/*
* 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 the writeback threads are woken to
* perform some writeout.
*/
static void balance_dirty_pages(struct address_space *mapping,
unsigned long write_chunk)
{
long nr_reclaimable, bdi_nr_reclaimable;
long nr_writeback, bdi_nr_writeback;
unsigned long background_thresh;
unsigned long dirty_thresh;
unsigned long bdi_thresh;
unsigned long pages_written = 0;
unsigned long pause = 1;
bool dirty_exceeded = false;
struct backing_dev_info *bdi = mapping->backing_dev_info;
for (;;) {
struct writeback_control wbc = {
.sync_mode = WB_SYNC_NONE,
.older_than_this = NULL,
.nr_to_write = write_chunk,
.range_cyclic = 1,
};
nr_reclaimable = global_page_state(NR_FILE_DIRTY) +
global_page_state(NR_UNSTABLE_NFS);
nr_writeback = global_page_state(NR_WRITEBACK);
global_dirty_limits(&background_thresh, &dirty_thresh);
/*
* 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;
bdi_thresh = bdi_dirty_limit(bdi, dirty_thresh);
bdi_thresh = task_dirty_limit(current, bdi_thresh);
/*
* 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 {
bdi_nr_reclaimable = bdi_stat(bdi, BDI_RECLAIMABLE);
bdi_nr_writeback = bdi_stat(bdi, BDI_WRITEBACK);
}
/*
* The bdi thresh is somehow "soft" limit derived from the
* global "hard" limit. The former helps to prevent heavy IO
* bdi or process from holding back light ones; The latter is
* the last resort safeguard.
*/
dirty_exceeded =
(bdi_nr_reclaimable + bdi_nr_writeback > bdi_thresh)
|| (nr_reclaimable + nr_writeback > dirty_thresh);
if (!dirty_exceeded)
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.
* Only move pages to writeback if this bdi is over its
* threshold otherwise wait until the disk writes catch
* up.
*/
trace_wbc_balance_dirty_start(&wbc, bdi);
if (bdi_nr_reclaimable > bdi_thresh) {
writeback_inodes_wb(&bdi->wb, &wbc);
pages_written += write_chunk - wbc.nr_to_write;
trace_wbc_balance_dirty_written(&wbc, bdi);
if (pages_written >= write_chunk)
break; /* We've done our duty */
}
trace_wbc_balance_dirty_wait(&wbc, bdi);
__set_current_state(TASK_UNINTERRUPTIBLE);
io_schedule_timeout(pause);
/*
* Increase the delay for each loop, up to our previous
* default of taking a 100ms nap.
*/
pause <<= 1;
if (pause > HZ / 10)
break;
}
if (!dirty_exceeded && bdi->dirty_exceeded)
bdi->dirty_exceeded = 0;
if (writeback_in_progress(bdi))
return;
/*
* 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 && (nr_reclaimable > background_thresh)))
bdi_start_background_writeback(bdi);
}
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);
}
}
static DEFINE_PER_CPU(unsigned long, bdp_ratelimits) = 0;
/**
* 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)
{
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(bdp_ratelimits);
*p += nr_pages_dirtied;
if (unlikely(*p >= ratelimit)) {
ratelimit = sync_writeback_pages(*p);
*p = 0;
preempt_enable();
balance_dirty_pages(mapping, ratelimit);
return;
}
preempt_enable();
}
/*
* 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;
}
}
/*
* 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 the writeback threads are woken to
* perform some writeout.
*/
static void balance_dirty_pages(struct address_space *mapping,
unsigned long write_chunk)
{
long nr_reclaimable, bdi_nr_reclaimable;
long nr_writeback, bdi_nr_writeback;
long ub_dirty, ub_writeback;
long ub_thresh, ub_background_thresh;
unsigned long background_thresh;
unsigned long dirty_thresh;
unsigned long bdi_thresh;
unsigned long pages_written = 0;
unsigned long pause = 1;
struct user_beancounter *ub = get_io_ub();
struct backing_dev_info *bdi = mapping->backing_dev_info;
for (;;) {
struct writeback_control wbc = {
.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);
if (ub_dirty_limits(&ub_background_thresh, &ub_thresh, ub)) {
ub_dirty = ub_stat_get(ub, dirty_pages);
ub_writeback = ub_stat_get(ub, writeback_pages);
} else {
ub_dirty = ub_writeback = 0;
ub_thresh = ub_background_thresh = LONG_MAX / 2;
}
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);
/*
* Check thresholds, set dirty_exceeded flags and
* start background writeback before throttling.
