end(file, mapping, pos, len, copied,
+ page, fsdata);
+ copied = ret2;
+ if (ret2 < 0)
+ ret = ret2;
+ ret2 = ext4_journal_stop(handle);
+ if (!ret)
+ ret = ret2;
+
+ return ret ? ret : copied;
+}
+
+static void ext4_da_invalidatepage(struct page *page, unsigned long offset)
+{
+ /*
+ * Drop reserved blocks
+ */
+ BUG_ON(!PageLocked(page));
+ if (!page_has_buffers(page))
+ goto out;
+
+ ext4_da_page_release_reservation(page, offset);
+
+out:
+ ext4_invalidatepage(page, offset);
+
+ return;
+}
+
+
/*
* bmap() is special. It gets used by applications such as lilo and by
* the swapper to find the on-disk block of a specific piece of data.
journal_t *journal;
int err;
+ if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY) &&
+ test_opt(inode->i_sb, DELALLOC)) {
+ /*
+ * With delalloc we want to sync the file
+ * so that we can make sure we allocate
+ * blocks for file
+ */
+ filemap_write_and_wait(mapping);
+ }
+
if (EXT4_I(inode)->i_state & EXT4_STATE_JDATA) {
/*
* This is a REALLY heavyweight approach, but the use of
return 0;
}
-static int ext4_bh_unmapped_or_delay(handle_t *handle, struct buffer_head *bh)
-{
- return !buffer_mapped(bh) || buffer_delay(bh);
-}
-
/*
* Note that we don't need to start a transaction unless we're journaling data
* because we should have holes filled from ext4_page_mkwrite(). We even don't
struct inode *inode = page->mapping->host;
if (test_opt(inode->i_sb, NOBH))
- return nobh_writepage(page, ext4_get_block, wbc);
+ return nobh_writepage(page,
+ ext4_normal_get_block_write, wbc);
else
- return block_write_full_page(page, ext4_get_block, wbc);
+ return block_write_full_page(page,
+ ext4_normal_get_block_write,
+ wbc);
}
-
static int ext4_normal_writepage(struct page *page,
struct writeback_control *wbc)
{
loff_t len;
J_ASSERT(PageLocked(page));
- J_ASSERT(page_has_buffers(page));
if (page->index == size >> PAGE_CACHE_SHIFT)
len = size & ~PAGE_CACHE_MASK;
else
len = PAGE_CACHE_SIZE;
- BUG_ON(walk_page_buffers(NULL, page_buffers(page), 0, len, NULL,
- ext4_bh_unmapped_or_delay));
+
+ if (page_has_buffers(page)) {
+ /* if page has buffers it should all be mapped
+ * and allocated. If there are not buffers attached
+ * to the page we know the page is dirty but it lost
+ * buffers. That means that at some moment in time
+ * after write_begin() / write_end() has been called
+ * all buffers have been clean and thus they must have been
+ * written at least once. So they are all mapped and we can
+ * happily proceed with mapping them and writing the page.
+ */
+ BUG_ON(walk_page_buffers(NULL, page_buffers(page), 0, len, NULL,
+ ext4_bh_unmapped_or_delay));
+ }
if (!ext4_journal_current_handle())
return __ext4_normal_writepage(page, wbc);
int ret = 0;
int err;
- ret = block_prepare_write(page, 0, PAGE_CACHE_SIZE, ext4_get_block);
+ ret = block_prepare_write(page, 0, PAGE_CACHE_SIZE,
+ ext4_normal_get_block_write);
if (ret != 0)
goto out_unlock;
loff_t len;
J_ASSERT(PageLocked(page));
- J_ASSERT(page_has_buffers(page));
if (page->index == size >> PAGE_CACHE_SHIFT)
len = size & ~PAGE_CACHE_MASK;
else
len = PAGE_CACHE_SIZE;
- BUG_ON(walk_page_buffers(NULL, page_buffers(page), 0, len, NULL,
- ext4_bh_unmapped_or_delay));
+
+ if (page_has_buffers(page)) {
+ /* if page has buffers it should all be mapped
+ * and allocated. If there are not buffers attached
+ * to the page we know the page is dirty but it lost
+ * buffers. That means that at some moment in time
+ * after write_begin() / write_end() has been called
+ * all buffers have been clean and thus they must have been
+ * written at least once. So they are all mapped and we can
+ * happily proceed with mapping them and writing the page.
