/* * mm/page-writeback.c * * Copyright (C) 2002, Linus Torvalds. * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra * * Contains functions related to writing back dirty pages at the * address_space level. * * 10Apr2002 Andrew Morton * Initial version */ #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include /* * Sleep at most 200ms at a time in balance_dirty_pages(). */ #define MAX_PAUSE max(HZ/5, 1) /* * Estimate write bandwidth at 200ms intervals. */ #define BANDWIDTH_INTERVAL max(HZ/5, 1) /* * After a CPU has dirtied this many pages, balance_dirty_pages_ratelimited * will look to see if it needs to force writeback or throttling. */ static long ratelimit_pages = 32; /* * When balance_dirty_pages decides that the caller needs to perform some * non-background writeback, this is how many pages it will attempt to write. * It should be somewhat larger than dirtied pages to ensure that reasonably * large amounts of I/O are submitted. */ static inline long sync_writeback_pages(unsigned long dirtied) { if (dirtied < ratelimit_pages) dirtied = ratelimit_pages; return dirtied + dirtied / 2; } /* The following parameters are exported via /proc/sys/vm */ /* * Start background writeback (via writeback threads) at this percentage */ int dirty_background_ratio = 10; /* * dirty_background_bytes starts at 0 (disabled) so that it is a function of * dirty_background_ratio * the amount of dirtyable memory */ unsigned long dirty_background_bytes; /* * free highmem will not be subtracted from the total free memory * for calculating free ratios if vm_highmem_is_dirtyable is true */ int vm_highmem_is_dirtyable; /* * The generator of dirty data starts writeback at this percentage */ int vm_dirty_ratio = 20; /* * vm_dirty_bytes starts at 0 (disabled) so that it is a function of * vm_dirty_ratio * the amount of dirtyable memory */ unsigned long vm_dirty_bytes; /* * The interval between `kupdate'-style writebacks */ unsigned int dirty_writeback_interval = 5 * 100; /* centiseconds */ /* * The longest time for which data is allowed to remain dirty */ unsigned int dirty_expire_interval = 30 * 100; /* centiseconds */ /* * Flag that makes the machine dump writes/reads and block dirtyings. */ int block_dump; /* * Flag that puts the machine in "laptop mode". Doubles as a timeout in jiffies: * a full sync is triggered after this time elapses without any disk activity. */ int laptop_mode; EXPORT_SYMBOL(laptop_mode); /* End of sysctl-exported parameters */ unsigned long global_dirty_limit; /* * Scale the writeback cache size proportional to the relative writeout speeds. * * We do this by keeping a floating proportion between BDIs, based on page * writeback completions [end_page_writeback()]. Those devices that write out * pages fastest will get the larger share, while the slower will get a smaller * share. * * We use page writeout completions because we are interested in getting rid of * dirty pages. Having them written out is the primary goal. * * We introduce a concept of time, a period over which we measure these events, * because demand can/will vary over time. The length of this period itself is * measured in page writeback completions. * */ static struct prop_descriptor vm_completions; static struct prop_descriptor vm_dirties; /* * couple the period to the dirty_ratio: * * period/2 ~ roundup_pow_of_two(dirty limit) */ static int calc_period_shift(void) { unsigned long dirty_total; if (vm_dirty_bytes) dirty_total = vm_dirty_bytes / PAGE_SIZE; else dirty_total = (vm_dirty_ratio * determine_dirtyable_memory()) / 100; return 2 + ilog2(dirty_total - 1); } /* * update the period when the dirty threshold changes. */ static void update_completion_period(void) { int shift = calc_period_shift(); prop_change_shift(&vm_completions, shift); prop_change_shift(&vm_dirties, shift); } int dirty_background_ratio_handler(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { int ret; ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (ret == 0 && write) dirty_background_bytes = 0; return ret; } int