summaryrefslogtreecommitdiff
path: root/fs/ext4/inode.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/ext4/inode.c')
-rw-r--r--fs/ext4/inode.c581
1 files changed, 389 insertions, 192 deletions
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index b3a5213bc73e..0723774bdfb5 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -37,6 +37,7 @@
#include <linux/printk.h>
#include <linux/slab.h>
#include <linux/ratelimit.h>
+#include <linux/aio.h>
#include "ext4_jbd2.h"
#include "xattr.h"
@@ -55,21 +56,21 @@ static __u32 ext4_inode_csum(struct inode *inode, struct ext4_inode *raw,
__u16 csum_hi = 0;
__u32 csum;
- csum_lo = raw->i_checksum_lo;
+ csum_lo = le16_to_cpu(raw->i_checksum_lo);
raw->i_checksum_lo = 0;
if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE &&
EXT4_FITS_IN_INODE(raw, ei, i_checksum_hi)) {
- csum_hi = raw->i_checksum_hi;
+ csum_hi = le16_to_cpu(raw->i_checksum_hi);
raw->i_checksum_hi = 0;
}
csum = ext4_chksum(sbi, ei->i_csum_seed, (__u8 *)raw,
EXT4_INODE_SIZE(inode->i_sb));
- raw->i_checksum_lo = csum_lo;
+ raw->i_checksum_lo = cpu_to_le16(csum_lo);
if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE &&
EXT4_FITS_IN_INODE(raw, ei, i_checksum_hi))
- raw->i_checksum_hi = csum_hi;
+ raw->i_checksum_hi = cpu_to_le16(csum_hi);
return csum;
}
@@ -210,8 +211,7 @@ void ext4_evict_inode(struct inode *inode)
journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
tid_t commit_tid = EXT4_I(inode)->i_datasync_tid;
- jbd2_log_start_commit(journal, commit_tid);
- jbd2_log_wait_commit(journal, commit_tid);
+ jbd2_complete_transaction(journal, commit_tid);
filemap_write_and_wait(&inode->i_data);
}
truncate_inode_pages(&inode->i_data, 0);
@@ -1081,20 +1081,42 @@ retry_journal:
/* For write_end() in data=journal mode */
static int write_end_fn(handle_t *handle, struct buffer_head *bh)
{
+ int ret;
if (!buffer_mapped(bh) || buffer_freed(bh))
return 0;
set_buffer_uptodate(bh);
- return ext4_handle_dirty_metadata(handle, NULL, bh);
+ ret = ext4_handle_dirty_metadata(handle, NULL, bh);
+ clear_buffer_meta(bh);
+ clear_buffer_prio(bh);
+ return ret;
}
-static int ext4_generic_write_end(struct file *file,
- struct address_space *mapping,
- loff_t pos, unsigned len, unsigned copied,
- struct page *page, void *fsdata)
+/*
+ * We need to pick up the new inode size which generic_commit_write gave us
+ * `file' can be NULL - eg, when called from page_symlink().
+ *
+ * ext4 never places buffers on inode->i_mapping->private_list. metadata
+ * buffers are managed internally.
+ */
+static int ext4_write_end(struct file *file,
+ struct address_space *mapping,
+ loff_t pos, unsigned len, unsigned copied,
+ struct page *page, void *fsdata)
{
- int i_size_changed = 0;
- struct inode *inode = mapping->host;
handle_t *handle = ext4_journal_current_handle();
+ struct inode *inode = mapping->host;
+ int ret = 0, ret2;
+ int i_size_changed = 0;
+
+ trace_ext4_write_end(inode, pos, len, copied);
+ if (ext4_test_inode_state(inode, EXT4_STATE_ORDERED_MODE)) {
+ ret = ext4_jbd2_file_inode(handle, inode);
+ if (ret) {
+ unlock_page(page);
+ page_cache_release(page);
+ goto errout;
+ }
+ }
if (ext4_has_inline_data(inode))
copied = ext4_write_inline_data_end(inode, pos, len,
@@ -1105,7 +1127,7 @@ static int ext4_generic_write_end(struct file *file,
/*
* No need to use i_size_read() here, the i_size
- * cannot change under us because we hold i_mutex.