+ */
+ BUG_ON(walk_page_buffers(NULL, page_buffers(page), 0, len, NULL,
+ ext4_bh_unmapped_or_delay));
+ }
if (ext4_journal_current_handle())
goto no_write;
* really know unless we go poke around in the buffer_heads.
* But block_write_full_page will do the right thing.
*/
- return block_write_full_page(page, ext4_get_block, wbc);
+ return block_write_full_page(page,
+ ext4_normal_get_block_write,
+ wbc);
}
no_write:
redirty_page_for_writepage(wbc, page);
}
static const struct address_space_operations ext4_ordered_aops = {
- .readpage = ext4_readpage,
- .readpages = ext4_readpages,
- .writepage = ext4_normal_writepage,
- .sync_page = block_sync_page,
- .write_begin = ext4_write_begin,
- .write_end = ext4_ordered_write_end,
- .bmap = ext4_bmap,
- .invalidatepage = ext4_invalidatepage,
- .releasepage = ext4_releasepage,
- .direct_IO = ext4_direct_IO,
- .migratepage = buffer_migrate_page,
+ .readpage = ext4_readpage,
+ .readpages = ext4_readpages,
+ .writepage = ext4_normal_writepage,
+ .sync_page = block_sync_page,
+ .write_begin = ext4_write_begin,
+ .write_end = ext4_ordered_write_end,
+ .bmap = ext4_bmap,
+ .invalidatepage = ext4_invalidatepage,
+ .releasepage = ext4_releasepage,
+ .direct_IO = ext4_direct_IO,
+ .migratepage = buffer_migrate_page,
+ .is_partially_uptodate = block_is_partially_uptodate,
};
static const struct address_space_operations ext4_writeback_aops = {
- .readpage = ext4_readpage,
- .readpages = ext4_readpages,
- .writepage = ext4_normal_writepage,
- .sync_page = block_sync_page,
- .write_begin = ext4_write_begin,
- .write_end = ext4_writeback_write_end,
- .bmap = ext4_bmap,
- .invalidatepage = ext4_invalidatepage,
- .releasepage = ext4_releasepage,
- .direct_IO = ext4_direct_IO,
- .migratepage = buffer_migrate_page,
+ .readpage = ext4_readpage,
+ .readpages = ext4_readpages,
+ .writepage = ext4_normal_writepage,
+ .sync_page = block_sync_page,
+ .write_begin = ext4_write_begin,
+ .write_end = ext4_writeback_write_end,
+ .bmap = ext4_bmap,
+ .invalidatepage = ext4_invalidatepage,
+ .releasepage = ext4_releasepage,
+ .direct_IO = ext4_direct_IO,
+ .migratepage = buffer_migrate_page,
+ .is_partially_uptodate = block_is_partially_uptodate,
};
static const struct address_space_operations ext4_journalled_aops = {
- .readpage = ext4_readpage,
- .readpages = ext4_readpages,
- .writepage = ext4_journalled_writepage,
- .sync_page = block_sync_page,
- .write_begin = ext4_write_begin,
- .write_end = ext4_journalled_write_end,
- .set_page_dirty = ext4_journalled_set_page_dirty,
- .bmap = ext4_bmap,
- .invalidatepage = ext4_invalidatepage,
- .releasepage = ext4_releasepage,
+ .readpage = ext4_readpage,
+ .readpages = ext4_readpages,
+ .writepage = ext4_journalled_writepage,
+ .sync_page = block_sync_page,
+ .write_begin = ext4_write_begin,
+ .write_end = ext4_journalled_write_end,
+ .set_page_dirty = ext4_journalled_set_page_dirty,
+ .bmap = ext4_bmap,
+ .invalidatepage = ext4_invalidatepage,
+ .releasepage = ext4_releasepage,
+ .is_partially_uptodate = block_is_partially_uptodate,
+};
+
+static const struct address_space_operations ext4_da_aops = {
