/**
* wait_iff_congested - Conditionally wait for a backing_dev to become uncongested or a pgdat to complete writes
* @pgdat: A pgdat to check if it is heavily congested
* @sync: SYNC or ASYNC IO
* @timeout: timeout in jiffies
*
* In the event of a congested backing_dev (any backing_dev) and the given
* @pgdat has experienced recent congestion, this waits for up to @timeout
* jiffies for either a BDI to exit congestion of the given @sync queue
* or a write to complete.
*
* In the absence of pgdat congestion, cond_resched() is called to yield
* the processor if necessary but otherwise does not sleep.
*
* The return value is 0 if the sleep is for the full timeout. Otherwise,
* it is the number of jiffies that were still remaining when the function
* returned. return_value == timeout implies the function did not sleep.
*/
long wait_iff_congested(struct pglist_data *pgdat, int sync, long timeout)
{
long ret;
unsigned long start = jiffies;
DEFINE_WAIT(wait);
wait_queue_head_t *wqh = &congestion_wqh[sync];
/*
* If there is no congestion, or heavy congestion is not being
* encountered in the current pgdat, yield if necessary instead
* of sleeping on the congestion queue
*/
if (atomic_read(&nr_wb_congested[sync]) == 0 ||
!test_bit(PGDAT_CONGESTED, &pgdat->flags)) {
cond_resched();
/* In case we scheduled, work out time remaining */
ret = timeout - (jiffies - start);
if (ret < 0)
ret = 0;
goto out;
}
/* Sleep until uncongested or a write happens */
prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE);
ret = io_schedule_timeout(timeout);
finish_wait(wqh, &wait);
out:
trace_writeback_wait_iff_congested(jiffies_to_usecs(timeout),
jiffies_to_usecs(jiffies - start));
return ret;
}
/**
* mempool_alloc - allocate an element from a specific memory pool
* @pool: pointer to the memory pool which was allocated via
* mempool_create().
* @gfp_mask: the usual allocation bitmask.
*
* this function only sleeps if the alloc_fn() function sleeps or
* returns NULL. Note that due to preallocation, this function
* *never* fails when called from process contexts. (it might
* fail if called from an IRQ context.)
*/
void * mempool_alloc(mempool_t *pool, gfp_t gfp_mask)
{
void *element;
unsigned long flags;
wait_queue_t wait;
gfp_t gfp_temp;
#ifdef CONFIG_KRG_EPM
struct task_struct *krg_cur;
#endif
might_sleep_if(gfp_mask & __GFP_WAIT);
gfp_mask |= __GFP_NOMEMALLOC; /* don't allocate emergency reserves */
gfp_mask |= __GFP_NORETRY; /* don't loop in __alloc_pages */
gfp_mask |= __GFP_NOWARN; /* failures are OK */
gfp_temp = gfp_mask & ~(__GFP_WAIT|__GFP_IO);
repeat_alloc:
element = pool->alloc(gfp_temp, pool->pool_data);
if (likely(element != NULL))
return element;
spin_lock_irqsave(&pool->lock, flags);
if (likely(pool->curr_nr)) {
element = remove_element(pool);
spin_unlock_irqrestore(&pool->lock, flags);
return element;
}
spin_unlock_irqrestore(&pool->lock, flags);
/* We must not sleep in the GFP_ATOMIC case */
if (!(gfp_mask & __GFP_WAIT))
return NULL;
#ifdef CONFIG_KRG_EPM
krg_current_save(krg_cur);
#endif
/* Now start performing page reclaim */
gfp_temp = gfp_mask;
init_wait(&wait);
prepare_to_wait(&pool->wait, &wait, TASK_UNINTERRUPTIBLE);
smp_mb();
if (!pool->curr_nr) {
/*
* FIXME: this should be io_schedule(). The timeout is there
* as a workaround for some DM problems in 2.6.18.
*/
io_schedule_timeout(5*HZ);
}
finish_wait(&pool->wait, &wait);
#ifdef CONFIG_KRG_EPM
krg_current_restore(krg_cur);
#endif
goto repeat_alloc;
}
/**
* congestion_wait - wait for a backing_dev to become uncongested
* @rw: READ or WRITE
* @timeout: timeout in jiffies
*
* Waits for up to @timeout jiffies for a backing_dev (any backing_dev) to exit
* write congestion. If no backing_devs are congested then just wait for the
* next write to be completed.
