void throttle_vm_writeout(gfp_t gfp_mask)
{
unsigned long background_thresh;
unsigned long dirty_thresh;
for ( ; ; ) {
global_dirty_limits(&background_thresh, &dirty_thresh);
/*
* Boost the allowable dirty threshold a bit for page
* allocators so they don't get DoS'ed by heavy writers
*/
dirty_thresh += dirty_thresh / 10; /* wheeee... */
if (global_page_state(NR_UNSTABLE_NFS) +
global_page_state(NR_WRITEBACK) <= dirty_thresh)
break;
congestion_wait(BLK_RW_ASYNC, HZ/10);
/*
* The caller might hold locks which can prevent IO completion
* or progress in the filesystem. So we cannot just sit here
* waiting for IO to complete.
*/
if ((gfp_mask & (__GFP_FS|__GFP_IO)) != (__GFP_FS|__GFP_IO))
break;
}
}
unsigned long __copy_to_user_ll(void __user *to, const void *from,
unsigned long n)
{
#ifndef CONFIG_X86_WP_WORKS_OK
if (unlikely(boot_cpu_data.wp_works_ok == 0) &&
((unsigned long)to) < TASK_SIZE) {
if (in_atomic())
return n;
while (n) {
unsigned long offset = ((unsigned long)to)%PAGE_SIZE;
unsigned long len = PAGE_SIZE - offset;
int retval;
struct page *pg;
void *maddr;
if (len > n)
len = n;
survive:
down_read(¤t->mm->mmap_sem);
retval = get_user_pages(current, current->mm,
(unsigned long)to, 1, 1, 0, &pg, NULL);
if (retval == -ENOMEM && is_global_init(current)) {
up_read(¤t->mm->mmap_sem);
congestion_wait(BLK_RW_ASYNC, HZ/50);
goto survive;
}
if (retval != 1) {
up_read(¤t->mm->mmap_sem);
break;
}
maddr = kmap_atomic(pg, KM_USER0);
memcpy(maddr + offset, from, len);
kunmap_atomic(maddr, KM_USER0);
set_page_dirty_lock(pg);
put_page(pg);
up_read(¤t->mm->mmap_sem);
from += len;
to += len;
n -= len;
}
return n;
}
#endif
if (movsl_is_ok(to, from, n))
__copy_user(to, from, n);
else
n = __copy_user_intel(to, from, n);
return n;
}
static int fat_file_release(struct inode *inode, struct file *filp)
{
if ((filp->f_mode & FMODE_WRITE) &&
MSDOS_SB(inode->i_sb)->options.flush) {
fat_flush_inodes(inode->i_sb, inode, NULL);
congestion_wait(BLK_RW_ASYNC, HZ/10);
}
return 0;
}
unsigned long __copy_to_user_ll(void __user *to, const void *from,
unsigned long n)
{
#ifndef CONFIG_X86_WP_WORKS_OK
if (unlikely(boot_cpu_data.wp_works_ok == 0) &&
((unsigned long)to) < TASK_SIZE) {
/*
* When we are in an atomic section (see
* mm/filemap.c:file_read_actor), return the full
* length to take the slow path.
*/
if (in_atomic())
return n;
/*
* CPU does not honor the WP bit when writing
* from supervisory mode, and due to preemption or SMP,
* the page tables can change at any time.
* Do it manually. Manfred <*****@*****.**>
*/
while (n) {
unsigned long offset = ((unsigned long)to)%PAGE_SIZE;
unsigned long len = PAGE_SIZE - offset;
int retval;
struct page *pg;
void *maddr;
if (len > n)
len = n;
survive:
down_read(¤t->mm->mmap_sem);
retval = get_user_pages(current, current->mm,
(unsigned long)to, 1, 1, 0, &pg, NULL);
if (retval == -ENOMEM && is_global_init(current)) {
up_read(¤t->mm->mmap_sem);
congestion_wait(BLK_RW_ASYNC, HZ/50);
goto survive;
}
if (retval != 1) {
up_read(¤t->mm->mmap_sem);
break;
}
<<<<<<< HEAD
maddr = kmap_atomic(pg);
memcpy(maddr + offset, from, len);
kunmap_atomic(maddr);
=======
<<<<<<< HEAD
maddr = kmap_atomic(pg);
memcpy(maddr + offset, from, len);
kunmap_atomic(maddr);
=======
struct inode *f2fs_iget_retry(struct super_block *sb, unsigned long ino)
{
struct inode *inode;
retry:
inode = f2fs_iget(sb, ino);
if (IS_ERR(inode)) {
if (PTR_ERR(inode) == -ENOMEM) {
congestion_wait(BLK_RW_ASYNC, HZ/50);
goto retry;
}
}
return inode;
}
/*
* writeback at least _min_pages, and keep writing until the amount of dirty
* memory is less than the background threshold, or until we're all clean.
