/*
* For strictlimit case, calculations above were based on wb counters
* and limits (starting from pos_ratio = wb_position_ratio() and up to
* balanced_dirty_ratelimit = task_ratelimit * write_bw / dirty_rate).
* Hence, to calculate "step" properly, we have to use wb_dirty as
* "dirty" and wb_setpoint as "setpoint".
*
* We rampup dirty_ratelimit forcibly if wb_dirty is low because
* it's possible that wb_thresh is close to zero due to inactivity
* of backing device.
*/
if (unlikely(wb->bdi->capabilities & BDI_CAP_STRICTLIMIT)) {
dirty = dtc->wb_dirty;
if (dtc->wb_dirty < 8)
setpoint = dtc->wb_dirty + 1;
else
setpoint = (dtc->wb_thresh + dtc->wb_bg_thresh) / 2;
}
if (dirty < setpoint) {
x = min3(wb->balanced_dirty_ratelimit,
balanced_dirty_ratelimit, task_ratelimit);
if (dirty_ratelimit < x)
step = x - dirty_ratelimit;
} else {
x = max3(wb->balanced_dirty_ratelimit,
balanced_dirty_ratelimit, task_ratelimit);
if (dirty_ratelimit > x)
step = dirty_ratelimit - x;
}
/*
* Don't pursue 100% rate matching. It's impossible since the balanced
* rate itself is constantly fluctuating. So decrease the track speed
* when it gets close to the target. Helps eliminate pointless tremors.
*/
step >>= dirty_ratelimit / (2 * step + 1);
/*
* Limit the tracking speed to avoid overshooting.
*/
step = (step + 7) / 8;
if (dirty_ratelimit < balanced_dirty_ratelimit)
dirty_ratelimit += step;
else
dirty_ratelimit -= step;
wb->dirty_ratelimit = max(dirty_ratelimit, 1UL);
wb->balanced_dirty_ratelimit = balanced_dirty_ratelimit;
trace_bdi_dirty_ratelimit(wb->bdi, dirty_rate, task_ratelimit);
}
static void __wb_update_bandwidth(struct dirty_throttle_control *gdtc,
struct dirty_throttle_control *mdtc,
unsigned long start_time,
bool update_ratelimit)
{
struct bdi_writeback *wb = gdtc->wb;
unsigned long now = jiffies;
unsigned long elapsed = now - wb->bw_time_stamp;
unsigned long dirtied;
unsigned long written;
lockdep_assert_held(&wb->list_lock);
/*
* rate-limit, only update once every 200ms.
*/
if (elapsed < BANDWIDTH_INTERVAL)
return;
dirtied = percpu_counter_read(&wb->stat[WB_DIRTIED]);
written = percpu_counter_read(&wb->stat[WB_WRITTEN]);
/*
* Skip quiet periods when disk bandwidth is under-utilized.
* (at least 1s idle time between two flusher runs)
*/
if (elapsed > HZ && time_before(wb->bw_time_stamp, start_time))
goto snapshot;
if (update_ratelimit) {
domain_update_bandwidth(gdtc, now);
wb_update_dirty_ratelimit(gdtc, dirtied, elapsed);
/*
* @mdtc is always NULL if !CGROUP_WRITEBACK but the
* compiler has no way to figure that out. Help it.
*/
if (IS_ENABLED(CONFIG_CGROUP_WRITEBACK) && mdtc) {
domain_update_bandwidth(mdtc, now);
wb_update_dirty_ratelimit(mdtc, dirtied, elapsed);
}
}
wb_update_write_bandwidth(wb, elapsed, written);
snapshot:
wb->dirtied_stamp = dirtied;
wb->written_stamp = written;
wb->bw_time_stamp = now;
}
void wb_update_bandwidth(struct bdi_writeback *wb, unsigned long start_time)
{
struct dirty_throttle_control gdtc = { GDTC_INIT(wb) };
__wb_update_bandwidth(&gdtc, NULL, start_time, false);
}
/*
* After a task dirtied this many pages, balance_dirty_pages_ratelimited()
* will look to see if it needs to start dirty throttling.
*
* If dirty_poll_interval is too low, big NUMA machines will call the expensive
* global_page_state() too often. So scale it near-sqrt to the safety margin
* (the number of pages we may dirty without exceeding the dirty limits).
*/
static unsigned long dirty_poll_interval(unsigned long dirty,
unsigned long thresh)
{
if (thresh > dirty)
return 1UL << (ilog2(thresh - dirty) >> 1);
return 1;
}
static unsigned long wb_max_pause(struct bdi_writeback *wb,
unsigned long wb_dirty)
{
unsigned long bw = wb->avg_write_bandwidth;
unsigned long t;
/*
* Limit pause time for small memory systems. If sleeping for too long
* time, a small pool of dirty/writeback pages may go empty and disk go
* idle.
*
* 8 serves as the safety ratio.
*/
t = wb_dirty / (1 + bw / roundup_pow_of_two(1 + HZ / 8));
t++;
return min_t(unsigned long, t, MAX_PAUSE);
}
static long wb_min_pause(struct bdi_writeback *wb,
long max_pause,
unsigned long task_ratelimit,
unsigned long dirty_ratelimit,
int *nr_dirtied_pause)
{
long hi = ilog2(wb->avg_write_bandwidth);
long lo = ilog2(wb->dirty_ratelimit);
long t; /* target pause */
long pause; /* estimated next pause */
int pages; /* target nr_dirtied_pause */
/* target for 10ms pause on 1-dd case */
t = max(1, HZ / 100);
/*
* Scale up pause time for concurrent dirtiers in order to reduce CPU
* overheads.
*
* (N * 10ms) on 2^N concurrent tasks.
*/
if (hi > lo)
t += (hi - lo) * (10 * HZ) / 1024;
/*
* This is a bit convoluted. We try to base the next nr_dirtied_pause
* on the much more stable dirty_ratelimit. However the next pause time
* will be computed based on task_ratelimit and the two rate limits may
* depart considerably at some time. Especially if task_ratelimit goes
* below dirty_ratelimit/2 and the target pause is max_pause, the next
* pause time will be max_pause*2 _trimmed down_ to max_pause. As a
* result task_ratelimit won't be executed faithfully, which could
* eventually bring down dirty_ratelimit.
*
* We apply two rules to fix it up:
* 1) try to estimate the next pause time and if necessary, use a lower
* nr_dirtied_pause so as not to exceed max_pause. When this happens,
* nr_dirtied_pause will be "dancing" with task_ratelimit.
* 2) limit the target pause time to max_pause/2, so that the normal
* small fluctuations of task_ratelimit won't trigger rule (1) and
* nr_dirtied_pause will remain as stable as dirty_ratelimit.
*/
t = min(t, 1 + max_pause / 2);
pages = dirty_ratelimit * t / roundup_pow_of_two(HZ);
/*
* Tiny nr_dirtied_pause is found to hurt I/O performance in the test
* case fio-mmap-randwrite-64k, which does 16*{sync read, async write}.
* When the 16 consecutive reads are often interrupted by some dirty
* throttling pause during the async writes, cfq will go into idles
* (deadline is fine). So push nr_dirtied_pause as high as possible
* until reaches DIRTY_POLL_THRESH=32 pages.
*/
if (pages < DIRTY_POLL_THRESH) {
t = max_pause;
pages = dirty_ratelimit * t / roundup_pow_of_two(HZ);
if (pages > DIRTY_POLL_THRESH) {
pages = DIRTY_POLL_THRESH;
t = HZ * DIRTY_POLL_THRESH / dirty_ratelimit;
}
}
pause = HZ * pages / (task_ratelimit + 1);
if (pause > max_pause) {
t = max_pause;
pages = task_ratelimit * t / roundup_pow_of_two(HZ);
}
*nr_dirtied_pause = pages;
/*
* The minimal pause time will normally be half the target pause time.
*/
return pages >= DIRTY_POLL_THRESH ? 1 + t / 2 : t;
}
static inline void wb_dirty_limits(struct dirty_throttle_control *dtc)
{
struct bdi_writeback *wb = dtc->wb;
unsigned long wb_reclaimable;
/*
* wb_thresh is not treated as some limiting factor as
* dirty_thresh, due to reasons
* - in JBOD setup, wb_thresh can fluctuate a lot
* - in a system with HDD and USB key, the USB key may somehow
* go into state (wb_dirty >> wb_thresh) either because
* wb_dirty starts high, or because wb_thresh drops low.
* In this case we don't want to hard throttle the USB key
* dirtiers for 100 seconds until wb_dirty drops under
* wb_thresh. Instead the auxiliary wb control line in
* wb_position_ratio() will let the dirtier task progress
* at some rate <= (write_bw / 2) for bringing down wb_dirty.
*/
dtc->wb_thresh = __wb_calc_thresh(dtc);
dtc->wb_bg_thresh = dtc->thresh ?
div_u64((u64)dtc->wb_thresh * dtc->bg_thresh, dtc->thresh) : 0;
/*
* 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 (dtc->wb_thresh < 2 * wb_stat_error(wb)) {
wb_reclaimable = wb_stat_sum(wb, WB_RECLAIMABLE);
dtc->wb_dirty = wb_reclaimable + wb_stat_sum(wb, WB_WRITEBACK);
} else {
wb_reclaimable = wb_stat(wb, WB_RECLAIMABLE);
dtc->wb_dirty = wb_reclaimable + wb_stat(wb, WB_WRITEBACK);
}
}
/*
* 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 wait once crossing the (background_thresh + dirty_thresh) / 2.
* 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,
struct bdi_writeback *wb,
unsigned long pages_dirtied)
{
struct dirty_throttle_control gdtc_stor = { GDTC_INIT(wb) };
struct dirty_throttle_control mdtc_stor = { MDTC_INIT(wb, &gdtc_stor) };
struct dirty_throttle_control * const gdtc = &gdtc_stor;
struct dirty_throttle_control * const mdtc = mdtc_valid(&mdtc_stor) ?
&mdtc_stor : NULL;
struct dirty_throttle_control *sdtc;
unsigned long nr_reclaimable; /* = file_dirty + unstable_nfs */
long period;
long pause;
long max_pause;
long min_pause;
int nr_dirtied_pause;
bool dirty_exceeded = false;
unsigned long task_ratelimit;
unsigned long dirty_ratelimit;
struct backing_dev_info *bdi = wb->bdi;
bool strictlimit = bdi->capabilities & BDI_CAP_STRICTLIMIT;
unsigned long start_time = jiffies;
for (;;) {
unsigned long now = jiffies;
unsigned long dirty, thresh, bg_thresh;
unsigned long m_dirty, m_thresh, m_bg_thresh;
/*
* 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.
*/
nr_reclaimable = global_page_state(NR_FILE_DIRTY) +
global_page_state(NR_UNSTABLE_NFS);
gdtc->avail = global_dirtyable_memory();
gdtc->dirty = nr_reclaimable + global_page_state(NR_WRITEBACK);
domain_dirty_limits(gdtc);
if (unlikely(strictlimit)) {
wb_dirty_limits(gdtc);
dirty = gdtc->wb_dirty;
thresh = gdtc->wb_thresh;
bg_thresh = gdtc->wb_bg_thresh;
} else {
dirty = gdtc->dirty;
thresh = gdtc->thresh;
bg_thresh = gdtc->bg_thresh;
}
if (mdtc) {
unsigned long writeback;
/*
* If @wb belongs to !root memcg, repeat the same
* basic calculations for the memcg domain.
*/
mem_cgroup_wb_stats(wb, &mdtc->avail, &mdtc->dirty,
&writeback);
mdtc_cap_avail(mdtc);
mdtc->dirty += writeback;
domain_dirty_limits(mdtc);
if (unlikely(strictlimit)) {
wb_dirty_limits(mdtc);
m_dirty = mdtc->wb_dirty;
m_thresh = mdtc->wb_thresh;
m_bg_thresh = mdtc->wb_bg_thresh;
} else {
m_dirty = mdtc->dirty;
m_thresh = mdtc->thresh;
m_bg_thresh = mdtc->bg_thresh;
}
}
/*
* Throttle it only when the background writeback cannot
* catch-up. This avoids (excessively) small writeouts
* when the wb limits are ramping up in case of !strictlimit.
*
* In strictlimit case make decision based on the wb counters
* and limits. Small writeouts when the wb limits are ramping
* up are the price we consciously pay for strictlimit-ing.
*
* If memcg domain is in effect, @dirty should be under
* both global and memcg freerun ceilings.
*/
if (dirty <= dirty_freerun_ceiling(thresh, bg_thresh) &&
(!mdtc ||
m_dirty <= dirty_freerun_ceiling(m_thresh, m_bg_thresh))) {
unsigned long intv = dirty_poll_interval(dirty, thresh);
unsigned long m_intv = ULONG_MAX;
current->dirty_paused_when = now;
current->nr_dirtied = 0;
if (mdtc)
m_intv = dirty_poll_interval(m_dirty, m_thresh);
current->nr_dirtied_pause = min(intv, m_intv);
break;
}
if (unlikely(!writeback_in_progress(wb)))
wb_start_background_writeback(wb);
/*
* Calculate global domain's pos_ratio and select the
* global dtc by default.
*/
if (!strictlimit)
wb_dirty_limits(gdtc);
dirty_exceeded = (gdtc->wb_dirty > gdtc->wb_thresh) &&
((gdtc->dirty > gdtc->thresh) || strictlimit);
wb_position_ratio(gdtc);
sdtc = gdtc;
if (mdtc) {
/*
* If memcg domain is in effect, calculate its
* pos_ratio. @wb should satisfy constraints from
* both global and memcg domains. Choose the one
* w/ lower pos_ratio.
*/
if (!strictlimit)
wb_dirty_limits(mdtc);
dirty_exceeded |= (mdtc->wb_dirty > mdtc->wb_thresh) &&
((mdtc->dirty > mdtc->thresh) || strictlimit);
wb_position_ratio(mdtc);
if (mdtc->pos_ratio < gdtc->pos_ratio)
sdtc = mdtc;
}
if (dirty_exceeded && !wb->dirty_exceeded)
wb->dirty_exceeded = 1;
if (time_is_before_jiffies(wb->bw_time_stamp +
BANDWIDTH_INTERVAL)) {
spin_lock(&wb->list_lock);
__wb_update_bandwidth(gdtc, mdtc, start_time, true);
spin_unlock(&wb->list_lock);
}
/* throttle according to the chosen dtc */
dirty_ratelimit = wb->dirty_ratelimit;
task_ratelimit = ((u64)dirty_ratelimit * sdtc->pos_ratio) >>
RATELIMIT_CALC_SHIFT;
max_pause = wb_max_pause(wb, sdtc->wb_dirty);
min_pause = wb_min_pause(wb, max_pause,
task_ratelimit, dirty_ratelimit,
&nr_dirtied_pause);
if (unlikely(task_ratelimit == 0)) {
period = max_pause;
pause = max_pause;
goto pause;
}
period = HZ * pages_dirtied / task_ratelimit;
pause = period;
if (current->dirty_paused_when)
pause -= now - current->dirty_paused_when;
/*
* For less than 1s think time (ext3/4 may block the dirtier
* for up to 800ms from time to time on 1-HDD; so does xfs,
* however at much less frequency), try to compensate it in
* future periods by updating the virtual time; otherwise just
* do a reset, as it may be a light dirtier.
*/
if (pause < min_pause) {
trace_balance_dirty_pages(bdi,
sdtc->thresh,
sdtc->bg_thresh,
sdtc->dirty,
sdtc->wb_thresh,
sdtc->wb_dirty,
dirty_ratelimit,
task_ratelimit,
pages_dirtied,
period,
min(pause, 0L),
start_time);
if (pause < -HZ) {
current->dirty_paused_when = now;
current->nr_dirtied = 0;
} else if (period) {
current->dirty_paused_when += period;
current->nr_dirtied = 0;
} else if (current->nr_dirtied_pause <= pages_dirtied)
current->nr_dirtied_pause += pages_dirtied;
break;
}
if (unlikely(pause > max_pause)) {
/* for occasional dropped task_ratelimit */
now += min(pause - max_pause, max_pause);
pause = max_pause;
}
pause:
trace_balance_dirty_pages(bdi,
sdtc->thresh,
sdtc->bg_thresh,
sdtc->dirty,
sdtc->wb_thresh,
sdtc->wb_dirty,
dirty_ratelimit,
task_ratelimit,
pages_dirtied,
period,
pause,
start_time);
__set_current_state(TASK_KILLABLE);
io_schedule_timeout(pause);
current->dirty_paused_when = now + pause;
current->nr_dirtied = 0;
current->nr_dirtied_pause = nr_dirtied_pause;
/*
* This is typically equal to (dirty < thresh) and can also
* keep "1000+ dd on a slow USB stick" under control.
*/
if (task_ratelimit)
break;
/*
* In the case of an unresponding NFS server and the NFS dirty
* pages exceeds dirty_thresh, give the other good wb's a pipe
* to go through, so that tasks on them still remain responsive.
*
* In theory 1 page is enough to keep the comsumer-producer
* pipe going: the flusher cleans 1 page => the task dirties 1
* more page. However wb_dirty has accounting errors. So use
* the larger and more IO friendly wb_stat_error.
*/
if (sdtc->wb_dirty <= wb_stat_error(wb))
break;
if (fatal_signal_pending(current))
break;
}
if (!dirty_exceeded && wb->dirty_exceeded)
wb->dirty_exceeded = 0;
if (writeback_in_progress(wb))
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)
return;
if (nr_reclaimable > gdtc->bg_thresh)
wb_start_background_writeback(wb);
}
static DEFINE_PER_CPU(int, bdp_ratelimits);
/*
* Normal tasks are throttled by
* loop {
* dirty tsk->nr_dirtied_pause pages;
* take a snap in balance_dirty_pages();
* }
* However there is a worst case. If every task exit immediately when dirtied
* (tsk->nr_dirtied_pause - 1) pages, balance_dirty_pages() will never be
* called to throttle the page dirties. The solution is to save the not yet
* throttled page dirties in dirty_throttle_leaks on task exit and charge them
* randomly into the running tasks. This works well for the above worst case,
* as the new task will pick up and accumulate the old task's leaked dirty
* count and eventually get throttled.
*/
DEFINE_PER_CPU(int, dirty_throttle_leaks) = 0;
/**
* balance_dirty_pages_ratelimited - balance dirty memory state
* @mapping: address_space which was 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(struct address_space *mapping)
{
struct inode *inode = mapping->host;
struct backing_dev_info *bdi = inode_to_bdi(inode);
struct bdi_writeback *wb = NULL;
int ratelimit;
int *p;
if (!bdi_cap_account_dirty(bdi))
return;
if (inode_cgwb_enabled(inode))
wb = wb_get_create_current(bdi, GFP_KERNEL);
if (!wb)
wb = &bdi->wb;
ratelimit = current->nr_dirtied_pause;
if (wb->dirty_exceeded)
ratelimit = min(ratelimit, 32 >> (PAGE_SHIFT - 10));
preempt_disable();
/*
* This prevents one CPU to accumulate too many dirtied pages without
* calling into balance_dirty_pages(), which can happen when there are
* 1000+ tasks, all of them start dirtying pages at exactly the same
* time, hence all honoured too large initial task->nr_dirtied_pause.
*/
p = this_cpu_ptr(&bdp_ratelimits);
if (unlikely(current->nr_dirtied >= ratelimit))
*p = 0;
else if (unlikely(*p >= ratelimit_pages)) {
*p = 0;
ratelimit = 0;
}
/*
* Pick up the dirtied pages by the exited tasks. This avoids lots of
* short-lived tasks (eg. gcc invocations in a kernel build) escaping
* the dirty throttling and livelock other long-run dirtiers.