+ * cannot change under us because we hole i_mutex.
*
* But it's important to update i_size while still holding page lock:
* page writeout could otherwise come in and zero beyond i_size.
@@ -1115,10 +1137,10 @@ static int ext4_generic_write_end(struct file *file,
i_size_changed = 1;
}
- if (pos + copied > EXT4_I(inode)->i_disksize) {
+ if (pos + copied > EXT4_I(inode)->i_disksize) {
/* We need to mark inode dirty even if
* new_i_size is less that inode->i_size
- * bu greater than i_disksize.(hint delalloc)
+ * but greater than i_disksize. (hint delalloc)
*/
ext4_update_i_disksize(inode, (pos + copied));
i_size_changed = 1;
@@ -1135,87 +1157,15 @@ static int ext4_generic_write_end(struct file *file,
if (i_size_changed)
ext4_mark_inode_dirty(handle, inode);
- return copied;
-}
-
-/*
- * We need to pick up the new inode size which generic_commit_write gave us
- * `file' can be NULL - eg, when called from page_symlink().
- *
- * ext4 never places buffers on inode->i_mapping->private_list. metadata
- * buffers are managed internally.
- */
-static int ext4_ordered_write_end(struct file *file,
- struct address_space *mapping,
- loff_t pos, unsigned len, unsigned copied,
- struct page *page, void *fsdata)
-{
- handle_t *handle = ext4_journal_current_handle();
- struct inode *inode = mapping->host;
- int ret = 0, ret2;
-
- trace_ext4_ordered_write_end(inode, pos, len, copied);
- ret = ext4_jbd2_file_inode(handle, inode);
-
- if (ret == 0) {
- ret2 = ext4_generic_write_end(file, mapping, pos, len, copied,
- page, fsdata);
- copied = ret2;
- if (pos + len > inode->i_size && ext4_can_truncate(inode))
- /* if we have allocated more blocks and copied
- * less. We will have blocks allocated outside
- * inode->i_size. So truncate them
- */
- ext4_orphan_add(handle, inode);
- if (ret2 < 0)
- ret = ret2;
- } else {
- unlock_page(page);
- page_cache_release(page);
- }
-
- ret2 = ext4_journal_stop(handle);
- if (!ret)
- ret = ret2;
-
- if (pos + len > inode->i_size) {
- ext4_truncate_failed_write(inode);
- /*
- * If truncate failed early the inode might still be
- * on the orphan list; we need to make sure the inode
- * is removed from the orphan list in that case.
- */
- if (inode->i_nlink)
- ext4_orphan_del(NULL, inode);
- }
-
-
- return ret ? ret : copied;
-}
-
-static int ext4_writeback_write_end(struct file *file,
- struct address_space *mapping,
- loff_t pos, unsigned len, unsigned copied,
- struct page *page, void *fsdata)
-{
- handle_t *handle = ext4_journal_current_handle();
- struct inode *inode = mapping->host;
- int ret = 0, ret2;
-
- trace_ext4_writeback_write_end(inode, pos, len, copied);
- ret2 = ext4_generic_write_end(file, mapping, pos, len, copied,
- page, fsdata);
- copied = ret2;
+ if (copied < 0)
+ ret = copied;
if (pos + len > inode->i_size && ext4_can_truncate(inode))
/* if we have allocated more blocks and copied
* less. We will have blocks allocated outside
* inode->i_size. So truncate them
*/
ext4_orphan_add(handle, inode);
-
- if (ret2 < 0)
- ret = ret2;
-
+errout:
ret2 = ext4_journal_stop(handle);
if (!ret)
ret = ret2;
@@ -1538,7 +1488,10 @@ static int mpage_da_submit_io(struct mpage_da_data *mpd,
struct ext4_io_submit io_submit;
BUG_ON(mpd->next_page <= mpd->first_page);
- memset(&io_submit, 0, sizeof(io_submit));
+ ext4_io_submit_init(&io_submit, mpd->wbc);
+ io_submit.io_end = ext4_init_io_end(inode, GFP_NOFS);
+ if (!io_submit.io_end)
+ return -ENOMEM;
/*
* We need to start from the first_page to the next_page - 1
* to make sure we also write the mapped dirty buffer_heads.