dirty_background_bytes_handler(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { int ret; ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos); if (ret == 0 && write) dirty_background_ratio = 0; return ret; } int dirty_ratio_handler(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { int old_ratio = vm_dirty_ratio; int ret; ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (ret == 0 && write && vm_dirty_ratio != old_ratio) { update_completion_period(); vm_dirty_bytes = 0; } return ret; } int dirty_bytes_handler(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { unsigned long old_bytes = vm_dirty_bytes; int ret; ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos); if (ret == 0 && write && vm_dirty_bytes != old_bytes) { update_completion_period(); vm_dirty_ratio = 0; } return ret; } /* * Increment the BDI's writeout completion count and the global writeout * completion count. Called from test_clear_page_writeback(). */ static inline void __bdi_writeout_inc(struct backing_dev_info *bdi) { __inc_bdi_stat(bdi, BDI_WRITTEN); __prop_inc_percpu_max(&vm_completions, &bdi->completions, bdi->max_prop_frac); } void bdi_writeout_inc(struct backing_dev_info *bdi) { unsigned long flags; local_irq_save(flags); __bdi_writeout_inc(bdi); local_irq_restore(flags); } EXPORT_SYMBOL_GPL(bdi_writeout_inc); void task_dirty_inc(struct task_struct *tsk) { prop_inc_single(&vm_dirties, &tsk->dirties); } /* * Obtain an accurate fraction of the BDI's portion. */ static void bdi_writeout_fraction(struct backing_dev_info *bdi, long *numerator, long *denominator) { prop_fraction_percpu(&vm_completions, &bdi->completions, numerator, denominator); } static inline void task_dirties_fraction(struct task_struct *tsk, long *numerator, long *denominator) { prop_fraction_single(&vm_dirties, &tsk->dirties, numerator, denominator); } /* * task_dirty_limit - scale down dirty throttling threshold for one task * * task specific dirty limit: * * dirty -= (dirty/8) * p_{t} * * To protect light/slow dirtying tasks from heavier/fast ones, we start * throttling individual tasks before reaching the bdi dirty limit. * Relatively low thresholds will be allocated to heavy dirtiers. So when * dirty pages grow large, heavy dirtiers will be throttled first, which will * effectively curb the growth of dirty pages. Light dirtiers with high enough * dirty threshold may never get throttled. */ #define TASK_LIMIT_FRACTION 8 static unsigned long task_dirty_limit(struct task_struct *tsk, unsigned long bdi_dirty) { long numerator, denominator; unsigned long dirty = bdi_dirty; u64 inv = dirty / TASK_LIMIT_FRACTION; task_dirties_fraction(tsk, &numerator, &denominator); inv *= numerator; do_div(inv, denominator); dirty -= inv; return max(dirty, bdi_dirty/2); } /* Minimum limit for any task */ static unsigned long task_min_dirty_limit(unsigned long bdi_dirty) { return bdi_dirty - bdi_dirty / TASK_LIMIT_FRACTION; } /* * */ static unsigned int bdi_min_ratio; int bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ratio) { int ret = 0; spin_lock_bh(&bdi_lock); if (min_ratio > bdi->max_ratio) { ret = -EINVAL; } else { min_ratio -= bdi->min_ratio; if (bdi_min_ratio + min_ratio < 100) { bdi_min_ratio += min_ratio; bdi->min_ratio += min_ratio; } else { ret = -EINVAL; } } spin_unlock_bh(&bdi_lock); return ret; } int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned max_ratio) { int ret = 0; if (max_ratio > 100) return -EINVAL; spin_lock_bh(&bdi_lock); if (bdi->min_ratio > max_ratio) { ret = -EINVAL; } else { bdi->max_ratio = max_ratio; bdi->max_prop_frac = (PROP_FRAC_BASE * max_ratio) / 100; } spin_unlock_bh(&bdi_lock); return ret; } EXPORT_SYMBOL(bdi_set_max_ratio); /* * Work out the current dirty-memory clamping and background writeout * thresholds. * * The main aim here is to lower them aggressively if there is a lot of mapped * memory around. To avoid stressing page reclaim with lots of unreclaimable * pages. It is better to clamp down on writers than to start swapping, and * performing lots of scanning. * * We only allow 