/*
* Initialise the state of a blockdev page's buffers.
*/
-static void
+static sector_t
init_page_buffers(struct page *page, struct block_device *bdev,
sector_t block, int size)
{
block++;
bh = bh->b_this_page;
} while (bh != head);
+
+ /*
+ * Caller needs to validate requested block against end of device.
+ */
+ return end_block;
}
/*
* Create the page-cache page that contains the requested block.
*
- * This is user purely for blockdev mappings.
+ * This is used purely for blockdev mappings.
*/
-static struct page *
+static int
grow_dev_page(struct block_device *bdev, sector_t block,
- pgoff_t index, int size)
+ pgoff_t index, int size, int sizebits)
{
struct inode *inode = bdev->bd_inode;
struct page *page;
struct buffer_head *bh;
+ sector_t end_block;
+ int ret = 0; /* Will call free_more_memory() */
page = find_or_create_page(inode->i_mapping, index,
(mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS)|__GFP_MOVABLE);
if (!page)
- return NULL;
+ return ret;
BUG_ON(!PageLocked(page));
if (page_has_buffers(page)) {
bh = page_buffers(page);
if (bh->b_size == size) {
- init_page_buffers(page, bdev, block, size);
- return page;
+ end_block = init_page_buffers(page, bdev,
+ index << sizebits, size);
+ goto done;
}
if (!try_to_free_buffers(page))
goto failed;
*/
spin_lock(&inode->i_mapping->private_lock);
link_dev_buffers(page, bh);
- init_page_buffers(page, bdev, block, size);
+ end_block = init_page_buffers(page, bdev, index << sizebits, size);
spin_unlock(&inode->i_mapping->private_lock);
- return page;
-
+done:
+ ret = (block < end_block) ? 1 : -ENXIO;
failed:
unlock_page(page);
page_cache_release(page);
- return NULL;
+ return ret;
}
/*
static int
grow_buffers(struct block_device *bdev, sector_t block, int size)
{
- struct page *page;
pgoff_t index;
int sizebits;
bdevname(bdev, b));
return -EIO;
}
- block = index << sizebits;
+
/* Create a page with the proper size buffers.. */
- page = grow_dev_page(bdev, block, index, size);
- if (!page)
- return 0;
- unlock_page(page);
- page_cache_release(page);
- return 1;
+ return grow_dev_page(bdev, block, index, size, sizebits);
}
static struct buffer_head *
__getblk_slow(struct block_device *bdev, sector_t block, int size)
{
- int ret;
- struct buffer_head *bh;
-
/* Size must be multiple of hard sectorsize */
if (unlikely(size & (bdev_logical_block_size(bdev)-1) ||
(size < 512 || size > PAGE_SIZE))) {
return NULL;
}
-retry:
- bh = __find_get_block(bdev, block, size);
- if (bh)
- return bh;
+ for (;;) {
+ struct buffer_head *bh;
+ int ret;
- ret = grow_buffers(bdev, block, size);
- if (ret == 0) {
- free_more_memory();
- goto retry;
- } else if (ret > 0) {
bh = __find_get_block(bdev, block, size);
if (bh)
return bh;
+
+ ret = grow_buffers(bdev, block, size);
+ if (ret < 0)
+ return NULL;
+ if (ret == 0)
+ free_more_memory();
}
- return NULL;
}
/*
* which corresponds to the passed block_device, block and size. The
* returned buffer has its reference count incremented.
*
- * __getblk() cannot fail - it just keeps trying. If you pass it an
- * illegal block number, __getblk() will happily return a buffer_head
- * which represents the non-existent block. Very weird.
- *
* __getblk() will lock up the machine if grow_dev_page's try_to_free_buffers()
* attempt is failing. FIXME, perhaps?
*/
loff_t size;
int ret;
- /*
- * Update file times before taking page lock. We may end up failing the
- * fault so this update may be superfluous but who really cares...
- */
- file_update_time(vma->vm_file);
-
lock_page(page);
size = i_size_read(inode);
if ((page->mapping != inode->i_mapping) ||
struct super_block *sb = vma->vm_file->f_path.dentry->d_inode->i_sb;
sb_start_pagefault(sb);
+
+ /*
+ * Update file times before taking page lock. We may end up failing the
+ * fault so this update may be superfluous but who really cares...
+ */
+ file_update_time(vma->vm_file);
+
ret = __block_page_mkwrite(vma, vmf, get_block);
sb_end_pagefault(sb);
return block_page_mkwrite_return(ret);
err = ext4_map_blocks(handle, inode, &map,
create ? EXT4_GET_BLOCKS_CREATE : 0);
+ /* ensure we send some value back into *errp */
+ *errp = 0;
+
if (err < 0)
*errp = err;
if (err <= 0)
return NULL;
- *errp = 0;
bh = sb_getblk(inode->i_sb, map.m_pblk);
if (!bh) {
return ret;
}
- static int ext4_set_bh_endio(struct buffer_head *bh, struct inode *inode);
- static void ext4_end_io_buffer_write(struct buffer_head *bh, int uptodate);
-
/*
* 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
* This function can get called via...