@@ -1626,6 +1579,8 @@ static int mpage_da_submit_io(struct mpage_da_data *mpd,
pagevec_release(&pvec);
}
ext4_io_submit(&io_submit);
+ /* Drop io_end reference we got from init */
+ ext4_put_io_end_defer(io_submit.io_end);
return ret;
}
@@ -1670,22 +1625,25 @@ static void ext4_print_free_blocks(struct inode *inode)
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
struct super_block *sb = inode->i_sb;
+ struct ext4_inode_info *ei = EXT4_I(inode);
ext4_msg(sb, KERN_CRIT, "Total free blocks count %lld",
EXT4_C2B(EXT4_SB(inode->i_sb),
- ext4_count_free_clusters(inode->i_sb)));
+ ext4_count_free_clusters(sb)));
ext4_msg(sb, KERN_CRIT, "Free/Dirty block details");
ext4_msg(sb, KERN_CRIT, "free_blocks=%lld",
- (long long) EXT4_C2B(EXT4_SB(inode->i_sb),
+ (long long) EXT4_C2B(EXT4_SB(sb),
percpu_counter_sum(&sbi->s_freeclusters_counter)));
ext4_msg(sb, KERN_CRIT, "dirty_blocks=%lld",
- (long long) EXT4_C2B(EXT4_SB(inode->i_sb),
+ (long long) EXT4_C2B(EXT4_SB(sb),
percpu_counter_sum(&sbi->s_dirtyclusters_counter)));
ext4_msg(sb, KERN_CRIT, "Block reservation details");
ext4_msg(sb, KERN_CRIT, "i_reserved_data_blocks=%u",
- EXT4_I(inode)->i_reserved_data_blocks);
+ ei->i_reserved_data_blocks);
ext4_msg(sb, KERN_CRIT, "i_reserved_meta_blocks=%u",
- EXT4_I(inode)->i_reserved_meta_blocks);
+ ei->i_reserved_meta_blocks);
+ ext4_msg(sb, KERN_CRIT, "i_allocated_meta_blocks=%u",
+ ei->i_allocated_meta_blocks);
return;
}
@@ -1740,12 +1698,21 @@ static void mpage_da_map_and_submit(struct mpage_da_data *mpd)
*/
map.m_lblk = next;
map.m_len = max_blocks;
- get_blocks_flags = EXT4_GET_BLOCKS_CREATE;
+ /*
+ * We're in delalloc path and it is possible that we're going to
+ * need more metadata blocks than previously reserved. However
+ * we must not fail because we're in writeback and there is
+ * nothing we can do about it so it might result in data loss.
+ * So use reserved blocks to allocate metadata if possible.
+ */
+ get_blocks_flags = EXT4_GET_BLOCKS_CREATE |
+ EXT4_GET_BLOCKS_METADATA_NOFAIL;
if (ext4_should_dioread_nolock(mpd->inode))
get_blocks_flags |= EXT4_GET_BLOCKS_IO_CREATE_EXT;
if (mpd->b_state & (1 << BH_Delay))
get_blocks_flags |= EXT4_GET_BLOCKS_DELALLOC_RESERVE;
+
blks = ext4_map_blocks(handle, mpd->inode, &map, get_blocks_flags);
if (blks < 0) {
struct super_block *sb = mpd->inode->i_sb;
@@ -2272,9 +2239,16 @@ static int ext4_writepage(struct page *page,
*/
return __ext4_journalled_writepage(page, len);
- memset(&io_submit, 0, sizeof(io_submit));
+ ext4_io_submit_init(&io_submit, wbc);
+ io_submit.io_end = ext4_init_io_end(inode, GFP_NOFS);
+ if (!io_submit.io_end) {
+ redirty_page_for_writepage(wbc, page);
+ return -ENOMEM;
+ }
ret = ext4_bio_write_page(&io_submit, page, len, wbc);
ext4_io_submit(&io_submit);
+ /* Drop io_end reference we got from init */
+ ext4_put_io_end_defer(io_submit.io_end);
return ret;
}
@@ -2661,7 +2635,7 @@ out_writepages:
static int ext4_nonda_switch(struct super_block *sb)
{
- s64 free_blocks, dirty_blocks;
+ s64 free_clusters, dirty_clusters;
struct ext4_sb_info *sbi = EXT4_SB(sb);
/*
@@ -2672,17 +2646,18 @@ static int ext4_nonda_switch(struct super_block *sb)
* Delalloc need an accurate free block accounting. So switch
* to non delalloc when we are near to error range.