1/2 of the currently-unmapped memory to be dirtied. * * We don't permit the clamping level to fall below 5% - that is getting rather * excessive. * * We make sure that the background writeout level is below the adjusted * clamping level. */ static unsigned long highmem_dirtyable_memory(unsigned long total) { #ifdef CONFIG_HIGHMEM int node; unsigned long x = 0; for_each_node_state(node, N_HIGH_MEMORY) { struct zone *z = &NODE_DATA(node)->node_zones[ZONE_HIGHMEM]; x += zone_page_state(z, NR_FREE_PAGES) + zone_reclaimable_pages(z); } /* * Make sure that the number of highmem pages is never larger * than the number of the total dirtyable memory. This can only * occur in very strange VM situations but we want to make sure * that this does not occur. */ return min(x, total); #else return 0; #endif } /** * determine_dirtyable_memory - amount of memory that may be used * * Returns the numebr of pages that can currently be freed and used * by the kernel for direct mappings. */ unsigned long determine_dirtyable_memory(void) { unsigned long x; x = global_page_state(NR_FREE_PAGES) + global_reclaimable_pages(); if (!vm_highmem_is_dirtyable) x -= highmem_dirtyable_memory(x); return x + 1; /* Ensure that we never return 0 */ } static unsigned long hard_dirty_limit(unsigned long thresh) { return max(thresh, global_dirty_limit); } /* * global_dirty_limits - background-writeback and dirty-throttling thresholds * * Calculate the dirty thresholds based on sysctl parameters * - vm.dirty_background_ratio or vm.dirty_background_bytes * - vm.dirty_ratio or vm.dirty_bytes * The dirty limits will be lifted by 1/4 for PF_LESS_THROTTLE (ie. nfsd) and * real-time tasks. */ void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty) { unsigned long background; unsigned long dirty; unsigned long uninitialized_var(available_memory); struct task_struct *tsk; if (!vm_dirty_bytes || !dirty_background_bytes) available_memory = determine_dirtyable_memory(); if (vm_dirty_bytes) dirty = DIV_ROUND_UP(vm_dirty_bytes, PAGE_SIZE); else dirty = (vm_dirty_ratio * available_memory) / 100; if (dirty_background_bytes) background = DIV_ROUND_UP(dirty_background_bytes, PAGE_SIZE); else background = (dirty_background_ratio * available_memory) / 100; if (background >= dirty) background = dirty / 2; tsk = current; if (tsk->flags & PF_LESS_THROTTLE || rt_task(tsk)) { background += background / 4; dirty += dirty / 4; } *pbackground = background; *pdirty = dirty; trace_global_dirty_state(background, dirty); } /** * bdi_dirty_limit - @bdi's share of dirty throttling threshold * @bdi: the backing_dev_info to query * @dirty: global dirty limit in pages * * Returns @bdi's dirty limit in pages. The term "dirty" in the context of * dirty balancing includes all PG_dirty, PG_writeback and NFS unstable pages. * And the "limit" in the name is not seriously taken as hard limit in * balance_dirty_pages(). * * It allocates high/low dirty limits to fast/slow devices, in order to prevent * - starving fast devices * - piling up dirty pages (that will take long time to sync) on slow devices * * The bdi's share of dirty limit will be adapting to its throughput and * bounded by the bdi->min_ratio and/or bdi->max_ratio parameters, if set. */ unsigned long bdi_dirty_limit(struct backing_dev_info *bdi, unsigned long dirty) { u64 bdi_dirty; long numerator, denominator; /* * Calculate this BDI's share of the dirty ratio. */ bdi_writeout_fraction(bdi, &numerator, &denominator); bdi_dirty = (dirty * (100 - bdi_min_ratio)) / 100; bdi_dirty *= numerator; do_div(bdi_dirty, denominator); bdi_dirty += (dirty * bdi->min_ratio) / 100; if (bdi_dirty > (dirty * bdi->max_ratio) / 100) bdi_dirty = dirty * bdi->max_ratio / 100; return bdi_dirty; } static void bdi_update_write_bandwidth(struct backing_dev_info *bdi, unsigned long elapsed, unsigned long written) { const unsigned long period = roundup_pow_of_two(3 * HZ); unsigned long avg = bdi->avg_write_bandwidth; unsigned long old = bdi->write_bandwidth; u64 bw; /* * bw = written * HZ / elapsed * * bw * elapsed + write_bandwidth * (period - elapsed) * write_bandwidth = --------------------------------------------------- * period */ bw = written - bdi->written_stamp; bw *= HZ; if (unlikely(elapsed > period)) { do_div(bw, elapsed); avg = bw; goto out; } bw += (u64)bdi->write_bandwidth * (period - elapsed); bw >>= ilog2(period); /* * one more level of smoothing, for filtering out sudden spikes */ if (avg > old && old >= (unsigned long)bw) avg -= (avg - old) >> 3; if (avg < old && old <= (unsigned long)bw) avg += (old - avg) >> 3; out: bdi->write_bandwidth = bw; bdi->avg_write_bandwidth = avg; } /* * The global dirtyable memory and dirty threshold could be suddenly knocked * down by a large amount (eg. on the startup of KVM in a swapless system). * This may throw the system into deep dirty exceeded state and throttle * heavy/light dirtiers alike. To retain good responsiveness, maintain * global_dirty_limit for tracking slowly down to the knocked down dirty * threshold. */ static void update_dirty_limit(unsigned long thresh, unsigned long dirty) { unsigned long limit = global_dirty_limit; /* * Follow up in one step. */ if (limit < thresh) { limit = thresh; goto update; } /* * Follow down slowly. Use the higher one as the target, because thresh * may drop below dirty. This is exactly the reason to introduce * global_dirty_limit which is guaranteed to lie above the dirty pages. */ thresh = max(thresh, dirty); if (limit > thresh) { limit -= (limit - thresh) >> 5; goto update; } return; update: global_dirty_limit = limit; } static void global_update_bandwidth(unsigned long thresh, unsigned long dirty, unsigned long now) { static DEFINE_SPINLOCK(dirty_lock); static unsigned long update_time; /* * check locklessly first to optimize away locking for the most time */ if (time_before(now, update_time + BANDWIDTH_INTERVAL)) return; spin_lock(&dirty_lock); if (time_after_eq(now, update_time + BANDWIDTH_INTERVAL)) { update_dirty_limit(thresh, dirty); update_time = now; } spin_unlock(&dirty_lock); } void __bdi_update_bandwidth(struct backing_dev_info *bdi, unsigned long thresh, unsigned long dirty, unsigned long bdi_thresh, unsigned long bdi_dirty, unsigned long start_time) { unsigned long now = jiffies; unsigned long elapsed = now - bdi->bw_time_stamp; unsigned long written; /* * rate-limit, only update once every 200ms. */ if (elapsed < BANDWIDTH_INTERVAL) return; written = percpu_counter_read(&bdi->bdi_stat[BDI_WRITTEN]); /* * Skip quiet periods when disk bandwidth is under-utilized. * (at least 1s idle time between two flusher runs) */ if (elapsed > HZ && time_before(bdi->bw_time_stamp, start_time)) goto snapshot; if (thresh) global_update_bandwidth(thresh, dirty, now); bdi_update_write_bandwidth(bdi, elapsed, written); snapshot: bdi->written_stamp = written; bdi->bw_time_stamp = now; } static void bdi_update_bandwidth(struct backing_dev_info *bdi, unsigned long thresh, unsigned long dirty, unsigned long bdi_thresh, unsigned long bdi_dirty, unsigned long start_time) { if (time_is_after_eq_jiffies(bdi->bw_time_stamp + BANDWIDTH_INTERVAL)) return; spin_lock(&bdi->wb.list_lock); __bdi_update_bandwidth(bdi, thresh, dirty, bdi_thresh, bdi_dirty, start_time); spin_unlock(&bdi->wb.list_lock); } /* * balance_dirty_pages() must be called by processes which are generating dirty * data. It looks at the number of dirty pages in the machine and will force * the caller to perform writeback if the system is over `vm_dirty_ratio'. * If we're over `background_thresh' then the writeback threads are woken to * perform some writeout. */ static void balance_dirty_pages(struct address_space *mapping, unsigned long write_chunk) { unsigned long nr_reclaimable, bdi_nr_reclaimable; unsigned long nr_dirty; /* = file_dirty + writeback + unstable_nfs */ unsigned long bdi_dirty; unsigned long background_thresh; unsigned long dirty_thresh; unsigned long bdi_thresh; unsigned long task_bdi_thresh; unsigned long min_task_bdi_thresh; unsigned long pages_written = 0; unsigned long pause = 1; bool dirty_exceeded = false; bool