* - ext4_da_writepages after taking page lock (have journal handle)
* - journal_submit_inode_data_buffers (no journal handle)
- * - shrink_page_list via pdflush (no journal handle)
+ * - shrink_page_list via the kswapd/direct reclaim (no journal handle)
* - grab_page_cache when doing write_begin (have journal handle)
*
* We don't do any block allocation in this function. If we have page with
free_blocks = EXT4_C2B(sbi,
percpu_counter_read_positive(&sbi->s_freeclusters_counter));
dirty_blocks = 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) &&
+ !writeback_in_progress(sb->s_bdi) &&
+ down_read_trylock(&sb->s_umount)) {
+ writeback_inodes_sb(sb, WB_REASON_FS_FREE_SPACE);
+ up_read(&sb->s_umount);
+ }
+
if (2 * free_blocks < 3 * dirty_blocks ||
free_blocks < (dirty_blocks + EXT4_FREECLUSTERS_WATERMARK)) {
/*
*/
return 1;
}
- /*
- * Even if we don't switch but are nearing capacity,
- * start pushing delalloc when 1/2 of free blocks are dirty.
- */
- if (free_blocks < 2 * dirty_blocks)
- writeback_inodes_sb_if_idle(sb, WB_REASON_FS_FREE_SPACE);
-
return 0;
}
{
struct inode *inode = iocb->ki_filp->f_path.dentry->d_inode;
ext4_io_end_t *io_end = iocb->private;
- struct workqueue_struct *wq;
- unsigned long flags;
- struct ext4_inode_info *ei;
/* if not async direct IO or dio with 0 bytes write, just return */
if (!io_end || !size)
io_end->iocb = iocb;
io_end->result = ret;
}
- wq = EXT4_SB(io_end->inode->i_sb)->dio_unwritten_wq;
- /* Add the io_end to per-inode completed aio dio list*/
- ei = EXT4_I(io_end->inode);
- spin_lock_irqsave(&ei->i_completed_io_lock, flags);
- list_add_tail(&io_end->list, &ei->i_completed_io_list);
- spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
-
- /* queue the work to convert unwritten extents to written */
- queue_work(wq, &io_end->work);
+ ext4_add_complete_io(io_end);
}
static void ext4_end_io_buffer_write(struct buffer_head *bh, int uptodate)
{
ext4_io_end_t *io_end = bh->b_private;
- struct workqueue_struct *wq;
struct inode *inode;
- unsigned long flags;
if (!test_clear_buffer_uninit(bh) || !io_end)
goto out;
*/
inode = io_end->inode;
ext4_set_io_unwritten_flag(inode, io_end);
-
- /* Add the io_end to per-inode completed io list*/
- spin_lock_irqsave(&EXT4_I(inode)->i_completed_io_lock, flags);
- list_add_tail(&io_end->list, &EXT4_I(inode)->i_completed_io_list);
- spin_unlock_irqrestore(&EXT4_I(inode)->i_completed_io_lock, flags);
-
- wq = EXT4_SB(inode->i_sb)->dio_unwritten_wq;
- /* queue the work to convert unwritten extents to written */
- queue_work(wq, &io_end->work);
+ ext4_add_complete_io(io_end);
out:
bh->b_private = NULL;
bh->b_end_io = NULL;
overwrite = *((int *)iocb->private);
if (overwrite) {
+ atomic_inc(&inode->i_dio_count);
down_read(&EXT4_I(inode)->i_data_sem);
mutex_unlock(&inode->i_mutex);
}
* hook to the iocb.
*/
iocb->private = NULL;
- EXT4_I(inode)->cur_aio_dio = 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);
* is a unwritten extents needs to be converted
* when IO is completed.
*/
- EXT4_I(inode)->cur_aio_dio = iocb->private;
+ ext4_inode_aio_set(inode, io_end);
}
if (overwrite)
NULL,
DIO_LOCKING);
if (iocb->private)
- EXT4_I(inode)->cur_aio_dio = NULL;
+ ext4_inode_aio_set(inode, NULL);
/*
* The io_end structure takes a reference to the inode,
* that structure needs to be destroyed and the
retake_lock:
/* take i_mutex locking again if we do a ovewrite dio */
if (overwrite) {
+ inode_dio_done(inode);
up_read(&EXT4_I(inode)->i_data_sem);
mutex_lock(&inode->i_mutex);
}
* handle: The journal handle
* inode: The files inode
* page: A locked page that contains the offset "from"
- * from: The starting byte offset (from the begining of the file)
+ * from: The starting byte offset (from the beginning of the file)
* to begin discarding
* len: The length of bytes to discard
* flags: Optional flags that may be used:
* EXT4_DISCARD_PARTIAL_PG_ZERO_UNMAPPED
* Only zero the regions of the page whose buffer heads
* have already been unmapped. This flag is appropriate
- * for updateing the contents of a page whose blocks may
+ * for updating the contents of a page whose blocks may
* have already been released, and we only want to zero
* out the regions that correspond to those released blocks.
*
- * Returns zero on sucess or negative on failure.
+ * Returns zero on success or negative on failure.