*/
static void background_writeout(unsigned long _min_pages)
{
long min_pages = _min_pages;
struct writeback_control wbc = {
.bdi = NULL,
.sync_mode = WB_SYNC_NONE,
.older_than_this = NULL,
.nr_to_write = 0,
.nonblocking = 1,
.range_cyclic = 1,
};
for ( ; ; ) {
long background_thresh;
long dirty_thresh;
get_dirty_limits(&background_thresh, &dirty_thresh, NULL, NULL);
if (global_page_state(NR_FILE_DIRTY) +
global_page_state(NR_UNSTABLE_NFS) < background_thresh
&& min_pages <= 0)
break;
wbc.more_io = 0;
wbc.encountered_congestion = 0;
wbc.nr_to_write = MAX_WRITEBACK_PAGES;
wbc.pages_skipped = 0;
writeback_inodes(&wbc);
min_pages -= MAX_WRITEBACK_PAGES - wbc.nr_to_write;
if (wbc.nr_to_write > 0 || wbc.pages_skipped > 0) {
/* Wrote less than expected */
if (wbc.encountered_congestion || wbc.more_io)
congestion_wait(WRITE, HZ/10);
else
break;
}
}
}
/*
* Start writeback of `nr_pages' pages. If `nr_pages' is zero, write back
* the whole world. Returns 0 if a pdflush thread was dispatched. Returns
* -1 if all pdflush threads were busy.
*/
int wakeup_pdflush(long nr_pages)
{
if (nr_pages == 0)
nr_pages = global_page_state(NR_FILE_DIRTY) +
global_page_state(NR_UNSTABLE_NFS);
return pdflush_operation(background_writeout, nr_pages);
}
static void wb_timer_fn(unsigned long unused);
static void laptop_timer_fn(unsigned long unused);
static DEFINE_TIMER(wb_timer, wb_timer_fn, 0, 0);
static DEFINE_TIMER(laptop_mode_wb_timer, laptop_timer_fn, 0, 0);
/*
* Periodic writeback of "old" data.
*
* Define "old": the first time one of an inode's pages is dirtied, we mark the
* dirtying-time in the inode's address_space. So this periodic writeback code
* just walks the superblock inode list, writing back any inodes which are
* older than a specific point in time.
*
* Try to run once per dirty_writeback_interval. But if a writeback event
* takes longer than a dirty_writeback_interval interval, then leave a
* one-second gap.
*
* older_than_this takes precedence over nr_to_write. So we'll only write back
* all dirty pages if they are all attached to "old" mappings.