*/
long congestion_wait(int rw, long timeout)
{
long ret;
DEFINE_WAIT(wait);
wait_queue_head_t *wqh = &congestion_wqh[rw];
prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE);
ret = io_schedule_timeout(timeout);
finish_wait(wqh, &wait);
return ret;
}
/**
* congestion_wait - wait for a backing_dev to become uncongested
* @sync: SYNC or ASYNC IO
* @timeout: timeout in jiffies
*
* Waits for up to @timeout jiffies for a backing_dev (any backing_dev) to exit
* write congestion. If no backing_devs are congested then just wait for the
* next write to be completed.
*/
long congestion_wait(int sync, long timeout)
{
long ret;
unsigned long start = jiffies;
DEFINE_WAIT(wait);
wait_queue_head_t *wqh = &congestion_wqh[sync];
prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE);
ret = io_schedule_timeout(timeout);
finish_wait(wqh, &wait);
trace_writeback_congestion_wait(jiffies_to_usecs(timeout),
jiffies_to_usecs(jiffies - start));
return ret;
}
/**
* wait_iff_congested - Conditionally wait for a backing_dev to become uncongested or a zone to complete writes
* @zone: A zone to check if it is heavily congested
* @sync: SYNC or ASYNC IO
* @timeout: timeout in jiffies
*
* In the event of a congested backing_dev (any backing_dev) and the given
* @zone has experienced recent congestion, this waits for up to @timeout
* jiffies for either a BDI to exit congestion of the given @sync queue
* or a write to complete.
*
* In the absence of zone congestion, a short sleep or a cond_resched is
* performed to yield the processor and to allow other subsystems to make
* a forward progress.
*
* The return value is 0 if the sleep is for the full timeout. Otherwise,
* it is the number of jiffies that were still remaining when the function
* returned. return_value == timeout implies the function did not sleep.
*/
long wait_iff_congested(struct zone *zone, int sync, long timeout)
{
long ret;
unsigned long start = jiffies;
DEFINE_WAIT(wait);
wait_queue_head_t *wqh = &congestion_wqh[sync];
/*
* If there is no congestion, or heavy congestion is not being
* encountered in the current zone, yield if necessary instead
* of sleeping on the congestion queue
*/
if (atomic_read(&nr_wb_congested[sync]) == 0 ||
!test_bit(ZONE_CONGESTED, &zone->flags)) {
/*
* Memory allocation/reclaim might be called from a WQ
* context and the current implementation of the WQ
* concurrency control doesn't recognize that a particular
* WQ is congested if the worker thread is looping without
* ever sleeping. Therefore we have to do a short sleep
* here rather than calling cond_resched().
*/
if (current->flags & PF_WQ_WORKER)
schedule_timeout_uninterruptible(1);
else
cond_resched();
/* In case we scheduled, work out time remaining */
ret = timeout - (jiffies - start);
if (ret < 0)
ret = 0;
goto out;
}
/* Sleep until uncongested or a write happens */
prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE);
ret = io_schedule_timeout(timeout);
finish_wait(wqh, &wait);
out:
trace_writeback_wait_iff_congested(jiffies_to_usecs(timeout),
jiffies_to_usecs(jiffies - start));
return ret;
}
/*
* 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 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();
}
/**
* mempool_alloc - allocate an element from a specific memory pool
* @pool: pointer to the memory pool which was allocated via
* mempool_create().
* @gfp_mask: the usual allocation bitmask.
*
* this function only sleeps if the alloc_fn() function sleeps or
* returns NULL. Note that due to preallocation, this function
* *never* fails when called from process contexts. (it might
* fail if called from an IRQ context.)
* Note: using __GFP_ZERO is not supported.
