On Fri, 18 Dec 2015 22:22:17 -0700 Ross Zwisler <ross.zwis...@linux.intel.com>
wrote:
> To properly handle fsync/msync in an efficient way DAX needs to track dirty
> pages so it is able to flush them durably to media on demand.
>
> The tracking of dirty pages is done via the radix tree in struct
> address_space. This radix tree is already used by the page writeback
> infrastructure for tracking dirty pages associated with an open file, and
> it already has support for exceptional (non struct page*) entries. We
> build upon these features to add exceptional entries to the radix tree for
> DAX dirty PMD or PTE pages at fault time.
I'm getting a few rejects here against other pending changes. Things
look OK to me but please do runtime test the end result as it resides
in linux-next. Which will be next year.
>
> ...
>
> +static void dax_writeback_one(struct address_space *mapping, pgoff_t index,
> + void *entry)
> +{
> + struct radix_tree_root *page_tree = &mapping->page_tree;
> + int type = RADIX_DAX_TYPE(entry);
> + struct radix_tree_node *node;
> + void **slot;
> +
> + if (type != RADIX_DAX_PTE && type != RADIX_DAX_PMD) {
> + WARN_ON_ONCE(1);
> + return;
> + }
--- a/fs/dax.c~dax-add-support-for-fsync-sync-fix
+++ a/fs/dax.c
@@ -383,10 +383,8 @@ static void dax_writeback_one(struct add
struct radix_tree_node *node;
void **slot;
- if (type != RADIX_DAX_PTE && type != RADIX_DAX_PMD) {
- WARN_ON_ONCE(1);
+ if (WARN_ON_ONCE(type != RADIX_DAX_PTE && type != RADIX_DAX_PMD))
return;
- }
spin_lock_irq(&mapping->tree_lock);
/*
> + spin_lock_irq(&mapping->tree_lock);
> + /*
> + * Regular page slots are stabilized by the page lock even
> + * without the tree itself locked. These unlocked entries
> + * need verification under the tree lock.
> + */
> + if (!__radix_tree_lookup(page_tree, index, &node, &slot))
> + goto unlock;
> + if (*slot != entry)
> + goto unlock;
> +
> + /* another fsync thread may have already written back this entry */
> + if (!radix_tree_tag_get(page_tree, index, PAGECACHE_TAG_TOWRITE))
> + goto unlock;
> +
> + radix_tree_tag_clear(page_tree, index, PAGECACHE_TAG_TOWRITE);
> +
> + if (type == RADIX_DAX_PMD)
> + wb_cache_pmem(RADIX_DAX_ADDR(entry), PMD_SIZE);
> + else
> + wb_cache_pmem(RADIX_DAX_ADDR(entry), PAGE_SIZE);
> + unlock:
> + spin_unlock_irq(&mapping->tree_lock);
> +}
> +
> +/*
> + * Flush the mapping to the persistent domain within the byte range of
> [start,
> + * end]. This is required by data integrity operations to ensure file data is
> + * on persistent storage prior to completion of the operation.
> + */
> +void dax_writeback_mapping_range(struct address_space *mapping, loff_t start,
> + loff_t end)
> +{
> + struct inode *inode = mapping->host;
> + pgoff_t indices[PAGEVEC_SIZE];
> + pgoff_t start_page, end_page;
> + struct pagevec pvec;
> + void *entry;
> + int i;
> +
> + if (inode->i_blkbits != PAGE_SHIFT) {
> + WARN_ON_ONCE(1);
> + return;
> + }
again
> + rcu_read_lock();
> + entry = radix_tree_lookup(&mapping->page_tree, start & PMD_MASK);
> + rcu_read_unlock();
What stabilizes the memory at *entry after rcu_read_unlock()?
> + /* see if the start of our range is covered by a PMD entry */
> + if (entry && RADIX_DAX_TYPE(entry) == RADIX_DAX_PMD)
> + start &= PMD_MASK;
> +
> + start_page = start >> PAGE_CACHE_SHIFT;
> + end_page = end >> PAGE_CACHE_SHIFT;
> +
> + tag_pages_for_writeback(mapping, start_page, end_page);
> +
> + pagevec_init(&pvec, 0);
> + while (1) {
> + pvec.nr = find_get_entries_tag(mapping, start_page,
> + PAGECACHE_TAG_TOWRITE, PAGEVEC_SIZE,
> + pvec.pages, indices);
> +
> + if (pvec.nr == 0)
> + break;
> +
> + for (i = 0; i < pvec.nr; i++)
> + dax_writeback_one(mapping, indices[i], pvec.pages[i]);
> + }
> + wmb_pmem();
> +}
> +EXPORT_SYMBOL_GPL(dax_writeback_mapping_range);
> +
>
> ...
>
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