clear_dirty_exceeded = true; struct backing_dev_info *bdi = mapping->backing_dev_info; unsigned long start_time = jiffies; for (;;) { nr_reclaimable = global_page_state(NR_FILE_DIRTY) + global_page_state(NR_UNSTABLE_NFS); nr_dirty = nr_reclaimable + global_page_state(NR_WRITEBACK); global_dirty_limits(&background_thresh, &dirty_thresh); /* * Throttle it only when the background writeback cannot * catch-up. This avoids (excessively) small writeouts * when the bdi limits are ramping up. */ if (nr_dirty <= (background_thresh + dirty_thresh) / 2) break; bdi_thresh = bdi_dirty_limit(bdi, dirty_thresh); min_task_bdi_thresh = task_min_dirty_limit(bdi_thresh); task_bdi_thresh = task_dirty_limit(current, bdi_thresh); /* * In order to avoid the stacked BDI deadlock we need * to ensure we accurately count the 'dirty' pages when * the threshold is low. * * Otherwise it would be possible to get thresh+n pages * reported dirty, even though there are thresh-m pages * actually dirty; with m+n sitting in the percpu * deltas. */ if (task_bdi_thresh < 2 * bdi_stat_error(bdi)) { bdi_nr_reclaimable = bdi_stat_sum(bdi, BDI_RECLAIMABLE); bdi_dirty = bdi_nr_reclaimable + bdi_stat_sum(bdi, BDI_WRITEBACK); } else { bdi_nr_reclaimable = bdi_stat(bdi, BDI_RECLAIMABLE); bdi_dirty = bdi_nr_reclaimable + bdi_stat(bdi, BDI_WRITEBACK); } /* * The bdi thresh is somehow "soft" limit derived from the * global "hard" limit. The former helps to prevent heavy IO * bdi or process from holding back light ones; The latter is * the last resort safeguard. */ dirty_exceeded = (bdi_dirty > task_bdi_thresh) || (nr_dirty > dirty_thresh); clear_dirty_exceeded = (bdi_dirty <= min_task_bdi_thresh) && (nr_dirty <= dirty_thresh); if (!dirty_exceeded) break; if (!bdi->dirty_exceeded) bdi->dirty_exceeded = 1; bdi_update_bandwidth(bdi, dirty_thresh, nr_dirty, bdi_thresh, bdi_dirty, start_time); /* Note: nr_reclaimable denotes nr_dirty + nr_unstable. * Unstable writes are a feature of certain networked * filesystems (i.e. NFS) in which data may have been * written to the server's write cache, but has not yet * been flushed to permanent storage. * Only move pages to writeback if this bdi is over its * threshold otherwise wait until the disk writes catch * up. */ trace_balance_dirty_start(bdi); if (bdi_nr_reclaimable > task_bdi_thresh) { pages_written += writeback_inodes_wb(&bdi->wb, write_chunk); trace_balance_dirty_written(bdi, pages_written); if (pages_written >= write_chunk) break; /* We've done our duty */ } __set_current_state(TASK_UNINTERRUPTIBLE); io_schedule_timeout(pause); trace_balance_dirty_wait(bdi); dirty_thresh = hard_dirty_limit(dirty_thresh); /* * max-pause area. If dirty exceeded but still within this * area, no need to sleep for more than 200ms: (a) 8 pages per * 200ms is typically more than enough to curb heavy dirtiers; * (b) the pause time limit makes the dirtiers more responsive. */ if (nr_dirty < dirty_thresh + dirty_thresh / DIRTY_MAXPAUSE_AREA && time_after(jiffies, start_time + MAX_PAUSE)) break; /* * pass-good area. When some bdi gets blocked (eg. NFS server * not responding), or write bandwidth dropped dramatically due * to concurrent reads, or dirty threshold suddenly dropped and * the dirty pages cannot be brought down anytime soon (eg. on * slow USB stick), at least let go of the good bdi's. */ if (nr_dirty < dirty_thresh + dirty_thresh / DIRTY_PASSGOOD_AREA && bdi_dirty < bdi_thresh) break; /* * Increase the delay for each loop, up to our previous * default of taking a 100ms nap. */ pause <<= 1; if (pause > HZ / 10) pause = HZ / 10; } /* Clear dirty_exceeded flag only when no task can exceed the limit */ if (clear_dirty_exceeded && bdi->dirty_exceeded) bdi->dirty_exceeded = 0; if (writeback_in_progress(bdi)) return; /* * In laptop mode, we wait until hitting the higher threshold before * starting background writeout, and then write out all the way down * to the lower threshold. So slow writers cause minimal disk activity. * * In normal mode, we start background writeout at the lower * background_thresh, to