*/
- free_blocks = EXT4_C2B(sbi,
- percpu_counter_read_positive(&sbi->s_freeclusters_counter));
- dirty_blocks = percpu_counter_read_positive(&sbi->s_dirtyclusters_counter);
+ free_clusters =
+ percpu_counter_read_positive(&sbi->s_freeclusters_counter);
+ dirty_clusters =
+ percpu_counter_read_positive(&sbi->s_dirtyclusters_counter);
/*
* Start pushing delalloc when 1/2 of free blocks are dirty.
*/
- if (dirty_blocks && (free_blocks < 2 * dirty_blocks))
+ if (dirty_clusters && (free_clusters < 2 * dirty_clusters))
try_to_writeback_inodes_sb(sb, WB_REASON_FS_FREE_SPACE);
- if (2 * free_blocks < 3 * dirty_blocks ||
- free_blocks < (dirty_blocks + EXT4_FREECLUSTERS_WATERMARK)) {
+ if (2 * free_clusters < 3 * dirty_clusters ||
+ free_clusters < (dirty_clusters + EXT4_FREECLUSTERS_WATERMARK)) {
/*
* free block count is less than 150% of dirty blocks
* or free blocks is less than watermark
@@ -2818,18 +2793,9 @@ static int ext4_da_write_end(struct file *file,
unsigned long start, end;
int write_mode = (int)(unsigned long)fsdata;
- if (write_mode == FALL_BACK_TO_NONDELALLOC) {
- switch (ext4_inode_journal_mode(inode)) {
- case EXT4_INODE_ORDERED_DATA_MODE:
- return ext4_ordered_write_end(file, mapping, pos,
- len, copied, page, fsdata);
- case EXT4_INODE_WRITEBACK_DATA_MODE:
- return ext4_writeback_write_end(file, mapping, pos,
- len, copied, page, fsdata);
- default:
- BUG();
- }
- }
+ if (write_mode == FALL_BACK_TO_NONDELALLOC)
+ return ext4_write_end(file, mapping, pos,
+ len, copied, page, fsdata);
trace_ext4_da_write_end(inode, pos, len, copied);
start = pos & (PAGE_CACHE_SIZE - 1);
@@ -3113,9 +3079,13 @@ static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset,
struct inode *inode = file_inode(iocb->ki_filp);
ext4_io_end_t *io_end = iocb->private;
- /* if not async direct IO or dio with 0 bytes write, just return */
- if (!io_end || !size)
- goto out;
+ /* if not async direct IO just return */
+ if (!io_end) {
+ inode_dio_done(inode);
+ if (is_async)
+ aio_complete(iocb, ret, 0);
+ return;
+ }
ext_debug("ext4_end_io_dio(): io_end 0x%p "
"for inode %lu, iocb 0x%p, offset %llu, size %zd\n",
@@ -3123,25 +3093,13 @@ static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset,
size);
iocb->private = NULL;
-
- /* if not aio dio with unwritten extents, just free io and return */
- if (!(io_end->flag & EXT4_IO_END_UNWRITTEN)) {
- ext4_free_io_end(io_end);
-out:
- inode_dio_done(inode);
- if (is_async)
- aio_complete(iocb, ret, 0);
- return;
- }
-
io_end->offset = offset;
io_end->size = size;
if (is_async) {
io_end->iocb = iocb;
io_end->result = ret;
}
-
- ext4_add_complete_io(io_end);
+ ext4_put_io_end_defer(io_end);
}
/*
@@ -3175,6 +3133,7 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb,
get_block_t *get_block_func = NULL;
int dio_flags = 0;
loff_t final_size = offset + count;
+ ext4_io_end_t *io_end = NULL;
/* Use the old path for reads and writes beyond i_size. */
if (rw != WRITE || final_size > inode->i_size)
@@ -3213,13 +3172,16 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb,
iocb->private = NULL;
ext4_inode_aio_set(inode, NULL);
if (!is_sync_kiocb(iocb)) {
- ext4_io_end_t *io_end = ext4_init_io_end(inode, GFP_NOFS);
+ io_end = ext4_init_io_end(inode, GFP_NOFS);
if (!io_end) {
ret = -ENOMEM;
goto retake_lock;
}
io_end->flag |= EXT4_IO_END_DIRECT;
- iocb->private = io_end;
+ /*
+ * Grab reference for DIO. Will be dropped in ext4_end_io_dio()
+ */
+ iocb->private = ext4_get_io_end(io_end);
/*
* we save the io structure for current async direct
* IO, so that later ext4_map_blocks() could flag the
@@ -3243,26 +3205,27 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb,
NULL,
dio_flags);
- if (iocb->private)
- ext4_inode_aio_set(inode, NULL);
/*
- * The io_end structure takes a reference to the inode, that
- * structure needs to be destroyed and the reference to the
- * inode need to be dropped, when IO is complete, even with 0
- * byte write, or failed.