*/
static void wb_kupdate(unsigned long arg)
{
unsigned long oldest_jif;
unsigned long start_jif;
unsigned long next_jif;
long nr_to_write;
struct writeback_control wbc = {
.bdi = NULL,
.sync_mode = WB_SYNC_NONE,
.older_than_this = &oldest_jif,
.nr_to_write = 0,
.nonblocking = 1,
.for_kupdate = 1,
.range_cyclic = 1,
};
sync_supers();
oldest_jif = jiffies - dirty_expire_interval;
start_jif = jiffies;
next_jif = start_jif + dirty_writeback_interval;
nr_to_write = global_page_state(NR_FILE_DIRTY) +
global_page_state(NR_UNSTABLE_NFS) +
(inodes_stat.nr_inodes - inodes_stat.nr_unused);
while (nr_to_write > 0) {
wbc.more_io = 0;
wbc.encountered_congestion = 0;
wbc.nr_to_write = MAX_WRITEBACK_PAGES;
writeback_inodes(&wbc);
if (wbc.nr_to_write > 0) {
if (wbc.encountered_congestion || wbc.more_io)
congestion_wait(WRITE, HZ/10);
else
break; /* All the old data is written */
}
nr_to_write -= MAX_WRITEBACK_PAGES - wbc.nr_to_write;
}
if (time_before(next_jif, jiffies + HZ))
next_jif = jiffies + HZ;
if (dirty_writeback_interval)
mod_timer(&wb_timer, next_jif);
}
/*
* sysctl handler for /proc/sys/vm/dirty_writeback_centisecs
*/
int dirty_writeback_centisecs_handler(ctl_table *table, int write,
struct file *file, void __user *buffer, size_t *length, loff_t *ppos)
{
proc_dointvec_userhz_jiffies(table, write, file, buffer, length, ppos);
if (dirty_writeback_interval)
mod_timer(&wb_timer, jiffies + dirty_writeback_interval);
else
del_timer(&wb_timer);
return 0;
}
/*
* balance_dirty_pages() must be called by processes which are generating dirty
* data. It looks at the number of dirty pages in the machine and will force
* the caller to perform writeback if the system is over `vm_dirty_ratio'.
* If we're over `background_thresh' then pdflush is woken to perform some
* writeout.
*/
static void balance_dirty_pages(struct address_space *mapping)
{
long nr_reclaimable, bdi_nr_reclaimable;
long nr_writeback, bdi_nr_writeback;
long background_thresh;
long dirty_thresh;
long bdi_thresh;
unsigned long pages_written = 0;
unsigned long write_chunk = sync_writeback_pages();
struct backing_dev_info *bdi = mapping->backing_dev_info;
for (;;) {
struct writeback_control wbc = {
.bdi = bdi,
.sync_mode = WB_SYNC_NONE,
.older_than_this = NULL,
.nr_to_write = write_chunk,
.range_cyclic = 1,
};
get_dirty_limits(&background_thresh, &dirty_thresh,
&bdi_thresh, bdi);
nr_reclaimable = global_page_state(NR_FILE_DIRTY) +
global_page_state(NR_UNSTABLE_NFS);
nr_writeback = global_page_state(NR_WRITEBACK);
bdi_nr_reclaimable = bdi_stat(bdi, BDI_RECLAIMABLE);
bdi_nr_writeback = bdi_stat(bdi, BDI_WRITEBACK);
if (bdi_nr_reclaimable + bdi_nr_writeback <= bdi_thresh)
break;
/*
* Throttle it only when the background writeback cannot
* catch-up. This avoids (excessively) small writeouts
* when the bdi limits are ramping up.
*/
if (nr_reclaimable + nr_writeback <
(background_thresh + dirty_thresh) / 2)
break;
if (!bdi->dirty_exceeded)
bdi->dirty_exceeded = 1;
/* Note: nr_reclaimable denotes nr_dirty + nr_unstable.
* Unstable writes are a feature of certain networked
* filesystems (i.e. NFS) in which data may have been
* written to the server's write cache, but has not yet
* been flushed to permanent storage.
*/
if (bdi_nr_reclaimable) {
writeback_inodes(&wbc);
pages_written += write_chunk - wbc.nr_to_write;
get_dirty_limits(&background_thresh, &dirty_thresh,
&bdi_thresh, bdi);
}
/*
* In order to avoid the stacked BDI deadlock we need
* to ensure we accurately count the 'dirty' pages when
* the threshold is low.
*
* Otherwise it would be possible to get thresh+n pages
* reported dirty, even though there are thresh-m pages
* actually dirty; with m+n sitting in the percpu
* deltas.