keep the amount of dirty memory low. */ if ((laptop_mode && pages_written) || (!laptop_mode && (nr_reclaimable > background_thresh))) bdi_start_background_writeback(bdi); } void set_page_dirty_balance(struct page *page, int page_mkwrite) { if (set_page_dirty(page) || page_mkwrite) { struct address_space *mapping = page_mapping(page); if (mapping) balance_dirty_pages_ratelimited(mapping); } } static DEFINE_PER_CPU(unsigned long, bdp_ratelimits) = 0; /** * balance_dirty_pages_ratelimited_nr - balance dirty memory state * @mapping: address_space which was dirtied * @nr_pages_dirtied: number of pages which the caller has just dirtied * * Processes which are dirtying memory should call in here once for each page * which was newly dirtied. The function will periodically check the system's * dirty state and will initiate writeback if needed. * * On really big machines, get_writeback_state is expensive, so try to avoid * calling it too often (ratelimiting). But once we're over the dirty memory * limit we decrease the ratelimiting by a lot, to prevent individual processes * from overshooting the limit by (ratelimit_pages) each. */ void balance_dirty_pages_ratelimited_nr(struct address_space *mapping, unsigned long nr_pages_dirtied) { struct backing_dev_info *bdi = mapping->backing_dev_info; unsigned long ratelimit; unsigned long *p; if (!bdi_cap_account_dirty(bdi)) return; ratelimit = ratelimit_pages; if (mapping->backing_dev_info->dirty_exceeded) ratelimit = 8; /* * Check the rate limiting. Also, we do not want to throttle real-time * tasks in balance_dirty_pages(). Period. */ preempt_disable(); p = &__get_cpu_var(bdp_ratelimits); *p += nr_pages_dirtied; if (unlikely(*p >= ratelimit)) { ratelimit = sync_writeback_pages(*p); *p = 0; preempt_enable(); balance_dirty_pages(mapping, ratelimit); return; } preempt_enable(); } EXPORT_SYMBOL(balance_dirty_pages_ratelimited_nr); void throttle_vm_writeout(gfp_t gfp_mask) { unsigned long background_thresh; unsigned long dirty_thresh; for ( ; ; ) { global_dirty_limits(&background_thresh, &dirty_thresh); /* * Boost the allowable dirty threshold a bit for page * allocators so they don't get DoS'ed by heavy writers */ dirty_thresh += dirty_thresh / 10; /* wheeee... */ if (global_page_state(NR_UNSTABLE_NFS) + global_page_state(NR_WRITEBACK) <= dirty_thresh) break; congestion_wait(BLK_RW_ASYNC, HZ/10); /* * The caller might hold locks which can prevent IO completion * or progress in the filesystem. So we cannot just sit here * waiting for IO to complete. */ if ((gfp_mask & (__GFP_FS|__GFP_IO)) != (__GFP_FS|__GFP_IO)) break; } } /* * sysctl handler for /proc/sys/vm/dirty_writeback_centisecs */ int dirty_writeback_centisecs_handler(ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos) { proc_dointvec(table, write, buffer, length, ppos); bdi_arm_supers_timer(); 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); /* * We want to write everything out, not just down to the dirty * threshold */ if (bdi_has_dirty_io(&q->backing_dev_info)) bdi_start_writeback(&q->backing_dev_info, nr_pages); } /* * 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 before writeback cuts in. * * But the limit should not be set too high. Because it also controls the * amount of memory which the balance_dirty_pages() caller has to write back. * If this is too large then the caller will block on the IO queue all the * time. So limit it to four megabytes - the balance_dirty_pages() caller * will write six megabyte chunks, max. */ void writeback_set_ratelimit(void) { ratelimit_pages = vm_total_pages / (num_online_cpus() * 32); if (ratelimit_pages < 16) ratelimit_pages = 16; if (ratelimit_pages * PAGE_CACHE_SIZE > 4096 * 1024) ratelimit_pages = (4096 * 1024) / PAGE_CACHE_SIZE; } static int __cpuinit ratelimit_handler(struct notifier_block *self, unsigned long u, void *v) { writeback_set_ratelimit(); return NOTIFY_DONE; } static struct notifier_block __cpuinitdata 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) { int