*/
static int ext4_discard_partial_page_buffers_no_lock(handle_t *handle,
struct inode *inode, struct page *page, loff_t from,
* @offset: The offset where the hole will begin
* @len: The length of the hole
*
- * Returns: 0 on sucess or negative on failure
+ * Returns: 0 on success or negative on failure
*/
int ext4_punch_hole(struct file *file, loff_t offset, loff_t length)
if (i_blocks <= ~0U) {
/*
- * i_blocks can be represnted in a 32 bit variable
+ * i_blocks can be represented in a 32 bit variable
* as multiple of 512 bytes
*/
raw_inode->i_blocks_lo = cpu_to_le32(i_blocks);
struct ext4_inode_info *ei = EXT4_I(inode);
struct buffer_head *bh = iloc->bh;
int err = 0, rc, block;
+ int need_datasync = 0;
uid_t i_uid;
gid_t i_gid;
raw_inode->i_file_acl_high =
cpu_to_le16(ei->i_file_acl >> 32);
raw_inode->i_file_acl_lo = cpu_to_le32(ei->i_file_acl);
- ext4_isize_set(raw_inode, ei->i_disksize);
+ if (ei->i_disksize != ext4_isize(raw_inode)) {
+ ext4_isize_set(raw_inode, ei->i_disksize);
+ need_datasync = 1;
+ }
if (ei->i_disksize > 0x7fffffffULL) {
struct super_block *sb = inode->i_sb;
if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
err = rc;
ext4_clear_inode_state(inode, EXT4_STATE_NEW);
- ext4_update_inode_fsync_trans(handle, inode, 0);
+ ext4_update_inode_fsync_trans(handle, inode, need_datasync);
out_brelse:
brelse(bh);
ext4_std_error(inode->i_sb, err);
*
* - Within generic_file_write() for O_SYNC files.
* Here, there will be no transaction running. We wait for any running
- * trasnaction to commit.
+ * transaction to commit.
*
* - Within sys_sync(), kupdate and such.
* We wait on commit, if tol to.
}
if (attr->ia_valid & ATTR_SIZE) {
- inode_dio_wait(inode);
if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) {
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
}
if (attr->ia_valid & ATTR_SIZE) {
- if (attr->ia_size != i_size_read(inode))
+ if (attr->ia_size != i_size_read(inode)) {
truncate_setsize(inode, attr->ia_size);
+ /* Inode size will be reduced, wait for dio in flight.
+ * Temporarily disable dioread_nolock to prevent
+ * livelock. */
+ if (orphan) {
+ ext4_inode_block_unlocked_dio(inode);
+ inode_dio_wait(inode);
+ ext4_inode_resume_unlocked_dio(inode);
+ }
+ }
ext4_truncate(inode);
}
* worse case, the indexs blocks spread over different block groups
*
* If datablocks are discontiguous, they are possible to spread over
- * different block groups too. If they are contiuguous, with flexbg,
+ * different block groups too. If they are contiguous, with flexbg,
* they could still across block group boundary.
*
* Also account for superblock, inode, quota and xattr blocks
* inode out, but prune_icache isn't a user-visible syncing function.
* Whenever the user wants stuff synced (sys_sync, sys_msync, sys_fsync)
* we start and wait on commits.
- *
- * Is this efficient/effective? Well, we're being nice to the system
- * by cleaning up our inodes proactively so they can be reaped
- * without I/O. But we are potentially leaving up to five seconds'
- * worth of inodes floating about which prune_icache wants us to
- * write out. One way to fix that would be to get prune_icache()
- * to do a write_super() to free up some memory. It has the desired
- * effect.
*/
int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode)
{
return err;
}
+ /* Wait for all existing dio workers */
+ ext4_inode_block_unlocked_dio(inode);
+ inode_dio_wait(inode);
+
jbd2_journal_lock_updates(journal);
/*
ext4_set_aops(inode);
jbd2_journal_unlock_updates(journal);
+ ext4_inode_resume_unlocked_dio(inode);
/* Finally we can mark the inode as dirty. */
int retries = 0;
sb_start_pagefault(inode->i_sb);
+ file_update_time(vma->vm_file);
/* Delalloc case is easy... */
if (test_opt(inode->i_sb, DELALLOC) &&
!ext4_should_journal_data(inode) &&
case EXT4_IOC_MOVE_EXT: {
struct move_extent me;
