* mm/page-writeback.c
*
* Copyright (C) 2002, Linus Torvalds.
+ * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
*
* Contains functions related to writing back dirty pages at the
* address_space level.
/*
* 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.
*/
static long ratelimit_pages = 32;
-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.
/*
* Start background writeback (via pdflush) at this percentage
*/
-int dirty_background_ratio = 10;
+int dirty_background_ratio = 5;
/*
* The generator of dirty data starts writeback at this percentage
*/
-int vm_dirty_ratio = 40;
+int vm_dirty_ratio = 10;
/*
* The interval between `kupdate'-style writebacks, in jiffies
static void background_writeout(unsigned long _min_pages);
/*
+ * 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;
+
+static unsigned long determine_dirtyable_memory(void);
+
+/*
+ * 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;
+
+ dirty_total = (vm_dirty_ratio * determine_dirtyable_memory()) / 100;
+ return 2 + ilog2(dirty_total - 1);
+}
+
+/*
+ * update the period when the dirty ratio changes.
+ */
+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 = proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos);
+ if (ret == 0 && write && vm_dirty_ratio != old_ratio) {
+ int shift = calc_period_shift();
+ prop_change_shift(&vm_completions, shift);
+ prop_change_shift(&vm_dirties, shift);
+ }
+ 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(&vm_completions, &bdi->completions);
+}
+
+static inline 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));
+
+ 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}
+ */
+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;
+}
+
+/*
* Work out the current dirty-memory clamping and background writeout
* thresholds.
*
* 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_page_state(z, NR_INACTIVE)
+ + zone_page_state(z, NR_ACTIVE);
+ }
+ /*
+ * 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
+}
+
+static unsigned long determine_dirtyable_memory(void)
+{
+ unsigned long x;
+
+ x = global_page_state(NR_FREE_PAGES)
+ + global_page_state(NR_INACTIVE)
+ + global_page_state(NR_ACTIVE);
+ x -= highmem_dirtyable_memory(x);
+ return x + 1; /* Ensure that we never return 0 */
+}
+
static void
-get_dirty_limits(long *pbackground, long *pdirty,
- struct address_space *mapping)
+get_dirty_limits(long *pbackground, long *pdirty, long *pbdi_dirty,
+ struct backing_dev_info *bdi)
{
int background_ratio; /* Percentages */
int dirty_ratio;
int unmapped_ratio;
long background;
long dirty;
- unsigned long available_memory = vm_total_pages;
+ unsigned long available_memory = determine_dirtyable_memory();
struct task_struct *tsk;
-#ifdef CONFIG_HIGHMEM
- /*
- * If this mapping can only allocate from low memory,
- * we exclude high memory from our count.
- */
- if (mapping && !(mapping_gfp_mask(mapping) & __GFP_HIGHMEM))
- available_memory -= totalhigh_pages;
-#endif
-
-
unmapped_ratio = 100 - ((global_page_state(NR_FILE_MAPPED) +
global_page_state(NR_ANON_PAGES)) * 100) /
- vm_total_pages;
+ available_memory;
dirty_ratio = vm_dirty_ratio;
if (dirty_ratio > unmapped_ratio / 2)
}
*pbackground = background;
*pdirty = dirty;
+
+ if (bdi) {
+ u64 bdi_dirty = dirty;
+ long numerator, denominator;
+
+ /*
+ * Calculate this BDI's share of the dirty ratio.