*/
p = this_cpu_ptr(&dirty_throttle_leaks);
if (*p > 0 && current->nr_dirtied < ratelimit) {
unsigned long nr_pages_dirtied;
nr_pages_dirtied = min(*p, ratelimit - current->nr_dirtied);
*p -= nr_pages_dirtied;
current->nr_dirtied += nr_pages_dirtied;
}
preempt_enable();
if (unlikely(current->nr_dirtied >= ratelimit))
balance_dirty_pages(mapping, wb, current->nr_dirtied);
wb_put(wb);
}
EXPORT_SYMBOL(balance_dirty_pages_ratelimited);
/**
* wb_over_bg_thresh - does @wb need to be written back?
* @wb: bdi_writeback of interest
*
* Determines whether background writeback should keep writing @wb or it's
* clean enough. Returns %true if writeback should continue.
*/
bool wb_over_bg_thresh(struct bdi_writeback *wb)
{
struct dirty_throttle_control gdtc_stor = { GDTC_INIT(wb) };
struct dirty_throttle_control mdtc_stor = { MDTC_INIT(wb, &gdtc_stor) };
struct dirty_throttle_control * const gdtc = &gdtc_stor;
struct dirty_throttle_control * const mdtc = mdtc_valid(&mdtc_stor) ?
&mdtc_stor : NULL;
/*
* Similar to balance_dirty_pages() but ignores pages being written
* as we're trying to decide whether to put more under writeback.
*/
gdtc->avail = global_dirtyable_memory();
gdtc->dirty = global_page_state(NR_FILE_DIRTY) +
global_page_state(NR_UNSTABLE_NFS);
domain_dirty_limits(gdtc);
if (gdtc->dirty > gdtc->bg_thresh)
return true;
if (wb_stat(wb, WB_RECLAIMABLE) > __wb_calc_thresh(gdtc))
return true;
if (mdtc) {
unsigned long writeback;
mem_cgroup_wb_stats(wb, &mdtc->avail, &mdtc->dirty, &writeback);
mdtc_cap_avail(mdtc);
domain_dirty_limits(mdtc); /* ditto, ignore writeback */
if (mdtc->dirty > mdtc->bg_thresh)
return true;
if (wb_stat(wb, WB_RECLAIMABLE) > __wb_calc_thresh(mdtc))
return true;
}
return false;
}
void throttle_vm_writeout(gfp_t gfp_mask)
{
unsigned long background_thresh;
unsigned long dirty_thresh;
for ( ; ; ) {
global_dirty_limits(&background_thresh, &dirty_thresh);
dirty_thresh = hard_dirty_limit(&global_wb_domain, 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;
}
}
/*
* sysctl handler for /proc/sys/vm/dirty_writeback_centisecs
*/
int dirty_writeback_centisecs_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *length, loff_t *ppos)
{
proc_dointvec(table, write, buffer, length, ppos);
return 0;
}
#ifdef CONFIG_BLOCK
void laptop_mode_timer_fn(unsigned long data)
{
struct request_queue *q = (struct request_queue *)data;
int nr_pages = global_page_state(NR_FILE_DIRTY) +
global_page_state(NR_UNSTABLE_NFS);
struct bdi_writeback *wb;
struct wb_iter iter;
/*
* We want to write everything out, not just down to the dirty
* threshold
*/
if (!bdi_has_dirty_io(&q->backing_dev_info))
return;
bdi_for_each_wb(wb, &q->backing_dev_info, &iter, 0)
if (wb_has_dirty_io(wb))
wb_start_writeback(wb, nr_pages, true,
WB_REASON_LAPTOP_TIMER);
}
/*
* We've spun up the disk and we're in laptop mode: schedule writeback
* of all dirty data a few seconds from now. If the flush is already scheduled
* then push it back - the user is still using the disk.
*/
void laptop_io_completion(struct backing_dev_info *info)
{
mod_timer(&info->laptop_mode_wb_timer, jiffies + laptop_mode);
}
/*
* We're in laptop mode and we've just synced. The sync's writes will have
* caused another writeback to be scheduled by laptop_io_completion.
* Nothing needs to be written back anymore, so we unschedule the writeback.
*/
void laptop_sync_completion(void)
{
struct backing_dev_info *bdi;
rcu_read_lock();
list_for_each_entry_rcu(bdi, &bdi_list, bdi_list)
del_timer(&bdi->laptop_mode_wb_timer);
rcu_read_unlock();
}
#endif
/*
* If ratelimit_pages is too high then we can get into dirty-data overload
* if a large number of processes all perform writes at the same time.
* If it is too low then SMP machines will call the (expensive)
* get_writeback_state too often.
*
* Here we set ratelimit_pages to a level which ensures that when all CPUs are
* dirtying in parallel, we cannot go more than 3% (1/32) over the dirty memory
* thresholds.
*/
void writeback_set_ratelimit(void)
{
struct wb_domain *dom = &global_wb_domain;
unsigned long background_thresh;
unsigned long dirty_thresh;
global_dirty_limits(&background_thresh, &dirty_thresh);
dom->dirty_limit = dirty_thresh;
ratelimit_pages = dirty_thresh / (num_online_cpus() * 32);
if (ratelimit_pages < 16)
ratelimit_pages = 16;
}
static int
ratelimit_handler(struct notifier_block *self, unsigned long action,
void *hcpu)
{
switch (action & ~CPU_TASKS_FROZEN) {
case CPU_ONLINE:
case CPU_DEAD:
writeback_set_ratelimit();
return NOTIFY_OK;
default:
return NOTIFY_DONE;
}
}
static struct notifier_block ratelimit_nb = {
.notifier_call = ratelimit_handler,
.next = NULL,
};
/*
* Called early on to tune the page writeback dirty limits.
*
* We used to scale dirty pages according to how total memory
* related to pages that could be allocated for buffers (by
* comparing nr_free_buffer_pages() to vm_total_pages.
*
* However, that was when we used "dirty_ratio" to scale with
* all memory, and we don't do that any more. "dirty_ratio"
* is now applied to total non-HIGHPAGE memory (by subtracting
* totalhigh_pages from vm_total_pages), and as such we can't
* get into the old insane situation any more where we had
* large amounts of dirty pages compared to a small amount of
* non-HIGHMEM memory.
*
* But we might still want to scale the dirty_ratio by how
* much memory the box has..
*/
void __init page_writeback_init(void)
{
BUG_ON(wb_domain_init(&global_wb_domain, GFP_KERNEL));
writeback_set_ratelimit();
register_cpu_notifier(&ratelimit_nb);
}
/**
* tag_pages_for_writeback - tag pages to be written by write_cache_pages
* @mapping: address space structure to write
* @start: starting page index
* @end: ending page index (inclusive)
*
* This function scans the page range from @start to @end (inclusive) and tags
* all pages that have DIRTY tag set with a special TOWRITE tag. The idea is
* that write_cache_pages (or whoever calls this function) will then use
* TOWRITE tag to identify pages eligible for writeback. This mechanism is
* used to avoid livelocking of writeback by a process steadily creating new
* dirty pages in the file (thus it is important for this function to be quick
* so that it can tag pages faster than a dirtying process can create them).
*/
/*
* We tag pages in batches of WRITEBACK_TAG_BATCH to reduce tree_lock latency.
*/
void tag_pages_for_writeback(struct address_space *mapping,
pgoff_t start, pgoff_t end)
{
#define WRITEBACK_TAG_BATCH 4096
unsigned long tagged;
do {
spin_lock_irq(&mapping->tree_lock);
tagged = radix_tree_range_tag_if_tagged(&mapping->page_tree,
&start, end, WRITEBACK_TAG_BATCH,
PAGECACHE_TAG_DIRTY, PAGECACHE_TAG_TOWRITE);
spin_unlock_irq(&mapping->tree_lock);
WARN_ON_ONCE(tagged > WRITEBACK_TAG_BATCH);
cond_resched();
/* We check 'start' to handle wrapping when end == ~0UL */
} while (tagged >= WRITEBACK_TAG_BATCH && start);
}
EXPORT_SYMBOL(tag_pages_for_writeback);
/**
* write_cache_pages - walk the list of dirty pages of the given address space and write all of them.
* @mapping: address space structure to write
* @wbc: subtract the number of written pages from *@wbc->nr_to_write
* @writepage: function called for each page
* @data: data passed to writepage function
*
* If a page is already under I/O, write_cache_pages() skips it, even
* if it's dirty. This is desirable behaviour for memory-cleaning writeback,
* but it is INCORRECT for data-integrity system calls such as fsync(). fsync()
* and msync() need to guarantee that all the data which was dirty at the time
* the call was made get new I/O started against them. If wbc->sync_mode is
* WB_SYNC_ALL then we were called for data integrity and we must wait for
* existing IO to complete.
*
* To avoid livelocks (when other process dirties new pages), we first tag
* pages which should be written back with TOWRITE tag and only then start
* writing them. For data-integrity sync we have to be careful so that we do
* not miss some pages (e.g., because some other process has cleared TOWRITE
* tag we set). The rule we follow is that TOWRITE tag can be cleared only
* by the process clearing the DIRTY tag (and submitting the page for IO).
*/
int write_cache_pages(struct address_space *mapping,
struct writeback_control *wbc, writepage_t writepage,
void *data)
{
int ret = 0;
int done = 0;
struct pagevec pvec;
int nr_pages;
pgoff_t uninitialized_var(writeback_index);
pgoff_t index;
pgoff_t end; /* Inclusive */
pgoff_t done_index;
int cycled;
int range_whole = 0;
int tag;
pagevec_init(&pvec, 0);
if (wbc->range_cyclic) {
writeback_index = mapping->writeback_index; /* prev offset */
index = writeback_index;
if (index == 0)
cycled = 1;
else
cycled = 0;
end = -1;
} else {
index = wbc->range_start >> PAGE_CACHE_SHIFT;
end = wbc->range_end >> PAGE_CACHE_SHIFT;
if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
range_whole = 1;
cycled = 1; /* ignore range_cyclic tests */
}
if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
tag = PAGECACHE_TAG_TOWRITE;
else
tag = PAGECACHE_TAG_DIRTY;
retry:
if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
tag_pages_for_writeback(mapping, index, end);
done_index = index;
while (!done && (index <= end)) {
int i;
nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, tag,
min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1);
if (nr_pages == 0)
break;
for (i = 0; i < nr_pages; i++) {
struct page *page = pvec.pages[i];
/*
* At this point, the page may be truncated or
* invalidated (changing page->mapping to NULL), or
* even swizzled back from swapper_space to tmpfs file
* mapping. However, page->index will not change
* because we have a reference on the page.
*/
if (page->index > end) {
/*
* can't be range_cyclic (1st pass) because
* end == -1 in that case.
*/
done = 1;
break;
}
done_index = page->index;
lock_page(page);
/*
* Page truncated or invalidated. We can freely skip it
* then, even for data integrity operations: the page
* has disappeared concurrently, so there could be no
* real expectation of this data interity operation
* even if there is now a new, dirty page at the same
* pagecache address.
*/
if (unlikely(page->mapping != mapping)) {
continue_unlock:
unlock_page(page);
continue;
}
if (!PageDirty(page)) {
/* someone wrote it for us */
goto continue_unlock;
}
if (PageWriteback(page)) {
if (wbc->sync_mode != WB_SYNC_NONE)
wait_on_page_writeback(page);
else
goto continue_unlock;
}
BUG_ON(PageWriteback(page));
if (!clear_page_dirty_for_io(page))
goto continue_unlock;
trace_wbc_writepage(wbc, inode_to_bdi(mapping->host));
ret = (*writepage)(page, wbc, data);
if (unlikely(ret)) {
if (ret == AOP_WRITEPAGE_ACTIVATE) {
unlock_page(page);
ret = 0;
} else {
/*
* done_index is set past this page,
* so media errors will not choke
* background writeout for the entire
* file. This has consequences for
* range_cyclic semantics (ie. it may
* not be suitable for data integrity
* writeout).
*/
done_index = page->index + 1;
done = 1;
break;
}
}
/*
* We stop writing back only if we are not doing
* integrity sync. In case of integrity sync we have to
* keep going until we have written all the pages
* we tagged for writeback prior to entering this loop.
*/
if (--wbc->nr_to_write <= 0 &&
wbc->sync_mode == WB_SYNC_NONE) {
done = 1;
break;
}
}
pagevec_release(&pvec);
cond_resched();
}
if (!cycled && !done) {
/*
* range_cyclic:
* We hit the last page and there is more work to be done: wrap
* back to the start of the file
*/
cycled = 1;
index = 0;
end = writeback_index - 1;
goto retry;
}
if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
mapping->writeback_index = done_index;
return ret;
}
EXPORT_SYMBOL(write_cache_pages);
/*
* Function used by generic_writepages to call the real writepage
* function and set the mapping flags on error
*/
static int __writepage(struct page *page, struct writeback_control *wbc,
void *data)
{
struct address_space *mapping = data;
int ret = mapping->a_ops->writepage(page, wbc);
mapping_set_error(mapping, ret);
return ret;
}
/**
* generic_writepages - walk the list of dirty pages of the given address space and writepage() all of them.
* @mapping: address space structure to write
* @wbc: subtract the number of written pages from *@wbc->nr_to_write
*
* This is a library function, which implements the writepages()
* address_space_operation.
*/
int generic_writepages(struct address_space *mapping,
struct writeback_control *wbc)
{
struct blk_plug plug;
int ret;
/* deal with chardevs and other special file */
if (!mapping->a_ops->writepage)
return 0;
blk_start_plug(&plug);
ret = write_cache_pages(mapping, wbc, __writepage, mapping);
blk_finish_plug(&plug);
return ret;
}
EXPORT_SYMBOL(generic_writepages);
int do_writepages(struct address_space *mapping, struct writeback_control *wbc)
{
int ret;
if (wbc->nr_to_write <= 0)
return 0;
if (mapping->a_ops->writepages)
ret = mapping->a_ops->writepages(mapping, wbc);
else
ret = generic_writepages(mapping, wbc);
return ret;
}
/**
* write_one_page - write out a single page and optionally wait on I/O
* @page: the page to write
* @wait: if true, wait on writeout
*
* The page must be locked by the caller and will be unlocked upon return.
*
* write_one_page() returns a negative error code if I/O failed.
*/
int write_one_page(struct page *page, int wait)
{
struct address_space *mapping = page->mapping;
int ret = 0;
struct writeback_control wbc = {
.sync_mode = WB_SYNC_ALL,
.nr_to_write = 1,
};
BUG_ON(!PageLocked(page));
if (wait)
wait_on_page_writeback(page);
if (clear_page_dirty_for_io(page)) {
page_cache_get(page);
ret = mapping->a_ops->writepage(page, &wbc);
if (ret == 0 && wait) {
wait_on_page_writeback(page);
if (PageError(page))
ret = -EIO;
}
page_cache_release(page);
} else {
unlock_page(page);
}
return ret;
}
EXPORT_SYMBOL(write_one_page);
/*
* For address_spaces which do not use buffers nor write back.
*/
int __set_page_dirty_no_writeback(struct page *page)
{
if (!PageDirty(page))
return !TestSetPageDirty(page);
return 0;
}
/*
* Helper function for set_page_dirty family.
*
* Caller must hold mem_cgroup_begin_page_stat().
*
* NOTE: This relies on being atomic wrt interrupts.
*/
void account_page_dirtied(struct page *page, struct address_space *mapping,
struct mem_cgroup *memcg)
{
struct inode *inode = mapping->host;
trace_writeback_dirty_page(page, mapping);
if (mapping_cap_account_dirty(mapping)) {
struct bdi_writeback *wb;
inode_attach_wb(inode, page);
wb = inode_to_wb(inode);
mem_cgroup_inc_page_stat(memcg, MEM_CGROUP_STAT_DIRTY);
__inc_zone_page_state(page, NR_FILE_DIRTY);
__inc_zone_page_state(page, NR_DIRTIED);
__inc_wb_stat(wb, WB_RECLAIMABLE);
__inc_wb_stat(wb, WB_DIRTIED);
task_io_account_write(PAGE_CACHE_SIZE);
current->nr_dirtied++;
this_cpu_inc(bdp_ratelimits);
}
}
EXPORT_SYMBOL(account_page_dirtied);
/*
* Helper function for deaccounting dirty page without writeback.
*
* Caller must hold mem_cgroup_begin_page_stat().
*/
void account_page_cleaned(struct page *page, struct address_space *mapping,
struct mem_cgroup *memcg, struct bdi_writeback *wb)
{
if (mapping_cap_account_dirty(mapping)) {
mem_cgroup_dec_page_stat(memcg, MEM_CGROUP_STAT_DIRTY);
dec_zone_page_state(page, NR_FILE_DIRTY);
dec_wb_stat(wb, WB_RECLAIMABLE);
task_io_account_cancelled_write(PAGE_CACHE_SIZE);
}
}
/*
* For address_spaces which do not use buffers. Just tag the page as dirty in
* its radix tree.
*
* This is also used when a single buffer is being dirtied: we want to set the
* page dirty in that case, but not all the buffers. This is a "bottom-up"
* dirtying, whereas __set_page_dirty_buffers() is a "top-down" dirtying.
*
* The caller must ensure this doesn't race with truncation. Most will simply
* hold the page lock, but e.g. zap_pte_range() calls with the page mapped and
* the pte lock held, which also locks out truncation.
*/
int __set_page_dirty_nobuffers(struct page *page)
{
struct mem_cgroup *memcg;
memcg = mem_cgroup_begin_page_stat(page);
if (!TestSetPageDirty(page)) {
struct address_space *mapping = page_mapping(page);
unsigned long flags;
if (!mapping) {
mem_cgroup_end_page_stat(memcg);
return 1;
}
spin_lock_irqsave(&mapping->tree_lock, flags);
BUG_ON(page_mapping(page) != mapping);
WARN_ON_ONCE(!PagePrivate(page) && !PageUptodate(page));
account_page_dirtied(page, mapping, memcg);
radix_tree_tag_set(&mapping->page_tree, page_index(page),
PAGECACHE_TAG_DIRTY);
spin_unlock_irqrestore(&mapping->tree_lock, flags);
mem_cgroup_end_page_stat(memcg);
if (mapping->host) {
/* !PageAnon && !swapper_space */
__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
}
return 1;
}
mem_cgroup_end_page_stat(memcg);
return 0;
}
EXPORT_SYMBOL(__set_page_dirty_nobuffers);
/*
* Call this whenever redirtying a page, to de-account the dirty counters
* (NR_DIRTIED, BDI_DIRTIED, tsk->nr_dirtied), so that they match the written
* counters (NR_WRITTEN, BDI_WRITTEN) in long term. The mismatches will lead to
* systematic errors in balanced_dirty_ratelimit and the dirty pages position
* control.