shift; writeback_set_ratelimit(); register_cpu_notifier(&ratelimit_nb); shift = calc_period_shift(); prop_descriptor_init(&vm_completions, shift); prop_descriptor_init(&vm_dirties, shift); } /** * 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, mapping->backing_dev_info); 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. * NOTE: This relies on being atomic wrt interrupts. */ void account_page_dirtied(struct page *page, struct address_space *mapping) { if (mapping_cap_account_dirty(mapping)) { __inc_zone_page_state(page, NR_FILE_DIRTY); __inc_zone_page_state(page, NR_DIRTIED); __inc_bdi_stat(mapping->backing_dev_info, BDI_RECLAIMABLE); task_dirty_inc(current); task_io_account_write(PAGE_CACHE_SIZE); } } EXPORT_SYMBOL(account_page_dirtied); /* * Helper function for set_page_writeback family. * NOTE: Unlike account_page_dirtied this does not rely on being atomic * wrt interrupts. */ void account_page_writeback(struct page *page) { inc_zone_page_state(page, NR_WRITEBACK); inc_zone_page_state(page, NR_WRITTEN); } EXPORT_SYMBOL(account_page_writeback); /* * 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. * * Most callers have locked the page, which pins the address_space in memory. * But zap_pte_range() does not lock the page, however in that case the * mapping is pinned by the vma's ->vm_file reference. * * We take care to handle the case where the page was truncated from the * mapping by re-checking page_mapping() inside tree_lock. */ int __set_page_dirty_nobuffers(struct page *page) { if (!TestSetPageDirty(page)) { struct address_space *mapping = page_mapping(page); struct address_space *mapping2; if (!mapping) return 1; spin_lock_irq(&mapping->tree_lock); mapping2 = page_mapping(page); if (mapping2) { /* Race with truncate? */ BUG_ON(mapping2 != mapping); WARN_ON_ONCE(!PagePrivate(page) && !PageUptodate(page)); account_page_dirtied(page, mapping); radix_tree_tag_set(&mapping->page_tree, page_index(page), PAGECACHE_TAG_DIRTY); } spin_unlock_irq(&mapping->tree_lock); if (mapping->host) { /* !PageAnon && !swapper_space */ __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); } return 1; } return 0; } EXPORT_SYMBOL(__set_page_dirty_nobuffers); /* * 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) { wbc->pages_skipped++; return __set_page_dirty_nobuffers(page); } 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. */ 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); /* * 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); BUG_ON(!PageLocked(page)); if (mapping && mapping_cap_account_dirty(mapping)) { /* * 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 at some point after installing their * pte, but before marking the page dirty. * Pages are always locked coming in here, so we get * the desired exclusion. See mm/memory.c:do_wp_page() * for more comments. */ if (TestClearPageDirty(page)) { dec_zone_page_state(page, NR_FILE_DIRTY); dec_bdi_stat(mapping->backing_dev_info, BDI_RECLAIMABLE); return 1; } return 0; } 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); int ret; if (mapping) { struct backing_dev_info *bdi = mapping->backing_dev_info; 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)) { __dec_bdi_stat(bdi, BDI_WRITEBACK); __bdi_writeout_inc(bdi); } } spin_unlock_irqrestore(&mapping->tree_lock, flags); } else { ret = TestClearPageWriteback(page); } if (ret) dec_zone_page_state(page, NR_WRITEBACK); return ret; } int test_set_page_writeback(struct page *page) { struct address_space *mapping = page_mapping(page); int ret; if (mapping) { struct backing_dev_info *bdi = mapping->backing_dev_info; 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_bdi_stat(bdi, BDI_WRITEBACK); } if (!PageDirty(page)) radix_tree_tag_clear(&mapping->page_tree, page_index(page), PAGECACHE_TAG_DIRTY); 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) account_page_writeback(page); 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) { int ret; rcu_read_lock(); ret = radix_tree_tagged(&mapping->page_tree, tag); rcu_read_unlock(); return ret; } EXPORT_SYMBOL(mapping_tagged);