X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=mm%2Fpage-writeback.c;h=bb553c3e955da10631ca7f8229be2b1bdb791f25;hb=22ef37eed673587ac984965dc88ba94c68873291;hp=8ac6bfb400736c4ae92f33bcd6524b529f6f3459;hpb=74b85f3790aa2550c617fe14439482e13e615fa0;p=safe%2Fjmp%2Flinux-2.6 diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 8ac6bfb..bb553c3 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -1,12 +1,13 @@ /* - * mm/page-writeback.c. + * 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 akpm@zip.com.au + * 10Apr2002 Andrew Morton * Initial version */ @@ -21,18 +22,22 @@ #include #include #include +#include #include #include +#include #include #include #include #include #include #include +#include +#include /* * The maximum number of pages to writeout in a single bdflush/kupdate - * operation. We do this so we don't hold I_LOCK against an inode for + * operation. We do this so we don't hold I_SYNC against an inode for * enormous amounts of time, which would block a userspace task which has * been forced to throttle against that inode. Also, the code reevaluates * the dirty each time it has written this many pages. @@ -45,9 +50,6 @@ */ static long ratelimit_pages = 32; -static long total_pages; /* The total number of pages in the machine. */ -static int dirty_exceeded __cacheline_aligned_in_smp; /* Dirty mem may be over limit */ - /* * 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. @@ -67,19 +69,37 @@ static inline long sync_writeback_pages(void) 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 = 40; +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, in jiffies + * The interval between `kupdate'-style writebacks */ -int dirty_writeback_interval = 5 * HZ; +unsigned int dirty_writeback_interval = 5 * 100; /* centiseconds */ /* - * The longest number of jiffies for which data is allowed to remain dirty + * The longest time for which data is allowed to remain dirty */ -int dirty_expire_interval = 30 * HZ; +unsigned int dirty_expire_interval = 30 * 100; /* centiseconds */ /* * Flag that makes the machine dump writes/reads and block dirtyings. @@ -99,23 +119,253 @@ EXPORT_SYMBOL(laptop_mode); static void background_writeout(unsigned long _min_pages); -struct writeback_state +/* + * 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) { - unsigned long nr_dirty; - unsigned long nr_unstable; - unsigned long nr_mapped; - unsigned long nr_writeback; -}; + int shift = calc_period_shift(); + prop_change_shift(&vm_completions, shift); + prop_change_shift(&vm_dirties, shift); +} -static void get_writeback_state(struct writeback_state *wbs) +int dirty_background_ratio_handler(struct ctl_table *table, int write, + struct file *filp, void __user *buffer, size_t *lenp, + loff_t *ppos) { - wbs->nr_dirty = read_page_state(nr_dirty); - wbs->nr_unstable = read_page_state(nr_unstable); - wbs->nr_mapped = read_page_state(nr_mapped); - wbs->nr_writeback = read_page_state(nr_writeback); + int ret; + + ret = proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos); + if (ret == 0 && write) + dirty_background_bytes = 0; + return ret; +} + +int dirty_background_bytes_handler(struct ctl_table *table, int write, + struct file *filp, void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + int ret; + + ret = proc_doulongvec_minmax(table, write, filp, buffer, lenp, ppos); + if (ret == 0 && write) + dirty_background_ratio = 0; + return ret; +} + +int dirty_ratio_handler(struct ctl_table *table, int write, + struct file *filp, void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + int old_ratio = vm_dirty_ratio; + int ret; + + ret = proc_dointvec_minmax(table, write, filp, 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, + struct file *filp, void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + unsigned long old_bytes = vm_dirty_bytes; + int ret; + + ret = proc_doulongvec_minmax(table, write, filp, 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) +{ + __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) +{ + if (bdi_cap_writeback_dirty(bdi)) { + prop_fraction_percpu(&vm_completions, &bdi->completions, + numerator, denominator); + } else { + *numerator = 0; + *denominator = 1; + } +} + +/* + * Clip the earned share of dirty pages to that which is actually available. + * This avoids exceeding the total dirty_limit when the floating averages + * fluctuate too quickly. + */ +static void +clip_bdi_dirty_limit(struct backing_dev_info *bdi, long dirty, long *pbdi_dirty) +{ + long avail_dirty; + + avail_dirty = dirty - + (global_page_state(NR_FILE_DIRTY) + + global_page_state(NR_WRITEBACK) + + global_page_state(NR_UNSTABLE_NFS) + + global_page_state(NR_WRITEBACK_TEMP)); + + if (avail_dirty < 0) + avail_dirty = 0; + + avail_dirty += bdi_stat(bdi, BDI_RECLAIMABLE) + + bdi_stat(bdi, BDI_WRITEBACK); + + *pbdi_dirty = min(*pbdi_dirty, avail_dirty); +} + +static inline void task_dirties_fraction(struct task_struct *tsk, + long *numerator, long *denominator) +{ + prop_fraction_single(&vm_dirties, &tsk->dirties, + numerator, denominator); +} + +/* + * scale the dirty limit + * + * task specific dirty limit: + * + * dirty -= (dirty/8) * p_{t} + */ +static void task_dirty_limit(struct task_struct *tsk, long *pdirty) +{ + long numerator, denominator; + long dirty = *pdirty; + u64 inv = dirty >> 3; + + task_dirties_fraction(tsk, &numerator, &denominator); + inv *= numerator; + do_div(inv, denominator); + + dirty -= inv; + if (dirty < *pdirty/2) + dirty = *pdirty/2; + + *pdirty = dirty; +} + +/* + * + */ +static DEFINE_SPINLOCK(bdi_lock); +static unsigned int bdi_min_ratio; + +int bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ratio) +{ + int ret = 0; + unsigned long flags; + + spin_lock_irqsave(&bdi_lock, flags); + 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_irqrestore(&bdi_lock, flags); + + return ret; +} + +int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned max_ratio) +{ + unsigned long flags; + int ret = 0; + + if (max_ratio > 100) + return -EINVAL; + + spin_lock_irqsave(&bdi_lock, flags); + 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_irqrestore(&bdi_lock, flags); + + return ret; +} +EXPORT_SYMBOL(bdi_set_max_ratio); + +/* * Work out the current dirty-memory clamping and background writeout * thresholds. * @@ -132,45 +382,76 @@ static void get_writeback_state(struct writeback_state *wbs) * We make sure that the background writeout level is below the adjusted * clamping level. */ -static void -get_dirty_limits(struct writeback_state *wbs, long *pbackground, long *pdirty, - struct address_space *mapping) -{ - int background_ratio; /* Percentages */ - int dirty_ratio; - int unmapped_ratio; - long background; - long dirty; - unsigned long available_memory = total_pages; - struct task_struct *tsk; - - get_writeback_state(wbs); +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_lru_pages(z); + } /* - * If this mapping can only allocate from low memory, - * we exclude high memory from our count. + * 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. */ - if (mapping && !(mapping_gfp_mask(mapping) & __GFP_HIGHMEM)) - available_memory -= totalhigh_pages; + 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; - unmapped_ratio = 100 - (wbs->nr_mapped * 100) / total_pages; + x = global_page_state(NR_FREE_PAGES) + global_lru_pages(); - dirty_ratio = vm_dirty_ratio; - if (dirty_ratio > unmapped_ratio / 2) - dirty_ratio = unmapped_ratio / 2; + if (!vm_highmem_is_dirtyable) + x -= highmem_dirtyable_memory(x); - if (dirty_ratio < 5) - dirty_ratio = 5; + return x + 1; /* Ensure that we never return 0 */ +} + +void +get_dirty_limits(unsigned long *pbackground, unsigned long *pdirty, + unsigned long *pbdi_dirty, struct backing_dev_info *bdi) +{ + unsigned long background; + unsigned long dirty; + unsigned long available_memory = determine_dirtyable_memory(); + struct task_struct *tsk; - background_ratio = dirty_background_ratio; - if (background_ratio >= dirty_ratio) - background_ratio = dirty_ratio / 2; + if (vm_dirty_bytes) + dirty = DIV_ROUND_UP(vm_dirty_bytes, PAGE_SIZE); + else { + int dirty_ratio; - background = (background_ratio * available_memory) / 100; - dirty = (dirty_ratio * available_memory) / 100; + dirty_ratio = vm_dirty_ratio; + if (dirty_ratio < 5) + dirty_ratio = 5; + dirty = (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; @@ -178,6 +459,27 @@ get_dirty_limits(struct writeback_state *wbs, long *pbackground, long *pdirty, } *pbackground = background; *pdirty = dirty; + + if (bdi) { + 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; + + *pbdi_dirty = bdi_dirty; + clip_bdi_dirty_limit(bdi, dirty, pbdi_dirty); + task_dirty_limit(current, pbdi_dirty); + } } /* @@ -189,10 +491,11 @@ get_dirty_limits(struct writeback_state *wbs, long *pbackground, long *pdirty, */ static void balance_dirty_pages(struct address_space *mapping) { - struct writeback_state wbs; - long nr_reclaimable; - long background_thresh; - long dirty_thresh; + long nr_reclaimable, bdi_nr_reclaimable; + long nr_writeback, bdi_nr_writeback; + unsigned long background_thresh; + unsigned long dirty_thresh; + unsigned long bdi_thresh; unsigned long pages_written = 0; unsigned long write_chunk = sync_writeback_pages(); @@ -207,14 +510,30 @@ static void balance_dirty_pages(struct address_space *mapping) .range_cyclic = 1, }; - get_dirty_limits(&wbs, &background_thresh, - &dirty_thresh, mapping); - nr_reclaimable = wbs.nr_dirty + wbs.nr_unstable; - if (nr_reclaimable + wbs.nr_writeback <= dirty_thresh) + get_dirty_limits(&background_thresh, &dirty_thresh, + &bdi_thresh, bdi); + + nr_reclaimable = global_page_state(NR_FILE_DIRTY) + + global_page_state(NR_UNSTABLE_NFS); + nr_writeback = global_page_state(NR_WRITEBACK); + + bdi_nr_reclaimable = bdi_stat(bdi, BDI_RECLAIMABLE); + bdi_nr_writeback = bdi_stat(bdi, BDI_WRITEBACK); + + if (bdi_nr_reclaimable + bdi_nr_writeback <= bdi_thresh) + break; + + /* + * Throttle it only when the background writeback cannot + * catch-up. This avoids (excessively) small writeouts + * when the bdi limits are ramping up. + */ + if (nr_reclaimable + nr_writeback < + (background_thresh + dirty_thresh) / 2) break; - if (!dirty_exceeded) - dirty_exceeded = 1; + if (!bdi->dirty_exceeded) + bdi->dirty_exceeded = 1; /* Note: nr_reclaimable denotes nr_dirty + nr_unstable. * Unstable writes are a feature of certain networked @@ -222,22 +541,42 @@ static void balance_dirty_pages(struct address_space *mapping) * written to the server's write cache, but has not yet * been flushed to permanent storage. */ - if (nr_reclaimable) { + if (bdi_nr_reclaimable) { writeback_inodes(&wbc); - get_dirty_limits(&wbs, &background_thresh, - &dirty_thresh, mapping); - nr_reclaimable = wbs.nr_dirty + wbs.nr_unstable; - if (nr_reclaimable + wbs.nr_writeback <= dirty_thresh) - break; pages_written += write_chunk - wbc.nr_to_write; - if (pages_written >= write_chunk) - break; /* We've done our duty */ + get_dirty_limits(&background_thresh, &dirty_thresh, + &bdi_thresh, bdi); + } + + /* + * In order to avoid the stacked BDI deadlock we need + * to ensure we accurately count the 'dirty' pages when + * the threshold is low. + * + * Otherwise it would be possible to get thresh+n pages + * reported dirty, even though there are thresh-m pages + * actually dirty; with m+n sitting in the percpu + * deltas. + */ + if (bdi_thresh < 2*bdi_stat_error(bdi)) { + bdi_nr_reclaimable = bdi_stat_sum(bdi, BDI_RECLAIMABLE); + bdi_nr_writeback = bdi_stat_sum(bdi, BDI_WRITEBACK); + } else if (bdi_nr_reclaimable) { + bdi_nr_reclaimable = bdi_stat(bdi, BDI_RECLAIMABLE); + bdi_nr_writeback = bdi_stat(bdi, BDI_WRITEBACK); } - blk_congestion_wait(WRITE, HZ/10); + + if (bdi_nr_reclaimable + bdi_nr_writeback <= bdi_thresh) + break; + if (pages_written >= write_chunk) + break; /* We've done our duty */ + + congestion_wait(WRITE, HZ/10); } - if (nr_reclaimable + wbs.nr_writeback <= dirty_thresh && dirty_exceeded) - dirty_exceeded = 0; + if (bdi_nr_reclaimable + bdi_nr_writeback < bdi_thresh && + bdi->dirty_exceeded) + bdi->dirty_exceeded = 0; if (writeback_in_progress(bdi)) return; /* pdflush is already working this queue */ @@ -251,10 +590,22 @@ static void balance_dirty_pages(struct address_space *mapping) * background_thresh, to keep the amount of dirty memory low. */ if ((laptop_mode && pages_written) || - (!laptop_mode && (nr_reclaimable > background_thresh))) + (!laptop_mode && (global_page_state(NR_FILE_DIRTY) + + global_page_state(NR_UNSTABLE_NFS) + > background_thresh))) pdflush_operation(background_writeout, 0); } +void set_page_dirty_balance(struct page *page, int page_mkwrite) +{ + if (set_page_dirty(page) || page_mkwrite) { + struct address_space *mapping = page_mapping(page); + + if (mapping) + balance_dirty_pages_ratelimited(mapping); + } +} + /** * balance_dirty_pages_ratelimited_nr - balance dirty memory state * @mapping: address_space which was dirtied @@ -277,7 +628,7 @@ void balance_dirty_pages_ratelimited_nr(struct address_space *mapping, unsigned long *p; ratelimit = ratelimit_pages; - if (dirty_exceeded) + if (mapping->backing_dev_info->dirty_exceeded) ratelimit = 8; /* @@ -297,14 +648,13 @@ void balance_dirty_pages_ratelimited_nr(struct address_space *mapping, } EXPORT_SYMBOL(balance_dirty_pages_ratelimited_nr); -void throttle_vm_writeout(void) +void throttle_vm_writeout(gfp_t gfp_mask) { - struct writeback_state wbs; - long background_thresh; - long dirty_thresh; + unsigned long background_thresh; + unsigned long dirty_thresh; for ( ; ; ) { - get_dirty_limits(&wbs, &background_thresh, &dirty_thresh, NULL); + get_dirty_limits(&background_thresh, &dirty_thresh, NULL, NULL); /* * Boost the allowable dirty threshold a bit for page @@ -312,13 +662,21 @@ void throttle_vm_writeout(void) */ dirty_thresh += dirty_thresh / 10; /* wheeee... */ - if (wbs.nr_unstable + wbs.nr_writeback <= dirty_thresh) - break; - blk_congestion_wait(WRITE, HZ/10); + if (global_page_state(NR_UNSTABLE_NFS) + + global_page_state(NR_WRITEBACK) <= dirty_thresh) + break; + congestion_wait(WRITE, HZ/10); + + /* + * The caller might hold locks which can prevent IO completion + * or progress in the filesystem. So we cannot just sit here + * waiting for IO to complete. + */ + if ((gfp_mask & (__GFP_FS|__GFP_IO)) != (__GFP_FS|__GFP_IO)) + break; } } - /* * writeback at least _min_pages, and keep writing until the amount of dirty * memory is less than the background threshold, or until we're all clean. @@ -336,14 +694,15 @@ static void background_writeout(unsigned long _min_pages) }; for ( ; ; ) { - struct writeback_state wbs; - long background_thresh; - long dirty_thresh; + unsigned long background_thresh; + unsigned long dirty_thresh; - get_dirty_limits(&wbs, &background_thresh, &dirty_thresh, NULL); - if (wbs.nr_dirty + wbs.nr_unstable < background_thresh + get_dirty_limits(&background_thresh, &dirty_thresh, NULL, NULL); + if (global_page_state(NR_FILE_DIRTY) + + global_page_state(NR_UNSTABLE_NFS) < background_thresh && min_pages <= 0) break; + wbc.more_io = 0; wbc.encountered_congestion = 0; wbc.nr_to_write = MAX_WRITEBACK_PAGES; wbc.pages_skipped = 0; @@ -351,8 +710,9 @@ static void background_writeout(unsigned long _min_pages) min_pages -= MAX_WRITEBACK_PAGES - wbc.nr_to_write; if (wbc.nr_to_write > 0 || wbc.pages_skipped > 0) { /* Wrote less than expected */ - blk_congestion_wait(WRITE, HZ/10); - if (!wbc.encountered_congestion) + if (wbc.encountered_congestion || wbc.more_io) + congestion_wait(WRITE, HZ/10); + else break; } } @@ -365,12 +725,9 @@ static void background_writeout(unsigned long _min_pages) */ int wakeup_pdflush(long nr_pages) { - if (nr_pages == 0) { - struct writeback_state wbs; - - get_writeback_state(&wbs); - nr_pages = wbs.nr_dirty + wbs.nr_unstable; - } + if (nr_pages == 0) + nr_pages = global_page_state(NR_FILE_DIRTY) + + global_page_state(NR_UNSTABLE_NFS); return pdflush_operation(background_writeout, nr_pages); } @@ -401,7 +758,6 @@ static void wb_kupdate(unsigned long arg) unsigned long start_jif; unsigned long next_jif; long nr_to_write; - struct writeback_state wbs; struct writeback_control wbc = { .bdi = NULL, .sync_mode = WB_SYNC_NONE, @@ -414,19 +770,20 @@ static void wb_kupdate(unsigned long arg) sync_supers(); - get_writeback_state(&wbs); - oldest_jif = jiffies - dirty_expire_interval; + oldest_jif = jiffies - msecs_to_jiffies(dirty_expire_interval * 10); start_jif = jiffies; - next_jif = start_jif + dirty_writeback_interval; - nr_to_write = wbs.nr_dirty + wbs.nr_unstable + + next_jif = start_jif + msecs_to_jiffies(dirty_writeback_interval * 10); + nr_to_write = global_page_state(NR_FILE_DIRTY) + + global_page_state(NR_UNSTABLE_NFS) + (inodes_stat.nr_inodes - inodes_stat.nr_unused); while (nr_to_write > 0) { + wbc.more_io = 0; wbc.encountered_congestion = 0; wbc.nr_to_write = MAX_WRITEBACK_PAGES; writeback_inodes(&wbc); if (wbc.nr_to_write > 0) { - if (wbc.encountered_congestion) - blk_congestion_wait(WRITE, HZ/10); + if (wbc.encountered_congestion || wbc.more_io) + congestion_wait(WRITE, HZ/10); else break; /* All the old data is written */ } @@ -442,15 +799,14 @@ static void wb_kupdate(unsigned long arg) * sysctl handler for /proc/sys/vm/dirty_writeback_centisecs */ int dirty_writeback_centisecs_handler(ctl_table *table, int write, - struct file *file, void __user *buffer, size_t *length, loff_t *ppos) + struct file *file, void __user *buffer, size_t *length, loff_t *ppos) { - proc_dointvec_userhz_jiffies(table, write, file, buffer, length, ppos); - if (dirty_writeback_interval) { - mod_timer(&wb_timer, - jiffies + dirty_writeback_interval); - } else { + proc_dointvec(table, write, file, buffer, length, ppos); + if (dirty_writeback_interval) + mod_timer(&wb_timer, jiffies + + msecs_to_jiffies(dirty_writeback_interval * 10)); + else del_timer(&wb_timer); - } return 0; } @@ -507,20 +863,20 @@ void laptop_sync_completion(void) * will write six megabyte chunks, max. */ -static void set_ratelimit(void) +void writeback_set_ratelimit(void) { - ratelimit_pages = total_pages / (num_online_cpus() * 32); + 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 +static int __cpuinit ratelimit_handler(struct notifier_block *self, unsigned long u, void *v) { - set_ratelimit(); - return 0; + writeback_set_ratelimit(); + return NOTIFY_DONE; } static struct notifier_block __cpuinitdata ratelimit_nb = { @@ -529,35 +885,256 @@ static struct notifier_block __cpuinitdata ratelimit_nb = { }; /* - * If the machine has a large highmem:lowmem ratio then scale back the default - * dirty memory thresholds: allowing too much dirty highmem pins an excessive - * number of buffer_heads. + * 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) { - long buffer_pages = nr_free_buffer_pages(); - long correction; + int shift; - total_pages = nr_free_pagecache_pages(); + mod_timer(&wb_timer, + jiffies + msecs_to_jiffies(dirty_writeback_interval * 10)); + writeback_set_ratelimit(); + register_cpu_notifier(&ratelimit_nb); - correction = (100 * 4 * buffer_pages) / total_pages; + shift = calc_period_shift(); + prop_descriptor_init(&vm_completions, shift); + prop_descriptor_init(&vm_dirties, shift); +} - if (correction < 100) { - dirty_background_ratio *= correction; - dirty_background_ratio /= 100; - vm_dirty_ratio *= correction; - vm_dirty_ratio /= 100; +/** + * 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. + */ +int write_cache_pages(struct address_space *mapping, + struct writeback_control *wbc, writepage_t writepage, + void *data) +{ + struct backing_dev_info *bdi = mapping->backing_dev_info; + 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; + long nr_to_write = wbc->nr_to_write; + + if (wbc->nonblocking && bdi_write_congested(bdi)) { + wbc->encountered_congestion = 1; + return 0; + } - if (dirty_background_ratio <= 0) - dirty_background_ratio = 1; - if (vm_dirty_ratio <= 0) - vm_dirty_ratio = 1; + 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 */ } - mod_timer(&wb_timer, jiffies + dirty_writeback_interval); - set_ratelimit(); - register_cpu_notifier(&ratelimit_nb); +retry: + done_index = index; + while (!done && (index <= end)) { + int i; + + nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, + PAGECACHE_TAG_DIRTY, + 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 + 1; + + 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; + + 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 = 1; + break; + } + } + + if (nr_to_write > 0) { + nr_to_write--; + if (nr_to_write == 0 && + wbc->sync_mode == WB_SYNC_NONE) { + /* + * We stop writing back only if we are + * not doing integrity sync. In case of + * integrity sync we have to keep going + * because someone may be concurrently + * dirtying pages, and we might have + * synced a lot of newly appeared dirty + * pages, but have not synced all of the + * old dirty pages. + */ + done = 1; + break; + } + } + + if (wbc->nonblocking && bdi_write_congested(bdi)) { + wbc->encountered_congestion = 1; + 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->no_nrwrite_index_update) { + if (wbc->range_cyclic || (range_whole && nr_to_write > 0)) + mapping->writeback_index = done_index; + wbc->nr_to_write = nr_to_write; + } + + 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) +{ + /* deal with chardevs and other special file */ + if (!mapping->a_ops->writepage) + return 0; + + return write_cache_pages(mapping, wbc, __writepage, mapping); +} + +EXPORT_SYMBOL(generic_writepages); + int do_writepages(struct address_space *mapping, struct writeback_control *wbc) { int ret; @@ -566,7 +1143,7 @@ int do_writepages(struct address_space *mapping, struct writeback_control *wbc) return 0; wbc->for_writepages = 1; if (mapping->a_ops->writepages) - ret = mapping->a_ops->writepages(mapping, wbc); + ret = mapping->a_ops->writepages(mapping, wbc); else ret = generic_writepages(mapping, wbc); wbc->for_writepages = 0; @@ -575,7 +1152,6 @@ int do_writepages(struct address_space *mapping, struct writeback_control *wbc) /** * 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 * @@ -614,6 +1190,30 @@ int write_one_page(struct page *page, int wait) 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)) + SetPageDirty(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_bdi_stat(mapping->backing_dev_info, BDI_RECLAIMABLE); + task_dirty_inc(current); + task_io_account_write(PAGE_CACHE_SIZE); + } +} + +/* * For address_spaces which do not use buffers. Just tag the page as dirty in * its radix tree. * @@ -626,7 +1226,7 @@ EXPORT_SYMBOL(write_one_page); * 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() insode tree_lock. + * mapping by re-checking page_mapping() inside tree_lock. */ int __set_page_dirty_nobuffers(struct page *page) { @@ -634,22 +1234,22 @@ int __set_page_dirty_nobuffers(struct page *page) struct address_space *mapping = page_mapping(page); struct address_space *mapping2; - if (mapping) { - write_lock_irq(&mapping->tree_lock); - mapping2 = page_mapping(page); - if (mapping2) { /* Race with truncate? */ - BUG_ON(mapping2 != mapping); - if (mapping_cap_account_dirty(mapping)) - inc_page_state(nr_dirty); - radix_tree_tag_set(&mapping->page_tree, - page_index(page), PAGECACHE_TAG_DIRTY); - } - write_unlock_irq(&mapping->tree_lock); - if (mapping->host) { - /* !PageAnon && !swapper_space */ - __mark_inode_dirty(mapping->host, - I_DIRTY_PAGES); - } + 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; } @@ -673,15 +1273,17 @@ EXPORT_SYMBOL(redirty_page_for_writepage); * If the mapping doesn't provide a set_page_dirty a_op, then * just fall through and assume that it wants buffer_heads. */ -int fastcall set_page_dirty(struct page *page) +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; - if (spd) - return (*spd)(page); - return __set_page_dirty_buffers(page); +#ifdef CONFIG_BLOCK + if (!spd) + spd = __set_page_dirty_buffers; +#endif + return (*spd)(page); } if (!PageDirty(page)) { if (!TestSetPageDirty(page)) @@ -705,7 +1307,7 @@ int set_page_dirty_lock(struct page *page) { int ret; - lock_page(page); + lock_page_nosync(page); ret = set_page_dirty(page); unlock_page(page); return ret; @@ -713,33 +1315,6 @@ int set_page_dirty_lock(struct page *page) 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. - */ -int test_clear_page_dirty(struct page *page) -{ - struct address_space *mapping = page_mapping(page); - unsigned long flags; - - if (mapping) { - write_lock_irqsave(&mapping->tree_lock, flags); - if (TestClearPageDirty(page)) { - radix_tree_tag_clear(&mapping->page_tree, - page_index(page), - PAGECACHE_TAG_DIRTY); - write_unlock_irqrestore(&mapping->tree_lock, flags); - if (mapping_cap_account_dirty(mapping)) - dec_page_state(nr_dirty); - return 1; - } - write_unlock_irqrestore(&mapping->tree_lock, flags); - return 0; - } - return TestClearPageDirty(page); -} -EXPORT_SYMBOL(test_clear_page_dirty); - -/* * Clear a page's dirty flag, while caring for dirty memory accounting. * Returns true if the page was previously dirty. * @@ -757,10 +1332,51 @@ int clear_page_dirty_for_io(struct page *page) { struct address_space *mapping = page_mapping(page); - if (mapping) { + BUG_ON(!PageLocked(page)); + + ClearPageReclaim(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)) { - if (mapping_cap_account_dirty(mapping)) - dec_page_state(nr_dirty); + dec_zone_page_state(page, NR_FILE_DIRTY); + dec_bdi_stat(mapping->backing_dev_info, + BDI_RECLAIMABLE); return 1; } return 0; @@ -775,18 +1391,26 @@ int test_clear_page_writeback(struct page *page) int ret; if (mapping) { + struct backing_dev_info *bdi = mapping->backing_dev_info; unsigned long flags; - write_lock_irqsave(&mapping->tree_lock, flags); + spin_lock_irqsave(&mapping->tree_lock, flags); ret = TestClearPageWriteback(page); - if (ret) + if (ret) { radix_tree_tag_clear(&mapping->page_tree, page_index(page), PAGECACHE_TAG_WRITEBACK); - write_unlock_irqrestore(&mapping->tree_lock, flags); + 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; } @@ -796,39 +1420,43 @@ int test_set_page_writeback(struct page *page) int ret; if (mapping) { + struct backing_dev_info *bdi = mapping->backing_dev_info; unsigned long flags; - write_lock_irqsave(&mapping->tree_lock, flags); + spin_lock_irqsave(&mapping->tree_lock, flags); ret = TestSetPageWriteback(page); - if (!ret) + 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); - write_unlock_irqrestore(&mapping->tree_lock, flags); + spin_unlock_irqrestore(&mapping->tree_lock, flags); } else { ret = TestSetPageWriteback(page); } + if (!ret) + inc_zone_page_state(page, NR_WRITEBACK); return ret; } EXPORT_SYMBOL(test_set_page_writeback); /* - * Return true if any of the pages in the mapping are marged with the + * 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) { - unsigned long flags; int ret; - - read_lock_irqsave(&mapping->tree_lock, flags); + rcu_read_lock(); ret = radix_tree_tagged(&mapping->page_tree, tag); - read_unlock_irqrestore(&mapping->tree_lock, flags); + rcu_read_unlock(); return ret; } EXPORT_SYMBOL(mapping_tagged);