- struct file *donor_filp;
+ struct fd donor;
int err;
if (!(filp->f_mode & FMODE_READ) ||
return -EFAULT;
me.moved_len = 0;
- donor_filp = fget(me.donor_fd);
- if (!donor_filp)
+ donor = fdget(me.donor_fd);
+ if (!donor.file)
return -EBADF;
- if (!(donor_filp->f_mode & FMODE_WRITE)) {
+ if (!(donor.file->f_mode & FMODE_WRITE)) {
err = -EBADF;
goto mext_out;
}
if (err)
goto mext_out;
- err = ext4_move_extents(filp, donor_filp, me.orig_start,
+ err = ext4_move_extents(filp, donor.file, me.orig_start,
me.donor_start, me.len, &me.moved_len);
mnt_drop_write_file(filp);
&me, sizeof(me)))
err = -EFAULT;
mext_out:
- fput(donor_filp);
+ fdput(donor);
return err;
}
return -EOPNOTSUPP;
}
- if (EXT4_HAS_INCOMPAT_FEATURE(sb,
- EXT4_FEATURE_INCOMPAT_META_BG)) {
- ext4_msg(sb, KERN_ERR,
- "Online resizing not (yet) supported with meta_bg");
- return -EOPNOTSUPP;
- }
-
if (copy_from_user(&n_blocks_count, (__u64 __user *)arg,
sizeof(__u64))) {
return -EFAULT;
}
- if (n_blocks_count > MAX_32_NUM &&
- !EXT4_HAS_INCOMPAT_FEATURE(sb,
- EXT4_FEATURE_INCOMPAT_64BIT)) {
- ext4_msg(sb, KERN_ERR,
- "File system only supports 32-bit block numbers");
- return -EOPNOTSUPP;
- }
-
err = ext4_resize_begin(sb);
if (err)
return err;
if (!blk_queue_discard(q))
return -EOPNOTSUPP;
- if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
- EXT4_FEATURE_RO_COMPAT_BIGALLOC)) {
- ext4_msg(sb, KERN_ERR,
- "FITRIM not supported with bigalloc");
- return -EOPNOTSUPP;
- }
-
if (copy_from_user(&range, (struct fstrim_range __user *)arg,
sizeof(range)))
return -EFAULT;
#include "ext4_jbd2.h"
#include "mballoc.h"
#include <linux/debugfs.h>
+ #include <linux/log2.h>
#include <linux/slab.h>
#include <trace/events/ext4.h>
mb_check_buddy(e4b);
}
- static int mb_find_extent(struct ext4_buddy *e4b, int order, int block,
+ static int mb_find_extent(struct ext4_buddy *e4b, int block,
int needed, struct ext4_free_extent *ex)
{
int next = block;
- int max;
+ int max, order;
void *buddy;
assert_spin_locked(ext4_group_lock_ptr(e4b->bd_sb, e4b->bd_group));
BUG_ON(ex == NULL);
- buddy = mb_find_buddy(e4b, order, &max);
+ buddy = mb_find_buddy(e4b, 0, &max);
BUG_ON(buddy == NULL);
BUG_ON(block >= max);
if (mb_test_bit(block, buddy)) {
return 0;
}
- /* FIXME dorp order completely ? */
- if (likely(order == 0)) {
- /* find actual order */
- order = mb_find_order_for_block(e4b, block);
- block = block >> order;
- }
+ /* find actual order */
+ order = mb_find_order_for_block(e4b, block);
+ block = block >> order;
ex->fe_len = 1 << order;
ex->fe_start = block << order;
/* recheck chunk's availability - we don't know
* when it was found (within this lock-unlock
* period or not) */
- max = mb_find_extent(e4b, 0, bex->fe_start, gex->fe_len, &ex);
+ max = mb_find_extent(e4b, bex->fe_start, gex->fe_len, &ex);
if (max >= gex->fe_len) {
ext4_mb_use_best_found(ac, e4b);
return;
return err;
ext4_lock_group(ac->ac_sb, group);
- max = mb_find_extent(e4b, 0, ex.fe_start, ex.fe_len, &ex);
+ max = mb_find_extent(e4b, ex.fe_start, ex.fe_len, &ex);
if (max > 0) {
ac->ac_b_ex = ex;
int max;
int err;
struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb);
+ struct ext4_group_info *grp = ext4_get_group_info(ac->ac_sb, group);
struct ext4_free_extent ex;
if (!(ac->ac_flags & EXT4_MB_HINT_TRY_GOAL))
return 0;
+ if (grp->bb_free == 0)
+ return 0;
err = ext4_mb_load_buddy(ac->ac_sb, group, e4b);
if (err)
return err;
ext4_lock_group(ac->ac_sb, group);
- max = mb_find_extent(e4b, 0, ac->ac_g_ex.fe_start,
+ max = mb_find_extent(e4b, ac->ac_g_ex.fe_start,
ac->ac_g_ex.fe_len, &ex);
if (max >= ac->ac_g_ex.fe_len && ac->ac_g_ex.fe_len == sbi->s_stripe) {
break;
}
- mb_find_extent(e4b, 0, i, ac->ac_g_ex.fe_len, &ex);
+ mb_find_extent(e4b, i, ac->ac_g_ex.fe_len, &ex);
BUG_ON(ex.fe_len <= 0);
if (free < ex.fe_len) {
ext4_grp_locked_error(sb, e4b->bd_group, 0, 0,
while (i < EXT4_CLUSTERS_PER_GROUP(sb)) {