*/
void account_page_redirty(struct page *page)
{
struct address_space *mapping = page->mapping;
if (mapping && mapping_cap_account_dirty(mapping)) {
struct inode *inode = mapping->host;
struct bdi_writeback *wb;
bool locked;
wb = unlocked_inode_to_wb_begin(inode, &locked);
current->nr_dirtied--;
dec_zone_page_state(page, NR_DIRTIED);
dec_wb_stat(wb, WB_DIRTIED);
unlocked_inode_to_wb_end(inode, locked);
}
}
EXPORT_SYMBOL(account_page_redirty);
/*
* When a writepage implementation decides that it doesn't want to write this
* page for some reason, it should redirty the locked page via
* redirty_page_for_writepage() and it should then unlock the page and return 0
*/
int redirty_page_for_writepage(struct writeback_control *wbc, struct page *page)
{
int ret;
wbc->pages_skipped++;
ret = __set_page_dirty_nobuffers(page);
account_page_redirty(page);
return ret;
}
EXPORT_SYMBOL(redirty_page_for_writepage);
/*
* Dirty a page.
*
* For pages with a mapping this should be done under the page lock
* for the benefit of asynchronous memory errors who prefer a consistent
* dirty state. This rule can be broken in some special cases,
* but should be better not to.
*
* If the mapping doesn't provide a set_page_dirty a_op, then
* just fall through and assume that it wants buffer_heads.
*/
int set_page_dirty(struct page *page)
{
struct address_space *mapping = page_mapping(page);
if (likely(mapping)) {
int (*spd)(struct page *) = mapping->a_ops->set_page_dirty;
/*
* readahead/lru_deactivate_page could remain
* PG_readahead/PG_reclaim due to race with end_page_writeback
* About readahead, if the page is written, the flags would be
* reset. So no problem.
* About lru_deactivate_page, if the page is redirty, the flag
* will be reset. So no problem. but if the page is used by readahead
* it will confuse readahead and make it restart the size rampup
* process. But it's a trivial problem.
*/
if (PageReclaim(page))
ClearPageReclaim(page);
#ifdef CONFIG_BLOCK
if (!spd)
spd = __set_page_dirty_buffers;
#endif
return (*spd)(page);
}
if (!PageDirty(page)) {
if (!TestSetPageDirty(page))
return 1;
}
return 0;
}
EXPORT_SYMBOL(set_page_dirty);
/*
* set_page_dirty() is racy if the caller has no reference against
* page->mapping->host, and if the page is unlocked. This is because another
* CPU could truncate the page off the mapping and then free the mapping.
*
* Usually, the page _is_ locked, or the caller is a user-space process which
* holds a reference on the inode by having an open file.
*
* In other cases, the page should be locked before running set_page_dirty().
*/
int set_page_dirty_lock(struct page *page)
{
int ret;
lock_page(page);
ret = set_page_dirty(page);
unlock_page(page);
return ret;
}
EXPORT_SYMBOL(set_page_dirty_lock);
/*
* This cancels just the dirty bit on the kernel page itself, it does NOT
* actually remove dirty bits on any mmap's that may be around. It also
* leaves the page tagged dirty, so any sync activity will still find it on
* the dirty lists, and in particular, clear_page_dirty_for_io() will still
* look at the dirty bits in the VM.
*
* Doing this should *normally* only ever be done when a page is truncated,
* and is not actually mapped anywhere at all. However, fs/buffer.c does
* this when it notices that somebody has cleaned out all the buffers on a
* page without actually doing it through the VM. Can you say "ext3 is
* horribly ugly"? Thought you could.
*/
void cancel_dirty_page(struct page *page)
{
struct address_space *mapping = page_mapping(page);
if (mapping_cap_account_dirty(mapping)) {
struct inode *inode = mapping->host;
struct bdi_writeback *wb;
struct mem_cgroup *memcg;
bool locked;
memcg = mem_cgroup_begin_page_stat(page);
wb = unlocked_inode_to_wb_begin(inode, &locked);
if (TestClearPageDirty(page))
account_page_cleaned(page, mapping, memcg, wb);
unlocked_inode_to_wb_end(inode, locked);
mem_cgroup_end_page_stat(memcg);
} else {
ClearPageDirty(page);
}
}
EXPORT_SYMBOL(cancel_dirty_page);
/*
* Clear a page's dirty flag, while caring for dirty memory accounting.
* Returns true if the page was previously dirty.
*
* This is for preparing to put the page under writeout. We leave the page
* tagged as dirty in the radix tree so that a concurrent write-for-sync
* can discover it via a PAGECACHE_TAG_DIRTY walk. The ->writepage
* implementation will run either set_page_writeback() or set_page_dirty(),
* at which stage we bring the page's dirty flag and radix-tree dirty tag
* back into sync.
*
* This incoherency between the page's dirty flag and radix-tree tag is
* unfortunate, but it only exists while the page is locked.
*/
int clear_page_dirty_for_io(struct page *page)
{
struct address_space *mapping = page_mapping(page);
int ret = 0;
BUG_ON(!PageLocked(page));
if (mapping && mapping_cap_account_dirty(mapping)) {
struct inode *inode = mapping->host;
struct bdi_writeback *wb;
struct mem_cgroup *memcg;
bool locked;
/*
* Yes, Virginia, this is indeed insane.
*
* We use this sequence to make sure that
* (a) we account for dirty stats properly
* (b) we tell the low-level filesystem to
* mark the whole page dirty if it was
* dirty in a pagetable. Only to then
* (c) clean the page again and return 1 to
* cause the writeback.
*
* This way we avoid all nasty races with the
* dirty bit in multiple places and clearing
* them concurrently from different threads.
*
* Note! Normally the "set_page_dirty(page)"
* has no effect on the actual dirty bit - since
* that will already usually be set. But we
* need the side effects, and it can help us
* avoid races.
*
* We basically use the page "master dirty bit"
* as a serialization point for all the different
* threads doing their things.
*/
if (page_mkclean(page))
set_page_dirty(page);
/*
* We carefully synchronise fault handlers against
* installing a dirty pte and marking the page dirty
* at this point. We do this by having them hold the
* page lock while dirtying the page, and pages are
* always locked coming in here, so we get the desired
* exclusion.
*/
memcg = mem_cgroup_begin_page_stat(page);
wb = unlocked_inode_to_wb_begin(inode, &locked);
if (TestClearPageDirty(page)) {
mem_cgroup_dec_page_stat(memcg, MEM_CGROUP_STAT_DIRTY);
dec_zone_page_state(page, NR_FILE_DIRTY);
dec_wb_stat(wb, WB_RECLAIMABLE);
ret = 1;
}
unlocked_inode_to_wb_end(inode, locked);
mem_cgroup_end_page_stat(memcg);
return ret;
}
return TestClearPageDirty(page);
}
EXPORT_SYMBOL(clear_page_dirty_for_io);
int test_clear_page_writeback(struct page *page)
{
struct address_space *mapping = page_mapping(page);
struct mem_cgroup *memcg;
int ret;
memcg = mem_cgroup_begin_page_stat(page);
if (mapping) {
struct inode *inode = mapping->host;
struct backing_dev_info *bdi = inode_to_bdi(inode);
unsigned long flags;
spin_lock_irqsave(&mapping->tree_lock, flags);
ret = TestClearPageWriteback(page);
if (ret) {
radix_tree_tag_clear(&mapping->page_tree,
page_index(page),
PAGECACHE_TAG_WRITEBACK);
if (bdi_cap_account_writeback(bdi)) {
struct bdi_writeback *wb = inode_to_wb(inode);
__dec_wb_stat(wb, WB_WRITEBACK);
__wb_writeout_inc(wb);
}
}
spin_unlock_irqrestore(&mapping->tree_lock, flags);
} else {
ret = TestClearPageWriteback(page);
}
if (ret) {
mem_cgroup_dec_page_stat(memcg, MEM_CGROUP_STAT_WRITEBACK);
dec_zone_page_state(page, NR_WRITEBACK);
inc_zone_page_state(page, NR_WRITTEN);
}
mem_cgroup_end_page_stat(memcg);
return ret;
}
int __test_set_page_writeback(struct page *page, bool keep_write)
{
struct address_space *mapping = page_mapping(page);
struct mem_cgroup *memcg;
int ret;
memcg = mem_cgroup_begin_page_stat(page);
if (mapping) {
struct inode *inode = mapping->host;
struct backing_dev_info *bdi = inode_to_bdi(inode);
unsigned long flags;
spin_lock_irqsave(&mapping->tree_lock, flags);
ret = TestSetPageWriteback(page);
if (!ret) {
radix_tree_tag_set(&mapping->page_tree,
page_index(page),
PAGECACHE_TAG_WRITEBACK);
if (bdi_cap_account_writeback(bdi))
__inc_wb_stat(inode_to_wb(inode), WB_WRITEBACK);
}
if (!PageDirty(page))
radix_tree_tag_clear(&mapping->page_tree,
page_index(page),
PAGECACHE_TAG_DIRTY);
if (!keep_write)
radix_tree_tag_clear(&mapping->page_tree,
page_index(page),
PAGECACHE_TAG_TOWRITE);
spin_unlock_irqrestore(&mapping->tree_lock, flags);
} else {
ret = TestSetPageWriteback(page);
}
if (!ret) {
mem_cgroup_inc_page_stat(memcg, MEM_CGROUP_STAT_WRITEBACK);
inc_zone_page_state(page, NR_WRITEBACK);
}
mem_cgroup_end_page_stat(memcg);
return ret;
}
EXPORT_SYMBOL(__test_set_page_writeback);
/*
* Return true if any of the pages in the mapping are marked with the
* passed tag.
*/
int mapping_tagged(struct address_space *mapping, int tag)
{
return radix_tree_tagged(&mapping->page_tree, tag);
}
EXPORT_SYMBOL(mapping_tagged);
/**
* wait_for_stable_page() - wait for writeback to finish, if necessary.
* @page: The page to wait on.
*
* This function determines if the given page is related to a backing device
* that requires page contents to be held stable during writeback. If so, then
* it will wait for any pending writeback to complete.
*/
void wait_for_stable_page(struct page *page)
{
if (bdi_cap_stable_pages_required(inode_to_bdi(page->mapping->host)))
wait_on_page_writeback(page);
}
EXPORT_SYMBOL_GPL(wait_for_stable_page);
C:\Users\Admin\Desktop\ 4.2.y-new\linux-4.2.y\mm/pagewalk.c
#include <linux/mm.h>
#include <linux/highmem.h>
#include <linux/sched.h>
#include <linux/hugetlb.h>
static int walk_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
struct mm_walk *walk)
{
pte_t *pte;
int err = 0;
pte = pte_offset_map(pmd, addr);
for (;;) {
err = walk->pte_entry(pte, addr, addr + PAGE_SIZE, walk);
if (err)
break;
addr += PAGE_SIZE;
if (addr == end)
break;
pte++;
}
pte_unmap(pte);
return err;
}
static int walk_pmd_range(pud_t *pud, unsigned long addr, unsigned long end,
struct mm_walk *walk)
{
pmd_t *pmd;
unsigned long next;
int err = 0;
pmd = pmd_offset(pud, addr);
do {
again:
next = pmd_addr_end(addr, end);
if (pmd_none(*pmd) || !walk->vma) {
if (walk->pte_hole)
err = walk->pte_hole(addr, next, walk);
if (err)
break;
continue;
}
/*
* This implies that each ->pmd_entry() handler
* needs to know about pmd_trans_huge() pmds
*/
if (walk->pmd_entry)
err = walk->pmd_entry(pmd, addr, next, walk);
if (err)
break;
/*
* Check this here so we only break down trans_huge
* pages when we _need_ to
*/
if (!walk->pte_entry)
continue;
split_huge_page_pmd_mm(walk->mm, addr, pmd);
if (pmd_trans_unstable(pmd))
goto again;
err = walk_pte_range(pmd, addr, next, walk);
if (err)
break;
} while (pmd++, addr = next, addr != end);
return err;
}
static int walk_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end,
struct mm_walk *walk)
{
pud_t *pud;
unsigned long next;
int err = 0;
pud = pud_offset(pgd, addr);
do {
next = pud_addr_end(addr, end);
if (pud_none_or_clear_bad(pud)) {
if (walk->pte_hole)
err = walk->pte_hole(addr, next, walk);
if (err)
break;
continue;
}
if (walk->pmd_entry || walk->pte_entry)
err = walk_pmd_range(pud, addr, next, walk);
if (err)
break;
} while (pud++, addr = next, addr != end);
return err;
}
static int walk_pgd_range(unsigned long addr, unsigned long end,
struct mm_walk *walk)
{
pgd_t *pgd;
unsigned long next;
int err = 0;
pgd = pgd_offset(walk->mm, addr);
do {
next = pgd_addr_end(addr, end);
if (pgd_none_or_clear_bad(pgd)) {
if (walk->pte_hole)
err = walk->pte_hole(addr, next, walk);
if (err)
break;
continue;
}
if (walk->pmd_entry || walk->pte_entry)
err = walk_pud_range(pgd, addr, next, walk);
if (err)
break;
} while (pgd++, addr = next, addr != end);
return err;
}
#ifdef CONFIG_HUGETLB_PAGE
static unsigned long hugetlb_entry_end(struct hstate *h, unsigned long addr,
unsigned long end)
{
unsigned long boundary = (addr & huge_page_mask(h)) + huge_page_size(h);
return boundary < end ? boundary : end;
}
static int walk_hugetlb_range(unsigned long addr, unsigned long end,
struct mm_walk *walk)
{
struct vm_area_struct *vma = walk->vma;
struct hstate *h = hstate_vma(vma);
unsigned long next;
unsigned long hmask = huge_page_mask(h);
pte_t *pte;
int err = 0;
do {
next = hugetlb_entry_end(h, addr, end);
pte = huge_pte_offset(walk->mm, addr & hmask);
if (pte && walk->hugetlb_entry)
err = walk->hugetlb_entry(pte, hmask, addr, next, walk);
if (err)
break;
} while (addr = next, addr != end);
return err;
}
#else /* CONFIG_HUGETLB_PAGE */
static int walk_hugetlb_range(unsigned long addr, unsigned long end,
struct mm_walk *walk)
{
return 0;
}
#endif /* CONFIG_HUGETLB_PAGE */
/*
* Decide whether we really walk over the current vma on [@start, @end)
* or skip it via the returned value. Return 0 if we do walk over the
* current vma, and return 1 if we skip the vma. Negative values means
* error, where we abort the current walk.
*/
static int walk_page_test(unsigned long start, unsigned long end,
struct mm_walk *walk)
{
struct vm_area_struct *vma = walk->vma;
if (walk->test_walk)
return walk->test_walk(start, end, walk);
/*
* vma(VM_PFNMAP) doesn't have any valid struct pages behind VM_PFNMAP
* range, so we don't walk over it as we do for normal vmas. However,
* Some callers are interested in handling hole range and they don't
* want to just ignore any single address range. Such users certainly
* define their ->pte_hole() callbacks, so let's delegate them to handle
* vma(VM_PFNMAP).
*/
if (vma->vm_flags & VM_PFNMAP) {
int err = 1;
if (walk->pte_hole)
err = walk->pte_hole(start, end, walk);
return err ? err : 1;
}
return 0;
}
static int __walk_page_range(unsigned long start, unsigned long end,
struct mm_walk *walk)
{
int err = 0;
struct vm_area_struct *vma = walk->vma;
if (vma && is_vm_hugetlb_page(vma)) {
if (walk->hugetlb_entry)
err = walk_hugetlb_range(start, end, walk);
} else
err = walk_pgd_range(start, end, walk);
return err;
}
/**
* walk_page_range - walk page table with caller specific callbacks
*
* Recursively walk the page table tree of the process represented by @walk->mm
* within the virtual address range [@start, @end). During walking, we can do
* some caller-specific works for each entry, by setting up pmd_entry(),
* pte_entry(), and/or hugetlb_entry(). If you don't set up for some of these
* callbacks, the associated entries/pages are just ignored.
* The return values of these callbacks are commonly defined like below:
* - 0 : succeeded to handle the current entry, and if you don't reach the
* end address yet, continue to walk.
* - >0 : succeeded to handle the current entry, and return to the caller
* with caller specific value.
* - <0 : failed to handle the current entry, and return to the caller
* with error code.
*
* Before starting to walk page table, some callers want to check whether
* they really want to walk over the current vma, typically by checking
* its vm_flags. walk_page_test() and @walk->test_walk() are used for this
* purpose.
*
* struct mm_walk keeps current values of some common data like vma and pmd,
* which are useful for the access from callbacks. If you want to pass some
* caller-specific data to callbacks, @walk->private should be helpful.
*
* Locking:
* Callers of walk_page_range() and walk_page_vma() should hold
* @walk->mm->mmap_sem, because these function traverse vma list and/or
* access to vma's data.
*/
int walk_page_range(unsigned long start, unsigned long end,
struct mm_walk *walk)
{
int err = 0;
unsigned long next;
struct vm_area_struct *vma;
if (start >= end)
return -EINVAL;
if (!walk->mm)
return -EINVAL;
VM_BUG_ON_MM(!rwsem_is_locked(&walk->mm->mmap_sem), walk->mm);
vma = find_vma(walk->mm, start);
do {
if (!vma) { /* after the last vma */
walk->vma = NULL;
next = end;
} else if (start < vma->vm_start) { /* outside vma */
walk->vma = NULL;
next = min(end, vma->vm_start);
} else { /* inside vma */
walk->vma = vma;
next = min(end, vma->vm_end);
vma = vma->vm_next;
err = walk_page_test(start, next, walk);
if (err > 0) {
/*
* positive return values are purely for
* controlling the pagewalk, so should never
* be passed to the callers.
*/
err = 0;
continue;
}
if (err < 0)
break;
}
if (walk->vma || walk->pte_hole)
err = __walk_page_range(start, next, walk);
if (err)
break;
} while (start = next, start < end);
return err;
}
int walk_page_vma(struct vm_area_struct *vma, struct mm_walk *walk)
{
int err;
if (!walk->mm)
return -EINVAL;
VM_BUG_ON(!rwsem_is_locked(&walk->mm->mmap_sem));
VM_BUG_ON(!vma);
walk->vma = vma;
err = walk_page_test(vma->vm_start, vma->vm_end, walk);
if (err > 0)
return 0;
if (err < 0)
return err;
return __walk_page_range(vma->vm_start, vma->vm_end, walk);
}
C:\Users\Admin\Desktop\linux-4.2.y-new\linux-4.2.y\mm/page_alloc.c
/*
* linux/mm/page_alloc.c
*
* Manages the free list, the system allocates free pages here.