*/
if (bdi_thresh < 2*bdi_stat_error(bdi)) {
bdi_nr_reclaimable = bdi_stat_sum(bdi, BDI_RECLAIMABLE);
bdi_nr_writeback = bdi_stat_sum(bdi, BDI_WRITEBACK);
} else if (bdi_nr_reclaimable) {
bdi_nr_reclaimable = bdi_stat(bdi, BDI_RECLAIMABLE);
bdi_nr_writeback = bdi_stat(bdi, BDI_WRITEBACK);
}
if (bdi_nr_reclaimable + bdi_nr_writeback <= bdi_thresh)
break;
if (pages_written >= write_chunk)
break; /* We've done our duty */
congestion_wait(WRITE, HZ/10);
}
if (bdi_nr_reclaimable + bdi_nr_writeback < bdi_thresh &&
bdi->dirty_exceeded)
bdi->dirty_exceeded = 0;
if (writeback_in_progress(bdi))
return; /* pdflush is already working this queue */
/*
* In laptop mode, we wait until hitting the higher threshold before
* starting background writeout, and then write out all the way down
* to the lower threshold. So slow writers cause minimal disk activity.
*
* In normal mode, we start background writeout at the lower
* background_thresh, to keep the amount of dirty memory low.
*/
if ((laptop_mode && pages_written) ||
(!laptop_mode && (global_page_state(NR_FILE_DIRTY)
+ global_page_state(NR_UNSTABLE_NFS)
> background_thresh)))
pdflush_operation(background_writeout, 0);
}
void set_page_dirty_balance(struct page *page, int page_mkwrite)
{
if (set_page_dirty(page) || page_mkwrite) {
struct address_space *mapping = page_mapping(page);
if (mapping)
balance_dirty_pages_ratelimited(mapping);
}
}
/**
* balance_dirty_pages_ratelimited_nr - balance dirty memory state
* @mapping: address_space which was dirtied
* @nr_pages_dirtied: number of pages which the caller has just dirtied
*
* Processes which are dirtying memory should call in here once for each page
* which was newly dirtied. The function will periodically check the system's
* dirty state and will initiate writeback if needed.
*
* On really big machines, get_writeback_state is expensive, so try to avoid
* calling it too often (ratelimiting). But once we're over the dirty memory
* limit we decrease the ratelimiting by a lot, to prevent individual processes
* from overshooting the limit by (ratelimit_pages) each.
*/
void balance_dirty_pages_ratelimited_nr(struct address_space *mapping,
unsigned long nr_pages_dirtied)
{
static DEFINE_PER_CPU(unsigned long, ratelimits) = 0;
unsigned long ratelimit;
unsigned long *p;
ratelimit = ratelimit_pages;
if (mapping->backing_dev_info->dirty_exceeded)
ratelimit = 8;
/*
* Check the rate limiting. Also, we do not want to throttle real-time
* tasks in balance_dirty_pages(). Period.
*/
preempt_disable();
p = &__get_cpu_var(ratelimits);
*p += nr_pages_dirtied;
if (unlikely(*p >= ratelimit)) {
*p = 0;
preempt_enable();
balance_dirty_pages(mapping);
return;
}
preempt_enable();
}
EXPORT_SYMBOL(balance_dirty_pages_ratelimited_nr);
void throttle_vm_writeout(gfp_t gfp_mask)
{
long background_thresh;
long dirty_thresh;
for ( ; ; ) {
get_dirty_limits(&background_thresh, &dirty_thresh, NULL, NULL);
/*
* Boost the allowable dirty threshold a bit for page
* allocators so they don't get DoS'ed by heavy writers
*/
dirty_thresh += dirty_thresh / 10; /* wheeee... */
if (global_page_state(NR_UNSTABLE_NFS) +
global_page_state(NR_WRITEBACK) <= dirty_thresh)
break;
congestion_wait(WRITE, HZ/10);
/*
* The caller might hold locks which can prevent IO completion
* or progress in the filesystem. So we cannot just sit here
* waiting for IO to complete.