*/
if (bdi_nr_reclaimable + bdi_nr_writeback > bdi_thresh) {
if (!bdi->dirty_exceeded)
bdi->dirty_exceeded = 1;
if (!writeback_in_progress(bdi))
bdi_start_background_writeback(bdi, NULL);
} else if (ub_dirty + ub_writeback > ub_thresh) {
if (!test_bit(UB_DIRTY_EXCEEDED, &ub->ub_flags))
set_bit(UB_DIRTY_EXCEEDED, &ub->ub_flags);
if (!writeback_in_progress(bdi))
bdi_start_background_writeback(bdi, ub);
} else
break;
/*
* Throttle it only when the background writeback cannot
* catch-up. This avoids (excessively) small writeouts
* when the bdi limits are ramping up.
*/
if (bdi_cap_account_writeback(bdi) &&
nr_reclaimable + nr_writeback <
(background_thresh + dirty_thresh) / 2 &&
ub_dirty + ub_writeback <
(ub_background_thresh + ub_thresh) / 2)
break;
/* 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.
* Only move pages to writeback if this bdi is over its
* threshold otherwise wait until the disk writes catch
* up.
*/
trace_wbc_balance_dirty_start(&wbc, bdi);
if (bdi_nr_reclaimable > bdi_thresh) {
writeback_inodes_wb(&bdi->wb, &wbc);
pages_written += write_chunk - wbc.nr_to_write;
trace_wbc_balance_dirty_written(&wbc, bdi);
get_dirty_limits(&background_thresh, &dirty_thresh,
&bdi_thresh, bdi);
} else if (ub_dirty > ub_thresh) {
wbc.wb_ub = ub;
writeback_inodes_wb(&bdi->wb, &wbc);
pages_written += write_chunk - wbc.nr_to_write;
trace_wbc_balance_dirty_written(&wbc, bdi);
ub_dirty = ub_stat_get(ub, dirty_pages);
ub_writeback = ub_stat_get(ub, writeback_pages);
wbc.wb_ub = NULL;
}
/*
* 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);
}
/* fixup ub-stat per-cpu drift to avoid false-positive */
if (ub_dirty + ub_writeback > ub_thresh &&
ub_dirty + ub_writeback - ub_thresh <
UB_STAT_BATCH * num_possible_cpus()) {
ub_dirty = ub_stat_get_exact(ub, dirty_pages);
ub_writeback = ub_stat_get_exact(ub, writeback_pages);
}
if (bdi_nr_reclaimable + bdi_nr_writeback <= bdi_thresh &&
ub_dirty + ub_writeback <= ub_thresh)
break;
if (pages_written >= write_chunk)
break; /* We've done our duty */
trace_wbc_balance_dirty_wait(&wbc, bdi);
__set_current_state(TASK_KILLABLE);
io_schedule_timeout(pause);
/*
* Increase the delay for each loop, up to our previous
* default of taking a 100ms nap.
*/
pause <<= 1;
if (pause > HZ / 10)
pause = HZ / 10;
if (fatal_signal_pending(current))
break;
}
if(pages_written) trace_mm_balancedirty_writeout(pages_written);
if (bdi_nr_reclaimable + bdi_nr_writeback < bdi_thresh &&
bdi->dirty_exceeded)
bdi->dirty_exceeded = 0;
if (ub_dirty + ub_writeback < ub_thresh &&
test_bit(UB_DIRTY_EXCEEDED, &ub->ub_flags))
clear_bit(UB_DIRTY_EXCEEDED, &ub->ub_flags);
virtinfo_notifier_call(VITYPE_IO, VIRTINFO_IO_BALANCE_DIRTY,
(void*)write_chunk);
/*
* Even if this is filtered writeback for other ub it will write
* inodes for this ub, because ub->dirty_exceeded is set.