* Note that kmalloc() lives in slab.c
*
* Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds
* Swap reorganised 29.12.95, Stephen Tweedie
* Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999
* Reshaped it to be a zoned allocator, Ingo Molnar, Red Hat, 1999
* Discontiguous memory support, Kanoj Sarcar, SGI, Nov 1999
* Zone balancing, Kanoj Sarcar, SGI, Jan 2000
* Per cpu hot/cold page lists, bulk allocation, Martin J. Bligh, Sept 2002
* (lots of bits borrowed from Ingo Molnar & Andrew Morton)
*/
#include <linux/stddef.h>
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/interrupt.h>
#include <linux/pagemap.h>
#include <linux/jiffies.h>
#include <linux/bootmem.h>
#include <linux/memblock.h>
#include <linux/compiler.h>
#include <linux/kernel.h>
#include <linux/kmemcheck.h>
#include <linux/kasan.h>
#include <linux/module.h>
#include <linux/suspend.h>
#include <linux/pagevec.h>
#include <linux/blkdev.h>
#include <linux/slab.h>
#include <linux/ratelimit.h>
#include <linux/oom.h>
#include <linux/notifier.h>
#include <linux/topology.h>
#include <linux/sysctl.h>
#include <linux/cpu.h>
#include <linux/cpuset.h>
#include <linux/memory_hotplug.h>
#include <linux/nodemask.h>
#include <linux/vmalloc.h>
#include <linux/vmstat.h>
#include <linux/mempolicy.h>
#include <linux/stop_machine.h>
#include <linux/sort.h>
#include <linux/pfn.h>
#include <linux/backing-dev.h>
#include <linux/fault-inject.h>
#include <linux/page-isolation.h>
#include <linux/page_ext.h>
#include <linux/debugobjects.h>
#include <linux/kmemleak.h>
#include <linux/compaction.h>
#include <trace/events/kmem.h>
#include <linux/prefetch.h>
#include <linux/mm_inline.h>
#include <linux/migrate.h>
#include <linux/page_ext.h>
#include <linux/hugetlb.h>
#include <linux/sched/rt.h>
#include <linux/page_owner.h>
#include <linux/kthread.h>
#include <asm/sections.h>
#include <asm/tlbflush.h>
#include <asm/div64.h>
#include "internal.h"
/* prevent >1 _updater_ of zone percpu pageset ->high and ->batch fields */
static DEFINE_MUTEX(pcp_batch_high_lock);
#define MIN_PERCPU_PAGELIST_FRACTION (8)
#ifdef CONFIG_USE_PERCPU_NUMA_NODE_ID
DEFINE_PER_CPU(int, numa_node);
EXPORT_PER_CPU_SYMBOL(numa_node);
#endif
#ifdef CONFIG_HAVE_MEMORYLESS_NODES
/*
* N.B., Do NOT reference the '_numa_mem_' per cpu variable directly.
* It will not be defined when CONFIG_HAVE_MEMORYLESS_NODES is not defined.
* Use the accessor functions set_numa_mem(), numa_mem_id() and cpu_to_mem()
* defined in <linux/topology.h>.
*/
DEFINE_PER_CPU(int, _numa_mem_); /* Kernel "local memory" node */
EXPORT_PER_CPU_SYMBOL(_numa_mem_);
int _node_numa_mem_[MAX_NUMNODES];
#endif
/*
* Array of node states.
*/
nodemask_t node_states[NR_NODE_STATES] __read_mostly = {
[N_POSSIBLE] = NODE_MASK_ALL,
[N_ONLINE] = { { [0] = 1UL } },
#ifndef CONFIG_NUMA
[N_NORMAL_MEMORY] = { { [0] = 1UL } },
#ifdef CONFIG_HIGHMEM
[N_HIGH_MEMORY] = { { [0] = 1UL } },
#endif
#ifdef CONFIG_MOVABLE_NODE
[N_MEMORY] = { { [0] = 1UL } },
#endif
[N_CPU] = { { [0] = 1UL } },
#endif /* NUMA */
};
EXPORT_SYMBOL(node_states);
/* Protect totalram_pages and zone->managed_pages */
static DEFINE_SPINLOCK(managed_page_count_lock);
unsigned long totalram_pages __read_mostly;
unsigned long totalreserve_pages __read_mostly;
unsigned long totalcma_pages __read_mostly;
/*
* When calculating the number of globally allowed dirty pages, there
* is a certain number of per-zone reserves that should not be
* considered dirtyable memory. This is the sum of those reserves
* over all existing zones that contribute dirtyable memory.
*/
unsigned long dirty_balance_reserve __read_mostly;
int percpu_pagelist_fraction;
gfp_t gfp_allowed_mask __read_mostly = GFP_BOOT_MASK;
#ifdef CONFIG_PM_SLEEP
/*
* The following functions are used by the suspend/hibernate code to temporarily
* change gfp_allowed_mask in order to avoid using I/O during memory allocations
* while devices are suspended. To avoid races with the suspend/hibernate code,
* they should always be called with pm_mutex held (gfp_allowed_mask also should
* only be modified with pm_mutex held, unless the suspend/hibernate code is
* guaranteed not to run in parallel with that modification).
*/
static gfp_t saved_gfp_mask;
void pm_restore_gfp_mask(void)
{
WARN_ON(!mutex_is_locked(&pm_mutex));
if (saved_gfp_mask) {
gfp_allowed_mask = saved_gfp_mask;
saved_gfp_mask = 0;
}
}
void pm_restrict_gfp_mask(void)
{
WARN_ON(!mutex_is_locked(&pm_mutex));
WARN_ON(saved_gfp_mask);
saved_gfp_mask = gfp_allowed_mask;
gfp_allowed_mask &= ~GFP_IOFS;
}
bool pm_suspended_storage(void)
{
if ((gfp_allowed_mask & GFP_IOFS) == GFP_IOFS)
return false;
return true;
}
#endif /* CONFIG_PM_SLEEP */
#ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE
int pageblock_order __read_mostly;
#endif
static void __free_pages_ok(struct page *page, unsigned int order);
/*
* results with 256, 32 in the lowmem_reserve sysctl:
* 1G machine -> (16M dma, 800M-16M normal, 1G-800M high)
* 1G machine -> (16M dma, 784M normal, 224M high)
* NORMAL allocation will leave 784M/256 of ram reserved in the ZONE_DMA
* HIGHMEM allocation will leave 224M/32 of ram reserved in ZONE_NORMAL
* HIGHMEM allocation will leave (224M+784M)/256 of ram reserved in ZONE_DMA
*
* TBD: should special case ZONE_DMA32 machines here - in those we normally
* don't need any ZONE_NORMAL reservation
*/
int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES-1] = {
#ifdef CONFIG_ZONE_DMA
256,
#endif
#ifdef CONFIG_ZONE_DMA32
256,
#endif
#ifdef CONFIG_HIGHMEM
32,
#endif
32,
};
EXPORT_SYMBOL(totalram_pages);
static char * const zone_names[MAX_NR_ZONES] = {
#ifdef CONFIG_ZONE_DMA
"DMA",
#endif
#ifdef CONFIG_ZONE_DMA32
"DMA32",
#endif
"Normal",
#ifdef CONFIG_HIGHMEM
"HighMem",
#endif
"Movable",
};
int min_free_kbytes = 1024;
int user_min_free_kbytes = -1;
static unsigned long __meminitdata nr_kernel_pages;
static unsigned long __meminitdata nr_all_pages;
static unsigned long __meminitdata dma_reserve;
#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
static unsigned long __meminitdata arch_zone_lowest_possible_pfn[MAX_NR_ZONES];
static unsigned long __meminitdata arch_zone_highest_possible_pfn[MAX_NR_ZONES];
static unsigned long __initdata required_kernelcore;
static unsigned long __initdata required_movablecore;
static unsigned long __meminitdata zone_movable_pfn[MAX_NUMNODES];
/* movable_zone is the "real" zone pages in ZONE_MOVABLE are taken from */
int movable_zone;
EXPORT_SYMBOL(movable_zone);
#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
#if MAX_NUMNODES > 1
int nr_node_ids __read_mostly = MAX_NUMNODES;
int nr_online_nodes __read_mostly = 1;
EXPORT_SYMBOL(nr_node_ids);
EXPORT_SYMBOL(nr_online_nodes);
#endif
int page_group_by_mobility_disabled __read_mostly;
#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
static inline void reset_deferred_meminit(pg_data_t *pgdat)
{
pgdat->first_deferred_pfn = ULONG_MAX;
}
/* Returns true if the struct page for the pfn is uninitialised */
static inline bool __meminit early_page_uninitialised(unsigned long pfn)
{
if (pfn >= NODE_DATA(early_pfn_to_nid(pfn))->first_deferred_pfn)
return true;
return false;
}
static inline bool early_page_nid_uninitialised(unsigned long pfn, int nid)
{
if (pfn >= NODE_DATA(nid)->first_deferred_pfn)
return true;
return false;
}
/*
* Returns false when the remaining initialisation should be deferred until
* later in the boot cycle when it can be parallelised.
*/
static inline bool update_defer_init(pg_data_t *pgdat,
unsigned long pfn, unsigned long zone_end,
unsigned long *nr_initialised)
{
/* Always populate low zones for address-contrained allocations */
if (zone_end < pgdat_end_pfn(pgdat))
return true;
/* Initialise at least 2G of the highest zone */
(*nr_initialised)++;
if (*nr_initialised > (2UL << (30 - PAGE_SHIFT)) &&
(pfn & (PAGES_PER_SECTION - 1)) == 0) {
pgdat->first_deferred_pfn = pfn;
return false;
}
return true;
}
#else
static inline void reset_deferred_meminit(pg_data_t *pgdat)
{
}
static inline bool early_page_uninitialised(unsigned long pfn)
{
return false;
}
static inline bool early_page_nid_uninitialised(unsigned long pfn, int nid)
{
return false;
}
static inline bool update_defer_init(pg_data_t *pgdat,
unsigned long pfn, unsigned long zone_end,
unsigned long *nr_initialised)
{
return true;
}
#endif
void set_pageblock_migratetype(struct page *page, int migratetype)
{
if (unlikely(page_group_by_mobility_disabled &&
migratetype < MIGRATE_PCPTYPES))
migratetype = MIGRATE_UNMOVABLE;
set_pageblock_flags_group(page, (unsigned long)migratetype,
PB_migrate, PB_migrate_end);
}
#ifdef CONFIG_DEBUG_VM
static int page_outside_zone_boundaries(struct zone *zone, struct page *page)
{
int ret = 0;
unsigned seq;
unsigned long pfn = page_to_pfn(page);
unsigned long sp, start_pfn;
do {
seq = zone_span_seqbegin(zone);
start_pfn = zone->zone_start_pfn;
sp = zone->spanned_pages;
if (!zone_spans_pfn(zone, pfn))
ret = 1;
} while (zone_span_seqretry(zone, seq));
if (ret)
pr_err("page 0x%lx outside node %d zone %s [ 0x%lx - 0x%lx ]\n",
pfn, zone_to_nid(zone), zone->name,
start_pfn, start_pfn + sp);
return ret;
}
static int page_is_consistent(struct zone *zone, struct page *page)
{
if (!pfn_valid_within(page_to_pfn(page)))
return 0;
if (zone != page_zone(page))
return 0;
return 1;
}
/*
* Temporary debugging check for pages not lying within a given zone.
*/
static int bad_range(struct zone *zone, struct page *page)
{
if (page_outside_zone_boundaries(zone, page))
return 1;
if (!page_is_consistent(zone, page))
return 1;
return 0;
}
#else
static inline int bad_range(struct zone *zone, struct page *page)
{
return 0;
}
#endif
static void bad_page(struct page *page, const char *reason,
unsigned long bad_flags)
{
static unsigned long resume;
static unsigned long nr_shown;
static unsigned long nr_unshown;
/* Don't complain about poisoned pages */
if (PageHWPoison(page)) {
page_mapcount_reset(page); /* remove PageBuddy */
return;
}
/*
* Allow a burst of 60 reports, then keep quiet for that minute;
* or allow a steady drip of one report per second.
*/
if (nr_shown == 60) {
if (time_before(jiffies, resume)) {
nr_unshown++;
goto out;
}
if (nr_unshown) {
printk(KERN_ALERT
"BUG: Bad page state: %lu messages suppressed\n",
nr_unshown);
nr_unshown = 0;
}
nr_shown = 0;
}
if (nr_shown++ == 0)
resume = jiffies + 60 * HZ;
printk(KERN_ALERT "BUG: Bad page state in process %s pfn:%05lx\n",
current->comm, page_to_pfn(page));
dump_page_badflags(page, reason, bad_flags);
print_modules();
dump_stack();
out:
/* Leave bad fields for debug, except PageBuddy could make trouble */
page_mapcount_reset(page); /* remove PageBuddy */
add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE);
}
/*
* Higher-order pages are called "compound pages". They are structured thusly:
*
* The first PAGE_SIZE page is called the "head page".
*
* The remaining PAGE_SIZE pages are called "tail pages".
*
* All pages have PG_compound set. All tail pages have their ->first_page
* pointing at the head page.
*
* The first tail page's ->lru.next holds the address of the compound page's
* put_page() function. Its ->lru.prev holds the order of allocation.
* This usage means that zero-order pages may not be compound.
*/
static void free_compound_page(struct page *page)
{
__free_pages_ok(page, compound_order(page));
}
void prep_compound_page(struct page *page, unsigned long order)
{
int i;
int nr_pages = 1 << order;
set_compound_page_dtor(page, free_compound_page);
set_compound_order(page, order);
__SetPageHead(page);
for (i = 1; i < nr_pages; i++) {
struct page *p = page + i;
set_page_count(p, 0);
p->first_page = page;
/* Make sure p->first_page is always valid for PageTail() */
smp_wmb();
__SetPageTail(p);
}
}
#ifdef CONFIG_DEBUG_PAGEALLOC
unsigned int _debug_guardpage_minorder;
bool _debug_pagealloc_enabled __read_mostly;
bool _debug_guardpage_enabled __read_mostly;
static int __init early_debug_pagealloc(char *buf)
{
if (!buf)
return -EINVAL;
if (strcmp(buf, "on") == 0)
_debug_pagealloc_enabled = true;
return 0;
}
early_param("debug_pagealloc", early_debug_pagealloc);
static bool need_debug_guardpage(void)
{
/* If we don't use debug_pagealloc, we don't need guard page */
if (!debug_pagealloc_enabled())
return false;
return true;
}
static void init_debug_guardpage(void)
{
if (!debug_pagealloc_enabled())
return;
_debug_guardpage_enabled = true;
}
struct page_ext_operations debug_guardpage_ops = {
.need = need_debug_guardpage,
.init = init_debug_guardpage,
};
static int __init debug_guardpage_minorder_setup(char *buf)
{
unsigned long res;
if (kstrtoul(buf, 10, &res) < 0 || res > MAX_ORDER / 2) {
printk(KERN_ERR "Bad debug_guardpage_minorder value\n");
return 0;
}
_debug_guardpage_minorder = res;
printk(KERN_INFO "Setting debug_guardpage_minorder to %lu\n", res);
return 0;
}
__setup("debug_guardpage_minorder=", debug_guardpage_minorder_setup);
static inline void set_page_guard(struct zone *zone, struct page *page,
unsigned int order, int migratetype)
{
struct page_ext *page_ext;
if (!debug_guardpage_enabled())
return;
page_ext = lookup_page_ext(page);
__set_bit(PAGE_EXT_DEBUG_GUARD, &page_ext->flags);
INIT_LIST_HEAD(&page->lru);
set_page_private(page, order);
/* Guard pages are not available for any usage */
__mod_zone_freepage_state(zone, -(1 << order), migratetype);
}
static inline void clear_page_guard(struct zone *zone, struct page *page,
unsigned int order, int migratetype)
{
struct page_ext *page_ext;
if (!debug_guardpage_enabled())
return;
page_ext = lookup_page_ext(page);
__clear_bit(PAGE_EXT_DEBUG_GUARD, &page_ext->flags);
set_page_private(page, 0);
if (!is_migrate_isolate(migratetype))
__mod_zone_freepage_state(zone, (1 << order), migratetype);
}
#else
struct page_ext_operations debug_guardpage_ops = { NULL, };
static inline void set_page_guard(struct zone *zone, struct page *page,
unsigned int order, int migratetype) {}
static inline void clear_page_guard(struct zone *zone, struct page *page,
unsigned int order, int migratetype) {}
#endif
static inline void set_page_order(struct page *page, unsigned int order)
{
set_page_private(page, order);
__SetPageBuddy(page);
}
static inline void rmv_page_order(struct page *page)
{
__ClearPageBuddy(page);
set_page_private(page, 0);
}
/*
* This function checks whether a page is free && is the buddy
* we can do coalesce a page and its buddy if
* (a) the buddy is not in a hole &&
* (b) the buddy is in the buddy system &&
* (c) a page and its buddy have the same order &&
* (d) a page and its buddy are in the same zone.
*
* For recording whether a page is in the buddy system, we set ->_mapcount
* PAGE_BUDDY_MAPCOUNT_VALUE.
* Setting, clearing, and testing _mapcount PAGE_BUDDY_MAPCOUNT_VALUE is
* serialized by zone->lock.
*
* For recording page's order, we use page_private(page).
*/
static inline int page_is_buddy(struct page *page, struct page *buddy,
unsigned int order)
{
if (!pfn_valid_within(page_to_pfn(buddy)))
return 0;
if (page_is_guard(buddy) && page_order(buddy) == order) {
if (page_zone_id(page) != page_zone_id(buddy))
return 0;
VM_BUG_ON_PAGE(page_count(buddy) != 0, buddy);
return 1;
}
if (PageBuddy(buddy) && page_order(buddy) == order) {
/*
* zone check is done late to avoid uselessly
* calculating zone/node ids for pages that could
* never merge.
*/
if (page_zone_id(page) != page_zone_id(buddy))
return 0;
VM_BUG_ON_PAGE(page_count(buddy) != 0, buddy);
return 1;
}
return 0;
}
/*
* Freeing function for a buddy system allocator.
*
* The concept of a buddy system is to maintain direct-mapped table
* (containing bit values) for memory blocks of various "orders".
* The bottom level table contains the map for the smallest allocatable
* units of memory (here, pages), and each level above it describes
* pairs of units from the levels below, hence, "buddies".
* At a high level, all that happens here is marking the table entry
* at the bottom level available, and propagating the changes upward
* as necessary, plus some accounting needed to play nicely with other
* parts of the VM system.
* At each level, we keep a list of pages, which are heads of continuous
* free pages of length of (1 << order) and marked with _mapcount
* PAGE_BUDDY_MAPCOUNT_VALUE. Page's order is recorded in page_private(page)
* field.
* So when we are allocating or freeing one, we can derive the state of the
* other. That is, if we allocate a small block, and both were
* free, the remainder of the region must be split into blocks.
* If a block is freed, and its buddy is also free, then this
* triggers coalescing into a block of larger size.
*
* -- nyc
*/
static inline void __free_one_page(struct page *page,
unsigned long pfn,
struct zone *zone, unsigned int order,
int migratetype)
{
unsigned long page_idx;
unsigned long combined_idx;
unsigned long uninitialized_var(buddy_idx);
struct page *buddy;
int max_order = MAX_ORDER;
VM_BUG_ON(!zone_is_initialized(zone));
VM_BUG_ON_PAGE(page->flags & PAGE_FLAGS_CHECK_AT_PREP, page);
VM_BUG_ON(migratetype == -1);
if (is_migrate_isolate(migratetype)) {
/*
* We restrict max order of merging to prevent merge
* between freepages on isolate pageblock and normal
* pageblock. Without this, pageblock isolation
* could cause incorrect freepage accounting.
*/
max_order = min(MAX_ORDER, pageblock_order + 1);
} else {
__mod_zone_freepage_state(zone, 1 << order, migratetype);
}
page_idx = pfn & ((1 << max_order) - 1);
VM_BUG_ON_PAGE(page_idx & ((1 << order) - 1), page);
VM_BUG_ON_PAGE(bad_range(zone, page), page);
while (order < max_order - 1) {
buddy_idx = __find_buddy_index(page_idx, order);
buddy = page + (buddy_idx - page_idx);
if (!page_is_buddy(page, buddy, order))
break;
/*
* Our buddy is free or it is CONFIG_DEBUG_PAGEALLOC guard page,
* merge with it and move up one order.