- *
- * In the successful AIO DIO case, the io_end structure will
- * be destroyed and the reference to the inode will be dropped
- * after the end_io call back function is called.
- *
- * In the case there is 0 byte write, or error case, since VFS
- * direct IO won't invoke the end_io call back function, we
- * need to free the end_io structure here.
+ * Put our reference to io_end. This can free the io_end structure e.g.
+ * in sync IO case or in case of error. It can even perform extent
+ * conversion if all bios we submitted finished before we got here.
+ * Note that in that case iocb->private can be already set to NULL
+ * here.
*/
- if (ret != -EIOCBQUEUED && ret <= 0 && iocb->private) {
- ext4_free_io_end(iocb->private);
- iocb->private = NULL;
- } else if (ret > 0 && !overwrite && ext4_test_inode_state(inode,
+ if (io_end) {
+ ext4_inode_aio_set(inode, NULL);
+ ext4_put_io_end(io_end);
+ /*
+ * In case of error or no write ext4_end_io_dio() was not
+ * called so we have to put iocb's reference.
+ */
+ if (ret <= 0 && ret != -EIOCBQUEUED) {
+ WARN_ON(iocb->private != io_end);
+ ext4_put_io_end(io_end);
+ iocb->private = NULL;
+ }
+ }
+ if (ret > 0 && !overwrite && ext4_test_inode_state(inode,
EXT4_STATE_DIO_UNWRITTEN)) {
int err;
/*
@@ -3334,27 +3297,12 @@ static int ext4_journalled_set_page_dirty(struct page *page)
return __set_page_dirty_nobuffers(page);
}
-static const struct address_space_operations ext4_ordered_aops = {
+static const struct address_space_operations ext4_aops = {
.readpage = ext4_readpage,
.readpages = ext4_readpages,
.writepage = ext4_writepage,
.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,
- .error_remove_page = generic_error_remove_page,
-};
-
-static const struct address_space_operations ext4_writeback_aops = {
- .readpage = ext4_readpage,
- .readpages = ext4_readpages,
- .writepage = ext4_writepage,
- .write_begin = ext4_write_begin,
- .write_end = ext4_writeback_write_end,
+ .write_end = ext4_write_end,
.bmap = ext4_bmap,
.invalidatepage = ext4_invalidatepage,
.releasepage = ext4_releasepage,
@@ -3399,23 +3347,21 @@ void ext4_set_aops(struct inode *inode)
{
switch (ext4_inode_journal_mode(inode)) {
case EXT4_INODE_ORDERED_DATA_MODE:
- if (test_opt(inode->i_sb, DELALLOC))
- inode->i_mapping->a_ops = &ext4_da_aops;
- else
- inode->i_mapping->a_ops = &ext4_ordered_aops;
+ ext4_set_inode_state(inode, EXT4_STATE_ORDERED_MODE);
break;
case EXT4_INODE_WRITEBACK_DATA_MODE:
- if (test_opt(inode->i_sb, DELALLOC))
- inode->i_mapping->a_ops = &ext4_da_aops;
- else
- inode->i_mapping->a_ops = &ext4_writeback_aops;
+ ext4_clear_inode_state(inode, EXT4_STATE_ORDERED_MODE);
break;
case EXT4_INODE_JOURNAL_DATA_MODE:
inode->i_mapping->a_ops = &ext4_journalled_aops;
- break;
+ return;
default:
BUG();
}
+ if (test_opt(inode->i_sb, DELALLOC))
+ inode->i_mapping->a_ops = &ext4_da_aops;
+ else
+ inode->i_mapping->a_ops = &ext4_aops;