+ */
+ bdi_writeout_fraction(bdi, &numerator, &denominator);
+
+ bdi_dirty *= numerator;
+ do_div(bdi_dirty, denominator);
+
+ *pbdi_dirty = bdi_dirty;
+ clip_bdi_dirty_limit(bdi, dirty, pbdi_dirty);
+ task_dirty_limit(current, pbdi_dirty);
+ }
}
/*
*/
static void balance_dirty_pages(struct address_space *mapping)
{
- long nr_reclaimable;
+ long bdi_nr_reclaimable;
+ long bdi_nr_writeback;
long background_thresh;
long dirty_thresh;
+ long bdi_thresh;
unsigned long pages_written = 0;
unsigned long write_chunk = sync_writeback_pages();
.range_cyclic = 1,
};
- get_dirty_limits(&background_thresh, &dirty_thresh, mapping);
- nr_reclaimable = global_page_state(NR_FILE_DIRTY) +
- global_page_state(NR_UNSTABLE_NFS);
- if (nr_reclaimable + global_page_state(NR_WRITEBACK) <=
- dirty_thresh)
- break;
+ get_dirty_limits(&background_thresh, &dirty_thresh,
+ &bdi_thresh, bdi);
+ bdi_nr_reclaimable = bdi_stat(bdi, BDI_RECLAIMABLE);
+ bdi_nr_writeback = bdi_stat(bdi, BDI_WRITEBACK);
+ if (bdi_nr_reclaimable + bdi_nr_writeback <= bdi_thresh)
+ break;
- if (!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
* 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(&background_thresh,
- &dirty_thresh, mapping);
- nr_reclaimable = global_page_state(NR_FILE_DIRTY) +
- global_page_state(NR_UNSTABLE_NFS);
- if (nr_reclaimable +
- global_page_state(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);
+ }
+
+ 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 + global_page_state(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 */
* 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)
+void set_page_dirty_balance(struct page *page, int page_mkwrite)
{
- if (set_page_dirty(page)) {
+ if (set_page_dirty(page) || page_mkwrite) {
struct address_space *mapping = page_mapping(page);
if (mapping)
unsigned long *p;
ratelimit = ratelimit_pages;
- if (dirty_exceeded)
+ if (mapping->backing_dev_info->dirty_exceeded)
ratelimit = 8;
/*
}
EXPORT_SYMBOL(balance_dirty_pages_ratelimited_nr);
-void throttle_vm_writeout(void)
+void throttle_vm_writeout(gfp_t gfp_mask)
{
long background_thresh;
long dirty_thresh;
for ( ; ; ) {
- get_dirty_limits(&background_thresh, &dirty_thresh, NULL);
+ get_dirty_limits(&background_thresh, &dirty_thresh, NULL, NULL);
/*
* Boost the allowable dirty threshold a bit for page
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.
long background_thresh;
long dirty_thresh;
- get_dirty_limits(&background_thresh, &dirty_thresh, NULL);
+ 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;
min_pages -= MAX_WRITEBACK_PAGES - wbc.nr_to_write;
if (wbc.nr_to_write > 0 || wbc.pages_skipped > 0) {
/* Wrote less than expected */
- congestion_wait(WRITE, HZ/10);
- if (!wbc.encountered_congestion)
+ if (wbc.encountered_congestion || wbc.more_io)
+ congestion_wait(WRITE, HZ/10);
+ else
break;
}
}
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)
+ if (wbc.encountered_congestion || wbc.more_io)
congestion_wait(WRITE, HZ/10);
else
break; /* All the old data is written */
* 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 {
+ if (dirty_writeback_interval)
+ mod_timer(&wb_timer, jiffies + dirty_writeback_interval);
+ else
del_timer(&wb_timer);
- }
return 0;
}
ratelimit_handler(struct notifier_block *self, unsigned long u, void *v)
{
writeback_set_ratelimit();
- return 0;
+ return NOTIFY_DONE;
}
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;
-
- correction = (100 * 4 * buffer_pages) / vm_total_pages;
+ int shift;
- if (correction < 100) {
- dirty_background_ratio *= correction;
- dirty_background_ratio /= 100;
- vm_dirty_ratio *= correction;
- vm_dirty_ratio /= 100;
-
- if (dirty_background_ratio <= 0)
- dirty_background_ratio = 1;
- if (vm_dirty_ratio <= 0)
- vm_dirty_ratio = 1;
- }
mod_timer(&wb_timer, jiffies + dirty_writeback_interval);
writeback_set_ratelimit();
register_cpu_notifier(&ratelimit_nb);
+
+ shift = calc_period_shift();
+ prop_descriptor_init(&vm_completions, shift);
+ prop_descriptor_init(&vm_dirties, shift);
}
/**
- * generic_writepages - walk the list of dirty pages of the given
- * address space and writepage() all of them.
- *
+ * 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
*
- * This is a library function, which implements the writepages()
- * address_space_operation.