if (!mb_test_bit(i, bitmap)) {
- max = mb_find_extent(e4b, 0, i, sbi->s_stripe, &ex);
+ max = mb_find_extent(e4b, i, sbi->s_stripe, &ex);
if (max >= sbi->s_stripe) {
ac->ac_found++;
ac->ac_b_ex = ex;
BUG_ON(cr < 0 || cr >= 4);
+ free = grp->bb_free;
+ if (free == 0)
+ return 0;
+ if (cr <= 2 && free < ac->ac_g_ex.fe_len)
+ return 0;
+
/* We only do this if the grp has never been initialized */
if (unlikely(EXT4_MB_GRP_NEED_INIT(grp))) {
int ret = ext4_mb_init_group(ac->ac_sb, group);
return 0;
}
- free = grp->bb_free;
fragments = grp->bb_fragments;
- if (free == 0)
- return 0;
if (fragments == 0)
return 0;
return cachep;
}
+ /*
+ * Allocate the top-level s_group_info array for the specified number
+ * of groups
+ */
+ int ext4_mb_alloc_groupinfo(struct super_block *sb, ext4_group_t ngroups)
+ {
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+ unsigned size;
+ struct ext4_group_info ***new_groupinfo;
+
+ size = (ngroups + EXT4_DESC_PER_BLOCK(sb) - 1) >>
+ EXT4_DESC_PER_BLOCK_BITS(sb);
+ if (size <= sbi->s_group_info_size)
+ return 0;
+
+ size = roundup_pow_of_two(sizeof(*sbi->s_group_info) * size);
+ new_groupinfo = ext4_kvzalloc(size, GFP_KERNEL);
+ if (!new_groupinfo) {
+ ext4_msg(sb, KERN_ERR, "can't allocate buddy meta group");
+ return -ENOMEM;
+ }
+ if (sbi->s_group_info) {
+ memcpy(new_groupinfo, sbi->s_group_info,
+ sbi->s_group_info_size * sizeof(*sbi->s_group_info));
+ ext4_kvfree(sbi->s_group_info);
+ }
+ sbi->s_group_info = new_groupinfo;
+ sbi->s_group_info_size = size / sizeof(*sbi->s_group_info);
+ ext4_debug("allocated s_groupinfo array for %d meta_bg's\n",
+ sbi->s_group_info_size);
+ return 0;
+ }
+
/* Create and initialize ext4_group_info data for the given group. */
int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group,
struct ext4_group_desc *desc)
sbi->s_group_info[group >> EXT4_DESC_PER_BLOCK_BITS(sb)];
i = group & (EXT4_DESC_PER_BLOCK(sb) - 1);
- meta_group_info[i] = kmem_cache_alloc(cachep, GFP_KERNEL);
+ meta_group_info[i] = kmem_cache_zalloc(cachep, GFP_KERNEL);
if (meta_group_info[i] == NULL) {
ext4_msg(sb, KERN_ERR, "can't allocate buddy mem");
goto exit_group_info;
}
- memset(meta_group_info[i], 0, kmem_cache_size(cachep));
set_bit(EXT4_GROUP_INFO_NEED_INIT_BIT,
&(meta_group_info[i]->bb_state));
ext4_group_t ngroups = ext4_get_groups_count(sb);
ext4_group_t i;
struct ext4_sb_info *sbi = EXT4_SB(sb);
- struct ext4_super_block *es = sbi->s_es;
- int num_meta_group_infos;
- int num_meta_group_infos_max;
- int array_size;
+ int err;
struct ext4_group_desc *desc;
struct kmem_cache *cachep;
- /* This is the number of blocks used by GDT */
- num_meta_group_infos = (ngroups + EXT4_DESC_PER_BLOCK(sb) -
- 1) >> EXT4_DESC_PER_BLOCK_BITS(sb);
-
- /*
- * This is the total number of blocks used by GDT including
- * the number of reserved blocks for GDT.
- * The s_group_info array is allocated with this value
- * to allow a clean online resize without a complex
- * manipulation of pointer.
- * The drawback is the unused memory when no resize
- * occurs but it's very low in terms of pages
- * (see comments below)
- * Need to handle this properly when META_BG resizing is allowed
- */
- num_meta_group_infos_max = num_meta_group_infos +
- le16_to_cpu(es->s_reserved_gdt_blocks);
+ err = ext4_mb_alloc_groupinfo(sb, ngroups);
+ if (err)
+ return err;
- /*
- * array_size is the size of s_group_info array. We round it
- * to the next power of two because this approximation is done
- * internally by kmalloc so we can have some more memory
- * for free here (e.g. may be used for META_BG resize).
- */
- array_size = 1;
- while (array_size < sizeof(*sbi->s_group_info) *
- num_meta_group_infos_max)
- array_size = array_size << 1;
- /* An 8TB filesystem with 64-bit pointers requires a 4096 byte
- * kmalloc. A 128kb malloc should suffice for a 256TB filesystem.