+ .readpage = ext4_readpage,
+ .readpages = ext4_readpages,
+ .writepage = ext4_da_writepage,
+ .writepages = ext4_da_writepages,
+ .sync_page = block_sync_page,
+ .write_begin = ext4_da_write_begin,
+ .write_end = ext4_da_write_end,
+ .bmap = ext4_bmap,
+ .invalidatepage = ext4_da_invalidatepage,
+ .releasepage = ext4_releasepage,
+ .direct_IO = ext4_direct_IO,
+ .migratepage = buffer_migrate_page,
+ .is_partially_uptodate = block_is_partially_uptodate,
};
void ext4_set_aops(struct inode *inode)
{
- if (ext4_should_order_data(inode))
+ if (ext4_should_order_data(inode) &&
+ test_opt(inode->i_sb, DELALLOC))
+ inode->i_mapping->a_ops = &ext4_da_aops;
+ else if (ext4_should_order_data(inode))
inode->i_mapping->a_ops = &ext4_ordered_aops;
+ else if (ext4_should_writeback_data(inode) &&
+ test_opt(inode->i_sb, DELALLOC))
+ inode->i_mapping->a_ops = &ext4_da_aops;
else if (ext4_should_writeback_data(inode))
inode->i_mapping->a_ops = &ext4_writeback_aops;
else
goto out_stop;
/*
+ * From here we block out all ext4_get_block() callers who want to
+ * modify the block allocation tree.
+ */
+ down_write(&ei->i_data_sem);
+ /*
* The orphan list entry will now protect us from any crash which
* occurs before the truncate completes, so it is now safe to propagate
* the new, shorter inode size (held for now in i_size) into the
*/
ei->i_disksize = inode->i_size;
- /*
- * From here we block out all ext4_get_block() callers who want to
- * modify the block allocation tree.
- */
- down_write(&ei->i_data_sem);
-
if (n == 1) { /* direct blocks */
ext4_free_data(handle, inode, NULL, i_data+offsets[0],
i_data + EXT4_NDIR_BLOCKS);
}
if (!buffer_uptodate(bh)) {
lock_buffer(bh);
+
+ /*
+ * If the buffer has the write error flag, we have failed
+ * to write out another inode in the same block. In this
+ * case, we don't have to read the block because we may
+ * read the old inode data successfully.
+ */
+ if (buffer_write_io_error(bh) && !buffer_uptodate(bh))
+ set_buffer_uptodate(bh);
+
if (buffer_uptodate(bh)) {
/* someone brought it uptodate while we waited */
unlock_buffer(bh);
return error;
}
+int ext4_getattr(struct vfsmount *mnt, struct dentry *dentry,
+ struct kstat *stat)
+{
+ struct inode *inode;
+ unsigned long delalloc_blocks;
+
+ inode = dentry->d_inode;
+ generic_fillattr(inode, stat);
+
+ /*
+ * We can't update i_blocks if the block allocation is delayed
+ * otherwise in the case of system crash before the real block
+ * allocation is done, we will have i_blocks inconsistent with
+ * on-disk file blocks.
+ * We always keep i_blocks updated together with real
+ * allocation. But to not confuse with user, stat
+ * will return the blocks that include the delayed allocation
+ * blocks for this file.
+ */
+ spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
+ delalloc_blocks = EXT4_I(inode)->i_reserved_data_blocks;
+ spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
+
+ stat->blocks += (delalloc_blocks << inode->i_sb->s_blocksize_bits)>>9;
+ return 0;
+}
/*
* How many blocks doth make a writepage()?
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff