#ifdef CONFIG_HIGHMEM
/*
- * If this mapping can only allocate from low memory,
- * we exclude high memory from our count.
+ * We always exclude high memory from our count.
*/
- if (mapping && !(mapping_gfp_mask(mapping) & __GFP_HIGHMEM))
- available_memory -= totalhigh_pages;
+ available_memory -= totalhigh_pages;
#endif
};
/*
- * 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;
-
- 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);
}
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.
}
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)
- return TestClearPageDirty(page);
-
- 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;
-}
-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)
- return TestClearPageDirty(page);
-
- if (TestClearPageDirty(page)) {
- if (mapping_cap_account_dirty(mapping)) {
- page_mkclean(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.
+ *
+ * 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)) {
dec_zone_page_state(page, NR_FILE_DIRTY);
+ return 1;
}
- return 1;
+ return 0;
}
- return 0;
+ return TestClearPageDirty(page);
}
EXPORT_SYMBOL(clear_page_dirty_for_io);