- * So a two level scheme suffices for now. */
- sbi->s_group_info = ext4_kvzalloc(array_size, GFP_KERNEL);
- if (sbi->s_group_info == NULL) {
- ext4_msg(sb, KERN_ERR, "can't allocate buddy meta group");
- return -ENOMEM;
- }
sbi->s_buddy_cache = new_inode(sb);
if (sbi->s_buddy_cache == NULL) {
ext4_msg(sb, KERN_ERR, "can't get new inode");
cachep = get_groupinfo_cache(sb->s_blocksize_bits);
while (i-- > 0)
kmem_cache_free(cachep, ext4_get_group_info(sb, i));
- i = num_meta_group_infos;
+ i = sbi->s_group_info_size;
while (i-- > 0)
kfree(sbi->s_group_info[i]);
iput(sbi->s_buddy_cache);
ext4_get_group_no_and_offset(sb, goal, &group, &block);
/* set up allocation goals */
- memset(ac, 0, sizeof(struct ext4_allocation_context));
ac->ac_b_ex.fe_logical = ar->logical & ~(sbi->s_cluster_ratio - 1);
ac->ac_status = AC_STATUS_CONTINUE;
ac->ac_sb = sb;
}
}
- ac = kmem_cache_alloc(ext4_ac_cachep, GFP_NOFS);
+ ac = kmem_cache_zalloc(ext4_ac_cachep, GFP_NOFS);
if (!ac) {
ar->len = 0;
*errp = -ENOMEM;
* with group lock held. generate_buddy look at
* them with group lock_held
*/
+ if (test_opt(sb, DISCARD))
+ ext4_issue_discard(sb, block_group, bit, count);
ext4_lock_group(sb, block_group);
mb_clear_bits(bitmap_bh->b_data, bit, count_clusters);
mb_free_blocks(inode, &e4b, bit, count_clusters);
* ext4_group_add_blocks() -- Add given blocks to an existing group
* @handle: handle to this transaction
* @sb: super block
- * @block: start physcial block to add to the block group
+ * @block: start physical block to add to the block group
* @count: number of blocks to free
*
* This marks the blocks as free in the bitmap and buddy.
start = range->start >> sb->s_blocksize_bits;
end = start + (range->len >> sb->s_blocksize_bits) - 1;
- minlen = range->minlen >> sb->s_blocksize_bits;
+ minlen = EXT4_NUM_B2C(EXT4_SB(sb),
+ range->minlen >> sb->s_blocksize_bits);
if (unlikely(minlen > EXT4_CLUSTERS_PER_GROUP(sb)) ||
unlikely(start >= max_blks))
atomic_set(&EXT4_SB(sb)->s_last_trim_minblks, minlen);
out:
- range->len = trimmed * sb->s_blocksize;
+ range->len = EXT4_C2B(EXT4_SB(sb), trimmed) << sb->s_blocksize_bits;
return ret;
}
/*
* Wrappers for jbd2_journal_start/end.
- *
- * The only special thing we need to do here is to make sure that all
- * journal_end calls result in the superblock being marked dirty, so
- * that sync() will call the filesystem's write_super callback if
- * appropriate.
*/
handle_t *ext4_journal_start_sb(struct super_block *sb, int nblocks)
{
return jbd2_journal_start(journal, nblocks);
}
-/*
- * The only special thing we need to do here is to make sure that all
- * jbd2_journal_stop calls result in the superblock being marked dirty, so
- * that sync() will call the filesystem's write_super callback if
- * appropriate.
- */
int __ext4_journal_stop(const char *where, unsigned int line, handle_t *handle)
{
struct super_block *sb;
*/
if (!es->s_error_count)
mod_timer(&EXT4_SB(sb)->s_err_report, jiffies + 24*60*60*HZ);
- es->s_error_count = cpu_to_le32(le32_to_cpu(es->s_error_count) + 1);
+ le32_add_cpu(&es->s_error_count, 1);
}
static void save_error_info(struct super_block *sb, const char *func,
flush_workqueue(sbi->dio_unwritten_wq);
destroy_workqueue(sbi->dio_unwritten_wq);
- lock_super(sb);
if (sbi->s_journal) {
err = jbd2_journal_destroy(sbi->s_journal);
sbi->s_journal = NULL;
* Now that we are completely done shutting down the
* superblock, we need to actually destroy the kobject.
*/
- unlock_super(sb);
kobject_put(&sbi->s_kobj);
wait_for_completion(&sbi->s_kobj_unregister);
if (sbi->s_chksum_driver)
ei->jinode = NULL;
INIT_LIST_HEAD(&ei->i_completed_io_list);
spin_lock_init(&ei->i_completed_io_lock);
- ei->cur_aio_dio = NULL;
ei->i_sync_tid = 0;
ei->i_datasync_tid = 0;
atomic_set(&ei->i_ioend_count, 0);
- atomic_set(&ei->i_aiodio_unwritten, 0);
+ atomic_set(&ei->i_unwritten, 0);
return &ei->vfs_inode;
}
static void destroy_inodecache(void)
{
+ /*
+ * Make sure all delayed rcu free inodes are flushed before we
+ * destroy cache.
+ */
+ rcu_barrier();
kmem_cache_destroy(ext4_inode_cachep);
}
Opt_inode_readahead_blks, Opt_journal_ioprio,
Opt_dioread_nolock, Opt_dioread_lock,
Opt_discard, Opt_nodiscard, Opt_init_itable, Opt_noinit_itable,
+ Opt_max_dir_size_kb,
};
static const match_table_t tokens = {
{Opt_init_itable, "init_itable=%u"},
{Opt_init_itable, "init_itable"},
{Opt_noinit_itable, "noinit_itable"},
+ {Opt_max_dir_size_kb, "max_dir_size_kb=%u"},
{Opt_removed, "check=none"}, /* mount option from ext2/3 */
{Opt_removed, "nocheck"}, /* mount option from ext2/3 */
{Opt_removed, "reservation"}, /* mount option from ext2/3 */
{Opt_jqfmt_vfsold, QFMT_VFS_OLD, MOPT_QFMT},
{Opt_jqfmt_vfsv0, QFMT_VFS_V0, MOPT_QFMT},
{Opt_jqfmt_vfsv1, QFMT_VFS_V1, MOPT_QFMT},
+ {Opt_max_dir_size_kb, 0, MOPT_GTE0},
{Opt_err, 0, 0}
};
if (!args->from)
arg = EXT4_DEF_LI_WAIT_MULT;
sbi->s_li_wait_mult = arg;
+ } else if (token == Opt_max_dir_size_kb) {
+ sbi->s_max_dir_size_kb = arg;
} else if (token == Opt_stripe) {
sbi->s_stripe = arg;
} else if (m->flags & MOPT_DATAJ) {
* Initialize args struct so we know whether arg was
* found; some options take optional arguments.
*/
- args[0].to = args[0].from = 0;
+ args[0].to = args[0].from = NULL;
token = match_token(p, tokens, args);
if (handle_mount_opt(sb, p, token, args, journal_devnum,
journal_ioprio, is_remount) < 0)
static const char *token2str(int token)
{
- static const struct match_token *t;
+ const struct match_token *t;
for (t = tokens; t->token != Opt_err; t++)
if (t->token == token && !strchr(t->pattern, '='))
if (nodefs || (test_opt(sb, INIT_INODE_TABLE) &&
(sbi->s_li_wait_mult != EXT4_DEF_LI_WAIT_MULT)))
SEQ_OPTS_PRINT("init_itable=%u", sbi->s_li_wait_mult);
+ if (nodefs || sbi->s_max_dir_size_kb)
+ SEQ_OPTS_PRINT("max_dir_size_kb=%u", sbi->s_max_dir_size_kb);
ext4_show_quota_options(seq, sb);
return 0;
return res;
}
+ int ext4_alloc_flex_bg_array(struct super_block *sb, ext4_group_t ngroup)
+ {
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+ struct flex_groups *new_groups;
+ int size;
+
+ if (!sbi->s_log_groups_per_flex)
+ return 0;
+
+ size = ext4_flex_group(sbi, ngroup - 1) + 1;
+ if (size <= sbi->s_flex_groups_allocated)
+ return 0;
+
+ size = roundup_pow_of_two(size * sizeof(struct flex_groups));
+ new_groups = ext4_kvzalloc(size, GFP_KERNEL);
+ if (!new_groups) {
+ ext4_msg(sb, KERN_ERR, "not enough memory for %d flex groups",
+ size / (int) sizeof(struct flex_groups));
+ return -ENOMEM;
+ }
+
+ if (sbi->s_flex_groups) {
+ memcpy(new_groups, sbi->s_flex_groups,
+ (sbi->s_flex_groups_allocated *
+ sizeof(struct flex_groups)));
+ ext4_kvfree(sbi->s_flex_groups);
+ }
+ sbi->s_flex_groups = new_groups;
+ sbi->s_flex_groups_allocated = size / sizeof(struct flex_groups);
+ return 0;
+ }
+
static int ext4_fill_flex_info(struct super_block *sb)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_group_desc *gdp = NULL;
- ext4_group_t flex_group_count;
ext4_group_t flex_group;
unsigned int groups_per_flex = 0;
- size_t size;
- int i;
+ int i, err;
sbi->s_log_groups_per_flex = sbi->s_es->s_log_groups_per_flex;
if (sbi->s_log_groups_per_flex < 1 || sbi->s_log_groups_per_flex > 31) {
}
groups_per_flex = 1 << sbi->s_log_groups_per_flex;
- /* We allocate both existing and potentially added groups */
- flex_group_count = ((sbi->s_groups_count + groups_per_flex - 1) +
- ((le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks) + 1) <<
- EXT4_DESC_PER_BLOCK_BITS(sb))) / groups_per_flex;
- size = flex_group_count * sizeof(struct flex_groups);
- sbi->s_flex_groups = ext4_kvzalloc(size, GFP_KERNEL);
- if (sbi->s_flex_groups == NULL) {
- ext4_msg(sb, KERN_ERR, "not enough memory for %u flex groups",
- flex_group_count);
+ err = ext4_alloc_flex_bg_array(sb, sbi->s_groups_count);
+ if (err)
goto failed;
- }
for (i = 0; i < sbi->s_groups_count; i++) {
gdp = ext4_get_group_desc(sb, i, NULL);
}
if (EXT4_SB(sb)->s_mount_state & EXT4_ERROR_FS) {
- if (es->s_last_orphan)