}
@@ -3646,20 +3592,190 @@ int ext4_can_truncate(struct inode *inode)
int ext4_punch_hole(struct file *file, loff_t offset, loff_t length)
{
struct inode *inode = file_inode(file);
+ struct super_block *sb = inode->i_sb;
+ ext4_lblk_t first_block, stop_block;
+ struct address_space *mapping = inode->i_mapping;
+ loff_t first_page, last_page, page_len;
+ loff_t first_page_offset, last_page_offset;
+ handle_t *handle;
+ unsigned int credits;
+ int ret = 0;
+
if (!S_ISREG(inode->i_mode))
return -EOPNOTSUPP;
- if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
- return ext4_ind_punch_hole(file, offset, length);
-
- if (EXT4_SB(inode->i_sb)->s_cluster_ratio > 1) {
+ if (EXT4_SB(sb)->s_cluster_ratio > 1) {
/* TODO: Add support for bigalloc file systems */
return -EOPNOTSUPP;
}
trace_ext4_punch_hole(inode, offset, length);
- return ext4_ext_punch_hole(file, offset, length);
+ /*
+ * Write out all dirty pages to avoid race conditions
+ * Then release them.
+ */
+ if (mapping->nrpages && mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) {
+ ret = filemap_write_and_wait_range(mapping, offset,
+ offset + length - 1);
+ if (ret)
+ return ret;
+ }
+
+ mutex_lock(&inode->i_mutex);
+ /* It's not possible punch hole on append only file */
+ if (IS_APPEND(inode) || IS_IMMUTABLE(inode)) {
+ ret = -EPERM;
+ goto out_mutex;
+ }
+ if (IS_SWAPFILE(inode)) {
+ ret = -ETXTBSY;
+ goto out_mutex;
+ }
+
+ /* No need to punch hole beyond i_size */
+ if (offset >= inode->i_size)
+ goto out_mutex;
+
+ /*
+ * If the hole extends beyond i_size, set the hole
+ * to end after the page that contains i_size
+ */
+ if (offset + length > inode->i_size) {
+ length = inode->i_size +
+ PAGE_CACHE_SIZE - (inode->i_size & (PAGE_CACHE_SIZE - 1)) -
+ offset;
+ }
+
+ first_page = (offset + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+ last_page = (offset + length) >> PAGE_CACHE_SHIFT;
+
+ first_page_offset = first_page << PAGE_CACHE_SHIFT;
+ last_page_offset = last_page << PAGE_CACHE_SHIFT;
+
+ /* Now release the pages */
+ if (last_page_offset > first_page_offset) {
+ truncate_pagecache_range(inode, first_page_offset,
+ last_page_offset - 1);
+ }
+
+ /* Wait all existing dio workers, newcomers will block on i_mutex */
+ ext4_inode_block_unlocked_dio(inode);
+ ret = ext4_flush_unwritten_io(inode);
+ if (ret)
+ goto out_dio;
+ inode_dio_wait(inode);
+
+ if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
+ credits = ext4_writepage_trans_blocks(inode);
+ else
+ credits = ext4_blocks_for_truncate(inode);
+ handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits);
+ if (IS_ERR(handle)) {
+ ret = PTR_ERR(handle);
+ ext4_std_error(sb, ret);
+ goto out_dio;
+ }
+
+ /*
+ * Now we need to zero out the non-page-aligned data in the
+ * pages at the start and tail of the hole, and unmap the
+ * buffer heads for the block aligned regions of the page that
+ * were completely zeroed.