*/
if ((gfp_mask & (__GFP_FS|__GFP_IO)) != (__GFP_FS|__GFP_IO))
break;
}
}
static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
struct page *page)
{
struct dnode_of_data dn;
struct node_info ni;
unsigned int start, end;
int err = 0, recovered = 0;
/* step 1: recover xattr */
if (IS_INODE(page)) {
f2fs_recover_inline_xattr(inode, page);
} else if (f2fs_has_xattr_block(ofs_of_node(page))) {
err = f2fs_recover_xattr_data(inode, page);
if (!err)
recovered++;
goto out;
}
/* step 2: recover inline data */
if (f2fs_recover_inline_data(inode, page))
goto out;
/* step 3: recover data indices */
start = f2fs_start_bidx_of_node(ofs_of_node(page), inode);
end = start + ADDRS_PER_PAGE(page, inode);
set_new_dnode(&dn, inode, NULL, NULL, 0);
retry_dn:
err = f2fs_get_dnode_of_data(&dn, start, ALLOC_NODE);
if (err) {
if (err == -ENOMEM) {
congestion_wait(BLK_RW_ASYNC, HZ/50);
goto retry_dn;
}
goto out;
}
f2fs_wait_on_page_writeback(dn.node_page, NODE, true, true);
err = f2fs_get_node_info(sbi, dn.nid, &ni);
if (err)
goto err;
f2fs_bug_on(sbi, ni.ino != ino_of_node(page));
if (ofs_of_node(dn.node_page) != ofs_of_node(page)) {
f2fs_msg(sbi->sb, KERN_WARNING,
"Inconsistent ofs_of_node, ino:%lu, ofs:%u, %u",
inode->i_ino, ofs_of_node(dn.node_page),
ofs_of_node(page));
err = -EFAULT;
goto err;
}
for (; start < end; start++, dn.ofs_in_node++) {
block_t src, dest;
src = datablock_addr(dn.inode, dn.node_page, dn.ofs_in_node);
dest = datablock_addr(dn.inode, page, dn.ofs_in_node);
if (__is_valid_data_blkaddr(src) &&
!f2fs_is_valid_blkaddr(sbi, src, META_POR)) {
err = -EFAULT;
goto err;
}
if (__is_valid_data_blkaddr(dest) &&
!f2fs_is_valid_blkaddr(sbi, dest, META_POR)) {
err = -EFAULT;
goto err;
}
/* skip recovering if dest is the same as src */
if (src == dest)
continue;
/* dest is invalid, just invalidate src block */
if (dest == NULL_ADDR) {
f2fs_truncate_data_blocks_range(&dn, 1);
continue;
}
if (!file_keep_isize(inode) &&
(i_size_read(inode) <= ((loff_t)start << PAGE_SHIFT)))
f2fs_i_size_write(inode,
(loff_t)(start + 1) << PAGE_SHIFT);
/*
* dest is reserved block, invalidate src block
* and then reserve one new block in dnode page.
*/
if (dest == NEW_ADDR) {
f2fs_truncate_data_blocks_range(&dn, 1);
f2fs_reserve_new_block(&dn);
continue;
}
/* dest is valid block, try to recover from src to dest */
if (f2fs_is_valid_blkaddr(sbi, dest, META_POR)) {
if (src == NULL_ADDR) {
err = f2fs_reserve_new_block(&dn);
while (err &&
IS_ENABLED(CONFIG_F2FS_FAULT_INJECTION))
err = f2fs_reserve_new_block(&dn);
/* We should not get -ENOSPC */
f2fs_bug_on(sbi, err);
if (err)
goto err;
}
retry_prev:
/* Check the previous node page having this index */
err = check_index_in_prev_nodes(sbi, dest, &dn);
if (err) {
if (err == -ENOMEM) {
congestion_wait(BLK_RW_ASYNC, HZ/50);
goto retry_prev;
}
goto err;
}
/* write dummy data page */
f2fs_replace_block(sbi, &dn, src, dest,
ni.version, false, false);
recovered++;
}
}
copy_node_footer(dn.node_page, page);
fill_node_footer(dn.node_page, dn.nid, ni.ino,
ofs_of_node(page), false);
set_page_dirty(dn.node_page);
err:
f2fs_put_dnode(&dn);
out:
f2fs_msg(sbi->sb, KERN_NOTICE,
"recover_data: ino = %lx (i_size: %s) recovered = %d, err = %d",
inode->i_ino,
file_keep_isize(inode) ? "keep" : "recover",
recovered, err);
return err;
}
static int start_this_handle(journal_t *journal, handle_t *handle,
gfp_t gfp_mask)
{