+ /* don't clear list on RO mount w/ errors */
+ if (es->s_last_orphan && !(s_flags & MS_RDONLY)) {
jbd_debug(1, "Errors on filesystem, "
"clearing orphan list.\n");
- es->s_last_orphan = 0;
+ es->s_last_orphan = 0;
+ }
jbd_debug(1, "Skipping orphan recovery on fs with errors.\n");
return;
}
EXT4_RW_ATTR_SBI_UI(mb_stream_req, s_mb_stream_request);
EXT4_RW_ATTR_SBI_UI(mb_group_prealloc, s_mb_group_prealloc);
EXT4_RW_ATTR_SBI_UI(max_writeback_mb_bump, s_max_writeback_mb_bump);
+ EXT4_RW_ATTR_SBI_UI(extent_max_zeroout_kb, s_extent_max_zeroout_kb);
EXT4_ATTR(trigger_fs_error, 0200, NULL, trigger_test_error);
static struct attribute *ext4_attrs[] = {
ATTR_LIST(mb_stream_req),
ATTR_LIST(mb_group_prealloc),
ATTR_LIST(max_writeback_mb_bump),
+ ATTR_LIST(extent_max_zeroout_kb),
ATTR_LIST(trigger_fs_error),
NULL,
};
/* Features this copy of ext4 supports */
EXT4_INFO_ATTR(lazy_itable_init);
EXT4_INFO_ATTR(batched_discard);
+ EXT4_INFO_ATTR(meta_bg_resize);
static struct attribute *ext4_feat_attrs[] = {
ATTR_LIST(lazy_itable_init),
ATTR_LIST(batched_discard),
+ ATTR_LIST(meta_bg_resize),
NULL,
};
* enable delayed allocation by default
* Use -o nodelalloc to turn it off
*/
- if (!IS_EXT3_SB(sb) &&
+ if (!IS_EXT3_SB(sb) && !IS_EXT2_SB(sb) &&
((def_mount_opts & EXT4_DEFM_NODELALLOC) == 0))
set_opt(sb, DELALLOC);
sbi->s_stripe = ext4_get_stripe_size(sbi);
sbi->s_max_writeback_mb_bump = 128;
+ sbi->s_extent_max_zeroout_kb = 32;
/*
* set up enough so that it can read an inode
if (sb->s_flags & MS_RDONLY)
return 0;
- lock_super(sb);
/* Reset the needs_recovery flag before the fs is unlocked. */
EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
ext4_commit_super(sb, 1);
- unlock_super(sb);
return 0;
}
char *orig_data = kstrdup(data, GFP_KERNEL);
/* Store the original options */
- lock_super(sb);
old_sb_flags = sb->s_flags;
old_opts.s_mount_opt = sbi->s_mount_opt;
old_opts.s_mount_opt2 = sbi->s_mount_opt2;
if (sbi->s_journal == NULL)
ext4_commit_super(sb, 1);
- unlock_super(sb);
#ifdef CONFIG_QUOTA
/* Release old quota file names */
for (i = 0; i < MAXQUOTAS; i++)
else if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
EXT4_FEATURE_RO_COMPAT_QUOTA)) {
err = ext4_enable_quotas(sb);
- if (err) {
- lock_super(sb);
+ if (err)
goto restore_opts;
- }
}
}
#endif
sbi->s_qf_names[i] = old_opts.s_qf_names[i];
}
#endif
- unlock_super(sb);
kfree(orig_data);
return err;
}
static inline struct inode *dquot_to_inode(struct dquot *dquot)
{
- return sb_dqopt(dquot->dq_sb)->files[dquot->dq_type];
+ return sb_dqopt(dquot->dq_sb)->files[dquot->dq_id.type];
}
static int ext4_write_dquot(struct dquot *dquot)
if (err)
goto out6;
ext4_kset = kset_create_and_add("ext4", NULL, fs_kobj);
- if (!ext4_kset)
+ if (!ext4_kset) {
+ err = -ENOMEM;
goto out5;
+ }
ext4_proc_root = proc_mkdir("fs/ext4", NULL);
err = ext4_init_feat_adverts();
{
return test_bit(BDI_writeback_running, &bdi->state);
}
+ EXPORT_SYMBOL(writeback_in_progress);
static inline struct backing_dev_info *inode_to_bdi(struct inode *inode)
{
/*
* Write a portion of b_io inodes which belong to @sb.
*
- * If @only_this_sb is true, then find and write all such
- * inodes. Otherwise write only ones which go sequentially
- * in reverse order.
- *
* Return the number of pages and/or inodes written.
*/
static long writeback_sb_inodes(struct super_block *sb,
ret = 1;
} else if (journal->j_committing_transaction) {
/*
- * If ext3_write_super() recently started a commit, then we
- * have to wait for completion of that transaction
+ * If commit has been started, then we have to wait for
+ * completion of that transaction.
*/
if (ptid)
*ptid = journal->j_committing_transaction->t_tid;
BUG_ON(!mutex_is_locked(&journal->j_checkpoint_mutex));
read_lock(&journal->j_state_lock);
+ /* Is it already empty? */
+ if (sb->s_start == 0) {
+ read_unlock(&journal->j_state_lock);
+ return;
+ }
jbd_debug(1, "JBD2: Marking journal as empty (seq %d)\n",
journal->j_tail_sequence);