*/
void * mempool_alloc(mempool_t *pool, gfp_t gfp_mask)
{
void *element;
unsigned long flags;
wait_queue_t wait;
gfp_t gfp_temp;
VM_WARN_ON_ONCE(gfp_mask & __GFP_ZERO);
might_sleep_if(gfp_mask & __GFP_WAIT);
gfp_mask |= __GFP_NOMEMALLOC; /* don't allocate emergency reserves */
gfp_mask |= __GFP_NORETRY; /* don't loop in __alloc_pages */
gfp_mask |= __GFP_NOWARN; /* failures are OK */
gfp_temp = gfp_mask & ~(__GFP_WAIT|__GFP_IO);
repeat_alloc:
element = pool->alloc(gfp_temp, pool->pool_data);
if (likely(element != NULL))
return element;
spin_lock_irqsave(&pool->lock, flags);
if (likely(pool->curr_nr)) {
element = remove_element(pool);
spin_unlock_irqrestore(&pool->lock, flags);
/* paired with rmb in mempool_free(), read comment there */
smp_wmb();
/*
* Update the allocation stack trace as this is more useful
* for debugging.
*/
kmemleak_update_trace(element);
return element;
}
/*
* We use gfp mask w/o __GFP_WAIT or IO for the first round. If
* alloc failed with that and @pool was empty, retry immediately.
*/
if (gfp_temp != gfp_mask) {
spin_unlock_irqrestore(&pool->lock, flags);
gfp_temp = gfp_mask;
goto repeat_alloc;
}
/* We must not sleep if !__GFP_WAIT */
if (!(gfp_mask & __GFP_WAIT)) {
spin_unlock_irqrestore(&pool->lock, flags);
return NULL;
}
/* Let's wait for someone else to return an element to @pool */
init_wait(&wait);
prepare_to_wait(&pool->wait, &wait, TASK_UNINTERRUPTIBLE);
spin_unlock_irqrestore(&pool->lock, flags);
/*
* FIXME: this should be io_schedule(). The timeout is there as a
* workaround for some DM problems in 2.6.18.
*/
io_schedule_timeout(5*HZ);
finish_wait(&pool->wait, &wait);
goto repeat_alloc;
}
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();
}
/* _VMKLNX_CODECHECK_: mempool_alloc */
void * mempool_alloc(mempool_t *pool, gfp_t gfp_mask)
{
void *element;
unsigned long flags;
wait_queue_t wait;
gfp_t gfp_temp;
#if defined(__VMKLNX__)
VMK_ASSERT(vmk_PreemptionIsEnabled() == VMK_FALSE);
#endif
might_sleep_if(gfp_mask & __GFP_WAIT);
gfp_mask |= __GFP_NOMEMALLOC; /* don't allocate emergency reserves */
gfp_mask |= __GFP_NORETRY; /* don't loop in __alloc_pages */
gfp_mask |= __GFP_NOWARN; /* failures are OK */
gfp_temp = gfp_mask & ~(__GFP_WAIT|__GFP_IO);
#if defined(__VMKLNX__) && defined(VMX86_DEBUG)
if (gfp_mask & __GFP_WAIT) {
vmk_WorldAssertIsSafeToBlock();
}
#endif /* defined(__VMKLNX__) */
repeat_alloc:
#if defined(__VMKLNX__)
VMKAPI_MODULE_CALL(pool->module_id, element, pool->alloc,
gfp_temp, pool->pool_data);
#else /* !defined(__VMKLNX__) */
element = pool->alloc(gfp_temp, pool->pool_data);
#endif /* defined(__VMKLNX__) */
if (likely(element != NULL))
return element;
spin_lock_irqsave(&pool->lock, flags);
if (likely(pool->curr_nr)) {
element = remove_element(pool);
spin_unlock_irqrestore(&pool->lock, flags);
return element;
}
spin_unlock_irqrestore(&pool->lock, flags);
/* We must not sleep in the GFP_ATOMIC case */
if (!(gfp_mask & __GFP_WAIT))
return NULL;
/* Now start performing page reclaim */
gfp_temp = gfp_mask;
init_wait(&wait);
prepare_to_wait(&pool->wait, &wait, TASK_UNINTERRUPTIBLE);
smp_mb();
if (!pool->curr_nr) {
/*
* FIXME: this should be io_schedule(). The timeout is there
* as a workaround for some DM problems in 2.6.18.
*/
#if defined(__VMKLNX__)
schedule_timeout(5*HZ);
#else /* !defined(__VMKLNX__) */
io_schedule_timeout(5*HZ);
#endif /* defined(__VMKLNX__) */
}
finish_wait(&pool->wait, &wait);
goto repeat_alloc;
}