*/
if (writeback_in_progress(bdi))
return;
/*
* 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)))
bdi_start_background_writeback(bdi, NULL);
else if ((laptop_mode && pages_written) ||
(!laptop_mode && ub_dirty > ub_background_thresh))
bdi_start_background_writeback(bdi, ub);
}
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);
}
}
static DEFINE_PER_CPU(unsigned long, bdp_ratelimits) = 0;
/**
* 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)
{
unsigned long ratelimit;
unsigned long *p;
ratelimit = ratelimit_pages;
if (mapping->backing_dev_info->dirty_exceeded ||
test_bit(UB_DIRTY_EXCEEDED, &get_io_ub()->ub_flags))
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(bdp_ratelimits);
*p += nr_pages_dirtied;
if (unlikely(*p >= ratelimit)) {
ratelimit = sync_writeback_pages(*p);
*p = 0;
preempt_enable();
balance_dirty_pages(mapping, ratelimit);
return;
}
preempt_enable();
}
/*
* This is a little more tricky than the file -> pipe splicing. There are
* basically three cases:
*
* - Destination page already exists in the address space and there
* are users of it. For that case we have no other option that
* copying the data. Tough luck.
* - Destination page already exists in the address space, but there
* are no users of it. Make sure it's uptodate, then drop it. Fall
* through to last case.
* - Destination page does not exist, we can add the pipe page to
* the page cache and avoid the copy.
*
* If asked to move pages to the output file (SPLICE_F_MOVE is set in
* sd->flags), we attempt to migrate pages from the pipe to the output
* file address space page cache. This is possible if no one else has
* the pipe page referenced outside of the pipe and page cache. If
* SPLICE_F_MOVE isn't set, or we cannot move the page, we simply create
* a new page in the output file page cache and fill/dirty that.
*/
static int pipe_to_file(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
struct splice_desc *sd)
{
struct file *file = sd->file;
struct address_space *mapping = file->f_mapping;
unsigned int offset, this_len;
struct page *page;
pgoff_t index;
int ret;
/*
* make sure the data in this buffer is uptodate
*/
ret = buf->ops->pin(pipe, buf);
if (unlikely(ret))
return ret;
index = sd->pos >> PAGE_CACHE_SHIFT;
offset = sd->pos & ~PAGE_CACHE_MASK;
this_len = sd->len;
if (this_len + offset > PAGE_CACHE_SIZE)
this_len = PAGE_CACHE_SIZE - offset;
/*
* Reuse buf page, if SPLICE_F_MOVE is set and we are doing a full
* page.
*/
if ((sd->flags & SPLICE_F_MOVE) && this_len == PAGE_CACHE_SIZE) {
/*
* If steal succeeds, buf->page is now pruned from the
* pagecache and we can reuse it. The page will also be
* locked on successful return.
*/
if (buf->ops->steal(pipe, buf))
goto find_page;
page = buf->page;
if (add_to_page_cache(page, mapping, index, GFP_KERNEL)) {
unlock_page(page);
goto find_page;
}
page_cache_get(page);
if (!(buf->flags & PIPE_BUF_FLAG_LRU))
lru_cache_add(page);
} else {
find_page:
page = find_lock_page(mapping, index);
if (!page) {
ret = -ENOMEM;
page = page_cache_alloc_cold(mapping);
if (unlikely(!page))
goto out_ret;
/*
* This will also lock the page
*/
ret = add_to_page_cache_lru(page, mapping, index,
GFP_KERNEL);
if (unlikely(ret))
goto out;
}
/*
* We get here with the page locked. If the page is also
* uptodate, we don't need to do more. If it isn't, we
* may need to bring it in if we are not going to overwrite
* the full page.
*/
if (!PageUptodate(page)) {
if (this_len < PAGE_CACHE_SIZE) {
ret = mapping->a_ops->readpage(file, page);
if (unlikely(ret))
goto out;
lock_page(page);
if (!PageUptodate(page)) {
/*
* Page got invalidated, repeat.
*/
if (!page->mapping) {
unlock_page(page);
page_cache_release(page);
goto find_page;
}
ret = -EIO;
goto out;
}
} else
SetPageUptodate(page);
}
}
ret = mapping->a_ops->prepare_write(file, page, offset, offset+this_len);
if (unlikely(ret)) {
loff_t isize = i_size_read(mapping->host);
if (ret != AOP_TRUNCATED_PAGE)
unlock_page(page);
page_cache_release(page);
if (ret == AOP_TRUNCATED_PAGE)
goto find_page;
/*
* prepare_write() may have instantiated a few blocks
* outside i_size. Trim these off again.