+ */
+ if (first_page > last_page) {
+ /*
+ * If the file space being truncated is contained
+ * within a page just zero out and unmap the middle of
+ * that page
+ */
+ ret = ext4_discard_partial_page_buffers(handle,
+ mapping, offset, length, 0);
+
+ if (ret)
+ goto out_stop;
+ } else {
+ /*
+ * zero out and unmap the partial page that contains
+ * the start of the hole
+ */
+ page_len = first_page_offset - offset;
+ if (page_len > 0) {
+ ret = ext4_discard_partial_page_buffers(handle, mapping,
+ offset, page_len, 0);
+ if (ret)
+ goto out_stop;
+ }
+
+ /*
+ * zero out and unmap the partial page that contains
+ * the end of the hole
+ */
+ page_len = offset + length - last_page_offset;
+ if (page_len > 0) {
+ ret = ext4_discard_partial_page_buffers(handle, mapping,
+ last_page_offset, page_len, 0);
+ if (ret)
+ goto out_stop;
+ }
+ }
+
+ /*
+ * If i_size is contained in the last page, we need to
+ * unmap and zero the partial page after i_size
+ */
+ if (inode->i_size >> PAGE_CACHE_SHIFT == last_page &&
+ inode->i_size % PAGE_CACHE_SIZE != 0) {
+ page_len = PAGE_CACHE_SIZE -
+ (inode->i_size & (PAGE_CACHE_SIZE - 1));
+
+ if (page_len > 0) {
+ ret = ext4_discard_partial_page_buffers(handle,
+ mapping, inode->i_size, page_len, 0);
+
+ if (ret)
+ goto out_stop;
+ }
+ }
+
+ first_block = (offset + sb->s_blocksize - 1) >>
+ EXT4_BLOCK_SIZE_BITS(sb);
+ stop_block = (offset + length) >> EXT4_BLOCK_SIZE_BITS(sb);
+
+ /* If there are no blocks to remove, return now */
+ if (first_block >= stop_block)
+ goto out_stop;
+
+ down_write(&EXT4_I(inode)->i_data_sem);
+ ext4_discard_preallocations(inode);
+
+ ret = ext4_es_remove_extent(inode, first_block,
+ stop_block - first_block);
+ if (ret) {
+ up_write(&EXT4_I(inode)->i_data_sem);
+ goto out_stop;
+ }
+
+ if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
+ ret = ext4_ext_remove_space(inode, first_block,
+ stop_block - 1);
+ else
+ ret = ext4_free_hole_blocks(handle, inode, first_block,
+ stop_block);
+
+ ext4_discard_preallocations(inode);
+ up_write(&EXT4_I(inode)->i_data_sem);
+ if (IS_SYNC(inode))
+ ext4_handle_sync(handle);
+ inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
+ ext4_mark_inode_dirty(handle, inode);
+out_stop:
+ ext4_journal_stop(handle);
+out_dio:
+ ext4_inode_resume_unlocked_dio(inode);
+out_mutex:
+ mutex_unlock(&inode->i_mutex);
+ return ret;
}
/*
@@ -3692,6 +3808,19 @@ int ext4_punch_hole(struct file *file, loff_t offset, loff_t length)
*/
void ext4_truncate(struct inode *inode)
{
+ struct ext4_inode_info *ei = EXT4_I(inode);
+ unsigned int credits;
+ handle_t *handle;
+ struct address_space *mapping = inode->i_mapping;
+ loff_t page_len;
+
+ /*
+ * There is a possibility that we're either freeing the inode
+ * or it completely new indode. In those cases we might not
+ * have i_mutex locked because it's not necessary.
+ */
+ if (!(inode->i_state & (I_NEW|I_FREEING)))
+ WARN_ON(!mutex_is_locked(&inode->i_mutex));
trace_ext4_truncate_enter(inode);
if (!ext4_can_truncate(inode))
@@ -3710,10 +3839,72 @@ void ext4_truncate(struct inode *inode)
return;
}
+ /*
+ * finish any pending end_io work so we won't run the risk of
+ * converting any truncated blocks to initialized later
+ */
+ ext4_flush_unwritten_io(inode);
+
+ if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
+ credits = ext4_writepage_trans_blocks(inode);
+ else
+ credits = ext4_blocks_for_truncate(inode);
+
+ handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits);
+ if (IS_ERR(handle)) {
+ ext4_std_error(inode->i_sb, PTR_ERR(handle));
+ return;
+ }
+
+ if (inode->i_size % PAGE_CACHE_SIZE != 0) {
+ page_len = PAGE_CACHE_SIZE -
+ (inode->i_size & (PAGE_CACHE_SIZE - 1));
+
+ if (ext4_discard_partial_page_buffers(handle,
+ mapping, inode->i_size, page_len, 0))
+ goto out_stop;
+ }
+
+ /*
+ * We add the inode to the orphan list, so that if this
+ * truncate spans multiple transactions, and we crash, we will
+ * resume the truncate when the filesystem recovers. It also
+ * marks the inode dirty, to catch the new size.