transaction_t *transaction, *new_transaction = NULL;
tid_t tid;
int needed, need_to_start;
int nblocks = handle->h_buffer_credits;
unsigned long ts = jiffies;
if (nblocks > journal->j_max_transaction_buffers) {
printk(KERN_ERR "JBD2: %s wants too many credits (%d > %d)\n",
current->comm, nblocks,
journal->j_max_transaction_buffers);
return -ENOSPC;
}
alloc_transaction:
if (!journal->j_running_transaction) {
new_transaction = kmem_cache_alloc(transaction_cache,
gfp_mask | __GFP_ZERO);
if (!new_transaction) {
if ((gfp_mask & __GFP_FS) == 0) {
congestion_wait(BLK_RW_ASYNC, HZ/50);
goto alloc_transaction;
}
return -ENOMEM;
}
}
jbd_debug(3, "New handle %p going live.\n", handle);
repeat:
read_lock(&journal->j_state_lock);
BUG_ON(journal->j_flags & JBD2_UNMOUNT);
if (is_journal_aborted(journal) ||
(journal->j_errno != 0 && !(journal->j_flags & JBD2_ACK_ERR))) {
read_unlock(&journal->j_state_lock);
jbd2_journal_free_transaction(new_transaction);
return -EROFS;
}
if (journal->j_barrier_count) {
read_unlock(&journal->j_state_lock);
wait_event(journal->j_wait_transaction_locked,
journal->j_barrier_count == 0);
goto repeat;
}
if (!journal->j_running_transaction) {
read_unlock(&journal->j_state_lock);
if (!new_transaction)
goto alloc_transaction;
write_lock(&journal->j_state_lock);
if (journal->j_barrier_count) {
printk(KERN_WARNING "JBD: %s: wait for transaction barrier\n", __func__);
write_unlock(&journal->j_state_lock);
goto repeat;
}
if (!journal->j_running_transaction) {
jbd2_get_transaction(journal, new_transaction);
new_transaction = NULL;
}
write_unlock(&journal->j_state_lock);
goto repeat;
}
transaction = journal->j_running_transaction;
if (transaction->t_state == T_LOCKED) {
DEFINE_WAIT(wait);
prepare_to_wait(&journal->j_wait_transaction_locked,
&wait, TASK_UNINTERRUPTIBLE);
read_unlock(&journal->j_state_lock);
schedule();
finish_wait(&journal->j_wait_transaction_locked, &wait);
goto repeat;
}
needed = atomic_add_return(nblocks,
&transaction->t_outstanding_credits);
if (needed > journal->j_max_transaction_buffers) {
DEFINE_WAIT(wait);
jbd_debug(2, "Handle %p starting new commit...\n", handle);
atomic_sub(nblocks, &transaction->t_outstanding_credits);
prepare_to_wait(&journal->j_wait_transaction_locked, &wait,
TASK_UNINTERRUPTIBLE);
tid = transaction->t_tid;
need_to_start = !tid_geq(journal->j_commit_request, tid);
read_unlock(&journal->j_state_lock);
if (need_to_start)
jbd2_log_start_commit(journal, tid);
schedule();
finish_wait(&journal->j_wait_transaction_locked, &wait);
goto repeat;
}
if (__jbd2_log_space_left(journal) < jbd_space_needed(journal)) {
jbd_debug(2, "Handle %p waiting for checkpoint...\n", handle);
atomic_sub(nblocks, &transaction->t_outstanding_credits);
read_unlock(&journal->j_state_lock);
write_lock(&journal->j_state_lock);
if (__jbd2_log_space_left(journal) < jbd_space_needed(journal))
__jbd2_log_wait_for_space(journal);
write_unlock(&journal->j_state_lock);
goto repeat;
}
update_t_max_wait(transaction, ts);
handle->h_transaction = transaction;
atomic_inc(&transaction->t_updates);
atomic_inc(&transaction->t_handle_count);
jbd_debug(4, "Handle %p given %d credits (total %d, free %d)\n",
handle, nblocks,
atomic_read(&transaction->t_outstanding_credits),
__jbd2_log_space_left(journal));
read_unlock(&journal->j_state_lock);
lock_map_acquire(&handle->h_lockdep_map);
jbd2_journal_free_transaction(new_transaction);
return 0;
}