*/
if (page_is_guard(buddy)) {
clear_page_guard(zone, buddy, order, migratetype);
} else {
list_del(&buddy->lru);
zone->free_area[order].nr_free--;
rmv_page_order(buddy);
}
combined_idx = buddy_idx & page_idx;
page = page + (combined_idx - page_idx);
page_idx = combined_idx;
order++;
}
set_page_order(page, order);
/*
* If this is not the largest possible page, check if the buddy
* of the next-highest order is free. If it is, it's possible
* that pages are being freed that will coalesce soon. In case,
* that is happening, add the free page to the tail of the list
* so it's less likely to be used soon and more likely to be merged
* as a higher order page
*/
if ((order < MAX_ORDER-2) && pfn_valid_within(page_to_pfn(buddy))) {
struct page *higher_page, *higher_buddy;
combined_idx = buddy_idx & page_idx;
higher_page = page + (combined_idx - page_idx);
buddy_idx = __find_buddy_index(combined_idx, order + 1);
higher_buddy = higher_page + (buddy_idx - combined_idx);
if (page_is_buddy(higher_page, higher_buddy, order + 1)) {
list_add_tail(&page->lru,
&zone->free_area[order].free_list[migratetype]);
goto out;
}
}
list_add(&page->lru, &zone->free_area[order].free_list[migratetype]);
out:
zone->free_area[order].nr_free++;
}
static inline int free_pages_check(struct page *page)
{
const char *bad_reason = NULL;
unsigned long bad_flags = 0;
if (unlikely(page_mapcount(page)))
bad_reason = "nonzero mapcount";
if (unlikely(page->mapping != NULL))
bad_reason = "non-NULL mapping";
if (unlikely(atomic_read(&page->_count) != 0))
bad_reason = "nonzero _count";
if (unlikely(page->flags & PAGE_FLAGS_CHECK_AT_FREE)) {
bad_reason = "PAGE_FLAGS_CHECK_AT_FREE flag(s) set";
bad_flags = PAGE_FLAGS_CHECK_AT_FREE;
}
#ifdef CONFIG_MEMCG
if (unlikely(page->mem_cgroup))
bad_reason = "page still charged to cgroup";
#endif
if (unlikely(bad_reason)) {
bad_page(page, bad_reason, bad_flags);
return 1;
}
page_cpupid_reset_last(page);
if (page->flags & PAGE_FLAGS_CHECK_AT_PREP)
page->flags &= ~PAGE_FLAGS_CHECK_AT_PREP;
return 0;
}
/*
* Frees a number of pages from the PCP lists
* Assumes all pages on list are in same zone, and of same order.
* count is the number of pages to free.
*
* If the zone was previously in an "all pages pinned" state then look to
* see if this freeing clears that state.
*
* And clear the zone's pages_scanned counter, to hold off the "all pages are
* pinned" detection logic.
*/
static void free_pcppages_bulk(struct zone *zone, int count,
struct per_cpu_pages *pcp)
{
int migratetype = 0;
int batch_free = 0;
int to_free = count;
unsigned long nr_scanned;
spin_lock(&zone->lock);
nr_scanned = zone_page_state(zone, NR_PAGES_SCANNED);
if (nr_scanned)
__mod_zone_page_state(zone, NR_PAGES_SCANNED, -nr_scanned);
while (to_free) {
struct page *page;
struct list_head *list;
/*
* Remove pages from lists in a round-robin fashion. A
* batch_free count is maintained that is incremented when an
* empty list is encountered. This is so more pages are freed
* off fuller lists instead of spinning excessively around empty
* lists
*/
do {
batch_free++;
if (++migratetype == MIGRATE_PCPTYPES)
migratetype = 0;
list = &pcp->lists[migratetype];
} while (list_empty(list));
/* This is the only non-empty list. Free them all. */
if (batch_free == MIGRATE_PCPTYPES)
batch_free = to_free;
do {
int mt; /* migratetype of the to-be-freed page */
page = list_entry(list->prev, struct page, lru);
/* must delete as __free_one_page list manipulates */
list_del(&page->lru);
mt = get_freepage_migratetype(page);
if (unlikely(has_isolate_pageblock(zone)))
mt = get_pageblock_migratetype(page);
/* MIGRATE_MOVABLE list may include MIGRATE_RESERVEs */
__free_one_page(page, page_to_pfn(page), zone, 0, mt);
trace_mm_page_pcpu_drain(page, 0, mt);
} while (--to_free && --batch_free && !list_empty(list));
}
spin_unlock(&zone->lock);
}
static void free_one_page(struct zone *zone,
struct page *page, unsigned long pfn,
unsigned int order,
int migratetype)
{
unsigned long nr_scanned;
spin_lock(&zone->lock);
nr_scanned = zone_page_state(zone, NR_PAGES_SCANNED);
if (nr_scanned)
__mod_zone_page_state(zone, NR_PAGES_SCANNED, -nr_scanned);
if (unlikely(has_isolate_pageblock(zone) ||
is_migrate_isolate(migratetype))) {
migratetype = get_pfnblock_migratetype(page, pfn);
}
__free_one_page(page, pfn, zone, order, migratetype);
spin_unlock(&zone->lock);
}
static int free_tail_pages_check(struct page *head_page, struct page *page)
{
if (!IS_ENABLED(CONFIG_DEBUG_VM))
return 0;
if (unlikely(!PageTail(page))) {
bad_page(page, "PageTail not set", 0);
return 1;
}
if (unlikely(page->first_page != head_page)) {
bad_page(page, "first_page not consistent", 0);
return 1;
}
return 0;
}
static void __meminit __init_single_page(struct page *page, unsigned long pfn,
unsigned long zone, int nid)
{
set_page_links(page, zone, nid, pfn);
init_page_count(page);
page_mapcount_reset(page);
page_cpupid_reset_last(page);
INIT_LIST_HEAD(&page->lru);
#ifdef WANT_PAGE_VIRTUAL
/* The shift won't overflow because ZONE_NORMAL is below 4G. */
if (!is_highmem_idx(zone))
set_page_address(page, __va(pfn << PAGE_SHIFT));
#endif
}
static void __meminit __init_single_pfn(unsigned long pfn, unsigned long zone,
int nid)
{
return __init_single_page(pfn_to_page(pfn), pfn, zone, nid);
}
#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
static void init_reserved_page(unsigned long pfn)
{
pg_data_t *pgdat;
int nid, zid;
if (!early_page_uninitialised(pfn))
return;
nid = early_pfn_to_nid(pfn);
pgdat = NODE_DATA(nid);
for (zid = 0; zid < MAX_NR_ZONES; zid++) {
struct zone *zone = &pgdat->node_zones[zid];
if (pfn >= zone->zone_start_pfn && pfn < zone_end_pfn(zone))
break;
}
__init_single_pfn(pfn, zid, nid);
}
#else
static inline void init_reserved_page(unsigned long pfn)
{
}
#endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */
/*
* Initialised pages do not have PageReserved set. This function is
* called for each range allocated by the bootmem allocator and
* marks the pages PageReserved. The remaining valid pages are later
* sent to the buddy page allocator.
*/
void __meminit reserve_bootmem_region(unsigned long start, unsigned long end)
{
unsigned long start_pfn = PFN_DOWN(start);
unsigned long end_pfn = PFN_UP(end);
for (; start_pfn < end_pfn; start_pfn++) {
if (pfn_valid(start_pfn)) {
struct page *page = pfn_to_page(start_pfn);
init_reserved_page(start_pfn);
SetPageReserved(page);
}
}
}
static bool free_pages_prepare(struct page *page, unsigned int order)
{
bool compound = PageCompound(page);
int i, bad = 0;
VM_BUG_ON_PAGE(PageTail(page), page);
VM_BUG_ON_PAGE(compound && compound_order(page) != order, page);
trace_mm_page_free(page, order);
kmemcheck_free_shadow(page, order);
kasan_free_pages(page, order);
if (PageAnon(page))
page->mapping = NULL;
bad += free_pages_check(page);
for (i = 1; i < (1 << order); i++) {
if (compound)
bad += free_tail_pages_check(page, page + i);
bad += free_pages_check(page + i);
}
if (bad)
return false;
reset_page_owner(page, order);
if (!PageHighMem(page)) {
debug_check_no_locks_freed(page_address(page),
PAGE_SIZE << order);
debug_check_no_obj_freed(page_address(page),
PAGE_SIZE << order);
}
arch_free_page(page, order);
kernel_map_pages(page, 1 << order, 0);
return true;
}
static void __free_pages_ok(struct page *page, unsigned int order)
{
unsigned long flags;
int migratetype;
unsigned long pfn = page_to_pfn(page);
if (!free_pages_prepare(page, order))
return;
migratetype = get_pfnblock_migratetype(page, pfn);
local_irq_save(flags);
__count_vm_events(PGFREE, 1 << order);
set_freepage_migratetype(page, migratetype);
free_one_page(page_zone(page), page, pfn, order, migratetype);
local_irq_restore(flags);
}
static void __init __free_pages_boot_core(struct page *page,
unsigned long pfn, unsigned int order)
{
unsigned int nr_pages = 1 << order;
struct page *p = page;
unsigned int loop;
prefetchw(p);
for (loop = 0; loop < (nr_pages - 1); loop++, p++) {
prefetchw(p + 1);
__ClearPageReserved(p);
set_page_count(p, 0);
}
__ClearPageReserved(p);
set_page_count(p, 0);
page_zone(page)->managed_pages += nr_pages;
set_page_refcounted(page);
__free_pages(page, order);
}
#if defined(CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID) || \
defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP)
static struct mminit_pfnnid_cache early_pfnnid_cache __meminitdata;
int __meminit early_pfn_to_nid(unsigned long pfn)
{
static DEFINE_SPINLOCK(early_pfn_lock);
int nid;
spin_lock(&early_pfn_lock);
nid = __early_pfn_to_nid(pfn, &early_pfnnid_cache);
if (nid < 0)
nid = 0;
spin_unlock(&early_pfn_lock);
return nid;
}
#endif
#ifdef CONFIG_NODES_SPAN_OTHER_NODES
static inline bool __meminit meminit_pfn_in_nid(unsigned long pfn, int node,
struct mminit_pfnnid_cache *state)
{
int nid;
nid = __early_pfn_to_nid(pfn, state);
if (nid >= 0 && nid != node)
return false;
return true;
}
/* Only safe to use early in boot when initialisation is single-threaded */
static inline bool __meminit early_pfn_in_nid(unsigned long pfn, int node)
{
return meminit_pfn_in_nid(pfn, node, &early_pfnnid_cache);
}
#else
static inline bool __meminit early_pfn_in_nid(unsigned long pfn, int node)
{
return true;
}
static inline bool __meminit meminit_pfn_in_nid(unsigned long pfn, int node,
struct mminit_pfnnid_cache *state)
{
return true;
}
#endif
void __init __free_pages_bootmem(struct page *page, unsigned long pfn,
unsigned int order)
{
if (early_page_uninitialised(pfn))
return;
return __free_pages_boot_core(page, pfn, order);
}
#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
static void __init deferred_free_range(struct page *page,
unsigned long pfn, int nr_pages)
{
int i;
if (!page)
return;
/* Free a large naturally-aligned chunk if possible */
if (nr_pages == MAX_ORDER_NR_PAGES &&
(pfn & (MAX_ORDER_NR_PAGES-1)) == 0) {
set_pageblock_migratetype(page, MIGRATE_MOVABLE);
__free_pages_boot_core(page, pfn, MAX_ORDER-1);
return;
}
for (i = 0; i < nr_pages; i++, page++, pfn++)
__free_pages_boot_core(page, pfn, 0);
}
/* Completion tracking for deferred_init_memmap() threads */
static atomic_t pgdat_init_n_undone __initdata;
static __initdata DECLARE_COMPLETION(pgdat_init_all_done_comp);
static inline void __init pgdat_init_report_one_done(void)
{
if (atomic_dec_and_test(&pgdat_init_n_undone))
complete(&pgdat_init_all_done_comp);
}
/* Initialise remaining memory on a node */
static int __init deferred_init_memmap(void *data)
{
pg_data_t *pgdat = data;
int nid = pgdat->node_id;
struct mminit_pfnnid_cache nid_init_state = { };
unsigned long start = jiffies;
unsigned long nr_pages = 0;
unsigned long walk_start, walk_end;
int i, zid;
struct zone *zone;
unsigned long first_init_pfn = pgdat->first_deferred_pfn;
const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id);
if (first_init_pfn == ULONG_MAX) {
pgdat_init_report_one_done();
return 0;
}
/* Bind memory initialisation thread to a local node if possible */
if (!cpumask_empty(cpumask))
set_cpus_allowed_ptr(current, cpumask);
/* Sanity check boundaries */
BUG_ON(pgdat->first_deferred_pfn < pgdat->node_start_pfn);
BUG_ON(pgdat->first_deferred_pfn > pgdat_end_pfn(pgdat));
pgdat->first_deferred_pfn = ULONG_MAX;
/* Only the highest zone is deferred so find it */
for (zid = 0; zid < MAX_NR_ZONES; zid++) {
zone = pgdat->node_zones + zid;
if (first_init_pfn < zone_end_pfn(zone))
break;
}
for_each_mem_pfn_range(i, nid, &walk_start, &walk_end, NULL) {
unsigned long pfn, end_pfn;
struct page *page = NULL;
struct page *free_base_page = NULL;
unsigned long free_base_pfn = 0;
int nr_to_free = 0;
end_pfn = min(walk_end, zone_end_pfn(zone));
pfn = first_init_pfn;
if (pfn < walk_start)
pfn = walk_start;
if (pfn < zone->zone_start_pfn)
pfn = zone->zone_start_pfn;
for (; pfn < end_pfn; pfn++) {
if (!pfn_valid_within(pfn))
goto free_range;
/*
* Ensure pfn_valid is checked every
* MAX_ORDER_NR_PAGES for memory holes
*/
if ((pfn & (MAX_ORDER_NR_PAGES - 1)) == 0) {
if (!pfn_valid(pfn)) {
page = NULL;
goto free_range;
}
}
if (!meminit_pfn_in_nid(pfn, nid, &nid_init_state)) {
page = NULL;
goto free_range;
}
/* Minimise pfn page lookups and scheduler checks */
if (page && (pfn & (MAX_ORDER_NR_PAGES - 1)) != 0) {
page++;
} else {
nr_pages += nr_to_free;
deferred_free_range(free_base_page,
free_base_pfn, nr_to_free);
free_base_page = NULL;
free_base_pfn = nr_to_free = 0;
page = pfn_to_page(pfn);
cond_resched();
}
if (page->flags) {
VM_BUG_ON(page_zone(page) != zone);
goto free_range;
}
__init_single_page(page, pfn, zid, nid);
if (!free_base_page) {
free_base_page = page;
free_base_pfn = pfn;
nr_to_free = 0;
}
nr_to_free++;
/* Where possible, batch up pages for a single free */
continue;
free_range:
/* Free the current block of pages to allocator */
nr_pages += nr_to_free;
deferred_free_range(free_base_page, free_base_pfn,
nr_to_free);
free_base_page = NULL;
free_base_pfn = nr_to_free = 0;
}
first_init_pfn = max(end_pfn, first_init_pfn);
}
/* Sanity check that the next zone really is unpopulated */
WARN_ON(++zid < MAX_NR_ZONES && populated_zone(++zone));
pr_info("node %d initialised, %lu pages in %ums\n", nid, nr_pages,
jiffies_to_msecs(jiffies - start));
pgdat_init_report_one_done();
return 0;
}
void __init page_alloc_init_late(void)
{
int nid;
/* There will be num_node_state(N_MEMORY) threads */
atomic_set(&pgdat_init_n_undone, num_node_state(N_MEMORY));
for_each_node_state(nid, N_MEMORY) {
kthread_run(deferred_init_memmap, NODE_DATA(nid), "pgdatinit%d", nid);
}
/* Block until all are initialised */
wait_for_completion(&pgdat_init_all_done_comp);
/* Reinit limits that are based on free pages after the kernel is up */
files_maxfiles_init();
}
#endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */
#ifdef CONFIG_CMA
/* Free whole pageblock and set its migration type to MIGRATE_CMA. */
void __init init_cma_reserved_pageblock(struct page *page)
{
unsigned i = pageblock_nr_pages;
struct page *p = page;
do {
__ClearPageReserved(p);
set_page_count(p, 0);
} while (++p, --i);
set_pageblock_migratetype(page, MIGRATE_CMA);
if (pageblock_order >= MAX_ORDER) {
i = pageblock_nr_pages;
p = page;
do {
set_page_refcounted(p);
__free_pages(p, MAX_ORDER - 1);
p += MAX_ORDER_NR_PAGES;
} while (i -= MAX_ORDER_NR_PAGES);
} else {
set_page_refcounted(page);
__free_pages(page, pageblock_order);
}
adjust_managed_page_count(page, pageblock_nr_pages);
}
#endif
/*
* The order of subdivision here is critical for the IO subsystem.
* Please do not alter this order without good reasons and regression
* testing. Specifically, as large blocks of memory are subdivided,
* the order in which smaller blocks are delivered depends on the order
* they're subdivided in this function. This is the primary factor
* influencing the order in which pages are delivered to the IO
* subsystem according to empirical testing, and this is also justified
* by considering the behavior of a buddy system containing a single
* large block of memory acted on by a series of small allocations.
* This behavior is a critical factor in sglist merging's success.
*
* -- nyc
*/
static inline void expand(struct zone *zone, struct page *page,
int low, int high, struct free_area *area,
int migratetype)
{
unsigned long size = 1 << high;
while (high > low) {
area--;
high--;
size >>= 1;
VM_BUG_ON_PAGE(bad_range(zone, &page[size]), &page[size]);
if (IS_ENABLED(CONFIG_DEBUG_PAGEALLOC) &&
debug_guardpage_enabled() &&
high < debug_guardpage_minorder()) {
/*
* Mark as guard pages (or page), that will allow to
* merge back to allocator when buddy will be freed.
* Corresponding page table entries will not be touched,
* pages will stay not present in virtual address space
*/
set_page_guard(zone, &page[size], high, migratetype);
continue;
}
list_add(&page[size].lru, &area->free_list[migratetype]);
area->nr_free++;
set_page_order(&page[size], high);
}
}
/*
* This page is about to be returned from the page allocator
*/
static inline int check_new_page(struct page *page)
{
const char *bad_reason = NULL;
unsigned long bad_flags = 0;
if (unlikely(page_mapcount(page)))
bad_reason = "nonzero mapcount";
if (unlikely(page->mapping != NULL))
bad_reason = "non-NULL mapping";
if (unlikely(atomic_read(&page->_count) != 0))
bad_reason = "nonzero _count";
if (unlikely(page->flags & __PG_HWPOISON)) {
bad_reason = "HWPoisoned (hardware-corrupted)";
bad_flags = __PG_HWPOISON;
}
if (unlikely(page->flags & PAGE_FLAGS_CHECK_AT_PREP)) {
bad_reason = "PAGE_FLAGS_CHECK_AT_PREP flag set";
bad_flags = PAGE_FLAGS_CHECK_AT_PREP;
}
#ifdef CONFIG_MEMCG
if (unlikely(page->mem_cgroup))
bad_reason = "page still charged to cgroup";
#endif
if (unlikely(bad_reason)) {
bad_page(page, bad_reason, bad_flags);
return 1;
}
return 0;
}
static int prep_new_page(struct page *page, unsigned int order, gfp_t gfp_flags,
int alloc_flags)
{
int i;
for (i = 0; i < (1 << order); i++) {
struct page *p = page + i;
if (unlikely(check_new_page(p)))
return 1;
}
set_page_private(page, 0);
set_page_refcounted(page);
arch_alloc_page(page, order);
kernel_map_pages(page, 1 << order, 1);
kasan_alloc_pages(page, order);
if (gfp_flags & __GFP_ZERO)
for (i = 0; i < (1 << order); i++)
clear_highpage(page + i);
if (order && (gfp_flags & __GFP_COMP))
prep_compound_page(page, order);
set_page_owner(page, order, gfp_flags);
/*
* page is set pfmemalloc when ALLOC_NO_WATERMARKS was necessary to
* allocate the page. The expectation is that the caller is taking
* steps that will free more memory. The caller should avoid the page
* being used for !PFMEMALLOC purposes.