+ *
+ * Implication: the file must always be in a sane, consistent
+ * truncatable state while each transaction commits.
+ */
+ if (ext4_orphan_add(handle, inode))
+ goto out_stop;
+
+ down_write(&EXT4_I(inode)->i_data_sem);
+
+ ext4_discard_preallocations(inode);
+
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
- ext4_ext_truncate(inode);
+ ext4_ext_truncate(handle, inode);
else
- ext4_ind_truncate(inode);
+ ext4_ind_truncate(handle, inode);
+
+ up_write(&ei->i_data_sem);
+
+ if (IS_SYNC(inode))
+ ext4_handle_sync(handle);
+
+out_stop:
+ /*
+ * If this was a simple ftruncate() and the file will remain alive,
+ * then we need to clear up the orphan record which we created above.
+ * However, if this was a real unlink then we were called by
+ * ext4_delete_inode(), and we allow that function to clean up the
+ * orphan info for us.
+ */
+ if (inode->i_nlink)
+ ext4_orphan_del(handle, inode);
+
+ inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
+ ext4_mark_inode_dirty(handle, inode);
+ ext4_journal_stop(handle);
trace_ext4_truncate_exit(inode);
}
@@ -3821,13 +4012,14 @@ make_io:
if (EXT4_SB(sb)->s_inode_readahead_blks) {
ext4_fsblk_t b, end, table;
unsigned num;
+ __u32 ra_blks = EXT4_SB(sb)->s_inode_readahead_blks;
table = ext4_inode_table(sb, gdp);
/* s_inode_readahead_blks is always a power of 2 */
- b = block & ~(EXT4_SB(sb)->s_inode_readahead_blks-1);
+ b = block & ~((ext4_fsblk_t) ra_blks - 1);
if (table > b)
b = table;
- end = b + EXT4_SB(sb)->s_inode_readahead_blks;
+ end = b + ra_blks;
num = EXT4_INODES_PER_GROUP(sb);
if (ext4_has_group_desc_csum(sb))
num -= ext4_itable_unused_count(sb, gdp);
@@ -4024,8 +4216,9 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
* NeilBrown 1999oct15
*/
if (inode->i_nlink == 0) {
- if (inode->i_mode == 0 ||
- !(EXT4_SB(inode->i_sb)->s_mount_state & EXT4_ORPHAN_FS)) {
+ if ((inode->i_mode == 0 ||
+ !(EXT4_SB(inode->i_sb)->s_mount_state & EXT4_ORPHAN_FS)) &&
+ ino != EXT4_BOOT_LOADER_INO) {
/* this inode is deleted */
ret = -ESTALE;
goto bad_inode;
@@ -4033,7 +4226,9 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
/* The only unlinked inodes we let through here have
* valid i_mode and are being read by the orphan
* recovery code: that's fine, we're about to complete
- * the process of deleting those. */
+ * the process of deleting those.
+ * OR it is the EXT4_BOOT_LOADER_INO which is
+ * not initialized on a new filesystem. */
}
ei->i_flags = le32_to_cpu(raw_inode->i_flags);
inode->i_blocks = ext4_inode_blocks(raw_inode, ei);
@@ -4153,6 +4348,8 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
else
init_special_inode(inode, inode->i_mode,
new_decode_dev(le32_to_cpu(raw_inode->i_block[1])));
+ } else if (ino == EXT4_BOOT_LOADER_INO) {
+ make_bad_inode(inode);
} else {
ret = -EIO;
EXT4_ERROR_INODE(inode, "bogus i_mode (%o)", inode->i_mode);