*/
if (sd->pos + this_len > isize)
vmtruncate(mapping->host, isize);
goto out_ret;
}
if (buf->page != page) {
/*
* Careful, ->map() uses KM_USER0!
*/
char *src = buf->ops->map(pipe, buf, 1);
char *dst = kmap_atomic(page, KM_USER1);
memcpy(dst + offset, src + buf->offset, this_len);
flush_dcache_page(page);
kunmap_atomic(dst, KM_USER1);
buf->ops->unmap(pipe, buf, src);
}
ret = mapping->a_ops->commit_write(file, page, offset, offset+this_len);
if (!ret) {
/*
* Return the number of bytes written and mark page as
* accessed, we are now done!
*/
ret = this_len;
mark_page_accessed(page);
balance_dirty_pages_ratelimited(mapping);
} else if (ret == AOP_TRUNCATED_PAGE) {
page_cache_release(page);
goto find_page;
}
out:
page_cache_release(page);
unlock_page(page);
out_ret:
return ret;
}
/*
* Almost copy of generic_file_splice_write() (added changed_begin/end,
* tux3_iattrdirty()).
*/
static ssize_t tux3_file_splice_write(struct pipe_inode_info *pipe,
struct file *out, loff_t *ppos,
size_t len, unsigned int flags)
{
if(DEBUG_MODE_K==1)
{
printk(KERN_INFO"%25s %25s %4d #in\n",__FILE__,__func__,__LINE__);
}
struct address_space *mapping = out->f_mapping;
struct inode *inode = mapping->host;
struct sb *sb = tux_sb(inode->i_sb);
struct splice_desc sd = {
.total_len = len,
.flags = flags,
.pos = *ppos,
.u.file = out,
};
ssize_t ret;
sb_start_write(inode->i_sb);
pipe_lock(pipe);
splice_from_pipe_begin(&sd);
do {
ret = splice_from_pipe_next(pipe, &sd);
if (ret <= 0)
break;
mutex_lock_nested(&inode->i_mutex, I_MUTEX_CHILD);
/* For each ->write_end() calls change_end(). */
change_begin(sb);
/* For timestamp. FIXME: convert this to ->update_time
* handler? */
tux3_iattrdirty(inode);
ret = file_remove_suid(out);
if (!ret) {
ret = file_update_time(out);
if (!ret)
ret = splice_from_pipe_feed(pipe, &sd,
pipe_to_file);
}
change_end_if_needed(sb);
mutex_unlock(&inode->i_mutex);
} while (ret > 0);
splice_from_pipe_end(pipe, &sd);
pipe_unlock(pipe);
if (sd.num_spliced)
ret = sd.num_spliced;
if (ret > 0) {
int err;
err = generic_write_sync(out, *ppos, ret);
if (err)
ret = err;
else
*ppos += ret;
balance_dirty_pages_ratelimited(mapping);
}
sb_end_write(inode->i_sb);
return ret;
}
/*
* This is a little more tricky than the file -> pipe splicing. There are
* basically three cases:
*
* - Destination page already exists in the address space and there
* are users of it. For that case we have no other option that
* copying the data. Tough luck.
* - Destination page already exists in the address space, but there
* are no users of it. Make sure it's uptodate, then drop it. Fall
* through to last case.
* - Destination page does not exist, we can add the pipe page to
* the page cache and avoid the copy.
*
* If asked to move pages to the output file (SPLICE_F_MOVE is set in
* sd->flags), we attempt to migrate pages from the pipe to the output
* file address space page cache. This is possible if no one else has
* the pipe page referenced outside of the pipe and page cache. If
* SPLICE_F_MOVE isn't set, or we cannot move the page, we simply create
* a new page in the output file page cache and fill/dirty that.