*/
if (alloc_flags & ALLOC_NO_WATERMARKS)
set_page_pfmemalloc(page);
else
clear_page_pfmemalloc(page);
return 0;
}
/*
* Go through the free lists for the given migratetype and remove
* the smallest available page from the freelists
*/
static inline
struct page *__rmqueue_smallest(struct zone *zone, unsigned int order,
int migratetype)
{
unsigned int current_order;
struct free_area *area;
struct page *page;
/* Find a page of the appropriate size in the preferred list */
for (current_order = order; current_order < MAX_ORDER; ++current_order) {
area = &(zone->free_area[current_order]);
if (list_empty(&area->free_list[migratetype]))
continue;
page = list_entry(area->free_list[migratetype].next,
struct page, lru);
list_del(&page->lru);
rmv_page_order(page);
area->nr_free--;
expand(zone, page, order, current_order, area, migratetype);
set_freepage_migratetype(page, migratetype);
return page;
}
return NULL;
}
/*
* This array describes the order lists are fallen back to when
* the free lists for the desirable migrate type are depleted
*/
static int fallbacks[MIGRATE_TYPES][4] = {
[MIGRATE_UNMOVABLE] = { MIGRATE_RECLAIMABLE, MIGRATE_MOVABLE, MIGRATE_RESERVE },
[MIGRATE_RECLAIMABLE] = { MIGRATE_UNMOVABLE, MIGRATE_MOVABLE, MIGRATE_RESERVE },
[MIGRATE_MOVABLE] = { MIGRATE_RECLAIMABLE, MIGRATE_UNMOVABLE, MIGRATE_RESERVE },
#ifdef CONFIG_CMA
[MIGRATE_CMA] = { MIGRATE_RESERVE }, /* Never used */
#endif
[MIGRATE_RESERVE] = { MIGRATE_RESERVE }, /* Never used */
#ifdef CONFIG_MEMORY_ISOLATION
[MIGRATE_ISOLATE] = { MIGRATE_RESERVE }, /* Never used */
#endif
};
#ifdef CONFIG_CMA
static struct page *__rmqueue_cma_fallback(struct zone *zone,
unsigned int order)
{
return __rmqueue_smallest(zone, order, MIGRATE_CMA);
}
#else
static inline struct page *__rmqueue_cma_fallback(struct zone *zone,
unsigned int order) { return NULL; }
#endif
/*
* Move the free pages in a range to the free lists of the requested type.
* Note that start_page and end_pages are not aligned on a pageblock
* boundary. If alignment is required, use move_freepages_block()
*/
int move_freepages(struct zone *zone,
struct page *start_page, struct page *end_page,
int migratetype)
{
struct page *page;
unsigned long order;
int pages_moved = 0;
#ifndef CONFIG_HOLES_IN_ZONE
/*
* page_zone is not safe to call in this context when
* CONFIG_HOLES_IN_ZONE is set. This bug check is probably redundant
* anyway as we check zone boundaries in move_freepages_block().
* Remove at a later date when no bug reports exist related to
* grouping pages by mobility
*/
VM_BUG_ON(page_zone(start_page) != page_zone(end_page));
#endif
for (page = start_page; page <= end_page;) {
/* Make sure we are not inadvertently changing nodes */
VM_BUG_ON_PAGE(page_to_nid(page) != zone_to_nid(zone), page);
if (!pfn_valid_within(page_to_pfn(page))) {
page++;
continue;
}
if (!PageBuddy(page)) {
page++;
continue;
}
order = page_order(page);
list_move(&page->lru,
&zone->free_area[order].free_list[migratetype]);
set_freepage_migratetype(page, migratetype);
page += 1 << order;
pages_moved += 1 << order;
}
return pages_moved;
}
int move_freepages_block(struct zone *zone, struct page *page,
int migratetype)
{
unsigned long start_pfn, end_pfn;
struct page *start_page, *end_page;
start_pfn = page_to_pfn(page);
start_pfn = start_pfn & ~(pageblock_nr_pages-1);
start_page = pfn_to_page(start_pfn);
end_page = start_page + pageblock_nr_pages - 1;
end_pfn = start_pfn + pageblock_nr_pages - 1;
/* Do not cross zone boundaries */
if (!zone_spans_pfn(zone, start_pfn))
start_page = page;
if (!zone_spans_pfn(zone, end_pfn))
return 0;
return move_freepages(zone, start_page, end_page, migratetype);
}
static void change_pageblock_range(struct page *pageblock_page,
int start_order, int migratetype)
{
int nr_pageblocks = 1 << (start_order - pageblock_order);
while (nr_pageblocks--) {
set_pageblock_migratetype(pageblock_page, migratetype);
pageblock_page += pageblock_nr_pages;
}
}
/*
* When we are falling back to another migratetype during allocation, try to
* steal extra free pages from the same pageblocks to satisfy further
* allocations, instead of polluting multiple pageblocks.
*
* If we are stealing a relatively large buddy page, it is likely there will
* be more free pages in the pageblock, so try to steal them all. For
* reclaimable and unmovable allocations, we steal regardless of page size,
* as fragmentation caused by those allocations polluting movable pageblocks
* is worse than movable allocations stealing from unmovable and reclaimable
* pageblocks.
*/
static bool can_steal_fallback(unsigned int order, int start_mt)
{
/*
* Leaving this order check is intended, although there is
* relaxed order check in next check. The reason is that
* we can actually steal whole pageblock if this condition met,
* but, below check doesn't guarantee it and that is just heuristic
* so could be changed anytime.
*/
if (order >= pageblock_order)
return true;
if (order >= pageblock_order / 2 ||
start_mt == MIGRATE_RECLAIMABLE ||
start_mt == MIGRATE_UNMOVABLE ||
page_group_by_mobility_disabled)
return true;
return false;
}
/*
* This function implements actual steal behaviour. If order is large enough,
* we can steal whole pageblock. If not, we first move freepages in this
* pageblock and check whether half of pages are moved or not. If half of
* pages are moved, we can change migratetype of pageblock and permanently
* use it's pages as requested migratetype in the future.
*/
static void steal_suitable_fallback(struct zone *zone, struct page *page,
int start_type)
{
int current_order = page_order(page);
int pages;
/* Take ownership for orders >= pageblock_order */
if (current_order >= pageblock_order) {
change_pageblock_range(page, current_order, start_type);
return;
}
pages = move_freepages_block(zone, page, start_type);
/* Claim the whole block if over half of it is free */
if (pages >= (1 << (pageblock_order-1)) ||
page_group_by_mobility_disabled)
set_pageblock_migratetype(page, start_type);
}
/*
* Check whether there is a suitable fallback freepage with requested order.
* If only_stealable is true, this function returns fallback_mt only if
* we can steal other freepages all together. This would help to reduce
* fragmentation due to mixed migratetype pages in one pageblock.
*/
int find_suitable_fallback(struct free_area *area, unsigned int order,
int migratetype, bool only_stealable, bool *can_steal)
{
int i;
int fallback_mt;
if (area->nr_free == 0)
return -1;
*can_steal = false;
for (i = 0;; i++) {
fallback_mt = fallbacks[migratetype][i];
if (fallback_mt == MIGRATE_RESERVE)
break;
if (list_empty(&area->free_list[fallback_mt]))
continue;
if (can_steal_fallback(order, migratetype))
*can_steal = true;
if (!only_stealable)
return fallback_mt;
if (*can_steal)
return fallback_mt;
}
return -1;
}
/* Remove an element from the buddy allocator from the fallback list */
static inline struct page *
__rmqueue_fallback(struct zone *zone, unsigned int order, int start_migratetype)
{
struct free_area *area;
unsigned int current_order;
struct page *page;
int fallback_mt;
bool can_steal;
/* Find the largest possible block of pages in the other list */
for (current_order = MAX_ORDER-1;
current_order >= order && current_order <= MAX_ORDER-1;
--current_order) {
area = &(zone->free_area[current_order]);
fallback_mt = find_suitable_fallback(area, current_order,
start_migratetype, false, &can_steal);
if (fallback_mt == -1)
continue;
page = list_entry(area->free_list[fallback_mt].next,
struct page, lru);
if (can_steal)
steal_suitable_fallback(zone, page, start_migratetype);
/* Remove the page from the freelists */
area->nr_free--;
list_del(&page->lru);
rmv_page_order(page);
expand(zone, page, order, current_order, area,
start_migratetype);
/*
* The freepage_migratetype may differ from pageblock's
* migratetype depending on the decisions in
* try_to_steal_freepages(). This is OK as long as it
* does not differ for MIGRATE_CMA pageblocks. For CMA
* we need to make sure unallocated pages flushed from
* pcp lists are returned to the correct freelist.
*/
set_freepage_migratetype(page, start_migratetype);
trace_mm_page_alloc_extfrag(page, order, current_order,
start_migratetype, fallback_mt);
return page;
}
return NULL;
}
/*
* Do the hard work of removing an element from the buddy allocator.
* Call me with the zone->lock already held.
*/
static struct page *__rmqueue(struct zone *zone, unsigned int order,
int migratetype)
{
struct page *page;
retry_reserve:
page = __rmqueue_smallest(zone, order, migratetype);
if (unlikely(!page) && migratetype != MIGRATE_RESERVE) {
if (migratetype == MIGRATE_MOVABLE)
page = __rmqueue_cma_fallback(zone, order);
if (!page)
page = __rmqueue_fallback(zone, order, migratetype);
/*
* Use MIGRATE_RESERVE rather than fail an allocation. goto
* is used because __rmqueue_smallest is an inline function
* and we want just one call site
*/
if (!page) {
migratetype = MIGRATE_RESERVE;
goto retry_reserve;
}
}
trace_mm_page_alloc_zone_locked(page, order, migratetype);
return page;
}
/*
* Obtain a specified number of elements from the buddy allocator, all under
* a single hold of the lock, for efficiency. Add them to the supplied list.
* Returns the number of new pages which were placed at *list.
*/
static int rmqueue_bulk(struct zone *zone, unsigned int order,
unsigned long count, struct list_head *list,
int migratetype, bool cold)
{
int i;
spin_lock(&zone->lock);
for (i = 0; i < count; ++i) {
struct page *page = __rmqueue(zone, order, migratetype);
if (unlikely(page == NULL))
break;
/*
* Split buddy pages returned by expand() are received here
* in physical page order. The page is added to the callers and
* list and the list head then moves forward. From the callers
* perspective, the linked list is ordered by page number in
* some conditions. This is useful for IO devices that can
* merge IO requests if the physical pages are ordered
* properly.
*/
if (likely(!cold))
list_add(&page->lru, list);
else
list_add_tail(&page->lru, list);
list = &page->lru;
if (is_migrate_cma(get_freepage_migratetype(page)))
__mod_zone_page_state(zone, NR_FREE_CMA_PAGES,
-(1 << order));
}
__mod_zone_page_state(zone, NR_FREE_PAGES, -(i << order));
spin_unlock(&zone->lock);
return i;
}
#ifdef CONFIG_NUMA
/*
* Called from the vmstat counter updater to drain pagesets of this
* currently executing processor on remote nodes after they have
* expired.
*
* Note that this function must be called with the thread pinned to
* a single processor.
*/
void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp)
{
unsigned long flags;
int to_drain, batch;
local_irq_save(flags);
batch = READ_ONCE(pcp->batch);
to_drain = min(pcp->count, batch);
if (to_drain > 0) {
free_pcppages_bulk(zone, to_drain, pcp);
pcp->count -= to_drain;
}
local_irq_restore(flags);
}
#endif
/*
* Drain pcplists of the indicated processor and zone.
*
* The processor must either be the current processor and the
* thread pinned to the current processor or a processor that
* is not online.
*/
static void drain_pages_zone(unsigned int cpu, struct zone *zone)
{
unsigned long flags;
struct per_cpu_pageset *pset;
struct per_cpu_pages *pcp;
local_irq_save(flags);
pset = per_cpu_ptr(zone->pageset, cpu);
pcp = &pset->pcp;
if (pcp->count) {
free_pcppages_bulk(zone, pcp->count, pcp);
pcp->count = 0;
}
local_irq_restore(flags);
}
/*
* Drain pcplists of all zones on the indicated processor.
*
* The processor must either be the current processor and the
* thread pinned to the current processor or a processor that
* is not online.
*/
static void drain_pages(unsigned int cpu)
{
struct zone *zone;
for_each_populated_zone(zone) {
drain_pages_zone(cpu, zone);
}
}
/*
* Spill all of this CPU's per-cpu pages back into the buddy allocator.
*
* The CPU has to be pinned. When zone parameter is non-NULL, spill just
* the single zone's pages.
*/
void drain_local_pages(struct zone *zone)
{
int cpu = smp_processor_id();
if (zone)
drain_pages_zone(cpu, zone);
else
drain_pages(cpu);
}
/*
* Spill all the per-cpu pages from all CPUs back into the buddy allocator.
*
* When zone parameter is non-NULL, spill just the single zone's pages.
*
* Note that this code is protected against sending an IPI to an offline
* CPU but does not guarantee sending an IPI to newly hotplugged CPUs:
* on_each_cpu_mask() blocks hotplug and won't talk to offlined CPUs but
* nothing keeps CPUs from showing up after we populated the cpumask and
* before the call to on_each_cpu_mask().
*/
void drain_all_pages(struct zone *zone)
{
int cpu;
/*
* Allocate in the BSS so we wont require allocation in
* direct reclaim path for CONFIG_CPUMASK_OFFSTACK=y
*/
static cpumask_t cpus_with_pcps;
/*
* We don't care about racing with CPU hotplug event
* as offline notification will cause the notified
* cpu to drain that CPU pcps and on_each_cpu_mask
* disables preemption as part of its processing
*/
for_each_online_cpu(cpu) {
struct per_cpu_pageset *pcp;
struct zone *z;
bool has_pcps = false;
if (zone) {
pcp = per_cpu_ptr(zone->pageset, cpu);
if (pcp->pcp.count)
has_pcps = true;
} else {
for_each_populated_zone(z) {
pcp = per_cpu_ptr(z->pageset, cpu);
if (pcp->pcp.count) {
has_pcps = true;
break;
}
}
}
if (has_pcps)
cpumask_set_cpu(cpu, &cpus_with_pcps);
else
cpumask_clear_cpu(cpu, &cpus_with_pcps);
}
on_each_cpu_mask(&cpus_with_pcps, (smp_call_func_t) drain_local_pages,
zone, 1);
}
#ifdef CONFIG_HIBERNATION
void mark_free_pages(struct zone *zone)
{
unsigned long pfn, max_zone_pfn;
unsigned long flags;
unsigned int order, t;
struct list_head *curr;
if (zone_is_empty(zone))
return;
spin_lock_irqsave(&zone->lock, flags);
max_zone_pfn = zone_end_pfn(zone);
for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++)
if (pfn_valid(pfn)) {
struct page *page = pfn_to_page(pfn);
if (!swsusp_page_is_forbidden(page))
swsusp_unset_page_free(page);
}
for_each_migratetype_order(order, t) {
list_for_each(curr, &zone->free_area[order].free_list[t]) {
unsigned long i;
pfn = page_to_pfn(list_entry(curr, struct page, lru));
for (i = 0; i < (1UL << order); i++)
swsusp_set_page_free(pfn_to_page(pfn + i));
}
}
spin_unlock_irqrestore(&zone->lock, flags);
}
#endif /* CONFIG_PM */
/*
* Free a 0-order page
* cold == true ? free a cold page : free a hot page
*/
void free_hot_cold_page(struct page *page, bool cold)
{
struct zone *zone = page_zone(page);
struct per_cpu_pages *pcp;
unsigned long flags;
unsigned long pfn = page_to_pfn(page);
int migratetype;
if (!free_pages_prepare(page, 0))
return;
migratetype = get_pfnblock_migratetype(page, pfn);
set_freepage_migratetype(page, migratetype);
local_irq_save(flags);
__count_vm_event(PGFREE);
/*
* We only track unmovable, reclaimable and movable on pcp lists.
* Free ISOLATE pages back to the allocator because they are being
* offlined but treat RESERVE as movable pages so we can get those
* areas back if necessary. Otherwise, we may have to free
* excessively into the page allocator
*/
if (migratetype >= MIGRATE_PCPTYPES) {
if (unlikely(is_migrate_isolate(migratetype))) {
free_one_page(zone, page, pfn, 0, migratetype);
goto out;
}
migratetype = MIGRATE_MOVABLE;
}
pcp = &this_cpu_ptr(zone->pageset)->pcp;
if (!cold)
list_add(&page->lru, &pcp->lists[migratetype]);
else
list_add_tail(&page->lru, &pcp->lists[migratetype]);
pcp->count++;
if (pcp->count >= pcp->high) {
unsigned long batch = READ_ONCE(pcp->batch);
free_pcppages_bulk(zone, batch, pcp);
pcp->count -= batch;
}
out:
local_irq_restore(flags);
}
/*
* Free a list of 0-order pages
*/
void free_hot_cold_page_list(struct list_head *list, bool cold)
{
struct page *page, *next;
list_for_each_entry_safe(page, next, list, lru) {
trace_mm_page_free_batched(page, cold);
free_hot_cold_page(page, cold);
}
}
/*
* split_page takes a non-compound higher-order page, and splits it into
* n (1<<order) sub-pages: page[0..n]
* Each sub-page must be freed individually.
*
* Note: this is probably too low level an operation for use in drivers.
* Please consult with lkml before using this in your driver.
*/
void split_page(struct page *page, unsigned int order)
{
int i;
gfp_t gfp_mask;
VM_BUG_ON_PAGE(PageCompound(page), page);
VM_BUG_ON_PAGE(!page_count(page), page);
#ifdef CONFIG_KMEMCHECK
/*
* Split shadow pages too, because free(page[0]) would
* otherwise free the whole shadow.
*/
if (kmemcheck_page_is_tracked(page))
split_page(virt_to_page(page[0].shadow), order);
#endif
gfp_mask = get_page_owner_gfp(page);
set_page_owner(page, 0, gfp_mask);
for (i = 1; i < (1 << order); i++) {
set_page_refcounted(page + i);
set_page_owner(page + i, 0, gfp_mask);
}
}
EXPORT_SYMBOL_GPL(split_page);
int __isolate_free_page(struct page *page, unsigned int order)
{
unsigned long watermark;
struct zone *zone;
int mt;
BUG_ON(!PageBuddy(page));
zone = page_zone(page);
mt = get_pageblock_migratetype(page);
if (!is_migrate_isolate(mt)) {
/* Obey watermarks as if the page was being allocated */
watermark = low_wmark_pages(zone) + (1 << order);
if (!zone_watermark_ok(zone, 0, watermark, 0, 0))
return 0;
__mod_zone_freepage_state(zone, -(1UL << order), mt);
}
/* Remove page from free list */
list_del(&page->lru);
zone->free_area[order].nr_free--;
rmv_page_order(page);
set_page_owner(page, order, __GFP_MOVABLE);
/* Set the pageblock if the isolated page is at least a pageblock */
if (order >= pageblock_order - 1) {
struct page *endpage = page + (1 << order) - 1;
for (; page < endpage; page += pageblock_nr_pages) {
int mt = get_pageblock_migratetype(page);
if (!is_migrate_isolate(mt) && !is_migrate_cma(mt))
set_pageblock_migratetype(page,
MIGRATE_MOVABLE);
}
}
return 1UL << order;
}
/*
* Similar to split_page except the page is already free. As this is only
* being used for migration, the migratetype of the block also changes.