- *
- * If a page is already under I/O, generic_writepages() skips it, even
+ * 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.
- *
- * Derived from mpage_writepages() - if you fix this you should check that
- * also!
*/
-int generic_writepages(struct address_space *mapping,
- struct writeback_control *wbc)
+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;
- int (*writepage)(struct page *page, struct writeback_control *wbc);
struct pagevec pvec;
int nr_pages;
pgoff_t index;
return 0;
}
- writepage = mapping->a_ops->writepage;
-
- /* deal with chardevs and other special file */
- if (!writepage)
- return 0;
-
pagevec_init(&pvec, 0);
if (wbc->range_cyclic) {
index = mapping->writeback_index; /* Start from prev offset */
continue;
}
- ret = (*writepage)(page, wbc);
- if (ret) {
- if (ret == -ENOSPC)
- set_bit(AS_ENOSPC, &mapping->flags);
- else
- set_bit(AS_EIO, &mapping->flags);
- }
+ ret = (*writepage)(page, wbc, data);
- if (unlikely(ret == AOP_WRITEPAGE_ACTIVATE))
+ if (unlikely(ret == AOP_WRITEPAGE_ACTIVATE)) {
unlock_page(page);
+ ret = 0;
+ }
if (ret || (--(wbc->nr_to_write) <= 0))
done = 1;
if (wbc->nonblocking && bdi_write_congested(bdi)) {
mapping->writeback_index = 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)
+{
+ /* 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);
/**
* 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
*
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;
+}
+
+/*
* For address_spaces which do not use buffers. Just tag the page as dirty in
* its radix tree.
*
mapping2 = page_mapping(page);
if (mapping2) { /* Race with truncate? */
BUG_ON(mapping2 != mapping);
+ WARN_ON_ONCE(!PagePrivate(page) && !PageUptodate(page));
if (mapping_cap_account_dirty(mapping)) {
__inc_zone_page_state(page, NR_FILE_DIRTY);
+ __inc_bdi_stat(mapping->backing_dev_info,
+ BDI_RECLAIMABLE);
task_io_account_write(PAGE_CACHE_SIZE);
}
radix_tree_tag_set(&mapping->page_tree,
* 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)
+static int __set_page_dirty(struct page *page)
{
struct address_space *mapping = page_mapping(page);
}
return 0;
}
+
+int fastcall set_page_dirty(struct page *page)
+{
+ int ret = __set_page_dirty(page);
+ if (ret)
+ task_dirty_inc(current);
+ return ret;
+}
EXPORT_SYMBOL(set_page_dirty);
/*
{
struct address_space *mapping = page_mapping(page);
+ BUG_ON(!PageLocked(page));
+
+ ClearPageReclaim(page);
if (mapping && mapping_cap_account_dirty(mapping)) {
/*
* Yes, Virginia, this is indeed insane.
* We basically use the page "master dirty bit"
* as a serialization point for all the different
* threads doing their things.
- *
- * FIXME! We still have a race here: if somebody
- * adds the page back to the page tables in
- * between the "page_mkclean()" and the "TestClearPageDirty()",
- * we might have it mapped without the dirty bit set.
*/
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;
int ret;
if (mapping) {
+ struct backing_dev_info *bdi = mapping->backing_dev_info;
unsigned long flags;
write_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);
+ if (bdi_cap_writeback_dirty(bdi)) {
+ __dec_bdi_stat(bdi, BDI_WRITEBACK);
+ __bdi_writeout_inc(bdi);
+ }
+ }
write_unlock_irqrestore(&mapping->tree_lock, flags);
} else {
ret = TestClearPageWriteback(page);
}
+ if (ret)
+ dec_zone_page_state(page, NR_WRITEBACK);
return ret;
}
int ret;
if (mapping) {
+ struct backing_dev_info *bdi = mapping->backing_dev_info;
unsigned long flags;
write_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_writeback_dirty(bdi))
+ __inc_bdi_stat(bdi, BDI_WRITEBACK);
+ }
if (!PageDirty(page))
radix_tree_tag_clear(&mapping->page_tree,
page_index(page),
} 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);
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff