/*
- * mm/page-writeback.c.
+ * mm/page-writeback.c
*
* Copyright (C) 2002, Linus Torvalds.
*
#include <linux/writeback.h>
#include <linux/init.h>
#include <linux/backing-dev.h>
+#include <linux/task_io_accounting_ops.h>
#include <linux/blkdev.h>
#include <linux/mpage.h>
#include <linux/rmap.h>
#include <linux/sysctl.h>
#include <linux/cpu.h>
#include <linux/syscalls.h>
+#include <linux/buffer_head.h>
+#include <linux/pagevec.h>
/*
* The maximum number of pages to writeout in a single bdflush/kupdate
/*
* 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
* 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_online_node(node) {
+ 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)
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)
if (pages_written >= write_chunk)
break; /* We've done our duty */
}
- blk_congestion_wait(WRITE, HZ/10);
+ congestion_wait(WRITE, HZ/10);
}
if (nr_reclaimable + global_page_state(NR_WRITEBACK)
}
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;
+ if ((gfp_mask & (__GFP_FS|__GFP_IO)) != (__GFP_FS|__GFP_IO)) {
+ /*
+ * 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.
+ */
+ congestion_wait(WRITE, HZ/10);
+ return;
+ }
+
for ( ; ; ) {
get_dirty_limits(&background_thresh, &dirty_thresh, NULL);
if (global_page_state(NR_UNSTABLE_NFS) +
global_page_state(NR_WRITEBACK) <= dirty_thresh)
break;
- blk_congestion_wait(WRITE, HZ/10);
+ congestion_wait(WRITE, HZ/10);
}
}
-
/*
* 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.
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);
+ congestion_wait(WRITE, HZ/10);
if (!wbc.encountered_congestion)
break;
}
writeback_inodes(&wbc);
if (wbc.nr_to_write > 0) {
if (wbc.encountered_congestion)
- blk_congestion_wait(WRITE, HZ/10);
+ 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;
}
* will write six megabyte chunks, max.
*/
-static void set_ratelimit(void)
+void writeback_set_ratelimit(void)
{
ratelimit_pages = vm_total_pages / (num_online_cpus() * 32);
if (ratelimit_pages < 16)
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 = {
};
/*
- * 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;
+ mod_timer(&wb_timer, jiffies + dirty_writeback_interval);
+ writeback_set_ratelimit();
+ register_cpu_notifier(&ratelimit_nb);
+}
+
+/**
+ * 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 index;
+ pgoff_t end; /* Inclusive */
+ int scanned = 0;
+ int range_whole = 0;
+
+ if (wbc->nonblocking && bdi_write_congested(bdi)) {
+ wbc->encountered_congestion = 1;
+ return 0;
+ }
+
+ pagevec_init(&pvec, 0);
+ if (wbc->range_cyclic) {
+ index = mapping->writeback_index; /* Start from prev offset */
+ 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;
+ scanned = 1;
+ }
+retry:
+ while (!done && (index <= end) &&
+ (nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
+ PAGECACHE_TAG_DIRTY,
+ min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1))) {
+ unsigned i;
- correction = (100 * 4 * buffer_pages) / vm_total_pages;
+ scanned = 1;
+ for (i = 0; i < nr_pages; i++) {
+ struct page *page = pvec.pages[i];
- if (correction < 100) {
- dirty_background_ratio *= correction;
- dirty_background_ratio /= 100;
- vm_dirty_ratio *= correction;
- vm_dirty_ratio /= 100;
+ /*
+ * At this point we hold neither mapping->tree_lock nor
+ * lock on the page itself: the page may be truncated or
+ * invalidated (changing page->mapping to NULL), or even
+ * swizzled back from swapper_space to tmpfs file
+ * mapping
+ */
+ lock_page(page);
+
+ if (unlikely(page->mapping != mapping)) {
+ unlock_page(page);
+ continue;
+ }
+
+ if (!wbc->range_cyclic && page->index > end) {
+ done = 1;
+ unlock_page(page);
+ continue;
+ }
+
+ if (wbc->sync_mode != WB_SYNC_NONE)
+ wait_on_page_writeback(page);
+
+ if (PageWriteback(page) ||
+ !clear_page_dirty_for_io(page)) {
+ unlock_page(page);
+ continue;
+ }
+
+ ret = (*writepage)(page, wbc, data);
- if (dirty_background_ratio <= 0)
- dirty_background_ratio = 1;
- if (vm_dirty_ratio <= 0)
- vm_dirty_ratio = 1;
+ if (unlikely(ret == AOP_WRITEPAGE_ACTIVATE))
+ unlock_page(page);
+ if (ret || (--(wbc->nr_to_write) <= 0))
+ done = 1;
+ if (wbc->nonblocking && bdi_write_congested(bdi)) {
+ wbc->encountered_congestion = 1;
+ done = 1;
+ }
+ }
+ pagevec_release(&pvec);
+ cond_resched();
}
- mod_timer(&wb_timer, jiffies + dirty_writeback_interval);
- set_ratelimit();
- register_cpu_notifier(&ratelimit_nb);
+ if (!scanned && !done) {
+ /*
+ * We hit the last page and there is more work to be done: wrap
+ * back to the start of the file
+ */
+ scanned = 1;
+ index = 0;
+ goto retry;
+ }
+ if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
+ 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);
+
int do_writepages(struct address_space *mapping, struct writeback_control *wbc)
{
int 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
*
}
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.
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_zone_page_state(page,
- NR_FILE_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;
+
+ write_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));
+ if (mapping_cap_account_dirty(mapping)) {
+ __inc_zone_page_state(page, NR_FILE_DIRTY);
+ task_io_account_write(PAGE_CACHE_SIZE);
}
+ 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);
}
return 1;
}
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))
}
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);
- /*
- * We can continue to use `mapping' here because the
- * page is locked, which pins the address_space
- */
- if (mapping_cap_account_dirty(mapping)) {
- page_mkclean(page);
- dec_zone_page_state(page, NR_FILE_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.
{
struct address_space *mapping = page_mapping(page);
- if (mapping) {
+ 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.
+ *
+ * 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);
if (TestClearPageDirty(page)) {
- if (mapping_cap_account_dirty(mapping)) {
- page_mkclean(page);
- dec_zone_page_state(page, NR_FILE_DIRTY);
- }
+ dec_zone_page_state(page, NR_FILE_DIRTY);
return 1;
}
return 0;
}
EXPORT_SYMBOL(test_set_page_writeback);
-/*
- * Wakes up tasks that are being throttled due to writeback congestion
- */
-void writeback_congestion_end(void)
-{
- blk_congestion_end(WRITE);
-}
-EXPORT_SYMBOL(writeback_congestion_end);
-
/*
* Return true if any of the pages in the mapping are marged with the
* passed tag.