* As this is called with interrupts disabled, the caller is responsible
* for calling arch_alloc_page() and kernel_map_page() after interrupts
* are enabled.
*
* Note: this is probably too low level an operation for use in drivers.
* Please consult with lkml before using this in your driver.
*/
int split_free_page(struct page *page)
{
unsigned int order;
int nr_pages;
order = page_order(page);
nr_pages = __isolate_free_page(page, order);
if (!nr_pages)
return 0;
/* Split into individual pages */
set_page_refcounted(page);
split_page(page, order);
return nr_pages;
}
/*
* Allocate a page from the given zone. Use pcplists for order-0 allocations.
*/
static inline
struct page *buffered_rmqueue(struct zone *preferred_zone,
struct zone *zone, unsigned int order,
gfp_t gfp_flags, int migratetype)
{
unsigned long flags;
struct page *page;
bool cold = ((gfp_flags & __GFP_COLD) != 0);
if (likely(order == 0)) {
struct per_cpu_pages *pcp;
struct list_head *list;
local_irq_save(flags);
pcp = &this_cpu_ptr(zone->pageset)->pcp;
list = &pcp->lists[migratetype];
if (list_empty(list)) {
pcp->count += rmqueue_bulk(zone, 0,
pcp->batch, list,
migratetype, cold);
if (unlikely(list_empty(list)))
goto failed;
}
if (cold)
page = list_entry(list->prev, struct page, lru);
else
page = list_entry(list->next, struct page, lru);
list_del(&page->lru);
pcp->count--;
} else {
if (unlikely(gfp_flags & __GFP_NOFAIL)) {
/*
* __GFP_NOFAIL is not to be used in new code.
*
* All __GFP_NOFAIL callers should be fixed so that they
* properly detect and handle allocation failures.
*
* We most definitely don't want callers attempting to
* allocate greater than order-1 page units with
* __GFP_NOFAIL.
*/
WARN_ON_ONCE(order > 1);
}
spin_lock_irqsave(&zone->lock, flags);
page = __rmqueue(zone, order, migratetype);
spin_unlock(&zone->lock);
if (!page)
goto failed;
__mod_zone_freepage_state(zone, -(1 << order),
get_freepage_migratetype(page));
}
__mod_zone_page_state(zone, NR_ALLOC_BATCH, -(1 << order));
if (atomic_long_read(&zone->vm_stat[NR_ALLOC_BATCH]) <= 0 &&
!test_bit(ZONE_FAIR_DEPLETED, &zone->flags))
set_bit(ZONE_FAIR_DEPLETED, &zone->flags);
__count_zone_vm_events(PGALLOC, zone, 1 << order);
zone_statistics(preferred_zone, zone, gfp_flags);
local_irq_restore(flags);
VM_BUG_ON_PAGE(bad_range(zone, page), page);
return page;
failed:
local_irq_restore(flags);
return NULL;
}
#ifdef CONFIG_FAIL_PAGE_ALLOC
static struct {
struct fault_attr attr;
u32 ignore_gfp_highmem;
u32 ignore_gfp_wait;
u32 min_order;
} fail_page_alloc = {
.attr = FAULT_ATTR_INITIALIZER,
.ignore_gfp_wait = 1,
.ignore_gfp_highmem = 1,
.min_order = 1,
};
static int __init setup_fail_page_alloc(char *str)
{
return setup_fault_attr(&fail_page_alloc.attr, str);
}
__setup("fail_page_alloc=", setup_fail_page_alloc);
static bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order)
{
if (order < fail_page_alloc.min_order)
return false;
if (gfp_mask & __GFP_NOFAIL)
return false;
if (fail_page_alloc.ignore_gfp_highmem && (gfp_mask & __GFP_HIGHMEM))
return false;
if (fail_page_alloc.ignore_gfp_wait && (gfp_mask & __GFP_WAIT))
return false;
return should_fail(&fail_page_alloc.attr, 1 << order);
}
#ifdef CONFIG_FAULT_INJECTION_DEBUG_FS
static int __init fail_page_alloc_debugfs(void)
{
umode_t mode = S_IFREG | S_IRUSR | S_IWUSR;
struct dentry *dir;
dir = fault_create_debugfs_attr("fail_page_alloc", NULL,
&fail_page_alloc.attr);
if (IS_ERR(dir))
return PTR_ERR(dir);
if (!debugfs_create_bool("ignore-gfp-wait", mode, dir,
&fail_page_alloc.ignore_gfp_wait))
goto fail;
if (!debugfs_create_bool("ignore-gfp-highmem", mode, dir,
&fail_page_alloc.ignore_gfp_highmem))
goto fail;
if (!debugfs_create_u32("min-order", mode, dir,
&fail_page_alloc.min_order))
goto fail;
return 0;
fail:
debugfs_remove_recursive(dir);
return -ENOMEM;
}
late_initcall(fail_page_alloc_debugfs);
#endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */
#else /* CONFIG_FAIL_PAGE_ALLOC */
static inline bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order)
{
return false;
}
#endif /* CONFIG_FAIL_PAGE_ALLOC */
/*
* Return true if free pages are above 'mark'. This takes into account the order
* of the allocation.
*/
static bool __zone_watermark_ok(struct zone *z, unsigned int order,
unsigned long mark, int classzone_idx, int alloc_flags,
long free_pages)
{
/* free_pages may go negative - that's OK */
long min = mark;
int o;
long free_cma = 0;
free_pages -= (1 << order) - 1;
if (alloc_flags & ALLOC_HIGH)
min -= min / 2;
if (alloc_flags & ALLOC_HARDER)
min -= min / 4;
#ifdef CONFIG_CMA
/* If allocation can't use CMA areas don't use free CMA pages */
if (!(alloc_flags & ALLOC_CMA))
free_cma = zone_page_state(z, NR_FREE_CMA_PAGES);
#endif
if (free_pages - free_cma <= min + z->lowmem_reserve[classzone_idx])
return false;
for (o = 0; o < order; o++) {
/* At the next order, this order's pages become unavailable */
free_pages -= z->free_area[o].nr_free << o;
/* Require fewer higher order pages to be free */
min >>= 1;
if (free_pages <= min)
return false;
}
return true;
}
bool zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
int classzone_idx, int alloc_flags)
{
return __zone_watermark_ok(z, order, mark, classzone_idx, alloc_flags,
zone_page_state(z, NR_FREE_PAGES));
}
bool zone_watermark_ok_safe(struct zone *z, unsigned int order,
unsigned long mark, int classzone_idx, int alloc_flags)
{
long free_pages = zone_page_state(z, NR_FREE_PAGES);
if (z->percpu_drift_mark && free_pages < z->percpu_drift_mark)
free_pages = zone_page_state_snapshot(z, NR_FREE_PAGES);
return __zone_watermark_ok(z, order, mark, classzone_idx, alloc_flags,
free_pages);
}
#ifdef CONFIG_NUMA
/*
* zlc_setup - Setup for "zonelist cache". Uses cached zone data to
* skip over zones that are not allowed by the cpuset, or that have
* been recently (in last second) found to be nearly full. See further
* comments in mmzone.h. Reduces cache footprint of zonelist scans
* that have to skip over a lot of full or unallowed zones.
*
* If the zonelist cache is present in the passed zonelist, then
* returns a pointer to the allowed node mask (either the current
* tasks mems_allowed, or node_states[N_MEMORY].)
*
* If the zonelist cache is not available for this zonelist, does
* nothing and returns NULL.
*
* If the fullzones BITMAP in the zonelist cache is stale (more than
* a second since last zap'd) then we zap it out (clear its bits.)
*
* We hold off even calling zlc_setup, until after we've checked the
* first zone in the zonelist, on the theory that most allocations will
* be satisfied from that first zone, so best to examine that zone as
* quickly as we can.
*/
static nodemask_t *zlc_setup(struct zonelist *zonelist, int alloc_flags)
{
struct zonelist_cache *zlc; /* cached zonelist speedup info */
nodemask_t *allowednodes; /* zonelist_cache approximation */
zlc = zonelist->zlcache_ptr;
if (!zlc)
return NULL;
if (time_after(jiffies, zlc->last_full_zap + HZ)) {
bitmap_zero(zlc->fullzones, MAX_ZONES_PER_ZONELIST);
zlc->last_full_zap = jiffies;
}
allowednodes = !in_interrupt() && (alloc_flags & ALLOC_CPUSET) ?
&cpuset_current_mems_allowed :
&node_states[N_MEMORY];
return allowednodes;
}
/*
* Given 'z' scanning a zonelist, run a couple of quick checks to see
* if it is worth looking at further for free memory:
* 1) Check that the zone isn't thought to be full (doesn't have its
* bit set in the zonelist_cache fullzones BITMAP).
* 2) Check that the zones node (obtained from the zonelist_cache
* z_to_n[] mapping) is allowed in the passed in allowednodes mask.
* Return true (non-zero) if zone is worth looking at further, or
* else return false (zero) if it is not.
*
* This check -ignores- the distinction between various watermarks,
* such as GFP_HIGH, GFP_ATOMIC, PF_MEMALLOC, ... If a zone is
* found to be full for any variation of these watermarks, it will
* be considered full for up to one second by all requests, unless
* we are so low on memory on all allowed nodes that we are forced
* into the second scan of the zonelist.
*
* In the second scan we ignore this zonelist cache and exactly
* apply the watermarks to all zones, even it is slower to do so.
* We are low on memory in the second scan, and should leave no stone
* unturned looking for a free page.
*/
static int zlc_zone_worth_trying(struct zonelist *zonelist, struct zoneref *z,
nodemask_t *allowednodes)
{
struct zonelist_cache *zlc; /* cached zonelist speedup info */
int i; /* index of *z in zonelist zones */
int n; /* node that zone *z is on */
zlc = zonelist->zlcache_ptr;
if (!zlc)
return 1;
i = z - zonelist->_zonerefs;
n = zlc->z_to_n[i];
/* This zone is worth trying if it is allowed but not full */
return node_isset(n, *allowednodes) && !test_bit(i, zlc->fullzones);
}
/*
* Given 'z' scanning a zonelist, set the corresponding bit in
* zlc->fullzones, so that subsequent attempts to allocate a page
* from that zone don't waste time re-examining it.
*/
static void zlc_mark_zone_full(struct zonelist *zonelist, struct zoneref *z)
{
struct zonelist_cache *zlc; /* cached zonelist speedup info */
int i; /* index of *z in zonelist zones */
zlc = zonelist->zlcache_ptr;
if (!zlc)
return;
i = z - zonelist->_zonerefs;
set_bit(i, zlc->fullzones);
}
/*
* clear all zones full, called after direct reclaim makes progress so that
* a zone that was recently full is not skipped over for up to a second
*/
static void zlc_clear_zones_full(struct zonelist *zonelist)
{
struct zonelist_cache *zlc; /* cached zonelist speedup info */
zlc = zonelist->zlcache_ptr;
if (!zlc)
return;
bitmap_zero(zlc->fullzones, MAX_ZONES_PER_ZONELIST);
}
static bool zone_local(struct zone *local_zone, struct zone *zone)
{
return local_zone->node == zone->node;
}
static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone)
{
return node_distance(zone_to_nid(local_zone), zone_to_nid(zone)) <
RECLAIM_DISTANCE;
}
#else /* CONFIG_NUMA */
static nodemask_t *zlc_setup(struct zonelist *zonelist, int alloc_flags)
{
return NULL;
}
static int zlc_zone_worth_trying(struct zonelist *zonelist, struct zoneref *z,
nodemask_t *allowednodes)
{
return 1;
}
static void zlc_mark_zone_full(struct zonelist *zonelist, struct zoneref *z)
{
}
static void zlc_clear_zones_full(struct zonelist *zonelist)
{
}
static bool zone_local(struct zone *local_zone, struct zone *zone)
{
return true;
}
static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone)
{
return true;
}
#endif /* CONFIG_NUMA */
static void reset_alloc_batches(struct zone *preferred_zone)
{
struct zone *zone = preferred_zone->zone_pgdat->node_zones;
do {
mod_zone_page_state(zone, NR_ALLOC_BATCH,
high_wmark_pages(zone) - low_wmark_pages(zone) -
atomic_long_read(&zone->vm_stat[NR_ALLOC_BATCH]));
clear_bit(ZONE_FAIR_DEPLETED, &zone->flags);
} while (zone++ != preferred_zone);
}
/*
* get_page_from_freelist goes through the zonelist trying to allocate
* a page.
*/
static struct page *
get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags,
const struct alloc_context *ac)
{
struct zonelist *zonelist = ac->zonelist;
struct zoneref *z;
struct page *page = NULL;
struct zone *zone;
nodemask_t *allowednodes = NULL;/* zonelist_cache approximation */
int zlc_active = 0; /* set if using zonelist_cache */
int did_zlc_setup = 0; /* just call zlc_setup() one time */
bool consider_zone_dirty = (alloc_flags & ALLOC_WMARK_LOW) &&
(gfp_mask & __GFP_WRITE);
int nr_fair_skipped = 0;
bool zonelist_rescan;
zonelist_scan:
zonelist_rescan = false;
/*
* Scan zonelist, looking for a zone with enough free.
* See also __cpuset_node_allowed() comment in kernel/cpuset.c.
*/
for_each_zone_zonelist_nodemask(zone, z, zonelist, ac->high_zoneidx,
ac->nodemask) {
unsigned long mark;
if (IS_ENABLED(CONFIG_NUMA) && zlc_active &&
!zlc_zone_worth_trying(zonelist, z, allowednodes))
continue;
if (cpusets_enabled() &&
(alloc_flags & ALLOC_CPUSET) &&
!cpuset_zone_allowed(zone, gfp_mask))
continue;
/*
* Distribute pages in proportion to the individual
* zone size to ensure fair page aging. The zone a
* page was allocated in should have no effect on the
* time the page has in memory before being reclaimed.
*/
if (alloc_flags & ALLOC_FAIR) {
if (!zone_local(ac->preferred_zone, zone))
break;
if (test_bit(ZONE_FAIR_DEPLETED, &zone->flags)) {
nr_fair_skipped++;
continue;
}
}
/*
* When allocating a page cache page for writing, we
* want to get it from a zone that is within its dirty
* limit, such that no single zone holds more than its
* proportional share of globally allowed dirty pages.
* The dirty limits take into account the zone's
* lowmem reserves and high watermark so that kswapd
* should be able to balance it without having to
* write pages from its LRU list.
*
* This may look like it could increase pressure on
* lower zones by failing allocations in higher zones
* before they are full. But the pages that do spill
* over are limited as the lower zones are protected
* by this very same mechanism. It should not become
* a practical burden to them.
*
* XXX: For now, allow allocations to potentially
* exceed the per-zone dirty limit in the slowpath
* (ALLOC_WMARK_LOW unset) before going into reclaim,
* which is important when on a NUMA setup the allowed
* zones are together not big enough to reach the
* global limit. The proper fix for these situations
* will require awareness of zones in the
* dirty-throttling and the flusher threads.
*/
if (consider_zone_dirty && !zone_dirty_ok(zone))
continue;
mark = zone->watermark[alloc_flags & ALLOC_WMARK_MASK];
if (!zone_watermark_ok(zone, order, mark,
ac->classzone_idx, alloc_flags)) {
int ret;
/* Checked here to keep the fast path fast */
BUILD_BUG_ON(ALLOC_NO_WATERMARKS < NR_WMARK);
if (alloc_flags & ALLOC_NO_WATERMARKS)
goto try_this_zone;
if (IS_ENABLED(CONFIG_NUMA) &&
!did_zlc_setup && nr_online_nodes > 1) {
/*
* we do zlc_setup if there are multiple nodes
* and before considering the first zone allowed
* by the cpuset.
*/
allowednodes = zlc_setup(zonelist, alloc_flags);
zlc_active = 1;
did_zlc_setup = 1;
}
if (zone_reclaim_mode == 0 ||
!zone_allows_reclaim(ac->preferred_zone, zone))
goto this_zone_full;
/*
* As we may have just activated ZLC, check if the first
* eligible zone has failed zone_reclaim recently.
*/
if (IS_ENABLED(CONFIG_NUMA) && zlc_active &&
!zlc_zone_worth_trying(zonelist, z, allowednodes))
continue;
ret = zone_reclaim(zone, gfp_mask, order);
switch (ret) {
case ZONE_RECLAIM_NOSCAN:
/* did not scan */
continue;
case ZONE_RECLAIM_FULL:
/* scanned but unreclaimable */
continue;
default:
/* did we reclaim enough */
if (zone_watermark_ok(zone, order, mark,
ac->classzone_idx, alloc_flags))
goto try_this_zone;
/*
* Failed to reclaim enough to meet watermark.
* Only mark the zone full if checking the min
* watermark or if we failed to reclaim just
* 1<<order pages or else the page allocator
* fastpath will prematurely mark zones full
* when the watermark is between the low and
* min watermarks.
*/
if (((alloc_flags & ALLOC_WMARK_MASK) == ALLOC_WMARK_MIN) ||
ret == ZONE_RECLAIM_SOME)
goto this_zone_full;
continue;
}
}
try_this_zone:
page = buffered_rmqueue(ac->preferred_zone, zone, order,
gfp_mask, ac->migratetype);
if (page) {
if (prep_new_page(page, order, gfp_mask, alloc_flags))
goto try_this_zone;
return page;
}
this_zone_full:
if (IS_ENABLED(CONFIG_NUMA) && zlc_active)
zlc_mark_zone_full(zonelist, z);
}
/*
* The first pass makes sure allocations are spread fairly within the
* local node. However, the local node might have free pages left
* after the fairness batches are exhausted, and remote zones haven't
* even been considered yet. Try once more without fairness, and
* include remote zones now, before entering the slowpath and waking
* kswapd: prefer spilling to a remote zone over swapping locally.
*/
if (alloc_flags & ALLOC_FAIR) {
alloc_flags &= ~ALLOC_FAIR;
if (nr_fair_skipped) {
zonelist_rescan = true;
reset_alloc_batches(ac->preferred_zone);
}
if (nr_online_nodes > 1)
zonelist_rescan = true;
}
if (unlikely(IS_ENABLED(CONFIG_NUMA) && zlc_active)) {
/* Disable zlc cache for second zonelist scan */
zlc_active = 0;
zonelist_rescan = true;
}
if (zonelist_rescan)
goto zonelist_scan;
return NULL;
}
/*
* Large machines with many possible nodes should not always dump per-node
* meminfo in irq context.
*/
static inline bool should_suppress_show_mem(void)
{
bool ret = false;
#if NODES_SHIFT > 8
ret = in_interrupt();
#endif
return ret;
}
static DEFINE_RATELIMIT_STATE(nopage_rs,
DEFAULT_RATELIMIT_INTERVAL,
DEFAULT_RATELIMIT_BURST);
void warn_alloc_failed(gfp_t gfp_mask, int order, const char *fmt, ...)
{
unsigned int filter = SHOW_MEM_FILTER_NODES;
if ((gfp_mask & __GFP_NOWARN) || !__ratelimit(&nopage_rs) ||
debug_guardpage_minorder() > 0)
return;
/*
* This documents exceptions given to allocations in certain
* contexts that are allowed to allocate outside current's set
* of allowed nodes.