*/
static int pipe_to_file(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
struct splice_desc *sd)
{
struct file *file = sd->file;
struct address_space *mapping = file->f_mapping;
unsigned int offset, this_len;
struct page *page;
pgoff_t index;
int ret;
/*
* make sure the data in this buffer is uptodate
*/
ret = buf->ops->pin(pipe, buf);
if (unlikely(ret))
return ret;
index = sd->pos >> PAGE_CACHE_SHIFT;
offset = sd->pos & ~PAGE_CACHE_MASK;
this_len = sd->len;
if (this_len + offset > PAGE_CACHE_SIZE)
this_len = PAGE_CACHE_SIZE - offset;
find_page:
page = find_lock_page(mapping, index);
if (!page) {
ret = -ENOMEM;
page = page_cache_alloc_cold(mapping);
if (unlikely(!page))
goto out_ret;
/*
* This will also lock the page
*/
ret = add_to_page_cache_lru(page, mapping, index,
GFP_KERNEL);
if (unlikely(ret))
goto out;
}
ret = mapping->a_ops->prepare_write(file, page, offset, offset+this_len);
if (unlikely(ret)) {
loff_t isize = i_size_read(mapping->host);
if (ret != AOP_TRUNCATED_PAGE)
unlock_page(page);
page_cache_release(page);
if (ret == AOP_TRUNCATED_PAGE)
goto find_page;
/*
* prepare_write() may have instantiated a few blocks
* outside i_size. Trim these off again.
*/
if (sd->pos + this_len > isize)
vmtruncate(mapping->host, isize);
goto out_ret;
}
if (buf->page != page) {
/*
* Careful, ->map() uses KM_USER0!
*/
char *src = buf->ops->map(pipe, buf, 1);
char *dst = kmap_atomic(page, KM_USER1);
memcpy(dst + offset, src + buf->offset, this_len);
flush_dcache_page(page);
kunmap_atomic(dst, KM_USER1);
buf->ops->unmap(pipe, buf, src);
}
ret = mapping->a_ops->commit_write(file, page, offset, offset+this_len);
if (ret) {
if (ret == AOP_TRUNCATED_PAGE) {
page_cache_release(page);
goto find_page;
}
if (ret < 0)
goto out;
/*
* Partial write has happened, so 'ret' already initialized by
* number of bytes written, Where is nothing we have to do here.
*/
} else
ret = this_len;
/*
* Return the number of bytes written and mark page as
* accessed, we are now done!
*/
mark_page_accessed(page);
balance_dirty_pages_ratelimited(mapping);
out:
page_cache_release(page);
unlock_page(page);
out_ret:
return ret;
}
static void balance_dirty_pages(struct address_space *mapping,
unsigned long write_chunk)
{
long nr_reclaimable, bdi_nr_reclaimable;
long nr_writeback, bdi_nr_writeback;
unsigned long background_thresh;
unsigned long dirty_thresh;
unsigned long bdi_thresh;
unsigned long pages_written = 0;
unsigned long pause = 1;
struct backing_dev_info *bdi = mapping->backing_dev_info;
for (;;) {
struct writeback_control wbc = {
.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.
* Only move pages to writeback if this bdi is over its
* threshold otherwise wait until the disk writes catch
* up.
*/
if (bdi_nr_reclaimable > bdi_thresh) {
writeback_inodes_wb(&bdi->wb, &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 */
__set_current_state(TASK_INTERRUPTIBLE);
io_schedule_timeout(pause);
/*
* Increase the delay for each loop, up to our previous
* default of taking a 100ms nap.
*/
pause <<= 1;
if (pause > HZ / 10)
pause = HZ / 10;
}
if (bdi_nr_reclaimable + bdi_nr_writeback < bdi_thresh &&
bdi->dirty_exceeded)
bdi->dirty_exceeded = 0;
if (writeback_in_progress(bdi))
return;
/*
* 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)))
bdi_start_background_writeback(bdi);
}
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);
}
}
static DEFINE_PER_CPU(unsigned long, bdp_ratelimits) = 0;
void balance_dirty_pages_ratelimited_nr(struct address_space *mapping,
unsigned long nr_pages_dirtied)
{
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(bdp_ratelimits);
*p += nr_pages_dirtied;
if (unlikely(*p >= ratelimit)) {
ratelimit = sync_writeback_pages(*p);
*p = 0;
preempt_enable();
balance_dirty_pages(mapping, ratelimit);
return;
}
preempt_enable();
}