*/
if (!(gfp_mask & __GFP_NOMEMALLOC))
if (test_thread_flag(TIF_MEMDIE) ||
(current->flags & (PF_MEMALLOC | PF_EXITING)))
filter &= ~SHOW_MEM_FILTER_NODES;
if (in_interrupt() || !(gfp_mask & __GFP_WAIT))
filter &= ~SHOW_MEM_FILTER_NODES;
if (fmt) {
struct va_format vaf;
va_list args;
va_start(args, fmt);
vaf.fmt = fmt;
vaf.va = &args;
pr_warn("%pV", &vaf);
va_end(args);
}
pr_warn("%s: page allocation failure: order:%d, mode:0x%x\n",
current->comm, order, gfp_mask);
dump_stack();
if (!should_suppress_show_mem())
show_mem(filter);
}
static inline struct page *
__alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
const struct alloc_context *ac, unsigned long *did_some_progress)
{
struct page *page;
*did_some_progress = 0;
/*
* Acquire the oom lock. If that fails, somebody else is
* making progress for us.
*/
if (!mutex_trylock(&oom_lock)) {
*did_some_progress = 1;
schedule_timeout_uninterruptible(1);
return NULL;
}
/*
* Go through the zonelist yet one more time, keep very high watermark
* here, this is only to catch a parallel oom killing, we must fail if
* we're still under heavy pressure.
*/
page = get_page_from_freelist(gfp_mask | __GFP_HARDWALL, order,
ALLOC_WMARK_HIGH|ALLOC_CPUSET, ac);
if (page)
goto out;
if (!(gfp_mask & __GFP_NOFAIL)) {
/* Coredumps can quickly deplete all memory reserves */
if (current->flags & PF_DUMPCORE)
goto out;
/* The OOM killer will not help higher order allocs */
if (order > PAGE_ALLOC_COSTLY_ORDER)
goto out;
/* The OOM killer does not needlessly kill tasks for lowmem */
if (ac->high_zoneidx < ZONE_NORMAL)
goto out;
/* The OOM killer does not compensate for IO-less reclaim */
if (!(gfp_mask & __GFP_FS)) {
/*
* XXX: Page reclaim didn't yield anything,
* and the OOM killer can't be invoked, but
* keep looping as per tradition.
*/
*did_some_progress = 1;
goto out;
}
if (pm_suspended_storage())
goto out;
/* The OOM killer may not free memory on a specific node */
if (gfp_mask & __GFP_THISNODE)
goto out;
}
/* Exhausted what can be done so it's blamo time */
if (out_of_memory(ac->zonelist, gfp_mask, order, ac->nodemask, false)
|| WARN_ON_ONCE(gfp_mask & __GFP_NOFAIL))
*did_some_progress = 1;
out:
mutex_unlock(&oom_lock);
return page;
}
#ifdef CONFIG_COMPACTION
/* Try memory compaction for high-order allocations before reclaim */
static struct page *
__alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
int alloc_flags, const struct alloc_context *ac,
enum migrate_mode mode, int *contended_compaction,
bool *deferred_compaction)
{
unsigned long compact_result;
struct page *page;
if (!order)
return NULL;
current->flags |= PF_MEMALLOC;
compact_result = try_to_compact_pages(gfp_mask, order, alloc_flags, ac,
mode, contended_compaction);
current->flags &= ~PF_MEMALLOC;
switch (compact_result) {
case COMPACT_DEFERRED:
*deferred_compaction = true;
/* fall-through */
case COMPACT_SKIPPED:
return NULL;
default:
break;
}
/*
* At least in one zone compaction wasn't deferred or skipped, so let's
* count a compaction stall
*/
count_vm_event(COMPACTSTALL);
page = get_page_from_freelist(gfp_mask, order,
alloc_flags & ~ALLOC_NO_WATERMARKS, ac);
if (page) {
struct zone *zone = page_zone(page);
zone->compact_blockskip_flush = false;
compaction_defer_reset(zone, order, true);
count_vm_event(COMPACTSUCCESS);
return page;
}
/*
* It's bad if compaction run occurs and fails. The most likely reason
* is that pages exist, but not enough to satisfy watermarks.
*/
count_vm_event(COMPACTFAIL);
cond_resched();
return NULL;
}
#else
static inline struct page *
__alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
int alloc_flags, const struct alloc_context *ac,
enum migrate_mode mode, int *contended_compaction,
bool *deferred_compaction)
{
return NULL;
}
#endif /* CONFIG_COMPACTION */
/* Perform direct synchronous page reclaim */
static int
__perform_reclaim(gfp_t gfp_mask, unsigned int order,
const struct alloc_context *ac)
{
struct reclaim_state reclaim_state;
int progress;
cond_resched();
/* We now go into synchronous reclaim */
cpuset_memory_pressure_bump();
current->flags |= PF_MEMALLOC;
lockdep_set_current_reclaim_state(gfp_mask);
reclaim_state.reclaimed_slab = 0;
current->reclaim_state = &reclaim_state;
progress = try_to_free_pages(ac->zonelist, order, gfp_mask,
ac->nodemask);
current->reclaim_state = NULL;
lockdep_clear_current_reclaim_state();
current->flags &= ~PF_MEMALLOC;
cond_resched();
return progress;
}
/* The really slow allocator path where we enter direct reclaim */
static inline struct page *
__alloc_pages_direct_reclaim(gfp_t gfp_mask, unsigned int order,
int alloc_flags, const struct alloc_context *ac,
unsigned long *did_some_progress)
{
struct page *page = NULL;
bool drained = false;
*did_some_progress = __perform_reclaim(gfp_mask, order, ac);
if (unlikely(!(*did_some_progress)))
return NULL;
/* After successful reclaim, reconsider all zones for allocation */
if (IS_ENABLED(CONFIG_NUMA))
zlc_clear_zones_full(ac->zonelist);
retry:
page = get_page_from_freelist(gfp_mask, order,
alloc_flags & ~ALLOC_NO_WATERMARKS, ac);
/*
* If an allocation failed after direct reclaim, it could be because
* pages are pinned on the per-cpu lists. Drain them and try again
*/
if (!page && !drained) {
drain_all_pages(NULL);
drained = true;
goto retry;
}
return page;
}
/*
* This is called in the allocator slow-path if the allocation request is of
* sufficient urgency to ignore watermarks and take other desperate measures
*/
static inline struct page *
__alloc_pages_high_priority(gfp_t gfp_mask, unsigned int order,
const struct alloc_context *ac)
{
struct page *page;
do {
page = get_page_from_freelist(gfp_mask, order,
ALLOC_NO_WATERMARKS, ac);
if (!page && gfp_mask & __GFP_NOFAIL)
wait_iff_congested(ac->preferred_zone, BLK_RW_ASYNC,
HZ/50);
} while (!page && (gfp_mask & __GFP_NOFAIL));
return page;
}
static void wake_all_kswapds(unsigned int order, const struct alloc_context *ac)
{
struct zoneref *z;
struct zone *zone;
for_each_zone_zonelist_nodemask(zone, z, ac->zonelist,
ac->high_zoneidx, ac->nodemask)
wakeup_kswapd(zone, order, zone_idx(ac->preferred_zone));
}
static inline int
gfp_to_alloc_flags(gfp_t gfp_mask)
{
int alloc_flags = ALLOC_WMARK_MIN | ALLOC_CPUSET;
const bool atomic = !(gfp_mask & (__GFP_WAIT | __GFP_NO_KSWAPD));
/* __GFP_HIGH is assumed to be the same as ALLOC_HIGH to save a branch. */
BUILD_BUG_ON(__GFP_HIGH != (__force gfp_t) ALLOC_HIGH);
/*
* The caller may dip into page reserves a bit more if the caller
* cannot run direct reclaim, or if the caller has realtime scheduling
* policy or is asking for __GFP_HIGH memory. GFP_ATOMIC requests will
* set both ALLOC_HARDER (atomic == true) and ALLOC_HIGH (__GFP_HIGH).
*/
alloc_flags |= (__force int) (gfp_mask & __GFP_HIGH);
if (atomic) {
/*
* Not worth trying to allocate harder for __GFP_NOMEMALLOC even
* if it can't schedule.
*/
if (!(gfp_mask & __GFP_NOMEMALLOC))
alloc_flags |= ALLOC_HARDER;
/*
* Ignore cpuset mems for GFP_ATOMIC rather than fail, see the
* comment for __cpuset_node_allowed().
*/
alloc_flags &= ~ALLOC_CPUSET;
} else if (unlikely(rt_task(current)) && !in_interrupt())
alloc_flags |= ALLOC_HARDER;
if (likely(!(gfp_mask & __GFP_NOMEMALLOC))) {
if (gfp_mask & __GFP_MEMALLOC)
alloc_flags |= ALLOC_NO_WATERMARKS;
else if (in_serving_softirq() && (current->flags & PF_MEMALLOC))
alloc_flags |= ALLOC_NO_WATERMARKS;
else if (!in_interrupt() &&
((current->flags & PF_MEMALLOC) ||
unlikely(test_thread_flag(TIF_MEMDIE))))
alloc_flags |= ALLOC_NO_WATERMARKS;
}
#ifdef CONFIG_CMA
if (gfpflags_to_migratetype(gfp_mask) == MIGRATE_MOVABLE)
alloc_flags |= ALLOC_CMA;
#endif
return alloc_flags;
}
bool gfp_pfmemalloc_allowed(gfp_t gfp_mask)
{
return !!(gfp_to_alloc_flags(gfp_mask) & ALLOC_NO_WATERMARKS);
}
static inline struct page *
__alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
struct alloc_context *ac)
{
const gfp_t wait = gfp_mask & __GFP_WAIT;
struct page *page = NULL;
int alloc_flags;
unsigned long pages_reclaimed = 0;
unsigned long did_some_progress;
enum migrate_mode migration_mode = MIGRATE_ASYNC;
bool deferred_compaction = false;
int contended_compaction = COMPACT_CONTENDED_NONE;
/*
* In the slowpath, we sanity check order to avoid ever trying to
* reclaim >= MAX_ORDER areas which will never succeed. Callers may
* be using allocators in order of preference for an area that is
* too large.
*/
if (order >= MAX_ORDER) {
WARN_ON_ONCE(!(gfp_mask & __GFP_NOWARN));
return NULL;
}
/*
* If this allocation cannot block and it is for a specific node, then
* fail early. There's no need to wakeup kswapd or retry for a
* speculative node-specific allocation.
*/
if (IS_ENABLED(CONFIG_NUMA) && (gfp_mask & __GFP_THISNODE) && !wait)
goto nopage;
retry:
if (!(gfp_mask & __GFP_NO_KSWAPD))
wake_all_kswapds(order, ac);
/*
* OK, we're below the kswapd watermark and have kicked background
* reclaim. Now things get more complex, so set up alloc_flags according
* to how we want to proceed.
*/
alloc_flags = gfp_to_alloc_flags(gfp_mask);
/*
* Find the true preferred zone if the allocation is unconstrained by
* cpusets.
*/
if (!(alloc_flags & ALLOC_CPUSET) && !ac->nodemask) {
struct zoneref *preferred_zoneref;
preferred_zoneref = first_zones_zonelist(ac->zonelist,
ac->high_zoneidx, NULL, &ac->preferred_zone);
ac->classzone_idx = zonelist_zone_idx(preferred_zoneref);
}
/* This is the last chance, in general, before the goto nopage. */
page = get_page_from_freelist(gfp_mask, order,
alloc_flags & ~ALLOC_NO_WATERMARKS, ac);
if (page)
goto got_pg;
/* Allocate without watermarks if the context allows */
if (alloc_flags & ALLOC_NO_WATERMARKS) {
/*
* Ignore mempolicies if ALLOC_NO_WATERMARKS on the grounds
* the allocation is high priority and these type of
* allocations are system rather than user orientated
*/
ac->zonelist = node_zonelist(numa_node_id(), gfp_mask);
page = __alloc_pages_high_priority(gfp_mask, order, ac);
if (page) {
goto got_pg;
}
}
/* Atomic allocations - we can't balance anything */
if (!wait) {
/*
* All existing users of the deprecated __GFP_NOFAIL are
* blockable, so warn of any new users that actually allow this
* type of allocation to fail.
*/
WARN_ON_ONCE(gfp_mask & __GFP_NOFAIL);
goto nopage;
}
/* Avoid recursion of direct reclaim */
if (current->flags & PF_MEMALLOC)
goto nopage;
/* Avoid allocations with no watermarks from looping endlessly */
if (test_thread_flag(TIF_MEMDIE) && !(gfp_mask & __GFP_NOFAIL))
goto nopage;
/*
* Try direct compaction. The first pass is asynchronous. Subsequent
* attempts after direct reclaim are synchronous
*/
page = __alloc_pages_direct_compact(gfp_mask, order, alloc_flags, ac,
migration_mode,
&contended_compaction,
&deferred_compaction);
if (page)
goto got_pg;
/* Checks for THP-specific high-order allocations */
if ((gfp_mask & GFP_TRANSHUGE) == GFP_TRANSHUGE) {
/*
* If compaction is deferred for high-order allocations, it is
* because sync compaction recently failed. If this is the case
* and the caller requested a THP allocation, we do not want
* to heavily disrupt the system, so we fail the allocation
* instead of entering direct reclaim.
*/
if (deferred_compaction)
goto nopage;
/*
* In all zones where compaction was attempted (and not
* deferred or skipped), lock contention has been detected.
* For THP allocation we do not want to disrupt the others
* so we fallback to base pages instead.
*/
if (contended_compaction == COMPACT_CONTENDED_LOCK)
goto nopage;
/*
* If compaction was aborted due to need_resched(), we do not
* want to further increase allocation latency, unless it is
* khugepaged trying to collapse.
*/
if (contended_compaction == COMPACT_CONTENDED_SCHED
&& !(current->flags & PF_KTHREAD))
goto nopage;
}
/*
* It can become very expensive to allocate transparent hugepages at
* fault, so use asynchronous memory compaction for THP unless it is
* khugepaged trying to collapse.
*/
if ((gfp_mask & GFP_TRANSHUGE) != GFP_TRANSHUGE ||
(current->flags & PF_KTHREAD))
migration_mode = MIGRATE_SYNC_LIGHT;
/* Try direct reclaim and then allocating */
page = __alloc_pages_direct_reclaim(gfp_mask, order, alloc_flags, ac,
&did_some_progress);
if (page)
goto got_pg;
/* Do not loop if specifically requested */
if (gfp_mask & __GFP_NORETRY)
goto noretry;
/* Keep reclaiming pages as long as there is reasonable progress */
pages_reclaimed += did_some_progress;
if ((did_some_progress && order <= PAGE_ALLOC_COSTLY_ORDER) ||
((gfp_mask & __GFP_REPEAT) && pages_reclaimed < (1 << order))) {
/* Wait for some write requests to complete then retry */
wait_iff_congested(ac->preferred_zone, BLK_RW_ASYNC, HZ/50);
goto retry;
}
/* Reclaim has failed us, start killing things */
page = __alloc_pages_may_oom(gfp_mask, order, ac, &did_some_progress);
if (page)
goto got_pg;
/* Retry as long as the OOM killer is making progress */
if (did_some_progress)
goto retry;
noretry:
/*
* High-order allocations do not necessarily loop after
* direct reclaim and reclaim/compaction depends on compaction
* being called after reclaim so call directly if necessary
*/
page = __alloc_pages_direct_compact(gfp_mask, order, alloc_flags,
ac, migration_mode,
&contended_compaction,
&deferred_compaction);
if (page)
goto got_pg;
nopage:
warn_alloc_failed(gfp_mask, order, NULL);
got_pg:
return page;
}
/*
* This is the 'heart' of the zoned buddy allocator.
*/
struct page *
__alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
struct zonelist *zonelist, nodemask_t *nodemask)
{
struct zoneref *preferred_zoneref;
struct page *page = NULL;
unsigned int cpuset_mems_cookie;
int alloc_flags = ALLOC_WMARK_LOW|ALLOC_CPUSET|ALLOC_FAIR;
gfp_t alloc_mask; /* The gfp_t that was actually used for allocation */
struct alloc_context ac = {
.high_zoneidx = gfp_zone(gfp_mask),
.nodemask = nodemask,
.migratetype = gfpflags_to_migratetype(gfp_mask),
};
gfp_mask &= gfp_allowed_mask;
lockdep_trace_alloc(gfp_mask);
might_sleep_if(gfp_mask & __GFP_WAIT);
if (should_fail_alloc_page(gfp_mask, order))
return NULL;
/*
* Check the zones suitable for the gfp_mask contain at least one
* valid zone. It's possible to have an empty zonelist as a result
* of __GFP_THISNODE and a memoryless node
*/
if (unlikely(!zonelist->_zonerefs->zone))
return NULL;
if (IS_ENABLED(CONFIG_CMA) && ac.migratetype == MIGRATE_MOVABLE)
alloc_flags |= ALLOC_CMA;
retry_cpuset:
cpuset_mems_cookie = read_mems_allowed_begin();
/* We set it here, as __alloc_pages_slowpath might have changed it */
ac.zonelist = zonelist;
/* The preferred zone is used for statistics later */
preferred_zoneref = first_zones_zonelist(ac.zonelist, ac.high_zoneidx,
ac.nodemask ? : &cpuset_current_mems_allowed,
&ac.preferred_zone);
if (!ac.preferred_zone)
goto out;
ac.classzone_idx = zonelist_zone_idx(preferred_zoneref);
/* First allocation attempt */
alloc_mask = gfp_mask|__GFP_HARDWALL;
page = get_page_from_freelist(alloc_mask, order, alloc_flags, &ac);
if (unlikely(!page)) {
/*
* Runtime PM, block IO and its error handling path
* can deadlock because I/O on the device might not
* complete.
*/
alloc_mask = memalloc_noio_flags(gfp_mask);
page = __alloc_pages_slowpath(alloc_mask, order, &ac);
}
if (kmemcheck_enabled && page)
kmemcheck_pagealloc_alloc(page, order, gfp_mask);
trace_mm_page_alloc(page, order, alloc_mask, ac.migratetype);
out:
/*
* When updating a task's mems_allowed, it is possible to race with
* parallel threads in such a way that an allocation can fail while
* the mask is being updated. If a page allocation is about to fail,
* check if the cpuset changed during allocation and if so, retry.
*/
if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie)))
goto retry_cpuset;
return page;
}
EXPORT_SYMBOL(__alloc_pages_nodemask);
/*
* Common helper functions.
*/
unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order)
{
struct page *page;
/*
* __get_free_pages() returns a 32-bit address, which cannot represent
* a highmem page
*/
VM_BUG_ON((gfp_mask & __GFP_HIGHMEM) != 0);
page = alloc_pages(gfp_mask, order);
if (!page)
return 0;
return (unsigned long) page_address(page);
}
EXPORT_SYMBOL(__get_free_pages);
unsigned long get_zeroed_page(gfp_t gfp_mask)
{
return __get_free_pages(gfp_mask | __GFP_ZERO, 0);
}
EXPORT_SYMBOL(get_zeroed_page);
void __free_pages(struct page *page, unsigned int order)
{
if (put_page_testzero(page)) {
if (order == 0)
free_hot_cold_page(page, false);
else
__free_pages_ok(page, order);
}
}
mm15.txt
最新推荐文章于 2024-05-10 10:22:36 发布